diff options
Diffstat (limited to 'gnu/usr.bin/perl/lib')
108 files changed, 15456 insertions, 4678 deletions
diff --git a/gnu/usr.bin/perl/lib/AnyDBM_File.pm b/gnu/usr.bin/perl/lib/AnyDBM_File.pm index 3b41a4a100b..4153af2de2d 100644 --- a/gnu/usr.bin/perl/lib/AnyDBM_File.pm +++ b/gnu/usr.bin/perl/lib/AnyDBM_File.pm @@ -22,6 +22,8 @@ __END__ AnyDBM_File - provide framework for multiple DBMs +NDBM_File, DB_File, GDBM_File, SDBM_File, ODBM_File - various DBM implementations + =head1 SYNOPSIS use AnyDBM_File; diff --git a/gnu/usr.bin/perl/lib/B/Deparse-core.t b/gnu/usr.bin/perl/lib/B/Deparse-core.t index b42ad0a9022..6ee935f5f71 100644 --- a/gnu/usr.bin/perl/lib/B/Deparse-core.t +++ b/gnu/usr.bin/perl/lib/B/Deparse-core.t @@ -80,21 +80,23 @@ sub testit { $desc .= " (lex sub)" if $lexsub; + my $code; my $code_ref; if ($lexsub) { package lexsubtest; no warnings 'experimental::lexical_subs'; use feature 'lexical_subs'; no strict 'vars'; - $code_ref = - eval "sub { state sub $keyword; ${vars}() = $expr }" - || die "$@ in $expr"; + $code = "sub { state sub $keyword; ${vars}() = $expr }"; + $code_ref = eval $code + or die "$@ in $expr"; } else { package test; use subs (); import subs $keyword; - $code_ref = eval "no strict 'vars'; sub { ${vars}() = $expr }" + $code = "no strict 'vars'; sub { ${vars}() = $expr }"; + $code_ref = eval $code or die "$@ in $expr"; } @@ -102,10 +104,12 @@ sub testit { unless ($got_text =~ / package (?:lexsub)?test; - use strict 'refs', 'subs'; +(?: BEGIN \{\$\{\^WARNING_BITS\} = "[^"]+"\} +)? use strict 'refs', 'subs'; use feature [^\n]+ - \Q$vars\E\(\) = (.*) -}/s) { +(?: (?:CORE::)?state sub \w+; +)? \Q$vars\E\(\) = (.*) +\}/s) { ::fail($desc); ::diag("couldn't extract line from boilerplate\n"); ::diag($got_text); @@ -113,7 +117,8 @@ sub testit { } my $got_expr = $1; - is $got_expr, $expected_expr, $desc; + is $got_expr, $expected_expr, $desc + or ::diag("ORIGINAL CODE:\n$code");; } } @@ -637,7 +642,7 @@ sprintf 123 p sqrt 01 $ srand 01 - stat 01 $ -state 123 p+ # skip with 0 args, as state() => () +state 123 p1+ # skip with 0 args, as state() => () study 01 $+ # sub handled specially substr 234 p diff --git a/gnu/usr.bin/perl/lib/B/Deparse.pm b/gnu/usr.bin/perl/lib/B/Deparse.pm index 9879d678b17..23045a8dd37 100644 --- a/gnu/usr.bin/perl/lib/B/Deparse.pm +++ b/gnu/usr.bin/perl/lib/B/Deparse.pm @@ -12,10 +12,16 @@ use Carp; use B qw(class main_root main_start main_cv svref_2object opnumber perlstring OPf_WANT OPf_WANT_VOID OPf_WANT_SCALAR OPf_WANT_LIST OPf_KIDS OPf_REF OPf_STACKED OPf_SPECIAL OPf_MOD OPf_PARENS - OPpLVAL_INTRO OPpOUR_INTRO OPpENTERSUB_AMPER OPpSLICE OPpCONST_BARE + OPpLVAL_INTRO OPpOUR_INTRO OPpENTERSUB_AMPER OPpSLICE OPpKVSLICE + OPpCONST_BARE OPpTRANS_SQUASH OPpTRANS_DELETE OPpTRANS_COMPLEMENT OPpTARGET_MY OPpEXISTS_SUB OPpSORT_NUMERIC OPpSORT_INTEGER OPpREPEAT_DOLIST OPpSORT_REVERSE OPpMULTIDEREF_EXISTS OPpMULTIDEREF_DELETE + OPpSPLIT_ASSIGN OPpSPLIT_LEX + OPpPADHV_ISKEYS OPpRV2HV_ISKEYS + OPpCONCAT_NESTED + OPpMULTICONCAT_APPEND OPpMULTICONCAT_STRINGIFY OPpMULTICONCAT_FAKE + OPpTRUEBOOL OPpINDEX_BOOLNEG SVf_IOK SVf_NOK SVf_ROK SVf_POK SVpad_OUR SVf_FAKE SVs_RMG SVs_SMG SVs_PADTMP SVpad_TYPED CVf_METHOD CVf_LVALUE @@ -46,12 +52,14 @@ use B qw(class main_root main_start main_cv svref_2object opnumber perlstring MDEREF_SHIFT ); -$VERSION = '1.37'; +$VERSION = '1.48'; use strict; -use vars qw/$AUTOLOAD/; +our $AUTOLOAD; use warnings (); require feature; +use Config; + BEGIN { # List version-specific constants here. # Easiest way to keep this code portable between version looks to @@ -69,104 +77,6 @@ BEGIN { } } -# Changes between 0.50 and 0.51: -# - fixed nulled leave with live enter in sort { } -# - fixed reference constants (\"str") -# - handle empty programs gracefully -# - handle infinite loops (for (;;) {}, while (1) {}) -# - differentiate between 'for my $x ...' and 'my $x; for $x ...' -# - various minor cleanups -# - moved globals into an object -# - added '-u', like B::C -# - package declarations using cop_stash -# - subs, formats and code sorted by cop_seq -# Changes between 0.51 and 0.52: -# - added pp_threadsv (special variables under USE_5005THREADS) -# - added documentation -# Changes between 0.52 and 0.53: -# - many changes adding precedence contexts and associativity -# - added '-p' and '-s' output style options -# - various other minor fixes -# Changes between 0.53 and 0.54: -# - added support for new 'for (1..100)' optimization, -# thanks to Gisle Aas -# Changes between 0.54 and 0.55: -# - added support for new qr// construct -# - added support for new pp_regcreset OP -# Changes between 0.55 and 0.56: -# - tested on base/*.t, cmd/*.t, comp/*.t, io/*.t -# - fixed $# on non-lexicals broken in last big rewrite -# - added temporary fix for change in opcode of OP_STRINGIFY -# - fixed problem in 0.54's for() patch in 'for (@ary)' -# - fixed precedence in conditional of ?: -# - tweaked list paren elimination in 'my($x) = @_' -# - made continue-block detection trickier wrt. null ops -# - fixed various prototype problems in pp_entersub -# - added support for sub prototypes that never get GVs -# - added unquoting for special filehandle first arg in truncate -# - print doubled rv2gv (a bug) as '*{*GV}' instead of illegal '**GV' -# - added semicolons at the ends of blocks -# - added -l '#line' declaration option -- fixes cmd/subval.t 27,28 -# Changes between 0.56 and 0.561: -# - fixed multiply-declared my var in pp_truncate (thanks to Sarathy) -# - used new B.pm symbolic constants (done by Nick Ing-Simmons) -# Changes between 0.561 and 0.57: -# - stylistic changes to symbolic constant stuff -# - handled scope in s///e replacement code -# - added unquote option for expanding "" into concats, etc. -# - split method and proto parts of pp_entersub into separate functions -# - various minor cleanups -# Changes after 0.57: -# - added parens in \&foo (patch by Albert Dvornik) -# Changes between 0.57 and 0.58: -# - fixed '0' statements that weren't being printed -# - added methods for use from other programs -# (based on patches from James Duncan and Hugo van der Sanden) -# - added -si and -sT to control indenting (also based on a patch from Hugo) -# - added -sv to print something else instead of '???' -# - preliminary version of utf8 tr/// handling -# Changes after 0.58: -# - uses of $op->ppaddr changed to new $op->name (done by Sarathy) -# - added support for Hugo's new OP_SETSTATE (like nextstate) -# Changes between 0.58 and 0.59 -# - added support for Chip's OP_METHOD_NAMED -# - added support for Ilya's OPpTARGET_MY optimization -# - elided arrows before '()' subscripts when possible -# Changes between 0.59 and 0.60 -# - support for method attributes was added -# - some warnings fixed -# - separate recognition of constant subs -# - rewrote continue block handling, now recognizing for loops -# - added more control of expanding control structures -# Changes between 0.60 and 0.61 (mostly by Robin Houston) -# - many bug-fixes -# - support for pragmas and 'use' -# - support for the little-used $[ variable -# - support for __DATA__ sections -# - UTF8 support -# - BEGIN, CHECK, INIT and END blocks -# - scoping of subroutine declarations fixed -# - compile-time output from the input program can be suppressed, so that the -# output is just the deparsed code. (a change to O.pm in fact) -# - our() declarations -# - *all* the known bugs are now listed in the BUGS section -# - comprehensive test mechanism (TEST -deparse) -# Changes between 0.62 and 0.63 (mostly by Rafael Garcia-Suarez) -# - bug-fixes -# - new switch -P -# - support for command-line switches (-l, -0, etc.) -# Changes between 0.63 and 0.64 -# - support for //, CHECK blocks, and assertions -# - improved handling of foreach loops and lexicals -# - option to use Data::Dumper for constants -# - more bug fixes -# - discovered lots more bugs not yet fixed -# -# ... -# -# Changes between 0.72 and 0.73 -# - support new switch constructs - # Todo: # (See also BUGS section at the end of this file) # @@ -361,7 +271,8 @@ BEGIN { BEGIN { for (qw[ const stringify rv2sv list glob pushmark null aelem - nextstate dbstate rv2av rv2hv helem custom ]) { + kvaslice kvhslice padsv + nextstate dbstate rv2av rv2hv helem custom ]) { eval "sub OP_\U$_ () { " . opnumber($_) . "}" }} @@ -401,13 +312,27 @@ sub _pessimise_walk { # pessimisations end here - if (class($op) eq 'PMOP' - && ref($op->pmreplroot) - && ${$op->pmreplroot} - && $op->pmreplroot->isa( 'B::OP' )) - { - $self-> _pessimise_walk($op->pmreplroot); - } + if (class($op) eq 'PMOP') { + if (ref($op->pmreplroot) + && ${$op->pmreplroot} + && $op->pmreplroot->isa( 'B::OP' )) + { + $self-> _pessimise_walk($op->pmreplroot); + } + + # pessimise any /(?{...})/ code blocks + my ($re, $cv); + my $code_list = $op->code_list; + if ($$code_list) { + $self->_pessimise_walk($code_list); + } + elsif (${$re = $op->pmregexp} && ${$cv = $re->qr_anoncv}) { + $code_list = $cv->ROOT # leavesub + ->first # qr + ->code_list; # list + $self->_pessimise_walk($code_list); + } + } if ($op->flags & OPf_KIDS) { $self-> _pessimise_walk($op->first); @@ -423,6 +348,8 @@ sub _pessimise_walk { sub _pessimise_walk_exe { my ($self, $startop, $visited) = @_; + no warnings 'recursion'; + return unless $$startop; return if $visited->{$$startop}; my ($op, $prevop); @@ -460,6 +387,7 @@ sub _pessimise_walk_exe { sub pessimise { my ($self, $root, $start) = @_; + no warnings 'recursion'; # walk tree in root-to-branch order $self->_pessimise_walk($root); @@ -474,6 +402,9 @@ sub null { return class($op) eq "NULL"; } + +# Add a CV to the list of subs that still need deparsing. + sub todo { my $self = shift; my($cv, $is_form, $name) = @_; @@ -487,58 +418,34 @@ sub todo { } else { $seq = 0; } + my $stash = $cv->STASH; + if (class($stash) eq 'HV') { + $self->{packs}{$stash->NAME}++; + } push @{$self->{'subs_todo'}}, [$seq, $cv, $is_form, $name]; } + +# Pop the next sub from the todo list and deparse it + sub next_todo { my $self = shift; my $ent = shift @{$self->{'subs_todo'}}; - my $cv = $ent->[1]; - if (ref $ent->[3]) { # lexical sub - my @text; + my ($seq, $cv, $is_form, $name) = @$ent; - # At this point, we may not yet have deparsed the hints that allow - # lexical subroutines to be recognized. So adjust the current - # hints and deparse them. - # When lex subs cease being experimental, we should be able to - # remove this code. - { - local $^H = $self->{'hints'}; - local %^H = %{ $self->{'hinthash'} || {} }; - local ${^WARNING_BITS} = $self->{'warnings'}; - feature->import("lexical_subs"); - warnings->unimport("experimental::lexical_subs"); - # Here we depend on the fact that individual features - # will always set the feature bundle to ‘custom’ - # (== $feature::hint_mask). If we had another specific bundle - # enabled previously, normalise it. - if (($self->{'hints'} & $feature::hint_mask) - != $feature::hint_mask) - { - if ($self->{'hinthash'}) { - delete $self->{'hinthash'}{$_} - for grep /^feature_/, keys %{$self->{'hinthash'}}; - } - else { $self->{'hinthash'} = {} } - $self->{'hinthash'} - = _features_from_bundle(@$self{'hints','hinthash'}); - } - push @text, $self->declare_hinthash($self->{'hinthash'}, \%^H, - $self->{indent_size}, $^H); - push @text, $self->declare_warnings($self->{'warnings'}, - ${^WARNING_BITS}) - unless ($self->{'warnings'} // 'u') - eq (${^WARNING_BITS } // 'u'); - $self->{'warnings'} = ${^WARNING_BITS}; - $self->{'hints'} = $^H; - $self->{'hinthash'} = {%^H}; - } + # any 'use strict; package foo' that should come before the sub + # declaration to sync with the first COP of the sub + my $pragmata = ''; + if ($cv and !null($cv->START) and is_state($cv->START)) { + $pragmata = $self->pragmata($cv->START); + } - # Now emit the sub itself. - my $padname = $ent->[3]; - my $flags = $padname->FLAGS; + if (ref $name) { # lexical sub + # emit the sub. + my @text; + my $flags = $name->FLAGS; push @text, - !$cv || $ent->[0] <= $padname->COP_SEQ_RANGE_LOW + !$cv || $seq <= $name->COP_SEQ_RANGE_LOW ? $self->keyword($flags & SVpad_OUR ? "our" : $flags & SVpad_STATE @@ -548,7 +455,7 @@ sub next_todo { # XXX We would do $self->keyword("sub"), but ‘my CORE::sub’ # doesn’t work and ‘my sub’ ignores a &sub in scope. I.e., # we have a core bug here. - push @text, "sub " . substr $padname->PVX, 1; + push @text, "sub " . substr $name->PVX, 1; if ($cv) { # my sub foo { } push @text, " " . $self->deparse_sub($cv); @@ -558,19 +465,41 @@ sub next_todo { # my sub foo; push @text, ";\n"; } - return join "", @text; + return $pragmata . join "", @text; } + my $gv = $cv->GV; - my $name = $ent->[3] // $self->gv_name($gv); - if ($ent->[2]) { - return $self->keyword("format") . " $name =\n" - . $self->deparse_format($ent->[1]). "\n"; + $name //= $self->gv_name($gv); + if ($is_form) { + return $pragmata . $self->keyword("format") . " $name =\n" + . $self->deparse_format($cv). "\n"; } else { my $use_dec; if ($name eq "BEGIN") { $use_dec = $self->begin_is_use($cv); if (defined ($use_dec) and $self->{'expand'} < 5) { - return () if 0 == length($use_dec); + return $pragmata if 0 == length($use_dec); + + # XXX bit of a hack: Test::More's use_ok() method + # builds a fake use statement which deparses as, e.g. + # use Net::Ping (@{$args[0];}); + # As well as being superfluous (the use_ok() is deparsed + # too) and ugly, it fails under use strict and otherwise + # makes use of a lexical var that's not in scope. + # So strip it out. + return $pragmata + if $use_dec =~ + m/ + \A + use \s \S+ \s \(\@\{ + ( + \s*\#line\ \d+\ \".*"\s* + )? + \$args\[0\];\}\); + \n + \Z + /x; + $use_dec =~ s/^(use|no)\b/$self->keyword($1)/e; } } @@ -591,7 +520,7 @@ sub next_todo { } } if ($use_dec) { - return "$p$l$use_dec"; + return "$pragmata$p$l$use_dec"; } if ( $name !~ /::/ and $self->lex_in_scope("&$name") || $self->lex_in_scope("&$name", 1) ) @@ -600,13 +529,14 @@ sub next_todo { } elsif (defined $stash) { $name =~ s/^\Q$stash\E::(?!\z|.*::)//; } - my $ret = "${p}${l}" . $self->keyword("sub") . " $name " + my $ret = "$pragmata${p}${l}" . $self->keyword("sub") . " $name " . $self->deparse_sub($cv); $self->{'subs_declared'}{$name} = 1; return $ret; } } + # Return a "use" declaration for this BEGIN block, if appropriate sub begin_is_use { my ($self, $cv) = @_; @@ -622,6 +552,9 @@ sub begin_is_use { my $req_op = $lineseq->first->sibling; return if $req_op->name ne "require"; + # maybe it's C<require expr> rather than C<require 'foo'> + return if ($req_op->first->name ne 'const'); + my $module; if ($req_op->first->private & OPpCONST_BARE) { # Actually it should always be a bareword @@ -725,7 +658,8 @@ sub stash_subs { if ($seen ||= {})->{ $INC{"overload.pm"} ? overload::StrVal($stash) : $stash }++; - my %stash = svref_2object($stash)->ARRAY; + my $stashobj = svref_2object($stash); + my %stash = $stashobj->ARRAY; while (my ($key, $val) = each %stash) { my $flags = $val->FLAGS; if ($flags & SVf_ROK) { @@ -766,7 +700,20 @@ sub stash_subs { } elsif (class($val) eq "GV") { if (class(my $cv = $val->CV) ne "SPECIAL") { next if $self->{'subs_done'}{$$val}++; - next if $$val != ${$cv->GV}; # Ignore imposters + + # Ignore imposters (aliases etc) + my $name = $cv->NAME_HEK; + if(defined $name) { + # avoid using $cv->GV here because if the $val GV is + # an alias, CvGV() could upgrade the real stash entry + # from an RV to a GV + next unless $name eq $key; + next unless $$stashobj == ${$cv->STASH}; + } + else { + next if $$val != ${$cv->GV}; + } + $self->todo($cv, 0); } if (class(my $cv = $val->FORM) ne "SPECIAL") { @@ -786,6 +733,14 @@ sub print_protos { my $ar; my @ret; foreach $ar (@{$self->{'protos_todo'}}) { + if (ref $ar->[1]) { + # Only print a constant if it occurs in the same package as a + # dumped sub. This is not perfect, but a heuristic that will + # hopefully work most of the time. Ideally we would use + # CvFILE, but a constant stub has no CvFILE. + my $pack = ($ar->[0] =~ /(.*)::/)[0]; + next if $pack and !$self->{packs}{$pack} + } my $body = defined $ar->[1] ? ref $ar->[1] ? " () {\n " . $self->const($ar->[1]->RV,0) . ";\n}" @@ -827,6 +782,7 @@ sub new { $self->{'ex_const'} = "'???'"; $self->{'expand'} = 0; $self->{'files'} = {}; + $self->{'packs'} = {}; $self->{'indent_size'} = 4; $self->{'linenums'} = 0; $self->{'parens'} = 0; @@ -886,7 +842,6 @@ sub init { ? $self->{'ambient_warnings'} & WARN_MASK : undef; $self->{'hints'} = $self->{'ambient_hints'}; - $self->{'hints'} &= 0xFF if $] < 5.009; $self->{'hinthash'} = $self->{'ambient_hinthash'}; # also a convenient place to clear out subs_declared @@ -1221,22 +1176,132 @@ sub pad_subs { sort {$a->[0] <=> $b->[0]} @{$self->{'subs_todo'}}, @todo } + +# deparse_argops(): deparse, if possible, a sequence of argcheck + argelem +# ops into a subroutine signature. If successful, return the first op +# following the signature ops plus the signature string; else return the +# empty list. +# +# Normally a bunch of argelem ops will have been generated by the +# signature parsing, but it's possible that ops have been added manually +# or altered. In this case we return "()" and fall back to general +# deparsing of the individual sigelems as 'my $x = $_[N]' etc. +# +# We're only called if the first two ops are nextstate and argcheck. + +sub deparse_argops { + my ($self, $firstop, $cv) = @_; + + my @sig; + my $o = $firstop; + return if $o->label; #first nextstate; + + # OP_ARGCHECK + + $o = $o->sibling; + my ($params, $opt_params, $slurpy) = $o->aux_list($cv); + my $mandatory = $params - $opt_params; + my $seen_slurpy = 0; + my $last_ix = -1; + + # keep looking for valid nextstate + argelem pairs + + while (1) { + # OP_NEXTSTATE + $o = $o->sibling; + last unless $$o; + last unless $o->name =~ /^(next|db)state$/; + last if $o->label; + + # OP_ARGELEM + my $o2 = $o->sibling; + last unless $$o2; + + if ($o2->name eq 'argelem') { + my $ix = $o2->string($cv); + while (++$last_ix < $ix) { + push @sig, $last_ix < $mandatory ? '$' : '$='; + } + my $var = $self->padname($o2->targ); + if ($var =~ /^[@%]/) { + return if $seen_slurpy; + $seen_slurpy = 1; + return if $ix != $params or !$slurpy + or substr($var,0,1) ne $slurpy; + } + else { + return if $ix >= $params; + } + if ($o2->flags & OPf_KIDS) { + my $kid = $o2->first; + return unless $$kid and $kid->name eq 'argdefelem'; + my $def = $self->deparse($kid->first, 7); + $def = "($def)" if $kid->first->flags & OPf_PARENS; + $var .= " = $def"; + } + push @sig, $var; + } + elsif ($o2->name eq 'null' + and ($o2->flags & OPf_KIDS) + and $o2->first->name eq 'argdefelem') + { + # special case - a void context default expression: $ = expr + + my $defop = $o2->first; + my $ix = $defop->targ; + while (++$last_ix < $ix) { + push @sig, $last_ix < $mandatory ? '$' : '$='; + } + return if $last_ix >= $params + or $last_ix < $mandatory; + my $def = $self->deparse($defop->first, 7); + $def = "($def)" if $defop->first->flags & OPf_PARENS; + push @sig, '$ = ' . $def; + } + else { + last; + } + + $o = $o2; + } + + while (++$last_ix < $params) { + push @sig, $last_ix < $mandatory ? '$' : '$='; + } + push @sig, $slurpy if $slurpy and !$seen_slurpy; + + return ($o, join(', ', @sig)); +} + +# Deparse a sub. Returns everything except the 'sub foo', +# e.g. ($$) : method { ...; } +# or : prototype($$) lvalue ($a, $b) { ...; }; + sub deparse_sub { my $self = shift; my $cv = shift; - my $proto = ""; + my @attrs; + my $proto; + my $sig; + Carp::confess("NULL in deparse_sub") if !defined($cv) || $cv->isa("B::NULL"); Carp::confess("SPECIAL in deparse_sub") if $cv->isa("B::SPECIAL"); local $self->{'curcop'} = $self->{'curcop'}; + + my $has_sig = $self->{hinthash}{feature_signatures}; if ($cv->FLAGS & SVf_POK) { - $proto = "(". $cv->PV . ") "; + my $myproto = $cv->PV; + if ($has_sig) { + push @attrs, "prototype($myproto)"; + } + else { + $proto = $myproto; + } } if ($cv->CvFLAGS & (CVf_METHOD|CVf_LOCKED|CVf_LVALUE|CVf_ANONCONST)) { - $proto .= ": "; - $proto .= "lvalue " if $cv->CvFLAGS & CVf_LVALUE; - $proto .= "locked " if $cv->CvFLAGS & CVf_LOCKED; - $proto .= "method " if $cv->CvFLAGS & CVf_METHOD; - $proto .= "const " if $cv->CvFLAGS & CVf_ANONCONST; + push @attrs, "lvalue" if $cv->CvFLAGS & CVf_LVALUE; + push @attrs, "method" if $cv->CvFLAGS & CVf_METHOD; + push @attrs, "const" if $cv->CvFLAGS & CVf_ANONCONST; } local($self->{'curcv'}) = $cv; @@ -1251,11 +1316,36 @@ Carp::confess("SPECIAL in deparse_sub") if $cv->isa("B::SPECIAL"); $self->pessimise($root, $cv->START); my $lineseq = $root->first; if ($lineseq->name eq "lineseq") { - my @ops; - for(my$o=$lineseq->first; $$o; $o=$o->sibling) { + my $firstop = $lineseq->first; + + if ($has_sig) { + my $o2; + # try to deparse first few ops as a signature if possible + if ( $$firstop + and $firstop->name =~ /^(next|db)state$/ + and (($o2 = $firstop->sibling)) + and $$o2) + { + if ($o2->name eq 'argcheck') { + my ($nexto, $mysig) = $self->deparse_argops($firstop, $cv); + if (defined $nexto) { + $firstop = $nexto; + $sig = $mysig; + } + } + } + } + + my @ops; + for (my $o = $firstop; $$o; $o=$o->sibling) { push @ops, $o; } $body = $self->lineseq(undef, 0, @ops).";"; + if (!$has_sig and $ops[-1]->name =~ /^(next|db)state$/) { + # this handles void context in + # use feature signatures; sub ($=1) {} + $body .= "\n()"; + } my $scope_en = $self->find_scope_en($lineseq); if (defined $scope_en) { my $subs = join"", $self->seq_subs($scope_en); @@ -1265,17 +1355,33 @@ Carp::confess("SPECIAL in deparse_sub") if $cv->isa("B::SPECIAL"); else { $body = $self->deparse($root->first, 0); } + + my $l = ''; + if ($self->{'linenums'}) { + # a glob's gp_line is set from the line containing a + # sub's closing '}' if the CV is the first use of the GV. + # So make sure the linenum is set correctly for '}' + my $gv = $cv->GV; + my $line = $gv->LINE; + my $file = $gv->FILE; + $l = "\f#line $line \"$file\"\n"; + } + $body = "{\n\t$body\n$l\b}"; } else { my $sv = $cv->const_sv; if ($$sv) { # uh-oh. inlinable sub... format it differently - return $proto . "{ " . $self->const($sv, 0) . " }\n"; + $body = "{ " . $self->const($sv, 0) . " }\n"; } else { # XSUB? (or just a declaration) - return "$proto;\n"; + $body = ';' } } - return $proto ."{\n\t$body\n\b}" ."\n"; + $proto = defined $proto ? "($proto) " : ""; + $sig = defined $sig ? "($sig) " : ""; + my $attrs = ''; + $attrs = ': ' . join('', map "$_ ", @attrs) if @attrs; + return "$proto$attrs$sig$body\n"; } sub deparse_format { @@ -1469,7 +1575,7 @@ sub maybe_local { if $self->{'avoid_local'}{$$op}; if ($need_parens) { return "$our_local($text)"; - } elsif (want_scalar($op)) { + } elsif (want_scalar($op) || $our_local eq 'our') { return "$our_local $text"; } else { return $self->maybe_parens_func("$our_local", $text, $cx, 16); @@ -1717,7 +1823,7 @@ sub gv_name { sub stash_variable { my ($self, $prefix, $name, $cx) = @_; - return "$prefix$name" if $name =~ /::/; + return $prefix.$self->maybe_qualify($prefix, $name) if $name =~ /::/; unless ($prefix eq '$' || $prefix eq '@' || $prefix eq '&' || #' $prefix eq '%' || $prefix eq '$#') { @@ -1793,11 +1899,16 @@ sub stash_variable_name { sub maybe_qualify { my ($self,$prefix,$name) = @_; my $v = ($prefix eq '$#' ? '@' : $prefix) . $name; - return $name if !$prefix || $name =~ /::/; + if ($prefix eq "") { + $name .= "::" if $name =~ /(?:\ACORE::[^:]*|::)\z/; + return $name; + } + return $name if $name =~ /::/; return $self->{'curstash'}.'::'. $name if $name =~ /^(?!\d)\w/ # alphabetic && $v !~ /^\$[ab]\z/ # not $a or $b + && $v =~ /\A[\$\@\%\&]/ # scalar, array, hash, or sub && !$globalnames{$name} # not a global name && $self->{hints} & $strict_bits{vars} # strict vars && !$self->lex_in_scope($v,1) # no "our" @@ -1887,14 +1998,6 @@ sub find_scope { sub cop_subs { my ($self, $op, $out_seq) = @_; my $seq = $op->cop_seq; - if ($] < 5.021006) { - # If we have nephews, then our sequence number indicates - # the cop_seq of the end of some sort of scope. - if (class($op->sibling) ne "NULL" && $op->sibling->flags & OPf_KIDS - and my $nseq = $self->find_scope_st($op->sibling) ) { - $seq = $nseq; - } - } $seq = $out_seq if defined($out_seq) && $out_seq < $seq; return $self->seq_subs($seq); } @@ -1934,18 +2037,15 @@ sub _features_from_bundle { return $hh; } -# Notice how subs and formats are inserted between statements here; -# also $[ assignments and pragmas. -sub pp_nextstate { +# generate any pragmas, 'package foo' etc needed to synchronise +# with the given cop + +sub pragmata { my $self = shift; - my($op, $cx) = @_; - $self->{'curcop'} = $op; + my($op) = @_; + my @text; - push @text, $self->cop_subs($op); - if (@text) { - # Special marker to swallow up the semicolon - push @text, "\cK"; - } + my $stash = $op->stashpv; if ($stash ne $self->{'curstash'}) { push @text, $self->keyword("package") . " $stash;\n"; @@ -1979,7 +2079,7 @@ sub pp_nextstate { $self->{'warnings'} = $warning_bits; } - my $hints = $] < 5.008009 ? $op->private : $op->hints; + my $hints = $op->hints; my $old_hints = $self->{'hints'}; if ($self->{'hints'} != $hints) { push @text, $self->declare_hints($self->{'hints'}, $hints); @@ -1987,11 +2087,9 @@ sub pp_nextstate { } my $newhh; - if ($] > 5.009) { - $newhh = $op->hints_hash->HASH; - } + $newhh = $op->hints_hash->HASH; - if ($] >= 5.015006) { + { # feature bundle hints my $from = $old_hints & $feature::hint_mask; my $to = $ hints & $feature::hint_mask; @@ -2016,7 +2114,7 @@ sub pp_nextstate { } } - if ($] > 5.009) { + { push @text, $self->declare_hinthash( $self->{'hinthash'}, $newhh, $self->{indent_size}, $self->{hints}, @@ -2024,6 +2122,29 @@ sub pp_nextstate { $self->{'hinthash'} = $newhh; } + return join("", @text); +} + + +# Notice how subs and formats are inserted between statements here; +# also $[ assignments and pragmas. +sub pp_nextstate { + my $self = shift; + my($op, $cx) = @_; + $self->{'curcop'} = $op; + + my @text; + + my @subs = $self->cop_subs($op); + if (@subs) { + # Special marker to swallow up the semicolon + push @subs, "\cK"; + } + push @text, @subs; + + push @text, $self->pragmata($op); + + # This should go after of any branches that add statements, to # increase the chances that it refers to the same line it did in # the original program. @@ -2039,12 +2160,18 @@ sub pp_nextstate { sub declare_warnings { my ($self, $from, $to) = @_; - if (($to & WARN_MASK) eq (warnings::bits("all") & WARN_MASK)) { - return $self->keyword("use") . " warnings;\n"; - } - elsif (($to & WARN_MASK) eq ("\0"x length($to) & WARN_MASK)) { - return $self->keyword("no") . " warnings;\n"; + $from //= ''; + my $all = (warnings::bits("all") & WARN_MASK); + unless ((($from & WARN_MASK) & ~$all) =~ /[^\0]/) { + # no FATAL bits need turning off + if ( ($to & WARN_MASK) eq $all) { + return $self->keyword("use") . " warnings;\n"; + } + elsif (($to & WARN_MASK) eq ("\0"x length($to) & WARN_MASK)) { + return $self->keyword("no") . " warnings;\n"; + } } + return "BEGIN {\${^WARNING_BITS} = \"" . join("", map { sprintf("\\x%02x", ord $_) } split "", $to) . "\"}\n\cK"; @@ -2086,7 +2213,7 @@ sub declare_hinthash { my @unfeatures; # bugs? for my $key (sort keys %$to) { next if $ignored_hints{$key}; - my $is_feature = $key =~ /^feature_/ && $^V ge 5.15.6; + my $is_feature = $key =~ /^feature_/; next if $is_feature and not $doing_features; if (!exists $from->{$key} or $from->{$key} ne $to->{$key}) { push(@features, $key), next if $is_feature; @@ -2102,7 +2229,7 @@ sub declare_hinthash { } for my $key (sort keys %$from) { next if $ignored_hints{$key}; - my $is_feature = $key =~ /^feature_/ && $^V ge 5.15.6; + my $is_feature = $key =~ /^feature_/; next if $is_feature and not $doing_features; if (!exists $to->{$key}) { push(@unfeatures, $key), next if $is_feature; @@ -2500,7 +2627,7 @@ sub pp_delete { my($op, $cx) = @_; my $arg; my $name = $self->keyword("delete"); - if ($op->private & OPpSLICE) { + if ($op->private & (OPpSLICE|OPpKVSLICE)) { if ($op->flags & OPf_SPECIAL) { # Deleting from an array, not a hash return $self->maybe_parens_func($name, @@ -2859,7 +2986,7 @@ sub binop { my $leftop = $left; $left = $self->deparse_binop_left($op, $left, $prec); $left = "($left)" if $flags & LIST_CONTEXT - and $left !~ /^(my|our|local|)[\@\(]/ + and $left !~ /^(my|our|local|state|)\s*[\@%\(]/ || do { # Parenthesize if the left argument is a # lone repeat op. @@ -2923,7 +3050,7 @@ sub pp_aassign { binop(@_, "=", 7, SWAP_CHILDREN | LIST_CONTEXT) } sub pp_smartmatch { my ($self, $op, $cx) = @_; - if ($op->flags & OPf_SPECIAL) { + if (($op->flags & OPf_SPECIAL) && $self->{expand} < 2) { return $self->deparse($op->last, $cx); } else { @@ -2942,7 +3069,8 @@ sub real_concat { my $right = $op->last; my $eq = ""; my $prec = 18; - if ($op->flags & OPf_STACKED and $op->first->name ne "concat") { + if (($op->flags & OPf_STACKED) and !($op->private & OPpCONCAT_NESTED)) { + # '.=' rather than optimised '.' $eq = "="; $prec = 7; } @@ -3138,9 +3266,35 @@ sub pp_substr { } maybe_local(@_, listop(@_, "substr")) } + +sub pp_index { + # Also handles pp_rindex. + # + # The body of this function includes an unrolled maybe_targmy(), + # since the two parts of that sub's actions need to have have the + # '== -1' bit in between + + my($self, $op, $cx) = @_; + + my $lex = ($op->private & OPpTARGET_MY); + my $bool = ($op->private & OPpTRUEBOOL); + + my $val = $self->listop($op, ($bool ? 14 : $lex ? 7 : $cx), $op->name); + + # (index() == -1) has op_eq and op_const optimised away + if ($bool) { + $val .= ($op->private & OPpINDEX_BOOLNEG) ? " == -1" : " != -1"; + $val = "($val)" if ($op->flags & OPf_PARENS); + } + if ($lex) { + my $var = $self->padname($op->targ); + $val = $self->maybe_parens("$var = $val", $cx, 7); + } + $val; +} + +sub pp_rindex { pp_index(@_); } sub pp_vec { maybe_targmy(@_, \&maybe_local, listop(@_, "vec")) } -sub pp_index { maybe_targmy(@_, \&listop, "index") } -sub pp_rindex { maybe_targmy(@_, \&listop, "rindex") } sub pp_sprintf { maybe_targmy(@_, \&listop, "sprintf") } sub pp_formline { listop(@_, "formline") } # see also deparse_format sub pp_crypt { maybe_targmy(@_, \&listop, "crypt") } @@ -3368,9 +3522,175 @@ BEGIN { delete @uses_intro{qw( lvref lvrefslice lvavref entersub )}; } + +# Look for a my/state attribute declaration in a list or ex-list. +# Returns undef if not found, 'my($x, @a) :Foo(bar)' etc otherwise. +# +# There are three basic tree structs that are expected: +# +# my $x :foo; +# <1> ex-list vK/LVINTRO ->c +# <0> ex-pushmark v ->3 +# <1> entersub[t2] vKRS*/TARG ->b +# .... +# <0> padsv[$x:64,65] vM/LVINTRO ->c +# +# my @a :foo; +# my %h :foo; +# +# <1> ex-list vK ->c +# <0> ex-pushmark v ->3 +# <0> padav[@a:64,65] vM/LVINTRO ->4 +# <1> entersub[t2] vKRS*/TARG ->c +# .... +# +# my ($x,@a,%h) :foo; +# +# <;> nextstate(main 64 -e:1) v:{ ->3 +# <@> list vKP ->w +# <0> pushmark vM/LVINTRO ->4 +# <0> padsv[$x:64,65] vM/LVINTRO ->5 +# <0> padav[@a:64,65] vM/LVINTRO ->6 +# <0> padhv[%h:64,65] vM/LVINTRO ->7 +# <1> entersub[t4] vKRS*/TARG ->f +# .... +# <1> entersub[t5] vKRS*/TARG ->n +# .... +# <1> entersub[t6] vKRS*/TARG ->v +# .... +# where the entersub in all cases looks like +# <1> entersub[t2] vKRS*/TARG ->c +# <0> pushmark s ->5 +# <$> const[PV "attributes"] sM ->6 +# <$> const[PV "main"] sM ->7 +# <1> srefgen sKM/1 ->9 +# <1> ex-list lKRM ->8 +# <0> padsv[@a:64,65] sRM ->8 +# <$> const[PV "foo"] sM ->a +# <.> method_named[PV "import"] ->b + +sub maybe_var_attr { + my ($self, $op, $cx) = @_; + + my $kid = $op->first->sibling; # skip pushmark + return if class($kid) eq 'NULL'; + + my $lop; + my $type; + + # Extract out all the pad ops and entersub ops into + # @padops and @entersubops. Return if anything else seen. + # Also determine what class (if any) all the pad vars belong to + my $class; + my $decl; # 'my' or 'state' + my (@padops, @entersubops); + for ($lop = $kid; !null($lop); $lop = $lop->sibling) { + my $lopname = $lop->name; + my $loppriv = $lop->private; + if ($lopname =~ /^pad[sah]v$/) { + return unless $loppriv & OPpLVAL_INTRO; + + my $padname = $self->padname_sv($lop->targ); + my $thisclass = ($padname->FLAGS & SVpad_TYPED) + ? $padname->SvSTASH->NAME : 'main'; + + # all pad vars must be in the same class + $class //= $thisclass; + return unless $thisclass eq $class; + + # all pad vars must be the same sort of declaration + # (all my, all state, etc) + my $this = ($loppriv & OPpPAD_STATE) ? 'state' : 'my'; + if (defined $decl) { + return unless $this eq $decl; + } + $decl = $this; + + push @padops, $lop; + } + elsif ($lopname eq 'entersub') { + push @entersubops, $lop; + } + else { + return; + } + } + + return unless @padops && @padops == @entersubops; + + # there should be a balance: each padop has a corresponding + # 'attributes'->import() method call, in the same order. + + my @varnames; + my $attr_text; + + for my $i (0..$#padops) { + my $padop = $padops[$i]; + my $esop = $entersubops[$i]; + + push @varnames, $self->padname($padop->targ); + + return unless ($esop->flags & OPf_KIDS); + + my $kid = $esop->first; + return unless $kid->type == OP_PUSHMARK; + + $kid = $kid->sibling; + return unless $$kid && $kid->type == OP_CONST; + return unless $self->const_sv($kid)->PV eq 'attributes'; + + $kid = $kid->sibling; + return unless $$kid && $kid->type == OP_CONST; # __PACKAGE__ + + $kid = $kid->sibling; + return unless $$kid + && $kid->name eq "srefgen" + && ($kid->flags & OPf_KIDS) + && ($kid->first->flags & OPf_KIDS) + && $kid->first->first->name =~ /^pad[sah]v$/ + && $kid->first->first->targ == $padop->targ; + + $kid = $kid->sibling; + my @attr; + while ($$kid) { + last if ($kid->type != OP_CONST); + push @attr, $self->const_sv($kid)->PV; + $kid = $kid->sibling; + } + return unless @attr; + my $thisattr = ":" . join(' ', @attr); + $attr_text //= $thisattr; + # all import calls must have the same list of attributes + return unless $attr_text eq $thisattr; + + return unless $kid->name eq 'method_named'; + return unless $self->meth_sv($kid)->PV eq 'import'; + + $kid = $kid->sibling; + return if $$kid; + } + + my $res = $decl; + $res .= " $class " if $class ne 'main'; + $res .= + (@varnames > 1) + ? "(" . join(', ', @varnames) . ')' + : " $varnames[0]"; + + return "$res $attr_text"; +} + + sub pp_list { my $self = shift; my($op, $cx) = @_; + + { + # might be my ($s,@a,%h) :Foo(bar); + my $my_attr = maybe_var_attr($self, $op, $cx); + return $my_attr if defined $my_attr; + } + my($expr, @exprs); my $kid = $op->first->sibling; # skip pushmark return '' if class($kid) eq 'NULL'; @@ -3448,6 +3768,10 @@ sub pp_list { push @exprs, $expr; } if ($local) { + if (@exprs == 1 && ($local eq 'state' || $local eq 'CORE::state')) { + # 'state @a = ...' is legal, while 'state(@a) = ...' currently isn't + return "$local $exprs[0]"; + } return "$local(" . join(", ", @exprs) . ")"; } else { return $self->maybe_parens( join(", ", @exprs), $cx, 6); @@ -3664,6 +3988,13 @@ sub _op_is_or_was { sub pp_null { my($self, $op, $cx) = @_; + + # might be 'my $s :Foo(bar);' + if ($op->targ == OP_LIST) { + my $my_attr = maybe_var_attr($self, $op, $cx); + return $my_attr if defined $my_attr; + } + if (class($op) eq "OP") { # old value is lost return $self->{'ex_const'} if $op->targ == OP_CONST; @@ -3740,7 +4071,31 @@ sub pp_padsv { } sub pp_padav { pp_padsv(@_) } -sub pp_padhv { pp_padsv(@_) } + +# prepend 'keys' where its been optimised away, with suitable handling +# of CORE:: and parens + +sub add_keys_keyword { + my ($self, $str, $cx) = @_; + $str = $self->maybe_parens($str, $cx, 16); + # 'keys %h' versus 'keys(%h)' + $str = " $str" unless $str =~ /^\(/; + return $self->keyword("keys") . $str; +} + +sub pp_padhv { + my ($self, $op, $cx) = @_; + my $str = pp_padsv(@_); + # with OPpPADHV_ISKEYS the keys op is optimised away, except + # in scalar context the old op is kept (but not executed) so its targ + # can be used. + if ( ($op->private & OPpPADHV_ISKEYS) + && !(($op->flags & OPf_WANT) == OPf_WANT_SCALAR)) + { + $str = $self->add_keys_keyword($str, $cx); + } + $str; +} sub gv_or_padgv { my $self = shift; @@ -3764,7 +4119,7 @@ sub pp_gv { my $self = shift; my($op, $cx) = @_; my $gv = $self->gv_or_padgv($op); - return $self->gv_name($gv); + return $self->maybe_qualify("", $self->gv_name($gv)); } sub pp_aelemfast_lex { @@ -3801,7 +4156,8 @@ sub rv2x { } my $kid = $op->first; if ($kid->name eq "gv") { - return $self->stash_variable($type, $self->deparse($kid, 0), $cx); + return $self->stash_variable($type, + $self->gv_name($self->gv_or_padgv($kid)), $cx); } elsif (is_scalar $kid) { my $str = $self->deparse($kid, 0); if ($str =~ /^\$([^\w\d])\z/) { @@ -3823,18 +4179,43 @@ sub rv2x { } sub pp_rv2sv { maybe_local(@_, rv2x(@_, "\$")) } -sub pp_rv2hv { maybe_local(@_, rv2x(@_, "%")) } sub pp_rv2gv { maybe_local(@_, rv2x(@_, "*")) } +sub pp_rv2hv { + my ($self, $op, $cx) = @_; + my $str = rv2x(@_, "%"); + if ($op->private & OPpRV2HV_ISKEYS) { + $str = $self->add_keys_keyword($str, $cx); + } + return maybe_local(@_, $str); +} + # skip rv2av sub pp_av2arylen { my $self = shift; my($op, $cx) = @_; - if ($op->first->name eq "padav") { - return $self->maybe_local($op, $cx, '$#' . $self->padany($op->first)); + my $kid = $op->first; + if ($kid->name eq "padav") { + return $self->maybe_local($op, $cx, '$#' . $self->padany($kid)); } else { - return $self->maybe_local($op, $cx, - $self->rv2x($op->first, $cx, '$#')); + my $kkid; + if ( $kid->name eq "rv2av" + && ($kkid = $kid->first) + && $kkid->name !~ /^(scope|leave|gv)$/) + { + # handle (expr)->$#* postfix form + my $expr; + $expr = $self->deparse($kkid, 24); # 24 is '->' + $expr = "$expr->\$#*"; + # XXX maybe_local is probably wrong here: local($#-expression) + # doesn't "do" local (the is no INTRO flag set) + return $self->maybe_local($op, $cx, $expr); + } + else { + # handle $#{expr} form + # XXX see maybe_local comment above + return $self->maybe_local($op, $cx, $self->rv2x($kid, $cx, '$#')); + } } } @@ -4004,6 +4385,146 @@ sub multideref_var_name { } +# deparse an OP_MULTICONCAT. If $in_dq is 1, we're within +# a double-quoted string, so for example. +# "abc\Qdef$x\Ebar" +# might get compiled as +# multiconcat("abc", metaquote(multiconcat("def", $x)), "bar") +# and the inner multiconcat should be deparsed as C<def$x> rather than +# the normal C<def . $x> +# Ditto if $in_dq is 2, handle qr/...\Qdef$x\E.../. + +sub do_multiconcat { + my $self = shift; + my($op, $cx, $in_dq) = @_; + + my $kid; + my @kids; + my $assign; + my $append; + my $lhs = ""; + + for ($kid = $op->first; !null $kid; $kid = $kid->sibling) { + # skip the consts and/or padsv we've optimised away + push @kids, $kid + unless $kid->type == OP_NULL + && ( $kid->targ == OP_PADSV + || $kid->targ == OP_CONST + || $kid->targ == OP_PUSHMARK); + } + + $append = ($op->private & OPpMULTICONCAT_APPEND); + + if ($op->private & OPpTARGET_MY) { + # '$lex = ...' or '$lex .= ....' or 'my $lex = ' + $lhs = $self->padname($op->targ); + $lhs = "my $lhs" if ($op->private & OPpLVAL_INTRO); + $assign = 1; + } + elsif ($op->flags & OPf_STACKED) { + # 'expr = ...' or 'expr .= ....' + my $expr = $append ? shift(@kids) : pop(@kids); + $lhs = $self->deparse($expr, 7); + $assign = 1; + } + + if ($assign) { + $lhs .= $append ? ' .= ' : ' = '; + } + + my ($nargs, $const_str, @const_lens) = $op->aux_list($self->{curcv}); + + my @consts; + my $i = 0; + for (@const_lens) { + if ($_ == -1) { + push @consts, undef; + } + else { + push @consts, substr($const_str, $i, $_); + my @args; + $i += $_; + } + } + + my $rhs = ""; + + if ( $in_dq + || (($op->private & OPpMULTICONCAT_STRINGIFY) && !$self->{'unquote'})) + { + # "foo=$foo bar=$bar " + my $not_first; + while (@consts) { + if ($not_first) { + my $s = $self->dq(shift(@kids), 18); + # don't deparse "a${$}b" as "a$$b" + $s = '${$}' if $s eq '$$'; + $rhs = dq_disambiguate($rhs, $s); + } + $not_first = 1; + my $c = shift @consts; + if (defined $c) { + if ($in_dq == 2) { + # in pattern: don't convert newline to '\n' etc etc + my $s = re_uninterp(escape_re(re_unback($c))); + $rhs = re_dq_disambiguate($rhs, $s) + } + else { + my $s = uninterp(escape_str(unback($c))); + $rhs = dq_disambiguate($rhs, $s) + } + } + } + return $rhs if $in_dq; + $rhs = single_delim("qq", '"', $rhs, $self); + } + elsif ($op->private & OPpMULTICONCAT_FAKE) { + # sprintf("foo=%s bar=%s ", $foo, $bar) + + my @all; + @consts = map { $_ //= ''; s/%/%%/g; $_ } @consts; + my $fmt = join '%s', @consts; + push @all, $self->quoted_const_str($fmt); + + # the following is a stripped down copy of sub listop {} + my $parens = $assign || ($cx >= 5) || $self->{'parens'}; + my $fullname = $self->keyword('sprintf'); + push @all, map $self->deparse($_, 6), @kids; + + $rhs = $parens + ? "$fullname(" . join(", ", @all) . ")" + : "$fullname " . join(", ", @all); + } + else { + # "foo=" . $foo . " bar=" . $bar + my @all; + my $not_first; + while (@consts) { + push @all, $self->deparse(shift(@kids), 18) if $not_first; + $not_first = 1; + my $c = shift @consts; + if (defined $c) { + push @all, $self->quoted_const_str($c); + } + } + $rhs .= join ' . ', @all; + } + + my $text = $lhs . $rhs; + + $text = "($text)" if ($cx >= (($assign) ? 7 : 18+1)) + || $self->{'parens'}; + + return $text; +} + + +sub pp_multiconcat { + my $self = shift; + $self->do_multiconcat(@_, 0); +} + + sub pp_multideref { my $self = shift; my($op, $cx) = @_; @@ -4021,7 +4542,11 @@ sub pp_multideref { if ($op->first && ($op->first->flags & OPf_KIDS)) { # arbitrary initial expression, e.g. f(1,2,3)->[...] - $text .= $self->deparse($op->first, 24); + my $expr = $self->deparse($op->first, 24); + # stop "exists (expr)->{...}" being interpreted as + #"(exists (expr))->{...}" + $expr = "+$expr" if $expr =~ /^\(/; + $text .= $expr; } my @items = $op->aux_list($self->{curcv}); @@ -4139,6 +4664,7 @@ sub pp_gelem { my $scope = is_scope($glob); $glob = $self->deparse($glob, 0); $part = $self->deparse($part, 1); + $glob =~ s/::\z// unless $scope; return "*" . ($scope ? "{$glob}" : $glob) . "{$part}"; } @@ -4167,8 +4693,9 @@ sub slice { } else { $list = $self->elem_or_slice_single_index($kid); } - my $lead = '@'; - $lead = '%' if $op->name =~ /^kv/i; + my $lead = ( _op_is_or_was($op, OP_KVHSLICE) + || _op_is_or_was($op, OP_KVASLICE)) + ? '%' : '@'; return $lead . $array . $left . $list . $right; } @@ -4381,7 +4908,7 @@ sub retscalar { |study|pos|preinc|i_preinc|predec|i_predec|postinc |i_postinc|postdec|i_postdec|pow|multiply|i_multiply |divide|i_divide|modulo|i_modulo|add|i_add|subtract - |i_subtract|concat|stringify|left_shift|right_shift|lt + |i_subtract|concat|multiconcat|stringify|left_shift|right_shift|lt |i_lt|gt|i_gt|le|i_le|ge|i_ge|eq|i_eq|ne|i_ne|ncmp|i_ncmp |slt|sgt|sle|sge|seq|sne|scmp|[sn]?bit_(?:and|x?or)|negate |i_negate|not|[sn]?complement|smartmatch|atan2|sin|cos @@ -4443,7 +4970,7 @@ sub pp_entersub { $proto = $cv->PV if $cv->FLAGS & SVf_POK; } $simple = 1; # only calls of named functions can be prototyped - $kid = $self->deparse($kid, 24); + $kid = $self->maybe_qualify("!", $self->gv_name($gv)); my $fq; # Fully qualify any sub name that conflicts with a lexical. if ($self->lex_in_scope("&$kid") @@ -4655,11 +5182,33 @@ sub unback { # Remove backslashes which precede literal control characters, # to avoid creating ambiguity when we escape the latter. +# +# Don't remove a backslash from escaped whitespace: where the T represents +# a literal tab character, /T/x is not equivalent to /\T/x + sub re_unback { my($str) = @_; # the insane complexity here is due to the behaviour of "\c\" - $str =~ s/(^|[^\\]|\\c\\)(?<!\\c)\\(\\\\)*(?=[[:^print:]])/$1$2/g; + $str =~ s/ + # these two lines ensure that the backslash we're about to + # remove isn't preceeded by something which makes it part + # of a \c + + (^ | [^\\] | \\c\\) # $1 + (?<!\\c) + + # the backslash to remove + \\ + + # keep pairs of backslashes + (\\\\)* # $2 + + # only remove if the thing following is a control char + (?=[[:^print:]]) + # and not whitespace + (?=\S) + /$1$2/xg; return $str; } @@ -4735,6 +5284,20 @@ sub split_float { return ($mantissa, $exponent); } + +# suitably single- or double-quote a literal constant string + +sub quoted_const_str { + my ($self, $str) =@_; + if ($str =~ /[[:^print:]]/a) { + return single_delim("qq", '"', + uninterp(escape_str unback $str), $self); + } else { + return single_delim("q", "'", unback($str), $self); + } +} + + sub const { my $self = shift; my($sv, $cx) = @_; @@ -4820,13 +5383,8 @@ sub const { } return "{" . join(", ", @elts) . "}"; } elsif ($class eq "CV") { - BEGIN { - if ($] > 5.0150051) { - require overloading; - unimport overloading; - } - } - if ($] > 5.0150051 && $self->{curcv} && + no overloading; + if ($self->{curcv} && $self->{curcv}->object_2svref == $ref->object_2svref) { return $self->keyword("__SUB__"); } @@ -4848,12 +5406,7 @@ sub const { return $self->maybe_parens("\\$const", $cx, 20); } elsif ($sv->FLAGS & SVf_POK) { my $str = $sv->PV; - if ($str =~ /[[:^print:]]/a) { - return single_delim("qq", '"', - uninterp(escape_str unback $str), $self); - } else { - return single_delim("q", "'", unback($str), $self); - } + return $self->quoted_const_str($str); } else { return "undef"; } @@ -4913,6 +5466,25 @@ sub pp_const { return $self->const($sv, $cx); } + +# Join two components of a double-quoted string, disambiguating +# "${foo}bar", "${foo}{bar}", "${foo}[1]", "$foo\::bar" + +sub dq_disambiguate { + my ($first, $last) = @_; + ($last =~ /^[A-Z\\\^\[\]_?]/ && + $first =~ s/([\$@])\^$/${1}{^}/) # "${^}W" etc + || ($last =~ /^[:'{\[\w_]/ && #' + $first =~ s/([\$@])([A-Za-z_]\w*)$/${1}{$2}/); + return $first . $last; +} + + +# Deparse a double-quoted optree. For example, "$a[0]\Q$b\Efo\"o" gets +# compiled to concat(concat($[0],quotemeta($b)),const("fo\"o")), and this +# sub deparses it back to $a[0]\Q$b\Efo"o +# (It does not add delimiters) + sub dq { my $self = shift; my $op = shift; @@ -4921,16 +5493,9 @@ sub dq { return '$[' if $op->private & OPpCONST_ARYBASE; return uninterp(escape_str(unback($self->const_sv($op)->as_string))); } elsif ($type eq "concat") { - my $first = $self->dq($op->first); - my $last = $self->dq($op->last); - - # Disambiguate "${foo}bar", "${foo}{bar}", "${foo}[1]", "$foo\::bar" - ($last =~ /^[A-Z\\\^\[\]_?]/ && - $first =~ s/([\$@])\^$/${1}{^}/) # "${^}W" etc - || ($last =~ /^[:'{\[\w_]/ && #' - $first =~ s/([\$@])([A-Za-z_]\w*)$/${1}{$2}/); - - return $first . $last; + return dq_disambiguate($self->dq($op->first), $self->dq($op->last)); + } elsif ($type eq "multiconcat") { + return $self->do_multiconcat($op, 26, 1); } elsif ($type eq "uc") { return '\U' . $self->dq($op->first->sibling) . '\E'; } elsif ($type eq "lc") { @@ -5019,7 +5584,9 @@ sub double_delim { } } +# Escape a characrter. # Only used by tr///, so backslashes hyphens + sub pchr { # ASCII my($n) = @_; if ($n == ord '\\') { @@ -5047,13 +5614,16 @@ sub pchr { # ASCII } elsif ($n == ord "\r") { return '\\r'; } elsif ($n >= ord("\cA") and $n <= ord("\cZ")) { - return '\\c' . unctrl{chr $n}; + return '\\c' . $unctrl{chr $n}; } else { # return '\x' . sprintf("%02x", $n); return '\\' . sprintf("%03o", $n); } } +# Convert a list of characters into a string suitable for tr/// search or +# replacement, with suitable escaping and collapsing of ranges + sub collapse { my(@chars) = @_; my($str, $c, $tr) = (""); @@ -5074,8 +5644,10 @@ sub collapse { sub tr_decode_byte { my($table, $flags) = @_; - my(@table) = unpack("s*", $table); - splice @table, 0x100, 1; # Number of subsequent elements + my $ssize_t = $Config{ptrsize} == 8 ? 'q' : 'l'; + my ($size, @table) = unpack("${ssize_t}s*", $table); + pop @table; # remove the wildcard final entry + my($c, $tr, @from, @to, @delfrom, $delhyphen); if ($table[ord "-"] != -1 and $table[ord("-") - 1] == -1 || $table[ord("-") + 1] == -1) @@ -5098,7 +5670,12 @@ sub tr_decode_byte { } } @from = (@from, @delfrom); + if ($flags & OPpTRANS_COMPLEMENT) { + unless ($flags & OPpTRANS_DELETE) { + @to = () if ("@from" eq "@to"); + } + my @newfrom = (); my %from; @from{@from} = (1) x @from; @@ -5255,9 +5832,11 @@ sub pp_trans { sub pp_transr { push @_, 'r'; goto &pp_trans } +# Join two components of a double-quoted re, disambiguating +# "${foo}bar", "${foo}{bar}", "${foo}[1]". + sub re_dq_disambiguate { my ($first, $last) = @_; - # Disambiguate "${foo}bar", "${foo}{bar}", "${foo}[1]" ($last =~ /^[A-Z\\\^\[\]_?]/ && $first =~ s/([\$@])\^$/${1}{^}/) # "${^}W" etc || ($last =~ /^[{\[\w_]/ && @@ -5279,6 +5858,8 @@ sub re_dq { my $first = $self->re_dq($op->first); my $last = $self->re_dq($op->last); return re_dq_disambiguate($first, $last); + } elsif ($type eq "multiconcat") { + return $self->do_multiconcat($op, 26, 2); } elsif ($type eq "uc") { return '\U' . $self->re_dq($op->first->sibling) . '\E'; } elsif ($type eq "lc") { @@ -5327,6 +5908,31 @@ sub pure_string { return $self->pure_string($op->first) && $self->pure_string($op->last); } + elsif ($type eq 'multiconcat') { + my ($kid, @kids); + for ($kid = $op->first; !null $kid; $kid = $kid->sibling) { + # skip the consts and/or padsv we've optimised away + push @kids, $kid + unless $kid->type == OP_NULL + && ( $kid->targ == OP_PADSV + || $kid->targ == OP_CONST + || $kid->targ == OP_PUSHMARK); + } + + if ($op->flags & OPf_STACKED) { + # remove expr from @kids where 'expr = ...' or 'expr .= ....' + if ($op->private & OPpMULTICONCAT_APPEND) { + shift(@kids); + } + else { + pop(@kids); + } + } + for (@kids) { + return 0 unless $self->pure_string($_); + } + return 1; + } elsif (is_scalar($op) || $type =~ /^[ah]elem$/) { return 1; } @@ -5478,7 +6084,7 @@ sub matchop { my($op, $cx, $name, $delim) = @_; my $kid = $op->first; my ($binop, $var, $re) = ("", "", ""); - if ($op->flags & OPf_STACKED) { + if ($op->name ne 'split' && $op->flags & OPf_STACKED) { $binop = 1; $var = $self->deparse($kid, 20); $kid = $kid->sibling; @@ -5517,7 +6123,13 @@ sub matchop { } elsif (!$have_kid) { $re = re_uninterp(escape_re(re_unback($op->precomp))); } elsif ($kid->name ne 'regcomp') { - carp("found ".$kid->name." where regcomp expected"); + if ($op->name eq 'split') { + # split has other kids, not just regcomp + $re = re_uninterp(escape_re(re_unback($op->precomp))); + } + else { + carp("found ".$kid->name." where regcomp expected"); + } } else { ($re, $quote) = $self->regcomp($kid, 21); } @@ -5557,64 +6169,58 @@ sub matchop { } sub pp_match { matchop(@_, "m", "/") } -sub pp_pushre { matchop(@_, "m", "/") } sub pp_qr { matchop(@_, "qr", "") } sub pp_runcv { unop(@_, "__SUB__"); } sub pp_split { - maybe_targmy(@_, \&split); -} -sub split { my $self = shift; my($op, $cx) = @_; my($kid, @exprs, $ary, $expr); + my $stacked = $op->flags & OPf_STACKED; + $kid = $op->first; + $kid = $kid->sibling if $kid->name eq 'regcomp'; + for (; !null($kid); $kid = $kid->sibling) { + push @exprs, $self->deparse($kid, 6); + } - # For our kid (an OP_PUSHRE), pmreplroot is never actually the - # root of a replacement; it's either empty, or abused to point to - # the GV for an array we split into (an optimization to save - # assignment overhead). Depending on whether we're using ithreads, - # this OP* holds either a GV* or a PADOFFSET. Luckily, B.xs - # figures out for us which it is. - my $replroot = $kid->pmreplroot; - my $gv = 0; - my $stacked = $op->flags & OPf_STACKED; - if (ref($replroot) eq "B::GV") { - $gv = $replroot; - } elsif (!ref($replroot) and $replroot > 0) { - $gv = $self->padval($replroot); - } elsif ($kid->targ) { - $ary = $self->padname($kid->targ) - } elsif ($stacked) { - $ary = $self->deparse($op->last, 7); - } - $ary = $self->maybe_local(@_, + unshift @exprs, $self->matchop($op, $cx, "m", "/"); + + if ($op->private & OPpSPLIT_ASSIGN) { + # With C<@array = split(/pat/, str);>, + # array is stored in split's pmreplroot; either + # as an integer index into the pad (for a lexical array) + # or as GV for a package array (which will be a pad index + # on threaded builds) + # With my/our @array = split(/pat/, str), the array is instead + # accessed via an extra padav/rv2av op at the end of the + # split's kid ops. + + if ($stacked) { + $ary = pop @exprs; + } + else { + if ($op->private & OPpSPLIT_LEX) { + $ary = $self->padname($op->pmreplroot); + } + else { + # union with op_pmtargetoff, op_pmtargetgv + my $gv = $op->pmreplroot; + $gv = $self->padval($gv) if !ref($gv); + $ary = $self->maybe_local(@_, $self->stash_variable('@', $self->gv_name($gv), $cx)) - if $gv; - - # Skip the last kid when OPf_STACKED is set, since it is the array - # on the left. - for (; !null($stacked ? $kid->sibling : $kid); $kid = $kid->sibling) { - push @exprs, $self->deparse($kid, 6); + } + if ($op->private & OPpLVAL_INTRO) { + $ary = $op->private & OPpSPLIT_LEX ? "my $ary" : "local $ary"; + } + } } # handle special case of split(), and split(' ') that compiles to /\s+/ - # Under 5.10, the reflags may be undef if the split regexp isn't a constant - # Under 5.17.5-5.17.9, the special flag is on split itself. - $kid = $op->first; - if ( $op->flags & OPf_SPECIAL - or ( - $kid->flags & OPf_SPECIAL - and ( $] < 5.009 ? $kid->pmflags & PMf_SKIPWHITE() - : ($kid->reflags || 0) & RXf_SKIPWHITE() - ) - ) - ) { - $exprs[0] = "' '"; - } + $exprs[0] = q{' '} if ($op->reflags // 0) & RXf_SKIPWHITE(); $expr = "split(" . join(", ", @exprs) . ")"; if ($ary) { @@ -5772,6 +6378,63 @@ sub pp_lvavref { : &pp_padsv) . ')' } + +sub pp_argcheck { + my $self = shift; + my($op, $cx) = @_; + my ($params, $opt_params, $slurpy) = $op->aux_list($self->{curcv}); + my $mandatory = $params - $opt_params; + my $check = ''; + + $check .= <<EOF if !$slurpy; +die sprintf("Too many arguments for subroutine at %s line %d.\\n", (caller)[1, 2]) unless \@_ <= $params; +EOF + + $check .= <<EOF if $mandatory > 0; +die sprintf("Too few arguments for subroutine at %s line %d.\\n", (caller)[1, 2]) unless \@_ >= $mandatory; +EOF + + my $cond = ($params & 1) ? 'unless' : 'if'; + $check .= <<EOF if $slurpy eq '%'; +die sprintf("Odd name/value argument for subroutine at %s line %d.\\n", (caller)[1, 2]) if \@_ > $params && ((\@_ - $params) & 1); +EOF + + $check =~ s/;\n\z//; + return $check; +} + + +sub pp_argelem { + my $self = shift; + my($op, $cx) = @_; + my $var = $self->padname($op->targ); + my $ix = $op->string($self->{curcv}); + my $expr; + if ($op->flags & OPf_KIDS) { + $expr = $self->deparse($op->first, 7); + } + elsif ($var =~ /^[@%]/) { + $expr = $ix ? "\@_[$ix .. \$#_]" : '@_'; + } + else { + $expr = "\$_[$ix]"; + } + return "my $var = $expr"; +} + + +sub pp_argdefelem { + my $self = shift; + my($op, $cx) = @_; + my $ix = $op->targ; + my $expr = "\@_ >= " . ($ix+1) . " ? \$_[$ix] : "; + my $def = $self->deparse($op->first, 7); + $def = "($def)" if $op->first->flags & OPf_PARENS; + $expr .= $self->deparse($op->first, $cx); + return $expr; +} + + 1; __END__ @@ -6110,7 +6773,7 @@ expect. =item $[ Takes a number, the value of the array base $[. -Cannot be non-zero on Perl 5.15.3 or later. +Obsolete: cannot be non-zero. =item bytes @@ -6197,11 +6860,10 @@ the main:: package, the code will include a package declaration. =item * -In Perl 5.20 and earlier, the only pragmas to +The only pragmas to be completely supported are: C<use warnings>, C<use strict>, C<use bytes>, C<use integer> -and C<use feature>. (C<$[>, which -behaves like a pragma, is also supported.) +and C<use feature>. Excepting those listed above, we're currently unable to guarantee that B::Deparse will produce a pragma at the correct point in the program. @@ -6219,9 +6881,6 @@ exactly the right place. So if you use a module which affects compilation (such as by over-riding keywords, overloading constants or whatever) then the output code might not work as intended. -This is the most serious problem in Perl 5.20 and earlier. Fixing this -required internal changes in Perl 5.22. - =item * Some constants don't print correctly either with or without B<-d>. @@ -6256,7 +6915,7 @@ which is not, consequently, deparsed correctly. =item * Lexical (my) variables declared in scopes external to a subroutine -appear in code2ref output text as package variables. This is a tricky +appear in coderef2text output text as package variables. This is a tricky problem, as perl has no native facility for referring to a lexical variable defined within a different scope, although L<PadWalker> is a good start. @@ -6267,12 +6926,6 @@ L<PadWalker> to serialize closures properly. There are probably many more bugs on non-ASCII platforms (EBCDIC). -=item * - -Prior to Perl 5.22, lexical C<my> subroutines were not deparsed properly. -They were emitted as pure declarations, sometimes in the wrong place. -Lexical C<state> subroutines were not deparsed at all. - =back =head1 AUTHOR diff --git a/gnu/usr.bin/perl/lib/B/Deparse.t b/gnu/usr.bin/perl/lib/B/Deparse.t index 19db4040bca..2451ce5e774 100644 --- a/gnu/usr.bin/perl/lib/B/Deparse.t +++ b/gnu/usr.bin/perl/lib/B/Deparse.t @@ -1,7 +1,7 @@ #!./perl BEGIN { - unshift @INC, 't'; + splice @INC, 0, 0, 't', '.'; require Config; if (($Config::Config{'extensions'} !~ /\bB\b/) ){ print "1..0 # Skip -- Perl configured without B module\n"; @@ -13,7 +13,7 @@ BEGIN { use warnings; use strict; -my $tests = 46; # not counting those in the __DATA__ section +my $tests = 52; # not counting those in the __DATA__ section use B::Deparse; my $deparse = B::Deparse->new(); @@ -63,7 +63,7 @@ while (<DATA>) { new B::Deparse split /,/, $meta{options} : $deparse; - my $coderef = eval "$meta{context};\n" . <<'EOC' . "sub {$input\n}"; + my $code = "$meta{context};\n" . <<'EOC' . "sub {$input\n}"; # Tell B::Deparse about our ambient pragmas my ($hint_bits, $warning_bits, $hinthash); BEGIN { @@ -75,10 +75,14 @@ $deparse->ambient_pragmas ( '%^H' => $hinthash, ); EOC + my $coderef = eval $code; local $::TODO = $meta{todo}; if ($@) { - is($@, "", "compilation of $desc"); + is($@, "", "compilation of $desc") + or diag "=============================================\n" + . "CODE:\n--------\n$code\n--------\n" + . "=============================================\n"; } else { my $deparsed = $deparse->coderef2text( $coderef ); @@ -87,7 +91,12 @@ EOC $regex =~ s/\s+/\\s+/g; $regex = '^\{\s*' . $regex . '\s*\}$'; - like($deparsed, qr/$regex/, $desc); + like($deparsed, qr/$regex/, $desc) + or diag "=============================================\n" + . "CODE:\n--------\n$input\n--------\n" + . "EXPECTED:\n--------\n{\n$expected\n}\n--------\n" + . "GOT:\n--------\n$deparsed\n--------\n" + . "=============================================\n"; } } @@ -143,6 +152,21 @@ $a =~ s/-e syntax OK\n//g; is($a, "use constant ('PI', 4);\n", "Proxy Constant Subroutines must not show up as (incorrect) prototypes"); +$a = `$^X $path "-MO=Deparse" -e "sub foo(){1}" 2>&1`; +$a =~ s/-e syntax OK\n//g; +is($a, "sub foo () {\n 1;\n}\n", + "Main prog consisting of just a constant (via empty proto)"); + +$a = readpipe qq|$^X $path "-MO=Deparse"| + .qq| -e "package F; sub f(){0} sub s{}"| + .qq| -e "#line 123 four-five-six"| + .qq| -e "package G; sub g(){0} sub s{}" 2>&1|; +$a =~ s/-e syntax OK\n//g; +like($a, qr/sub F::f \(\) \{\s*0;?\s*}/, + "Constant is dumped in package in which other subs are dumped"); +unlike($a, qr/sub g/, + "Constant is not dumped in package in which other subs are not dumped"); + #Re: perlbug #35857, patch #24505 #handle warnings::register-ed packages properly. package B::Deparse::Wrapper; @@ -363,20 +387,20 @@ EOCODP # CORE::no $a = readpipe qq`$^X $path "-MO=Deparse" -Xe ` .qq`"use feature q|:all|; my sub no; CORE::no less" 2>&1`; -like($a, qr/my sub no;\nCORE::no less;/, +like($a, qr/my sub no;\n.*CORE::no less;/s, 'CORE::no after my sub no'); # CORE::use $a = readpipe qq`$^X $path "-MO=Deparse" -Xe ` .qq`"use feature q|:all|; my sub use; CORE::use less" 2>&1`; -like($a, qr/my sub use;\nCORE::use less;/, +like($a, qr/my sub use;\n.*CORE::use less;/s, 'CORE::use after my sub use'); # CORE::__DATA__ $a = readpipe qq`$^X $path "-MO=Deparse" -Xe ` .qq`"use feature q|:all|; my sub __DATA__; ` .qq`CORE::__DATA__" 2>&1`; -like($a, qr/my sub __DATA__;\n.*\nCORE::__DATA__/s, +like($a, qr/my sub __DATA__;\n.*CORE::__DATA__/s, 'CORE::__DATA__ after my sub __DATA__'); # sub declarations @@ -522,6 +546,22 @@ unlike runperl(stderr => 1, switches => [ '-MO=-qq,Deparse', $path, '-w' ], qr'Use of uninitialized value', 'no warnings for undefined sub'; +is runperl(stderr => 1, switches => [ '-MO=-qq,Deparse', $path ], + prog => 'sub f { 1; } BEGIN { *g = \&f; }'), + "sub f {\n 1;\n}\nsub BEGIN {\n *g = \\&f;\n}\n", + "sub glob alias shouldn't impede emitting original sub"; + +is runperl(stderr => 1, switches => [ '-MO=-qq,Deparse', $path ], + prog => 'package Foo; sub f { 1; } BEGIN { *g = \&f; }'), + "package Foo;\nsub f {\n 1;\n}\nsub BEGIN {\n *g = \\&f;\n}\n", + "sub glob alias outside main shouldn't impede emitting original sub"; + +is runperl(stderr => 1, switches => [ '-MO=-qq,Deparse', $path ], + prog => 'package Foo; sub f { 1; } BEGIN { *Bar::f = \&f; }'), + "package Foo;\nsub f {\n 1;\n}\nsub BEGIN {\n *Bar::f = \\&f;\n}\n", + "sub glob alias in separate package shouldn't impede emitting original sub"; + + done_testing($tests); __DATA__ @@ -780,12 +820,38 @@ print $_ foreach (reverse 1, 2..5); our @ary; @ary = split(' ', 'foo', 0); #### +my @ary; +@ary = split(' ', 'foo', 0); +#### # Split to our array our @array = split(//, 'foo', 0); #### # Split to my array my @array = split(//, 'foo', 0); #### +our @array; +my $c; +@array = split(/x(?{ $c++; })y/, 'foo', 0); +#### +my($x, $y, $p); +our $c; +($x, $y) = split(/$p(?{ $c++; })y/, 'foo', 2); +#### +our @ary; +my $pat; +@ary = split(/$pat/, 'foo', 0); +#### +my @ary; +our $pat; +@ary = split(/$pat/, 'foo', 0); +#### +our @array; +my $pat; +local @array = split(/$pat/, 'foo', 0); +#### +our $pat; +my @array = split(/$pat/, 'foo', 0); +#### # bug #40055 do { () }; #### @@ -1372,11 +1438,48 @@ s/X//r; use feature 'unicode_strings'; s/X//d; #### -# all the flags (tr///) -tr/X/Y/c; -tr/X//d; -tr/X//s; -tr/X//r; +# tr/// with all the flags: empty replacement +tr/B-G//; +tr/B-G//c; +tr/B-G//d; +tr/B-G//s; +tr/B-G//cd; +tr/B-G//ds; +tr/B-G//cs; +tr/B-G//cds; +tr/B-G//r; +#### +# tr/// with all the flags: short replacement +tr/B-G/b/; +tr/B-G/b/c; +tr/B-G/b/d; +tr/B-G/b/s; +tr/B-G/b/cd; +tr/B-G/b/ds; +tr/B-G/b/cs; +tr/B-G/b/cds; +tr/B-G/b/r; +#### +# tr/// with all the flags: equal length replacement +tr/B-G/b-g/; +tr/B-G/b-g/c; +tr/B-G/b-g/s; +tr/B-G/b-g/cs; +tr/B-G/b-g/r; +#### +# tr with extended table (/c) +tr/\000-\375/AB/c; +tr/\000-\375/A-C/c; +tr/\000-\375/A-D/c; +tr/\000-\375/A-I/c; +tr/\000-\375/AB/cd; +tr/\000-\375/A-C/cd; +tr/\000-\375/A-D/cd; +tr/\000-\375/A-I/cd; +tr/\000-\375/AB/cds; +tr/\000-\375/A-C/cds; +tr/\000-\375/A-D/cds; +tr/\000-\375/A-I/cds; #### # [perl #119807] s//\(3)/ge should not warn when deparsed (\3 warns) s/foo/\(3);/eg; @@ -1941,36 +2044,28 @@ my($a, $b, $c) = @_; #### # SKIP ?$] < 5.017004 && "lexical subs not implemented on this Perl version" # lexical subroutine -use feature 'lexical_subs'; +# CONTEXT use feature 'lexical_subs'; no warnings "experimental::lexical_subs"; my sub f {} print f(); >>>> -use feature 'lexical_subs'; -BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x55\x15"} +BEGIN {${^WARNING_BITS} = "\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x55\x55"} my sub f { - BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x15"} } -BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x15"} print f(); #### # SKIP ?$] < 5.017004 && "lexical subs not implemented on this Perl version" # lexical "state" subroutine -use feature 'state', 'lexical_subs'; +# CONTEXT use feature 'state', 'lexical_subs'; no warnings 'experimental::lexical_subs'; state sub f {} print f(); >>>> -use feature 'lexical_subs'; -BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x55\x15"} -CORE::state sub f { - BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x15"} - use feature 'state'; +BEGIN {${^WARNING_BITS} = "\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x55\x55"} +state sub f { } -BEGIN {${^WARNING_BITS} = "\x54\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x54\x55\x55\x15"} -use feature 'state'; print f(); #### # SKIP ?$] < 5.017004 && "lexical subs not implemented on this Perl version" @@ -2461,12 +2556,17 @@ my $e = delete $h{'foo'}[$i]; #### # multideref with leading expression my $r; -my $x = ($r // [])->{'foo'}[0]; +my $x = +($r // [])->{'foo'}[0]; #### # multideref with complex middle index my(%h, $i, $j, $k); my $x = $h{'foo'}[$i + $j]{$k}; #### +# multideref with trailing non-simple index that initially looks simple +# (i.e. the constant "3") +my($r, $i, $j, $k); +my $x = +($r || {})->{'foo'}[$i + $j]{3 + $k}; +#### # chdir chdir 'file'; chdir FH; @@ -2488,3 +2588,478 @@ $_ ^= $_; $_ |.= $_; $_ &.= $_; $_ ^.= $_; +#### +#### +# Should really use 'no warnings "experimental::signatures"', +# but it doesn't yet deparse correctly. +# anon subs used because this test framework doesn't deparse named subs +# in the DATA code snippets. +# +# general signature +no warnings; +use feature 'signatures'; +my $x; +sub ($a, $, $b = $glo::bal, $c = $a, $d = 'foo', $e = -37, $f = 0, $g = 1, $h = undef, $i = $a + 1, $j = /foo/, @) { + $x++; +} +; +$x++; +#### +# Signature and prototype +no warnings; +use feature 'signatures'; +my $x; +my $f = sub : prototype($$) ($a, $b) { + $x++; +} +; +$x++; +#### +# Signature and prototype and attrs +no warnings; +use feature 'signatures'; +my $x; +my $f = sub : prototype($$) lvalue ($a, $b) { + $x++; +} +; +$x++; +#### +# Signature and attrs +no warnings; +use feature 'signatures'; +my $x; +my $f = sub : lvalue method ($a, $b) { + $x++; +} +; +$x++; +#### +# named array slurp, null body +no warnings; +use feature 'signatures'; +sub (@a) { + ; +} +; +#### +# named hash slurp +no warnings; +use feature 'signatures'; +sub ($key, %h) { + $h{$key}; +} +; +#### +# anon hash slurp +no warnings; +use feature 'signatures'; +sub ($a, %) { + $a; +} +; +#### +# parenthesised default arg +no warnings; +use feature 'signatures'; +sub ($a, $b = (/foo/), $c = 1) { + $a + $b + $c; +} +; +#### +# parenthesised default arg with TARGMY +no warnings; +use feature 'signatures'; +sub ($a, $b = ($a + 1), $c = 1) { + $a + $b + $c; +} +; +#### +# empty default +no warnings; +use feature 'signatures'; +sub ($a, $=) { + $a; +} +; +#### +# padrange op within pattern code blocks +/(?{ my($x, $y) = (); })/; +my $a; +/$a(?{ my($x, $y) = (); })/; +my $r1 = qr/(?{ my($x, $y) = (); })/; +my $r2 = qr/$a(?{ my($x, $y) = (); })/; +#### +# don't remove pattern whitespace escapes +/a\ b/; +/a\ b/x; +/a\ b/; +/a\ b/x; +#### +# my attributes +my $s1 :foo(f1, f2) bar(b1, b2); +my @a1 :foo(f1, f2) bar(b1, b2); +my %h1 :foo(f1, f2) bar(b1, b2); +my($s2, @a2, %h2) :foo(f1, f2) bar(b1, b2); +#### +# my class attributes +package Foo::Bar; +my Foo::Bar $s1 :foo(f1, f2) bar(b1, b2); +my Foo::Bar @a1 :foo(f1, f2) bar(b1, b2); +my Foo::Bar %h1 :foo(f1, f2) bar(b1, b2); +my Foo::Bar ($s2, @a2, %h2) :foo(f1, f2) bar(b1, b2); +package main; +my Foo::Bar $s3 :foo(f1, f2) bar(b1, b2); +my Foo::Bar @a3 :foo(f1, f2) bar(b1, b2); +my Foo::Bar %h3 :foo(f1, f2) bar(b1, b2); +my Foo::Bar ($s4, @a4, %h4) :foo(f1, f2) bar(b1, b2); +#### +# avoid false positives in my $x :attribute +'attributes'->import('main', \my $x1, 'foo(bar)'), my $y1; +'attributes'->import('Fooo', \my $x2, 'foo(bar)'), my $y2; +#### +# hash slices and hash key/value slices +my(@a, %h); +our(@oa, %oh); +@a = @h{'foo', 'bar'}; +@a = %h{'foo', 'bar'}; +@a = delete @h{'foo', 'bar'}; +@a = delete %h{'foo', 'bar'}; +@oa = @oh{'foo', 'bar'}; +@oa = %oh{'foo', 'bar'}; +@oa = delete @oh{'foo', 'bar'}; +@oa = delete %oh{'foo', 'bar'}; +#### +# keys optimised away in void and scalar context +no warnings; +; +our %h1; +my($x, %h2); +%h1; +keys %h1; +$x = %h1; +$x = keys %h1; +%h2; +keys %h2; +$x = %h2; +$x = keys %h2; +#### +# eq,const optimised away for (index() == -1) +my($a, $b); +our $c; +$c = index($a, $b) == 2; +$c = rindex($a, $b) == 2; +$c = index($a, $b) == -1; +$c = rindex($a, $b) == -1; +$c = index($a, $b) != -1; +$c = rindex($a, $b) != -1; +$c = (index($a, $b) == -1); +$c = (rindex($a, $b) == -1); +$c = (index($a, $b) != -1); +$c = (rindex($a, $b) != -1); +#### +# eq,const,sassign,madmy optimised away for (index() == -1) +my($a, $b); +my $c; +$c = index($a, $b) == 2; +$c = rindex($a, $b) == 2; +$c = index($a, $b) == -1; +$c = rindex($a, $b) == -1; +$c = index($a, $b) != -1; +$c = rindex($a, $b) != -1; +$c = (index($a, $b) == -1); +$c = (rindex($a, $b) == -1); +$c = (index($a, $b) != -1); +$c = (rindex($a, $b) != -1); +#### +# plain multiconcat +my($a, $b, $c, $d, @a); +$d = length $a . $b . $c; +$d = length($a) . $b . $c; +print '' . $a; +push @a, ($a . '') * $b; +unshift @a, "$a" * ($b . ''); +print $a . 'x' . $b . $c; +print $a . 'x' . $b . $c, $d; +print $b . $c . ($a . $b); +print $b . $c . ($a . $b); +print $b . $c . @a; +print $a . "\x{100}"; +#### +# double-quoted multiconcat +my($a, $b, $c, $d, @a); +print "${a}x\x{100}$b$c"; +print "$a\Q$b\E$c\Ua$a\E\Lb$b\uc$c\E$a${b}c$c"; +print "A=$a[length 'b' . $c . 'd'] b=$b"; +print "A=@a B=$b"; +print "\x{101}$a\x{100}"; +$a = qr/\Q +$b $c +\x80 +\x{100} +\E$c +/; +#### +# sprintf multiconcat +my($a, $b, $c, $d, @a); +print sprintf("%s%s%%%sx%s\x{100}%s", $a, $b, $c, scalar @a, $d); +#### +# multiconcat with lexical assign +my($a, $b, $c, $d, $e, @a); +$d = 'foo' . $a; +$d = "foo$a"; +$d = $a . ''; +$d = 'foo' . $a . 'bar'; +$d = $a . $b; +$d = $a . $b . $c; +$d = $a . $b . $c . @a; +$e = ($d = $a . $b . $c); +$d = !$a . $b . $c; +$a = $b . $c . ($a . $b); +$e = f($d = !$a . $b) . $c; +$d = "${a}x\x{100}$b$c"; +f($d = !$a . $b . $c); +#### +# multiconcat with lexical my +my($a, $b, $c, $d, $e, @a); +my $d1 = 'foo' . $a; +my $d2 = "foo$a"; +my $d3 = $a . ''; +my $d4 = 'foo' . $a . 'bar'; +my $d5 = $a . $b; +my $d6 = $a . $b . $c; +my $e7 = ($d = $a . $b . $c); +my $d8 = !$a . $b . $c; +my $d9 = $b . $c . ($a . $b); +my $da = f($d = !$a . $b) . $c; +my $dc = "${a}x\x{100}$b$c"; +f(my $db = !$a . $b . $c); +my $dd = $a . $b . $c . @a; +#### +# multiconcat with lexical append +my($a, $b, $c, $d, $e, @a); +$d .= ''; +$d .= $a; +$d .= "$a"; +$d .= 'foo' . $a; +$d .= "foo$a"; +$d .= $a . ''; +$d .= 'foo' . $a . 'bar'; +$d .= $a . $b; +$d .= $a . $b . $c; +$d .= $a . $b . @a; +$e .= ($d = $a . $b . $c); +$d .= !$a . $b . $c; +$a .= $b . $c . ($a . $b); +$e .= f($d .= !$a . $b) . $c; +f($d .= !$a . $b . $c); +$d .= "${a}x\x{100}$b$c"; +#### +# multiconcat with expression assign +my($a, $b, $c, @a); +our($d, $e); +$d = 'foo' . $a; +$d = "foo$a"; +$d = $a . ''; +$d = 'foo' . $a . 'bar'; +$d = $a . $b; +$d = $a . $b . $c; +$d = $a . $b . @a; +$e = ($d = $a . $b . $c); +$a["-$b-"] = !$a . $b . $c; +$a[$b]{$c}{$d ? $a : $b . $c} = !$a . $b . $c; +$a = $b . $c . ($a . $b); +$e = f($d = !$a . $b) . $c; +$d = "${a}x\x{100}$b$c"; +f($d = !$a . $b . $c); +#### +# multiconcat with expression concat +my($a, $b, $c, @a); +our($d, $e); +$d .= 'foo' . $a; +$d .= "foo$a"; +$d .= $a . ''; +$d .= 'foo' . $a . 'bar'; +$d .= $a . $b; +$d .= $a . $b . $c; +$d .= $a . $b . @a; +$e .= ($d .= $a . $b . $c); +$a["-$b-"] .= !$a . $b . $c; +$a[$b]{$c}{$d ? $a : $b . $c} .= !$a . $b . $c; +$a .= $b . $c . ($a . $b); +$e .= f($d .= !$a . $b) . $c; +$d .= "${a}x\x{100}$b$c"; +f($d .= !$a . $b . $c); +#### +# multiconcat with CORE::sprintf +# CONTEXT sub sprintf {} +my($a, $b); +my $x = CORE::sprintf('%s%s', $a, $b); +#### +# multiconcat with backticks +my($a, $b); +our $x; +$x = `$a-$b`; +#### +# multiconcat within qr// +my($r, $a, $b); +$r = qr/abc\Q$a-$b\Exyz/; +#### +# tr with unprintable characters +my $str; +$str = 'foo'; +$str =~ tr/\cA//; +#### +# CORE::foo special case in bareword parsing +print $CORE::foo, $CORE::foo::bar; +print @CORE::foo, @CORE::foo::bar; +print %CORE::foo, %CORE::foo::bar; +print $CORE::foo{'a'}, $CORE::foo::bar{'a'}; +print &CORE::foo, &CORE::foo::bar; +print &CORE::foo(), &CORE::foo::bar(); +print \&CORE::foo, \&CORE::foo::bar; +print *CORE::foo, *CORE::foo::bar; +print stat CORE::foo::, stat CORE::foo::bar; +print CORE::foo:: 1; +print CORE::foo::bar 2; +#### +# trailing colons on glob names +no strict 'vars'; +$Foo::::baz = 1; +print $foo, $foo::, $foo::::; +print @foo, @foo::, @foo::::; +print %foo, %foo::, %foo::::; +print $foo{'a'}, $foo::{'a'}, $foo::::{'a'}; +print &foo, &foo::, &foo::::; +print &foo(), &foo::(), &foo::::(); +print \&foo, \&foo::, \&foo::::; +print *foo, *foo::, *foo::::; +print stat Foo, stat Foo::::; +print Foo 1; +print Foo:::: 2; +#### +# trailing colons mixed with CORE +no strict 'vars'; +print $CORE, $CORE::, $CORE::::; +print @CORE, @CORE::, @CORE::::; +print %CORE, %CORE::, %CORE::::; +print $CORE{'a'}, $CORE::{'a'}, $CORE::::{'a'}; +print &CORE, &CORE::, &CORE::::; +print &CORE(), &CORE::(), &CORE::::(); +print \&CORE, \&CORE::, \&CORE::::; +print *CORE, *CORE::, *CORE::::; +print stat CORE, stat CORE::::; +print CORE 1; +print CORE:::: 2; +print $CORE::foo, $CORE::foo::, $CORE::foo::::; +print @CORE::foo, @CORE::foo::, @CORE::foo::::; +print %CORE::foo, %CORE::foo::, %CORE::foo::::; +print $CORE::foo{'a'}, $CORE::foo::{'a'}, $CORE::foo::::{'a'}; +print &CORE::foo, &CORE::foo::, &CORE::foo::::; +print &CORE::foo(), &CORE::foo::(), &CORE::foo::::(); +print \&CORE::foo, \&CORE::foo::, \&CORE::foo::::; +print *CORE::foo, *CORE::foo::, *CORE::foo::::; +print stat CORE::foo::, stat CORE::foo::::; +print CORE::foo:: 1; +print CORE::foo:::: 2; +#### +# \&foo +my sub foo { + 1; +} +no strict 'vars'; +print \&main::foo; +print \&{foo}; +print \&bar; +use strict 'vars'; +print \&main::foo; +print \&{foo}; +print \&main::bar; +#### +# exists(&foo) +my sub foo { + 1; +} +no strict 'vars'; +print exists &main::foo; +print exists &{foo}; +print exists &bar; +use strict 'vars'; +print exists &main::foo; +print exists &{foo}; +print exists &main::bar; +# precedence of optimised-away 'keys' (OPpPADHV_ISKEYS/OPpRV2HV_ISKEYS) +my($r1, %h1, $res); +our($r2, %h2); +$res = keys %h1; +$res = keys %h2; +$res = keys %$r1; +$res = keys %$r2; +$res = keys(%h1) / 2 - 1; +$res = keys(%h2) / 2 - 1; +$res = keys(%$r1) / 2 - 1; +$res = keys(%$r2) / 2 - 1; +#### +# ditto in presence of sub keys {} +# CONTEXT sub keys {} +no warnings; +my($r1, %h1, $res); +our($r2, %h2); +CORE::keys %h1; +CORE::keys(%h1) / 2; +$res = CORE::keys %h1; +$res = CORE::keys %h2; +$res = CORE::keys %$r1; +$res = CORE::keys %$r2; +$res = CORE::keys(%h1) / 2 - 1; +$res = CORE::keys(%h2) / 2 - 1; +$res = CORE::keys(%$r1) / 2 - 1; +$res = CORE::keys(%$r2) / 2 - 1; +#### +# concat: STACKED: ambiguity between .= and optimised nested +my($a, $b); +$b = $a . $a . $a; +(($a .= $a) .= $a) .= $a; +#### +# multiconcat: $$ within string +my($a, $x); +$x = "${$}abc"; +$x = "\$$a"; +#### +# single state aggregate assignment +# CONTEXT use feature "state"; +state @a = (1, 2, 3); +state %h = ('a', 1, 'b', 2); +#### +# state var with attribute +# CONTEXT use feature "state"; +state $x :shared; +state $y :shared = 1; +state @a :shared; +state @b :shared = (1, 2); +state %h :shared; +state %i :shared = ('a', 1, 'b', 2); +#### +# \our @a shouldn't be a list +my $r = \our @a; +my(@l) = \our((@b)); +@l = \our(@c, @d); +#### +# postfix $# +our(@b, $s, $l); +$l = (\my @a)->$#*; +(\@b)->$#* = 1; +++(\my @c)->$#*; +$l = $#a; +$#a = 1; +$l = $#b; +$#b = 1; +my $r; +$l = $r->$#*; +$r->$#* = 1; +$l = $#{@$r;}; +$#{$r;} = 1; +$l = $s->$#*; +$s->$#* = 1; +$l = $#{@$s;}; +$#{$s;} = 1; diff --git a/gnu/usr.bin/perl/lib/B/Op_private.pm b/gnu/usr.bin/perl/lib/B/Op_private.pm index 9ab71ae9959..58953e1eee4 100644 --- a/gnu/usr.bin/perl/lib/B/Op_private.pm +++ b/gnu/usr.bin/perl/lib/B/Op_private.pm @@ -118,7 +118,7 @@ package B::Op_private; our %bits; -our $VERSION = "5.024003"; +our $VERSION = "5.028001"; $bits{$_}{3} = 'OPpENTERSUB_AMPER' for qw(entersub rv2cv); $bits{$_}{6} = 'OPpENTERSUB_DB' for qw(entersub rv2cv); @@ -130,14 +130,15 @@ $bits{$_}{2} = 'OPpFT_STACKED' for qw(ftatime ftbinary ftblk ftchr ftctime ftdir $bits{$_}{3} = 'OPpFT_STACKING' for qw(ftatime ftbinary ftblk ftchr ftctime ftdir fteexec fteowned fteread ftewrite ftfile ftis ftlink ftmtime ftpipe ftrexec ftrowned ftrread ftrwrite ftsgid ftsize ftsock ftsuid ftsvtx fttext fttty ftzero); $bits{$_}{1} = 'OPpHINT_STRICT_REFS' for qw(entersub multideref rv2av rv2cv rv2gv rv2hv rv2sv); $bits{$_}{5} = 'OPpHUSH_VMSISH' for qw(dbstate nextstate); +$bits{$_}{6} = 'OPpINDEX_BOOLNEG' for qw(index rindex); $bits{$_}{1} = 'OPpITER_REVERSED' for qw(enteriter iter); $bits{$_}{7} = 'OPpLVALUE' for qw(leave leaveloop); $bits{$_}{6} = 'OPpLVAL_DEFER' for qw(aelem helem multideref); -$bits{$_}{7} = 'OPpLVAL_INTRO' for qw(aelem aslice cond_expr delete enteriter entersub gvsv helem hslice list lvavref lvref lvrefslice multideref padav padhv padrange padsv pushmark refassign rv2av rv2gv rv2hv rv2sv); +$bits{$_}{7} = 'OPpLVAL_INTRO' for qw(aelem aslice cond_expr delete enteriter entersub gvsv helem hslice list lvavref lvref lvrefslice multiconcat multideref padav padhv padrange padsv pushmark refassign rv2av rv2gv rv2hv rv2sv split); $bits{$_}{2} = 'OPpLVREF_ELEM' for qw(lvref refassign); $bits{$_}{3} = 'OPpLVREF_ITER' for qw(lvref refassign); -$bits{$_}{3} = 'OPpMAYBE_LVSUB' for qw(aassign aelem aslice av2arylen helem hslice keys kvaslice kvhslice multideref padav padhv pos rv2av rv2gv rv2hv substr vec); -$bits{$_}{4} = 'OPpMAYBE_TRUEBOOL' for qw(padhv rv2hv); +$bits{$_}{3} = 'OPpMAYBE_LVSUB' for qw(aassign aelem akeys aslice av2arylen avhvswitch helem hslice keys kvaslice kvhslice multideref padav padhv pos rv2av rv2gv rv2hv substr values vec); +$bits{$_}{4} = 'OPpMAYBE_TRUEBOOL' for qw(padhv ref rv2hv); $bits{$_}{7} = 'OPpOFFBYONE' for qw(caller runcv wantarray); $bits{$_}{5} = 'OPpOPEN_IN_CRLF' for qw(backtick open); $bits{$_}{4} = 'OPpOPEN_IN_RAW' for qw(backtick open); @@ -147,9 +148,8 @@ $bits{$_}{6} = 'OPpOUR_INTRO' for qw(enteriter gvsv rv2av rv2hv rv2sv split); $bits{$_}{6} = 'OPpPAD_STATE' for qw(lvavref lvref padav padhv padsv pushmark refassign); $bits{$_}{7} = 'OPpPV_IS_UTF8' for qw(dump goto last next redo); $bits{$_}{6} = 'OPpREFCOUNTED' for qw(leave leaveeval leavesub leavesublv leavewrite); -$bits{$_}{6} = 'OPpRUNTIME' for qw(match pushre qr subst substcont); $bits{$_}{2} = 'OPpSLICEWARNING' for qw(aslice hslice padav padhv rv2av rv2hv); -$bits{$_}{4} = 'OPpTARGET_MY' for qw(abs add atan2 chdir chmod chomp chown chr chroot concat cos crypt divide exec exp flock getpgrp getppid getpriority hex i_add i_divide i_modulo i_multiply i_subtract index int kill left_shift length link log mkdir modulo multiply nbit_and nbit_or nbit_xor ncomplement oct ord pow push rand rename right_shift rindex rmdir schomp scomplement setpgrp setpriority sin sleep sqrt srand stringify subtract symlink system time unlink unshift utime wait waitpid); +$bits{$_}{4} = 'OPpTARGET_MY' for qw(abs add atan2 chdir chmod chomp chown chr chroot concat cos crypt divide exec exp flock getpgrp getppid getpriority hex i_add i_divide i_modulo i_multiply i_subtract index int kill left_shift length link log mkdir modulo multiconcat multiply nbit_and nbit_or nbit_xor ncomplement oct ord pow push rand rename right_shift rindex rmdir schomp scomplement setpgrp setpriority sin sleep sqrt srand stringify subtract symlink system time unlink unshift utime wait waitpid); $bits{$_}{5} = 'OPpTRANS_COMPLEMENT' for qw(trans transr); $bits{$_}{7} = 'OPpTRANS_DELETE' for qw(trans transr); $bits{$_}{0} = 'OPpTRANS_FROM_UTF' for qw(trans transr); @@ -157,7 +157,7 @@ $bits{$_}{6} = 'OPpTRANS_GROWS' for qw(trans transr); $bits{$_}{2} = 'OPpTRANS_IDENTICAL' for qw(trans transr); $bits{$_}{3} = 'OPpTRANS_SQUASH' for qw(trans transr); $bits{$_}{1} = 'OPpTRANS_TO_UTF' for qw(trans transr); -$bits{$_}{5} = 'OPpTRUEBOOL' for qw(padhv rv2hv); +$bits{$_}{5} = 'OPpTRUEBOOL' for qw(grepwhile index length padav padhv pos ref rindex rv2av rv2hv subst); my @bf = ( { @@ -175,6 +175,13 @@ my @bf = ( bitmask => 3, }, { + label => 'offset', + mask_def => 'OPpAVHVSWITCH_MASK', + bitmin => 0, + bitmax => 1, + bitmask => 3, + }, + { label => '-', mask_def => 'OPpARG3_MASK', bitmin => 0, @@ -189,7 +196,7 @@ my @bf = ( bitmask => 15, }, { - label => '-', + label => 'range', mask_def => 'OPpPADRANGE_COUNTMASK', bitcount_def => 'OPpPADRANGE_COUNTSHIFT', bitmin => 0, @@ -197,12 +204,23 @@ my @bf = ( bitmask => 127, }, { - label => '-', + label => 'key', bitmin => 0, bitmax => 7, bitmask => 255, }, { + mask_def => 'OPpARGELEM_MASK', + bitmin => 1, + bitmax => 2, + bitmask => 6, + enum => [ + 0, 'OPpARGELEM_SV', 'SV', + 1, 'OPpARGELEM_AV', 'AV', + 2, 'OPpARGELEM_HV', 'HV', + ], + }, + { mask_def => 'OPpDEREF', bitmin => 4, bitmax => 5, @@ -227,54 +245,58 @@ my @bf = ( }, ); -@{$bits{aassign}}{6,5,4,1,0} = ('OPpASSIGN_COMMON_SCALAR', 'OPpASSIGN_COMMON_RC1', 'OPpASSIGN_COMMON_AGG', $bf[1], $bf[1]); +@{$bits{aassign}}{6,5,4,2,1,0} = ('OPpASSIGN_COMMON_SCALAR', 'OPpASSIGN_COMMON_RC1', 'OPpASSIGN_COMMON_AGG', 'OPpASSIGN_TRUEBOOL', $bf[1], $bf[1]); $bits{abs}{0} = $bf[0]; -@{$bits{accept}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{accept}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{add}}{1,0} = ($bf[1], $bf[1]); $bits{aeach}{0} = $bf[0]; -@{$bits{aelem}}{5,4,1,0} = ($bf[6], $bf[6], $bf[1], $bf[1]); -@{$bits{aelemfast}}{7,6,5,4,3,2,1,0} = ($bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5]); -@{$bits{aelemfast_lex}}{7,6,5,4,3,2,1,0} = ($bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5]); +@{$bits{aelem}}{5,4,1,0} = ($bf[8], $bf[8], $bf[1], $bf[1]); +@{$bits{aelemfast}}{7,6,5,4,3,2,1,0} = ($bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6]); +@{$bits{aelemfast_lex}}{7,6,5,4,3,2,1,0} = ($bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6], $bf[6]); $bits{akeys}{0} = $bf[0]; $bits{alarm}{0} = $bf[0]; $bits{and}{0} = $bf[0]; $bits{andassign}{0} = $bf[0]; $bits{anonconst}{0} = $bf[0]; -@{$bits{anonhash}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{anonlist}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{atan2}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{anonhash}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{anonlist}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +$bits{argcheck}{0} = $bf[0]; +$bits{argdefelem}{0} = $bf[0]; +@{$bits{argelem}}{2,1,0} = ($bf[7], $bf[7], $bf[0]); +@{$bits{atan2}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{av2arylen}{0} = $bf[0]; $bits{avalues}{0} = $bf[0]; +@{$bits{avhvswitch}}{1,0} = ($bf[2], $bf[2]); $bits{backtick}{0} = $bf[0]; -@{$bits{bind}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{binmode}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{bind}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{binmode}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{bit_and}}{1,0} = ($bf[1], $bf[1]); @{$bits{bit_or}}{1,0} = ($bf[1], $bf[1]); @{$bits{bit_xor}}{1,0} = ($bf[1], $bf[1]); -@{$bits{bless}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{caller}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{chdir}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{chmod}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{bless}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{caller}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{chdir}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{chmod}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{chomp}{0} = $bf[0]; $bits{chop}{0} = $bf[0]; -@{$bits{chown}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{chown}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{chr}{0} = $bf[0]; $bits{chroot}{0} = $bf[0]; -@{$bits{close}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{close}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{closedir}{0} = $bf[0]; $bits{complement}{0} = $bf[0]; -@{$bits{concat}}{1,0} = ($bf[1], $bf[1]); +@{$bits{concat}}{6,1,0} = ('OPpCONCAT_NESTED', $bf[1], $bf[1]); $bits{cond_expr}{0} = $bf[0]; -@{$bits{connect}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{connect}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{const}}{6,4,3,2,1} = ('OPpCONST_BARE', 'OPpCONST_ENTERED', 'OPpCONST_STRICT', 'OPpCONST_SHORTCIRCUIT', 'OPpCONST_NOVER'); @{$bits{coreargs}}{7,6,1,0} = ('OPpCOREARGS_PUSHMARK', 'OPpCOREARGS_SCALARMOD', 'OPpCOREARGS_DEREF2', 'OPpCOREARGS_DEREF1'); $bits{cos}{0} = $bf[0]; -@{$bits{crypt}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{crypt}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{dbmclose}{0} = $bf[0]; -@{$bits{dbmopen}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{dbmopen}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{defined}{0} = $bf[0]; -@{$bits{delete}}{6,0} = ('OPpSLICE', $bf[0]); -@{$bits{die}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{delete}}{6,5,0} = ('OPpSLICE', 'OPpKVSLICE', $bf[0]); +@{$bits{die}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{divide}}{1,0} = ($bf[1], $bf[1]); $bits{dofile}{0} = $bf[0]; $bits{dor}{0} = $bf[0]; @@ -284,23 +306,23 @@ $bits{each}{0} = $bf[0]; @{$bits{entereval}}{5,4,3,2,1,0} = ('OPpEVAL_RE_REPARSING', 'OPpEVAL_COPHH', 'OPpEVAL_BYTES', 'OPpEVAL_UNICODE', 'OPpEVAL_HAS_HH', $bf[0]); $bits{entergiven}{0} = $bf[0]; $bits{enteriter}{3} = 'OPpITER_DEF'; -@{$bits{entersub}}{5,4,0} = ($bf[6], $bf[6], 'OPpENTERSUB_INARGS'); +@{$bits{entersub}}{5,4,0} = ($bf[8], $bf[8], 'OPpENTERSUB_INARGS'); $bits{entertry}{0} = $bf[0]; $bits{enterwhen}{0} = $bf[0]; -@{$bits{enterwrite}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{eof}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{enterwrite}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{eof}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{eq}}{1,0} = ($bf[1], $bf[1]); -@{$bits{exec}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{exec}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{exists}}{6,0} = ('OPpEXISTS_SUB', $bf[0]); -@{$bits{exit}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{exit}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{exp}{0} = $bf[0]; $bits{fc}{0} = $bf[0]; -@{$bits{fcntl}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{fileno}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{fcntl}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{fileno}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{flip}{0} = $bf[0]; -@{$bits{flock}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{flock}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{flop}{0} = $bf[0]; -@{$bits{formline}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{formline}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{ftatime}{0} = $bf[0]; $bits{ftbinary}{0} = $bf[0]; $bits{ftblk}{0} = $bf[0]; @@ -330,32 +352,32 @@ $bits{fttty}{0} = $bf[0]; $bits{ftzero}{0} = $bf[0]; @{$bits{ge}}{1,0} = ($bf[1], $bf[1]); @{$bits{gelem}}{1,0} = ($bf[1], $bf[1]); -@{$bits{getc}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{getc}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{getpeername}{0} = $bf[0]; -@{$bits{getpgrp}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{getpriority}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{getpgrp}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{getpriority}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{getsockname}{0} = $bf[0]; $bits{ggrgid}{0} = $bf[0]; $bits{ggrnam}{0} = $bf[0]; -@{$bits{ghbyaddr}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{ghbyaddr}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{ghbyname}{0} = $bf[0]; -@{$bits{glob}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{gmtime}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{gnbyaddr}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{glob}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{gmtime}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{gnbyaddr}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{gnbyname}{0} = $bf[0]; $bits{goto}{0} = $bf[0]; $bits{gpbyname}{0} = $bf[0]; -@{$bits{gpbynumber}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{gpbynumber}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{gpwnam}{0} = $bf[0]; $bits{gpwuid}{0} = $bf[0]; $bits{grepstart}{0} = $bf[0]; $bits{grepwhile}{0} = $bf[0]; -@{$bits{gsbyname}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{gsbyport}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{gsockopt}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{gsbyname}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{gsbyport}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{gsockopt}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{gt}}{1,0} = ($bf[1], $bf[1]); $bits{gv}{5} = 'OPpEARLY_CV'; -@{$bits{helem}}{5,4,1,0} = ($bf[6], $bf[6], $bf[1], $bf[1]); +@{$bits{helem}}{5,4,1,0} = ($bf[8], $bf[8], $bf[1], $bf[1]); $bits{hex}{0} = $bf[0]; @{$bits{i_add}}{1,0} = ($bf[1], $bf[1]); @{$bits{i_divide}}{1,0} = ($bf[1], $bf[1]); @@ -374,12 +396,12 @@ $bits{i_postinc}{0} = $bf[0]; $bits{i_predec}{0} = $bf[0]; $bits{i_preinc}{0} = $bf[0]; @{$bits{i_subtract}}{1,0} = ($bf[1], $bf[1]); -@{$bits{index}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{index}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{int}{0} = $bf[0]; -@{$bits{ioctl}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{join}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{ioctl}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{join}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{keys}{0} = $bf[0]; -@{$bits{kill}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{kill}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{last}{0} = $bf[0]; $bits{lc}{0} = $bf[0]; $bits{lcfirst}{0} = $bf[0]; @@ -393,9 +415,9 @@ $bits{leavewhen}{0} = $bf[0]; $bits{leavewrite}{0} = $bf[0]; @{$bits{left_shift}}{1,0} = ($bf[1], $bf[1]); $bits{length}{0} = $bf[0]; -@{$bits{link}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{link}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{list}{6} = 'OPpLIST_GUESSED'; -@{$bits{listen}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{listen}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{localtime}{0} = $bf[0]; $bits{lock}{0} = $bf[0]; $bits{log}{0} = $bf[0]; @@ -403,7 +425,7 @@ $bits{log}{0} = $bf[0]; $bits{lstat}{0} = $bf[0]; @{$bits{lt}}{1,0} = ($bf[1], $bf[1]); $bits{lvavref}{0} = $bf[0]; -@{$bits{lvref}}{5,4,0} = ($bf[7], $bf[7], $bf[0]); +@{$bits{lvref}}{5,4,0} = ($bf[9], $bf[9], $bf[0]); $bits{mapstart}{0} = $bf[0]; $bits{mapwhile}{0} = $bf[0]; $bits{method}{0} = $bf[0]; @@ -411,12 +433,13 @@ $bits{method_named}{0} = $bf[0]; $bits{method_redir}{0} = $bf[0]; $bits{method_redir_super}{0} = $bf[0]; $bits{method_super}{0} = $bf[0]; -@{$bits{mkdir}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{mkdir}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{modulo}}{1,0} = ($bf[1], $bf[1]); -@{$bits{msgctl}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{msgget}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{msgrcv}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{msgsnd}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{msgctl}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{msgget}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{msgrcv}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{msgsnd}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{multiconcat}}{6,5,3,0} = ('OPpMULTICONCAT_APPEND', 'OPpMULTICONCAT_FAKE', 'OPpMULTICONCAT_STRINGIFY', $bf[0]); @{$bits{multideref}}{5,4,0} = ('OPpMULTIDEREF_DELETE', 'OPpMULTIDEREF_EXISTS', $bf[0]); @{$bits{multiply}}{1,0} = ($bf[1], $bf[1]); @{$bits{nbit_and}}{1,0} = ($bf[1], $bf[1]); @@ -430,15 +453,16 @@ $bits{next}{0} = $bf[0]; $bits{not}{0} = $bf[0]; $bits{oct}{0} = $bf[0]; $bits{once}{0} = $bf[0]; -@{$bits{open}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{open_dir}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{open}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{open_dir}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{or}{0} = $bf[0]; $bits{orassign}{0} = $bf[0]; $bits{ord}{0} = $bf[0]; -@{$bits{pack}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{padrange}}{6,5,4,3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4], $bf[4], $bf[4], $bf[4]); -@{$bits{padsv}}{5,4} = ($bf[6], $bf[6]); -@{$bits{pipe_op}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{pack}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +$bits{padhv}{0} = 'OPpPADHV_ISKEYS'; +@{$bits{padrange}}{6,5,4,3,2,1,0} = ($bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5], $bf[5]); +@{$bits{padsv}}{5,4} = ($bf[8], $bf[8]); +@{$bits{pipe_op}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{pop}{0} = $bf[0]; $bits{pos}{0} = $bf[0]; $bits{postdec}{0} = $bf[0]; @@ -447,36 +471,36 @@ $bits{postinc}{0} = $bf[0]; $bits{predec}{0} = $bf[0]; $bits{preinc}{0} = $bf[0]; $bits{prototype}{0} = $bf[0]; -@{$bits{push}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{push}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{quotemeta}{0} = $bf[0]; -@{$bits{rand}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{rand}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{range}{0} = $bf[0]; -@{$bits{read}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{read}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{readdir}{0} = $bf[0]; $bits{readline}{0} = $bf[0]; $bits{readlink}{0} = $bf[0]; -@{$bits{recv}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{recv}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{redo}{0} = $bf[0]; $bits{ref}{0} = $bf[0]; -@{$bits{refassign}}{5,4,1,0} = ($bf[7], $bf[7], $bf[1], $bf[1]); +@{$bits{refassign}}{5,4,1,0} = ($bf[9], $bf[9], $bf[1], $bf[1]); $bits{refgen}{0} = $bf[0]; $bits{regcmaybe}{0} = $bf[0]; $bits{regcomp}{0} = $bf[0]; $bits{regcreset}{0} = $bf[0]; -@{$bits{rename}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{rename}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{repeat}}{6,1,0} = ('OPpREPEAT_DOLIST', $bf[1], $bf[1]); $bits{require}{0} = $bf[0]; -@{$bits{reset}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{reset}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{reverse}}{3,0} = ('OPpREVERSE_INPLACE', $bf[0]); $bits{rewinddir}{0} = $bf[0]; @{$bits{right_shift}}{1,0} = ($bf[1], $bf[1]); -@{$bits{rindex}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{rindex}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{rmdir}{0} = $bf[0]; $bits{rv2av}{0} = $bf[0]; @{$bits{rv2cv}}{7,5,0} = ('OPpENTERSUB_NOPAREN', 'OPpMAY_RETURN_CONSTANT', $bf[0]); -@{$bits{rv2gv}}{6,5,4,2,0} = ('OPpALLOW_FAKE', $bf[6], $bf[6], 'OPpDONT_INIT_GV', $bf[0]); -$bits{rv2hv}{0} = $bf[0]; -@{$bits{rv2sv}}{5,4,0} = ($bf[6], $bf[6], $bf[0]); +@{$bits{rv2gv}}{6,5,4,2,0} = ('OPpALLOW_FAKE', $bf[8], $bf[8], 'OPpDONT_INIT_GV', $bf[0]); +$bits{rv2hv}{0} = 'OPpRV2HV_ISKEYS'; +@{$bits{rv2sv}}{5,4,0} = ($bf[8], $bf[8], $bf[0]); @{$bits{sassign}}{7,6,1,0} = ('OPpASSIGN_CV_TO_GV', 'OPpASSIGN_BACKWARDS', $bf[1], $bf[1]); @{$bits{sbit_and}}{1,0} = ($bf[1], $bf[1]); @{$bits{sbit_or}}{1,0} = ($bf[1], $bf[1]); @@ -486,76 +510,76 @@ $bits{schomp}{0} = $bf[0]; $bits{schop}{0} = $bf[0]; @{$bits{scmp}}{1,0} = ($bf[1], $bf[1]); $bits{scomplement}{0} = $bf[0]; -@{$bits{seek}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{seekdir}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{select}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{semctl}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{semget}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{semop}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{send}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{seek}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{seekdir}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{select}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{semctl}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{semget}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{semop}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{send}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{seq}}{1,0} = ($bf[1], $bf[1]); -@{$bits{setpgrp}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{setpriority}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{setpgrp}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{setpriority}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{sge}}{1,0} = ($bf[1], $bf[1]); @{$bits{sgt}}{1,0} = ($bf[1], $bf[1]); $bits{shift}{0} = $bf[0]; -@{$bits{shmctl}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{shmget}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{shmread}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{shmwrite}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{shmctl}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{shmget}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{shmread}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{shmwrite}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{shostent}{0} = $bf[0]; -@{$bits{shutdown}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{shutdown}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{sin}{0} = $bf[0]; @{$bits{sle}}{1,0} = ($bf[1], $bf[1]); -@{$bits{sleep}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{sleep}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{slt}}{1,0} = ($bf[1], $bf[1]); @{$bits{smartmatch}}{1,0} = ($bf[1], $bf[1]); @{$bits{sne}}{1,0} = ($bf[1], $bf[1]); $bits{snetent}{0} = $bf[0]; -@{$bits{socket}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{sockpair}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{sort}}{6,5,4,3,2,1,0} = ('OPpSORT_STABLE', 'OPpSORT_QSORT', 'OPpSORT_DESCEND', 'OPpSORT_INPLACE', 'OPpSORT_REVERSE', 'OPpSORT_INTEGER', 'OPpSORT_NUMERIC'); -@{$bits{splice}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -$bits{split}{7} = 'OPpSPLIT_IMPLIM'; -@{$bits{sprintf}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{socket}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{sockpair}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{sort}}{7,6,4,3,2,1,0} = ('OPpSORT_UNSTABLE', 'OPpSORT_STABLE', 'OPpSORT_DESCEND', 'OPpSORT_INPLACE', 'OPpSORT_REVERSE', 'OPpSORT_INTEGER', 'OPpSORT_NUMERIC'); +@{$bits{splice}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{split}}{4,3,2} = ('OPpSPLIT_ASSIGN', 'OPpSPLIT_LEX', 'OPpSPLIT_IMPLIM'); +@{$bits{sprintf}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{sprotoent}{0} = $bf[0]; $bits{sqrt}{0} = $bf[0]; -@{$bits{srand}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{srand}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{srefgen}{0} = $bf[0]; -@{$bits{sselect}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{sselect}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{sservent}{0} = $bf[0]; -@{$bits{ssockopt}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{ssockopt}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{stat}{0} = $bf[0]; -@{$bits{stringify}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{stringify}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{study}{0} = $bf[0]; $bits{substcont}{0} = $bf[0]; -@{$bits{substr}}{4,2,1,0} = ('OPpSUBSTR_REPL_FIRST', $bf[2], $bf[2], $bf[2]); +@{$bits{substr}}{4,2,1,0} = ('OPpSUBSTR_REPL_FIRST', $bf[3], $bf[3], $bf[3]); @{$bits{subtract}}{1,0} = ($bf[1], $bf[1]); -@{$bits{symlink}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{syscall}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{sysopen}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{sysread}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{sysseek}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{system}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{syswrite}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{tell}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{symlink}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{syscall}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{sysopen}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{sysread}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{sysseek}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{system}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{syswrite}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{tell}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{telldir}{0} = $bf[0]; -@{$bits{tie}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{tie}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{tied}{0} = $bf[0]; -@{$bits{truncate}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{truncate}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{uc}{0} = $bf[0]; $bits{ucfirst}{0} = $bf[0]; -@{$bits{umask}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{umask}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{undef}{0} = $bf[0]; -@{$bits{unlink}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{unpack}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{unshift}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{unlink}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{unpack}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{unshift}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{untie}{0} = $bf[0]; -@{$bits{utime}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{utime}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); $bits{values}{0} = $bf[0]; @{$bits{vec}}{1,0} = ($bf[1], $bf[1]); -@{$bits{waitpid}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); -@{$bits{warn}}{3,2,1,0} = ($bf[3], $bf[3], $bf[3], $bf[3]); +@{$bits{waitpid}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); +@{$bits{warn}}{3,2,1,0} = ($bf[4], $bf[4], $bf[4], $bf[4]); @{$bits{xor}}{1,0} = ($bf[1], $bf[1]); @@ -565,11 +589,18 @@ our %defines = ( OPpARG2_MASK => 3, OPpARG3_MASK => 7, OPpARG4_MASK => 15, + OPpARGELEM_AV => 2, + OPpARGELEM_HV => 4, + OPpARGELEM_MASK => 6, + OPpARGELEM_SV => 0, OPpASSIGN_BACKWARDS => 64, OPpASSIGN_COMMON_AGG => 16, OPpASSIGN_COMMON_RC1 => 32, OPpASSIGN_COMMON_SCALAR => 64, OPpASSIGN_CV_TO_GV => 128, + OPpASSIGN_TRUEBOOL => 4, + OPpAVHVSWITCH_MASK => 3, + OPpCONCAT_NESTED => 64, OPpCONST_BARE => 64, OPpCONST_ENTERED => 16, OPpCONST_NOVER => 2, @@ -603,8 +634,10 @@ our %defines = ( OPpFT_STACKING => 8, OPpHINT_STRICT_REFS => 2, OPpHUSH_VMSISH => 32, + OPpINDEX_BOOLNEG => 64, OPpITER_DEF => 8, OPpITER_REVERSED => 2, + OPpKVSLICE => 32, OPpLIST_GUESSED => 64, OPpLVALUE => 128, OPpLVAL_DEFER => 64, @@ -619,6 +652,9 @@ our %defines = ( OPpMAYBE_LVSUB => 8, OPpMAYBE_TRUEBOOL => 16, OPpMAY_RETURN_CONSTANT => 32, + OPpMULTICONCAT_APPEND => 64, + OPpMULTICONCAT_FAKE => 32, + OPpMULTICONCAT_STRINGIFY => 8, OPpMULTIDEREF_DELETE => 32, OPpMULTIDEREF_EXISTS => 16, OPpOFFBYONE => 128, @@ -627,6 +663,7 @@ our %defines = ( OPpOPEN_OUT_CRLF => 128, OPpOPEN_OUT_RAW => 64, OPpOUR_INTRO => 64, + OPpPADHV_ISKEYS => 1, OPpPADRANGE_COUNTMASK => 127, OPpPADRANGE_COUNTSHIFT => 7, OPpPAD_STATE => 64, @@ -634,17 +671,19 @@ our %defines = ( OPpREFCOUNTED => 64, OPpREPEAT_DOLIST => 64, OPpREVERSE_INPLACE => 8, - OPpRUNTIME => 64, + OPpRV2HV_ISKEYS => 1, OPpSLICE => 64, OPpSLICEWARNING => 4, OPpSORT_DESCEND => 16, OPpSORT_INPLACE => 8, OPpSORT_INTEGER => 2, OPpSORT_NUMERIC => 1, - OPpSORT_QSORT => 32, OPpSORT_REVERSE => 4, OPpSORT_STABLE => 64, - OPpSPLIT_IMPLIM => 128, + OPpSORT_UNSTABLE => 128, + OPpSPLIT_ASSIGN => 16, + OPpSPLIT_IMPLIM => 4, + OPpSPLIT_LEX => 8, OPpSUBSTR_REPL_FIRST => 16, OPpTARGET_MY => 16, OPpTRANS_COMPLEMENT => 32, @@ -659,11 +698,16 @@ our %defines = ( our %labels = ( OPpALLOW_FAKE => 'FAKE', + OPpARGELEM_AV => 'AV', + OPpARGELEM_HV => 'HV', + OPpARGELEM_SV => 'SV', OPpASSIGN_BACKWARDS => 'BKWARD', OPpASSIGN_COMMON_AGG => 'COM_AGG', OPpASSIGN_COMMON_RC1 => 'COM_RC1', OPpASSIGN_COMMON_SCALAR => 'COM_SCALAR', OPpASSIGN_CV_TO_GV => 'CV2GV', + OPpASSIGN_TRUEBOOL => 'BOOL', + OPpCONCAT_NESTED => 'NESTED', OPpCONST_BARE => 'BARE', OPpCONST_ENTERED => 'ENTERED', OPpCONST_NOVER => 'NOVER', @@ -696,8 +740,10 @@ our %labels = ( OPpFT_STACKING => 'FTSTACKING', OPpHINT_STRICT_REFS => 'STRICT', OPpHUSH_VMSISH => 'HUSH', + OPpINDEX_BOOLNEG => 'NEG', OPpITER_DEF => 'DEF', OPpITER_REVERSED => 'REVERSED', + OPpKVSLICE => 'KVSLICE', OPpLIST_GUESSED => 'GUESSED', OPpLVALUE => 'LV', OPpLVAL_DEFER => 'LVDEFER', @@ -711,6 +757,9 @@ our %labels = ( OPpMAYBE_LVSUB => 'LVSUB', OPpMAYBE_TRUEBOOL => 'BOOL?', OPpMAY_RETURN_CONSTANT => 'CONST', + OPpMULTICONCAT_APPEND => 'APPEND', + OPpMULTICONCAT_FAKE => 'FAKE', + OPpMULTICONCAT_STRINGIFY => 'STRINGIFY', OPpMULTIDEREF_DELETE => 'DELETE', OPpMULTIDEREF_EXISTS => 'EXISTS', OPpOFFBYONE => '+1', @@ -719,22 +768,25 @@ our %labels = ( OPpOPEN_OUT_CRLF => 'OUTCR', OPpOPEN_OUT_RAW => 'OUTBIN', OPpOUR_INTRO => 'OURINTR', + OPpPADHV_ISKEYS => 'KEYS', OPpPAD_STATE => 'STATE', OPpPV_IS_UTF8 => 'UTF', OPpREFCOUNTED => 'REFC', OPpREPEAT_DOLIST => 'DOLIST', OPpREVERSE_INPLACE => 'INPLACE', - OPpRUNTIME => 'RTIME', + OPpRV2HV_ISKEYS => 'KEYS', OPpSLICE => 'SLICE', OPpSLICEWARNING => 'SLICEWARN', OPpSORT_DESCEND => 'DESC', OPpSORT_INPLACE => 'INPLACE', OPpSORT_INTEGER => 'INT', OPpSORT_NUMERIC => 'NUM', - OPpSORT_QSORT => 'QSORT', OPpSORT_REVERSE => 'REV', OPpSORT_STABLE => 'STABLE', + OPpSORT_UNSTABLE => 'UNSTABLE', + OPpSPLIT_ASSIGN => 'ASSIGN', OPpSPLIT_IMPLIM => 'IMPLIM', + OPpSPLIT_LEX => 'LEX', OPpSUBSTR_REPL_FIRST => 'REPL1ST', OPpTARGET_MY => 'TARGMY', OPpTRANS_COMPLEMENT => 'COMPL', @@ -752,6 +804,7 @@ our %ops_using = ( OPpALLOW_FAKE => [qw(rv2gv)], OPpASSIGN_BACKWARDS => [qw(sassign)], OPpASSIGN_COMMON_AGG => [qw(aassign)], + OPpCONCAT_NESTED => [qw(concat)], OPpCONST_BARE => [qw(const)], OPpCOREARGS_DEREF1 => [qw(coreargs)], OPpEARLY_CV => [qw(gv)], @@ -765,37 +818,42 @@ our %ops_using = ( OPpFT_AFTER_t => [qw(ftatime ftbinary ftblk ftchr ftctime ftdir fteexec fteowned fteread ftewrite ftfile ftis ftlink ftmtime ftpipe ftrexec ftrowned ftrread ftrwrite ftsgid ftsize ftsock ftsuid ftsvtx fttext fttty ftzero)], OPpHINT_STRICT_REFS => [qw(entersub multideref rv2av rv2cv rv2gv rv2hv rv2sv)], OPpHUSH_VMSISH => [qw(dbstate nextstate)], + OPpINDEX_BOOLNEG => [qw(index rindex)], OPpITER_DEF => [qw(enteriter)], OPpITER_REVERSED => [qw(enteriter iter)], + OPpKVSLICE => [qw(delete)], OPpLIST_GUESSED => [qw(list)], OPpLVALUE => [qw(leave leaveloop)], OPpLVAL_DEFER => [qw(aelem helem multideref)], - OPpLVAL_INTRO => [qw(aelem aslice cond_expr delete enteriter entersub gvsv helem hslice list lvavref lvref lvrefslice multideref padav padhv padrange padsv pushmark refassign rv2av rv2gv rv2hv rv2sv)], + OPpLVAL_INTRO => [qw(aelem aslice cond_expr delete enteriter entersub gvsv helem hslice list lvavref lvref lvrefslice multiconcat multideref padav padhv padrange padsv pushmark refassign rv2av rv2gv rv2hv rv2sv split)], OPpLVREF_ELEM => [qw(lvref refassign)], - OPpMAYBE_LVSUB => [qw(aassign aelem aslice av2arylen helem hslice keys kvaslice kvhslice multideref padav padhv pos rv2av rv2gv rv2hv substr vec)], - OPpMAYBE_TRUEBOOL => [qw(padhv rv2hv)], + OPpMAYBE_LVSUB => [qw(aassign aelem akeys aslice av2arylen avhvswitch helem hslice keys kvaslice kvhslice multideref padav padhv pos rv2av rv2gv rv2hv substr values vec)], + OPpMAYBE_TRUEBOOL => [qw(padhv ref rv2hv)], + OPpMULTICONCAT_APPEND => [qw(multiconcat)], OPpMULTIDEREF_DELETE => [qw(multideref)], OPpOFFBYONE => [qw(caller runcv wantarray)], OPpOPEN_IN_CRLF => [qw(backtick open)], OPpOUR_INTRO => [qw(enteriter gvsv rv2av rv2hv rv2sv split)], + OPpPADHV_ISKEYS => [qw(padhv)], OPpPAD_STATE => [qw(lvavref lvref padav padhv padsv pushmark refassign)], OPpPV_IS_UTF8 => [qw(dump goto last next redo)], OPpREFCOUNTED => [qw(leave leaveeval leavesub leavesublv leavewrite)], OPpREPEAT_DOLIST => [qw(repeat)], OPpREVERSE_INPLACE => [qw(reverse)], - OPpRUNTIME => [qw(match pushre qr subst substcont)], - OPpSLICE => [qw(delete)], + OPpRV2HV_ISKEYS => [qw(rv2hv)], OPpSLICEWARNING => [qw(aslice hslice padav padhv rv2av rv2hv)], OPpSORT_DESCEND => [qw(sort)], - OPpSPLIT_IMPLIM => [qw(split)], + OPpSPLIT_ASSIGN => [qw(split)], OPpSUBSTR_REPL_FIRST => [qw(substr)], - OPpTARGET_MY => [qw(abs add atan2 chdir chmod chomp chown chr chroot concat cos crypt divide exec exp flock getpgrp getppid getpriority hex i_add i_divide i_modulo i_multiply i_subtract index int kill left_shift length link log mkdir modulo multiply nbit_and nbit_or nbit_xor ncomplement oct ord pow push rand rename right_shift rindex rmdir schomp scomplement setpgrp setpriority sin sleep sqrt srand stringify subtract symlink system time unlink unshift utime wait waitpid)], + OPpTARGET_MY => [qw(abs add atan2 chdir chmod chomp chown chr chroot concat cos crypt divide exec exp flock getpgrp getppid getpriority hex i_add i_divide i_modulo i_multiply i_subtract index int kill left_shift length link log mkdir modulo multiconcat multiply nbit_and nbit_or nbit_xor ncomplement oct ord pow push rand rename right_shift rindex rmdir schomp scomplement setpgrp setpriority sin sleep sqrt srand stringify subtract symlink system time unlink unshift utime wait waitpid)], OPpTRANS_COMPLEMENT => [qw(trans transr)], + OPpTRUEBOOL => [qw(grepwhile index length padav padhv pos ref rindex rv2av rv2hv subst)], ); $ops_using{OPpASSIGN_COMMON_RC1} = $ops_using{OPpASSIGN_COMMON_AGG}; $ops_using{OPpASSIGN_COMMON_SCALAR} = $ops_using{OPpASSIGN_COMMON_AGG}; $ops_using{OPpASSIGN_CV_TO_GV} = $ops_using{OPpASSIGN_BACKWARDS}; +$ops_using{OPpASSIGN_TRUEBOOL} = $ops_using{OPpASSIGN_COMMON_AGG}; $ops_using{OPpCONST_ENTERED} = $ops_using{OPpCONST_BARE}; $ops_using{OPpCONST_NOVER} = $ops_using{OPpCONST_BARE}; $ops_using{OPpCONST_SHORTCIRCUIT} = $ops_using{OPpCONST_BARE}; @@ -814,22 +872,26 @@ $ops_using{OPpFT_STACKED} = $ops_using{OPpFT_AFTER_t}; $ops_using{OPpFT_STACKING} = $ops_using{OPpFT_AFTER_t}; $ops_using{OPpLVREF_ITER} = $ops_using{OPpLVREF_ELEM}; $ops_using{OPpMAY_RETURN_CONSTANT} = $ops_using{OPpENTERSUB_NOPAREN}; +$ops_using{OPpMULTICONCAT_FAKE} = $ops_using{OPpMULTICONCAT_APPEND}; +$ops_using{OPpMULTICONCAT_STRINGIFY} = $ops_using{OPpMULTICONCAT_APPEND}; $ops_using{OPpMULTIDEREF_EXISTS} = $ops_using{OPpMULTIDEREF_DELETE}; $ops_using{OPpOPEN_IN_RAW} = $ops_using{OPpOPEN_IN_CRLF}; $ops_using{OPpOPEN_OUT_CRLF} = $ops_using{OPpOPEN_IN_CRLF}; $ops_using{OPpOPEN_OUT_RAW} = $ops_using{OPpOPEN_IN_CRLF}; +$ops_using{OPpSLICE} = $ops_using{OPpKVSLICE}; $ops_using{OPpSORT_INPLACE} = $ops_using{OPpSORT_DESCEND}; $ops_using{OPpSORT_INTEGER} = $ops_using{OPpSORT_DESCEND}; $ops_using{OPpSORT_NUMERIC} = $ops_using{OPpSORT_DESCEND}; -$ops_using{OPpSORT_QSORT} = $ops_using{OPpSORT_DESCEND}; $ops_using{OPpSORT_REVERSE} = $ops_using{OPpSORT_DESCEND}; $ops_using{OPpSORT_STABLE} = $ops_using{OPpSORT_DESCEND}; +$ops_using{OPpSORT_UNSTABLE} = $ops_using{OPpSORT_DESCEND}; +$ops_using{OPpSPLIT_IMPLIM} = $ops_using{OPpSPLIT_ASSIGN}; +$ops_using{OPpSPLIT_LEX} = $ops_using{OPpSPLIT_ASSIGN}; $ops_using{OPpTRANS_DELETE} = $ops_using{OPpTRANS_COMPLEMENT}; $ops_using{OPpTRANS_FROM_UTF} = $ops_using{OPpTRANS_COMPLEMENT}; $ops_using{OPpTRANS_GROWS} = $ops_using{OPpTRANS_COMPLEMENT}; $ops_using{OPpTRANS_IDENTICAL} = $ops_using{OPpTRANS_COMPLEMENT}; $ops_using{OPpTRANS_SQUASH} = $ops_using{OPpTRANS_COMPLEMENT}; $ops_using{OPpTRANS_TO_UTF} = $ops_using{OPpTRANS_COMPLEMENT}; -$ops_using{OPpTRUEBOOL} = $ops_using{OPpMAYBE_TRUEBOOL}; # ex: set ro: diff --git a/gnu/usr.bin/perl/lib/Benchmark.t b/gnu/usr.bin/perl/lib/Benchmark.t index 4bf01b222e4..523618f5763 100644 --- a/gnu/usr.bin/perl/lib/Benchmark.t +++ b/gnu/usr.bin/perl/lib/Benchmark.t @@ -7,7 +7,7 @@ BEGIN { use warnings; use strict; -use vars qw($foo $bar $baz $ballast); +our ($foo, $bar, $baz, $ballast); use Test::More tests => 213; use Benchmark qw(:all); diff --git a/gnu/usr.bin/perl/lib/ExtUtils/Embed.pm b/gnu/usr.bin/perl/lib/ExtUtils/Embed.pm index 9305b5dc133..e75e41f8c48 100644 --- a/gnu/usr.bin/perl/lib/ExtUtils/Embed.pm +++ b/gnu/usr.bin/perl/lib/ExtUtils/Embed.pm @@ -3,22 +3,19 @@ require Exporter; use Config; require File::Spec; -use vars qw(@ISA @EXPORT $VERSION - @Extensions $Verbose $lib_ext - $opt_o $opt_s - ); +our ( @Extensions, $opt_o, $opt_s ); use strict; # This is not a dual-life module, so no need for development version numbers -$VERSION = '1.33'; +our $VERSION = '1.35'; -@ISA = qw(Exporter); -@EXPORT = qw(&xsinit &ldopts +our @ISA = qw(Exporter); +our @EXPORT = qw(&xsinit &ldopts &ccopts &ccflags &ccdlflags &perl_inc &xsi_header &xsi_protos &xsi_body); -$Verbose = 0; -$lib_ext = $Config{lib_ext} || '.a'; +our $Verbose = 0; +our $lib_ext = $Config{lib_ext} || '.a'; sub is_cmd { $0 eq '-e' } @@ -199,7 +196,7 @@ sub ldopts { push @archives, $archive; if(-e ($extra = File::Spec->catdir($_,"auto",$root,"extralibs.ld"))) { local(*FH); - if(open(FH, $extra)) { + if(open(FH, '<', $extra)) { my($libs) = <FH>; chomp $libs; push @potential_libs, split /\s+/, $libs; } diff --git a/gnu/usr.bin/perl/lib/ExtUtils/typemap b/gnu/usr.bin/perl/lib/ExtUtils/typemap index 4bfba95e9e0..db700b75bf6 100644 --- a/gnu/usr.bin/perl/lib/ExtUtils/typemap +++ b/gnu/usr.bin/perl/lib/ExtUtils/typemap @@ -398,8 +398,9 @@ T_ARRAY } T_STDIO { - GV *gv = newGVgen("$Package"); + GV *gv = (GV *)sv_newmortal(); PerlIO *fp = PerlIO_importFILE($var,0); + gv_init_pvn(gv, gv_stashpvs("$Package",1),"__ANONIO__",10,0); if ( fp && do_open(gv, "+<&", 3, FALSE, 0, 0, fp) ) { SV *rv = newRV_inc((SV*)gv); rv = sv_bless(rv, GvSTASH(gv)); @@ -411,7 +412,8 @@ T_STDIO } T_IN { - GV *gv = newGVgen("$Package"); + GV *gv = (GV *)sv_newmortal(); + gv_init_pvn(gv, gv_stashpvs("$Package",1),"__ANONIO__",10,0); if ( do_open(gv, "<&", 2, FALSE, 0, 0, $var) ) { SV *rv = newRV_inc((SV*)gv); rv = sv_bless(rv, GvSTASH(gv)); @@ -423,7 +425,8 @@ T_IN } T_INOUT { - GV *gv = newGVgen("$Package"); + GV *gv = (GV *)sv_newmortal(); + gv_init_pvn(gv, gv_stashpvs("$Package",1),"__ANONIO__",10,0); if ( do_open(gv, "+<&", 3, FALSE, 0, 0, $var) ) { SV *rv = newRV_inc((SV*)gv); rv = sv_bless(rv, GvSTASH(gv)); @@ -435,7 +438,8 @@ T_INOUT } T_OUT { - GV *gv = newGVgen("$Package"); + GV *gv = (GV *)sv_newmortal(); + gv_init_pvn(gv, gv_stashpvs("$Package",1),"__ANONIO__",10,0); if ( do_open(gv, "+>&", 3, FALSE, 0, 0, $var) ) { SV *rv = newRV_inc((SV*)gv); rv = sv_bless(rv, GvSTASH(gv)); diff --git a/gnu/usr.bin/perl/lib/File/Copy.pm b/gnu/usr.bin/perl/lib/File/Copy.pm index f7440b3d7b0..b796451e37a 100644 --- a/gnu/usr.bin/perl/lib/File/Copy.pm +++ b/gnu/usr.bin/perl/lib/File/Copy.pm @@ -24,7 +24,7 @@ sub syscopy; sub cp; sub mv; -$VERSION = '2.31_01'; +$VERSION = '2.33'; require Exporter; @ISA = qw(Exporter); @@ -481,6 +481,11 @@ from the input filespec, then all timestamps other than the revision date are propagated. If this parameter is not supplied, it defaults to 0. +C<rmscopy> is VMS specific and cannot be exported; it must be +referenced by its full name, e.g.: + + File::Copy::rmscopy($from, $to) or die $!; + Like C<copy>, C<rmscopy> returns 1 on success. If an error occurs, it sets C<$!>, deletes the output file, and returns 0. diff --git a/gnu/usr.bin/perl/lib/File/Copy.t b/gnu/usr.bin/perl/lib/File/Copy.t index 5dd564dad29..57d9478a68b 100644 --- a/gnu/usr.bin/perl/lib/File/Copy.t +++ b/gnu/usr.bin/perl/lib/File/Copy.t @@ -48,14 +48,14 @@ for my $cross_partition_test (0..1) { } # First we create a file - open(F, ">file-$$") or die $!; + open(F, ">", "file-$$") or die $!; binmode F; # for DOSISH platforms, because test 3 copies to stdout printf F "ok\n"; close F; copy "file-$$", "copy-$$"; - open(F, "copy-$$") or die $!; + open(F, "<", "copy-$$") or die $!; my $foo = <F>; close(F); @@ -70,16 +70,18 @@ for my $cross_partition_test (0..1) { $TB->current_test($TB->current_test + 1); unlink "copy-$$" or die "unlink: $!"; - open(F,"file-$$"); + open(F, "<", "file-$$"); + binmode F; copy(*F, "copy-$$"); - open(R, "copy-$$") or die "open copy-$$: $!"; $foo = <R>; close(R); + open(R, "<:raw", "copy-$$") or die "open copy-$$: $!"; $foo = <R>; close(R); is $foo, "ok\n", 'copy(*F, fn): same contents'; unlink "copy-$$" or die "unlink: $!"; - open(F,"file-$$"); + open(F, "<", "file-$$"); + binmode F; copy(\*F, "copy-$$"); close(F) or die "close: $!"; - open(R, "copy-$$") or die; $foo = <R>; close(R) or die "close: $!"; + open(R, "<", "copy-$$") or die; $foo = <R>; close(R) or die "close: $!"; is $foo, "ok\n", 'copy(\*F, fn): same contents'; unlink "copy-$$" or die "unlink: $!"; @@ -88,7 +90,7 @@ for my $cross_partition_test (0..1) { binmode $fh or die $!; copy("file-$$",$fh); $fh->close or die "close: $!"; - open(R, "copy-$$") or die; $foo = <R>; close(R); + open(R, "<", "copy-$$") or die; $foo = <R>; close(R); is $foo, "ok\n", 'copy(fn, io): same contents'; unlink "copy-$$" or die "unlink: $!"; @@ -97,7 +99,7 @@ for my $cross_partition_test (0..1) { binmode $fh or die $!; copy("file-$$",$fh); $fh->close; - open(R, "copy-$$") or die $!; $foo = <R>; close(R); + open(R, "<", "copy-$$") or die $!; $foo = <R>; close(R); is $foo, "ok\n", 'copy(fn, fh): same contents'; unlink "file-$$" or die "unlink: $!"; @@ -116,7 +118,7 @@ for my $cross_partition_test (0..1) { ok move("copy-$$", "file-$$"), 'move'; ok -e "file-$$", ' destination exists'; ok !-e "copy-$$", ' source does not'; - open(R, "file-$$") or die $!; $foo = <R>; close(R); + open(R, "<", "file-$$") or die $!; $foo = <R>; close(R); is $foo, "ok\n", 'contents preserved'; TODO: { @@ -131,13 +133,13 @@ for my $cross_partition_test (0..1) { # trick: create lib/ if not exists - not needed in Perl core unless (-d 'lib') { mkdir 'lib' or die $!; } copy "file-$$", "lib"; - open(R, "lib/file-$$") or die $!; $foo = <R>; close(R); + open(R, "<", "lib/file-$$") or die $!; $foo = <R>; close(R); is $foo, "ok\n", 'copy(fn, dir): same contents'; unlink "lib/file-$$" or die "unlink: $!"; # Do it twice to ensure copying over the same file works. copy "file-$$", "lib"; - open(R, "lib/file-$$") or die $!; $foo = <R>; close(R); + open(R, "<", "lib/file-$$") or die $!; $foo = <R>; close(R); is $foo, "ok\n", 'copy over the same file works'; unlink "lib/file-$$" or die "unlink: $!"; @@ -151,7 +153,7 @@ for my $cross_partition_test (0..1) { } move "file-$$", "lib"; - open(R, "lib/file-$$") or die "open lib/file-$$: $!"; $foo = <R>; close(R); + open(R, "<", "lib/file-$$") or die "open lib/file-$$: $!"; $foo = <R>; close(R); is $foo, "ok\n", 'move(fn, dir): same contents'; ok !-e "file-$$", 'file moved indeed'; unlink "lib/file-$$" or die "unlink: $!"; @@ -159,7 +161,7 @@ for my $cross_partition_test (0..1) { SKIP: { skip "Testing symlinks", 3 unless $Config{d_symlink}; - open(F, ">file-$$") or die $!; + open(F, ">", "file-$$") or die $!; print F "dummy content\n"; close F; symlink("file-$$", "symlink-$$") or die $!; @@ -180,7 +182,7 @@ for my $cross_partition_test (0..1) { skip "Testing hard links", 3 if !$Config{d_link} or $^O eq 'MSWin32' or $^O eq 'cygwin'; - open(F, ">file-$$") or die $!; + open(F, ">", "file-$$") or die $!; print F "dummy content\n"; close F; link("file-$$", "hardlink-$$") or die $!; @@ -197,13 +199,13 @@ for my $cross_partition_test (0..1) { unlink "file-$$" or die $!; } - open(F, ">file-$$") or die $!; + open(F, ">", "file-$$") or die $!; binmode F; print F "this is file\n"; close F; my $copy_msg = "this is copy\n"; - open(F, ">copy-$$") or die $!; + open(F, ">", "copy-$$") or die $!; binmode F; print F $copy_msg; close F; @@ -221,7 +223,7 @@ for my $cross_partition_test (0..1) { } is -s "copy-$$", length $copy_msg, "but does not truncate the destination"; - open(F, "copy-$$") or die $!; + open(F, "<", "copy-$$") or die $!; $foo = <F>; close(F); is $foo, $copy_msg, "nor change the destination's contents"; @@ -233,7 +235,7 @@ for my $cross_partition_test (0..1) { TODO: { local $TODO = 'spaces in filenames require DECC$EFS_CHARSET enabled' if $^O eq 'VMS'; - open(F, ">file-$$") or die $!; + open(F, ">", "file-$$") or die $!; close F; copy "file-$$", " copy-$$"; ok -e " copy-$$", "copy with leading whitespace"; @@ -350,6 +352,7 @@ SKIP: { chmod $c_perm3 => $copy6 or die $!; open my $fh => "<", $src or die $!; + binmode $fh; copy ($src, $copy1); copy ($fh, $copy2); @@ -470,6 +473,8 @@ SKIP: { open(my $IN, "-|") || exec $^X, '-e', 'print "Hello, world!\n"'; open(my $OUT, "|-") || exec $^X, '-ne', 'exit(/Hello/ ? 55 : 0)'; + binmode $IN; + binmode $OUT; ok(copy($IN, $OUT), "copy pipe to another"); close($OUT); diff --git a/gnu/usr.bin/perl/lib/File/stat.pm b/gnu/usr.bin/perl/lib/File/stat.pm index b631fbf8752..578c3118c86 100644 --- a/gnu/usr.bin/perl/lib/File/stat.pm +++ b/gnu/usr.bin/perl/lib/File/stat.pm @@ -10,9 +10,16 @@ BEGIN { *warnif = \&warnings::warnif } our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); -our $VERSION = '1.07'; +our $VERSION = '1.08'; + +our @fields; +our ( $st_dev, $st_ino, $st_mode, + $st_nlink, $st_uid, $st_gid, + $st_rdev, $st_size, + $st_atime, $st_mtime, $st_ctime, + $st_blksize, $st_blocks +); -my @fields; BEGIN { use Exporter (); @EXPORT = qw(stat lstat); @@ -25,7 +32,6 @@ BEGIN { @EXPORT_OK = ( @fields, "stat_cando" ); %EXPORT_TAGS = ( FIELDS => [ @fields, @EXPORT ] ); } -use vars @fields; use Fcntl qw(S_IRUSR S_IWUSR S_IXUSR); diff --git a/gnu/usr.bin/perl/lib/File/stat.t b/gnu/usr.bin/perl/lib/File/stat.t index 7c9b9cc340b..c403fc44980 100644 --- a/gnu/usr.bin/perl/lib/File/stat.t +++ b/gnu/usr.bin/perl/lib/File/stat.t @@ -144,7 +144,7 @@ for (split //, "tTB") { SKIP: { local *STAT; - skip("Could not open file: $!", 2) unless open(STAT, $file); + skip("Could not open file: $!", 2) unless open(STAT, '<', $file); isa_ok(File::stat::stat('STAT'), 'File::stat', '... should be able to find filehandle'); diff --git a/gnu/usr.bin/perl/lib/FileHandle.pm b/gnu/usr.bin/perl/lib/FileHandle.pm index 6b3636a089d..133221bb6b5 100644 --- a/gnu/usr.bin/perl/lib/FileHandle.pm +++ b/gnu/usr.bin/perl/lib/FileHandle.pm @@ -4,7 +4,7 @@ use 5.006; use strict; our($VERSION, @ISA, @EXPORT, @EXPORT_OK); -$VERSION = "2.02"; +$VERSION = "2.03"; require IO::File; @ISA = qw(IO::File); @@ -36,7 +36,7 @@ require IO::File; # # Everything we're willing to export, we must first import. # -import IO::Handle grep { !defined(&$_) } @EXPORT, @EXPORT_OK; +IO::Handle->import( grep { !defined(&$_) } @EXPORT, @EXPORT_OK ); # # Some people call "FileHandle::function", so all the functions @@ -88,8 +88,8 @@ sub import { # sub pipe { - my $r = new IO::Handle; - my $w = new IO::Handle; + my $r = IO::Handle->new; + my $w = IO::Handle->new; CORE::pipe($r, $w) or return undef; ($r, $w); } diff --git a/gnu/usr.bin/perl/lib/Getopt/Std.pm b/gnu/usr.bin/perl/lib/Getopt/Std.pm index b98bd57f077..5b8878dbb86 100644 --- a/gnu/usr.bin/perl/lib/Getopt/Std.pm +++ b/gnu/usr.bin/perl/lib/Getopt/Std.pm @@ -4,7 +4,7 @@ require Exporter; =head1 NAME -Getopt::Std, getopt, getopts - Process single-character switches with switch clustering +Getopt::Std - Process single-character switches with switch clustering =head1 SYNOPSIS @@ -81,7 +81,7 @@ and version_mess() with the switches string as an argument. @ISA = qw(Exporter); @EXPORT = qw(getopt getopts); -$VERSION = '1.11'; +$VERSION = '1.12'; # uncomment the next line to disable 1.03-backward compatibility paranoia # $STANDARD_HELP_VERSION = 1; diff --git a/gnu/usr.bin/perl/lib/Net/hostent.pm b/gnu/usr.bin/perl/lib/Net/hostent.pm index 3a2fc013877..8831919fb43 100644 --- a/gnu/usr.bin/perl/lib/Net/hostent.pm +++ b/gnu/usr.bin/perl/lib/Net/hostent.pm @@ -2,8 +2,14 @@ package Net::hostent; use strict; use 5.006_001; -our $VERSION = '1.01'; -our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our $VERSION = '1.02'; +our (@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ( + $h_name, @h_aliases, + $h_addrtype, $h_length, + @h_addr_list, $h_addr +); + BEGIN { use Exporter (); @EXPORT = qw(gethostbyname gethostbyaddr gethost); @@ -14,7 +20,6 @@ BEGIN { ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); } -use vars @EXPORT_OK; # Class::Struct forbids use of @ISA sub import { goto &Exporter::import } diff --git a/gnu/usr.bin/perl/lib/Net/netent.pm b/gnu/usr.bin/perl/lib/Net/netent.pm index f7d32cb9254..b21c5d11b86 100644 --- a/gnu/usr.bin/perl/lib/Net/netent.pm +++ b/gnu/usr.bin/perl/lib/Net/netent.pm @@ -2,8 +2,13 @@ package Net::netent; use strict; use 5.006_001; -our $VERSION = '1.00'; +our $VERSION = '1.01'; our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ( + $n_name, @n_aliases, + $n_addrtype, $n_net +); + BEGIN { use Exporter (); @EXPORT = qw(getnetbyname getnetbyaddr getnet); @@ -13,7 +18,6 @@ BEGIN { ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); } -use vars @EXPORT_OK; # Class::Struct forbids use of @ISA sub import { goto &Exporter::import } diff --git a/gnu/usr.bin/perl/lib/Net/protoent.pm b/gnu/usr.bin/perl/lib/Net/protoent.pm index 2cbccad3cbc..cef20fbd0b0 100644 --- a/gnu/usr.bin/perl/lib/Net/protoent.pm +++ b/gnu/usr.bin/perl/lib/Net/protoent.pm @@ -2,15 +2,15 @@ package Net::protoent; use strict; use 5.006_001; -our $VERSION = '1.00'; +our $VERSION = '1.01'; our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ( $p_name, @p_aliases, $p_proto ); BEGIN { use Exporter (); @EXPORT = qw(getprotobyname getprotobynumber getprotoent getproto); @EXPORT_OK = qw( $p_name @p_aliases $p_proto ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); } -use vars @EXPORT_OK; # Class::Struct forbids use of @ISA sub import { goto &Exporter::import } diff --git a/gnu/usr.bin/perl/lib/Net/servent.pm b/gnu/usr.bin/perl/lib/Net/servent.pm index 78a16814555..a3b2bad2c2b 100644 --- a/gnu/usr.bin/perl/lib/Net/servent.pm +++ b/gnu/usr.bin/perl/lib/Net/servent.pm @@ -2,15 +2,15 @@ package Net::servent; use strict; use 5.006_001; -our $VERSION = '1.01'; +our $VERSION = '1.02'; our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ( $s_name, @s_aliases, $s_port, $s_proto ); BEGIN { use Exporter (); @EXPORT = qw(getservbyname getservbyport getservent getserv); @EXPORT_OK = qw( $s_name @s_aliases $s_port $s_proto ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); } -use vars @EXPORT_OK; # Class::Struct forbids use of @ISA sub import { goto &Exporter::import } diff --git a/gnu/usr.bin/perl/lib/Symbol.pm b/gnu/usr.bin/perl/lib/Symbol.pm index 1e408b59f71..0e8d67fffd9 100644 --- a/gnu/usr.bin/perl/lib/Symbol.pm +++ b/gnu/usr.bin/perl/lib/Symbol.pm @@ -9,7 +9,7 @@ Symbol - manipulate Perl symbols and their names use Symbol; $sym = gensym; - open($sym, "filename"); + open($sym, '<', "filename"); $_ = <$sym>; # etc. @@ -85,7 +85,7 @@ require Exporter; @EXPORT = qw(gensym ungensym qualify qualify_to_ref); @EXPORT_OK = qw(delete_package geniosym); -$VERSION = '1.07'; +$VERSION = '1.08'; my $genpkg = "Symbol::"; my $genseq = 0; diff --git a/gnu/usr.bin/perl/lib/Time/gmtime.pm b/gnu/usr.bin/perl/lib/Time/gmtime.pm index eb5b371a004..99f470be51f 100644 --- a/gnu/usr.bin/perl/lib/Time/gmtime.pm +++ b/gnu/usr.bin/perl/lib/Time/gmtime.pm @@ -4,7 +4,12 @@ use 5.006_001; use Time::tm; -our(@ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS, $VERSION); +our (@ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS, $VERSION); +our ( $tm_sec, $tm_min, $tm_hour, $tm_mday, + $tm_mon, $tm_year, $tm_wday, $tm_yday, + $tm_isdst, +); + BEGIN { use Exporter (); @ISA = qw(Exporter Time::tm); @@ -15,9 +20,8 @@ BEGIN { $tm_isdst ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); - $VERSION = 1.03; + $VERSION = 1.04; } -use vars @EXPORT_OK; sub populate (@) { return unless @_; diff --git a/gnu/usr.bin/perl/lib/Time/localtime.pm b/gnu/usr.bin/perl/lib/Time/localtime.pm index c3d9fb36085..f2ef0840383 100644 --- a/gnu/usr.bin/perl/lib/Time/localtime.pm +++ b/gnu/usr.bin/perl/lib/Time/localtime.pm @@ -4,7 +4,13 @@ use 5.006_001; use Time::tm; -our(@ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS, $VERSION); +our (@ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS, $VERSION); +our ( + $tm_sec, $tm_min, $tm_hour, $tm_mday, + $tm_mon, $tm_year, $tm_wday, $tm_yday, + $tm_isdst +); + BEGIN { use Exporter (); @ISA = qw(Exporter Time::tm); @@ -15,9 +21,8 @@ BEGIN { $tm_isdst ); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); - $VERSION = 1.02; + $VERSION = 1.03; } -use vars @EXPORT_OK; sub populate (@) { return unless @_; diff --git a/gnu/usr.bin/perl/lib/Unicode/UCD.pm b/gnu/usr.bin/perl/lib/Unicode/UCD.pm index 13c2c785981..6733e119ea4 100644 --- a/gnu/usr.bin/perl/lib/Unicode/UCD.pm +++ b/gnu/usr.bin/perl/lib/Unicode/UCD.pm @@ -5,7 +5,7 @@ use warnings; no warnings 'surrogate'; # surrogates can be inputs to this use charnames (); -our $VERSION = '0.64'; +our $VERSION = '0.70'; require Exporter; @@ -98,6 +98,9 @@ Unicode::UCD - Unicode character database use Unicode::UCD 'search_invlist'; my $index = search_invlist(\@invlist, $code_point); + # The following function should be used only internally in + # implementations of the Unicode Normalization Algorithm, and there + # are better choices than it. use Unicode::UCD 'compexcl'; my $compexcl = compexcl($codepoint); @@ -128,7 +131,8 @@ Examples: 223 # Decimal 223 in native character set 0223 # Hexadecimal 223, native (= 547 decimal) - 0xDF # Hexadecimal DF, native (= 223 decimal + 0xDF # Hexadecimal DF, native (= 223 decimal) + '0xDF' # String form of hexadecimal (= 223 decimal) 'U+DF' # Hexadecimal DF, in Unicode's character set (= LATIN SMALL LETTER SHARP S) @@ -136,28 +140,18 @@ Note that the largest code point in Unicode is U+10FFFF. =cut -my $BLOCKSFH; -my $VERSIONFH; -my $CASEFOLDFH; -my $CASESPECFH; -my $NAMEDSEQFH; my $v_unicode_version; # v-string. sub openunicode { - my ($rfh, @path) = @_; - my $f; - unless (defined $$rfh) { - for my $d (@INC) { - use File::Spec; - $f = File::Spec->catfile($d, "unicore", @path); - last if open($$rfh, $f); - undef $f; - } - croak __PACKAGE__, ": failed to find ", - File::Spec->catfile(@path), " in @INC" - unless defined $f; + my (@path) = @_; + my $rfh; + for my $d (@INC) { + use File::Spec; + my $f = File::Spec->catfile($d, "unicore", @path); + return $rfh if open($rfh, '<', $f); } - return $f; + croak __PACKAGE__, ": failed to find ", + File::Spec->catfile("unicore", @path), " in @INC"; } sub _dclone ($) { # Use Storable::dclone if available; otherwise emulate it. @@ -334,7 +328,8 @@ See L</Blocks versus Scripts>. the script I<code> belongs to. The L</prop_value_aliases()> function can be used to get all the synonyms -of the script name. +of the script name. Note that this is the older "Script" property value, and +not the improved "Script_Extensions" value. See L</Blocks versus Scripts>. @@ -694,14 +689,14 @@ that are internal-only. =cut -sub charprop ($$) { - my ($input_cp, $prop) = @_; +sub charprop ($$;$) { + my ($input_cp, $prop, $internal_ok) = @_; my $cp = _getcode($input_cp); croak __PACKAGE__, "::charprop: unknown code point '$input_cp'" unless defined $cp; my ($list_ref, $map_ref, $format, $default) - = prop_invmap($prop); + = prop_invmap($prop, $internal_ok); return undef unless defined $list_ref; my $i = search_invlist($list_ref, $cp); @@ -875,10 +870,11 @@ sub _charblocks { push @BLOCKS, $subrange; push @{$BLOCKS{'No_Block'}}, $subrange; } - elsif (openunicode(\$BLOCKSFH, "Blocks.txt")) { + else { + my $blocksfh = openunicode("Blocks.txt"); local $_; local $/ = "\n"; - while (<$BLOCKSFH>) { + while (<$blocksfh>) { # Old versions used a different syntax to mark the range. $_ =~ s/;\s+/../ if $v_unicode_version lt v3.1.0; @@ -890,7 +886,6 @@ sub _charblocks { push @{$BLOCKS{$3}}, $subrange; } } - close($BLOCKSFH); if (! IS_ASCII_PLATFORM) { # The first two blocks, through 0xFF, are wrong on EBCDIC # platforms. @@ -962,6 +957,10 @@ that it doesn't have scripts, this function returns C<"Unknown">. The L</prop_value_aliases()> function can be used to get all the synonyms of the script name. +Note that the Script_Extensions property is an improved version of the Script +property, and you should probably be using that instead, with the +L</charprop()> function. + If supplied with an argument that can't be a code point, charscript() tries to do the opposite and interpret the argument as a script name. The return value is a I<range set>: an anonymous array of arrays that contain @@ -1052,7 +1051,9 @@ names as the keys, and the code point ranges (see L</charscript()>) as the values. L<prop_invmap("script")|/prop_invmap()> can be used to get this same data in a -different type of data structure. +different type of data structure. Since the Script_Extensions property is an +improved version of the Script property, you should instead use +L<prop_invmap("scx")|/prop_invmap()>. L<C<prop_values("Script")>|/prop_values()> can be used to get all the known script names as a list, without the code point ranges. @@ -1199,6 +1200,12 @@ sub bidi_types { =head2 B<compexcl()> +WARNING: Unicode discourages the use of this function or any of the +alternative mechanisms listed in this section (the documentation of +C<compexcl()>), except internally in implementations of the Unicode +Normalization Algorithm. You should be using L<Unicode::Normalize> directly +instead of these. Using these will likely lead to half-baked results. + use Unicode::UCD 'compexcl'; my $compexcl = compexcl(0x09dc); @@ -1631,13 +1638,11 @@ my %CASESPEC; sub _casespec { unless (%CASESPEC) { UnicodeVersion() unless defined $v_unicode_version; - if ($v_unicode_version lt v2.1.8) { - %CASESPEC = {}; - } - elsif (openunicode(\$CASESPECFH, "SpecialCasing.txt")) { + if ($v_unicode_version ge v2.1.8) { + my $casespecfh = openunicode("SpecialCasing.txt"); local $_; local $/ = "\n"; - while (<$CASESPECFH>) { + while (<$casespecfh>) { if (/^([0-9A-F]+); ([0-9A-F]+(?: [0-9A-F]+)*)?; ([0-9A-F]+(?: [0-9A-F]+)*)?; ([0-9A-F]+(?: [0-9A-F]+)*)?; (\w+(?: \w+)*)?/) { my ($hexcode, $lower, $title, $upper, $condition) = @@ -1702,7 +1707,6 @@ sub _casespec { } } } - close($CASESPECFH); } } } @@ -1752,19 +1756,17 @@ my %NAMEDSEQ; sub _namedseq { unless (%NAMEDSEQ) { - if (openunicode(\$NAMEDSEQFH, "Name.pl")) { - local $_; - local $/ = "\n"; - while (<$NAMEDSEQFH>) { - if (/^ [0-9A-F]+ \ /x) { - chomp; - my ($sequence, $name) = split /\t/; - my @s = map { chr(hex($_)) } split(' ', $sequence); - $NAMEDSEQ{$name} = join("", @s); - } - } - close($NAMEDSEQFH); - } + my $namedseqfh = openunicode("Name.pl"); + local $_; + local $/ = "\n"; + while (<$namedseqfh>) { + if (/^ [0-9A-F]+ \ /x) { + chomp; + my ($sequence, $name) = split /\t/; + my @s = map { chr(hex($_)) } split(' ', $sequence); + $NAMEDSEQ{$name} = join("", @s); + } + } } } @@ -1848,14 +1850,18 @@ sub _numeric { my $val = num("123"); my $one_quarter = num("\N{VULGAR FRACTION 1/4}"); + my $val = num("12a", \$valid_length); # $valid_length contains 2 C<num()> returns the numeric value of the input Unicode string; or C<undef> if it doesn't think the entire string has a completely valid, safe numeric value. +If called with an optional second parameter, a reference to a scalar, C<num()> +will set the scalar to the length of any valid initial substring; or to 0 if none. If the string is just one character in length, the Unicode numeric value -is returned if it has one, or C<undef> otherwise. Note that this need -not be a whole number. C<num("\N{TIBETAN DIGIT HALF ZERO}")>, for -example returns -0.5. +is returned if it has one, or C<undef> otherwise. If the optional scalar ref +is passed, it would be set to 1 if the return is valid; or 0 if the return is +C<undef>. Note that the numeric value returned need not be a whole number. +C<num("\N{TIBETAN DIGIT HALF ZERO}")>, for example returns -0.5. =cut @@ -1877,7 +1883,9 @@ is returned. A further restriction is that the digits all have to be of the same form. A half-width digit mixed with a full-width one will return C<undef>. The Arabic script has two sets of digits; C<num> will return C<undef> unless all the digits in the string come from the same -set. +set. In all cases, the optional scalar ref parameter is set to how +long any valid initial substring of digits is; hence it will be set to the +entire string length if the main return value is not C<undef>. C<num> errs on the side of safety, and there may be valid strings of decimal digits that it doesn't recognize. Note that Unicode defines @@ -1901,16 +1909,30 @@ change these into digits, and then call C<num> on the result. # consider those, and return the <decomposition> type in the second # array element. -sub num { - my $string = $_[0]; +sub num ($;$) { + my ($string, $retlen_ref) = @_; + + use feature 'unicode_strings'; _numeric unless %NUMERIC; + $$retlen_ref = 0 if $retlen_ref; # Assume will fail + + my $length = length $string; + return if $length == 0; - my $length = length($string); - return $NUMERIC{ord($string)} if $length == 1; - return if $string =~ /\D/; my $first_ord = ord(substr($string, 0, 1)); + return if ! exists $NUMERIC{$first_ord} + || ! defined $NUMERIC{$first_ord}; + + # Here, we know the first character is numeric my $value = $NUMERIC{$first_ord}; + $$retlen_ref = 1 if $retlen_ref; # Assume only this one is numeric + + return $value if $length == 1; + + # Here, the input is longer than a single character. To be valid, it must + # be entirely decimal digits, which means it must start with one. + return if $string =~ / ^ \D /x; # To be a valid decimal number, it should be in a block of 10 consecutive # characters, whose values are 0, 1, 2, ... 9. Therefore this digit's @@ -1922,7 +1944,8 @@ sub num { # release, we verify that this first character is a member of such a # block. That is, that the block of characters surrounding this one # consists of all \d characters whose numeric values are the expected - # ones. + # ones. If not, then this single character is numeric, but the string as + # a whole is not considered to be. UnicodeVersion() unless defined $v_unicode_version; if ($v_unicode_version lt v6.0.0) { for my $i (0 .. 9) { @@ -1944,10 +1967,14 @@ sub num { # function. my $ord = ord(substr($string, $i, 1)); my $digit = $ord - $zero_ord; - return unless $digit >= 0 && $digit <= 9; + if ($digit < 0 || $digit > 9) { + $$retlen_ref = $i if $retlen_ref; + return; + } $value = $value * 10 + $digit; } + $$retlen_ref = $length if $retlen_ref; return $value; } @@ -2427,8 +2454,8 @@ sub prop_value_aliases ($$) { return ( $list_ref->[0], $list_ref->[0] ); } -# All 1 bits is the largest possible UV. -$Unicode::UCD::MAX_CP = ~0; +# All 1 bits but the top one is the largest possible IV. +$Unicode::UCD::MAX_CP = (~0) >> 1; =pod @@ -2458,7 +2485,7 @@ resolving the input property's name as is done for regular expressions. These are also specified in L<perluniprops|perluniprops/Properties accessible through \p{} and \P{}>. Examples of using the "property=value" form are: - say join ", ", prop_invlist("Script=Shavian"); + say join ", ", prop_invlist("Script_Extensions=Shavian"); prints: 66640, 66688 @@ -2520,11 +2547,7 @@ code points that have the property-value: for (my $i = 0; $i < @invlist; $i += 2) { my $upper = ($i + 1) < @invlist ? $invlist[$i+1] - 1 # In range - : $Unicode::UCD::MAX_CP; # To infinity. You may want - # to stop much much earlier; - # going this high may expose - # perl deficiencies with very - # large numbers. + : $Unicode::UCD::MAX_CP; # To infinity. for my $j ($invlist[$i] .. $upper) { push @full_list, $j; } @@ -3043,6 +3066,8 @@ L<Unicode::Normalize::NFD()|Unicode::Normalize>. Note that the mapping is the one that is specified in the Unicode data files, and to get the final decomposition, it may need to be applied recursively. +Unicode in fact discourages use of this property except internally in +implementations of the Unicode Normalization Algorithm. The fourth (index [3]) element (C<$default>) in the list returned for this format is 0. @@ -3136,11 +3161,48 @@ return C<undef> if called with one of those. The returned values for the Perl extension properties, such as C<Any> and C<Greek> are somewhat misleading. The values are either C<"Y"> or C<"N>". All Unicode properties are bipartite, so you can actually use the C<"Y"> or -C<"N>" in a Perl regular rexpression for these, like C<qr/\p{ID_Start=Y/}> or +C<"N>" in a Perl regular expression for these, like C<qr/\p{ID_Start=Y/}> or C<qr/\p{Upper=N/}>. But the Perl extensions aren't specified this way, only like C</qr/\p{Any}>, I<etc>. You can't actually use the C<"Y"> and C<"N>" in them. +=head3 Getting every available name + +Instead of reading the Unicode Database directly from files, as you were able +to do for a long time, you are encouraged to use the supplied functions. So, +instead of reading C<Name.pl> - which may disappear without notice in the +future - directly, as with + + my (%name, %cp); + for (split m/\s*\n/ => do "unicore/Name.pl") { + my ($cp, $name) = split m/\t/ => $_; + $cp{$name} = $cp; + $name{$cp} = $name unless $cp =~ m/ /; + } + +You ought to use L</prop_invmap()> like this: + + my (%name, %cp, %cps, $n); + # All codepoints + foreach my $cat (qw( Name Name_Alias )) { + my ($codepoints, $names, $format, $default) = prop_invmap($cat); + # $format => "n", $default => "" + foreach my $i (0 .. @$codepoints - 2) { + my ($cp, $n) = ($codepoints->[$i], $names->[$i]); + # If $n is a ref, the same codepoint has multiple names + foreach my $name (ref $n ? @$n : $n) { + $name{$cp} //= $name; + $cp{$name} //= $cp; + } + } + } + # Named sequences + { my %ns = namedseq(); + foreach my $name (sort { $ns{$a} cmp $ns{$b} } keys %ns) { + $cp{$name} //= [ map { ord } split "" => $ns{$name} ]; + } + } + =cut # User-defined properties could be handled with some changes to utf8_heavy.pl; @@ -4044,10 +4106,9 @@ my $UNICODEVERSION; sub UnicodeVersion { unless (defined $UNICODEVERSION) { - openunicode(\$VERSIONFH, "version"); + my $versionfh = openunicode("version"); local $/ = "\n"; - chomp($UNICODEVERSION = <$VERSIONFH>); - close($VERSIONFH); + chomp($UNICODEVERSION = <$versionfh>); croak __PACKAGE__, "::VERSION: strange version '$UNICODEVERSION'" unless $UNICODEVERSION =~ /^\d+(?:\.\d+)+$/; } diff --git a/gnu/usr.bin/perl/lib/Unicode/UCD.t b/gnu/usr.bin/perl/lib/Unicode/UCD.t index 83320d34a01..0538bda3055 100644 --- a/gnu/usr.bin/perl/lib/Unicode/UCD.t +++ b/gnu/usr.bin/perl/lib/Unicode/UCD.t @@ -19,7 +19,7 @@ use Test::More; use Unicode::UCD qw(charinfo charprop charprops_all); -my $expected_version = '8.0.0'; +my $expected_version = '10.0.0'; my $current_version = Unicode::UCD::UnicodeVersion; my $v_unicode_version = pack "C*", split /\./, $current_version; my $unknown_script = ($v_unicode_version lt v5.0.0) @@ -819,10 +819,19 @@ use charnames (); # Don't use \N{} on things not in original Unicode # version; else will get a compilation error when this .t # is run on an older version. +my $ret_len; is(num("0"), 0, 'Verify num("0") == 0'); -is(num("98765"), 98765, 'Verify num("98765") == 98765'); -ok(! defined num("98765\N{FULLWIDTH DIGIT FOUR}"), +is(num("0", \$ret_len), 0, 'Verify num("0", \$ret_len) == 0'); +is($ret_len, 1, "... and the returned length is 1"); +ok(! defined num("", \$ret_len), 'Verify num("", \$ret_len) isnt defined'); +is($ret_len, 0, "... and the returned length is 0"); +ok(! defined num("A", \$ret_len), 'Verify num("A") isnt defined'); +is($ret_len, 0, "... and the returned length is 0"); +is(num("98765", \$ret_len), 98765, 'Verify num("98765") == 98765'); +is($ret_len, 5, "... and the returned length is 5"); +ok(! defined num("98765\N{FULLWIDTH DIGIT FOUR}", \$ret_len), 'Verify num("98765\N{FULLWIDTH DIGIT FOUR}") isnt defined'); +is($ret_len, 5, "... but the returned length is 5"); my $tai_lue_2; if ($v_unicode_version ge v4.1.0) { my $tai_lue_1 = charnames::string_vianame("NEW TAI LUE DIGIT ONE"); @@ -834,8 +843,13 @@ if ($v_unicode_version ge v4.1.0) { } if ($v_unicode_version ge v5.2.0) { ok(! defined num($tai_lue_2 - . charnames::string_vianame("NEW TAI LUE THAM DIGIT ONE")), + . charnames::string_vianame("NEW TAI LUE THAM DIGIT ONE"), \$ret_len), 'Verify num("\N{NEW TAI LUE DIGIT TWO}\N{NEW TAI LUE THAM DIGIT ONE}") isnt defined'); + is($ret_len, 1, "... but the returned length is 1"); + ok(! defined num(charnames::string_vianame("NEW TAI LUE THAM DIGIT ONE") + . $tai_lue_2, \$ret_len), + 'Verify num("\N{NEW TAI LUE THAM DIGIT ONE}\N{NEW TAI LUE DIGIT TWO}") isnt defined'); + is($ret_len, 1, "... but the returned length is 1"); } if ($v_unicode_version ge v5.1.0) { my $cham_0 = charnames::string_vianame("CHAM DIGIT ZERO"); @@ -843,8 +857,10 @@ if ($v_unicode_version ge v5.1.0) { 'Verify num("\N{CHAM DIGIT ZERO}\N{CHAM DIGIT THREE}") == 3'); if ($v_unicode_version ge v5.2.0) { ok(! defined num( $cham_0 - . charnames::string_vianame("JAVANESE DIGIT NINE")), + . charnames::string_vianame("JAVANESE DIGIT NINE"), + \$ret_len), 'Verify num("\N{CHAM DIGIT ZERO}\N{JAVANESE DIGIT NINE}") isnt defined'); + is($ret_len, 1, "... but the returned length is 1"); } } is(num("\N{SUPERSCRIPT TWO}"), 2, 'Verify num("\N{SUPERSCRIPT TWO} == 2'); @@ -1415,9 +1431,14 @@ sub fail_with_diff ($$$$) { # For use below to output better messages my ($prop, $official, $constructed, $tested_function_name) = @_; - is($constructed, $official, "$tested_function_name('$prop')"); - diag("Comment out lines " . (__LINE__ - 1) . " through " . (__LINE__ + 1) . " in '$0' on Un*x-like systems to see just the differences. Uses the 'diff' first in your \$PATH"); - return; + if (! $ENV{PERL_DIFF_TOOL}) { + + is($constructed, $official, "$tested_function_name('$prop')"); + + diag("Set environment variable PERL_DIFF_TOOL=diff_tool to see just " + . "the differences."); + return; + } fail("$tested_function_name('$prop')"); @@ -1434,7 +1455,7 @@ sub fail_with_diff ($$$$) { close $gend || die "Can't close gend"; my $diff = File::Temp->new(); - system("diff $off $gend > $diff"); + system("$ENV{PERL_DIFF_TOOL} $off $gend > $diff"); open my $fh, "<", $diff || die "Can't open $diff"; my @diffs = <$fh>; @@ -2695,4 +2716,12 @@ if (! ok(@warnings == 0, "No warnings were generated")) { diag(join "\n", "The warnings are:", @warnings); } +# And make sure that the max code point returned actually fits in an IV, which +# currently range iterators are. +my $count = 0; +for my $i ($Unicode::UCD::MAX_CP - 1 .. $Unicode::UCD::MAX_CP) { + $count++; +} +is($count, 2, "MAX_CP isn't too large"); + done_testing(); diff --git a/gnu/usr.bin/perl/lib/User/grent.pm b/gnu/usr.bin/perl/lib/User/grent.pm index ce6ee5ea447..b66771f2e12 100644 --- a/gnu/usr.bin/perl/lib/User/grent.pm +++ b/gnu/usr.bin/perl/lib/User/grent.pm @@ -2,15 +2,15 @@ package User::grent; use strict; use 5.006_001; -our $VERSION = '1.01'; +our $VERSION = '1.02'; our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ($gr_name, $gr_gid, $gr_passwd, $gr_mem, @gr_members); BEGIN { use Exporter (); @EXPORT = qw(getgrent getgrgid getgrnam getgr); @EXPORT_OK = qw($gr_name $gr_gid $gr_passwd $gr_mem @gr_members); %EXPORT_TAGS = ( FIELDS => [ @EXPORT_OK, @EXPORT ] ); } -use vars @EXPORT_OK; # Class::Struct forbids use of @ISA sub import { goto &Exporter::import } diff --git a/gnu/usr.bin/perl/lib/User/pwent.pm b/gnu/usr.bin/perl/lib/User/pwent.pm index 91d23bd3f68..3f82e8c8615 100644 --- a/gnu/usr.bin/perl/lib/User/pwent.pm +++ b/gnu/usr.bin/perl/lib/User/pwent.pm @@ -1,7 +1,7 @@ package User::pwent; use 5.006; -our $VERSION = '1.00'; +our $VERSION = '1.01'; use strict; use warnings; @@ -10,6 +10,12 @@ use Config; use Carp; our(@EXPORT, @EXPORT_OK, %EXPORT_TAGS); +our ( $pw_name, $pw_passwd, $pw_uid, $pw_gid, + $pw_gecos, $pw_dir, $pw_shell, + $pw_expire, $pw_change, $pw_class, + $pw_age, + $pw_quota, $pw_comment, + ); BEGIN { use Exporter (); @EXPORT = qw(getpwent getpwuid getpwnam getpw); @@ -21,15 +27,12 @@ BEGIN { $pw_expire $pw_change $pw_class $pw_age $pw_quota $pw_comment - $pw_expire - ); %EXPORT_TAGS = ( FIELDS => [ grep(/^\$pw_/, @EXPORT_OK), @EXPORT ], ALL => [ @EXPORT, @EXPORT_OK ], ); } -use vars grep /^\$pw_/, @EXPORT_OK; # # XXX: these mean somebody hacked this module's source diff --git a/gnu/usr.bin/perl/lib/_charnames.pm b/gnu/usr.bin/perl/lib/_charnames.pm index bb7d7c6c7b0..c6169d16f86 100644 --- a/gnu/usr.bin/perl/lib/_charnames.pm +++ b/gnu/usr.bin/perl/lib/_charnames.pm @@ -6,7 +6,7 @@ package _charnames; use strict; use warnings; -our $VERSION = '1.43'; +our $VERSION = '1.45'; use unicore::Name; # mktables-generated algorithmically-defined names use bytes (); # for $bytes::hint_bits @@ -22,8 +22,8 @@ $Carp::Internal{ (__PACKAGE__) } = 1; # The official names with their code points are stored in a table in # lib/unicore/Name.pl which is read in as a large string (almost 3/4 Mb in # Unicode 6.0). Each code point/name combination is separated by a \n in the -# string. (Some of the CJK and the Hangul syllable names are determined -# instead algorithmically via subroutines stored instead in +# string. (Some of the CJK and the Hangul syllable names are instead +# determined algorithmically via subroutines stored instead in # lib/unicore/Name.pm). Because of the large size of this table, it isn't # converted into hashes for faster lookup. # @@ -202,13 +202,6 @@ sub alias (@) # Set up a single alias } $^H{charnames_name_aliases}{$name} = $value; - if (warnings::enabled('deprecated') - && $name =~ / ( .* $nbsp ) ( .* ) $ /x) - { - carp "NO-BREAK SPACE in a charnames alias definition is " - . "deprecated; marked by <-- HERE in '$1 <-- HERE " - . $2 . "'"; - } } } } diff --git a/gnu/usr.bin/perl/lib/blib.pm b/gnu/usr.bin/perl/lib/blib.pm index b3ee3202b1e..f8fd500d5e6 100644 --- a/gnu/usr.bin/perl/lib/blib.pm +++ b/gnu/usr.bin/perl/lib/blib.pm @@ -39,9 +39,8 @@ Nick Ing-Simmons nik@tiuk.ti.com use Cwd; use File::Spec; -use vars qw($VERSION $Verbose); -$VERSION = '1.06'; -$Verbose = 0; +our $VERSION = '1.07'; +our $Verbose = 0; sub import { diff --git a/gnu/usr.bin/perl/lib/bytes.pm b/gnu/usr.bin/perl/lib/bytes.pm index f0022eeb51a..bc4304a509c 100644 --- a/gnu/usr.bin/perl/lib/bytes.pm +++ b/gnu/usr.bin/perl/lib/bytes.pm @@ -1,6 +1,6 @@ package bytes; -our $VERSION = '1.05'; +our $VERSION = '1.06'; $bytes::hint_bits = 0x00000008; @@ -82,8 +82,6 @@ implict) encoding using the L<Encode> module: Or, if performance is needed and you are only interested in the UTF-8 representation: - use utf8; - utf8::encode(my $utf8_byte_string = $string); C<no bytes> can be used to reverse the effect of C<use bytes> within the diff --git a/gnu/usr.bin/perl/lib/charnames.pm b/gnu/usr.bin/perl/lib/charnames.pm index 2efe3d58b27..e22c71913c8 100644 --- a/gnu/usr.bin/perl/lib/charnames.pm +++ b/gnu/usr.bin/perl/lib/charnames.pm @@ -1,7 +1,7 @@ package charnames; use strict; use warnings; -our $VERSION = '1.43'; +our $VERSION = '1.45'; use unicore::Name; # mktables-generated algorithmically-defined names use _charnames (); # The submodule for this where most of the work gets done @@ -278,11 +278,9 @@ mean C<"B">, etc. Aliases must begin with a character that is alphabetic. After that, each may contain any combination of word (C<\w>) characters, SPACE (U+0020), -HYPHEN-MINUS (U+002D), LEFT PARENTHESIS (U+0028), RIGHT PARENTHESIS (U+0029), -and NO-BREAK SPACE (U+00A0). These last three should never have been allowed -in names, and are retained for backwards compatibility only; NO-BREAK SPACE IS -currently deprecated and scheduled for removal in Perl v5.26; the other two -may also be +HYPHEN-MINUS (U+002D), LEFT PARENTHESIS (U+0028), and RIGHT PARENTHESIS +(U+0029). These last two should never have been allowed +in names, and are retained for backwards compatibility only, and may be deprecated and removed in future releases of Perl, so don't use them for new names. (More precisely, the first character of a name you specify must be something that matches all of C<\p{ID_Start}>, C<\p{Alphabetic}>, and diff --git a/gnu/usr.bin/perl/lib/charnames.t b/gnu/usr.bin/perl/lib/charnames.t index cd87350bfe3..14bdebddb05 100644 --- a/gnu/usr.bin/perl/lib/charnames.t +++ b/gnu/usr.bin/perl/lib/charnames.t @@ -188,7 +188,7 @@ sub test_vianame ($$$) { } { - # 20001114.001 + # 20001114.001 (#4690) no utf8; # naked Latin-1 @@ -1009,7 +1009,7 @@ is("\N{U+1D0C5}", "\N{BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS}", 'V die "Can't open ../../lib/unicore/UnicodeData.txt: $!"; while (<$fh>) { chomp; - my ($code, $name, undef, undef, undef, undef, undef, undef, undef, undef, $u1name) = split ";"; + my ($code, $name, $category, undef, undef, undef, undef, undef, undef, undef, $u1name) = split ";"; my $decimal = utf8::unicode_to_native(hex $code); $code = sprintf("%04X", $decimal) unless $::IS_ASCII; @@ -1042,12 +1042,26 @@ is("\N{U+1D0C5}", "\N{BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS}", 'V /^(.*?);/; my $end_decimal = hex $1; - # Only the CJK (and the Hangul which are instead dealt with below) - # ones have names, and they all have the code point as part of the - # name, which we can construct - if ($name =~ /^<CJK/) { + # Only the ones whose category is a letter currently have names, + # and of those the Hangul Syllables are dealt with below + if ( $category eq 'Lo' && $name !~ /^Hangul/i) { + + # The CJK ones all get translated to a particular form; we + # just capitalize any others in the hopes that Unicode will + # use the correct term in any future ones it might add. + if ($name =~ /^<CJK/) { + $name = "CJK UNIFIED IDEOGRAPH"; + } + else { + $name =~ s/<//; + $name =~ s/,.*//; + $name = uc($name); + } + + # They all have the code point as part of the name, which we + # can construct for my $i ($decimal .. $end_decimal) { - $names[$i] = sprintf "CJK UNIFIED IDEOGRAPH-%04X", $i; + $names[$i] = sprintf "$name-%04X", $i; my $block = $i >> $block_size_bits; $algorithmic_names_count[$block]++; } diff --git a/gnu/usr.bin/perl/lib/diagnostics.pm b/gnu/usr.bin/perl/lib/diagnostics.pm index 40c6748c57c..860a0aa846e 100644 --- a/gnu/usr.bin/perl/lib/diagnostics.pm +++ b/gnu/usr.bin/perl/lib/diagnostics.pm @@ -186,7 +186,7 @@ use 5.009001; use Carp; $Carp::Internal{__PACKAGE__.""}++; -our $VERSION = '1.34'; +our $VERSION = '1.36'; our $DEBUG; our $VERBOSE; our $PRETTY; @@ -231,7 +231,7 @@ CONFIG: { $PRETTY = $opt_p; } - if (open(POD_DIAG, $PODFILE)) { + if (open(POD_DIAG, '<', $PODFILE)) { warn "Happy happy podfile from real $PODFILE\n" if $DEBUG; last CONFIG; } @@ -240,7 +240,7 @@ CONFIG: { INCPATH: { for my $file ( (map { "$_/".__PACKAGE__.".pm" } @INC), $0) { warn "Checking $file\n" if $DEBUG; - if (open(POD_DIAG, $file)) { + if (open(POD_DIAG, '<', $file)) { while (<POD_DIAG>) { next unless /^__END__\s*# wish diag dbase were more accessible/; @@ -310,6 +310,7 @@ sub transmo { EOFUNC my %msg; +my $over_level = 0; # We look only at =item lines at the first =over level { print STDERR "FINISHING COMPILATION for $_\n" if $DEBUG; local $/ = ''; @@ -386,7 +387,7 @@ my %msg; push @headers, $header if defined $header; } - unless ( s/=item (.*?)\s*\z//s) { + if ( ! s/=item (.*?)\s*\z//s || $over_level != 1) { if ( s/=head1\sDESCRIPTION//) { $msg{$header = 'DESCRIPTION'} = ''; @@ -395,11 +396,17 @@ my %msg; elsif( s/^=for\s+diagnostics\s*\n(.*?)\s*\z// ) { $for_item = $1; } - elsif( /^=back/ ) { # Stop processing body here - undef $header; - undef $for_item; - $seen_body = 0; - next; + elsif( /^=over\b/ ) { + $over_level++; + } + elsif( /^=back\b/ ) { # Stop processing body here + $over_level--; + if ($over_level == 0) { + undef $header; + undef $for_item; + $seen_body = 0; + next; + } } next; } diff --git a/gnu/usr.bin/perl/lib/diagnostics.t b/gnu/usr.bin/perl/lib/diagnostics.t index 0b35d16c066..6521df2d5cb 100644 --- a/gnu/usr.bin/perl/lib/diagnostics.t +++ b/gnu/usr.bin/perl/lib/diagnostics.t @@ -4,7 +4,7 @@ BEGIN { chdir '..' if -d '../pod' && -d '../t'; @INC = 'lib'; require './t/test.pl'; - plan(29); + plan(31); } BEGIN { @@ -144,17 +144,30 @@ like $warning, { # Find last warning in perldiag.pod, and last items if any my $lw; + my $over_level = 0; my $inlast; my $item; + my $items_not_in_overs = 0; open(my $f, '<', "pod/perldiag.pod") or die "failed to open pod/perldiag.pod for reading: $!"; while (<$f>) { - if ( /^=item\s+(.*)/) { - $lw = $1; - } elsif (/^=back/) { - $inlast = 1; + + # We only look for entries (=item lines) in the first level of =overs + + if ( /^=over\b/) { + $over_level++; + } elsif ( /^=item\s+(.*)/) { + if ($over_level < 1) { + $items_not_in_overs++; + } + elsif ($over_level == 1) { + $lw = $1; + } + } elsif (/^=back\b/) { + $inlast = 1 if $over_level == 1; + $over_level--; } elsif ($inlast) { # Skip headings next if /^=/; @@ -174,6 +187,8 @@ like $warning, } close($f); + is($over_level, 0, "(sanity...) =over balanced with =back (off by $over_level)"); + is($items_not_in_overs, 0, "(sanity...) all =item lines are within =over..=back blocks"); ok($item, "(sanity...) found an item to check with ($item)"); seek STDERR, 0,0; $warning = ''; diff --git a/gnu/usr.bin/perl/lib/feature.pm b/gnu/usr.bin/perl/lib/feature.pm index ec9fff7a6d4..6466eb70c65 100644 --- a/gnu/usr.bin/perl/lib/feature.pm +++ b/gnu/usr.bin/perl/lib/feature.pm @@ -5,7 +5,7 @@ package feature; -our $VERSION = '1.42'; +our $VERSION = '1.52'; our %feature = ( fc => 'feature_fc', @@ -14,14 +14,13 @@ our %feature = ( switch => 'feature_switch', bitwise => 'feature_bitwise', evalbytes => 'feature_evalbytes', - postderef => 'feature_postderef', array_base => 'feature_arybase', signatures => 'feature_signatures', current_sub => 'feature___SUB__', refaliasing => 'feature_refaliasing', - lexical_subs => 'feature_lexsubs', postderef_qq => 'feature_postderef_qq', unicode_eval => 'feature_unieval', + declared_refs => 'feature_myref', unicode_strings => 'feature_unicode', ); @@ -30,7 +29,8 @@ our %feature_bundle = ( "5.11" => [qw(array_base say state switch unicode_strings)], "5.15" => [qw(current_sub evalbytes fc say state switch unicode_eval unicode_strings)], "5.23" => [qw(current_sub evalbytes fc postderef_qq say state switch unicode_eval unicode_strings)], - "all" => [qw(array_base bitwise current_sub evalbytes fc lexical_subs postderef postderef_qq refaliasing say signatures state switch unicode_eval unicode_strings)], + "5.27" => [qw(bitwise current_sub evalbytes fc postderef_qq say state switch unicode_eval unicode_strings)], + "all" => [qw(array_base bitwise current_sub declared_refs evalbytes fc postderef_qq refaliasing say signatures state switch unicode_eval unicode_strings)], "default" => [qw(array_base)], ); @@ -45,11 +45,18 @@ $feature_bundle{"5.20"} = $feature_bundle{"5.15"}; $feature_bundle{"5.21"} = $feature_bundle{"5.15"}; $feature_bundle{"5.22"} = $feature_bundle{"5.15"}; $feature_bundle{"5.24"} = $feature_bundle{"5.23"}; +$feature_bundle{"5.25"} = $feature_bundle{"5.23"}; +$feature_bundle{"5.26"} = $feature_bundle{"5.23"}; +$feature_bundle{"5.28"} = $feature_bundle{"5.27"}; $feature_bundle{"5.9.5"} = $feature_bundle{"5.10"}; +my %noops = ( + postderef => 1, + lexical_subs => 1, +); our $hint_shift = 26; our $hint_mask = 0x1c000000; -our @hint_bundles = qw( default 5.10 5.11 5.15 5.23 ); +our @hint_bundles = qw( default 5.10 5.11 5.15 5.23 5.27 ); # This gets set (for now) in $^H as well as in %^H, # for runtime speed of the uc/lc/ucfirst/lcfirst functions. @@ -169,54 +176,29 @@ potentially using Unicode in your program, the C<use feature 'unicode_strings'> subpragma is B<strongly> recommended. This feature is available starting with Perl 5.12; was almost fully -implemented in Perl 5.14; and extended in Perl 5.16 to cover C<quotemeta>. +implemented in Perl 5.14; and extended in Perl 5.16 to cover C<quotemeta>; +was extended further in Perl 5.26 to cover L<the range +operator|perlop/Range Operators>; and was extended again in Perl 5.28 to +cover L<special-cased whitespace splitting|perlfunc/split>. =head2 The 'unicode_eval' and 'evalbytes' features -Under the C<unicode_eval> feature, Perl's C<eval> function, when passed a -string, will evaluate it as a string of characters, ignoring any -C<use utf8> declarations. C<use utf8> exists to declare the encoding of -the script, which only makes sense for a stream of bytes, not a string of -characters. Source filters are forbidden, as they also really only make -sense on strings of bytes. Any attempt to activate a source filter will -result in an error. - -The C<evalbytes> feature enables the C<evalbytes> keyword, which evaluates -the argument passed to it as a string of bytes. It dies if the string -contains any characters outside the 8-bit range. Source filters work -within C<evalbytes>: they apply to the contents of the string being -evaluated. - -Together, these two features are intended to replace the historical C<eval> -function, which has (at least) two bugs in it, that cannot easily be fixed -without breaking existing programs: - -=over - -=item * - -C<eval> behaves differently depending on the internal encoding of the -string, sometimes treating its argument as a string of bytes, and sometimes -as a string of characters. - -=item * - -Source filters activated within C<eval> leak out into whichever I<file> -scope is currently being compiled. To give an example with the CPAN module -L<Semi::Semicolons>: - - BEGIN { eval "use Semi::Semicolons; # not filtered here " } - # filtered here! +Together, these two features are intended to replace the legacy string +C<eval> function, which behaves problematically in some instances. They are +available starting with Perl 5.16, and are enabled by default by a +S<C<use 5.16>> or higher declaration. -C<evalbytes> fixes that to work the way one would expect: +C<unicode_eval> changes the behavior of plain string C<eval> to work more +consistently, especially in the Unicode world. Certain (mis)behaviors +couldn't be changed without breaking some things that had come to rely on +them, so the feature can be enabled and disabled. Details are at +L<perlfunc/Under the "unicode_eval" feature>. - use feature "evalbytes"; - BEGIN { evalbytes "use Semi::Semicolons; # filtered " } - # not filtered - -=back - -These two features are available starting with Perl 5.16. +C<evalbytes> is like string C<eval>, but operating on a byte stream that is +not UTF-8 encoded. Details are at L<perlfunc/evalbytes EXPR>. Without a +S<C<use feature 'evalbytes'>> nor a S<C<use v5.16>> (or higher) declaration in +the current scope, you can still access it by instead writing +C<CORE::evalbytes>. =head2 The 'current_sub' feature @@ -246,17 +228,21 @@ This feature is available from Perl 5.16 onwards. =head2 The 'lexical_subs' feature -B<WARNING>: This feature is still experimental and the implementation may -change in future versions of Perl. For this reason, Perl will -warn when you use the feature, unless you have explicitly disabled the -warning: +In Perl versions prior to 5.26, this feature enabled +declaration of subroutines via C<my sub foo>, C<state sub foo> +and C<our sub foo> syntax. See L<perlsub/Lexical Subroutines> for details. - no warnings "experimental::lexical_subs"; +This feature is available from Perl 5.18 onwards. From Perl 5.18 to 5.24, +it was classed as experimental, and Perl emitted a warning for its +usage, except when explicitly disabled: -This enables declaration of subroutines via C<my sub foo>, C<state sub foo> -and C<our sub foo> syntax. See L<perlsub/Lexical Subroutines> for details. + no warnings "experimental::lexical_subs"; -This feature is available from Perl 5.18 onwards. +As of Perl 5.26, use of this feature no longer triggers a warning, though +the C<experimental::lexical_subs> warning category still exists (for +compatibility with code that disables it). In addition, this syntax is +not only no longer experimental, but it is enabled for all Perl code, +regardless of what feature declarations are in scope. =head2 The 'postderef' and 'postderef_qq' features @@ -330,13 +316,6 @@ This feature is available from Perl 5.22 onwards. =head2 The 'bitwise' feature -B<WARNING>: This feature is still experimental and the implementation may -change in future versions of Perl. For this reason, Perl will -warn when you use the feature, unless you have explicitly disabled the -warning: - - no warnings "experimental::bitwise"; - This makes the four standard bitwise operators (C<& | ^ ~>) treat their operands consistently as numbers, and introduces four new dotted operators (C<&. |. ^. ~.>) that treat their operands consistently as strings. The @@ -344,7 +323,26 @@ same applies to the assignment variants (C<&= |= ^= &.= |.= ^.=>). See L<perlop/Bitwise String Operators> for details. -This feature is available from Perl 5.22 onwards. +This feature is available from Perl 5.22 onwards. Starting in Perl 5.28, +C<use v5.28> will enable the feature. Before 5.28, it was still +experimental and would emit a warning in the "experimental::bitwise" +category. + +=head2 The 'declared_refs' feature + +B<WARNING>: This feature is still experimental and the implementation may +change in future versions of Perl. For this reason, Perl will +warn when you use the feature, unless you have explicitly disabled the +warning: + + no warnings "experimental::declared_refs"; + +This allows a reference to a variable to be declared with C<my>, C<state>, +our C<our>, or localized with C<local>. It is intended mainly for use in +conjunction with the "refaliasing" feature. See L<perlref/Declaring a +Reference to a Variable> for examples. + +This feature is available from Perl 5.26 onwards. =head1 FEATURE BUNDLES @@ -382,6 +380,14 @@ The following feature bundles are available: unicode_eval evalbytes current_sub fc postderef_qq + :5.26 say state switch unicode_strings + unicode_eval evalbytes current_sub fc + postderef_qq + + :5.28 say state switch unicode_strings + unicode_eval evalbytes current_sub fc + postderef_qq bitwise + The C<:default> bundle represents the feature set that is enabled before any C<use feature> or C<no feature> declaration. @@ -431,6 +437,9 @@ with the same effect. If the required version is older than Perl 5.10, the ":default" feature bundle is automatically loaded instead. +Unlike C<use feature ":5.12">, saying C<use v5.12> (or any higher version) +also does the equivalent of C<use strict>; see L<perlfunc/use> for details. + =back =cut @@ -487,6 +496,9 @@ sub __common { next; } if (!exists $feature{$name}) { + if (exists $noops{$name}) { + next; + } unknown_feature($name); } if ($import) { diff --git a/gnu/usr.bin/perl/lib/h2ph.t b/gnu/usr.bin/perl/lib/h2ph.t index 64d9dc080f4..377cc631313 100644 --- a/gnu/usr.bin/perl/lib/h2ph.t +++ b/gnu/usr.bin/perl/lib/h2ph.t @@ -1,5 +1,4 @@ #!./perl -use strict; # quickie tests to see if h2ph actually runs and does more or less what is # expected @@ -24,7 +23,7 @@ plan(6); sub txt_compare { local $/; my ($A, $B); - for (($A,$B) = @_) { open(_,"<$_") ? $_ = <_> : die "$_ : $!"; close _ } + for (($A,$B) = @_) { open(_,"<",$_) ? $_ = <_> : die "$_ : $!"; close _ } $A cmp $B; } diff --git a/gnu/usr.bin/perl/lib/h2xs.t b/gnu/usr.bin/perl/lib/h2xs.t index 25502dadd16..69746a52b30 100644 --- a/gnu/usr.bin/perl/lib/h2xs.t +++ b/gnu/usr.bin/perl/lib/h2xs.t @@ -167,7 +167,7 @@ for (my $i = $#tests; $i > 0; $i-=3) { plan tests => $total_tests; -ok (open (HEADER, ">$header"), "open '$header'"); +ok (open (HEADER, '>', $header), "open '$header'"); print HEADER <<HEADER or die $!; #define Camel 2 #define Dromedary 1 @@ -238,7 +238,7 @@ while (my ($args, $version, $expectation) = splice @tests, 0, 3) { foreach my $leaf (File::Spec->catfile('lib', "$name.pm"), 'Makefile.PL') { my $file = File::Spec->catfile($name, $leaf); - if (ok (open (FILE, $file), "open $file")) { + if (ok (open (FILE, '<', $file), "open $file")) { my $match = qr/use $version;/; my $found; while (<FILE>) { diff --git a/gnu/usr.bin/perl/lib/locale.t b/gnu/usr.bin/perl/lib/locale.t index dc31b4689a8..17931c894d6 100644 --- a/gnu/usr.bin/perl/lib/locale.t +++ b/gnu/usr.bin/perl/lib/locale.t @@ -5,9 +5,31 @@ # without using 'eval' as much as possible, which might cloud the issue, the # crucial parts of the code are duplicated in a block for each pragma. +# Unfortunately, many systems have defective locale definitions. This test +# file looks for both perl bugs and bugs in the system's locale definitions. +# It can be difficult to tease apart which is which. For the latter, there +# are tests that are based on the POSIX standard. A character isn't supposed +# to be both a space and graphic, for example. Another example is if a +# character is the uppercase of another, that other should be the lowercase of +# the first. Including tests for these allows you to test for defective +# locales, as described in perllocale. The way this file distinguishes +# between defective locales, and perl bugs is to see what percentage of +# locales fail a given test. If it's a lot, then it's more likely to be a +# perl bug; only a few, those particular locales are likely defective. In +# that case the failing tests are marked TODO. (They should be reported to +# the vendor, however; but it's not perl's problem.) In some cases, this +# script has caused tickets to be filed against perl which turn out to be the +# platform's bug, but a higher percentage of locales are failing than the +# built-in cut-off point. For those platforms, code has been added to +# increase the cut-off, so those platforms don't trigger failing test reports. +# Ideally, the platforms would get fixed and that code would be changed to +# only kick-in when run on versions that are earlier than the fixed one. But, +# this rarely happens in practice. + # To make a TODO test, add the string 'TODO' to its %test_names value my $is_ebcdic = ord("A") == 193; +my $os = lc $^O; no warnings 'locale'; # We test even weird locales; and do some scary things # in ok locales @@ -29,18 +51,22 @@ BEGIN { } use strict; -use feature 'fc', 'postderef'; +use feature 'fc'; # =1 adds debugging output; =2 increases the verbosity somewhat -my $debug = $ENV{PERL_DEBUG_FULL_TEST} // 0; +our $debug = $ENV{PERL_DEBUG_FULL_TEST} // 0; # Certain tests have been shown to be problematical for a few locales. Don't # fail them unless at least this percentage of the tested locales fail. # On AIX machines, many locales call a no-break space a graphic. # (There aren't 1000 locales currently in existence, so 99.9 works) -my $acceptable_failure_percentage = ($^O =~ / ^ ( AIX ) $ /ix) +# EBCDIC os390 has more locales fail than normal, because it has locales that +# move various critical characters like '['. +my $acceptable_failure_percentage = ($os =~ / ^ ( aix ) $ /x) ? 99.9 - : 5; + : ($os =~ / ^ ( os390 ) $ /x) + ? 10 + : 5; # The list of test numbers of the problematic tests. my %problematical_tests; @@ -51,11 +77,17 @@ my %known_bad_locales = ( irix => qr/ ^ (?: cs | hu | sk ) $/x, darwin => qr/ ^ lt_LT.ISO8859 /ix, os390 => qr/ ^ italian /ix, + netbsd => qr/\bISO8859-2\b/i, + + # This may be the same bug as the cygwin below; it's + # generating malformed UTF-8 on the radix being + # mulit-byte + solaris => qr/ ^ ( ar_ | pa_ ) /x, ); # cygwin isn't returning proper radix length in this locale, but supposedly to # be fixed in later versions. -if ($^O eq 'cygwin' && version->new(($Config{osvers} =~ /^(\d+(?:\.\d+)+)/)[0]) le v2.4.1) { +if ($os eq 'cygwin' && version->new(($Config{osvers} =~ /^(\d+(?:\.\d+)+)/)[0]) le v2.4.1) { $known_bad_locales{'cygwin'} = qr/ ^ ps_AF /ix; } @@ -66,6 +98,7 @@ my $dumper = Dumpvalue->new( quoteHighBit => 0, unctrl => "quote" ); + sub debug { return unless $debug; my($mess) = join "", '# ', @_; @@ -73,6 +106,11 @@ sub debug { print STDERR $dumper->stringify($mess,1), "\n"; } +sub note { + local $debug = 1; + debug @_; +} + sub debug_more { return unless $debug > 1; return debug(@_); @@ -97,6 +135,14 @@ sub ok { return ($result) ? 1 : 0; } +sub skip { + return ok 1, "skipped: " . shift; +} + +sub fail { + return ok 0, shift; +} + # First we'll do a lot of taint checking for locales. # This is the easiest to test, actually, as any locale, # even the default locale will taint under 'use locale'. @@ -736,7 +782,54 @@ debug "Scanning for locales...\n"; require POSIX; import POSIX ':locale_h'; -my @Locale = find_locales([ &POSIX::LC_CTYPE, &POSIX::LC_NUMERIC, &POSIX::LC_ALL ]); +my $categories = [ 'LC_CTYPE', 'LC_NUMERIC', 'LC_ALL' ]; +debug "Scanning for just compatible"; +my @Locale = find_locales($categories); +debug "Scanning for even incompatible"; +my @include_incompatible_locales = find_locales($categories, + 'even incompatible locales'); + +# The locales included in the incompatible list that aren't in the compatible +# one. +my @incompatible_locales; + +if (@Locale < @include_incompatible_locales) { + my %seen; + @seen{@Locale} = (); + + foreach my $item (@include_incompatible_locales) { + push @incompatible_locales, $item unless exists $seen{$item}; + } + + # For each bad locale, switch into it to find out why it's incompatible + for my $bad_locale (@incompatible_locales) { + my @warnings; + + use warnings 'locale'; + + local $SIG{__WARN__} = sub { + my $warning = $_[0]; + chomp $warning; + push @warnings, ($warning =~ s/\n/\n# /sgr); + }; + + debug "Trying incompatible $bad_locale"; + my $ret = setlocale(&POSIX::LC_CTYPE, $bad_locale); + + my $message = "testing of locale '$bad_locale' is skipped"; + if (@warnings) { + skip $message . ":\n# " . join "\n# ", @warnings; + } + elsif (! $ret) { + skip("$message:\n#" + . " setlocale(&POSIX::LC_CTYPE, '$bad_locale') failed"); + } + else { + fail $message . ", because it is was found to be incompatible with" + . " Perl, but could not discern reason"; + } + } +} debug "Locales =\n"; for ( @Locale ) { @@ -900,14 +993,14 @@ sub disp_str ($) { sub report_result { my ($Locale, $i, $pass_fail, $message) = @_; - $message //= ""; - $message = " ($message)" if $message; if ($pass_fail) { push @{$Okay{$i}}, $Locale; } else { - $Known_bad_locale{$i}{$Locale} = 1 if exists $known_bad_locales{$^O} - && $Locale =~ $known_bad_locales{$^O}; + $message //= ""; + $message = " ($message)" if $message; + $Known_bad_locale{$i}{$Locale} = 1 if exists $known_bad_locales{$os} + && $Locale =~ $known_bad_locales{$os}; $Problem{$i}{$Locale} = 1; debug "failed $i ($test_names{$i}) with locale '$Locale'$message\n"; } @@ -926,7 +1019,8 @@ sub report_multi_result { report_result($Locale, $i, @$results_ref == 0, $message); } -my $first_locales_test_number = $final_without_setlocale + 1; +my $first_locales_test_number = $final_without_setlocale + + 1 + @incompatible_locales; my $locales_test_number; my $not_necessarily_a_problem_test_number; my $first_casing_test_number; @@ -973,7 +1067,7 @@ foreach my $Locale (@Locale) { @{$posixes{'punct'}} = grep /[[:punct:]]/, map {chr } 0..255; @{$posixes{'upper'}} = grep /[[:upper:]]/, map {chr } 0..255; @{$posixes{'xdigit'}} = grep /[[:xdigit:]]/, map {chr } 0..255; - @{$posixes{'cased'}} = grep /[[:upper:]]/i, map {chr } 0..255; + @{$posixes{'cased'}} = grep /[[:upper:][:lower:]]/i, map {chr } 0..255; # Sieve the uppercase and the lowercase. @@ -1004,7 +1098,7 @@ foreach my $Locale (@Locale) { @{$posixes{'punct'}} = grep /[[:punct:]]/, map {chr } 0..255; @{$posixes{'upper'}} = grep /[[:upper:]]/, map {chr } 0..255; @{$posixes{'xdigit'}} = grep /[[:xdigit:]]/, map {chr } 0..255; - @{$posixes{'cased'}} = grep /[[:upper:]]/i, map {chr } 0..255; + @{$posixes{'cased'}} = grep /[[:upper:][:lower:]]/i, map {chr } 0..255; for (@{$posixes{'word'}}) { if (/[^\d_]/) { # skip digits and the _ if (uc($_) eq $_) { @@ -1024,13 +1118,13 @@ foreach my $Locale (@Locale) { debug ":cased: = ", disp_chars(@{$posixes{'cased'}}), "\n"; debug ":alpha: = ", disp_chars(@{$posixes{'alpha'}}), "\n"; debug ":alnum: = ", disp_chars(@{$posixes{'alnum'}}), "\n"; - debug " w = ", disp_chars(@{$posixes{'word'}}), "\n"; + debug ' \w = ', disp_chars(@{$posixes{'word'}}), "\n"; debug ":graph: = ", disp_chars(@{$posixes{'graph'}}), "\n"; debug ":print: = ", disp_chars(@{$posixes{'print'}}), "\n"; - debug " d = ", disp_chars(@{$posixes{'digit'}}), "\n"; + debug ' \d = ', disp_chars(@{$posixes{'digit'}}), "\n"; debug ":xdigit: = ", disp_chars(@{$posixes{'xdigit'}}), "\n"; debug ":blank: = ", disp_chars(@{$posixes{'blank'}}), "\n"; - debug " s = ", disp_chars(@{$posixes{'space'}}), "\n"; + debug ' \s = ', disp_chars(@{$posixes{'space'}}), "\n"; debug ":punct: = ", disp_chars(@{$posixes{'punct'}}), "\n"; debug ":cntrl: = ", disp_chars(@{$posixes{'cntrl'}}), "\n"; debug ":ascii: = ", disp_chars(@{$posixes{'ascii'}}), "\n"; @@ -1198,7 +1292,7 @@ foreach my $Locale (@Locale) { (/[[:xdigit:]]/ xor /[[:^xdigit:]]/) || # effectively is what [:cased:] would be if it existed. - (/[[:upper:]]/i xor /[[:^upper:]]/i); + (/[[:upper:][:lower:]]/i xor /[^[:upper:][:lower:]]/i); } else { push @f, $_ unless (/[[:alpha:]]/ xor /[[:^alpha:]]/) || @@ -1214,7 +1308,7 @@ foreach my $Locale (@Locale) { (/[[:upper:]]/ xor /[[:^upper:]]/) || (/[[:word:]]/ xor /[[:^word:]]/) || (/[[:xdigit:]]/ xor /[[:^xdigit:]]/) || - (/[[:upper:]]/i xor /[[:^upper:]]/i); + (/[[:upper:][:lower:]]/i xor /[^[:upper:][:lower:]]/i); } } report_multi_result($Locale, $locales_test_number, \@f); @@ -1735,6 +1829,121 @@ foreach my $Locale (@Locale) { last; } } + + use locale; + + my @sorted_controls; + + ++$locales_test_number; + $test_names{$locales_test_number} + = 'Skip in locales where there are no controls;' + . ' otherwise verify that \0 sorts before any (other) control'; + if (! $posixes{'cntrl'}) { + report_result($Locale, $locales_test_number, 1); + + # We use all code points for the tests below since there aren't + # any controls + push @sorted_controls, chr $_ for 1..255; + @sorted_controls = sort @sorted_controls; + } + else { + @sorted_controls = @{$posixes{'cntrl'}}; + push @sorted_controls, "\0", + unless grep { $_ eq "\0" } @sorted_controls; + @sorted_controls = sort @sorted_controls; + my $output = ""; + for my $control (@sorted_controls) { + $output .= " " . disp_chars($control); + } + debug "sorted :cntrl: (plus NUL) = $output\n"; + my $ok = $sorted_controls[0] eq "\0"; + report_result($Locale, $locales_test_number, $ok); + + shift @sorted_controls if $ok; + } + + my $lowest_control = $sorted_controls[0]; + + ++$locales_test_number; + $test_names{$locales_test_number} + = 'Skip in locales where all controls have primary sorting weight; ' + . 'otherwise verify that \0 doesn\'t have primary sorting weight'; + if ("a${lowest_control}c" lt "ab") { + report_result($Locale, $locales_test_number, 1); + } + else { + my $ok = "ab" lt "a\0c"; + report_result($Locale, $locales_test_number, $ok); + } + + ++$locales_test_number; + $test_names{$locales_test_number} + = 'Verify that strings with embedded NUL collate'; + my $ok = "a\0a\0a" lt "a${lowest_control}a${lowest_control}a"; + report_result($Locale, $locales_test_number, $ok); + + ++$locales_test_number; + $test_names{$locales_test_number} + = 'Verify that strings with embedded NUL and ' + . 'extra trailing NUL collate'; + $ok = "a\0a\0" lt "a${lowest_control}a${lowest_control}"; + report_result($Locale, $locales_test_number, $ok); + + ++$locales_test_number; + $test_names{$locales_test_number} + = 'Verify that empty strings collate'; + $ok = "" le ""; + report_result($Locale, $locales_test_number, $ok); + + ++$locales_test_number; + $test_names{$locales_test_number} + = "Skip in non-UTF-8 locales; otherwise verify that UTF8ness " + . "doesn't matter with collation"; + if (! $is_utf8_locale) { + report_result($Locale, $locales_test_number, 1); + } + else { + + # khw can't think of anything better. Start with a string that is + # higher than its UTF-8 representation in both EBCDIC and ASCII + my $string = chr utf8::unicode_to_native(0xff); + my $utf8_string = $string; + utf8::upgrade($utf8_string); + + # 8 should be lt 9 in all locales (except ones that aren't + # ASCII-based, which might fail this) + $ok = ("a${string}8") lt ("a${utf8_string}9"); + report_result($Locale, $locales_test_number, $ok); + } + + ++$locales_test_number; + $test_names{$locales_test_number} + = "Skip in UTF-8 locales; otherwise verify that single byte " + . "collates before 0x100 and above"; + if ($is_utf8_locale) { + report_result($Locale, $locales_test_number, 1); + } + else { + my $max_collating = chr 0; # Find byte that collates highest + for my $i (0 .. 255) { + my $char = chr $i; + $max_collating = $char if $char gt $max_collating; + } + $ok = $max_collating lt chr 0x100; + report_result($Locale, $locales_test_number, $ok); + } + + ++$locales_test_number; + $test_names{$locales_test_number} + = "Skip in UTF-8 locales; otherwise verify that 0x100 and " + . "above collate in code point order"; + if ($is_utf8_locale) { + report_result($Locale, $locales_test_number, 1); + } + else { + $ok = chr 0x100 lt chr 0x101; + report_result($Locale, $locales_test_number, $ok); + } } my $ok1; @@ -1884,11 +2093,15 @@ foreach my $Locale (@Locale) { foreach my $err (keys %!) { use Errno; $! = eval "&Errno::$err"; # Convert to strerror() output + my $errnum = 0+$!; my $strerror = "$!"; if ("$strerror" =~ /\P{ASCII}/) { $ok14 = utf8::is_utf8($strerror); no locale; $ok14_5 = "$!" !~ /\P{ASCII}/; + debug( disp_str( + "non-ASCII \$! for error $errnum='$strerror'")) + if ! $ok14_5; last; } } @@ -1934,8 +2147,9 @@ foreach my $Locale (@Locale) { use Errno; $! = eval "&Errno::$err"; # Convert to strerror() output my $strerror = "$!"; - if ("$strerror" =~ /\P{ASCII}/) { + if ($strerror =~ /\P{ASCII}/) { $ok21 = 0; + debug(disp_str("non-ASCII strerror=$strerror")); last; } } @@ -2028,6 +2242,7 @@ foreach my $Locale (@Locale) { report_result($Locale, ++$locales_test_number, $ok15); $test_names{$locales_test_number} = 'Verify that a number with a UTF-8 radix has a UTF-8 stringification'; + $problematical_tests{$locales_test_number} = 1; report_result($Locale, ++$locales_test_number, $ok16); $test_names{$locales_test_number} = 'Verify that a sprintf of a number with a UTF-8 radix yields UTF-8'; @@ -2049,12 +2264,12 @@ foreach my $Locale (@Locale) { # OS X 10.9.3 report_result($Locale, ++$locales_test_number, $ok21); - $test_names{$locales_test_number} = '"$!" is ASCII only outside of locale scope'; + $test_names{$locales_test_number} = '"$!" is ASCII-only outside of locale scope'; debug "$first_f_test..$locales_test_number: \$f = $f, \$g = $g, back to locale = $Locale\n"; # Does taking lc separately differ from taking - # the lc "in-line"? (This was the bug 19990704.002, change #3568.) + # the lc "in-line"? (This was the bug 19990704.002 (#965), change #3568.) # The bug was in the caching of the 'o'-magic. if (! $is_utf8_locale) { use locale; @@ -2268,28 +2483,30 @@ my $final_locales_test_number = $locales_test_number; TEST_NUM: foreach $test_num ($first_locales_test_number..$final_locales_test_number) { - if (%setlocale_failed) { - print "not "; + my $has_non_global_failure = $Problem{$test_num} + || ! defined $Okay{$test_num} + || ! @{$Okay{$test_num}}; + print "not " if %setlocale_failed || $has_non_global_failure; + print "ok $test_num"; + $test_names{$test_num} = "" unless defined $test_names{$test_num}; + + # If TODO is in the test name, make it thus + my $todo = $test_names{$test_num} =~ s/\s*TODO\s*//; + print " $test_names{$test_num}"; + if ($todo) { + print " # TODO\n"; } - elsif ($Problem{$test_num} - || ! defined $Okay{$test_num} - || ! @{$Okay{$test_num}}) - { - if (defined $not_necessarily_a_problem_test_number - && $test_num == $not_necessarily_a_problem_test_number) - { - print "# The failure of test $not_necessarily_a_problem_test_number is not necessarily fatal.\n"; - print "# It usually indicates a problem in the environment,\n"; - print "# not in Perl itself.\n"; - } + elsif (%setlocale_failed || ! $has_non_global_failure) { + print "\n"; + } + elsif ($has_non_global_failure) { # If there are any locales that pass this test, or are known-bad, it - # may be that there are enough passes that we TODO the failure. - if (($Okay{$test_num} || $Known_bad_locale{$test_num}) + # may be that there are enough passes that we TODO the failure, but + # only for tests that we have decided can be problematical. + if ( ($Okay{$test_num} || $Known_bad_locale{$test_num}) && grep { $_ == $test_num } keys %problematical_tests) { - no warnings 'experimental::postderef'; - # Don't count the known-bad failures when calculating the # percentage that fail. my $known_failures = (exists $Known_bad_locale{$test_num}) @@ -2301,8 +2518,7 @@ foreach $test_num ($first_locales_test_number..$final_locales_test_number) { # Specially handle failures where only known-bad locales fail. # This makes the diagnositics clearer. if ($adjusted_failures <= 0) { - print "not ok $test_num $test_names{$test_num} # TODO fails only on ", - "known bad locales: ", + print " # TODO fails only on known bad locales: ", join " ", keys $Known_bad_locale{$test_num}->%*, "\n"; next TEST_NUM; } @@ -2311,15 +2527,10 @@ foreach $test_num ($first_locales_test_number..$final_locales_test_number) { my $percent_fail = (int(.5 + (1000 * $adjusted_failures / scalar(@Locale)))) / 10; - if ($percent_fail < $acceptable_failure_percentage) { - if (! $debug) { - $test_names{$test_num} .= 'TODO'; - print "# ", 100 - $percent_fail, "% of locales not known to be problematic on this platform\n"; - print "# pass the following test, so it is likely that the failures\n"; - print "# are errors in the locale definitions. The test is marked TODO, as the\n"; - print "# problem is not likely to be Perl's\n"; - } - } + $todo = $percent_fail < $acceptable_failure_percentage; + print " # TODO" if $todo; + print "\n"; + if ($debug) { print "# $percent_fail% of locales (", scalar(keys $Problem{$test_num}->%*), @@ -2329,8 +2540,14 @@ foreach $test_num ($first_locales_test_number..$final_locales_test_number) { $acceptable_failure_percentage, "%)\n"; } + elsif ($todo) { + print "# ", 100 - $percent_fail, "% of locales not known to be problematic on this platform\n"; + print "# pass the above test, so it is likely that the failures\n"; + print "# are errors in the locale definitions. The test is marked TODO, as the\n"; + print "# problem is not likely to be Perl's\n"; + } } - print "#\n"; + if ($debug) { print "# The code points that had this failure are given above. Look for lines\n"; print "# that match 'failed $test_num'\n"; @@ -2339,21 +2556,19 @@ foreach $test_num ($first_locales_test_number..$final_locales_test_number) { print "# For more details, rerun, with environment variable PERL_DEBUG_FULL_TEST=1.\n"; print "# Then look at that output for lines that match 'failed $test_num'\n"; } - print "not "; - } - print "ok $test_num"; - if (defined $test_names{$test_num}) { - # If TODO is in the test name, make it thus - my $todo = $test_names{$test_num} =~ s/TODO\s*//; - print " $test_names{$test_num}"; - print " # TODO" if $todo; + if (defined $not_necessarily_a_problem_test_number + && $test_num == $not_necessarily_a_problem_test_number) + { + print "# The failure of test $not_necessarily_a_problem_test_number is not necessarily fatal.\n"; + print "# It usually indicates a problem in the environment,\n"; + print "# not in Perl itself.\n"; + } } - print "\n"; } $test_num = $final_locales_test_number; -unless ( $^O =~ m!^(dragonfly|openbsd|bitrig|mirbsd)$! ) { +unless ( $os =~ m!^(dragonfly|openbsd|bitrig|mirbsd)$! ) { # perl #115808 use warnings; my $warned = 0; @@ -2498,8 +2713,8 @@ foreach ($first_locales_test_number..$final_locales_test_number) { my @f = sort keys %{ $Problem{$_} }; # Don't list the failures caused by known-bad locales. - if (exists $known_bad_locales{$^O}) { - @f = grep { $_ !~ $known_bad_locales{$^O} } @f; + if (exists $known_bad_locales{$os}) { + @f = grep { $_ !~ $known_bad_locales{$os} } @f; next unless @f; } my $f = join(" ", @f); @@ -2515,7 +2730,7 @@ foreach ($first_locales_test_number..$final_locales_test_number) { print <<EOW; # # If your users are not using these locales you are safe for the moment, -# but please report this failure first to perlbug\@perl.com using the +# but please report this failure first to perlbug\@perl.org using the # perlbug script (as described in the INSTALL file) so that the exact # details of the failures can be sorted out first and then your operating # system supplier can be alerted about these anomalies. @@ -2580,7 +2795,7 @@ if ($didwarn) { } } -if (exists $known_bad_locales{$^O} && ! %Known_bad_locale) { +if (exists $known_bad_locales{$os} && ! %Known_bad_locale) { $test_num++; print "ok $test_num $^O no longer has known bad locales # TODO\n"; } diff --git a/gnu/usr.bin/perl/lib/overload.pm b/gnu/usr.bin/perl/lib/overload.pm index 4a1912c2366..f7d5d0f7cf9 100644 --- a/gnu/usr.bin/perl/lib/overload.pm +++ b/gnu/usr.bin/perl/lib/overload.pm @@ -1,6 +1,6 @@ package overload; -our $VERSION = '1.26'; +our $VERSION = '1.30'; %ops = ( with_assign => "+ - * / % ** << >> x .", @@ -21,9 +21,7 @@ our $VERSION = '1.26'; ); my %ops_seen; -for $category (keys %ops) { - $ops_seen{$_}++ for (split /\s+/, $ops{$category}); -} +@ops_seen{ map split(/ /), values %ops } = (); sub nil {} @@ -40,7 +38,7 @@ sub OVERLOAD { } } else { warnings::warnif("overload arg '$_' is invalid") - unless $ops_seen{$_}; + unless exists $ops_seen{$_}; $sub = $arg{$_}; if (not ref $sub) { $ {$package . "::(" . $_} = $sub; @@ -65,7 +63,7 @@ sub unimport { *{$package . "::(("} = \&nil; for (@_) { warnings::warnif("overload arg '$_' is invalid") - unless $ops_seen{$_}; + unless exists $ops_seen{$_}; delete $ {$package . "::"}{$_ eq 'fallback' ? '()' : "(" .$_}; } } @@ -312,7 +310,7 @@ An appropriate implementation of C<--> might look like # ... sub decr { --${$_[0]}; } -If the experimental "bitwise" feature is enabled (see L<feature>), a fifth +If the "bitwise" feature is enabled (see L<feature>), a fifth TRUE argument is passed to subroutines handling C<&>, C<|>, C<^> and C<~>. This indicates that the caller is expecting numeric behaviour. The fourth argument will be C<undef>, as that position (C<$_[3]>) is reserved for use @@ -695,7 +693,7 @@ The specified function will be passed four parameters. The first three arguments coincide with those that would have been passed to the corresponding method if it had been defined. The fourth argument is the C<use overload> key for that missing -method. If the experimental "bitwise" feature is enabled (see L<feature>), +method. If the "bitwise" feature is enabled (see L<feature>), a fifth TRUE argument is passed to subroutines handling C<&>, C<|>, C<^> and C<~> to indicate that the caller is expecting numeric behaviour. For example, if C<$a> is an object blessed into a package declaring diff --git a/gnu/usr.bin/perl/lib/overload.t b/gnu/usr.bin/perl/lib/overload.t index ef4ce4e593d..055daab30ff 100644 --- a/gnu/usr.bin/perl/lib/overload.t +++ b/gnu/usr.bin/perl/lib/overload.t @@ -48,7 +48,7 @@ package main; $| = 1; BEGIN { require './test.pl'; require './charset_tools.pl' } -plan tests => 5215; +plan tests => 5362; use Scalar::Util qw(tainted); @@ -1021,7 +1021,7 @@ unless ($aaa) { main::ok($x+0 =~ qr/Recurse=ARRAY/); } -# BugID 20010422.003 +# BugID 20010422.003 (#6872) package Foo; use overload @@ -2816,6 +2816,16 @@ package bitops2 { 'experimental "bitwise" ops with nomethod' } +package length_utf8 { + use overload '""' => sub { "\x{100}" }; + my $o = bless []; +print length $o, "\n"; + + ::is length($o), 1, "overloaded utf8 length"; + ::is "$o", "\x{100}", "overloaded utf8 value"; +} + + { # undefining the overload stash -- KEEP THIS TEST LAST package ant; use overload '+' => 'onion'; @@ -2826,4 +2836,341 @@ package bitops2 { } -# EOF +# test various aspects of string concat overloading, especially where +# multiple concats etc are optimised into a single multiconcat op + +package Concat { + + my $id; + + # append a brief description of @_ to $id + sub id { + my @a = map ref $_ ? "[" . $_->[0] . "]" : + !defined $_ ? "u" : + $_, + @_; + $id .= '(' . join (',', @a) . ')'; + } + + use overload + '.' => sub { + id('.', @_); + my ($l, $r, $rev) = @_; + ($l, $r) = map ref $_ ? $_->[0] : $_, $l, $r; + ($l,$r) = ($r, $l) if $rev; + bless [ $l . $r ]; + }, + + '.=' => sub { + id('.=', @_); + my ($l, $r, $rev) = @_; + my ($ll, $rr) = map ref $_ ? $_->[0] : $_, $l, $r; + die "Unexpected reverse in .=" if $rev; + $l->[0] .= ref $r ? $r->[0] : $r; + $l; + }, + + '=' => sub { + id('=', @_); + bless [ $_[0][0] ]; + }, + + '""' => sub { + id('""', @_); + $_[0][0]; + }, + ; + + my $a = 'a'; + my $b = 'b'; + my $c = 'c'; + my $A = bless [ 'A' ]; + my $B = bless [ 'B' ]; + my $C = bless [ 'C' ]; + + my ($r, $R); + + + # like cc, but with $is_ref set to 1 + sub c { + my ($expr, $expect, $exp_id) = @_; + cc($expr, $expect, 1, $exp_id); + } + + # eval $expr, and see if it returns $expect, and whether + # the returned value is a ref ($is_ref). Finally, check that + # $id, which has accumulated info from all overload method calls, + # matches $exp_id. + + sub cc { + my ($expr, $expect, $is_ref, $exp_id) = @_; + + $id = ''; + $r = 'r'; + $R = bless ['R']; + + my $got = eval $expr; + die "eval failed: $@" if $@; + ::is "$got", $expect, "expect: $expr"; + ::is $id, $exp_id, "id: $expr"; + ::is ref($got), ($is_ref ? 'Concat' : ''), "is_ref: $expr"; + } + + # single concats + + c '$r=$A.$b', 'Ab', '(.,[A],b,)("",[Ab],u,)'; + c '$r=$a.$B', 'aB', '(.,[B],a,1)("",[aB],u,)'; + c '$r=$A.$B', 'AB', '(.,[A],[B],)("",[AB],u,)'; + c '$R.=$a', 'Ra', '(.=,[R],a,u)("",[Ra],u,)'; + c '$R.=$A', 'RA', '(.=,[R],[A],u)("",[RA],u,)'; + + # two concats + + c '$r=$A.$b.$c', 'Abc', '(.,[A],b,)(.=,[Ab],c,u)("",[Abc],u,)'; + c '$r=$A.($b.$c)', 'Abc', '(.,[A],bc,)("",[Abc],u,)'; + c '$r=$a.$B.$c', 'aBc', '(.,[B],a,1)(.=,[aB],c,u)("",[aBc],u,)'; + c '$r=$a.($B.$c)', 'aBc', '(.,[B],c,)(.,[Bc],a,1)("",[aBc],u,)'; + c '$r=$a.$b.$C', 'abC', '(.,[C],ab,1)("",[abC],u,)'; + c '$r=$a.($b.$C)', 'abC', '(.,[C],b,1)(.,[bC],a,1)("",[abC],u,)'; + + # two concats plus mutator + + c '$r.=$A.$b.$c', 'rAbc', '(.,[A],b,)(.=,[Ab],c,u)(.,[Abc],r,1)' + .'("",[rAbc],u,)'; + c '$r.=$A.($b.$c)', 'rAbc', '(.,[A],bc,)(.,[Abc],r,1)("",[rAbc],u,)'; + c '$r.=$a.$B.$c', 'raBc', '(.,[B],a,1)(.=,[aB],c,u)(.,[aBc],r,1)' + .'("",[raBc],u,)'; + c '$r.=$a.($B.$c)', 'raBc', '(.,[B],c,)(.,[Bc],a,1)(.,[aBc],r,1)' + .'("",[raBc],u,)'; + c '$r.=$a.$b.$C', 'rabC', '(.,[C],ab,1)(.,[abC],r,1)("",[rabC],u,)'; + c '$r.=$a.($b.$C)', 'rabC', '(.,[C],b,1)(.,[bC],a,1)(.,[abC],r,1)' + .'("",[rabC],u,)'; + + c '$R.=$A.$b.$c', 'RAbc', '(.,[A],b,)(.=,[Ab],c,u)(.=,[R],[Abc],u)' + .'("",[RAbc],u,)'; + c '$R.=$A.($b.$c)', 'RAbc', '(.,[A],bc,)(.=,[R],[Abc],u)("",[RAbc],u,)'; + c '$R.=$a.$B.$c', 'RaBc', '(.,[B],a,1)(.=,[aB],c,u)(.=,[R],[aBc],u)' + .'("",[RaBc],u,)'; + c '$R.=$a.($B.$c)', 'RaBc', '(.,[B],c,)(.,[Bc],a,1)(.=,[R],[aBc],u)' + .'("",[RaBc],u,)'; + c '$R.=$a.$b.$C', 'RabC', '(.,[C],ab,1)(.=,[R],[abC],u)("",[RabC],u,)'; + c '$R.=$a.($b.$C)', 'RabC', '(.,[C],b,1)(.,[bC],a,1)(.=,[R],[abC],u)' + .'("",[RabC],u,)'; + + # concat over assign + + c '($R.=$a).$B.$c', 'RaBc', '(.=,[R],a,u)(.,[Ra],[B],)(.=,[RaB],c,u)' + .'("",[RaBc],u,)'; + ::is "$R", "Ra", 'R in concat over assign'; + + + # nested mutators + + c '(($R.=$a).=$b).=$c', 'Rabc', '(.=,[R],a,u)(=,[Ra],u,)(.=,[Ra],b,u)' + . '(=,[Rab],u,)(.=,[Rab],c,u)("",[Rabc],u,)'; + c '(($R.=$a).=$B).=$c', 'RaBc', '(.=,[R],a,u)(=,[Ra],u,)(.=,[Ra],[B],u)' + . '(=,[RaB],u,)(.=,[RaB],c,u)("",[RaBc],u,)'; + + # plain SV on both LHS and RHS with RHS object + + c '$r=$r.$A.$r', 'rAr', '(.,[A],r,1)(.=,[rA],r,u)("",[rAr],u,)'; + c '$r.=$r.$A.$r', 'rrAr', '(.,[A],r,1)(.=,[rA],r,u)(.,[rAr],r,1)' + .'("",[rrAr],u,)'; + + # object on both LHS and RHS + + c '$R.=$R', 'RR', '(.=,[R],[R],u)("",[RR],u,)'; + c '$R.=$R.$b.$c', 'RRbc', '(.,[R],b,)(.=,[Rb],c,u)(.=,[R],[Rbc],u)' + .'("",[RRbc],u,)'; + c '$R.=$a.$R.$c', 'RaRc', '(.,[R],a,1)(.=,[aR],c,u)(.=,[R],[aRc],u)' + .'("",[RaRc],u,)'; + c '$R.=$a.$b.$R', 'RabR', '(.,[R],ab,1)(.=,[R],[abR],u)("",[RabR],u,)'; + + + # sprintf shouldn't do concat overloading + + cc '$r=sprintf("%s%s%s",$a,$B,$c)', 'aBc', 0, '("",[B],u,)'; + cc '$R=sprintf("%s%s%s",$a,$B,$c)', 'aBc', 0, '("",[B],u,)'; + cc '$r.=sprintf("%s%s%s",$a,$B,$c)', 'raBc', 0, '("",[B],u,)'; + cc '$R.=sprintf("%s%s%s",$a,$B,$c)', 'RaBc', 1, '("",[B],u,)(.=,[R],aBc,u)' + .'("",[RaBc],u,)'; + + # multiple constants should individually overload (RT #132385) + + c '$r=$A."b"."c"', 'Abc', '(.,[A],b,)(.=,[Ab],c,u)("",[Abc],u,)'; + + # ... except for this + c '$R.="a"."b"', 'Rab', '(.=,[R],ab,u)("",[Rab],u,)'; +} + +# RT #132385 +# The first arg of a reversed concat shouldn't be stringified: +# $left . $right +# where $right is overloaded, should invoke +# concat($right, $left, 1) +# rather than +# concat($right, "$left", 1) +# There's a similar issue with +# $left .= $right +# when left is overloaded + +package RT132385 { + + use constant C => [ "constref" ]; + + use overload '.' => sub { + my ($l, $r, $rev) = @_; + ($l,$r) = ($r,$l) if $rev; + $l = ref $l ? $l->[0] : "$l"; + $r = ref $r ? $r->[0] : "$r"; + "$l-$r"; + } + ; + + my $r1 = [ "ref1" ]; + my $r2 = [ "ref2" ]; + my $s1 = "str1"; + + my $o = bless [ "obj" ]; + + # try variations that will call either pp_concat or pp_multiconcat, + # with the ref as the first or a later arg + + ::is($r1.$o, "ref1-obj", "RT #132385 r1.o"); + ::is($r1.$o.$s1 , "ref1-objstr1", "RT #132385 r1.o.s1"); + ::is("const".$o.$s1 ,"const-objstr1", "RT #132385 const.o.s1"); + ::is(C.$o.$s1 ,"constref-objstr1", "RT #132385 C.o.s1"); + + ::like($r1.$r2.$o, qr/^ARRAY\(0x\w+\)ARRAY\(0x\w+\)-obj/, + "RT #132385 r1.r2.o"); + + # ditto with a mutator + ::is($o .= $r1, "obj-ref1", "RT #132385 o.=r1"); +} + +# the RHS of an overloaded .= should be passed as-is to the overload +# method, rather than being stringified or otherwise being processed in +# such a way that it triggers an undef warning +package RT132783 { + use warnings; + use overload '.=' => sub { return "foo" }; + my $w = 0; + local $SIG{__WARN__} = sub { $w++ }; + my $undef; + my $ov = bless []; + $ov .= $undef; + ::is($w, 0, "RT #132783 - should be no warnings"); +} + +# changing the overloaded object to a plain string within an overload +# method should be permanent. +package RT132827 { + use overload '""' => sub { $_[0] = "a" }; + my $ov = bless []; + my $b = $ov . "b"; + ::is(ref \$ov, "SCALAR", "RT #132827"); +} + +# RT #132793 +# An arg like like "$b" in $overloaded .= "$b" should be stringified +# before being passed to the method + +package RT132793 { + my $type; + my $str = 0; + use overload + '.=' => sub { $type = ref(\$_[1]); "foo"; }, + '""' => sub { $str++; "bar" }; + + my $a = bless {}; + my $b = bless {}; + $a .= "$b"; + ::is($type, "SCALAR", "RT #132793 type"); + ::is($str, 1, "RT #132793 stringify count"); +} + +# RT #132801 +# A second RHS-not-stringified bug + +package RT132801 { + my $type; + my $str = 0; + my $concat = 0; + use overload + '.' => sub { $concat++; bless []; }, + '""' => sub { $str++; "bar" }; + + my $a = "A"; + my $b = bless []; + my $c; + $c = "$a-$b"; + ::is($concat, 1, "RT #132801 concat count"); + ::is($str, 1, "RT #132801 stringify count"); +} + +# General testing of optimising away OP_STRINGIFY, and whether +# OP_MULTICONCAT emulates existing behaviour. +# +# It could well be argued that the existing behaviour is buggy, but +# for now emulate the old behaviour. +# +# In more detail: +# +# Since 5.000, any OP_STRINGIFY immediately following an OP_CONCAT +# is optimised away, on the assumption that since concat will always +# return a valid string anyway, it doesn't need stringifying. +# So in "$x", the stringify is needed, but on "$x$y" it isn't. +# This assumption is flawed once overloading has been introduced, since +# concat might return an overloaded object which still needs stringifying. +# However, this flawed behaviour is apparently needed by at least one +# module, and is tested for in opbasic/concat.t: see RT #124160. +# +# There is also a wart with the OPpTARGET_MY optimisation: specifically, +# in $lex = "...", if $lex is a lexical var, then a chain of 2 or more +# concats *doesn't* optimise away OP_STRINGIFY: +# +# $lex = "$x"; # stringifies +# $lex = "$x$y"; # doesn't stringify +# $lex = "$x$y$z..."; # stringifies + +package Stringify { + my $count; + use overload + '.' => sub { + my ($a, $b, $rev) = @_; + bless [ $rev ? "$b" . $a->[0] : $a->[0] . "$b" ]; + }, + '""' => sub { $count++; $_[0][0] }, + ; + + for my $test( + [ 1, '$pkg = "$ov"' ], + [ 1, '$lex = "$ov"' ], + [ 1, 'my $a = "$ov"' ], + [ 1, '$pkg .= "$ov"' ], + [ 1, '$lex .= "$ov"' ], + [ 1, 'my $a .= "$ov"' ], + + [ 0, '$pkg = "$ov$x"' ], + [ 0, '$lex = "$ov$x"' ], + [ 0, 'my $a = "$ov$x"' ], + [ 0, '$pkg .= "$ov$x"' ], + [ 0, '$lex .= "$ov$x"' ], + [ 0, 'my $a .= "$ov$x"' ], + + [ 0, '$pkg = "$ov$x$y"' ], + [ 1, '$lex = "$ov$x$y"' ], # XXX note the anomaly + [ 0, 'my $a = "$ov$x$y"' ], + [ 0, '$pkg .= "$ov$x$y"' ], + [ 0, '$lex .= "$ov$x$y"' ], + [ 0, 'my $a .= "$ov$x$y"' ], + ) + { + my ($stringify, $code) = @$test; + our $pkg = 'P'; + my ($ov, $x, $y, $lex) = (bless(['OV']), qw(X Y L)); + $count = 0; + eval "$code; 1" or die $@; + ::is $count, $stringify, $code; + } +} diff --git a/gnu/usr.bin/perl/lib/perl5db.pl b/gnu/usr.bin/perl/lib/perl5db.pl index 6dae6b0f5c3..ecc49a814d8 100644 --- a/gnu/usr.bin/perl/lib/perl5db.pl +++ b/gnu/usr.bin/perl/lib/perl5db.pl @@ -528,7 +528,8 @@ BEGIN { # Debugger for Perl 5.00x; perl5db.pl patch level: use vars qw($VERSION $header); -$VERSION = '1.49_05'; +# bump to X.XX in blead, only use X.XX_XX in maint +$VERSION = '1.53'; $header = "perl5db.pl version $VERSION"; @@ -1532,14 +1533,6 @@ We then determine what the console should be on various systems: undef $console; } -=item * Unix - use F</dev/tty>. - -=cut - - elsif ( -e "/dev/tty" ) { - $console = "/dev/tty"; - } - =item * Windows or MSDOS - use C<con>. =cut @@ -1564,6 +1557,17 @@ We then determine what the console should be on various systems: $console = 'sys$command'; } +# Keep this penultimate, on the grounds that it satisfies a wide variety of +# Unix-like systems that would otherwise need to be identified individually. + +=item * Unix - use F</dev/tty>. + +=cut + + elsif ( -e "/dev/tty" ) { + $console = "/dev/tty"; + } + # Keep this last. else { @@ -1655,14 +1659,14 @@ and if we can. $o = $i unless defined $o; # read/write on in, or just read, or read on STDIN. - open( IN, "+<$i" ) - || open( IN, "<$i" ) + open( IN, '+<', $i ) + || open( IN, '<', $i ) || open( IN, "<&STDIN" ); # read/write/create/clobber out, or write/create/clobber out, # or merge with STDERR, or merge with STDOUT. - open( OUT, "+>$o" ) - || open( OUT, ">$o" ) + open( OUT, '+>', $o ) + || open( OUT, '>', $o ) || open( OUT, ">&STDERR" ) || open( OUT, ">&STDOUT" ); # so we don't dongle stdout @@ -1867,7 +1871,10 @@ sub _DB__trim_command_and_return_first_component { $cmd =~ s/\A\s+//s; # trim annoying leading whitespace $cmd =~ s/\s+\z//s; # trim annoying trailing whitespace - my ($verb, $args) = $cmd =~ m{\A(\S*)\s*(.*)}s; + # A single-character debugger command can be immediately followed by its + # argument if they aren't both alphanumeric; otherwise require space + # between commands and arguments: + my ($verb, $args) = $cmd =~ m{\A(.\b|\S*)\s*(.*)}s; $obj->cmd_verb($verb); $obj->cmd_args($args); @@ -6624,9 +6631,9 @@ sub dump_trace { $i++ ) { - - # Go through the arguments and save them for later. - my $save_args = _dump_trace_calc_save_args($nothard); + # if the sub has args ($h true), make an anonymous array of the + # dumped args. + my $args = $h ? _dump_trace_calc_save_args($nothard) : undef; # If context is true, this is array (@)context. # If context is false, this is scalar ($) context. @@ -6634,10 +6641,6 @@ sub dump_trace { # happen' trap.) $context = $context ? '@' : ( defined $context ? "\$" : '.' ); - # if the sub has args ($h true), make an anonymous array of the - # dumped args. - $args = $h ? $save_args : undef; - # remove trailing newline-whitespace-semicolon-end of line sequence # from the eval text, if any. $e =~ s/\n\s*\;\s*\Z// if $e; @@ -6827,8 +6830,8 @@ sub setterm { if ($tty) { my ( $i, $o ) = split $tty, /,/; $o = $i unless defined $o; - open( IN, "<$i" ) or die "Cannot open TTY '$i' for read: $!"; - open( OUT, ">$o" ) or die "Cannot open TTY '$o' for write: $!"; + open( IN, '<', $i ) or die "Cannot open TTY '$i' for read: $!"; + open( OUT, '>', $o ) or die "Cannot open TTY '$o' for write: $!"; $IN = \*IN; $OUT = \*OUT; _autoflush($OUT); @@ -7751,8 +7754,8 @@ sub TTY { } # Open file onto the debugger's filehandles, if you can. - open IN, $in or die "cannot open '$in' for read: $!"; - open OUT, ">$out" or die "cannot open '$out' for write: $!"; + open IN, '<', $in or die "cannot open '$in' for read: $!"; + open OUT, '>', $out or die "cannot open '$out' for write: $!"; # Swap to the new filehandles. reset_IN_OUT( \*IN, \*OUT ); diff --git a/gnu/usr.bin/perl/lib/perl5db.t b/gnu/usr.bin/perl/lib/perl5db.t index 0c4fc429418..3d432ad52ea 100644 --- a/gnu/usr.bin/perl/lib/perl5db.t +++ b/gnu/usr.bin/perl/lib/perl5db.t @@ -10,6 +10,8 @@ use strict; use warnings; use Config; +delete $ENV{PERLDB_OPTS}; + BEGIN { if (! -c "/dev/null") { print "1..0 # Skip: no /dev/null\n"; @@ -29,7 +31,7 @@ BEGIN { $ENV{PERL_RL} = 'Perl'; # Suppress system Term::ReadLine::Gnu } -plan(123); +plan(127); my $rc_filename = '.perldb'; @@ -2769,7 +2771,7 @@ SKIP: ); $wrapper->output_like( - qr/No manual entry for perlrules/, + qr/No (?:manual )?entry for perlrules/, 'perldoc command works fine', ); } @@ -2815,6 +2817,90 @@ SKIP: ); } +{ + # perl 5 RT #120174 - 'p' command + my $wrapper = DebugWrap->new( + { + cmds => + [ + 'b 2', + 'c', + 'p@abc', + 'q', + ], + prog => '../lib/perl5db/t/rt-120174', + } + ); + + $wrapper->contents_like( + qr/1234/, + q/RT 120174: p command can be invoked without space after 'p'/, + ); +} + +{ + # perl 5 RT #120174 - 'x' command on array + my $wrapper = DebugWrap->new( + { + cmds => + [ + 'b 2', + 'c', + 'x@abc', + 'q', + ], + prog => '../lib/perl5db/t/rt-120174', + } + ); + + $wrapper->contents_like( + qr/0\s+1\n1\s+2\n2\s+3\n3\s+4/ms, + q/RT 120174: x command can be invoked without space after 'x' before array/, + ); +} + +{ + # perl 5 RT #120174 - 'x' command on array ref + my $wrapper = DebugWrap->new( + { + cmds => + [ + 'b 2', + 'c', + 'x\@abc', + 'q', + ], + prog => '../lib/perl5db/t/rt-120174', + } + ); + + $wrapper->contents_like( + qr/\s+0\s+1\n\s+1\s+2\n\s+2\s+3\n\s+3\s+4/ms, + q/RT 120174: x command can be invoked without space after 'x' before array ref/, + ); +} + +{ + # perl 5 RT #120174 - 'x' command on hash ref + my $wrapper = DebugWrap->new( + { + cmds => + [ + 'b 4', + 'c', + 'x\%xyz', + 'q', + ], + prog => '../lib/perl5db/t/rt-120174', + } + ); + + $wrapper->contents_like( + qr/\s+'alpha'\s+=>\s+'beta'\n\s+'gamma'\s+=>\s+'delta'/ms, + q/RT 120174: x command can be invoked without space after 'x' before hash ref/, + ); +} + END { 1 while unlink ($rc_filename, $out_fn); } diff --git a/gnu/usr.bin/perl/lib/sort.t b/gnu/usr.bin/perl/lib/sort.t index b44269ac299..e0ef9d3faca 100644 --- a/gnu/usr.bin/perl/lib/sort.t +++ b/gnu/usr.bin/perl/lib/sort.t @@ -26,10 +26,8 @@ use strict; use warnings; use Test::More tests => @TestSizes * 2 # sort() tests - * 6 # number of pragmas to test - + 1 # extra test for qsort instability - + 3 # tests for sort::current - + 3; # tests for "defaults" and "no sort" + * 3 # number of pragmas to test + + 2; # tests for sort::current # Generate array of specified size for testing sort. # @@ -130,48 +128,34 @@ sub main { } } -# Test with no pragma still loaded -- stability expected (this is a mergesort) +# Test with no pragma yet loaded. Stability is expected from default sort. main(sub { sort {&{$_[0]}} @{$_[1]} }, 0); -{ - use sort qw(_qsort); - my $sort_current; BEGIN { $sort_current = sort::current(); } - is($sort_current, 'quicksort', 'sort::current for _qsort'); - main(sub { sort {&{$_[0]}} @{$_[1]} }, 1); -} +# Verify that we have eliminated the segfault that could be triggered +# by invoking a sort as part of a comparison routine. +# No need for an explicit test. If we don't segfault, we're good. { - use sort qw(_mergesort); - my $sort_current; BEGIN { $sort_current = sort::current(); } - is($sort_current, 'mergesort', 'sort::current for _mergesort'); - main(sub { sort {&{$_[0]}} @{$_[1]} }, 0); + sub dumbsort { + my ($a, $b) = @_; + use sort qw( defaults stable ); + my @ignore = sort (5,4,3,2,1); + return $a <=> $b; + } + use sort qw( defaults stable ); + my @nested = sort { dumbsort($a,$b) } (3,2,2,1); } { - use sort qw(_qsort stable); + use sort qw(stable); my $sort_current; BEGIN { $sort_current = sort::current(); } - is($sort_current, 'quicksort stable', 'sort::current for _qsort stable'); + is($sort_current, 'stable', 'sort::current for stable'); main(sub { sort {&{$_[0]}} @{$_[1]} }, 0); } # Tests added to check "defaults" subpragma, and "no sort" { - use sort qw(_qsort stable); - no sort qw(_qsort); - my $sort_current; BEGIN { $sort_current = sort::current(); } - is($sort_current, 'stable', 'sort::current after no _qsort'); - main(sub { sort {&{$_[0]}} @{$_[1]} }, 0); -} - -{ - use sort qw(defaults _qsort); - my $sort_current; BEGIN { $sort_current = sort::current(); } - is($sort_current, 'quicksort', 'sort::current after defaults _qsort'); - # Not expected to be stable, so don't test for stability here -} - -{ use sort qw(defaults stable); my $sort_current; BEGIN { $sort_current = sort::current(); } is($sort_current, 'stable', 'sort::current after defaults stable'); diff --git a/gnu/usr.bin/perl/lib/strict.t b/gnu/usr.bin/perl/lib/strict.t index d6c6ed0e411..bfee7620c27 100644 --- a/gnu/usr.bin/perl/lib/strict.t +++ b/gnu/usr.bin/perl/lib/strict.t @@ -1,7 +1,7 @@ #!./perl chdir 't' if -d 't'; -@INC = '../lib'; +@INC = ( '.', '../lib' ); our $local_tests = 6; require "../t/lib/common.pl"; diff --git a/gnu/usr.bin/perl/lib/subs.pm b/gnu/usr.bin/perl/lib/subs.pm index 10d6e023f46..24814596baa 100644 --- a/gnu/usr.bin/perl/lib/subs.pm +++ b/gnu/usr.bin/perl/lib/subs.pm @@ -1,10 +1,10 @@ package subs; -our $VERSION = '1.02'; +our $VERSION = '1.03'; =head1 NAME -subs - Perl pragma to predeclare sub names +subs - Perl pragma to predeclare subroutine names =head1 SYNOPSIS @@ -13,13 +13,14 @@ subs - Perl pragma to predeclare sub names =head1 DESCRIPTION -This will predeclare all the subroutine whose names are -in the list, allowing you to use them without parentheses +This will predeclare all the subroutines whose names are +in the list, allowing you to use them without parentheses (as list operators) even before they're declared. Unlike pragmas that affect the C<$^H> hints variable, the C<use vars> and -C<use subs> declarations are not BLOCK-scoped. They are thus effective -for the entire package in which they appear. You may not rescind such +C<use subs> declarations are not lexically scoped to the block they appear +in: they affect +the entire package in which they appear. It is not possible to rescind these declarations with C<no vars> or C<no subs>. See L<perlmodlib/Pragmatic Modules> and L<strict/strict subs>. diff --git a/gnu/usr.bin/perl/lib/unicore/ArabicShaping.txt b/gnu/usr.bin/perl/lib/unicore/ArabicShaping.txt index b0e5b5b7af7..f2ef1fad74c 100644 --- a/gnu/usr.bin/perl/lib/unicore/ArabicShaping.txt +++ b/gnu/usr.bin/perl/lib/unicore/ArabicShaping.txt @@ -1,23 +1,23 @@ -# ArabicShaping-8.0.0.txt -# Date: 2015-02-17, 23:33:00 GMT [RP] +# ArabicShaping-10.0.0.txt +# Date: 2017-02-16, 00:00:00 GMT [RP, KW] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2014 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # This file defines the Joining_Type and Joining_Group property # values for Arabic, Syriac, N'Ko, Mandaic, and Manichaean positional # shaping, repeating in machine readable form the information # exemplified in Tables 9-3, 9-8, 9-9, 9-10, 9-14, 9-15, 9-16, 9-19, # 9-20, 10-4, 10-5, 10-6, 10-7, and 19-5 of The Unicode Standard core # specification. This file also defines Joining_Type values for -# Mongolian, Phags-pa, and Psalter Pahlavi positional shaping, which -# are not listed in tables in the standard. +# Mongolian, Phags-pa, Psalter Pahlavi, and Adlam positional shaping, +# which are not listed in tables in the standard. # -# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4 of -# The Unicode Standard core specification for more information. +# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4, and 19.9 +# of The Unicode Standard core specification for more information. # # Each line contains four fields, separated by a semicolon. # @@ -50,8 +50,8 @@ # Field 3: defines the joining group (property name: Joining_Group) # # The values of the joining group are based schematically on character -# names. Where a schematic character name consists of two or more parts separated -# by spaces, the formal Joining_Group property value, as specified in +# names. Where a schematic character name consists of two or more parts +# separated by spaces, the formal Joining_Group property value, as specified in # PropertyValueAliases.txt, consists of the same name parts joined by # underscores. Hence, the entry: # @@ -86,11 +86,11 @@ # Note: Code points that are not explicitly listed in this file are # either of joining type T or U: # -# - Those that not explicitly listed that are of General Category Mn, Me, or Cf +# - Those that are not explicitly listed and that are of General Category Mn, Me, or Cf # have joining type T. # - All others not explicitly listed have joining type U. # -# For an explicit listing of characters of joining type T, see +# For an explicit listing of all characters of joining type T, see # the derived property file DerivedJoiningType.txt. # # ############################################################# @@ -413,6 +413,20 @@ 0857; MANDAIC KAD; U; No_Joining_Group 0858; MANDAIC AIN; U; No_Joining_Group +# Syriac Supplement Characters + +0860; MALAYALAM NGA; D; MALAYALAM NGA +0861; MALAYALAM JA; U; MALAYALAM JA +0862; MALAYALAM NYA; D; MALAYALAM NYA +0863; MALAYALAM TTA; D; MALAYALAM TTA +0864; MALAYALAM NNA; D; MALAYALAM NNA +0865; MALAYALAM NNNA; D; MALAYALAM NNNA +0866; MALAYALAM BHA; U; MALAYALAM BHA +0867; MALAYALAM RA; R; MALAYALAM RA +0868; MALAYALAM LLA; D; MALAYALAM LLA +0869; MALAYALAM LLLA; R; MALAYALAM LLLA +086A; MALAYALAM SSA; R; MALAYALAM SSA + # Arabic Extended-A Characters 08A0; DOTLESS BEH WITH V BELOW; D; BEH @@ -436,6 +450,15 @@ 08B2; REH WITH DOT AND INVERTED V ABOVE; R; REH 08B3; AIN WITH 3 DOTS BELOW; D; AIN 08B4; KAF WITH DOT BELOW; D; KAF +08B6; BEH WITH MEEM ABOVE; D; BEH +08B7; DOTLESS BEH WITH 3 DOTS BELOW AND MEEM ABOVE; D; BEH +08B8; DOTLESS BEH WITH TEH ABOVE; D; BEH +08B9; REH WITH NOON ABOVE; R; REH +08BA; YEH WITH NOON ABOVE; D; YEH +08BB; AFRICAN FEH; D; AFRICAN FEH +08BC; AFRICAN QAF; D; AFRICAN QAF +08BD; AFRICAN NOON; D; AFRICAN NOON +08E2; ARABIC DISPUTED END OF AYAH; U; No_Joining_Group # Mongolian Characters @@ -536,8 +559,8 @@ 1882; MONGOLIAN ALI GALI DAMARU; U; No_Joining_Group 1883; MONGOLIAN ALI GALI UBADAMA; U; No_Joining_Group 1884; MONGOLIAN ALI GALI INVERTED UBADAMA; U; No_Joining_Group -1885; MONGOLIAN ALI GALI BALUDA; U; No_Joining_Group -1886; MONGOLIAN ALI GALI THREE BALUDA; U; No_Joining_Group +1885; MONGOLIAN ALI GALI BALUDA; T; No_Joining_Group +1886; MONGOLIAN ALI GALI THREE BALUDA; T; No_Joining_Group 1887; MONGOLIAN ALI GALI A; D; No_Joining_Group 1888; MONGOLIAN ALI GALI I; D; No_Joining_Group 1889; MONGOLIAN ALI GALI KA; D; No_Joining_Group @@ -578,6 +601,7 @@ 200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group 200D; ZERO WIDTH JOINER; C; No_Joining_Group +202F; NARROW NO-BREAK SPACE; U; No_Joining_Group 2066; LEFT-TO-RIGHT ISOLATE; U; No_Joining_Group 2067; RIGHT-TO-LEFT ISOLATE; U; No_Joining_Group 2068; FIRST STRONG ISOLATE; U; No_Joining_Group @@ -711,4 +735,75 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group 10BAE; PSALTER PAHLAVI TWENTY; D; No_Joining_Group 10BAF; PSALTER PAHLAVI HUNDRED; U; No_Joining_Group +# Adlam Characters + +1E900;ADLAM CAPITAL ALIF; D; No_Joining_Group +1E901;ADLAM CAPITAL DAALI; D; No_Joining_Group +1E902;ADLAM CAPITAL LAAM; D; No_Joining_Group +1E903;ADLAM CAPITAL MIIM; D; No_Joining_Group +1E904;ADLAM CAPITAL BA; D; No_Joining_Group +1E905;ADLAM CAPITAL SINNYIIYHE; D; No_Joining_Group +1E906;ADLAM CAPITAL PE; D; No_Joining_Group +1E907;ADLAM CAPITAL BHE; D; No_Joining_Group +1E908;ADLAM CAPITAL RA; D; No_Joining_Group +1E909;ADLAM CAPITAL E; D; No_Joining_Group +1E90A;ADLAM CAPITAL FA; D; No_Joining_Group +1E90B;ADLAM CAPITAL I; D; No_Joining_Group +1E90C;ADLAM CAPITAL O; D; No_Joining_Group +1E90D;ADLAM CAPITAL DHA; D; No_Joining_Group +1E90E;ADLAM CAPITAL YHE; D; No_Joining_Group +1E90F;ADLAM CAPITAL WAW; D; No_Joining_Group +1E910;ADLAM CAPITAL NUN; D; No_Joining_Group +1E911;ADLAM CAPITAL KAF; D; No_Joining_Group +1E912;ADLAM CAPITAL YA; D; No_Joining_Group +1E913;ADLAM CAPITAL U; D; No_Joining_Group +1E914;ADLAM CAPITAL JIIM; D; No_Joining_Group +1E915;ADLAM CAPITAL CHI; D; No_Joining_Group +1E916;ADLAM CAPITAL HA; D; No_Joining_Group +1E917;ADLAM CAPITAL QAAF; D; No_Joining_Group +1E918;ADLAM CAPITAL GA; D; No_Joining_Group +1E919;ADLAM CAPITAL NYA; D; No_Joining_Group +1E91A;ADLAM CAPITAL TU; D; No_Joining_Group +1E91B;ADLAM CAPITAL NHA; D; No_Joining_Group +1E91C;ADLAM CAPITAL VA; D; No_Joining_Group +1E91D;ADLAM CAPITAL KHA; D; No_Joining_Group +1E91E;ADLAM CAPITAL GBE; D; No_Joining_Group +1E91F;ADLAM CAPITAL ZAL; D; No_Joining_Group +1E920;ADLAM CAPITAL KPO; D; No_Joining_Group +1E921;ADLAM CAPITAL SHA; D; No_Joining_Group +1E922;ADLAM SMALL ALIF; D; No_Joining_Group +1E923;ADLAM SMALL DAALI; D; No_Joining_Group +1E924;ADLAM SMALL LAAM; D; No_Joining_Group +1E925;ADLAM SMALL MIIM; D; No_Joining_Group +1E926;ADLAM SMALL BA; D; No_Joining_Group +1E927;ADLAM SMALL SINNYIIYHE; D; No_Joining_Group +1E928;ADLAM SMALL PE; D; No_Joining_Group +1E929;ADLAM SMALL BHE; D; No_Joining_Group +1E92A;ADLAM SMALL RA; D; No_Joining_Group +1E92B;ADLAM SMALL E; D; No_Joining_Group +1E92C;ADLAM SMALL FA; D; No_Joining_Group +1E92D;ADLAM SMALL I; D; No_Joining_Group +1E92E;ADLAM SMALL O; D; No_Joining_Group +1E92F;ADLAM SMALL DHA; D; No_Joining_Group +1E930;ADLAM SMALL YHE; D; No_Joining_Group +1E931;ADLAM SMALL WAW; D; No_Joining_Group +1E932;ADLAM SMALL NUN; D; No_Joining_Group +1E933;ADLAM SMALL KAF; D; No_Joining_Group +1E934;ADLAM SMALL YA; D; No_Joining_Group +1E935;ADLAM SMALL U; D; No_Joining_Group +1E936;ADLAM SMALL JIIM; D; No_Joining_Group +1E937;ADLAM SMALL CHI; D; No_Joining_Group +1E938;ADLAM SMALL HA; D; No_Joining_Group +1E939;ADLAM SMALL QAAF; D; No_Joining_Group +1E93A;ADLAM SMALL GA; D; No_Joining_Group +1E93B;ADLAM SMALL NYA; D; No_Joining_Group +1E93C;ADLAM SMALL TU; D; No_Joining_Group +1E93D;ADLAM SMALL NHA; D; No_Joining_Group +1E93E;ADLAM SMALL VA; D; No_Joining_Group +1E93F;ADLAM SMALL KHA; D; No_Joining_Group +1E940;ADLAM SMALL GBE; D; No_Joining_Group +1E941;ADLAM SMALL ZAL; D; No_Joining_Group +1E942;ADLAM SMALL KPO; D; No_Joining_Group +1E943;ADLAM SMALL SHA; D; No_Joining_Group + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/BidiBrackets.txt b/gnu/usr.bin/perl/lib/unicore/BidiBrackets.txt index bfd83cd9429..2114e632b9f 100644 --- a/gnu/usr.bin/perl/lib/unicore/BidiBrackets.txt +++ b/gnu/usr.bin/perl/lib/unicore/BidiBrackets.txt @@ -1,14 +1,17 @@ -# BidiBrackets-8.0.0.txt -# Date: 2015-01-20, 19:00:00 GMT [AG, LI, KW] +# BidiBrackets-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [AG, LI, KW] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties -# +# # This file is a normative contributory data file in the Unicode # Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # Bidi_Paired_Bracket is a normative property of type Miscellaneous, # which establishes a mapping between characters that are treated as # bracket pairs by the Unicode Bidirectional Algorithm. @@ -26,6 +29,12 @@ # vice versa, and their Bidi_Paired_Bracket_Type (bpt) property values are # Open (o) and Close (c), respectively. # +# The brackets with ticks U+298D LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +# through U+2990 RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER are paired the +# same way their glyphs form mirror pairs, according to their bmg property +# values. They are not paired on the basis of a diagonal or antidiagonal +# matching of the corner ticks inferred from code point order. +# # For legacy reasons, the characters U+FD3E ORNATE LEFT PARENTHESIS and # U+FD3F ORNATE RIGHT PARENTHESIS do not mirror in bidirectional display # and therefore do not form a bracket pair. diff --git a/gnu/usr.bin/perl/lib/unicore/BidiMirroring.txt b/gnu/usr.bin/perl/lib/unicore/BidiMirroring.txt index fbc60f1ab6b..cbb61c4b570 100644 --- a/gnu/usr.bin/perl/lib/unicore/BidiMirroring.txt +++ b/gnu/usr.bin/perl/lib/unicore/BidiMirroring.txt @@ -1,32 +1,34 @@ -# BidiMirroring-8.0.0.txt -# Date: 2015-01-20, 18:30:00 GMT [KW, LI] +# BidiMirroring-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # Bidi_Mirroring_Glyph Property -# +# # This file is an informative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # This data file lists characters that have the Bidi_Mirrored=Yes property # value, for which there is another Unicode character that typically has a glyph # that is the mirror image of the original character's glyph. # -# The repertoire covered by the file is Unicode 8.0.0. -# +# The repertoire covered by the file is Unicode 10.0.0. +# # The file contains a list of lines with mappings from one code point # to another one for character-based mirroring. # Note that for "real" mirroring, a rendering engine needs to select # appropriate alternative glyphs, and that many Unicode characters do not # have a mirror-image Unicode character. -# +# # Each mapping line contains two fields, separated by a semicolon (';'). # Each of the two fields contains a code point represented as a # variable-length hexadecimal value with 4 to 6 digits. # A comment indicates where the characters are "BEST FIT" mirroring. -# -# Code points for which Bidi_Mirrored=Yes, but for which no appropriate +# +# Code points for which Bidi_Mirrored=Yes, but for which no appropriate # characters exist with mirrored glyphs, are # listed as comments at the end of the file. # @@ -36,14 +38,14 @@ # point has the default value for the Bidi_Mirroring_Glyph property, # that means that no other character exists whose glyph is suitable # for character-based mirroring. -# +# # For information on bidi mirroring, see UAX #9: Unicode Bidirectional Algorithm, # at http://www.unicode.org/unicode/reports/tr9/ -# +# # This file was originally created by Markus Scherer. # Extended for Unicode 3.2, 4.0, 4.1, 5.0, 5.1, 5.2, and 6.0 by Ken Whistler, # and for subsequent versions by Ken Whistler and Laurentiu Iancu. -# +# # ############################################################ # # Property: Bidi_Mirroring_Glyph diff --git a/gnu/usr.bin/perl/lib/unicore/Blocks.txt b/gnu/usr.bin/perl/lib/unicore/Blocks.txt index 0a4a5807635..a4f851b14a5 100644 --- a/gnu/usr.bin/perl/lib/unicore/Blocks.txt +++ b/gnu/usr.bin/perl/lib/unicore/Blocks.txt @@ -1,9 +1,9 @@ -# Blocks-8.0.0.txt -# Date: 2014-11-10, 23:04:00 GMT [KW] +# Blocks-10.0.0.txt +# Date: 2017-04-12, 17:30:00 GMT [KW] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2014 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see http://www.unicode.org/reports/tr44/ # # Format: @@ -14,12 +14,12 @@ # Note: When comparing block names, casing, whitespace, hyphens, # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. -# For more information on the comparison of property values, +# For more information on the comparison of property values, # see UAX #44: http://www.unicode.org/reports/tr44/ # # All block ranges start with a value where (cp MOD 16) = 0, # and end with a value where (cp MOD 16) = 15. In other words, -# the last hexadecimal digit of the start of range is ...0 +# the last hexadecimal digit of the start of range is ...0 # and the last hexadecimal digit of the end of range is ...F. # This constraint on block ranges guarantees that allocations # are done in terms of whole columns, and that code chart display @@ -51,6 +51,7 @@ 07C0..07FF; NKo 0800..083F; Samaritan 0840..085F; Mandaic +0860..086F; Syriac Supplement 08A0..08FF; Arabic Extended-A 0900..097F; Devanagari 0980..09FF; Bengali @@ -93,6 +94,7 @@ 1BC0..1BFF; Batak 1C00..1C4F; Lepcha 1C50..1C7F; Ol Chiki +1C80..1C8F; Cyrillic Extended-C 1CC0..1CCF; Sundanese Supplement 1CD0..1CFF; Vedic Extensions 1D00..1D7F; Phonetic Extensions @@ -209,6 +211,7 @@ FFF0..FFFF; Specials 10400..1044F; Deseret 10450..1047F; Shavian 10480..104AF; Osmanya +104B0..104FF; Osage 10500..1052F; Elbasan 10530..1056F; Caucasian Albanian 10600..1077F; Linear A @@ -243,13 +246,20 @@ FFF0..FFFF; Specials 11280..112AF; Multani 112B0..112FF; Khudawadi 11300..1137F; Grantha +11400..1147F; Newa 11480..114DF; Tirhuta 11580..115FF; Siddham 11600..1165F; Modi +11660..1167F; Mongolian Supplement 11680..116CF; Takri 11700..1173F; Ahom 118A0..118FF; Warang Citi +11A00..11A4F; Zanabazar Square +11A50..11AAF; Soyombo 11AC0..11AFF; Pau Cin Hau +11C00..11C6F; Bhaiksuki +11C70..11CBF; Marchen +11D00..11D5F; Masaram Gondi 12000..123FF; Cuneiform 12400..1247F; Cuneiform Numbers and Punctuation 12480..1254F; Early Dynastic Cuneiform @@ -260,7 +270,12 @@ FFF0..FFFF; Specials 16AD0..16AFF; Bassa Vah 16B00..16B8F; Pahawh Hmong 16F00..16F9F; Miao +16FE0..16FFF; Ideographic Symbols and Punctuation +17000..187FF; Tangut +18800..18AFF; Tangut Components 1B000..1B0FF; Kana Supplement +1B100..1B12F; Kana Extended-A +1B170..1B2FF; Nushu 1BC00..1BC9F; Duployan 1BCA0..1BCAF; Shorthand Format Controls 1D000..1D0FF; Byzantine Musical Symbols @@ -270,7 +285,9 @@ FFF0..FFFF; Specials 1D360..1D37F; Counting Rod Numerals 1D400..1D7FF; Mathematical Alphanumeric Symbols 1D800..1DAAF; Sutton SignWriting +1E000..1E02F; Glagolitic Supplement 1E800..1E8DF; Mende Kikakui +1E900..1E95F; Adlam 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols 1F000..1F02F; Mahjong Tiles 1F030..1F09F; Domino Tiles @@ -289,6 +306,7 @@ FFF0..FFFF; Specials 2A700..2B73F; CJK Unified Ideographs Extension C 2B740..2B81F; CJK Unified Ideographs Extension D 2B820..2CEAF; CJK Unified Ideographs Extension E +2CEB0..2EBEF; CJK Unified Ideographs Extension F 2F800..2FA1F; CJK Compatibility Ideographs Supplement E0000..E007F; Tags E0100..E01EF; Variation Selectors Supplement diff --git a/gnu/usr.bin/perl/lib/unicore/CJKRadicals.txt b/gnu/usr.bin/perl/lib/unicore/CJKRadicals.txt index e8326579981..62865efbae1 100644 --- a/gnu/usr.bin/perl/lib/unicore/CJKRadicals.txt +++ b/gnu/usr.bin/perl/lib/unicore/CJKRadicals.txt @@ -1,28 +1,30 @@ -# CJKRadicals-8.0.0.txt -# Date: 2015-02-19, 00:30:00 GMT [RC, KW, LI] +# CJKRadicals-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [RC, KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see UAX #38: Unicode Han Database (Unihan), -# at http://www.unicode.org/reports/tr38/ +# For documentation, see http://www.unicode.org/reports/tr44/ # -# Mapping from radical numbers to characters. +# Mapping from CJK radical numbers to characters # -# This data file provides a mapping from the radical numbers used +# This data file provides a mapping from the CJK radical numbers used # in the kRSUnicode property to the corresponding character in # the Kangxi Radicals block or the CJK Radicals Supplement block, # as well as to a CJK unified ideograph which is formed from that # radical only. # -# There is one line per radical number. Each line contains three +# There is one line per CJK radical number. Each line contains three # fields, separated by a semicolon (';'). The first field is the -# radical number. The second field is the CJK radical character. +# CJK radical number. The second field is the CJK radical character. # The third field is the CJK unified ideograph. # -# Radical numbers match the regular expression [1-9][0-9]{0,2}\'? +# CJK radical numbers match the regular expression [1-9][0-9]{0,2}\'? # and in particular they can end with a U+0027 ' APOSTROPHE. # +# For more information, see UAX #38: Unicode Han Database (Unihan), +# at http://www.unicode.org/reports/tr38/ +# # This file was created for Unicode 5.2 by Richard Cook. # Updated for Unicode 6.0 by Richard Cook. # Updated for Unicode 6.1 and 6.2 by Ken Whistler, diff --git a/gnu/usr.bin/perl/lib/unicore/CaseFolding.txt b/gnu/usr.bin/perl/lib/unicore/CaseFolding.txt index 0197a6c40fb..efdf18e441c 100644 --- a/gnu/usr.bin/perl/lib/unicore/CaseFolding.txt +++ b/gnu/usr.bin/perl/lib/unicore/CaseFolding.txt @@ -1,10 +1,11 @@ -# CaseFolding-8.0.0.txt -# Date: 2015-01-13, 18:16:36 GMT [MD] +# CaseFolding-10.0.0.txt +# Date: 2017-04-14, 05:40:18 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # Case Folding Properties # @@ -23,7 +24,7 @@ # # NOTE: case folding does not preserve normalization formats! # -# For information on case folding, including how to have case folding +# For information on case folding, including how to have case folding # preserve normalization formats, see Section 3.13 Default Case Algorithms in # The Unicode Standard. # @@ -593,6 +594,15 @@ 13FB; C; 13F3; # CHEROKEE SMALL LETTER YU 13FC; C; 13F4; # CHEROKEE SMALL LETTER YV 13FD; C; 13F5; # CHEROKEE SMALL LETTER MV +1C80; C; 0432; # CYRILLIC SMALL LETTER ROUNDED VE +1C81; C; 0434; # CYRILLIC SMALL LETTER LONG-LEGGED DE +1C82; C; 043E; # CYRILLIC SMALL LETTER NARROW O +1C83; C; 0441; # CYRILLIC SMALL LETTER WIDE ES +1C84; C; 0442; # CYRILLIC SMALL LETTER TALL TE +1C85; C; 0442; # CYRILLIC SMALL LETTER THREE-LEGGED TE +1C86; C; 044A; # CYRILLIC SMALL LETTER TALL HARD SIGN +1C87; C; 0463; # CYRILLIC SMALL LETTER TALL YAT +1C88; C; A64B; # CYRILLIC SMALL LETTER UNBLENDED UK 1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW 1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE 1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW @@ -1163,6 +1173,7 @@ A7AA; C; 0266; # LATIN CAPITAL LETTER H WITH HOOK A7AB; C; 025C; # LATIN CAPITAL LETTER REVERSED OPEN E A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT +A7AE; C; 026A; # LATIN CAPITAL LETTER SMALL CAPITAL I A7B0; C; 029E; # LATIN CAPITAL LETTER TURNED K A7B1; C; 0287; # LATIN CAPITAL LETTER TURNED T A7B2; C; 029D; # LATIN CAPITAL LETTER J WITH CROSSED-TAIL @@ -1327,6 +1338,42 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z 10425; C; 1044D; # DESERET CAPITAL LETTER ENG 10426; C; 1044E; # DESERET CAPITAL LETTER OI 10427; C; 1044F; # DESERET CAPITAL LETTER EW +104B0; C; 104D8; # OSAGE CAPITAL LETTER A +104B1; C; 104D9; # OSAGE CAPITAL LETTER AI +104B2; C; 104DA; # OSAGE CAPITAL LETTER AIN +104B3; C; 104DB; # OSAGE CAPITAL LETTER AH +104B4; C; 104DC; # OSAGE CAPITAL LETTER BRA +104B5; C; 104DD; # OSAGE CAPITAL LETTER CHA +104B6; C; 104DE; # OSAGE CAPITAL LETTER EHCHA +104B7; C; 104DF; # OSAGE CAPITAL LETTER E +104B8; C; 104E0; # OSAGE CAPITAL LETTER EIN +104B9; C; 104E1; # OSAGE CAPITAL LETTER HA +104BA; C; 104E2; # OSAGE CAPITAL LETTER HYA +104BB; C; 104E3; # OSAGE CAPITAL LETTER I +104BC; C; 104E4; # OSAGE CAPITAL LETTER KA +104BD; C; 104E5; # OSAGE CAPITAL LETTER EHKA +104BE; C; 104E6; # OSAGE CAPITAL LETTER KYA +104BF; C; 104E7; # OSAGE CAPITAL LETTER LA +104C0; C; 104E8; # OSAGE CAPITAL LETTER MA +104C1; C; 104E9; # OSAGE CAPITAL LETTER NA +104C2; C; 104EA; # OSAGE CAPITAL LETTER O +104C3; C; 104EB; # OSAGE CAPITAL LETTER OIN +104C4; C; 104EC; # OSAGE CAPITAL LETTER PA +104C5; C; 104ED; # OSAGE CAPITAL LETTER EHPA +104C6; C; 104EE; # OSAGE CAPITAL LETTER SA +104C7; C; 104EF; # OSAGE CAPITAL LETTER SHA +104C8; C; 104F0; # OSAGE CAPITAL LETTER TA +104C9; C; 104F1; # OSAGE CAPITAL LETTER EHTA +104CA; C; 104F2; # OSAGE CAPITAL LETTER TSA +104CB; C; 104F3; # OSAGE CAPITAL LETTER EHTSA +104CC; C; 104F4; # OSAGE CAPITAL LETTER TSHA +104CD; C; 104F5; # OSAGE CAPITAL LETTER DHA +104CE; C; 104F6; # OSAGE CAPITAL LETTER U +104CF; C; 104F7; # OSAGE CAPITAL LETTER WA +104D0; C; 104F8; # OSAGE CAPITAL LETTER KHA +104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA +104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA +104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA 10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A 10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA 10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB @@ -1410,5 +1457,39 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z 118BD; C; 118DD; # WARANG CITI CAPITAL LETTER SSUU 118BE; C; 118DE; # WARANG CITI CAPITAL LETTER SII 118BF; C; 118DF; # WARANG CITI CAPITAL LETTER VIYO +1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF +1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI +1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM +1E903; C; 1E925; # ADLAM CAPITAL LETTER MIIM +1E904; C; 1E926; # ADLAM CAPITAL LETTER BA +1E905; C; 1E927; # ADLAM CAPITAL LETTER SINNYIIYHE +1E906; C; 1E928; # ADLAM CAPITAL LETTER PE +1E907; C; 1E929; # ADLAM CAPITAL LETTER BHE +1E908; C; 1E92A; # ADLAM CAPITAL LETTER RA +1E909; C; 1E92B; # ADLAM CAPITAL LETTER E +1E90A; C; 1E92C; # ADLAM CAPITAL LETTER FA +1E90B; C; 1E92D; # ADLAM CAPITAL LETTER I +1E90C; C; 1E92E; # ADLAM CAPITAL LETTER O +1E90D; C; 1E92F; # ADLAM CAPITAL LETTER DHA +1E90E; C; 1E930; # ADLAM CAPITAL LETTER YHE +1E90F; C; 1E931; # ADLAM CAPITAL LETTER WAW +1E910; C; 1E932; # ADLAM CAPITAL LETTER NUN +1E911; C; 1E933; # ADLAM CAPITAL LETTER KAF +1E912; C; 1E934; # ADLAM CAPITAL LETTER YA +1E913; C; 1E935; # ADLAM CAPITAL LETTER U +1E914; C; 1E936; # ADLAM CAPITAL LETTER JIIM +1E915; C; 1E937; # ADLAM CAPITAL LETTER CHI +1E916; C; 1E938; # ADLAM CAPITAL LETTER HA +1E917; C; 1E939; # ADLAM CAPITAL LETTER QAAF +1E918; C; 1E93A; # ADLAM CAPITAL LETTER GA +1E919; C; 1E93B; # ADLAM CAPITAL LETTER NYA +1E91A; C; 1E93C; # ADLAM CAPITAL LETTER TU +1E91B; C; 1E93D; # ADLAM CAPITAL LETTER NHA +1E91C; C; 1E93E; # ADLAM CAPITAL LETTER VA +1E91D; C; 1E93F; # ADLAM CAPITAL LETTER KHA +1E91E; C; 1E940; # ADLAM CAPITAL LETTER GBE +1E91F; C; 1E941; # ADLAM CAPITAL LETTER ZAL +1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO +1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA # # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/CompositionExclusions.txt b/gnu/usr.bin/perl/lib/unicore/CompositionExclusions.txt index a4324b8ce82..ff42508686d 100644 --- a/gnu/usr.bin/perl/lib/unicore/CompositionExclusions.txt +++ b/gnu/usr.bin/perl/lib/unicore/CompositionExclusions.txt @@ -1,5 +1,10 @@ -# CompositionExclusions-8.0.0.txt -# Date: 2015-02-19, 00:30:00 GMT [KW, LI] +# CompositionExclusions-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # This file lists the characters for the Composition Exclusion Table # defined in UAX #15, Unicode Normalization Forms. @@ -7,9 +12,6 @@ # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # For more information, see # http://www.unicode.org/unicode/reports/tr15/#Primary_Exclusion_List_Table # diff --git a/gnu/usr.bin/perl/lib/unicore/DAge.txt b/gnu/usr.bin/perl/lib/unicore/DAge.txt index f1b0addb1c0..917afd413cd 100644 --- a/gnu/usr.bin/perl/lib/unicore/DAge.txt +++ b/gnu/usr.bin/perl/lib/unicore/DAge.txt @@ -1,10 +1,11 @@ -# DerivedAge-8.0.0.txt -# Date: 2015-02-13, 13:30:18 GMT [MD] +# DerivedAge-10.0.0.txt +# Date: 2017-04-14, 05:40:18 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # Unicode Character Database: Derived Property Data # This file shows when various code points were first assigned in Unicode. @@ -12,7 +13,7 @@ # Notes: # # - The term 'assigned' means that a previously reserved code point was assigned -# to be a character (graphic, format, control, or private-use); +# to be a character (graphic, format, control, or private-use); # a noncharacter code point; or a surrogate code point. # For more information, see The Unicode Standard Section 2.4 # @@ -1535,4 +1536,115 @@ FE2E..FE2F ; 8.0 # [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILL # Total code points: 7716 +# ================================================ + +# Age=V9_0 + +# Newly assigned in Unicode 9.0.0 (June, 2016) + +08B6..08BD ; 9.0 # [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; 9.0 # [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2 ; 9.0 # ARABIC DISPUTED END OF AYAH +0C80 ; 9.0 # KANNADA SIGN SPACING CANDRABINDU +0D4F ; 9.0 # MALAYALAM SIGN PARA +0D54..0D56 ; 9.0 # [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL +0D58..0D5E ; 9.0 # [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH +0D76..0D78 ; 9.0 # [3] MALAYALAM FRACTION ONE SIXTEENTH..MALAYALAM FRACTION THREE SIXTEENTHS +1C80..1C88 ; 9.0 # [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1DFB ; 9.0 # COMBINING DELETION MARK +23FB..23FE ; 9.0 # [4] POWER SYMBOL..POWER SLEEP SYMBOL +2E43..2E44 ; 9.0 # [2] DASH WITH LEFT UPTURN..DOUBLE SUSPENSION MARK +A7AE ; 9.0 # LATIN CAPITAL LETTER SMALL CAPITAL I +A8C5 ; 9.0 # SAURASHTRA SIGN CANDRABINDU +1018D..1018E ; 9.0 # [2] GREEK INDICTION SIGN..NOMISMA SIGN +104B0..104D3 ; 9.0 # [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; 9.0 # [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +1123E ; 9.0 # KHOJKI SIGN SUKUN +11400..11459 ; 9.0 # [90] NEWA LETTER A..NEWA DIGIT NINE +1145B ; 9.0 # NEWA PLACEHOLDER MARK +1145D ; 9.0 # NEWA INSERTION SIGN +11660..1166C ; 9.0 # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +11C00..11C08 ; 9.0 # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C36 ; 9.0 # [45] BHAIKSUKI LETTER E..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C45 ; 9.0 # [14] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI GAP FILLER-2 +11C50..11C6C ; 9.0 # [29] BHAIKSUKI DIGIT ZERO..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C8F ; 9.0 # [32] MARCHEN HEAD MARK..MARCHEN LETTER A +11C92..11CA7 ; 9.0 # [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9..11CB6 ; 9.0 # [14] MARCHEN SUBJOINED LETTER YA..MARCHEN SIGN CANDRABINDU +16FE0 ; 9.0 # TANGUT ITERATION MARK +17000..187EC ; 9.0 # [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; 9.0 # [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1E000..1E006 ; 9.0 # [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; 9.0 # [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; 9.0 # [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; 9.0 # [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; 9.0 # [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E900..1E94A ; 9.0 # [75] ADLAM CAPITAL LETTER ALIF..ADLAM NUKTA +1E950..1E959 ; 9.0 # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; 9.0 # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK +1F19B..1F1AC ; 9.0 # [18] SQUARED THREE D..SQUARED VOD +1F23B ; 9.0 # SQUARED CJK UNIFIED IDEOGRAPH-914D +1F57A ; 9.0 # MAN DANCING +1F5A4 ; 9.0 # BLACK HEART +1F6D1..1F6D2 ; 9.0 # [2] OCTAGONAL SIGN..SHOPPING TROLLEY +1F6F4..1F6F6 ; 9.0 # [3] SCOOTER..CANOE +1F919..1F91E ; 9.0 # [6] CALL ME HAND..HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F920..1F927 ; 9.0 # [8] FACE WITH COWBOY HAT..SNEEZING FACE +1F930 ; 9.0 # PREGNANT WOMAN +1F933..1F93E ; 9.0 # [12] SELFIE..HANDBALL +1F940..1F94B ; 9.0 # [12] WILTED FLOWER..MARTIAL ARTS UNIFORM +1F950..1F95E ; 9.0 # [15] CROISSANT..PANCAKES +1F985..1F991 ; 9.0 # [13] EAGLE..SQUID + +# Total code points: 7500 + +# ================================================ + +# Age=V10_0 + +# Newly assigned in Unicode 10.0.0 (June, 2017) + +0860..086A ; 10.0 # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +09FC..09FD ; 10.0 # [2] BENGALI LETTER VEDIC ANUSVARA..BENGALI ABBREVIATION SIGN +0AFA..0AFF ; 10.0 # [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0D00 ; 10.0 # MALAYALAM SIGN COMBINING ANUSVARA ABOVE +0D3B..0D3C ; 10.0 # [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +1CF7 ; 10.0 # VEDIC SIGN ATIKRAMA +1DF6..1DF9 ; 10.0 # [4] COMBINING KAVYKA ABOVE RIGHT..COMBINING WIDE INVERTED BRIDGE BELOW +20BF ; 10.0 # BITCOIN SIGN +23FF ; 10.0 # OBSERVER EYE SYMBOL +2BD2 ; 10.0 # GROUP MARK +2E45..2E49 ; 10.0 # [5] INVERTED LOW KAVYKA..DOUBLE STACKED COMMA +312E ; 10.0 # BOPOMOFO LETTER O WITH DOT ABOVE +9FD6..9FEA ; 10.0 # [21] CJK UNIFIED IDEOGRAPH-9FD6..CJK UNIFIED IDEOGRAPH-9FEA +1032D..1032F ; 10.0 # [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE +11A00..11A47 ; 10.0 # [72] ZANABAZAR SQUARE LETTER A..ZANABAZAR SQUARE SUBJOINER +11A50..11A83 ; 10.0 # [52] SOYOMBO LETTER A..SOYOMBO LETTER KSSA +11A86..11A9C ; 10.0 # [23] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; 10.0 # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11D00..11D06 ; 10.0 # [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; 10.0 # [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D36 ; 10.0 # [44] MASARAM GONDI LETTER AU..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; 10.0 # MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; 10.0 # [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D47 ; 10.0 # [9] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI RA-KARA +11D50..11D59 ; 10.0 # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +16FE1 ; 10.0 # NUSHU ITERATION MARK +1B002..1B11E ; 10.0 # [285] HENTAIGANA LETTER A-1..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; 10.0 # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB +1F260..1F265 ; 10.0 # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F6D3..1F6D4 ; 10.0 # [2] STUPA..PAGODA +1F6F7..1F6F8 ; 10.0 # [2] SLED..FLYING SAUCER +1F900..1F90B ; 10.0 # [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F91F ; 10.0 # I LOVE YOU HAND SIGN +1F928..1F92F ; 10.0 # [8] FACE WITH ONE EYEBROW RAISED..SHOCKED FACE WITH EXPLODING HEAD +1F931..1F932 ; 10.0 # [2] BREAST-FEEDING..PALMS UP TOGETHER +1F94C ; 10.0 # CURLING STONE +1F95F..1F96B ; 10.0 # [13] DUMPLING..CANNED FOOD +1F992..1F997 ; 10.0 # [6] GIRAFFE FACE..CRICKET +1F9D0..1F9E6 ; 10.0 # [23] FACE WITH MONOCLE..SOCKS +2CEB0..2EBE0 ; 10.0 # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 + +# Total code points: 8518 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/DCoreProperties.txt b/gnu/usr.bin/perl/lib/unicore/DCoreProperties.txt index 35d51e50fb6..16cd9b88bf5 100644 --- a/gnu/usr.bin/perl/lib/unicore/DCoreProperties.txt +++ b/gnu/usr.bin/perl/lib/unicore/DCoreProperties.txt @@ -1,10 +1,11 @@ -# DerivedCoreProperties-8.0.0.txt -# Date: 2015-03-11, 22:29:21 GMT [MD] +# DerivedCoreProperties-10.0.0.txt +# Date: 2017-03-19, 00:05:15 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -339,7 +340,10 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0828 ; Alphabetic # Lm SAMARITAN MODIFIER LETTER I 0829..082C ; Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Alphabetic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; Alphabetic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08DF ; Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA 0903 ; Alphabetic # Mc DEVANAGARI SIGN VISARGA @@ -376,6 +380,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 09DF..09E1 ; Alphabetic # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09E2..09E3 ; Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09F0..09F1 ; Alphabetic # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; Alphabetic # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; Alphabetic # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Alphabetic # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -413,6 +418,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0AE0..0AE1 ; Alphabetic # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL 0AE2..0AE3 ; Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AF9 ; Alphabetic # Lo GUJARATI LETTER ZHA +0AFA..0AFC ; Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 0B01 ; Alphabetic # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; Alphabetic # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -467,6 +473,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; Alphabetic # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; Alphabetic # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; Alphabetic # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -487,7 +494,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; Alphabetic # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; Alphabetic # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; Alphabetic # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI @@ -498,6 +505,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0D46..0D48 ; Alphabetic # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI 0D4A..0D4C ; Alphabetic # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4E ; Alphabetic # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; Alphabetic # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; Alphabetic # Mc MALAYALAM AU LENGTH MARK 0D5F..0D61 ; Alphabetic # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; Alphabetic # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -629,7 +637,9 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1820..1842 ; Alphabetic # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Alphabetic # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; Alphabetic # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; Alphabetic # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; Alphabetic # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; Alphabetic # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; Alphabetic # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 ; Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA ; Alphabetic # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; Alphabetic # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -695,6 +705,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 1C4D..1C4F ; Alphabetic # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; Alphabetic # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; Alphabetic # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; Alphabetic # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CE9..1CEC ; Alphabetic # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; Alphabetic # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Alphabetic # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA @@ -784,12 +795,12 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 30A1..30FA ; Alphabetic # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; Alphabetic # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Alphabetic # Lo KATAKANA DIGRAPH KOTO -3105..312D ; Alphabetic # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Alphabetic # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Alphabetic # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; Alphabetic # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; Alphabetic # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; Alphabetic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Alphabetic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Alphabetic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Alphabetic # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Alphabetic # Lm YI SYLLABLE WU A016..A48C ; Alphabetic # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -815,7 +826,7 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; Alphabetic # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; Alphabetic # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; Alphabetic # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -831,6 +842,7 @@ A840..A873 ; Alphabetic # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRA A880..A881 ; Alphabetic # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; Alphabetic # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU +A8C5 ; Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU A8F2..A8F7 ; Alphabetic # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA A8FB ; Alphabetic # Lo DEVANAGARI HEADSTROKE A8FD ; Alphabetic # Lo DEVANAGARI JAIN OM @@ -946,7 +958,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10280..1029C ; Alphabetic # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; Alphabetic # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; Alphabetic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; Alphabetic # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Alphabetic # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; Alphabetic # Nl GOTHIC LETTER NINETY 10342..10349 ; Alphabetic # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; Alphabetic # Nl GOTHIC LETTER NINE HUNDRED @@ -958,6 +970,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 103D1..103D5 ; Alphabetic # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10400..1044F ; Alphabetic # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; Alphabetic # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +104B0..104D3 ; Alphabetic # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; Alphabetic # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; Alphabetic # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Alphabetic # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; Alphabetic # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -1029,6 +1043,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11232..11233 ; Alphabetic # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU 11234 ; Alphabetic # Mn KHOJKI SIGN ANUSVARA 11237 ; Alphabetic # Mn KHOJKI SIGN SHADDA +1123E ; Alphabetic # Mn KHOJKI SIGN SUKUN 11280..11286 ; Alphabetic # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; Alphabetic # Lo MULTANI LETTER GHA 1128A..1128D ; Alphabetic # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1056,6 +1071,13 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11357 ; Alphabetic # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; Alphabetic # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; Alphabetic # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11400..11434 ; Alphabetic # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; Alphabetic # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Alphabetic # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Alphabetic # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11443..11444 ; Alphabetic # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA +11445 ; Alphabetic # Mc NEWA SIGN VISARGA +11447..1144A ; Alphabetic # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; Alphabetic # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; Alphabetic # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Alphabetic # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -1096,7 +1118,49 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 11727..1172A ; Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM 118A0..118DF ; Alphabetic # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; Alphabetic # Lo WARANG CITI OM +11A00 ; Alphabetic # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; Alphabetic # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A35..11A38 ; Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Alphabetic # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A50 ; Alphabetic # Lo SOYOMBO LETTER A +11A51..11A56 ; Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; Alphabetic # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Alphabetic # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Alphabetic # Mc SOYOMBO SIGN VISARGA 11AC0..11AF8 ; Alphabetic # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; Alphabetic # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; Alphabetic # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Alphabetic # Mc BHAIKSUKI SIGN VISARGA +11C40 ; Alphabetic # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; Alphabetic # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; Alphabetic # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Alphabetic # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Alphabetic # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Alphabetic # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Alphabetic # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; Alphabetic # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Alphabetic # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Alphabetic # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Alphabetic # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; Alphabetic # Mn MASARAM GONDI SIGN CANDRA +11D46 ; Alphabetic # Lo MASARAM GONDI REPHA +11D47 ; Alphabetic # Mn MASARAM GONDI RA-KARA 12000..12399 ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1114,7 +1178,11 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 16F50 ; Alphabetic # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Alphabetic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; Alphabetic # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; Alphabetic # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; Alphabetic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; Alphabetic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; Alphabetic # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Alphabetic # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Alphabetic # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1150,7 +1218,14 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1D78A..1D7A8 ; Alphabetic # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Alphabetic # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Alphabetic # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1E000..1E006 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4 ; Alphabetic # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E900..1E943 ; Alphabetic # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E947 ; Alphabetic # Mn ADLAM HAMZA 1EE00..1EE03 ; Alphabetic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Alphabetic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Alphabetic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1191,9 +1266,10 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 2A700..2B734 ; Alphabetic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 110943 +# Total code points: 126629 # ================================================ @@ -1478,6 +1554,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 052F ; Lowercase # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Lowercase # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 13F8..13FD ; Lowercase # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Lowercase # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Lowercase # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Lowercase # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Lowercase # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -1820,6 +1897,7 @@ FB00..FB06 ; Lowercase # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATU FB13..FB17 ; Lowercase # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lowercase # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Lowercase # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Lowercase # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lowercase # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 1D41A..1D433 ; Lowercase # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -1850,8 +1928,9 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1D7AA..1D7C2 ; Lowercase # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lowercase # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lowercase # L& MATHEMATICAL BOLD SMALL DIGAMMA +1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2173 +# Total code points: 2252 # ================================================ @@ -2447,11 +2526,12 @@ A7A2 ; Uppercase # L& LATIN CAPITAL LETTER K WITH OBLIQUE STROKE A7A4 ; Uppercase # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Uppercase # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Uppercase # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Uppercase # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Uppercase # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Uppercase # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Uppercase # L& LATIN CAPITAL LETTER OMEGA FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Uppercase # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Uppercase # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Uppercase # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Uppercase # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 1D400..1D419 ; Uppercase # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -2485,11 +2565,12 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1D756..1D76E ; Uppercase # L& [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA 1D790..1D7A8 ; Uppercase # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7CA ; Uppercase # L& MATHEMATICAL BOLD CAPITAL DIGAMMA +1E900..1E921 ; Uppercase # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA 1F130..1F149 ; Uppercase # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1751 +# Total code points: 1822 # ================================================ @@ -2531,6 +2612,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 10CD ; Cased # L& GEORGIAN CAPITAL LETTER AEN 13A0..13F5 ; Cased # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Cased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Cased # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Cased # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Cased # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Cased # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -2593,7 +2675,7 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7AD ; Cased # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; Cased # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; Cased # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2606,6 +2688,8 @@ FB13..FB17 ; Cased # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL FF21..FF3A ; Cased # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10400..1044F ; Cased # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW +104B0..104D3 ; Cased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; Cased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10C80..10CB2 ; Cased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Cased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Cased # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO @@ -2639,11 +2723,12 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D78A..1D7A8 ; Cased # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; Cased # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; Cased # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1E900..1E943 ; Cased # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1F130..1F149 ; Cased # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 3955 +# Total code points: 4105 # ================================================ @@ -2716,6 +2801,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0828 ; Case_Ignorable # Lm SAMARITAN MODIFIER LETTER I 0829..082D ; Case_Ignorable # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Case_Ignorable # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Case_Ignorable # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2 ; Case_Ignorable # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; Case_Ignorable # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Case_Ignorable # Mn DEVANAGARI VOWEL SIGN OE 093C ; Case_Ignorable # Mn DEVANAGARI SIGN NUKTA @@ -2743,6 +2830,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0AC7..0AC8 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Case_Ignorable # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Case_Ignorable # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Case_Ignorable # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Case_Ignorable # Mn ORIYA SIGN CANDRABINDU 0B3C ; Case_Ignorable # Mn ORIYA SIGN NUKTA 0B3F ; Case_Ignorable # Mn ORIYA VOWEL SIGN I @@ -2765,7 +2853,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0CC6 ; Case_Ignorable # Mn KANNADA VOWEL SIGN E 0CCC..0CCD ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; Case_Ignorable # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Case_Ignorable # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Case_Ignorable # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Case_Ignorable # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; Case_Ignorable # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Case_Ignorable # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; Case_Ignorable # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -2817,6 +2906,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 180B..180D ; Case_Ignorable # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Case_Ignorable # Cf MONGOLIAN VOWEL SEPARATOR 1843 ; Case_Ignorable # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1885..1886 ; Case_Ignorable # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Case_Ignorable # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Case_Ignorable # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; Case_Ignorable # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -2860,8 +2950,8 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D2C..1D6A ; Case_Ignorable # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D78 ; Case_Ignorable # Lm MODIFIER LETTER CYRILLIC EN 1D9B..1DBF ; Case_Ignorable # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; Case_Ignorable # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Case_Ignorable # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; Case_Ignorable # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Case_Ignorable # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Case_Ignorable # Sk GREEK KORONIS 1FBF..1FC1 ; Case_Ignorable # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI 1FCD..1FCF ; Case_Ignorable # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI @@ -2919,7 +3009,7 @@ A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA A80B ; Case_Ignorable # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Case_Ignorable # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; Case_Ignorable # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Case_Ignorable # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Case_Ignorable # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Case_Ignorable # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Case_Ignorable # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -2993,6 +3083,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1122F..11231 ; Case_Ignorable # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Case_Ignorable # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Case_Ignorable # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Case_Ignorable # Mn KHOJKI SIGN SUKUN 112DF ; Case_Ignorable # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Case_Ignorable # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Case_Ignorable # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -3000,6 +3091,9 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 11340 ; Case_Ignorable # Mn GRANTHA VOWEL SIGN II 11366..1136C ; Case_Ignorable # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Case_Ignorable # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; Case_Ignorable # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; Case_Ignorable # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; Case_Ignorable # Mn NEWA SIGN NUKTA 114B3..114B8 ; Case_Ignorable # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Case_Ignorable # Mn TIRHUTA VOWEL SIGN SHORT E 114BF..114C0 ; Case_Ignorable # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA @@ -3018,11 +3112,33 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1171D..1171F ; Case_Ignorable # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Case_Ignorable # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Case_Ignorable # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Case_Ignorable # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Case_Ignorable # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Case_Ignorable # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Case_Ignorable # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Case_Ignorable # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Case_Ignorable # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Case_Ignorable # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Case_Ignorable # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; Case_Ignorable # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Case_Ignorable # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; Case_Ignorable # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Case_Ignorable # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; Case_Ignorable # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; Case_Ignorable # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; Case_Ignorable # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Case_Ignorable # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Case_Ignorable # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Case_Ignorable # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Case_Ignorable # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Case_Ignorable # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Case_Ignorable # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Case_Ignorable # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16B40..16B43 ; Case_Ignorable # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F8F..16F92 ; Case_Ignorable # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Case_Ignorable # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 +16FE0..16FE1 ; Case_Ignorable # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1BC9D..1BC9E ; Case_Ignorable # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1BCA0..1BCA3 ; Case_Ignorable # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D167..1D169 ; Case_Ignorable # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 @@ -3037,13 +3153,19 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1DA84 ; Case_Ignorable # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Case_Ignorable # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Case_Ignorable # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Case_Ignorable # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Case_Ignorable # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Case_Ignorable # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Case_Ignorable # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Case_Ignorable # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2115 +# Total code points: 2314 # ================================================ @@ -3633,15 +3755,17 @@ A7A2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER K WITH O A7A4 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Changes_When_Lowercased # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Changes_When_Lowercased # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER OMEGA FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Lowercased # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Changes_When_Lowercased # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Changes_When_Lowercased # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Lowercased # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO +1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1233 +# Total code points: 1304 # ================================================ @@ -3800,8 +3924,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 0260..0261 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G 0263 ; Changes_When_Uppercased # L& LATIN SMALL LETTER GAMMA 0265..0266 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK -0268..0269 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER IOTA -026B..026C ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER L WITH MIDDLE TILDE..LATIN SMALL LETTER L WITH BELT +0268..026C ; Changes_When_Uppercased # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Uppercased # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Uppercased # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK 0275 ; Changes_When_Uppercased # L& LATIN SMALL LETTER BARRED O @@ -3937,6 +4060,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 052F ; Changes_When_Uppercased # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Changes_When_Uppercased # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 13F8..13FD ; Changes_When_Uppercased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Changes_When_Uppercased # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D79 ; Changes_When_Uppercased # L& LATIN SMALL LETTER INSULAR G 1D7D ; Changes_When_Uppercased # L& LATIN SMALL LETTER P WITH STROKE 1E01 ; Changes_When_Uppercased # L& LATIN SMALL LETTER A WITH RING BELOW @@ -4253,10 +4377,12 @@ FB00..FB06 ; Changes_When_Uppercased # L& [7] LATIN SMALL LIGATURE FF..LATI FB13..FB17 ; Changes_When_Uppercased # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Uppercased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Changes_When_Uppercased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Changes_When_Uppercased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Uppercased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1316 +# Total code points: 1396 # ================================================ @@ -4416,8 +4542,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 0260..0261 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G 0263 ; Changes_When_Titlecased # L& LATIN SMALL LETTER GAMMA 0265..0266 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK -0268..0269 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER IOTA -026B..026C ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER L WITH MIDDLE TILDE..LATIN SMALL LETTER L WITH BELT +0268..026C ; Changes_When_Titlecased # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Titlecased # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Titlecased # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK 0275 ; Changes_When_Titlecased # L& LATIN SMALL LETTER BARRED O @@ -4553,6 +4678,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 052F ; Changes_When_Titlecased # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Changes_When_Titlecased # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 13F8..13FD ; Changes_When_Titlecased # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Changes_When_Titlecased # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D79 ; Changes_When_Titlecased # L& LATIN SMALL LETTER INSULAR G 1D7D ; Changes_When_Titlecased # L& LATIN SMALL LETTER P WITH STROKE 1E01 ; Changes_When_Titlecased # L& LATIN SMALL LETTER A WITH RING BELOW @@ -4869,10 +4995,12 @@ FB00..FB06 ; Changes_When_Titlecased # L& [7] LATIN SMALL LIGATURE FF..LATI FB13..FB17 ; Changes_When_Titlecased # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Changes_When_Titlecased # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Changes_When_Titlecased # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Changes_When_Titlecased # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Changes_When_Titlecased # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1289 +# Total code points: 1369 # ================================================ @@ -5163,6 +5291,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 10C7 ; Changes_When_Casefolded # L& GEORGIAN CAPITAL LETTER YN 10CD ; Changes_When_Casefolded # L& GEORGIAN CAPITAL LETTER AEN 13F8..13FD ; Changes_When_Casefolded # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Changes_When_Casefolded # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1E00 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER A WITH RING BELOW 1E02 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER B WITH DOT ABOVE 1E04 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER B WITH DOT BELOW @@ -5471,7 +5600,7 @@ A7A2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER K WITH O A7A4 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Changes_When_Casefolded # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Changes_When_Casefolded # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER OMEGA AB70..ABBF ; Changes_When_Casefolded # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5479,10 +5608,12 @@ FB00..FB06 ; Changes_When_Casefolded # L& [7] LATIN SMALL LIGATURE FF..LATI FB13..FB17 ; Changes_When_Casefolded # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Changes_When_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Changes_When_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Changes_When_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO +1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1297 +# Total code points: 1377 # ================================================ @@ -5512,8 +5643,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 0260..0261 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER G WITH HOOK..LATIN SMALL LETTER SCRIPT G 0263 ; Changes_When_Casemapped # L& LATIN SMALL LETTER GAMMA 0265..0266 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER TURNED H..LATIN SMALL LETTER H WITH HOOK -0268..0269 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER IOTA -026B..026C ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER L WITH MIDDLE TILDE..LATIN SMALL LETTER L WITH BELT +0268..026C ; Changes_When_Casemapped # L& [5] LATIN SMALL LETTER I WITH STROKE..LATIN SMALL LETTER L WITH BELT 026F ; Changes_When_Casemapped # L& LATIN SMALL LETTER TURNED M 0271..0272 ; Changes_When_Casemapped # L& [2] LATIN SMALL LETTER M WITH HOOK..LATIN SMALL LETTER N WITH LEFT HOOK 0275 ; Changes_When_Casemapped # L& LATIN SMALL LETTER BARRED O @@ -5544,6 +5674,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 10CD ; Changes_When_Casemapped # L& GEORGIAN CAPITAL LETTER AEN 13A0..13F5 ; Changes_When_Casemapped # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV 13F8..13FD ; Changes_When_Casemapped # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Changes_When_Casemapped # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D79 ; Changes_When_Casemapped # L& LATIN SMALL LETTER INSULAR G 1D7D ; Changes_When_Casemapped # L& LATIN SMALL LETTER P WITH STROKE 1E00..1E9B ; Changes_When_Casemapped # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE @@ -5592,7 +5723,7 @@ A732..A76F ; Changes_When_Casemapped # L& [62] LATIN CAPITAL LETTER AA..LATI A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR D..LATIN SMALL LETTER INSULAR T A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A793 ; Changes_When_Casemapped # L& [4] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH BAR -A796..A7AD ; Changes_When_Casemapped # L& [24] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER L WITH BELT +A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; Changes_When_Casemapped # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -5601,11 +5732,14 @@ FB13..FB17 ; Changes_When_Casemapped # L& [5] ARMENIAN SMALL LIGATURE MEN N FF21..FF3A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10400..1044F ; Changes_When_Casemapped # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW +104B0..104D3 ; Changes_When_Casemapped # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; Changes_When_Casemapped # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10C80..10CB2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; Changes_When_Casemapped # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118A0..118DF ; Changes_When_Casemapped # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2518 +# Total code points: 2669 # ================================================ @@ -5677,7 +5811,9 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0824 ; ID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; ID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; ID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ID_Start # Lo DEVANAGARI OM @@ -5695,6 +5831,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 09DC..09DD ; ID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; ID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ID_Start # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; ID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -5743,6 +5880,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; ID_Start # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; ID_Start # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -5757,6 +5895,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0D12..0D3A ; ID_Start # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; ID_Start # Lo MALAYALAM SIGN AVAGRAHA 0D4E ; ID_Start # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; ID_Start # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D5F..0D61 ; ID_Start # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D7A..0D7F ; ID_Start # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; ID_Start # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA @@ -5840,7 +5979,9 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1820..1842 ; ID_Start # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Start # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; ID_Start # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; ID_Start # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; ID_Start # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; ID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; ID_Start # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; ID_Start # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; ID_Start # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; ID_Start # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -5860,6 +6001,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 1C4D..1C4F ; ID_Start # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; ID_Start # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; ID_Start # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; ID_Start # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CE9..1CEC ; ID_Start # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; ID_Start # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF5..1CF6 ; ID_Start # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA @@ -5947,12 +6089,12 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 30A1..30FA ; ID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; ID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; ID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; ID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Start # Lm YI SYLLABLE WU A016..A48C ; ID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -5976,7 +6118,7 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; ID_Start # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; ID_Start # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; ID_Start # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6070,7 +6212,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; ID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; ID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; ID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ID_Start # Nl GOTHIC LETTER NINETY 10342..10349 ; ID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ID_Start # Nl GOTHIC LETTER NINE HUNDRED @@ -6081,6 +6223,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 103D1..103D5 ; ID_Start # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10400..1044F ; ID_Start # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; ID_Start # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +104B0..104D3 ; ID_Start # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; ID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; ID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -6142,6 +6286,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; ID_Start # Lo GRANTHA SIGN AVAGRAHA 11350 ; ID_Start # Lo GRANTHA OM 1135D..11361 ; ID_Start # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; ID_Start # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; ID_Start # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; ID_Start # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; ID_Start # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; ID_Start # Lo TIRHUTA OM @@ -6153,7 +6299,21 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11700..11719 ; ID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118A0..118DF ; ID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; ID_Start # Lo WARANG CITI OM +11A00 ; ID_Start # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; ID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; ID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; ID_Start # Lo SOYOMBO LETTER A +11A5C..11A83 ; ID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; ID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; ID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; ID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; ID_Start # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; ID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; ID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; ID_Start # Lo MASARAM GONDI REPHA 12000..12399 ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -6169,7 +6329,11 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; ID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; ID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; ID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; ID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; ID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; ID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -6205,6 +6369,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D7AA..1D7C2 ; ID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1E800..1E8C4 ; ID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E900..1E943 ; ID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1EE00..1EE03 ; ID_Start # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; ID_Start # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; ID_Start # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -6242,9 +6407,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2A700..2B734 ; ID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 109830 +# Total code points: 125334 # ================================================ @@ -6347,7 +6513,10 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0829..082D ; ID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0840..0858 ; ID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; ID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; ID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; ID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; ID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; ID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6389,6 +6558,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 09E2..09E3 ; ID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09E6..09EF ; ID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; ID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; ID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; ID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; ID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -6431,6 +6601,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0AE2..0AE3 ; ID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AE6..0AEF ; ID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE 0AF9 ; ID_Continue # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; ID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; ID_Continue # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; ID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; ID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -6491,6 +6662,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE +0C80 ; ID_Continue # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; ID_Continue # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; ID_Continue # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; ID_Continue # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6513,11 +6685,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; ID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; ID_Continue # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; ID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; ID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; ID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; ID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; ID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; ID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; ID_Continue # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; ID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; ID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -6525,6 +6698,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0D4A..0D4C ; ID_Continue # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D ; ID_Continue # Mn MALAYALAM SIGN VIRAMA 0D4E ; ID_Continue # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; ID_Continue # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; ID_Continue # Mc MALAYALAM AU LENGTH MARK 0D5F..0D61 ; ID_Continue # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; ID_Continue # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -6682,7 +6856,9 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1820..1842 ; ID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; ID_Continue # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; ID_Continue # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; ID_Continue # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; ID_Continue # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; ID_Continue # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 ; ID_Continue # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA ; ID_Continue # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; ID_Continue # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -6767,6 +6943,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1C50..1C59 ; ID_Continue # Nd [10] OL CHIKI DIGIT ZERO..OL CHIKI DIGIT NINE 1C5A..1C77 ; ID_Continue # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; ID_Continue # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; ID_Continue # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CD0..1CD2 ; ID_Continue # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; ID_Continue # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; ID_Continue # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -6777,6 +6954,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1CF2..1CF3 ; ID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; ID_Continue # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; ID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; ID_Continue # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; ID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; ID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; ID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -6784,8 +6962,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78 ; ID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; ID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; ID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; ID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; ID_Continue # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; ID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; ID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; ID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; ID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; ID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -6875,12 +7053,12 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30A1..30FA ; ID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; ID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; ID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; ID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; ID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; ID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; ID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; ID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ID_Continue # Lm YI SYLLABLE WU A016..A48C ; ID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -6909,7 +7087,7 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; ID_Continue # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; ID_Continue # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; ID_Continue # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6928,7 +7106,7 @@ A840..A873 ; ID_Continue # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDR A880..A881 ; ID_Continue # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; ID_Continue # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; ID_Continue # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; ID_Continue # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; ID_Continue # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8D0..A8D9 ; ID_Continue # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8E0..A8F1 ; ID_Continue # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A8F2..A8F7 ; ID_Continue # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA @@ -7068,7 +7246,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 102A0..102D0 ; ID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 102E0 ; ID_Continue # Mn COPTIC EPACT THOUSANDS MARK 10300..1031F ; ID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ID_Continue # Nl GOTHIC LETTER NINETY 10342..10349 ; ID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ID_Continue # Nl GOTHIC LETTER NINE HUNDRED @@ -7081,6 +7259,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10400..1044F ; ID_Continue # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; ID_Continue # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; ID_Continue # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; ID_Continue # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; ID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; ID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -7164,6 +7344,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11234 ; ID_Continue # Mn KHOJKI SIGN ANUSVARA 11235 ; ID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; ID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; ID_Continue # Mn KHOJKI SIGN SUKUN 11280..11286 ; ID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; ID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -7195,6 +7376,15 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 11362..11363 ; ID_Continue # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; ID_Continue # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; ID_Continue # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434 ; ID_Continue # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; ID_Continue # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; ID_Continue # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; ID_Continue # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; ID_Continue # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; ID_Continue # Mc NEWA SIGN VISARGA +11446 ; ID_Continue # Mn NEWA SIGN NUKTA +11447..1144A ; ID_Continue # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +11450..11459 ; ID_Continue # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 11480..114AF ; ID_Continue # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; ID_Continue # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; ID_Continue # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -7244,7 +7434,53 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 118A0..118DF ; ID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; ID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; ID_Continue # Lo WARANG CITI OM +11A00 ; ID_Continue # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; ID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; ID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; ID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; ID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; ID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; ID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; ID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; ID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; ID_Continue # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; ID_Continue # Lo SOYOMBO LETTER A +11A51..11A56 ; ID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; ID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; ID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; ID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; ID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; ID_Continue # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; ID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11AC0..11AF8 ; ID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; ID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; ID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; ID_Continue # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; ID_Continue # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; ID_Continue # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; ID_Continue # Mc BHAIKSUKI SIGN VISARGA +11C3F ; ID_Continue # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; ID_Continue # Lo BHAIKSUKI SIGN AVAGRAHA +11C50..11C59 ; ID_Continue # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C72..11C8F ; ID_Continue # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; ID_Continue # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; ID_Continue # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; ID_Continue # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; ID_Continue # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; ID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; ID_Continue # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; ID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; ID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; ID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; ID_Continue # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; ID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; ID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; ID_Continue # Lo MASARAM GONDI REPHA +11D47 ; ID_Continue # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; ID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -7266,7 +7502,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 16F51..16F7E ; ID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; ID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; ID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; ID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; ID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; ID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; ID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; ID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -7316,8 +7556,16 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1DA84 ; ID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; ID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; ID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; ID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; ID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; ID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; ID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4 ; ID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; ID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943 ; ID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A ; ID_Continue # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959 ; ID_Continue # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1EE00..1EE03 ; ID_Continue # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; ID_Continue # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; ID_Continue # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -7355,10 +7603,11 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 2A700..2B734 ; ID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 112352 +# Total code points: 128108 # ================================================ @@ -7427,7 +7676,9 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0824 ; XID_Start # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; XID_Start # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; XID_Start # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; XID_Start # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; XID_Start # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; XID_Start # Lo DEVANAGARI OM @@ -7445,6 +7696,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 09DC..09DD ; XID_Start # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; XID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; XID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; XID_Start # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; XID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; XID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; XID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -7493,6 +7745,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; XID_Start # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; XID_Start # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -7507,6 +7760,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0D12..0D3A ; XID_Start # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; XID_Start # Lo MALAYALAM SIGN AVAGRAHA 0D4E ; XID_Start # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; XID_Start # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D5F..0D61 ; XID_Start # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D7A..0D7F ; XID_Start # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; XID_Start # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA @@ -7590,7 +7844,9 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1820..1842 ; XID_Start # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Start # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; XID_Start # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; XID_Start # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; XID_Start # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; XID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; XID_Start # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; XID_Start # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; XID_Start # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; XID_Start # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -7610,6 +7866,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 1C4D..1C4F ; XID_Start # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; XID_Start # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; XID_Start # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; XID_Start # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CE9..1CEC ; XID_Start # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; XID_Start # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF5..1CF6 ; XID_Start # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA @@ -7696,12 +7953,12 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 30A1..30FA ; XID_Start # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Start # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Start # Lo KATAKANA DIGRAPH KOTO -3105..312D ; XID_Start # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; XID_Start # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; XID_Start # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Start # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Start # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Start # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; XID_Start # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; XID_Start # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; XID_Start # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Start # Lm YI SYLLABLE WU A016..A48C ; XID_Start # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -7725,7 +7982,7 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; XID_Start # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; XID_Start # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; XID_Start # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -7824,7 +8081,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10280..1029C ; XID_Start # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; XID_Start # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; XID_Start # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; XID_Start # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; XID_Start # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; XID_Start # Nl GOTHIC LETTER NINETY 10342..10349 ; XID_Start # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; XID_Start # Nl GOTHIC LETTER NINE HUNDRED @@ -7835,6 +8092,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 103D1..103D5 ; XID_Start # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10400..1044F ; XID_Start # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; XID_Start # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +104B0..104D3 ; XID_Start # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; XID_Start # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Start # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Start # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; XID_Start # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -7896,6 +8155,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1133D ; XID_Start # Lo GRANTHA SIGN AVAGRAHA 11350 ; XID_Start # Lo GRANTHA OM 1135D..11361 ; XID_Start # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; XID_Start # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; XID_Start # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; XID_Start # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; XID_Start # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; XID_Start # Lo TIRHUTA OM @@ -7907,7 +8168,21 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 11700..11719 ; XID_Start # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118A0..118DF ; XID_Start # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; XID_Start # Lo WARANG CITI OM +11A00 ; XID_Start # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; XID_Start # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; XID_Start # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; XID_Start # Lo SOYOMBO LETTER A +11A5C..11A83 ; XID_Start # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; XID_Start # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; XID_Start # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; XID_Start # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; XID_Start # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; XID_Start # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; XID_Start # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; XID_Start # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; XID_Start # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; XID_Start # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; XID_Start # Lo MASARAM GONDI REPHA 12000..12399 ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -7923,7 +8198,11 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 16F00..16F44 ; XID_Start # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; XID_Start # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; XID_Start # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; XID_Start # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; XID_Start # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; XID_Start # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; XID_Start # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; XID_Start # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; XID_Start # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; XID_Start # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -7959,6 +8238,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D7AA..1D7C2 ; XID_Start # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; XID_Start # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1E800..1E8C4 ; XID_Start # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E900..1E943 ; XID_Start # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1EE00..1EE03 ; XID_Start # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; XID_Start # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; XID_Start # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -7996,9 +8276,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 2A700..2B734 ; XID_Start # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 109807 +# Total code points: 125311 # ================================================ @@ -8097,7 +8378,10 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0829..082D ; XID_Continue # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0840..0858 ; XID_Continue # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; XID_Continue # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; XID_Continue # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; XID_Continue # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; XID_Continue # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; XID_Continue # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; XID_Continue # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -8139,6 +8423,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 09E2..09E3 ; XID_Continue # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09E6..09EF ; XID_Continue # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE 09F0..09F1 ; XID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; XID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; XID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; XID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; XID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -8181,6 +8466,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0AE2..0AE3 ; XID_Continue # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL 0AE6..0AEF ; XID_Continue # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE 0AF9 ; XID_Continue # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; XID_Continue # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; XID_Continue # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; XID_Continue # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; XID_Continue # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -8241,6 +8527,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE +0C80 ; XID_Continue # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; XID_Continue # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; XID_Continue # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; XID_Continue # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8263,11 +8550,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; XID_Continue # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; XID_Continue # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; XID_Continue # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; XID_Continue # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; XID_Continue # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; XID_Continue # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; XID_Continue # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; XID_Continue # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; XID_Continue # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; XID_Continue # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; XID_Continue # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -8275,6 +8563,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0D4A..0D4C ; XID_Continue # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D ; XID_Continue # Mn MALAYALAM SIGN VIRAMA 0D4E ; XID_Continue # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; XID_Continue # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; XID_Continue # Mc MALAYALAM AU LENGTH MARK 0D5F..0D61 ; XID_Continue # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; XID_Continue # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -8432,7 +8721,9 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1820..1842 ; XID_Continue # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; XID_Continue # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; XID_Continue # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; XID_Continue # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; XID_Continue # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; XID_Continue # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; XID_Continue # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 ; XID_Continue # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA ; XID_Continue # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; XID_Continue # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -8517,6 +8808,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1C50..1C59 ; XID_Continue # Nd [10] OL CHIKI DIGIT ZERO..OL CHIKI DIGIT NINE 1C5A..1C77 ; XID_Continue # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; XID_Continue # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; XID_Continue # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CD0..1CD2 ; XID_Continue # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; XID_Continue # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; XID_Continue # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -8527,6 +8819,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1CF2..1CF3 ; XID_Continue # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; XID_Continue # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; XID_Continue # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; XID_Continue # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; XID_Continue # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; XID_Continue # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; XID_Continue # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -8534,8 +8827,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1D78 ; XID_Continue # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; XID_Continue # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; XID_Continue # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; XID_Continue # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; XID_Continue # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; XID_Continue # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; XID_Continue # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; XID_Continue # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; XID_Continue # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; XID_Continue # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -8624,12 +8917,12 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30A1..30FA ; XID_Continue # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; XID_Continue # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; XID_Continue # Lo KATAKANA DIGRAPH KOTO -3105..312D ; XID_Continue # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; XID_Continue # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; XID_Continue # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; XID_Continue # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; XID_Continue # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; XID_Continue # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; XID_Continue # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; XID_Continue # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; XID_Continue # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; XID_Continue # Lm YI SYLLABLE WU A016..A48C ; XID_Continue # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -8658,7 +8951,7 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; XID_Continue # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; XID_Continue # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; XID_Continue # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8677,7 +8970,7 @@ A840..A873 ; XID_Continue # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CAND A880..A881 ; XID_Continue # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; XID_Continue # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; XID_Continue # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; XID_Continue # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; XID_Continue # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8D0..A8D9 ; XID_Continue # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8E0..A8F1 ; XID_Continue # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A8F2..A8F7 ; XID_Continue # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA @@ -8823,7 +9116,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 102A0..102D0 ; XID_Continue # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 102E0 ; XID_Continue # Mn COPTIC EPACT THOUSANDS MARK 10300..1031F ; XID_Continue # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; XID_Continue # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; XID_Continue # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; XID_Continue # Nl GOTHIC LETTER NINETY 10342..10349 ; XID_Continue # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; XID_Continue # Nl GOTHIC LETTER NINE HUNDRED @@ -8836,6 +9129,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10400..1044F ; XID_Continue # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; XID_Continue # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; XID_Continue # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; XID_Continue # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; XID_Continue # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; XID_Continue # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; XID_Continue # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; XID_Continue # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -8919,6 +9214,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11234 ; XID_Continue # Mn KHOJKI SIGN ANUSVARA 11235 ; XID_Continue # Mc KHOJKI SIGN VIRAMA 11236..11237 ; XID_Continue # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; XID_Continue # Mn KHOJKI SIGN SUKUN 11280..11286 ; XID_Continue # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; XID_Continue # Lo MULTANI LETTER GHA 1128A..1128D ; XID_Continue # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -8950,6 +9246,15 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 11362..11363 ; XID_Continue # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; XID_Continue # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; XID_Continue # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434 ; XID_Continue # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; XID_Continue # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; XID_Continue # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; XID_Continue # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; XID_Continue # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; XID_Continue # Mc NEWA SIGN VISARGA +11446 ; XID_Continue # Mn NEWA SIGN NUKTA +11447..1144A ; XID_Continue # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +11450..11459 ; XID_Continue # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 11480..114AF ; XID_Continue # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; XID_Continue # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; XID_Continue # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -8999,7 +9304,53 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 118A0..118DF ; XID_Continue # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118E0..118E9 ; XID_Continue # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118FF ; XID_Continue # Lo WARANG CITI OM +11A00 ; XID_Continue # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; XID_Continue # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; XID_Continue # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; XID_Continue # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; XID_Continue # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; XID_Continue # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; XID_Continue # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; XID_Continue # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; XID_Continue # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; XID_Continue # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; XID_Continue # Lo SOYOMBO LETTER A +11A51..11A56 ; XID_Continue # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; XID_Continue # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; XID_Continue # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; XID_Continue # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; XID_Continue # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; XID_Continue # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; XID_Continue # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; XID_Continue # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER 11AC0..11AF8 ; XID_Continue # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; XID_Continue # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; XID_Continue # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; XID_Continue # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; XID_Continue # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; XID_Continue # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; XID_Continue # Mc BHAIKSUKI SIGN VISARGA +11C3F ; XID_Continue # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; XID_Continue # Lo BHAIKSUKI SIGN AVAGRAHA +11C50..11C59 ; XID_Continue # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C72..11C8F ; XID_Continue # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; XID_Continue # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; XID_Continue # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; XID_Continue # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; XID_Continue # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; XID_Continue # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; XID_Continue # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; XID_Continue # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; XID_Continue # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; XID_Continue # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; XID_Continue # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; XID_Continue # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; XID_Continue # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; XID_Continue # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; XID_Continue # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; XID_Continue # Lo MASARAM GONDI REPHA +11D47 ; XID_Continue # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; XID_Continue # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -9021,7 +9372,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 16F51..16F7E ; XID_Continue # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; XID_Continue # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; XID_Continue # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; XID_Continue # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; XID_Continue # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; XID_Continue # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; XID_Continue # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; XID_Continue # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; XID_Continue # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; XID_Continue # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -9071,8 +9426,16 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1DA84 ; XID_Continue # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; XID_Continue # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; XID_Continue # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; XID_Continue # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; XID_Continue # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; XID_Continue # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; XID_Continue # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4 ; XID_Continue # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8D0..1E8D6 ; XID_Continue # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943 ; XID_Continue # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A ; XID_Continue # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959 ; XID_Continue # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1EE00..1EE03 ; XID_Continue # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; XID_Continue # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; XID_Continue # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -9110,10 +9473,11 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 2A700..2B734 ; XID_Continue # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 112333 +# Total code points: 128089 # ================================================ @@ -9123,8 +9487,8 @@ E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO # + Cf (Format characters) # + Variation_Selector # - White_Space -# - FFF9..FFFB (Annotation Characters) -# - 0600..0605, 06DD, 070F, 110BD (exceptional Cf characters that should be visible) +# - FFF9..FFFB (Annotation characters) +# - Prepended_Concatenation_Mark (Exceptional format characters that should be visible) 00AD ; Default_Ignorable_Code_Point # Cf SOFT HYPHEN 034F ; Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER @@ -9186,6 +9550,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0825..0827 ; Grapheme_Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Grapheme_Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Grapheme_Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Grapheme_Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Grapheme_Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Grapheme_Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Grapheme_Extend # Mn DEVANAGARI SIGN NUKTA @@ -9214,6 +9579,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0AC7..0AC8 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Grapheme_Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Grapheme_Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Grapheme_Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Grapheme_Extend # Mn ORIYA SIGN CANDRABINDU 0B3C ; Grapheme_Extend # Mn ORIYA SIGN NUKTA 0B3E ; Grapheme_Extend # Mc ORIYA VOWEL SIGN AA @@ -9242,7 +9608,8 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 0CCC..0CCD ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Grapheme_Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Grapheme_Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Grapheme_Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Grapheme_Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Grapheme_Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E ; Grapheme_Extend # Mc MALAYALAM VOWEL SIGN AA 0D41..0D44 ; Grapheme_Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Grapheme_Extend # Mn MALAYALAM SIGN VIRAMA @@ -9292,6 +9659,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 17C9..17D3 ; Grapheme_Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Grapheme_Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Grapheme_Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; Grapheme_Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Grapheme_Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Grapheme_Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; Grapheme_Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -9330,9 +9698,9 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>..<rese 1CED ; Grapheme_Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Grapheme_Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Grapheme_Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Grapheme_Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Grapheme_Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW -200C..200D ; Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +1DC0..1DF9 ; Grapheme_Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Grapheme_Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200C ; Grapheme_Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Grapheme_Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Grapheme_Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; Grapheme_Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -9353,7 +9721,7 @@ A802 ; Grapheme_Extend # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Grapheme_Extend # Mn SYLOTI NAGRI SIGN HASANTA A80B ; Grapheme_Extend # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Grapheme_Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; Grapheme_Extend # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Grapheme_Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Grapheme_Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Grapheme_Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Grapheme_Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -9406,6 +9774,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1122F..11231 ; Grapheme_Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Grapheme_Extend # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Grapheme_Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Grapheme_Extend # Mn KHOJKI SIGN SUKUN 112DF ; Grapheme_Extend # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Grapheme_Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Grapheme_Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -9415,6 +9784,9 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 11357 ; Grapheme_Extend # Mc GRANTHA AU LENGTH MARK 11366..1136C ; Grapheme_Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Grapheme_Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; Grapheme_Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; Grapheme_Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; Grapheme_Extend # Mn NEWA SIGN NUKTA 114B0 ; Grapheme_Extend # Mc TIRHUTA VOWEL SIGN AA 114B3..114B8 ; Grapheme_Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Grapheme_Extend # Mn TIRHUTA VOWEL SIGN SHORT E @@ -9436,6 +9808,27 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1171D..1171F ; Grapheme_Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Grapheme_Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Grapheme_Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Grapheme_Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Grapheme_Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Grapheme_Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Grapheme_Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Grapheme_Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Grapheme_Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Grapheme_Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Grapheme_Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; Grapheme_Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Grapheme_Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; Grapheme_Extend # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Grapheme_Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; Grapheme_Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; Grapheme_Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; Grapheme_Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Grapheme_Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Grapheme_Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Grapheme_Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Grapheme_Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Grapheme_Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Grapheme_Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Grapheme_Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Grapheme_Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -9453,10 +9846,17 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1DA84 ; Grapheme_Extend # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Grapheme_Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Grapheme_Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Grapheme_Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Grapheme_Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Grapheme_Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Grapheme_Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Grapheme_Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Grapheme_Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Grapheme_Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1610 +# Total code points: 1901 # ================================================ @@ -9613,7 +10013,9 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0830..083E ; Grapheme_Base # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; Grapheme_Base # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; Grapheme_Base # Po MANDAIC PUNCTUATION +0860..086A ; Grapheme_Base # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Grapheme_Base # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; Grapheme_Base # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; Grapheme_Base # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093B ; Grapheme_Base # Mc DEVANAGARI VOWEL SIGN OOE @@ -9648,6 +10050,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 09F4..09F9 ; Grapheme_Base # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; Grapheme_Base # So BENGALI ISSHAR 09FB ; Grapheme_Base # Sc BENGALI GANDA MARK +09FC ; Grapheme_Base # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; Grapheme_Base # Po BENGALI ABBREVIATION SIGN 0A03 ; Grapheme_Base # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Grapheme_Base # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Grapheme_Base # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -9727,6 +10131,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0C66..0C6F ; Grapheme_Base # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C78..0C7E ; Grapheme_Base # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; Grapheme_Base # So TELUGU SIGN TUUMU +0C80 ; Grapheme_Base # Lo KANNADA SIGN SPACING CANDRABINDU 0C82..0C83 ; Grapheme_Base # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; Grapheme_Base # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; Grapheme_Base # Lo [3] KANNADA LETTER E..KANNADA LETTER AI @@ -9752,9 +10157,12 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0D46..0D48 ; Grapheme_Base # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI 0D4A..0D4C ; Grapheme_Base # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4E ; Grapheme_Base # Lo MALAYALAM LETTER DOT REPH +0D4F ; Grapheme_Base # So MALAYALAM SIGN PARA +0D54..0D56 ; Grapheme_Base # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL +0D58..0D5E ; Grapheme_Base # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; Grapheme_Base # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D66..0D6F ; Grapheme_Base # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75 ; Grapheme_Base # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; Grapheme_Base # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79 ; Grapheme_Base # So MALAYALAM DATE MARK 0D7A..0D7F ; Grapheme_Base # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83 ; Grapheme_Base # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -9911,7 +10319,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1820..1842 ; Grapheme_Base # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Grapheme_Base # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; Grapheme_Base # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; Grapheme_Base # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; Grapheme_Base # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; Grapheme_Base # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; Grapheme_Base # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; Grapheme_Base # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; Grapheme_Base # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -9977,6 +10386,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1C5A..1C77 ; Grapheme_Base # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; Grapheme_Base # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F ; Grapheme_Base # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88 ; Grapheme_Base # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7 ; Grapheme_Base # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD3 ; Grapheme_Base # Po VEDIC SIGN NIHSHVASA 1CE1 ; Grapheme_Base # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -9984,6 +10394,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 1CEE..1CF1 ; Grapheme_Base # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Grapheme_Base # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; Grapheme_Base # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; Grapheme_Base # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; Grapheme_Base # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Grapheme_Base # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Grapheme_Base # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -10054,7 +10465,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 208D ; Grapheme_Base # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Grapheme_Base # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; Grapheme_Base # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BE ; Grapheme_Base # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Grapheme_Base # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 2100..2101 ; Grapheme_Base # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Grapheme_Base # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Grapheme_Base # So [4] DEGREE CELSIUS..CADA UNA @@ -10128,8 +10539,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 239B..23B3 ; Grapheme_Base # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Grapheme_Base # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Grapheme_Base # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; Grapheme_Base # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; Grapheme_Base # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Grapheme_Base # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; Grapheme_Base # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; Grapheme_Base # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; Grapheme_Base # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -10215,7 +10625,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; Grapheme_Base # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; Grapheme_Base # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; Grapheme_Base # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; Grapheme_Base # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; Grapheme_Base # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; Grapheme_Base # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; Grapheme_Base # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -10280,6 +10690,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2E40 ; Grapheme_Base # Pd DOUBLE HYPHEN 2E41 ; Grapheme_Base # Po REVERSED COMMA 2E42 ; Grapheme_Base # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; Grapheme_Base # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; Grapheme_Base # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; Grapheme_Base # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; Grapheme_Base # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -10331,7 +10742,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 30FB ; Grapheme_Base # Po KATAKANA MIDDLE DOT 30FC..30FE ; Grapheme_Base # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; Grapheme_Base # Lo KATAKANA DIGRAPH KOTO -3105..312D ; Grapheme_Base # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Grapheme_Base # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Grapheme_Base # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; Grapheme_Base # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; Grapheme_Base # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -10353,7 +10764,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 3300..33FF ; Grapheme_Base # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; Grapheme_Base # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DC0..4DFF ; Grapheme_Base # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5 ; Grapheme_Base # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Grapheme_Base # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Grapheme_Base # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; Grapheme_Base # Lm YI SYLLABLE WU A016..A48C ; Grapheme_Base # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -10387,7 +10798,7 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; Grapheme_Base # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; Grapheme_Base # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; Grapheme_Base # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Grapheme_Base # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -10618,7 +11029,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10175..10178 ; Grapheme_Base # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189 ; Grapheme_Base # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B ; Grapheme_Base # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C ; Grapheme_Base # So GREEK SINUSOID SIGN +1018C..1018E ; Grapheme_Base # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B ; Grapheme_Base # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0 ; Grapheme_Base # So GREEK SYMBOL TAU RHO 101D0..101FC ; Grapheme_Base # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -10627,7 +11038,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 102E1..102FB ; Grapheme_Base # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; Grapheme_Base # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; Grapheme_Base # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; Grapheme_Base # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Grapheme_Base # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; Grapheme_Base # Nl GOTHIC LETTER NINETY 10342..10349 ; Grapheme_Base # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; Grapheme_Base # Nl GOTHIC LETTER NINE HUNDRED @@ -10641,6 +11052,8 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10400..1044F ; Grapheme_Base # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; Grapheme_Base # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; Grapheme_Base # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; Grapheme_Base # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; Grapheme_Base # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; Grapheme_Base # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; Grapheme_Base # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; Grapheme_Base # Po CAUCASIAN ALBANIAN CITATION MARK @@ -10767,6 +11180,15 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11350 ; Grapheme_Base # Lo GRANTHA OM 1135D..11361 ; Grapheme_Base # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; Grapheme_Base # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11400..11434 ; Grapheme_Base # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; Grapheme_Base # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11440..11441 ; Grapheme_Base # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11445 ; Grapheme_Base # Mc NEWA SIGN VISARGA +11447..1144A ; Grapheme_Base # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; Grapheme_Base # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; Grapheme_Base # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; Grapheme_Base # Po NEWA PLACEHOLDER MARK +1145D ; Grapheme_Base # Po NEWA INSERTION SIGN 11480..114AF ; Grapheme_Base # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B1..114B2 ; Grapheme_Base # Mc [2] TIRHUTA VOWEL SIGN I..TIRHUTA VOWEL SIGN II 114B9 ; Grapheme_Base # Mc TIRHUTA VOWEL SIGN E @@ -10790,6 +11212,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 11641..11643 ; Grapheme_Base # Po [3] MODI DANDA..MODI ABBREVIATION SIGN 11644 ; Grapheme_Base # Lo MODI SIGN HUVA 11650..11659 ; Grapheme_Base # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C ; Grapheme_Base # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11680..116AA ; Grapheme_Base # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116AC ; Grapheme_Base # Mc TAKRI SIGN VISARGA 116AE..116AF ; Grapheme_Base # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II @@ -10806,7 +11229,38 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 118E0..118E9 ; Grapheme_Base # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; Grapheme_Base # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; Grapheme_Base # Lo WARANG CITI OM +11A00 ; Grapheme_Base # Lo ZANABAZAR SQUARE LETTER A +11A07..11A08 ; Grapheme_Base # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A0B..11A32 ; Grapheme_Base # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A39 ; Grapheme_Base # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Grapheme_Base # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3F..11A46 ; Grapheme_Base # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; Grapheme_Base # Lo SOYOMBO LETTER A +11A57..11A58 ; Grapheme_Base # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A5C..11A83 ; Grapheme_Base # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Grapheme_Base # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A97 ; Grapheme_Base # Mc SOYOMBO SIGN VISARGA +11A9A..11A9C ; Grapheme_Base # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Grapheme_Base # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; Grapheme_Base # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; Grapheme_Base # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; Grapheme_Base # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; Grapheme_Base # Mc BHAIKSUKI VOWEL SIGN AA +11C3E ; Grapheme_Base # Mc BHAIKSUKI SIGN VISARGA +11C40 ; Grapheme_Base # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; Grapheme_Base # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; Grapheme_Base # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; Grapheme_Base # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71 ; Grapheme_Base # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; Grapheme_Base # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11CA9 ; Grapheme_Base # Mc MARCHEN SUBJOINED LETTER YA +11CB1 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN I +11CB4 ; Grapheme_Base # Mc MARCHEN VOWEL SIGN O +11D00..11D06 ; Grapheme_Base # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Grapheme_Base # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Grapheme_Base # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; Grapheme_Base # Lo MASARAM GONDI REPHA +11D50..11D59 ; Grapheme_Base # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; Grapheme_Base # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; Grapheme_Base # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; Grapheme_Base # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -10833,7 +11287,11 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 16F50 ; Grapheme_Base # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; Grapheme_Base # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; Grapheme_Base # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; Grapheme_Base # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; Grapheme_Base # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; Grapheme_Base # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; Grapheme_Base # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; Grapheme_Base # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Grapheme_Base # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Grapheme_Base # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Grapheme_Base # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Grapheme_Base # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -10902,6 +11360,9 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1DA87..1DA8B ; Grapheme_Base # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1E800..1E8C4 ; Grapheme_Base # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; Grapheme_Base # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE +1E900..1E943 ; Grapheme_Base # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E950..1E959 ; Grapheme_Base # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; Grapheme_Base # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK 1EE00..1EE03 ; Grapheme_Base # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Grapheme_Base # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Grapheme_Base # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -10945,18 +11406,17 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F100..1F10C ; Grapheme_Base # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F110..1F12E ; Grapheme_Base # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F16B ; Grapheme_Base # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN -1F170..1F19A ; Grapheme_Base # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; Grapheme_Base # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F202 ; Grapheme_Base # So [29] REGIONAL INDICATOR SYMBOL LETTER A..SQUARED KATAKANA SA -1F210..1F23A ; Grapheme_Base # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; Grapheme_Base # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; Grapheme_Base # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; Grapheme_Base # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; Grapheme_Base # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; Grapheme_Base # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Grapheme_Base # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579 ; Grapheme_Base # So [378] RAT..JOYSTICK -1F57B..1F5A3 ; Grapheme_Base # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; Grapheme_Base # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP +1F400..1F6D4 ; Grapheme_Base # So [725] RAT..PAGODA 1F6E0..1F6EC ; Grapheme_Base # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; Grapheme_Base # So [4] SATELLITE..PASSENGER SHIP +1F6F0..1F6F8 ; Grapheme_Base # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; Grapheme_Base # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; Grapheme_Base # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; Grapheme_Base # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -10964,16 +11424,21 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1F850..1F859 ; Grapheme_Base # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Grapheme_Base # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Grapheme_Base # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; Grapheme_Base # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; Grapheme_Base # So [5] CRAB..UNICORN FACE +1F900..1F90B ; Grapheme_Base # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; Grapheme_Base # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; Grapheme_Base # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; Grapheme_Base # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; Grapheme_Base # So [24] CRAB..CRICKET 1F9C0 ; Grapheme_Base # So CHEESE WEDGE +1F9D0..1F9E6 ; Grapheme_Base # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; Grapheme_Base # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Grapheme_Base # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Grapheme_Base # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Grapheme_Base # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Grapheme_Base # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Grapheme_Base # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 118912 +# Total code points: 134733 # ================================================ @@ -10989,6 +11454,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 0BCD ; Grapheme_Link # Mn TAMIL SIGN VIRAMA 0C4D ; Grapheme_Link # Mn TELUGU SIGN VIRAMA 0CCD ; Grapheme_Link # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; Grapheme_Link # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; Grapheme_Link # Mn MALAYALAM SIGN VIRAMA 0DCA ; Grapheme_Link # Mn SINHALA SIGN AL-LAKUNA 0E3A ; Grapheme_Link # Mn THAI CHARACTER PHINTHU @@ -11018,12 +11484,18 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 11235 ; Grapheme_Link # Mc KHOJKI SIGN VIRAMA 112EA ; Grapheme_Link # Mn KHUDAWADI SIGN VIRAMA 1134D ; Grapheme_Link # Mc GRANTHA SIGN VIRAMA +11442 ; Grapheme_Link # Mn NEWA SIGN VIRAMA 114C2 ; Grapheme_Link # Mn TIRHUTA SIGN VIRAMA 115BF ; Grapheme_Link # Mn SIDDHAM SIGN VIRAMA 1163F ; Grapheme_Link # Mn MODI SIGN VIRAMA 116B6 ; Grapheme_Link # Mc TAKRI SIGN VIRAMA 1172B ; Grapheme_Link # Mn AHOM SIGN KILLER +11A34 ; Grapheme_Link # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; Grapheme_Link # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Grapheme_Link # Mn SOYOMBO SUBJOINER +11C3F ; Grapheme_Link # Mn BHAIKSUKI SIGN VIRAMA +11D44..11D45 ; Grapheme_Link # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA -# Total code points: 45 +# Total code points: 54 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/DNormalizationProps.txt b/gnu/usr.bin/perl/lib/unicore/DNormalizationProps.txt index 6492493da38..941c310b961 100644 --- a/gnu/usr.bin/perl/lib/unicore/DNormalizationProps.txt +++ b/gnu/usr.bin/perl/lib/unicore/DNormalizationProps.txt @@ -1,10 +1,11 @@ -# DerivedNormalizationProps-8.0.0.txt -# Date: 2015-02-13, 13:30:23 GMT [MD] +# DerivedNormalizationProps-10.0.0.txt +# Date: 2017-02-14, 04:26:07 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -1679,12 +1680,12 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1F16A..1F16B ; NFKD_QC; N # So [2] RAISED MC SIGN..RAISED MD SIGN 1F190 ; NFKD_QC; N # So SQUARE DJ 1F200..1F202 ; NFKD_QC; N # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; NFKD_QC; N # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; NFKD_QC; N # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; NFKD_QC; N # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; NFKD_QC; N # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 16893 +# Total code points: 16894 # ================================================ @@ -2082,12 +2083,12 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1F16A..1F16B ; NFKC_QC; N # So [2] RAISED MC SIGN..RAISED MD SIGN 1F190 ; NFKC_QC; N # So SQUARE DJ 1F200..1F202 ; NFKC_QC; N # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; NFKC_QC; N # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; NFKC_QC; N # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; NFKC_QC; N # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; NFKC_QC; N # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4793 +# Total code points: 4794 # ================================================ @@ -3513,6 +3514,14 @@ FFE3 ; Expands_On_NFKC # Sk FULLWIDTH MACRON 17B4..17B5 ; NFKC_CF; # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; NFKC_CF; # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; NFKC_CF; # Cf MONGOLIAN VOWEL SEPARATOR +1C80 ; NFKC_CF; 0432 # L& CYRILLIC SMALL LETTER ROUNDED VE +1C81 ; NFKC_CF; 0434 # L& CYRILLIC SMALL LETTER LONG-LEGGED DE +1C82 ; NFKC_CF; 043E # L& CYRILLIC SMALL LETTER NARROW O +1C83 ; NFKC_CF; 0441 # L& CYRILLIC SMALL LETTER WIDE ES +1C84..1C85 ; NFKC_CF; 0442 # L& [2] CYRILLIC SMALL LETTER TALL TE..CYRILLIC SMALL LETTER THREE-LEGGED TE +1C86 ; NFKC_CF; 044A # L& CYRILLIC SMALL LETTER TALL HARD SIGN +1C87 ; NFKC_CF; 0463 # L& CYRILLIC SMALL LETTER TALL YAT +1C88 ; NFKC_CF; A64B # L& CYRILLIC SMALL LETTER UNBLENDED UK 1D2C ; NFKC_CF; 0061 # Lm MODIFIER LETTER CAPITAL A 1D2D ; NFKC_CF; 00E6 # Lm MODIFIER LETTER CAPITAL AE 1D2E ; NFKC_CF; 0062 # Lm MODIFIER LETTER CAPITAL B @@ -5263,6 +5272,7 @@ A7AA ; NFKC_CF; 0266 # L& LATIN CAPITAL LETTER H WITH H A7AB ; NFKC_CF; 025C # L& LATIN CAPITAL LETTER REVERSED OPEN E A7AC ; NFKC_CF; 0261 # L& LATIN CAPITAL LETTER SCRIPT G A7AD ; NFKC_CF; 026C # L& LATIN CAPITAL LETTER L WITH BELT +A7AE ; NFKC_CF; 026A # L& LATIN CAPITAL LETTER SMALL CAPITAL I A7B0 ; NFKC_CF; 029E # L& LATIN CAPITAL LETTER TURNED K A7B1 ; NFKC_CF; 0287 # L& LATIN CAPITAL LETTER TURNED T A7B2 ; NFKC_CF; 029D # L& LATIN CAPITAL LETTER J WITH CROSSED-TAIL @@ -6731,6 +6741,42 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF 10425 ; NFKC_CF; 1044D # L& DESERET CAPITAL LETTER ENG 10426 ; NFKC_CF; 1044E # L& DESERET CAPITAL LETTER OI 10427 ; NFKC_CF; 1044F # L& DESERET CAPITAL LETTER EW +104B0 ; NFKC_CF; 104D8 # L& OSAGE CAPITAL LETTER A +104B1 ; NFKC_CF; 104D9 # L& OSAGE CAPITAL LETTER AI +104B2 ; NFKC_CF; 104DA # L& OSAGE CAPITAL LETTER AIN +104B3 ; NFKC_CF; 104DB # L& OSAGE CAPITAL LETTER AH +104B4 ; NFKC_CF; 104DC # L& OSAGE CAPITAL LETTER BRA +104B5 ; NFKC_CF; 104DD # L& OSAGE CAPITAL LETTER CHA +104B6 ; NFKC_CF; 104DE # L& OSAGE CAPITAL LETTER EHCHA +104B7 ; NFKC_CF; 104DF # L& OSAGE CAPITAL LETTER E +104B8 ; NFKC_CF; 104E0 # L& OSAGE CAPITAL LETTER EIN +104B9 ; NFKC_CF; 104E1 # L& OSAGE CAPITAL LETTER HA +104BA ; NFKC_CF; 104E2 # L& OSAGE CAPITAL LETTER HYA +104BB ; NFKC_CF; 104E3 # L& OSAGE CAPITAL LETTER I +104BC ; NFKC_CF; 104E4 # L& OSAGE CAPITAL LETTER KA +104BD ; NFKC_CF; 104E5 # L& OSAGE CAPITAL LETTER EHKA +104BE ; NFKC_CF; 104E6 # L& OSAGE CAPITAL LETTER KYA +104BF ; NFKC_CF; 104E7 # L& OSAGE CAPITAL LETTER LA +104C0 ; NFKC_CF; 104E8 # L& OSAGE CAPITAL LETTER MA +104C1 ; NFKC_CF; 104E9 # L& OSAGE CAPITAL LETTER NA +104C2 ; NFKC_CF; 104EA # L& OSAGE CAPITAL LETTER O +104C3 ; NFKC_CF; 104EB # L& OSAGE CAPITAL LETTER OIN +104C4 ; NFKC_CF; 104EC # L& OSAGE CAPITAL LETTER PA +104C5 ; NFKC_CF; 104ED # L& OSAGE CAPITAL LETTER EHPA +104C6 ; NFKC_CF; 104EE # L& OSAGE CAPITAL LETTER SA +104C7 ; NFKC_CF; 104EF # L& OSAGE CAPITAL LETTER SHA +104C8 ; NFKC_CF; 104F0 # L& OSAGE CAPITAL LETTER TA +104C9 ; NFKC_CF; 104F1 # L& OSAGE CAPITAL LETTER EHTA +104CA ; NFKC_CF; 104F2 # L& OSAGE CAPITAL LETTER TSA +104CB ; NFKC_CF; 104F3 # L& OSAGE CAPITAL LETTER EHTSA +104CC ; NFKC_CF; 104F4 # L& OSAGE CAPITAL LETTER TSHA +104CD ; NFKC_CF; 104F5 # L& OSAGE CAPITAL LETTER DHA +104CE ; NFKC_CF; 104F6 # L& OSAGE CAPITAL LETTER U +104CF ; NFKC_CF; 104F7 # L& OSAGE CAPITAL LETTER WA +104D0 ; NFKC_CF; 104F8 # L& OSAGE CAPITAL LETTER KHA +104D1 ; NFKC_CF; 104F9 # L& OSAGE CAPITAL LETTER GHA +104D2 ; NFKC_CF; 104FA # L& OSAGE CAPITAL LETTER ZA +104D3 ; NFKC_CF; 104FB # L& OSAGE CAPITAL LETTER ZHA 10C80 ; NFKC_CF; 10CC0 # L& OLD HUNGARIAN CAPITAL LETTER A 10C81 ; NFKC_CF; 10CC1 # L& OLD HUNGARIAN CAPITAL LETTER AA 10C82 ; NFKC_CF; 10CC2 # L& OLD HUNGARIAN CAPITAL LETTER EB @@ -7819,6 +7865,40 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF 1D7FD ; NFKC_CF; 0037 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN 1D7FE ; NFKC_CF; 0038 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT 1D7FF ; NFKC_CF; 0039 # Nd MATHEMATICAL MONOSPACE DIGIT NINE +1E900 ; NFKC_CF; 1E922 # L& ADLAM CAPITAL LETTER ALIF +1E901 ; NFKC_CF; 1E923 # L& ADLAM CAPITAL LETTER DAALI +1E902 ; NFKC_CF; 1E924 # L& ADLAM CAPITAL LETTER LAAM +1E903 ; NFKC_CF; 1E925 # L& ADLAM CAPITAL LETTER MIIM +1E904 ; NFKC_CF; 1E926 # L& ADLAM CAPITAL LETTER BA +1E905 ; NFKC_CF; 1E927 # L& ADLAM CAPITAL LETTER SINNYIIYHE +1E906 ; NFKC_CF; 1E928 # L& ADLAM CAPITAL LETTER PE +1E907 ; NFKC_CF; 1E929 # L& ADLAM CAPITAL LETTER BHE +1E908 ; NFKC_CF; 1E92A # L& ADLAM CAPITAL LETTER RA +1E909 ; NFKC_CF; 1E92B # L& ADLAM CAPITAL LETTER E +1E90A ; NFKC_CF; 1E92C # L& ADLAM CAPITAL LETTER FA +1E90B ; NFKC_CF; 1E92D # L& ADLAM CAPITAL LETTER I +1E90C ; NFKC_CF; 1E92E # L& ADLAM CAPITAL LETTER O +1E90D ; NFKC_CF; 1E92F # L& ADLAM CAPITAL LETTER DHA +1E90E ; NFKC_CF; 1E930 # L& ADLAM CAPITAL LETTER YHE +1E90F ; NFKC_CF; 1E931 # L& ADLAM CAPITAL LETTER WAW +1E910 ; NFKC_CF; 1E932 # L& ADLAM CAPITAL LETTER NUN +1E911 ; NFKC_CF; 1E933 # L& ADLAM CAPITAL LETTER KAF +1E912 ; NFKC_CF; 1E934 # L& ADLAM CAPITAL LETTER YA +1E913 ; NFKC_CF; 1E935 # L& ADLAM CAPITAL LETTER U +1E914 ; NFKC_CF; 1E936 # L& ADLAM CAPITAL LETTER JIIM +1E915 ; NFKC_CF; 1E937 # L& ADLAM CAPITAL LETTER CHI +1E916 ; NFKC_CF; 1E938 # L& ADLAM CAPITAL LETTER HA +1E917 ; NFKC_CF; 1E939 # L& ADLAM CAPITAL LETTER QAAF +1E918 ; NFKC_CF; 1E93A # L& ADLAM CAPITAL LETTER GA +1E919 ; NFKC_CF; 1E93B # L& ADLAM CAPITAL LETTER NYA +1E91A ; NFKC_CF; 1E93C # L& ADLAM CAPITAL LETTER TU +1E91B ; NFKC_CF; 1E93D # L& ADLAM CAPITAL LETTER NHA +1E91C ; NFKC_CF; 1E93E # L& ADLAM CAPITAL LETTER VA +1E91D ; NFKC_CF; 1E93F # L& ADLAM CAPITAL LETTER KHA +1E91E ; NFKC_CF; 1E940 # L& ADLAM CAPITAL LETTER GBE +1E91F ; NFKC_CF; 1E941 # L& ADLAM CAPITAL LETTER ZAL +1E920 ; NFKC_CF; 1E942 # L& ADLAM CAPITAL LETTER KPO +1E921 ; NFKC_CF; 1E943 # L& ADLAM CAPITAL LETTER SHA 1EE00 ; NFKC_CF; 0627 # Lo ARABIC MATHEMATICAL ALEF 1EE01 ; NFKC_CF; 0628 # Lo ARABIC MATHEMATICAL BEH 1EE02 ; NFKC_CF; 062C # Lo ARABIC MATHEMATICAL JEEM @@ -8083,6 +8163,7 @@ FFF0..FFF8 ; NFKC_CF; # Cn [9] <reserved-FFF0>..<reserved-FF 1F238 ; NFKC_CF; 7533 # So SQUARED CJK UNIFIED IDEOGRAPH-7533 1F239 ; NFKC_CF; 5272 # So SQUARED CJK UNIFIED IDEOGRAPH-5272 1F23A ; NFKC_CF; 55B6 # So SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F23B ; NFKC_CF; 914D # So SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240 ; NFKC_CF; 3014 672C 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C 1F241 ; NFKC_CF; 3014 4E09 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09 1F242 ; NFKC_CF; 3014 4E8C 3015 # So TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E8C @@ -8634,7 +8715,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 10146 +# Total code points: 10227 # ================================================ @@ -8972,6 +9053,7 @@ E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved- 17B4..17B5 ; Changes_When_NFKC_Casefolded # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA 180B..180D ; Changes_When_NFKC_Casefolded # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE 180E ; Changes_When_NFKC_Casefolded # Cf MONGOLIAN VOWEL SEPARATOR +1C80..1C88 ; Changes_When_NFKC_Casefolded # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D2C..1D2E ; Changes_When_NFKC_Casefolded # Lm [3] MODIFIER LETTER CAPITAL A..MODIFIER LETTER CAPITAL B 1D30..1D3A ; Changes_When_NFKC_Casefolded # Lm [11] MODIFIER LETTER CAPITAL D..MODIFIER LETTER CAPITAL N 1D3C..1D4D ; Changes_When_NFKC_Casefolded # Lm [18] MODIFIER LETTER CAPITAL O..MODIFIER LETTER SMALL G @@ -9389,7 +9471,7 @@ A7A2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER K W A7A4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Changes_When_NFKC_Casefolded # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Changes_When_NFKC_Casefolded # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER OMEGA A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -9519,6 +9601,7 @@ FFE9..FFEC ; Changes_When_NFKC_Casefolded # Sm [4] HALFWIDTH LEFTWARDS ARRO FFED..FFEE ; Changes_When_NFKC_Casefolded # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserved-FFF8> 10400..10427 ; Changes_When_NFKC_Casefolded # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Changes_When_NFKC_Casefolded # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Changes_When_NFKC_Casefolded # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Changes_When_NFKC_Casefolded # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 1BCA0..1BCA3 ; Changes_When_NFKC_Casefolded # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP @@ -9566,6 +9649,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv 1D7C3 ; Changes_When_NFKC_Casefolded # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL 1D7C4..1D7CB ; Changes_When_NFKC_Casefolded # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1D7CE..1D7FF ; Changes_When_NFKC_Casefolded # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E900..1E921 ; Changes_When_NFKC_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA 1EE00..1EE03 ; Changes_When_NFKC_Casefolded # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Changes_When_NFKC_Casefolded # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Changes_When_NFKC_Casefolded # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -9605,7 +9689,7 @@ FFF0..FFF8 ; Changes_When_NFKC_Casefolded # Cn [9] <reserved-FFF0>..<reserv 1F16A..1F16B ; Changes_When_NFKC_Casefolded # So [2] RAISED MC SIGN..RAISED MD SIGN 1F190 ; Changes_When_NFKC_Casefolded # So SQUARE DJ 1F200..1F202 ; Changes_When_NFKC_Casefolded # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; Changes_When_NFKC_Casefolded # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; Changes_When_NFKC_Casefolded # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; Changes_When_NFKC_Casefolded # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; Changes_When_NFKC_Casefolded # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT 2F800..2FA1D ; Changes_When_NFKC_Casefolded # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D @@ -9617,6 +9701,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 10146 +# Total code points: 10227 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/EastAsianWidth.txt b/gnu/usr.bin/perl/lib/unicore/EastAsianWidth.txt index b72970e1713..0d3129bb0a8 100644 --- a/gnu/usr.bin/perl/lib/unicore/EastAsianWidth.txt +++ b/gnu/usr.bin/perl/lib/unicore/EastAsianWidth.txt @@ -1,35 +1,34 @@ -# EastAsianWidth-8.0.0.txt -# Date: 2015-02-10, 21:00:00 GMT [KW, LI] +# EastAsianWidth-10.0.0.txt +# Date: 2017-03-08, 02:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # East_Asian_Width Property # # This file is an informative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # The format is two fields separated by a semicolon. # Field 0: Unicode code point value or range of code point values # Field 1: East_Asian_Width property, consisting of one of the following values: -# "N", "A", "H", "W", "F", "Na" +# "A", "F", "H", "N", "Na", "W" # - All code points, assigned or unassigned, that are not listed -# explicitly are given the value "N". -# The unassigned code points that default to "W" include ranges in the -# following blocks: -# CJK Unified Ideographs Extension A: U+3400..U+4DBF -# CJK Unified Ideographs: U+4E00..U+9FFF -# CJK Compatibility Ideographs: U+F900..U+FAFF -# CJK Unified Ideographs Extension B: U+20000..U+2A6DF -# CJK Unified Ideographs Extension C: U+2A700..U+2B73F -# CJK Unified Ideographs Extension D: U+2B740..U+2B81F -# CJK Unified Ideographs Extension E: U+2B820..U+2CEAF -# CJK Compatibility Ideographs Supplement: U+2F800..U+2FA1F -# and any other reserved code points on -# Planes 2 and 3: U+20000..U+2FFFD -# U+30000..U+3FFFD -# - Character ranges are specified as for other property files in -# the Unicode Character Database. +# explicitly are given the value "N". +# - The unassigned code points in the following blocks default to "W": +# CJK Unified Ideographs Extension A: U+3400..U+4DBF +# CJK Unified Ideographs: U+4E00..U+9FFF +# CJK Compatibility Ideographs: U+F900..U+FAFF +# - All undesignated code points in Planes 2 and 3, whether inside or +# outside of allocated blocks, default to "W": +# Plane 2: U+20000..U+2FFFD +# Plane 3: U+30000..U+3FFFD +# +# Character ranges are specified as for other property files in the +# Unicode Character Database. # # For legacy reasons, there are no spaces before or after the semicolon # which separates the two fields. The comments following the number sign @@ -329,7 +328,11 @@ 0840..0858;N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B;N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E;N # Po MANDAIC PUNCTUATION +0860..086A;N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4;N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD;N # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1;N # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2;N # Cf ARABIC DISPUTED END OF AYAH 08E3..08FF;N # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 0900..0902;N # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0903;N # Mc DEVANAGARI SIGN VISARGA @@ -379,6 +382,8 @@ 09F4..09F9;N # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA;N # So BENGALI ISSHAR 09FB;N # Sc BENGALI GANDA MARK +09FC;N # Lo BENGALI LETTER VEDIC ANUSVARA +09FD;N # Po BENGALI ABBREVIATION SIGN 0A01..0A02;N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03;N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A;N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -423,6 +428,7 @@ 0AF0;N # Po GUJARATI ABBREVIATION SIGN 0AF1;N # Sc GUJARATI RUPEE SIGN 0AF9;N # Lo GUJARATI LETTER ZHA +0AFA..0AFF;N # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01;N # Mn ORIYA SIGN CANDRABINDU 0B02..0B03;N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C;N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -491,6 +497,7 @@ 0C66..0C6F;N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C78..0C7E;N # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F;N # So TELUGU SIGN TUUMU +0C80;N # Lo KANNADA SIGN SPACING CANDRABINDU 0C81;N # Mn KANNADA SIGN CANDRABINDU 0C82..0C83;N # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C;N # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -513,11 +520,12 @@ 0CE2..0CE3;N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF;N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2;N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01;N # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01;N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03;N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C;N # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10;N # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A;N # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C;N # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D;N # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40;N # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44;N # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -525,11 +533,14 @@ 0D4A..0D4C;N # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D;N # Mn MALAYALAM SIGN VIRAMA 0D4E;N # Lo MALAYALAM LETTER DOT REPH +0D4F;N # So MALAYALAM SIGN PARA +0D54..0D56;N # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57;N # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E;N # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61;N # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63;N # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0D66..0D6F;N # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75;N # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78;N # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79;N # So MALAYALAM DATE MARK 0D7A..0D7F;N # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83;N # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -732,7 +743,9 @@ 1820..1842;N # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843;N # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877;N # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8;N # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884;N # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886;N # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8;N # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9;N # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA;N # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5;N # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -832,6 +845,7 @@ 1C5A..1C77;N # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D;N # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F;N # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88;N # Ll [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7;N # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD0..1CD2;N # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD3;N # Po VEDIC SIGN NIHSHVASA @@ -844,6 +858,7 @@ 1CF2..1CF3;N # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4;N # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6;N # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7;N # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9;N # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B;N # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A;N # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -852,8 +867,8 @@ 1D79..1D7F;N # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A;N # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF;N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5;N # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF;N # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9;N # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF;N # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF;N # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15;N # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D;N # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -945,7 +960,7 @@ 20A9;H # Sc WON SIGN 20AA..20AB;N # Sc [2] NEW SHEQEL SIGN..DONG SIGN 20AC;A # Sc EURO SIGN -20AD..20BE;N # Sc [18] KIP SIGN..LARI SIGN +20AD..20BF;N # Sc [19] KIP SIGN..BITCOIN SIGN 20D0..20DC;N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0;N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1;N # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1092,7 +1107,9 @@ 230B;N # Pe RIGHT FLOOR 230C..2311;N # So [6] BOTTOM RIGHT CROP..SQUARE LOZENGE 2312;A # So ARC -2313..231F;N # So [13] SEGMENT..BOTTOM RIGHT CORNER +2313..2319;N # So [7] SEGMENT..TURNED NOT SIGN +231A..231B;W # So [2] WATCH..HOURGLASS +231C..231F;N # So [4] TOP LEFT CORNER..BOTTOM RIGHT CORNER 2320..2321;N # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328;N # So [7] FROWN..KEYBOARD 2329;W # Ps LEFT-POINTING ANGLE BRACKET @@ -1103,7 +1120,13 @@ 239B..23B3;N # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB;N # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1;N # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA;N # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD +23E2..23E8;N # So [7] WHITE TRAPEZIUM..DECIMAL EXPONENT SYMBOL +23E9..23EC;W # So [4] BLACK RIGHT-POINTING DOUBLE TRIANGLE..BLACK DOWN-POINTING DOUBLE TRIANGLE +23ED..23EF;N # So [3] BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR +23F0;W # So ALARM CLOCK +23F1..23F2;N # So [2] STOPWATCH..TIMER CLOCK +23F3;W # So HOURGLASS WITH FLOWING SAND +23F4..23FF;N # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL 2400..2426;N # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A;N # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B;A # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP @@ -1142,7 +1165,9 @@ 25E6..25EE;N # So [9] WHITE BULLET..UP-POINTING TRIANGLE WITH RIGHT HALF BLACK 25EF;A # So LARGE CIRCLE 25F0..25F7;N # So [8] WHITE SQUARE WITH UPPER LEFT QUADRANT..WHITE CIRCLE WITH UPPER RIGHT QUADRANT -25F8..25FF;N # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE +25F8..25FC;N # Sm [5] UPPER LEFT TRIANGLE..BLACK MEDIUM SQUARE +25FD..25FE;W # Sm [2] WHITE MEDIUM SMALL SQUARE..BLACK MEDIUM SMALL SQUARE +25FF;N # Sm LOWER RIGHT TRIANGLE 2600..2604;N # So [5] BLACK SUN WITH RAYS..COMET 2605..2606;A # So [2] BLACK STAR..WHITE STAR 2607..2608;N # So [2] LIGHTNING..THUNDERSTORM @@ -1150,7 +1175,7 @@ 260A..260D;N # So [4] ASCENDING NODE..OPPOSITION 260E..260F;A # So [2] BLACK TELEPHONE..WHITE TELEPHONE 2610..2613;N # So [4] BALLOT BOX..SALTIRE -2614..2615;A # So [2] UMBRELLA WITH RAIN DROPS..HOT BEVERAGE +2614..2615;W # So [2] UMBRELLA WITH RAIN DROPS..HOT BEVERAGE 2616..261B;N # So [6] WHITE SHOGI PIECE..BLACK RIGHT POINTING INDEX 261C;A # So WHITE LEFT POINTING INDEX 261D;N # So WHITE UP POINTING INDEX @@ -1159,7 +1184,9 @@ 2640;A # So FEMALE SIGN 2641;N # So EARTH 2642;A # So MALE SIGN -2643..265F;N # So [29] JUPITER..BLACK CHESS PAWN +2643..2647;N # So [5] JUPITER..PLUTO +2648..2653;W # So [12] ARIES..PISCES +2654..265F;N # So [12] WHITE CHESS KING..BLACK CHESS PAWN 2660..2661;A # So [2] BLACK SPADE SUIT..WHITE HEART SUIT 2662;N # So WHITE DIAMOND SUIT 2663..2665;A # So [3] BLACK CLUB SUIT..BLACK HEART SUIT @@ -1169,22 +1196,56 @@ 266C..266D;A # So [2] BEAMED SIXTEENTH NOTES..MUSIC FLAT SIGN 266E;N # So MUSIC NATURAL SIGN 266F;A # Sm MUSIC SHARP SIGN -2670..269D;N # So [46] WEST SYRIAC CROSS..OUTLINED WHITE STAR +2670..267E;N # So [15] WEST SYRIAC CROSS..PERMANENT PAPER SIGN +267F;W # So WHEELCHAIR SYMBOL +2680..2692;N # So [19] DIE FACE-1..HAMMER AND PICK +2693;W # So ANCHOR +2694..269D;N # So [10] CROSSED SWORDS..OUTLINED WHITE STAR 269E..269F;A # So [2] THREE LINES CONVERGING RIGHT..THREE LINES CONVERGING LEFT -26A0..26BD;N # So [30] WARNING SIGN..SOCCER BALL -26BE..26BF;A # So [2] BASEBALL..SQUARED KEY +26A0;N # So WARNING SIGN +26A1;W # So HIGH VOLTAGE SIGN +26A2..26A9;N # So [8] DOUBLED FEMALE SIGN..HORIZONTAL MALE WITH STROKE SIGN +26AA..26AB;W # So [2] MEDIUM WHITE CIRCLE..MEDIUM BLACK CIRCLE +26AC..26BC;N # So [17] MEDIUM SMALL WHITE CIRCLE..SESQUIQUADRATE +26BD..26BE;W # So [2] SOCCER BALL..BASEBALL +26BF;A # So SQUARED KEY 26C0..26C3;N # So [4] WHITE DRAUGHTS MAN..BLACK DRAUGHTS KING -26C4..26CD;A # So [10] SNOWMAN WITHOUT SNOW..DISABLED CAR -26CE;N # So OPHIUCHUS -26CF..26E1;A # So [19] PICK..RESTRICTED LEFT ENTRY-2 +26C4..26C5;W # So [2] SNOWMAN WITHOUT SNOW..SUN BEHIND CLOUD +26C6..26CD;A # So [8] RAIN..DISABLED CAR +26CE;W # So OPHIUCHUS +26CF..26D3;A # So [5] PICK..CHAINS +26D4;W # So NO ENTRY +26D5..26E1;A # So [13] ALTERNATE ONE-WAY LEFT WAY TRAFFIC..RESTRICTED LEFT ENTRY-2 26E2;N # So ASTRONOMICAL SYMBOL FOR URANUS 26E3;A # So HEAVY CIRCLE WITH STROKE AND TWO DOTS ABOVE 26E4..26E7;N # So [4] PENTAGRAM..INVERTED PENTAGRAM -26E8..26FF;A # So [24] BLACK CROSS ON SHIELD..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE -2700..273C;N # So [61] BLACK SAFETY SCISSORS..OPEN CENTRE TEARDROP-SPOKED ASTERISK +26E8..26E9;A # So [2] BLACK CROSS ON SHIELD..SHINTO SHRINE +26EA;W # So CHURCH +26EB..26F1;A # So [7] CASTLE..UMBRELLA ON GROUND +26F2..26F3;W # So [2] FOUNTAIN..FLAG IN HOLE +26F4;A # So FERRY +26F5;W # So SAILBOAT +26F6..26F9;A # So [4] SQUARE FOUR CORNERS..PERSON WITH BALL +26FA;W # So TENT +26FB..26FC;A # So [2] JAPANESE BANK SYMBOL..HEADSTONE GRAVEYARD SYMBOL +26FD;W # So FUEL PUMP +26FE..26FF;A # So [2] CUP ON BLACK SQUARE..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE +2700..2704;N # So [5] BLACK SAFETY SCISSORS..WHITE SCISSORS +2705;W # So WHITE HEAVY CHECK MARK +2706..2709;N # So [4] TELEPHONE LOCATION SIGN..ENVELOPE +270A..270B;W # So [2] RAISED FIST..RAISED HAND +270C..2727;N # So [28] VICTORY HAND..WHITE FOUR POINTED STAR +2728;W # So SPARKLES +2729..273C;N # So [20] STRESS OUTLINED WHITE STAR..OPEN CENTRE TEARDROP-SPOKED ASTERISK 273D;A # So HEAVY TEARDROP-SPOKED ASTERISK -273E..2756;N # So [25] SIX PETALLED BLACK AND WHITE FLORETTE..BLACK DIAMOND MINUS WHITE X -2757;A # So HEAVY EXCLAMATION MARK SYMBOL +273E..274B;N # So [14] SIX PETALLED BLACK AND WHITE FLORETTE..HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK +274C;W # So CROSS MARK +274D;N # So SHADOWED WHITE CIRCLE +274E;W # So NEGATIVE SQUARED CROSS MARK +274F..2752;N # So [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE +2753..2755;W # So [3] BLACK QUESTION MARK ORNAMENT..WHITE EXCLAMATION MARK ORNAMENT +2756;N # So BLACK DIAMOND MINUS WHITE X +2757;W # So HEAVY EXCLAMATION MARK SYMBOL 2758..2767;N # So [16] LIGHT VERTICAL BAR..ROTATED FLORAL HEART BULLET 2768;N # Ps MEDIUM LEFT PARENTHESIS ORNAMENT 2769;N # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT @@ -1202,7 +1263,12 @@ 2775;N # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT 2776..277F;A # No [10] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED NUMBER TEN 2780..2793;N # No [20] DINGBAT CIRCLED SANS-SERIF DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN -2794..27BF;N # So [44] HEAVY WIDE-HEADED RIGHTWARDS ARROW..DOUBLE CURLY LOOP +2794;N # So HEAVY WIDE-HEADED RIGHTWARDS ARROW +2795..2797;W # So [3] HEAVY PLUS SIGN..HEAVY DIVISION SIGN +2798..27AF;N # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW +27B0;W # So CURLY LOOP +27B1..27BE;N # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW +27BF;W # So DOUBLE CURLY LOOP 27C0..27C4;N # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET 27C5;N # Ps LEFT S-SHAPED BAG DELIMITER 27C6;N # Pe RIGHT S-SHAPED BAG DELIMITER @@ -1253,17 +1319,22 @@ 29FD;N # Pe RIGHT-POINTING CURVED ANGLE BRACKET 29FE..29FF;N # Sm [2] TINY..MINY 2A00..2AFF;N # Sm [256] N-ARY CIRCLED DOT OPERATOR..N-ARY WHITE VERTICAL BAR -2B00..2B2F;N # So [48] NORTH EAST WHITE ARROW..WHITE VERTICAL ELLIPSE +2B00..2B1A;N # So [27] NORTH EAST WHITE ARROW..DOTTED SQUARE +2B1B..2B1C;W # So [2] BLACK LARGE SQUARE..WHITE LARGE SQUARE +2B1D..2B2F;N # So [19] BLACK VERY SMALL SQUARE..WHITE VERTICAL ELLIPSE 2B30..2B44;N # Sm [21] LEFT ARROW WITH SMALL CIRCLE..RIGHTWARDS ARROW THROUGH SUPERSET 2B45..2B46;N # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C;N # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR -2B4D..2B54;N # So [8] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..WHITE RIGHT-POINTING PENTAGON -2B55..2B59;A # So [5] HEAVY LARGE CIRCLE..HEAVY CIRCLED SALTIRE +2B4D..2B4F;N # So [3] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..SHORT BACKSLANTED SOUTH ARROW +2B50;W # So WHITE MEDIUM STAR +2B51..2B54;N # So [4] BLACK SMALL STAR..WHITE RIGHT-POINTING PENTAGON +2B55;W # So HEAVY LARGE CIRCLE +2B56..2B59;A # So [4] HEAVY OVAL WITH OVAL INSIDE..HEAVY CIRCLED SALTIRE 2B5A..2B73;N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95;N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9;N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8;N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1;N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2;N # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF;N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E;N # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E;N # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1332,6 +1403,7 @@ 2E40;N # Pd DOUBLE HYPHEN 2E41;N # Po REVERSED COMMA 2E42;N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49;N # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99;W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3;W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5;W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1387,7 +1459,7 @@ 30FB;W # Po KATAKANA MIDDLE DOT 30FC..30FE;W # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF;W # Lo KATAKANA DIGRAPH KOTO -3105..312D;W # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E;W # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E;W # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191;W # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195;W # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1410,8 +1482,8 @@ 3400..4DB5;W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;W # Cn [10] <reserved-4DB6>..<reserved-4DBF> 4DC0..4DFF;N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5;W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF;W # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA;W # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF;W # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014;W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015;W # Lm YI SYLLABLE WU A016..A48C;W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1450,7 +1522,7 @@ A788;N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A;N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E;N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F;N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD;N # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE;N # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7;N # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7;N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9;N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1476,7 +1548,7 @@ A874..A877;N # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SH A880..A881;N # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3;N # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3;N # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4;N # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5;N # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8CE..A8CF;N # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A8D0..A8D9;N # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8E0..A8F1;N # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA @@ -1726,7 +1798,7 @@ FFFD;A # So REPLACEMENT CHARACTER 10175..10178;N # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189;N # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B;N # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C;N # So GREEK SINUSOID SIGN +1018C..1018E;N # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B;N # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0;N # So GREEK SYMBOL TAU RHO 101D0..101FC;N # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -1737,6 +1809,7 @@ FFFD;A # So REPLACEMENT CHARACTER 102E1..102FB;N # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F;N # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323;N # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F;N # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE 10330..10340;N # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA 10341;N # Nl GOTHIC LETTER NINETY 10342..10349;N # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL @@ -1753,6 +1826,8 @@ FFFD;A # So REPLACEMENT CHARACTER 10450..1047F;N # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW 10480..1049D;N # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO 104A0..104A9;N # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3;N # Lu [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB;N # Ll [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527;N # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563;N # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F;N # Po CAUCASIAN ALBANIAN CITATION MARK @@ -1880,6 +1955,7 @@ FFFD;A # So REPLACEMENT CHARACTER 11235;N # Mc KHOJKI SIGN VIRAMA 11236..11237;N # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 11238..1123D;N # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN +1123E;N # Mn KHOJKI SIGN SUKUN 11280..11286;N # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288;N # Lo MULTANI LETTER GHA 1128A..1128D;N # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1912,6 +1988,18 @@ FFFD;A # So REPLACEMENT CHARACTER 11362..11363;N # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C;N # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374;N # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434;N # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437;N # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F;N # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441;N # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444;N # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445;N # Mc NEWA SIGN VISARGA +11446;N # Mn NEWA SIGN NUKTA +11447..1144A;N # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F;N # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459;N # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B;N # Po NEWA PLACEHOLDER MARK +1145D;N # Po NEWA INSERTION SIGN 11480..114AF;N # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2;N # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8;N # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -1945,6 +2033,7 @@ FFFD;A # So REPLACEMENT CHARACTER 11641..11643;N # Po [3] MODI DANDA..MODI ABBREVIATION SIGN 11644;N # Lo MODI SIGN HUVA 11650..11659;N # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C;N # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11680..116AA;N # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116AB;N # Mn TAKRI SIGN ANUSVARA 116AC;N # Mc TAKRI SIGN VISARGA @@ -1968,7 +2057,59 @@ FFFD;A # So REPLACEMENT CHARACTER 118E0..118E9;N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2;N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF;N # Lo WARANG CITI OM +11A00;N # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06;N # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08;N # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A;N # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32;N # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38;N # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39;N # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A;N # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E;N # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46;N # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47;N # Mn ZANABAZAR SQUARE SUBJOINER +11A50;N # Lo SOYOMBO LETTER A +11A51..11A56;N # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58;N # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B;N # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83;N # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89;N # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96;N # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97;N # Mc SOYOMBO SIGN VISARGA +11A98..11A99;N # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C;N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2;N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8;N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08;N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E;N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F;N # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36;N # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D;N # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E;N # Mc BHAIKSUKI SIGN VISARGA +11C3F;N # Mn BHAIKSUKI SIGN VIRAMA +11C40;N # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45;N # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59;N # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C;N # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71;N # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F;N # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7;N # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9;N # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0;N # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1;N # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3;N # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4;N # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6;N # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06;N # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09;N # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30;N # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36;N # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A;N # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D;N # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45;N # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46;N # Lo MASARAM GONDI REPHA +11D47;N # Mn MASARAM GONDI RA-KARA +11D50..11D59;N # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399;N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E;N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474;N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -1998,7 +2139,12 @@ FFFD;A # So REPLACEMENT CHARACTER 16F51..16F7E;N # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92;N # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F;N # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001;W # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1;W # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC;W # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2;W # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B0FF;W # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 +1B100..1B11E;W # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB;W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A;N # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C;N # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88;N # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2079,9 +2225,18 @@ FFFD;A # So REPLACEMENT CHARACTER 1DA87..1DA8B;N # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1DA9B..1DA9F;N # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF;N # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006;N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018;N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021;N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024;N # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A;N # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4;N # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF;N # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6;N # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943;N # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A;N # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959;N # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F;N # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK 1EE00..1EE03;N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F;N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22;N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -2116,11 +2271,14 @@ FFFD;A # So REPLACEMENT CHARACTER 1EEA5..1EEA9;N # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB;N # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1;N # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -1F000..1F02B;N # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK +1F000..1F003;N # So [4] MAHJONG TILE EAST WIND..MAHJONG TILE NORTH WIND +1F004;W # So MAHJONG TILE RED DRAGON +1F005..1F02B;N # So [39] MAHJONG TILE GREEN DRAGON..MAHJONG TILE BACK 1F030..1F093;N # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 1F0A0..1F0AE;N # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES 1F0B1..1F0BF;N # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER -1F0C1..1F0CF;N # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER +1F0C1..1F0CE;N # So [14] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD KING OF DIAMONDS +1F0CF;W # So PLAYING CARD BLACK JOKER 1F0D1..1F0F5;N # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F100..1F10A;A # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA 1F10B..1F10C;N # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO @@ -2128,22 +2286,66 @@ FFFD;A # So REPLACEMENT CHARACTER 1F12E;N # So CIRCLED WZ 1F130..1F169;A # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F16A..1F16B;N # So [2] RAISED MC SIGN..RAISED MD SIGN -1F170..1F19A;A # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F18D;A # So [30] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED SA +1F18E;W # So NEGATIVE SQUARED AB +1F18F..1F190;A # So [2] NEGATIVE SQUARED WC..SQUARE DJ +1F191..1F19A;W # So [10] SQUARED CL..SQUARED VS +1F19B..1F1AC;A # So [18] SQUARED THREE D..SQUARED VOD 1F1E6..1F1FF;N # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z 1F200..1F202;W # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A;W # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B;W # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248;W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251;W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -1F300..1F3FA;N # So [251] CYCLONE..AMPHORA -1F3FB..1F3FF;N # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579;N # So [378] RAT..JOYSTICK -1F57B..1F5A3;N # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F5FF;N # So [91] DESKTOP COMPUTER..MOYAI -1F600..1F64F;N # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS +1F260..1F265;W # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F300..1F320;W # So [33] CYCLONE..SHOOTING STAR +1F321..1F32C;N # So [12] THERMOMETER..WIND BLOWING FACE +1F32D..1F335;W # So [9] HOT DOG..CACTUS +1F336;N # So HOT PEPPER +1F337..1F37C;W # So [70] TULIP..BABY BOTTLE +1F37D;N # So FORK AND KNIFE WITH PLATE +1F37E..1F393;W # So [22] BOTTLE WITH POPPING CORK..GRADUATION CAP +1F394..1F39F;N # So [12] HEART WITH TIP ON THE LEFT..ADMISSION TICKETS +1F3A0..1F3CA;W # So [43] CAROUSEL HORSE..SWIMMER +1F3CB..1F3CE;N # So [4] WEIGHT LIFTER..RACING CAR +1F3CF..1F3D3;W # So [5] CRICKET BAT AND BALL..TABLE TENNIS PADDLE AND BALL +1F3D4..1F3DF;N # So [12] SNOW CAPPED MOUNTAIN..STADIUM +1F3E0..1F3F0;W # So [17] HOUSE BUILDING..EUROPEAN CASTLE +1F3F1..1F3F3;N # So [3] WHITE PENNANT..WAVING WHITE FLAG +1F3F4;W # So WAVING BLACK FLAG +1F3F5..1F3F7;N # So [3] ROSETTE..LABEL +1F3F8..1F3FA;W # So [3] BADMINTON RACQUET AND SHUTTLECOCK..AMPHORA +1F3FB..1F3FF;W # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 +1F400..1F43E;W # So [63] RAT..PAW PRINTS +1F43F;N # So CHIPMUNK +1F440;W # So EYES +1F441;N # So EYE +1F442..1F4FC;W # So [187] EAR..VIDEOCASSETTE +1F4FD..1F4FE;N # So [2] FILM PROJECTOR..PORTABLE STEREO +1F4FF..1F53D;W # So [63] PRAYER BEADS..DOWN-POINTING SMALL RED TRIANGLE +1F53E..1F54A;N # So [13] LOWER RIGHT SHADOWED WHITE CIRCLE..DOVE OF PEACE +1F54B..1F54E;W # So [4] KAABA..MENORAH WITH NINE BRANCHES +1F54F;N # So BOWL OF HYGIEIA +1F550..1F567;W # So [24] CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY +1F568..1F579;N # So [18] RIGHT SPEAKER..JOYSTICK +1F57A;W # So MAN DANCING +1F57B..1F594;N # So [26] LEFT HAND TELEPHONE RECEIVER..REVERSED VICTORY HAND +1F595..1F596;W # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F597..1F5A3;N # So [13] WHITE DOWN POINTING LEFT HAND INDEX..BLACK DOWN POINTING BACKHAND INDEX +1F5A4;W # So BLACK HEART +1F5A5..1F5FA;N # So [86] DESKTOP COMPUTER..WORLD MAP +1F5FB..1F5FF;W # So [5] MOUNT FUJI..MOYAI +1F600..1F64F;W # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS 1F650..1F67F;N # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD -1F680..1F6D0;N # So [81] ROCKET..PLACE OF WORSHIP -1F6E0..1F6EC;N # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F680..1F6C5;W # So [70] ROCKET..LEFT LUGGAGE +1F6C6..1F6CB;N # So [6] TRIANGLE WITH ROUNDED CORNERS..COUCH AND LAMP +1F6CC;W # So SLEEPING ACCOMMODATION +1F6CD..1F6CF;N # So [3] SHOPPING BAGS..BED +1F6D0..1F6D2;W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY +1F6D3..1F6D4;N # So [2] STUPA..PAGODA +1F6E0..1F6EA;N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE +1F6EB..1F6EC;W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING 1F6F0..1F6F3;N # So [4] SATELLITE..PASSENGER SHIP +1F6F4..1F6F8;W # So [5] SCOOTER..FLYING SAUCER 1F700..1F773;N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4;N # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B;N # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -2151,9 +2353,13 @@ FFFD;A # So REPLACEMENT CHARACTER 1F850..1F859;N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887;N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD;N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918;N # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984;N # So [5] CRAB..UNICORN FACE -1F9C0;N # So CHEESE WEDGE +1F900..1F90B;N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E;W # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C;W # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B;W # So [28] CROISSANT..CANNED FOOD +1F980..1F997;W # So [24] CRAB..CRICKET +1F9C0;W # So CHEESE WEDGE +1F9D0..1F9E6;W # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6;W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF;W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734;W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -2161,7 +2367,9 @@ FFFD;A # So REPLACEMENT CHARACTER 2B740..2B81D;W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;W # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1;W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF;W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF;W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0;W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF;W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D;W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD;W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD;W # Cn [65534] <reserved-30000>..<reserved-3FFFD> diff --git a/gnu/usr.bin/perl/lib/unicore/EmojiSources.txt b/gnu/usr.bin/perl/lib/unicore/EmojiSources.txt index f6185d495cf..228665b52b5 100644 --- a/gnu/usr.bin/perl/lib/unicore/EmojiSources.txt +++ b/gnu/usr.bin/perl/lib/unicore/EmojiSources.txt @@ -1,25 +1,22 @@ -# EmojiSources-8.0.0.txt -# Date: 2015-01-20, 02:00:00 GMT [MS, KW] +# EmojiSources-10.0.0.txt +# Date: 2017-02-04, 00:00:00 GMT [MS, KW] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see http://www.unicode.org/reports/tr44/ # -# This file provides mappings between Unicode code points and sequences on one hand +# This file provides historical mappings between Unicode code points and sequences on one hand # and Shift-JIS codes for cell phone carrier symbols on the other hand. # Each mapping is symmetric ("round trip"), for equivalent Unicode and carrier # symbols or sequences. This file does not include best-fit ("fallback") # mappings to similar but not equivalent symbols in either mapping direction. # -# Note: It is possible that future versions of this file will include -# additional data columns providing mappings for additional vendors. -# # Created for Unicode 6.0 by Markus Scherer. # Updated for subsequent versions by Ken Whistler (no changes to mappings). # # Format: Semicolon-delimited file with a fixed number of fields. -# The number of fields may increase in the future. +# Note that the format, including the number of fields, may change in the future. # # Fields: # 0: Unicode code point or sequence @@ -30,6 +27,15 @@ # Each field 1..3 contains a code if and only if the vendor character set # has a symbol which is equivalent to the Unicode character or sequence. +# ================================================ + +# Keycap sequences for telephone keypad. +# The following 11 mappings are historical. The combining character sequences +# in these mappings do not include variation selectors for emoji presentation. +# Thus they do not match the named character sequences with keycaps listed in +# NamedSequences.txt. +# For modern data used in emoji support, see http://www.unicode.org/Public/emoji/latest/ + 0023 20E3;F985;F489;F7B0 0030 20E3;F990;F7C9;F7C5 0031 20E3;F987;F6FB;F7BC @@ -41,6 +47,7 @@ 0037 20E3;F98D;F744;F7C2 0038 20E3;F98E;F745;F7C3 0039 20E3;F98F;F746;F7C4 + 00A9;F9D6;F774;F7EE 00AE;F9DB;F775;F7EF 2002;;F7AA; diff --git a/gnu/usr.bin/perl/lib/unicore/HangulSyllableType.txt b/gnu/usr.bin/perl/lib/unicore/HangulSyllableType.txt index e30a82b82d7..9c990d7abae 100644 --- a/gnu/usr.bin/perl/lib/unicore/HangulSyllableType.txt +++ b/gnu/usr.bin/perl/lib/unicore/HangulSyllableType.txt @@ -1,10 +1,11 @@ -# HangulSyllableType-8.0.0.txt -# Date: 2014-12-16, 23:07:45 GMT [MD] +# HangulSyllableType-10.0.0.txt +# Date: 2017-02-14, 04:26:11 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2014 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/Index.txt b/gnu/usr.bin/perl/lib/unicore/Index.txt index 196a1e0acf4..d9277822e32 100644 --- a/gnu/usr.bin/perl/lib/unicore/Index.txt +++ b/gnu/usr.bin/perl/lib/unicore/Index.txt @@ -118,6 +118,7 @@ ACUTE TONE MARK, COMBINING 0341 ADDAK, GURMUKHI 0A71 ADDRESSED TO THE SUBJECT 2101 ADI SHAKTI 262C +Adlam 1E900 AE, LATIN CAPITAL LETTER 00C6 ae, latin capital ligature 00C6 AE, LATIN LETTER SMALL CAPITAL 1D01 @@ -165,6 +166,7 @@ AMPERSAND, TURNED 214B Anatolian Hieroglyphs 14400 ANCHOR 2693 ANCHOR, INTERLINEAR ANNOTATION FFF9 +Ancient Greek Textual Symbols 2E0E AND, CURLY LOGICAL 22CF AND, LOGICAL 2227 AND, N-ARY LOGICAL 22C0 @@ -202,6 +204,7 @@ Angles and Measured Angles 299B ANGSTROM SIGN 212B Animal Faces 1F42D Animal Symbols 1F400 +Animal Symbols 1F980 ANKH 2625 ANNOTATION ANCHOR, INTERLINEAR FFF9 ANNOTATION SEPARATOR, INTERLINEAR FFFA @@ -447,7 +450,9 @@ barred o, latin capital letter 019F BARRED O, LATIN SMALL LETTER 0275 base 22A5 BASEBALL 26BE +Basic Musical Symbols 2669 Bassa Vah 16AD0 +BAT 1F987 Batak 1BC0 batsaganchakan nshan, armenian 055C BATTERY 1F50B @@ -527,6 +532,7 @@ beta, curled 03D0 BETWEEN 226C Beverage Symbols 1F375 BEVERAGE, HOT 2615 +Bhaiksuki 11C00 Bidirectional Format Characters 202A Big 5, Duplicate Characters from FA0C BIG REVERSE SOLIDUS 29F9 @@ -539,9 +545,11 @@ BIOHAZARD SIGN 2623 BIRD 1F426 BIRGA, MONGOLIAN 1800 BISMILLAH AR-RAHMAN AR-RAHEEM, ARABIC LIGATURE FDFD +BITCOIN SIGN 20BF BLACK CIRCLE 25CF BLACK CIRCLE, MEDIUM 26AB BLACK FLAG 2691 +BLACK HEART 1F5A4 BLACK HOURGLASS 29D7 BLACK LEFT POINTING INDEX 261A BLACK LEFTWARDS BULLET 204C @@ -689,6 +697,7 @@ BRIDGE BELOW, COMBINING INVERTED 033A briffits 1F4A8 BROKEN BAR 00A6 broken vertical bar 00A6 +bronze medal 1F949 Bubble Symbols, Speech and Thought 1F5E8 Bud Ornaments, Pointing 1F660 BUG 1F41B @@ -710,6 +719,7 @@ bullseye 1F78B bullseye, latin letter 0298 buried symbol 26B0 Burmese 1000 +BUTTERFLY 1F98B by definition, equal to 225C BY DEFINITION, EQUAL TO 225D BY, MEASURED 225E @@ -736,6 +746,7 @@ C0 Control Codes, ASCII 0000 C1 Control Codes 0080 CADA UNA 2106 CADUCEUS 2624 +CALL ME HAND 1F919 Cambodian 1780 CAMEL, BACTRIAN 1F42B CAMEL, DROMEDARY 1F42A @@ -846,6 +857,7 @@ Chinese Bopomofo 3100 Chinese Bopomofo Extensions 31A0 chinese fifth or neutral tone, mandarin 02D9 chinese first tone, mandarin 02C9 +Chinese Folk Religion Symbols 1F260 chinese fourth tone, mandarin 02CB chinese second tone, mandarin 02CA chinese third tone, mandarin 02C7 @@ -931,6 +943,7 @@ CJK Unified Ideographs Extension B 20000 CJK Unified Ideographs Extension C 2A700 CJK Unified Ideographs Extension D 2B740 CJK Unified Ideographs Extension E 2B820 +CJK Unified Ideographs Extension F 2CEB0 CLAPPING HANDS SIGN 1F44F claudian antisigma 2183 claudian digamma inversum 2132 @@ -1271,6 +1284,7 @@ CROSS, ORTHODOX 2626 cross, st. andrew's 2613 CROSS, WEST SYRIAC 2670 CROSS, WHITE LATIN 1F546 +crossed fingers 1F91E CROSSED SWORDS 2694 Crosses 2719 Crosses, Greek 1F7A1 @@ -1346,6 +1360,7 @@ Cyrillic Capital Letters 0400 Cyrillic Combining Characters 0483 Cyrillic Extended-A 2DE0 Cyrillic Extended-B A640 +Cyrillic Extended-C 1C80 Cyrillic Extensions 0450 Cyrillic Extensions 048A Cyrillic Historic Letters 0460 @@ -1453,6 +1468,7 @@ Device Controls 0011 Device Controls, Symbols for 2411 DHARMA, WHEEL OF 2638 diacritic, finite function 20E6 +Diacritical Marks for Symbols 20D0 Diacritical Marks for Symbols, Combining 20D0 Diacritical Marks, Combining 0300 Diacritics for Greek 0342 @@ -1779,6 +1795,7 @@ E, LATIN SMALL LETTER TURNED 01DD E, LATIN SMALL LETTER TURNED OPEN 1D08 E, SCRIPT CAPITAL 2130 E, SCRIPT SMALL 212F +EAGLE 1F985 EAR 1F442 EARTH 2641 EARTH GROUND 23DA @@ -1991,11 +2008,13 @@ f, latin small letter script 0192 F, SCRIPT CAPITAL 2131 F, TURNED CAPITAL 2132 F, TURNED SMALL 214E +FACE PALM 1F926 FACE, BLACK SMILING 263B FACE, POSTAL MARK 3020 FACE, WHITE FROWNING 2639 FACE, WHITE SMILING 263A Faces 1F600 +Faces 1F920 Facial Parts Symbols 1F440 FACSIMILE SIGN 213B factorial 0021 @@ -2030,6 +2049,7 @@ FILL SPACE, IDEOGRAPHIC HALF 303F FILLER, HANGUL 3164 FILM FRAMES 1F39E Finger Dingbats, Pointing Index 261A +fingers crossed 1F91E finite function 21FB finite function diacritic 20E6 finite injection 2915 @@ -2061,10 +2081,12 @@ FLOOR, RIGHT 230B FLOPPY DISK 1F4BE FLORAL HEART BULLET, REVERSED ROTATED 2619 florin currency symbol 0192 +FLYING SAUCER 1F6F8 folder 0192 FONGMAN, THAI CHARACTER 0E4F food available symbol 1F37D Food Symbols 1F354 +Food Symbols 1F950 FOOTPRINTS 1F463 FOR ALL 2200 FORCES 22A9 @@ -2208,6 +2230,7 @@ GHOST 1F47B GIMEL SYMBOL 2137 GIRL 1F467 Glagolitic 2C00 +Glagolitic Supplement 1E000 GLEICH STARK 29E6 Globe Symbols 1F30D GLOBE WITH MERIDIANS 1F310 @@ -2224,6 +2247,7 @@ gnaborretni 2E18 Go Markers 2686 GOAT 1F410 GOBLIN, JAPANESE 1F47A +gold medal 1F947 Golden Numbers, Runic 16EE golf course 26F3 Gothic 10330 @@ -2383,11 +2407,14 @@ han-daku-on, combining japanese 309A han-daku-on, japanese 309C Hand Symbols 1F446 Hand Symbols 1F58E +Hand Symbols 1F918 Hand Symbols, Pointing 261A Hand, Index Finger Pointing 1F446 HAND, RAISED 270B +HAND, RAISED BACK OF 1F91A HAND, VICTORY 270C HAND, WRITING 270D +HANDSHAKE 1F91D Hangul Archaic Letters, Korean 3165 HANGUL CHOSEONG FILLER 115F Hangul Compatibility Jamo, Korean 3130 @@ -2431,6 +2458,7 @@ HEART BULLET, REVERSED ROTATED FLORAL 2619 Heart Dingbats 2763 Heart Ornaments 2763 Heart Symbols 1F493 +HEART, BLACK 1F5A4 HEAVY BALLOT X 2718 HEAVY CHECK MARK 2714 HEAVY EXCLAMATION MARK ORNAMENT 2762 @@ -2446,6 +2474,8 @@ hedera 2767 HEH WITH YEH ABOVE, ARABIC LETTER 06C0 HELM SYMBOL 2388 HELMET WITH WHITE CROSS 26D1 +Hentaigana 1B002 +Hentaigana 1B100 HERMES, STAFF OF 269A HERMITIAN CONJUGATE MATRIX 22B9 Hexagram Symbols, Yijing / I Ching 4DC0 @@ -2521,6 +2551,7 @@ I Ching / Yijing Hexagram Symbols 4DC0 I Ching / Yijing Monogram and Digram Symbols 268A I Ching / Yijing Trigram Symbols 2630 i dot, latin capital letter 0130 +I LOVE YOU HAND SIGN 1F91F I WITH ACUTE, LATIN CAPITAL LETTER 00CD I WITH ACUTE, LATIN SMALL LETTER 00ED I WITH BREVE, LATIN SMALL LETTER 012D @@ -2568,6 +2599,7 @@ IDEOGRAPHIC ITERATION MARK, VERTICAL 303B IDEOGRAPHIC NUMBER ZERO 3007 IDEOGRAPHIC SPACE 3000 Ideographic Supplement, Enclosed 1F200 +Ideographic Symbols and Punctuation 16FE0 Ideographic Telegraph Symbols for Days 33E0 Ideographic Telegraph Symbols for Hours 3358 Ideographic Telegraph Symbols for Months 32C0 @@ -2783,6 +2815,7 @@ K, LATIN SUBSCRIPT SMALL LETTER 2096 KA, HIRAGANA LETTER SMALL 3095 kabusiki-gaisya 337F Kaithi 11080 +Kana Extended-A 1B100 Kana Repeat Marks 3031 Kana Supplement 1B000 Kanbun Ideographic Annotation, Japanese 3190 @@ -3189,6 +3222,7 @@ LOOP, CURLY 27B0 LOOP, DOUBLE CURLY 27BF LORRAINE, CROSS OF 2628 lorry, black 26DF +love, hand sign 1F91F LOW ACUTE ACCENT, MODIFIER LETTER 02CF LOW ASTERISK 204E low double comma quotation mark 201E @@ -3283,6 +3317,7 @@ maps from 2906 maps to 27FC maps to 2905 maps to 2907 +Marchen 11C70 marina or yacht harbour 26F4 mark pre-wwii, german 2133 marker, histogram 25AE @@ -3294,6 +3329,7 @@ marque de commerce 1F16A marque deposee 1F16B MARRIAGE SYMBOL 26AD mars 2642 +Masaram Gondi 11D00 MASCULINE ORDINAL INDICATOR 00BA masks of comedy and tragedy 1F3AD MASU MARK 303C @@ -3403,6 +3439,8 @@ MINUS, SQUARED 229F MINUS-OR-PLUS SIGN 2213 minutes 2032 MINY 29FF +Miscellaneous Symbols 2600 +Miscellaneous Symbols 1F940 Mkhedruli, Georgian 10D0 mmsp 205F Modal Logic Operators 27E0 @@ -3436,6 +3474,7 @@ MONGOLIAN MANCHU FULL STOP 1809 MONGOLIAN NIRUGU 180A Mongolian Punctuation 1800 MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER 1807 +Mongolian Supplement 11660 MONGOLIAN TODO SOFT HYPHEN 1806 MONGOLIAN VOWEL SEPARATOR 180E MONKEY 1F412 @@ -3561,6 +3600,7 @@ New Tai Lue 1980 New Tai Lue Digits 19D0 New Testament Editorial Symbols 2E00 new testament majority text 1D510 +Newa 11400 NEWLINE, SYMBOL FOR 2424 NEXT LINE 0085 NEXT PAGE 2398 @@ -3656,6 +3696,7 @@ NUMERATOR ONE, FRACTION 215F Numeric Symbols for Divination, Khmer 17F0 numerics lock 21ED NUMERO SIGN 2116 +Nushu 1B170 nut 2002 o bar, latin capital letter 019F o bar, latin small letter 0275 @@ -3811,6 +3852,7 @@ ORNATE RIGHT PARENTHESIS FD3F Ors, Logical Ands and 2A51 ORTHODOX CROSS 2626 orthogonal to 22A5 +Osage 104B0 Osmanya 10480 Osmanya Digits 104A0 OU, LATIN LETTER SMALL CAPITAL 1D15 @@ -3858,6 +3900,7 @@ P, DOUBLE-STRUCK CAPITAL 2119 P, LATIN LETTER SMALL CAPITAL 1D18 P, LATIN SUBSCRIPT SMALL LETTER 209A P, SCRIPT CAPITAL 2118 +paella 1F958 page down 21DF page down 2B7D PAGE FACING UP 1F4C4 @@ -4007,6 +4050,7 @@ Planet Symbols 263F Plant Symbols 1F330 Plastics Recycling Symbols 2673 Playing Card Suits 2660 +Playing Card Symbols 2660 Playing Cards 1F0A0 plewds 1F4A6 Plus and Minus Sign Operators 2A22 @@ -4039,7 +4083,7 @@ Points, Hebrew 05B0 Points, Syriac 0730 poison 2620 POLICE OFFICER 1F46E -Political Symbols, Religious and 2625 +Political Symbols, Religious and 2626 Polygonal Symbols 2B12 Polytonic Greek, Precomposed 1F00 POO, PILE OF 1F4A9 @@ -4048,6 +4092,8 @@ POP DIRECTIONAL FORMATTING 202C POP DIRECTIONAL ISOLATE 2069 pork (on menus) 1F416 Portrait and Role Symbols 1F464 +Portrait and Role Symbols 1F930 +Portrait and Role Symbols 1F9D0 POSITION INDICATOR 2316 POSITION INDICATOR, SQUARE 2BD0 positive difference or sum 2A24 @@ -4062,6 +4108,7 @@ pound sign 0023 POUND SIGN 00A3 pound sterling 00A3 pounds 2114 +Power On/Off Symbols 23FB power plant 26EE power set 1D4AB Precedence Signs, Order Relation 227A @@ -4482,8 +4529,12 @@ rlo 202E RNAM BCAD, TIBETAN SIGN 0F7F road closed 26D2 rock in rock, paper, scissors game 270A +rofl 1F923 Role Symbols 1F481 Role Symbols, Portrait and 1F464 +Role Symbols, Portrait and 1F930 +Role Symbols, Portrait and 1F9D0 +ROLLING ON THE FLOOR LAUGHING 1F923 Roman Numerals 2160 Roman Numerals, Archaic 2185 Roman Symbols 10190 @@ -4602,6 +4653,7 @@ SELECTED AREA, END OF 0087 SELECTED AREA, START OF 0086 Selectors Supplement, Variation E0100 Selectors, Variation FE00 +SELFIE 1F933 semibreve 1D15D SEMICOLON 003B SEMICOLON, ARABIC 061B @@ -4682,6 +4734,7 @@ SHOGI PIECE, TURNED BLACK 26CA SHOGI PIECE, TURNED WHITE 26C9 SHOGI PIECE, WHITE 2616 SHOOTING STAR 1F320 +shopping cart 1F6D2 short 0306 short slash overlay 0337 SHORT SOLIDUS OVERLAY, COMBINING 0337 @@ -4707,6 +4760,7 @@ Signage and Other Symbols 1F6A9 Signs, Warning 2620 Signs, Warning 26A0 SignWriting, Sutton 1D800 +silver medal 1F948 similar to 223C SINE WAVE 223F SINGLE CHARACTER INTRODUCER 009A @@ -4816,6 +4870,7 @@ Sora Sompeng 110D0 sound 1F50A SOUND RECORDING COPYRIGHT 2117 SOURCE, INFORMATION 2139 +Soyombo 11A50 SPACE 0020 SPACE MARK, OGHAM 1680 SPACE, EM 2003 @@ -4931,6 +4986,7 @@ STENOGRAPHIC FULL STOP 2E3C sterling, pound 00A3 stile, apl 2223 stop play 23F9 +stop sign 1F6D1 STOPWATCH 23F1 straight epsilon 03F5 straight epsilon, reversed 03F6 @@ -5048,60 +5104,146 @@ Symbols for Days, Ideographic Telegraph 33E0 Symbols for Divination, Khmer Numeric 17F0 Symbols for Hours, Ideographic Telegraph 3358 Symbols for Months, Ideographic Telegraph 32C0 +Symbols, Alchemical 1F700 Symbols, Ancient Greek Textual 2E0E +Symbols, Animal 1F400 +Symbols, Animal 1F980 Symbols, APL Functional 2336 +Symbols, Arabic Mathematical Alphabetic 1EE00 +Symbols, Area, 2000 +Symbols, Area, CJK Phonetics and 2E80 Symbols, ASCII Punctuation and 0020 Symbols, Astrological 263D +Symbols, Audio and Video 1F4F7 Symbols, Balinese Musical 1B61 +Symbols, Ballot 1F5F3 Symbols, Basic Musical 2669 +Symbols, Beverage 1F375 +Symbols, Black-letter Mathematical 1D504 +Symbols, Bold Fraktur Mathematical 1D56C +Symbols, Bold Greek Mathematical 1D6A8 +Symbols, Bold Italic Greek Mathematical 1D71C +Symbols, Bold Italic Mathematical 1D468 +Symbols, Bold Mathematical 1D400 +Symbols, Bold Script Mathematical 1D4D0 Symbols, Bowtie 29D1 +Symbols, Building and Map 1F3D4 +Symbols, Building and Map 1F3E0 Symbols, Byzantine Musical 1D000 +Symbols, Celebration 1F380 Symbols, Chess 2654 Symbols, Circle 29B5 +Symbols, Clock Face 1F550 Symbols, Combining Diacritical Marks for 20D0 +Symbols, Comic Style 1F4A0 +Symbols, Communication 1F4DD +Symbols, Communication 1F57B +Symbols, Computer Component 1F5A5 +Symbols, Cultural 1F5FB Symbols, Currency 20A0 Symbols, Dentistry Notation 23BE Symbols, Diacritical Marks for 20D0 Symbols, Dictionary and Map 2690 +Symbols, Dotless Mathematical 1D6A4 +Symbols, Double-struck Italic Mathematical 2145 +Symbols, Double-struck Mathematical 1D538 Symbols, Drafting 232D Symbols, Electrotechnical 238D +Symbols, Entertainment 1F3A0 Symbols, Error Bar 29EE +Symbols, Facial Parts 1F440 +Symbols, Fairy Tale 1F478 +Symbols, Food 1F354 +Symbols, Food 1F950 +Symbols, Fraktur Mathematical 1D504 +Symbols, Fruit and Vegetable 1F345 +Symbols, Game 1F3AE Symbols, Gender 26A2 Symbols, Genealogical 26AD +Symbols, Gesture 1F645 +Symbols, Globe 1F30D Symbols, Greek Mathematical 1D6A8 +Symbols, Gregorian Musical 1D1D0 +Symbols, Hand 1F446 +Symbols, Hand 1F58E +Symbols, Hand 1F918 +Symbols, Heart 1F493 Symbols, Hebrew Letterlike Mathematical 2135 Symbols, I Ching / Yijing Hexagram 4DC0 Symbols, I Ching / Yijing Monogram and Digram 268A Symbols, I Ching / Yijing Trigram 2630 +Symbols, Italic Greek Mathematical 1D6E2 +Symbols, Italic Mathematical 1D434 Symbols, Japanese Chess 2616 Symbols, Keyboard 21E6 Symbols, Keyboard 2324 Symbols, Keyboard 2380 Symbols, Keyboard 2396 Symbols, Khmer 19E0 +Symbols, Kievan Musical 1D1DE Symbols, Latin-1 Punctuation and 00A0 Symbols, Letterlike 2100 +Symbols, Lock 1F50F +Symbols, Mail 1F4E4 Symbols, Mathematical 27C0 Symbols, Mathematical 2980 Symbols, Mathematical Alphanumeric 1D400 Symbols, Mathematical Digits 1D7CE Symbols, Metrical 23D1 Symbols, Miscellaneous 2600 +Symbols, Miscellaneous 1F940 +Symbols, Money 1F4B0 +Symbols, Monospace Mathematical 1D670 +Symbols, Moon, Sun, and Star 1F311 +Symbols, Music 1F3B5 Symbols, Musical 1D100 Symbols, New Testament Editorial 2E00 +Symbols, Office 1F4BA +Symbols, Palaeotype Transliteration 2E32 +Symbols, Personal Care 1F484 Symbols, Planet 263F +Symbols, Plant 1F330 Symbols, Plastics Recycling 2673 Symbols, Playing Card 2660 Symbols, Pointing Hand 261A Symbols, Polygonal 2B12 +Symbols, Portrait and Role 1F464 +Symbols, Portrait and Role 1F930 +Symbols, Power On/Off 23FB Symbols, Recycling 2672 -Symbols, Religious and Political 2625 +Symbols, Religious and Political 2626 +Symbols, Restroom 1F6B9 +Symbols, Role 1F481 +Symbols, Roman 10190 +Symbols, Romance 1F48B +Symbols, Rumi Numeral 10E60 +Symbols, Sans-serif Bold Greek Mathematical 1D756 +Symbols, Sans-serif Bold Italic Greek Mathematical 1D790 +Symbols, Sans-serif Bold Italic Mathematical 1D63C +Symbols, Sans-serif Bold Mathematical 1D5D4 +Symbols, Sans-serif Italic Mathematical 1D608 +Symbols, Sans-serif Mathematical 1D5A0 +Symbols, Script Mathematical 1D49C +Symbols, Signage and Other 1F6A9 +Symbols, Speaker 1F507 +Symbols, Speech and Thought Bubble 1F5E8 +Symbols, Sport 1F3BD +Symbols, Sport 1F3CF Symbols, Square 29C4 Symbols, Tai Xuan Jing 1D300 Symbols, Tamil 0BF3 Symbols, Tibetan 0FC4 +Symbols, Tool 1F525 +Symbols, Transport and Map 1F680 Symbols, Triangle 29CA +Symbols, User Interface 1F500 +Symbols, User Interface 1F53A +Symbols, User Interface 1F5BF +Symbols, User Interface Input Status 1F520 +Symbols, Vehicle 1F6E5 +Symbols, Weather 1F321 Symbols, Weather and Astrological 2600 +Symbols, Weather, Landscape, and Sky 1F300 Symbols, Yijing / I Ching Hexagram 4DC0 Symbols, Yijing / I Ching Monogram and Digram 268A Symbols, Yijing / I Ching Trigram 2630 @@ -5120,6 +5262,7 @@ SYRIAC CROSS, WEST 2670 Syriac Letters 0710 Syriac Punctuation and Signs 0700 syriac sam 070F +Syriac Supplement 0860 T WITH CARON, LATIN SMALL LETTER 0165 T WITH CEDILLA, LATIN SMALL LETTER 0163 T WITH CIRCUMFLEX BELOW, LATIN SMALL LETTER 1E71 @@ -5139,6 +5282,7 @@ T, COMBINING LATIN SMALL LETTER 036D T, LATIN LETTER SMALL CAPITAL 1D1B T, LATIN SMALL LETTER TURNED 0287 T, LATIN SUBSCRIPT SMALL LETTER 209C +T-REX 1F996 tab 0009 TAB KEY, HORIZONTAL 2B7E TAB KEY, VERTICAL 2B7F @@ -5209,6 +5353,8 @@ Tamil Symbols 0BF3 tamil varavu 0BF7 tamil varudam 0BF5 TAMIL YEAR SIGN 0BF5 +Tangut 17000 +Tangut Components 18800 TAPE DRIVE 2707 TAPER, CONICAL 2332 TARGET, ROUND 1F78B @@ -5473,6 +5619,9 @@ TWO DOT LEADER 2025 TWO DOT PUNCTUATION 205A TWO, SUPERSCRIPT 00B2 TWO-EM DASH 2E3A +Typicon Punctuation 2E44 +Typicon Symbols 1F900 +tyrannosaurus rex 1F996 U BAR, LATIN CAPITAL LETTER 0244 U BAR, LATIN SMALL LETTER 0289 U WITH ACUTE, LATIN CAPITAL LETTER 00DA @@ -5588,6 +5737,7 @@ V, LATIN SUBSCRIPT SMALL LETTER 1D65 Vai A500 valentine 2665 valid 22A8 +VAMPIRE 1F9DB varavu, tamil 0BF7 varia, greek 0300 VARIATION INDICATOR, IDEOGRAPHIC 303E @@ -5854,6 +6004,7 @@ Z WITH SWASH TAIL, LATIN SMALL LETTER 0240 Z, BLACK-LETTER CAPITAL 2128 Z, DOUBLE-STRUCK CAPITAL 2124 Z, LATIN LETTER SMALL CAPITAL 1D22 +Zanabazar Square 11A00 Zapf Dingbats Series 100, ITC 2700 ZERO WIDTH JOINER 200D ZERO WIDTH NO-BREAK SPACE FEFF @@ -5865,6 +6016,7 @@ ZERO, SUPERSCRIPT 2070 ZIGZAG ABOVE, COMBINING 035B Zodiac, Signs of the Asian 1F400 Zodiacal Symbols 2648 +ZOMBIE 1F9DF zwj 200D zwnbsp FEFF zwnj 200C diff --git a/gnu/usr.bin/perl/lib/unicore/IndicSyllabicCategory.txt b/gnu/usr.bin/perl/lib/unicore/IndicSyllabicCategory.txt index d7834f30fe7..fcd40af9327 100644 --- a/gnu/usr.bin/perl/lib/unicore/IndicSyllabicCategory.txt +++ b/gnu/usr.bin/perl/lib/unicore/IndicSyllabicCategory.txt @@ -1,9 +1,9 @@ -# IndicSyllabicCategory-8.0.0.txt -# Date: 2015-05-12, 10:00:00 GMT [RP, KW, LI] -# -# Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. +# IndicSyllabicCategory-10.0.0.txt +# Date: 2017-05-31, 01:07:00 GMT [KW, RP] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html +# # For documentation, see UAX #44: Unicode Character Database, # at http://www.unicode.org/reports/tr44/ # @@ -21,7 +21,7 @@ # of Indic script characters which are relevant to how Indic # syllables (or aksaras) are constructed. Note that rules for # syllabic structure in Indic scripts may differ significantly -# from how phonological syllables are defined. +# from how phonological syllables are defined. # # Format: # Field 0 Unicode code point value or range of code point values @@ -35,14 +35,15 @@ # The scripts assessed as Indic in the structural sense used for the # Indic_Syllabic_Category are the following: # -# Ahom, Balinese, Batak, Bengali, Brahmi, Buginese, Buhid, Chakma, -# Cham, Devanagari, Grantha, Gujarati, Gurmukhi, Hanunoo, Javanese, -# Kaithi, Kannada, Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, -# Lao, Lepcha, Limbu, Mahajani, Malayalam, Meetei Mayek, Modi, -# Multani, Myanmar, New Tai Lue, Oriya, Phags-pa, Rejang, Saurashtra, -# Sharada, Siddham, Sinhala, Sundanese, Syloti Nagri, Tagalog, -# Tagbanwa, Tai Le, Tai Tham, Tai Viet, Takri, Tamil, Telugu, Thai, -# Tibetan, and Tirhuta. +# Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid, +# Chakma, Cham, Devanagari, Grantha, Gujarati, Gurmukhi, Hanunoo, +# Javanese, Kaithi, Kannada, Kayah Li, Kharoshthi, Khmer, Khojki, +# Khudawadi, Lao, Lepcha, Limbu, Mahajani, Malayalam, Marchen, +# Masaram Gondi, Meetei Mayek, Modi, Multani, Myanmar, Newa, New Tai +# Lue, Oriya, Phags-pa, Rejang, Saurashtra, Sharada, Siddham, +# Sinhala, Soyombo, Sundanese, Syloti Nagri, Tagalog, Tagbanwa, Tai +# Le, Tai Tham, Tai Viet, Takri, Tamil, Telugu, Thai, Tibetan, +# Tirhuta, and Zanabazar Square. # # All characters for all other scripts not in that list # take the default value for this property, unless they @@ -63,13 +64,13 @@ # Indic_Syllabic_Category=Bindu # Bindu/Anusvara (nasalization or -n) -# Excludes various Vedic nasalization signs. # [Not derivable] 0900..0902 ; Bindu # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0981 ; Bindu # Mn BENGALI SIGN CANDRABINDU 0982 ; Bindu # Mc BENGALI SIGN ANUSVARA +09FC ; Bindu # Lo BENGALI LETTER VEDIC ANUSVARA 0A01..0A02 ; Bindu # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A70 ; Bindu # Mn GURMUKHI TIPPI 0A81..0A82 ; Bindu # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA @@ -80,6 +81,7 @@ 0C01..0C02 ; Bindu # Mc [2] TELUGU SIGN CANDRABINDU..TELUGU SIGN ANUSVARA 0C81 ; Bindu # Mn KANNADA SIGN CANDRABINDU 0C82 ; Bindu # Mc KANNADA SIGN ANUSVARA +0D00 ; Bindu # Mn MALAYALAM SIGN COMBINING ANUSVARA ABOVE 0D01 ; Bindu # Mn MALAYALAM SIGN CANDRABINDU 0D02 ; Bindu # Mc MALAYALAM SIGN ANUSVARA 0D82 ; Bindu # Mc SINHALA SIGN ANUSVARAYA @@ -90,12 +92,15 @@ 1036 ; Bindu # Mn MYANMAR SIGN ANUSVARA 17C6 ; Bindu # Mn KHMER SIGN NIKAHIT 1932 ; Bindu # Mn LIMBU SMALL LETTER ANUSVARA +1A74 ; Bindu # Mn TAI THAM SIGN MAI KANG 1B00..1B02 ; Bindu # Mn [3] BALINESE SIGN ULU RICEM..BALINESE SIGN CECEK 1B80 ; Bindu # Mn SUNDANESE SIGN PANYECEK 1C34..1C35 ; Bindu # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG A80B ; Bindu # Mn SYLOTI NAGRI SIGN ANUSVARA A873 ; Bindu # Lo PHAGS-PA LETTER CANDRABINDU A880 ; Bindu # Mc SAURASHTRA SIGN ANUSVARA +A8C5 ; Bindu # Mn SAURASHTRA SIGN CANDRABINDU +A8F2..A8F3 ; Bindu # Lo [2] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU VIRAMA A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 10A0E ; Bindu # Mn KHAROSHTHI SIGN ANUSVARA 11000 ; Bindu # Mc BRAHMI SIGN CANDRABINDU @@ -107,10 +112,17 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK 112DF ; Bindu # Mn KHUDAWADI SIGN ANUSVARA 11300..11301 ; Bindu # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU 11302 ; Bindu # Mc GRANTHA SIGN ANUSVARA +1135E..1135F ; Bindu # Lo [2] GRANTHA LETTER VEDIC ANUSVARA..GRANTHA LETTER VEDIC DOUBLE ANUSVARA +11443..11444 ; Bindu # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA 114BF..114C0 ; Bindu # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA 115BC..115BD ; Bindu # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA 1163D ; Bindu # Mn MODI SIGN ANUSVARA 116AB ; Bindu # Mn TAKRI SIGN ANUSVARA +11A35..11A38 ; Bindu # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A96 ; Bindu # Mn SOYOMBO SIGN ANUSVARA +11C3C..11C3D ; Bindu # Mn [2] BHAIKSUKI SIGN CANDRABINDU..BHAIKSUKI SIGN ANUSVARA +11CB5..11CB6 ; Bindu # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D40 ; Bindu # Mn MASARAM GONDI SIGN ANUSVARA # ================================================ @@ -119,7 +131,7 @@ A980..A981 ; Bindu # Mn [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK # Visarga (-h) # Includes specialized case for Sanskrit: ardhavisarga # Excludes letters for jihvamuliya and upadhmaniya, which are -# related, but structured somewhat differently. +# related, but structured somewhat differently. # [Not derivable] @@ -147,10 +159,15 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA 11102 ; Visarga # Mn CHAKMA SIGN VISARGA 11182 ; Visarga # Mc SHARADA SIGN VISARGA 11303 ; Visarga # Mc GRANTHA SIGN VISARGA +11445 ; Visarga # Mc NEWA SIGN VISARGA 114C1 ; Visarga # Mc TIRHUTA SIGN VISARGA 115BE ; Visarga # Mc SIDDHAM SIGN VISARGA 1163E ; Visarga # Mc MODI SIGN VISARGA 116AC ; Visarga # Mc TAKRI SIGN VISARGA +11A39 ; Visarga # Mc ZANABAZAR SQUARE SIGN VISARGA +11A97 ; Visarga # Mc SOYOMBO SIGN VISARGA +11C3E ; Visarga # Mc BHAIKSUKI SIGN VISARGA +11D41 ; Visarga # Mn MASARAM GONDI SIGN VISARGA # ================================================ @@ -172,21 +189,28 @@ AAF5 ; Visarga # Mc MEETEI MAYEK VOWEL SIGN VISARGA 1BBA ; Avagraha # Lo SUNDANESE AVAGRAHA 111C1 ; Avagraha # Lo SHARADA SIGN AVAGRAHA 1133D ; Avagraha # Lo GRANTHA SIGN AVAGRAHA +11447 ; Avagraha # Lo NEWA SIGN AVAGRAHA 114C4 ; Avagraha # Lo TIRHUTA SIGN AVAGRAHA +11C40 ; Avagraha # Lo BHAIKSUKI SIGN AVAGRAHA # ================================================ # Indic_Syllabic_Category=Nukta # Nukta (diacritic for borrowed consonants or other consonant -# modifications) +# modifications). Note that while the resulting sound is typically a +# consonant, the base letter a nukta follows may be an independent +# vowel. For example, <U+0A85 GUJARATI LETTER A, U+0AFD GUJARATI +# SIGN THREE-DOT NUKTA ABOVE> is used to transcribe ARABIC LETTER +# AIN. -# [Derivation: (ccc=7) + 0F39 + 10A38..10A3A - 1037] +# [Not derivable] 093C ; Nukta # Mn DEVANAGARI SIGN NUKTA 09BC ; Nukta # Mn BENGALI SIGN NUKTA 0A3C ; Nukta # Mn GURMUKHI SIGN NUKTA 0ABC ; Nukta # Mn GUJARATI SIGN NUKTA +0AFD..0AFF ; Nukta # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Nukta # Mn ORIYA SIGN NUKTA 0CBC ; Nukta # Mn KANNADA SIGN NUKTA 0F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU @@ -201,9 +225,11 @@ A9B3 ; Nukta # Mn JAVANESE SIGN CECAK TELU 11236 ; Nukta # Mn KHOJKI SIGN NUKTA 112E9 ; Nukta # Mn KHUDAWADI SIGN NUKTA 1133C ; Nukta # Mn GRANTHA SIGN NUKTA +11446 ; Nukta # Mn NEWA SIGN NUKTA 114C3 ; Nukta # Mn TIRHUTA SIGN NUKTA 115C0 ; Nukta # Mn SIDDHAM SIGN NUKTA 116B7 ; Nukta # Mn TAKRI SIGN NUKTA +11D42 ; Nukta # Mn MASARAM GONDI SIGN NUKTA # ================================================ @@ -236,10 +262,12 @@ A9C0 ; Virama # Mc JAVANESE PANGKON 111C0 ; Virama # Mc SHARADA SIGN VIRAMA 11235 ; Virama # Mc KHOJKI SIGN VIRAMA 1134D ; Virama # Mc GRANTHA SIGN VIRAMA +11442 ; Virama # Mn NEWA SIGN VIRAMA 114C2 ; Virama # Mn TIRHUTA SIGN VIRAMA 115BF ; Virama # Mn SIDDHAM SIGN VIRAMA 1163F ; Virama # Mn MODI SIGN VIRAMA 116B6 ; Virama # Mc TAKRI SIGN VIRAMA +11C3F ; Virama # Mn BHAIKSUKI SIGN VIRAMA # ================================================ @@ -250,6 +278,8 @@ A9C0 ; Virama # Mc JAVANESE PANGKON # [Not derivable] +0D3B ; Pure_Killer # Mn MALAYALAM SIGN VERTICAL BAR VIRAMA +0D3C ; Pure_Killer # Mn MALAYALAM SIGN CIRCULAR VIRAMA 0E3A ; Pure_Killer # Mn THAI CHARACTER PHINTHU 0E4E ; Pure_Killer # Mn THAI CHARACTER YAMAKKAN 0F84 ; Pure_Killer # Mn TIBETAN MARK HALANTA @@ -257,6 +287,7 @@ A9C0 ; Virama # Mc JAVANESE PANGKON 1714 ; Pure_Killer # Mn TAGALOG SIGN VIRAMA 1734 ; Pure_Killer # Mn HANUNOO SIGN PAMUDPOD 17D1 ; Pure_Killer # Mn KHMER SIGN VIRIAM +1A7A ; Pure_Killer # Mn TAI THAM SIGN RA HAAM 1BAA ; Pure_Killer # Mc SUNDANESE SIGN PAMAAEH 1BF2..1BF3 ; Pure_Killer # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN A806 ; Pure_Killer # Mn SYLOTI NAGRI SIGN HASANTA @@ -265,6 +296,8 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK 11134 ; Pure_Killer # Mn CHAKMA MAAYYAA 112EA ; Pure_Killer # Mn KHUDAWADI SIGN VIRAMA 1172B ; Pure_Killer # Mn AHOM SIGN KILLER +11A34 ; Pure_Killer # Mn ZANABAZAR SQUARE SIGN VIRAMA +11D44 ; Pure_Killer # Mn MASARAM GONDI SIGN HALANTA # ================================================ @@ -281,6 +314,9 @@ ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK AAF6 ; Invisible_Stacker # Mn MEETEI MAYEK VIRAMA 10A3F ; Invisible_Stacker # Mn KHAROSHTHI VIRAMA 11133 ; Invisible_Stacker # Mn CHAKMA VIRAMA +11A47 ; Invisible_Stacker # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Invisible_Stacker # Mn SOYOMBO SUBJOINER +11D45 ; Invisible_Stacker # Mn MASARAM GONDI VIRAMA # ================================================ @@ -355,18 +391,28 @@ ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 1130F..11310 ; Vowel_Independent # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI 11313..11314 ; Vowel_Independent # Lo [2] GRANTHA LETTER OO..GRANTHA LETTER AU 11360..11361 ; Vowel_Independent # Lo [2] GRANTHA LETTER VOCALIC RR..GRANTHA LETTER VOCALIC LL +11400..1140D ; Vowel_Independent # Lo [14] NEWA LETTER A..NEWA LETTER AU 11481..1148E ; Vowel_Independent # Lo [14] TIRHUTA LETTER A..TIRHUTA LETTER AU 11580..1158D ; Vowel_Independent # Lo [14] SIDDHAM LETTER A..SIDDHAM LETTER AU 115D8..115DB ; Vowel_Independent # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U 11600..1160D ; Vowel_Independent # Lo [14] MODI LETTER A..MODI LETTER AU 11680..11689 ; Vowel_Independent # Lo [10] TAKRI LETTER A..TAKRI LETTER AU +11A00 ; Vowel_Independent # Lo ZANABAZAR SQUARE LETTER A +11A50 ; Vowel_Independent # Lo SOYOMBO LETTER A +11C00..11C08 ; Vowel_Independent # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C0D ; Vowel_Independent # Lo [4] BHAIKSUKI LETTER E..BHAIKSUKI LETTER AU +11D00..11D06 ; Vowel_Independent # Lo [6] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Vowel_Independent # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B ; Vowel_Independent # Lo MASARAM GONDI LETTER AU # ================================================ # Indic_Syllabic_Category=Vowel_Dependent -# Dependent Vowels (contrasted with independent vowels and/or with complex placement) -# Matras (in Indic scripts) +# Dependent Vowels (contrasted with independent vowels and/or with +# complex placement). Known as matras in Indic scripts. Also +# includes vowel modifiers that follow dependent (and sometimes +# independent) vowels. # [Not derivable] @@ -483,7 +529,7 @@ ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA 1A63..1A64 ; Vowel_Dependent # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA 1A65..1A6C ; Vowel_Dependent # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW 1A6D..1A72 ; Vowel_Dependent # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI -1A73..1A74 ; Vowel_Dependent # Mn [2] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN MAI KANG +1A73 ; Vowel_Dependent # Mn TAI THAM VOWEL SIGN OA ABOVE 1B35 ; Vowel_Dependent # Mc BALINESE VOWEL SIGN TEDUNG 1B36..1B3A ; Vowel_Dependent # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA 1B3B ; Vowel_Dependent # Mc BALINESE VOWEL SIGN RA REPA TEDUNG @@ -556,6 +602,9 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 1134B..1134C ; Vowel_Dependent # Mc [2] GRANTHA VOWEL SIGN OO..GRANTHA VOWEL SIGN AU 11357 ; Vowel_Dependent # Mc GRANTHA AU LENGTH MARK 11362..11363 ; Vowel_Dependent # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11435..11437 ; Vowel_Dependent # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Vowel_Dependent # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Vowel_Dependent # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU 114B0..114B2 ; Vowel_Dependent # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Vowel_Dependent # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; Vowel_Dependent # Mc TIRHUTA VOWEL SIGN E @@ -576,6 +625,24 @@ ABE9..ABEA ; Vowel_Dependent # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEET 11722..11725 ; Vowel_Dependent # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Vowel_Dependent # Mc AHOM VOWEL SIGN E 11727..1172A ; Vowel_Dependent # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11A01..11A06 ; Vowel_Dependent # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Vowel_Dependent # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Vowel_Dependent # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A51..11A56 ; Vowel_Dependent # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Vowel_Dependent # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Vowel_Dependent # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11C2F ; Vowel_Dependent # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Vowel_Dependent # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3B ; Vowel_Dependent # Mn [4] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI VOWEL SIGN AU +11CB0 ; Vowel_Dependent # Mn MARCHEN VOWEL SIGN AA +11CB1 ; Vowel_Dependent # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Vowel_Dependent # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Vowel_Dependent # Mc MARCHEN VOWEL SIGN O +11D31..11D36 ; Vowel_Dependent # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Vowel_Dependent # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Vowel_Dependent # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F ; Vowel_Dependent # Mn MASARAM GONDI VOWEL SIGN AU +11D43 ; Vowel_Dependent # Mn MASARAM GONDI SIGN CANDRA # ================================================ @@ -612,6 +679,9 @@ A926..A92A ; Vowel # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O 1900 ; Consonant_Placeholder # Lo LIMBU VOWEL-CARRIER LETTER 2010..2014 ; Consonant_Placeholder # Pd [5] HYPHEN..EM DASH 25CC ; Consonant_Placeholder # So DOTTED CIRCLE +AA74..AA76 ; Consonant_Placeholder # Lo [3] MYANMAR LOGOGRAM KHAMTI OAY..MYANMAR LOGOGRAM KHAMTI HM +11A3F ; Consonant_Placeholder # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A45 ; Consonant_Placeholder # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK # ================================================ @@ -760,11 +830,17 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE 1132A..11330 ; Consonant # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA 11332..11333 ; Consonant # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA 11335..11339 ; Consonant # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA +1140E..11434 ; Consonant # Lo [39] NEWA LETTER KA..NEWA LETTER HA 1148F..114AF ; Consonant # Lo [33] TIRHUTA LETTER KA..TIRHUTA LETTER HA 1158E..115AE ; Consonant # Lo [33] SIDDHAM LETTER KA..SIDDHAM LETTER HA 1160E..1162F ; Consonant # Lo [34] MODI LETTER KA..MODI LETTER LLA 1168A..116AA ; Consonant # Lo [33] TAKRI LETTER KA..TAKRI LETTER RRA 11700..11719 ; Consonant # Lo [26] AHOM LETTER KA..AHOM LETTER JHA +11A0B..11A32 ; Consonant # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A5C..11A83 ; Consonant # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11C0E..11C2E ; Consonant # Lo [33] BHAIKSUKI LETTER KA..BHAIKSUKI LETTER HA +11C72..11C8F ; Consonant # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D0C..11D30 ; Consonant # Lo [37] MASARAM GONDI LETTER KA..MASARAM GONDI LETTER TRA # ================================================ @@ -775,6 +851,7 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # [Not derivable] 09CE ; Consonant_Dead # Lo BENGALI LETTER KHANDA TA +0D54..0D56 ; Consonant_Dead # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D7A..0D7F ; Consonant_Dead # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K # ================================================ @@ -793,11 +870,13 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # Indic_Syllabic_Category=Consonant_Prefixed -# Cluster-intial consonants +# Cluster-initial consonants # [Not derivable] 111C2..111C3 ; Consonant_Prefixed # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA +11A3A ; Consonant_Prefixed # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A86..11A89 ; Consonant_Prefixed # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA # ================================================ @@ -808,16 +887,20 @@ ABD2..ABDA ; Consonant # Lo [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE # [Not derivable] 0D4E ; Consonant_Preceding_Repha # Lo MALAYALAM LETTER DOT REPH +11D46 ; Consonant_Preceding_Repha # Lo MASARAM GONDI REPHA # ================================================ # Indic_Syllabic_Category=Consonant_Succeeding_Repha -# Repha Form of RA (reanalyzed in some scripts), when succeeding the main consonant +# Repha Form of RA (reanalyzed in some scripts), when succeeding the main consonant. +# Additionally, U+1A5A TAI THAM CONSONANT SIGN LOW PA has been temporarily classified +# in this class due to its behavior, although it is not a RA. # [Not derivable] 17CC ; Consonant_Succeeding_Repha # Mn KHMER SIGN ROBAT +1A5A ; Consonant_Succeeding_Repha # Mn TAI THAM CONSONANT SIGN LOW PA 1B03 ; Consonant_Succeeding_Repha # Mn BALINESE SIGN SURANG 1B81 ; Consonant_Succeeding_Repha # Mn SUNDANESE SIGN PANGLAYAR A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR @@ -833,6 +916,8 @@ A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR 0F8D..0F97 ; Consonant_Subjoined # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA 0F99..0FBC ; Consonant_Subjoined # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA 1929..192B ; Consonant_Subjoined # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA +1A57 ; Consonant_Subjoined # Mc TAI THAM CONSONANT SIGN LA TANG LAI +1A5B..1A5E ; Consonant_Subjoined # Mn [4] TAI THAM CONSONANT SIGN HIGH RATHA OR LOW PA..TAI THAM CONSONANT SIGN SA 1BA1 ; Consonant_Subjoined # Mc SUNDANESE CONSONANT SIGN PAMINGKAL 1BA2..1BA3 ; Consonant_Subjoined # Mn [2] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE CONSONANT SIGN PANYIKU 1BAC..1BAD ; Consonant_Subjoined # Mn [2] SUNDANESE CONSONANT SIGN PASANGAN MA..SUNDANESE CONSONANT SIGN PASANGAN WA @@ -840,6 +925,9 @@ A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR A867..A868 ; Consonant_Subjoined # Lo [2] PHAGS-PA SUBJOINED LETTER WA..PHAGS-PA SUBJOINED LETTER YA A871 ; Consonant_Subjoined # Lo PHAGS-PA SUBJOINED LETTER RA A9BD ; Consonant_Subjoined # Mc JAVANESE CONSONANT SIGN KERET +11C92..11CA7 ; Consonant_Subjoined # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Consonant_Subjoined # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CAF ; Consonant_Subjoined # Mn [6] MARCHEN SUBJOINED LETTER RA..MARCHEN SUBJOINED LETTER A # ================================================ @@ -862,6 +950,8 @@ A9BE..A9BF ; Consonant_Medial # Mc [2] JAVANESE CONSONANT SIGN PENGKAL..JAV AA33..AA34 ; Consonant_Medial # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA 1171D..1171F ; Consonant_Medial # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11A3B..11A3E ; Consonant_Medial # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11D47 ; Consonant_Medial # Mn MASARAM GONDI RA-KARA # ================================================ @@ -875,8 +965,7 @@ AA35..AA36 ; Consonant_Medial # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONA 1933..1938 ; Consonant_Final # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA 1939 ; Consonant_Final # Mn LIMBU SIGN MUKPHRENG 19C1..19C7 ; Consonant_Final # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B -1A57 ; Consonant_Final # Mc TAI THAM CONSONANT SIGN LA TANG LAI -1A58..1A5E ; Consonant_Final # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A58..1A59 ; Consonant_Final # Mn [2] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN FINAL NGA 1BBE..1BBF ; Consonant_Final # Lo [2] SUNDANESE LETTER FINAL K..SUNDANESE LETTER FINAL M 1BF0..1BF1 ; Consonant_Final # Mn [2] BATAK CONSONANT SIGN NG..BATAK CONSONANT SIGN H 1C2D..1C33 ; Consonant_Final # Mn [7] LEPCHA CONSONANT SIGN K..LEPCHA CONSONANT SIGN T @@ -889,6 +978,7 @@ AA44..AA4B ; Consonant_Final # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FIN AA4C ; Consonant_Final # Mn CHAM CONSONANT SIGN FINAL M AA4D ; Consonant_Final # Mc CHAM CONSONANT SIGN FINAL H ABDB..ABE2 ; Consonant_Final # Lo [8] MEETEI MAYEK LETTER KOK LONSUM..MEETEI MAYEK LETTER I LONSUM +11A8A..11A95 ; Consonant_Final # Mn [12] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO FINAL CONSONANT SIGN -A # ================================================ @@ -961,6 +1051,7 @@ ABEC ; Tone_Mark # Mc MEETEI MAYEK LUM IYEK 0A71 ; Gemination_Mark # Mn GURMUKHI ADDAK 11237 ; Gemination_Mark # Mn KHOJKI SIGN SHADDA +11A98 ; Gemination_Mark # Mn SOYOMBO GEMINATION MARK # ================================================ @@ -971,12 +1062,15 @@ ABEC ; Tone_Mark # Mc MEETEI MAYEK LUM IYEK # [Not derivable] 0951..0952 ; Cantillation_Mark # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA +0AFA..0AFC ; Cantillation_Mark # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 1CD0..1CD2 ; Cantillation_Mark # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD4..1CE0 ; Cantillation_Mark # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA 1CE1 ; Cantillation_Mark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF4 ; Cantillation_Mark # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Cantillation_Mark # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Cantillation_Mark # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +1123E ; Cantillation_Mark # Mn KHOJKI SIGN SUKUN 11366..1136C ; Cantillation_Mark # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Cantillation_Mark # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA @@ -1006,12 +1100,15 @@ A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..CO 17CB ; Syllable_Modifier # Mn KHMER SIGN BANTOC 17CE..17D0 ; Syllable_Modifier # Mn [3] KHMER SIGN KAKABAT..KHMER SIGN SAMYOK SANNYA 17D3 ; Syllable_Modifier # Mn KHMER SIGN BATHAMASAT +17DD ; Syllable_Modifier # Mn KHMER SIGN ATTHACAN 193B ; Syllable_Modifier # Mn LIMBU SIGN SA-I -1A7A..1A7C ; Syllable_Modifier # Mn [3] TAI THAM SIGN RA HAAM..TAI THAM SIGN KHUEN-LUE KARAN +1A7B..1A7C ; Syllable_Modifier # Mn [2] TAI THAM SIGN MAI SAM..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Syllable_Modifier # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1C36 ; Syllable_Modifier # Mn LEPCHA SIGN RAN +1DFB ; Syllable_Modifier # Mn COMBINING DELETION MARK 2074 ; Syllable_Modifier # No SUPERSCRIPT FOUR 2082..2084 ; Syllable_Modifier # No [3] SUBSCRIPT TWO..SUBSCRIPT FOUR +11A33 ; Syllable_Modifier # Mn ZANABAZAR SQUARE FINAL CONSONANT MARK # ================================================ @@ -1060,6 +1157,10 @@ A8E0..A8F1 ; Cantillation_Mark # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..CO # Indic_Syllabic_Category=Number # Number (can be used as vowel-holders like consonant placeholders) +# Note: A number may even hold subjoined consonants which may in turn +# have been formed using a virama or a stacker, e.g. the sequence +# <U+1A93, U+1A60, U+1A34> where THAI THAM LETTER LOW TA is subjoined to +# TAI THAM THAM DIGIT THREE using an invisible stacker. # [Not derivable] @@ -1100,11 +1201,15 @@ ABF0..ABF9 ; Number # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI 111D0..111D9 ; Number # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 111E1..111F4 ; Number # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND 112F0..112F9 ; Number # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Number # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; Number # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; Number # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Number # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Number # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 1173A..1173B ; Number # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY +11C50..11C59 ; Number # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; Number # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11D50..11D59 ; Number # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/Jamo.txt b/gnu/usr.bin/perl/lib/unicore/Jamo.txt index 8f7c5937ae9..f2b5ecb5ca5 100644 --- a/gnu/usr.bin/perl/lib/unicore/Jamo.txt +++ b/gnu/usr.bin/perl/lib/unicore/Jamo.txt @@ -1,14 +1,14 @@ -# Jamo-8.0.0.txt -# Date: 2015-01-20, 01:30:00 GMT [KW, LI] +# Jamo-10.0.0.txt +# Date: 2017-02-15, 00:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see http://www.unicode.org/reports/tr44/ # # This file defines the Jamo_Short_Name property. # -# See Section 3.12 of The Unicode Standard, Version 8.0 +# See Section 3.12 of The Unicode Standard, Version 10.0 # for more information. # # Each line contains two fields, separated by a semicolon. diff --git a/gnu/usr.bin/perl/lib/unicore/LineBreak.txt b/gnu/usr.bin/perl/lib/unicore/LineBreak.txt index b627f874d0f..d80210bde3a 100644 --- a/gnu/usr.bin/perl/lib/unicore/LineBreak.txt +++ b/gnu/usr.bin/perl/lib/unicore/LineBreak.txt @@ -1,45 +1,45 @@ -# LineBreak-8.0.0.txt -# Date: 2015-02-13, 09:15:00 GMT [KW, LI] +# LineBreak-10.0.0.txt +# Date: 2017-03-08, 02:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # Line_Break Property # # This file is a normative contributory data file in the # Unicode Character Database. -# It contains both normative and informative data. -# -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html # # The format is two fields separated by a semicolon. # Field 0: Unicode code point value or range of code point values # Field 1: Line_Break property, consisting of one of the following values: -# Normative: -# "BK", "CR", "LF", "CM", "SG", "GL", "CB", "SP", "ZW", -# "NL", "WJ", "JL", "JV", "JT", "H2", "H3" -# Informative: -# "XX", "OP", "CL", "CP", "QU", "NS", "EX", "SY", -# "IS", "PR", "PO", "NU", "AL", "ID", "IN", "HY", -# "BB", "BA", "SA", "AI", "B2", "HL", "CJ", "RI" +# Non-tailorable: +# "BK", "CM", "CR", "GL", "LF", "NL", "SP", "WJ", "ZW", "ZWJ" +# Tailorable: +# "AI", "AL", "B2", "BA", "BB", "CB", "CJ", "CL", "CP", "EB", +# "EM", "EX", "H2", "H3", "HL", "HY", "ID", "IN", "IS", "JL", +# "JT", "JV", "NS", "NU", "OP", "PO", "PR", "QU", "RI", "SA", +# "SG", "SY", "XX" # - All code points, assigned and unassigned, that are not listed -# explicitly are given the value "XX". -# The unassigned code points that default to "ID" include ranges in the -# following blocks: -# CJK Unified Ideographs Extension A: U+3400..U+4DBF -# CJK Unified Ideographs: U+4E00..U+9FFF -# CJK Compatibility Ideographs: U+F900..U+FAFF -# CJK Unified Ideographs Extension B: U+20000..U+2A6DF -# CJK Unified Ideographs Extension C: U+2A700..U+2B73F -# CJK Unified Ideographs Extension D: U+2B740..U+2B81F -# CJK Unified Ideographs Extension E: U+2B820..U+2CEAF -# CJK Compatibility Ideographs Supplement: U+2F800..U+2FA1F -# and any other reserved code points on -# Planes 2 and 3: U+20000..U+2FFFD -# U+30000..U+3FFFD -# The unassigned code points that default to "PR" comprise a range in the -# following block: -# Currency Symbols: U+20A0..U+20CF -# - Character ranges are specified as for other property files in -# the Unicode Character Database. +# explicitly are given the value "XX". +# - The unassigned code points in the following blocks default to "ID": +# CJK Unified Ideographs Extension A: U+3400..U+4DBF +# CJK Unified Ideographs: U+4E00..U+9FFF +# CJK Compatibility Ideographs: U+F900..U+FAFF +# - All undesignated code points in Planes 2 and 3, whether inside or +# outside of allocated blocks, default to "ID": +# Plane 2: U+20000..U+2FFFD +# Plane 3: U+30000..U+3FFFD +# - All unassigned code points in the following Plane 1 range, whether +# inside or outside of allocated blocks, also default to "ID": +# Plane 1 range: U+1F000..U+1FFFD +# - The unassigned code points in the following block default to "PR": +# Currency Symbols: U+20A0..U+20CF +# +# Character ranges are specified as for other property files in the +# Unicode Character Database. # # For legacy reasons, there are no spaces before or after the semicolon # which separates the two fields. The comments following the number sign @@ -273,7 +273,11 @@ 0840..0858;AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B;CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E;AL # Po MANDAIC PUNCTUATION +0860..086A;AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4;AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD;AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1;CM # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2;AL # Cf ARABIC DISPUTED END OF AYAH 08E3..08FF;CM # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA 0900..0902;CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0903;CM # Mc DEVANAGARI SIGN VISARGA @@ -324,6 +328,8 @@ 09F9;PO # No BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA;AL # So BENGALI ISSHAR 09FB;PR # Sc BENGALI GANDA MARK +09FC;AL # Lo BENGALI LETTER VEDIC ANUSVARA +09FD;AL # Po BENGALI ABBREVIATION SIGN 0A01..0A02;CM # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03;CM # Mc GURMUKHI SIGN VISARGA 0A05..0A0A;AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -368,6 +374,7 @@ 0AF0;AL # Po GUJARATI ABBREVIATION SIGN 0AF1;PR # Sc GUJARATI RUPEE SIGN 0AF9;AL # Lo GUJARATI LETTER ZHA +0AFA..0AFF;CM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01;CM # Mn ORIYA SIGN CANDRABINDU 0B02..0B03;CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C;AL # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -436,6 +443,7 @@ 0C66..0C6F;NU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C78..0C7E;AL # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F;AL # So TELUGU SIGN TUUMU +0C80;AL # Lo KANNADA SIGN SPACING CANDRABINDU 0C81;CM # Mn KANNADA SIGN CANDRABINDU 0C82..0C83;CM # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C;AL # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -458,11 +466,12 @@ 0CE2..0CE3;CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF;NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2;AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01;CM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01;CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03;CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C;AL # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10;AL # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A;AL # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C;CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D;AL # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40;CM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44;CM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -470,11 +479,14 @@ 0D4A..0D4C;CM # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D;CM # Mn MALAYALAM SIGN VIRAMA 0D4E;AL # Lo MALAYALAM LETTER DOT REPH +0D4F;AL # So MALAYALAM SIGN PARA +0D54..0D56;AL # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57;CM # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E;AL # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61;AL # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63;CM # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0D66..0D6F;NU # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75;AL # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78;AL # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79;PO # So MALAYALAM DATE MARK 0D7A..0D7F;AL # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83;CM # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -700,7 +712,9 @@ 1820..1842;AL # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843;AL # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877;AL # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8;AL # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884;AL # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886;CM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8;AL # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9;CM # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA;AL # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5;AL # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -802,6 +816,7 @@ 1C5A..1C77;AL # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D;AL # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F;BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88;AL # Ll [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7;AL # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD0..1CD2;CM # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD3;AL # Po VEDIC SIGN NIHSHVASA @@ -814,6 +829,7 @@ 1CF2..1CF3;CM # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4;CM # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6;AL # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7;CM # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9;CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B;AL # Ll [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A;AL # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -822,8 +838,8 @@ 1D79..1D7F;AL # Ll [7] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER UPSILON WITH STROKE 1D80..1D9A;AL # Ll [27] LATIN SMALL LETTER B WITH PALATAL HOOK..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF;AL # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5;CM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF;CM # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9;CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF;CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1EFF;AL # L& [256] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER Y WITH LOOP 1F00..1F15;AL # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D;AL # Lu [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA @@ -855,7 +871,9 @@ 2007;GL # Zs FIGURE SPACE 2008..200A;BA # Zs [3] PUNCTUATION SPACE..HAIR SPACE 200B;ZW # Cf ZERO WIDTH SPACE -200C..200F;CM # Cf [4] ZERO WIDTH NON-JOINER..RIGHT-TO-LEFT MARK +200C;CM # Cf ZERO WIDTH NON-JOINER +200D;ZWJ # Cf ZERO WIDTH JOINER +200E..200F;CM # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 2010;BA # Pd HYPHEN 2011;GL # Pd NON-BREAKING HYPHEN 2012..2013;BA # Pd [2] FIGURE DASH..EN DASH @@ -928,7 +946,8 @@ 20BB;PO # Sc NORDIC MARK SIGN 20BC..20BD;PR # Sc [2] MANAT SIGN..RUBLE SIGN 20BE;PO # Sc LARI SIGN -20BF..20CF;PR # Cn [17] <reserved-20BF>..<reserved-20CF> +20BF;PR # Sc BITCOIN SIGN +20C0..20CF;PR # Cn [16] <reserved-20C0>..<reserved-20CF> 20D0..20DC;CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0;CM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1;CM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1091,7 +1110,7 @@ 23DC..23E1;AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET 23E2..23EF;AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR 23F0..23F3;ID # So [4] ALARM CLOCK..HOURGLASS WITH FLOWING SAND -23F4..23FA;AL # So [7] BLACK MEDIUM LEFT-POINTING TRIANGLE..BLACK CIRCLE FOR RECORD +23F4..23FF;AL # So [12] BLACK MEDIUM LEFT-POINTING TRIANGLE..OBSERVER EYE SYMBOL 2400..2426;AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A;AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B;AI # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP @@ -1143,7 +1162,9 @@ 2616..2617;AI # So [2] WHITE SHOGI PIECE..BLACK SHOGI PIECE 2618;ID # So SHAMROCK 2619;AL # So REVERSED ROTATED FLORAL HEART BULLET -261A..261F;ID # So [6] BLACK LEFT POINTING INDEX..WHITE DOWN POINTING INDEX +261A..261C;ID # So [3] BLACK LEFT POINTING INDEX..WHITE LEFT POINTING INDEX +261D;EB # So WHITE UP POINTING INDEX +261E..261F;ID # So [2] WHITE RIGHT POINTING INDEX..WHITE DOWN POINTING INDEX 2620..2638;AL # So [25] SKULL AND CROSSBONES..WHEEL OF DHARMA 2639..263B;ID # So [3] WHITE FROWNING FACE..BLACK SMILING FACE 263C..263F;AL # So [4] WHITE SUN WITH RAYS..MERCURY @@ -1188,19 +1209,23 @@ 26EB..26F0;AI # So [6] CASTLE..MOUNTAIN 26F1..26F5;ID # So [5] UMBRELLA ON GROUND..SAILBOAT 26F6;AI # So SQUARE FOUR CORNERS -26F7..26FA;ID # So [4] SKIER..TENT +26F7..26F8;ID # So [2] SKIER..ICE SKATE +26F9;EB # So PERSON WITH BALL +26FA;ID # So TENT 26FB..26FC;AI # So [2] JAPANESE BANK SYMBOL..HEADSTONE GRAVEYARD SYMBOL 26FD..26FF;ID # So [3] FUEL PUMP..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE 2700..2704;ID # So [5] BLACK SAFETY SCISSORS..WHITE SCISSORS 2705..2707;AL # So [3] WHITE HEAVY CHECK MARK..TAPE DRIVE -2708..270D;ID # So [6] AIRPLANE..WRITING HAND +2708..2709;ID # So [2] AIRPLANE..ENVELOPE +270A..270D;EB # So [4] RAISED FIST..WRITING HAND 270E..2756;AL # So [73] LOWER RIGHT PENCIL..BLACK DIAMOND MINUS WHITE X 2757;AI # So HEAVY EXCLAMATION MARK SYMBOL 2758..275A;AL # So [3] LIGHT VERTICAL BAR..HEAVY VERTICAL BAR 275B..2760;QU # So [6] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT 2761;AL # So CURVED STEM PARAGRAPH SIGN ORNAMENT 2762..2763;EX # So [2] HEAVY EXCLAMATION MARK ORNAMENT..HEAVY HEART EXCLAMATION MARK ORNAMENT -2764..2767;AL # So [4] HEAVY BLACK HEART..ROTATED FLORAL HEART BULLET +2764;ID # So HEAVY BLACK HEART +2765..2767;AL # So [3] ROTATED HEAVY BLACK HEART BULLET..ROTATED FLORAL HEART BULLET 2768;OP # Ps MEDIUM LEFT PARENTHESIS ORNAMENT 2769;CL # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT 276A;OP # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT @@ -1277,7 +1302,7 @@ 2B76..2B95;AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9;AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8;AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1;AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2;AL # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF;AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E;AL # Lu [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E;AL # Ll [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1355,6 +1380,7 @@ 2E40;BA # Pd DOUBLE HYPHEN 2E41;BA # Po REVERSED COMMA 2E42;OP # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49;BA # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99;ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3;ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5;ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1453,7 +1479,7 @@ 30FC;CJ # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK 30FD..30FE;NS # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK 30FF;ID # Lo KATAKANA DIGRAPH KOTO -3105..312D;ID # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E;ID # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E;ID # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191;ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195;ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1476,8 +1502,8 @@ 3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;ID # Cn [10] <reserved-4DB6>..<reserved-4DBF> 4DC0..4DFF;AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5;ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF;ID # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA;ID # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF;ID # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014;ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015;NS # Lm YI SYLLABLE WU A016..A48C;ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1519,7 +1545,7 @@ A788;AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A;AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E;AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F;AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD;AL # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE;AL # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7;AL # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7;AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9;AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1546,7 +1572,7 @@ A876..A877;EX # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD A880..A881;CM # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3;AL # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3;CM # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4;CM # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5;CM # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8CE..A8CF;BA # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A8D0..A8D9;NU # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8E0..A8F1;CM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA @@ -2574,16 +2600,16 @@ FF62;OP # Ps HALFWIDTH LEFT CORNER BRACKET FF63;CL # Pe HALFWIDTH RIGHT CORNER BRACKET FF64;CL # Po HALFWIDTH IDEOGRAPHIC COMMA FF65;NS # Po HALFWIDTH KATAKANA MIDDLE DOT -FF66;AL # Lo HALFWIDTH KATAKANA LETTER WO +FF66;ID # Lo HALFWIDTH KATAKANA LETTER WO FF67..FF6F;CJ # Lo [9] HALFWIDTH KATAKANA LETTER SMALL A..HALFWIDTH KATAKANA LETTER SMALL TU FF70;CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK -FF71..FF9D;AL # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +FF71..FF9D;ID # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N FF9E..FF9F;NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK -FFA0..FFBE;AL # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH -FFC2..FFC7;AL # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E -FFCA..FFCF;AL # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE -FFD2..FFD7;AL # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU -FFDA..FFDC;AL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I +FFA0..FFBE;ID # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7;ID # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF;ID # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7;ID # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC;ID # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I FFE0;PO # Sc FULLWIDTH CENT SIGN FFE1;PR # Sc FULLWIDTH POUND SIGN FFE2;ID # Sm FULLWIDTH NOT SIGN @@ -2610,7 +2636,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 10175..10178;AL # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189;AL # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B;AL # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C;AL # So GREEK SINUSOID SIGN +1018C..1018E;AL # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B;AL # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0;AL # So GREEK SYMBOL TAU RHO 101D0..101FC;AL # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -2621,6 +2647,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 102E1..102FB;AL # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F;AL # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323;AL # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F;AL # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE 10330..10340;AL # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA 10341;AL # Nl GOTHIC LETTER NINETY 10342..10349;AL # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL @@ -2637,6 +2664,8 @@ FFFD;AI # So REPLACEMENT CHARACTER 10450..1047F;AL # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW 10480..1049D;AL # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO 104A0..104A9;NU # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3;AL # Lu [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB;AL # Ll [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527;AL # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563;AL # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F;AL # Po CAUCASIAN ALBANIAN CITATION MARK @@ -2774,6 +2803,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 1123A;AL # Po KHOJKI WORD SEPARATOR 1123B..1123C;BA # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK 1123D;AL # Po KHOJKI ABBREVIATION SIGN +1123E;CM # Mn KHOJKI SIGN SUKUN 11280..11286;AL # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288;AL # Lo MULTANI LETTER GHA 1128A..1128D;AL # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -2806,6 +2836,19 @@ FFFD;AI # So REPLACEMENT CHARACTER 11362..11363;CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C;CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374;CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434;AL # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437;CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F;CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441;CM # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444;CM # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445;CM # Mc NEWA SIGN VISARGA +11446;CM # Mn NEWA SIGN NUKTA +11447..1144A;AL # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144E;BA # Po [4] NEWA DANDA..NEWA GAP FILLER +1144F;AL # Po NEWA ABBREVIATION SIGN +11450..11459;NU # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B;BA # Po NEWA PLACEHOLDER MARK +1145D;AL # Po NEWA INSERTION SIGN 11480..114AF;AL # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2;CM # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8;CM # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -2844,6 +2887,7 @@ FFFD;AI # So REPLACEMENT CHARACTER 11643;AL # Po MODI ABBREVIATION SIGN 11644;AL # Lo MODI SIGN HUVA 11650..11659;NU # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C;BB # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11680..116AA;AL # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116AB;CM # Mn TAKRI SIGN ANUSVARA 116AC;CM # Mc TAKRI SIGN VISARGA @@ -2867,7 +2911,65 @@ FFFD;AI # So REPLACEMENT CHARACTER 118E0..118E9;NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2;AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF;AL # Lo WARANG CITI OM +11A00;AL # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06;CM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08;CM # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A;CM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32;AL # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38;CM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39;CM # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A;AL # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E;CM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F;BB # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A40;AL # Po ZANABAZAR SQUARE CLOSING HEAD MARK +11A41..11A44;BA # Po [4] ZANABAZAR SQUARE MARK TSHEG..ZANABAZAR SQUARE MARK LONG TSHEG +11A45;BB # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK +11A46;AL # Po ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47;CM # Mn ZANABAZAR SQUARE SUBJOINER +11A50;AL # Lo SOYOMBO LETTER A +11A51..11A56;CM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58;CM # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B;CM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83;AL # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89;AL # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96;CM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97;CM # Mc SOYOMBO SIGN VISARGA +11A98..11A99;CM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C;BA # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA0;BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN +11AA1..11AA2;BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 11AC0..11AF8;AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08;AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E;AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F;CM # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36;CM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D;CM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E;CM # Mc BHAIKSUKI SIGN VISARGA +11C3F;CM # Mn BHAIKSUKI SIGN VIRAMA +11C40;AL # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45;BA # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59;NU # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C;AL # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70;BB # Po MARCHEN HEAD MARK +11C71;EX # Po MARCHEN MARK SHAD +11C72..11C8F;AL # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7;CM # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9;CM # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0;CM # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1;CM # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3;CM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4;CM # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6;CM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06;AL # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09;AL # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30;AL # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36;CM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A;CM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D;CM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45;CM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46;AL # Lo MASARAM GONDI REPHA +11D47;CM # Mn MASARAM GONDI RA-KARA +11D50..11D59;NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399;AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E;AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474;BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -2914,7 +3016,12 @@ FFFD;AI # So REPLACEMENT CHARACTER 16F51..16F7E;CM # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92;CM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F;AL # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001;ID # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1;NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC;ID # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2;ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B0FF;ID # Lo [256] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER RE-2 +1B100..1B11E;ID # Lo [31] HENTAIGANA LETTER RE-3..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB;ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A;AL # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C;AL # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88;AL # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2996,9 +3103,18 @@ FFFD;AI # So REPLACEMENT CHARACTER 1DA8B;AL # Po SIGNWRITING PARENTHESIS 1DA9B..1DA9F;CM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF;CM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006;CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018;CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021;CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024;CM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A;CM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4;AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF;AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6;CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943;AL # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A;CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959;NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F;OP # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK 1EE00..1EE03;AL # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F;AL # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22;AL # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -3034,37 +3150,79 @@ FFFD;AI # So REPLACEMENT CHARACTER 1EEAB..1EEBB;AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1;AL # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL 1F000..1F02B;ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK +1F02C..1F02F;ID # Cn [4] <reserved-1F02C>..<reserved-1F02F> 1F030..1F093;ID # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 +1F094..1F09F;ID # Cn [12] <reserved-1F094>..<reserved-1F09F> 1F0A0..1F0AE;ID # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES +1F0AF..1F0B0;ID # Cn [2] <reserved-1F0AF>..<reserved-1F0B0> 1F0B1..1F0BF;ID # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER +1F0C0;ID # Cn <reserved-1F0C0> 1F0C1..1F0CF;ID # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER +1F0D0;ID # Cn <reserved-1F0D0> 1F0D1..1F0F5;ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 +1F0F6..1F0FF;ID # Cn [10] <reserved-1F0F6>..<reserved-1F0FF> 1F100..1F10C;AI # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO +1F10D..1F10F;ID # Cn [3] <reserved-1F10D>..<reserved-1F10F> 1F110..1F12D;AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD 1F12E;AL # So CIRCLED WZ +1F12F;ID # Cn <reserved-1F12F> 1F130..1F169;AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F16A..1F16B;AL # So [2] RAISED MC SIGN..RAISED MD SIGN -1F170..1F19A;AI # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F16C..1F16F;ID # Cn [4] <reserved-1F16C>..<reserved-1F16F> +1F170..1F1AC;AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD +1F1AD..1F1E5;ID # Cn [57] <reserved-1F1AD>..<reserved-1F1E5> 1F1E6..1F1FF;RI # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z 1F200..1F202;ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A;ID # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F203..1F20F;ID # Cn [13] <reserved-1F203>..<reserved-1F20F> +1F210..1F23B;ID # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D +1F23C..1F23F;ID # Cn [4] <reserved-1F23C>..<reserved-1F23F> 1F240..1F248;ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 +1F249..1F24F;ID # Cn [7] <reserved-1F249>..<reserved-1F24F> 1F250..1F251;ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -1F300..1F39B;ID # So [156] CYCLONE..CONTROL KNOBS +1F252..1F25F;ID # Cn [14] <reserved-1F252>..<reserved-1F25F> +1F260..1F265;ID # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F266..1F2FF;ID # Cn [154] <reserved-1F266>..<reserved-1F2FF> +1F300..1F384;ID # So [133] CYCLONE..CHRISTMAS TREE +1F385;EB # So FATHER CHRISTMAS +1F386..1F39B;ID # So [22] FIREWORKS..CONTROL KNOBS 1F39C..1F39D;AL # So [2] BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES 1F39E..1F3B4;ID # So [23] FILM FRAMES..FLOWER PLAYING CARDS 1F3B5..1F3B6;AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES 1F3B7..1F3BB;ID # So [5] SAXOPHONE..VIOLIN 1F3BC;AL # So MUSICAL SCORE -1F3BD..1F3FA;ID # So [62] RUNNING SHIRT WITH SASH..AMPHORA -1F3FB..1F3FF;AL # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F49F;ID # So [160] RAT..HEART DECORATION +1F3BD..1F3C1;ID # So [5] RUNNING SHIRT WITH SASH..CHEQUERED FLAG +1F3C2..1F3C4;EB # So [3] SNOWBOARDER..SURFER +1F3C5..1F3C6;ID # So [2] SPORTS MEDAL..TROPHY +1F3C7;EB # So HORSE RACING +1F3C8..1F3C9;ID # So [2] AMERICAN FOOTBALL..RUGBY FOOTBALL +1F3CA..1F3CC;EB # So [3] SWIMMER..GOLFER +1F3CD..1F3FA;ID # So [46] RACING MOTORCYCLE..AMPHORA +1F3FB..1F3FF;EM # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 +1F400..1F441;ID # So [66] RAT..EYE +1F442..1F443;EB # So [2] EAR..NOSE +1F444..1F445;ID # So [2] MOUTH..TONGUE +1F446..1F450;EB # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN +1F451..1F465;ID # So [21] CROWN..BUSTS IN SILHOUETTE +1F466..1F469;EB # So [4] BOY..WOMAN +1F46A..1F46D;ID # So [4] FAMILY..TWO WOMEN HOLDING HANDS +1F46E;EB # So POLICE OFFICER +1F46F;ID # So WOMAN WITH BUNNY EARS +1F470..1F478;EB # So [9] BRIDE WITH VEIL..PRINCESS +1F479..1F47B;ID # So [3] JAPANESE OGRE..GHOST +1F47C;EB # So BABY ANGEL +1F47D..1F480;ID # So [4] EXTRATERRESTRIAL ALIEN..SKULL +1F481..1F483;EB # So [3] INFORMATION DESK PERSON..DANCER +1F484;ID # So LIPSTICK +1F485..1F487;EB # So [3] NAIL POLISH..HAIRCUT +1F488..1F49F;ID # So [24] BARBER POLE..HEART DECORATION 1F4A0;AL # So DIAMOND SHAPE WITH A DOT INSIDE 1F4A1;ID # So ELECTRIC LIGHT BULB 1F4A2;AL # So ANGER SYMBOL 1F4A3;ID # So BOMB 1F4A4;AL # So SLEEPING SYMBOL -1F4A5..1F4AE;ID # So [10] COLLISION SYMBOL..WHITE FLOWER +1F4A5..1F4A9;ID # So [5] COLLISION SYMBOL..PILE OF POO +1F4AA;EB # So FLEXED BICEPS +1F4AB..1F4AE;ID # So [4] DIZZY SYMBOL..WHITE FLOWER 1F4AF;AL # So HUNDRED POINTS SYMBOL 1F4B0;ID # So MONEY BAG 1F4B1..1F4B2;AL # So [2] CURRENCY EXCHANGE..HEAVY DOLLAR SIGN @@ -3074,31 +3232,80 @@ FFFD;AI # So REPLACEMENT CHARACTER 1F517..1F524;AL # So [14] LINK SYMBOL..INPUT SYMBOL FOR LATIN LETTERS 1F525..1F531;ID # So [13] FIRE..TRIDENT EMBLEM 1F532..1F549;AL # So [24] BLACK SQUARE BUTTON..OM SYMBOL -1F54A..1F579;ID # So [48] DOVE OF PEACE..JOYSTICK -1F57B..1F5A3;ID # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F5D3;ID # So [47] DESKTOP COMPUTER..SPIRAL CALENDAR PAD +1F54A..1F573;ID # So [42] DOVE OF PEACE..HOLE +1F574..1F575;EB # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY +1F576..1F579;ID # So [4] DARK SUNGLASSES..JOYSTICK +1F57A;EB # So MAN DANCING +1F57B..1F58F;ID # So [21] LEFT HAND TELEPHONE RECEIVER..TURNED OK HAND SIGN +1F590;EB # So RAISED HAND WITH FINGERS SPLAYED +1F591..1F594;ID # So [4] REVERSED RAISED HAND WITH FINGERS SPLAYED..REVERSED VICTORY HAND +1F595..1F596;EB # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F597..1F5D3;ID # So [61] WHITE DOWN POINTING LEFT HAND INDEX..SPIRAL CALENDAR PAD 1F5D4..1F5DB;AL # So [8] DESKTOP WINDOW..DECREASE FONT SIZE SYMBOL 1F5DC..1F5F3;ID # So [24] COMPRESSION..BALLOT BOX WITH BALLOT 1F5F4..1F5F9;AL # So [6] BALLOT SCRIPT X..BALLOT BOX WITH BOLD CHECK 1F5FA..1F5FF;ID # So [6] WORLD MAP..MOYAI -1F600..1F64F;ID # So [80] GRINNING FACE..PERSON WITH FOLDED HANDS +1F600..1F644;ID # So [69] GRINNING FACE..FACE WITH ROLLING EYES +1F645..1F647;EB # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY +1F648..1F64A;ID # So [3] SEE-NO-EVIL MONKEY..SPEAK-NO-EVIL MONKEY +1F64B..1F64F;EB # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS 1F650..1F675;AL # So [38] NORTH WEST POINTING LEAF..SWASH AMPERSAND ORNAMENT 1F676..1F678;QU # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT 1F679..1F67B;NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT 1F67C..1F67F;AL # So [4] VERY HEAVY SOLIDUS..REVERSE CHECKER BOARD -1F680..1F6D0;ID # So [81] ROCKET..PLACE OF WORSHIP +1F680..1F6A2;ID # So [35] ROCKET..SHIP +1F6A3;EB # So ROWBOAT +1F6A4..1F6B3;ID # So [16] SPEEDBOAT..NO BICYCLES +1F6B4..1F6B6;EB # So [3] BICYCLIST..PEDESTRIAN +1F6B7..1F6BF;ID # So [9] NO PEDESTRIANS..SHOWER +1F6C0;EB # So BATH +1F6C1..1F6CB;ID # So [11] BATHTUB..COUCH AND LAMP +1F6CC;EB # So SLEEPING ACCOMMODATION +1F6CD..1F6D4;ID # So [8] SHOPPING BAGS..PAGODA +1F6D5..1F6DF;ID # Cn [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6E0..1F6EC;ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3;ID # So [4] SATELLITE..PASSENGER SHIP +1F6ED..1F6EF;ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> +1F6F0..1F6F8;ID # So [9] SATELLITE..FLYING SAUCER +1F6F9..1F6FF;ID # Cn [7] <reserved-1F6F9>..<reserved-1F6FF> 1F700..1F773;AL # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE +1F774..1F77F;ID # Cn [12] <reserved-1F774>..<reserved-1F77F> 1F780..1F7D4;AL # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR +1F7D5..1F7FF;ID # Cn [43] <reserved-1F7D5>..<reserved-1F7FF> 1F800..1F80B;AL # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD +1F80C..1F80F;ID # Cn [4] <reserved-1F80C>..<reserved-1F80F> 1F810..1F847;AL # So [56] LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD..DOWNWARDS HEAVY ARROW +1F848..1F84F;ID # Cn [8] <reserved-1F848>..<reserved-1F84F> 1F850..1F859;AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW +1F85A..1F85F;ID # Cn [6] <reserved-1F85A>..<reserved-1F85F> 1F860..1F887;AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW +1F888..1F88F;ID # Cn [8] <reserved-1F888>..<reserved-1F88F> 1F890..1F8AD;AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918;ID # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984;ID # So [5] CRAB..UNICORN FACE +1F8AE..1F8FF;ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF> +1F900..1F90B;AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F90C..1F90F;ID # Cn [4] <reserved-1F90C>..<reserved-1F90F> +1F910..1F917;ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE +1F918..1F91C;EB # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91D;ID # So HANDSHAKE +1F91E..1F91F;EB # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN +1F920..1F925;ID # So [6] FACE WITH COWBOY HAT..LYING FACE +1F926;EB # So FACE PALM +1F927..1F92F;ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD +1F930..1F939;EB # So [10] PREGNANT WOMAN..JUGGLING +1F93A..1F93C;ID # So [3] FENCER..WRESTLERS +1F93D..1F93E;EB # So [2] WATER POLO..HANDBALL +1F93F;ID # Cn <reserved-1F93F> +1F940..1F94C;ID # So [13] WILTED FLOWER..CURLING STONE +1F94D..1F94F;ID # Cn [3] <reserved-1F94D>..<reserved-1F94F> +1F950..1F96B;ID # So [28] CROISSANT..CANNED FOOD +1F96C..1F97F;ID # Cn [20] <reserved-1F96C>..<reserved-1F97F> +1F980..1F997;ID # So [24] CRAB..CRICKET +1F998..1F9BF;ID # Cn [40] <reserved-1F998>..<reserved-1F9BF> 1F9C0;ID # So CHEESE WEDGE +1F9C1..1F9CF;ID # Cn [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9D0;ID # So FACE WITH MONOCLE +1F9D1..1F9DD;EB # So [13] ADULT..ELF +1F9DE..1F9E6;ID # So [9] GENIE..SOCKS +1F9E7..1FFFD;ID # Cn [1559] <reserved-1F9E7>..<reserved-1FFFD> 20000..2A6D6;ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF;ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734;ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -3106,7 +3313,9 @@ FFFD;AI # So REPLACEMENT CHARACTER 2B740..2B81D;ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F;ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1;ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF;ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF;ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0;ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF;ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D;ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD;ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD;ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> diff --git a/gnu/usr.bin/perl/lib/unicore/NameAliases.txt b/gnu/usr.bin/perl/lib/unicore/NameAliases.txt index a59698a35ea..f4ba3caee5f 100644 --- a/gnu/usr.bin/perl/lib/unicore/NameAliases.txt +++ b/gnu/usr.bin/perl/lib/unicore/NameAliases.txt @@ -1,12 +1,14 @@ -# NameAliases-8.0.0.txt -# Date: 2014-11-19, 01:30:00 GMT [KW, LI] +# NameAliases-10.0.0.txt +# Date: 2017-05-06, 18:10:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 2005-2014 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # This file defines the formal name aliases for Unicode characters. # # For informative aliases, see NamesList.txt @@ -260,6 +262,10 @@ 0EA3;LAO LETTER RO;correction 0EA5;LAO LETTER LO;correction 0FD0;TIBETAN MARK BKA- SHOG GI MGO RGYAN;correction +11EC;HANGUL JONGSEONG YESIEUNG-KIYEOK;correction +11ED;HANGUL JONGSEONG YESIEUNG-SSANGKIYEOK;correction +11EE;HANGUL JONGSEONG SSANGYESIEUNG;correction +11EF;HANGUL JONGSEONG YESIEUNG-KHIEUKH;correction 180B;FVS1;abbreviation 180C;FVS2;abbreviation 180D;FVS3;abbreviation @@ -287,7 +293,6 @@ 2B7A;LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction 2B7C;RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE;correction A015;YI SYLLABLE ITERATION MARK;correction -FE18;PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET;correction FE00;VS1;abbreviation FE01;VS2;abbreviation FE02;VS3;abbreviation @@ -304,11 +309,13 @@ FE0C;VS13;abbreviation FE0D;VS14;abbreviation FE0E;VS15;abbreviation FE0F;VS16;abbreviation +FE18;PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRACKET;correction FEFF;BYTE ORDER MARK;alternate FEFF;BOM;abbreviation FEFF;ZWNBSP;abbreviation 122D4;CUNEIFORM SIGN NU11 TENU;correction 122D5;CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR;correction +1B001;HENTAIGANA LETTER E-1;correction 1D0C5;BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS;correction E0100;VS17;abbreviation E0101;VS18;abbreviation diff --git a/gnu/usr.bin/perl/lib/unicore/NamedSequences.txt b/gnu/usr.bin/perl/lib/unicore/NamedSequences.txt index b1bfc2f0a31..a315b42f5d0 100644 --- a/gnu/usr.bin/perl/lib/unicore/NamedSequences.txt +++ b/gnu/usr.bin/perl/lib/unicore/NamedSequences.txt @@ -1,14 +1,16 @@ -# NamedSequences-8.0.0.txt -# Date: 2015-02-19, 00:30:00 GMT [KW, LI] +# NamedSequences-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # Unicode Named Character Sequences # # This file is a normative contributory data file in the Unicode # Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # Format: # Name of Sequence; Code Point Sequence for USI # @@ -35,6 +37,28 @@ # ================================================ +# Named keycap sequences for telephone keypad (used for emoji) +# Provisional, 2015-05-05 +# FE0F added to the sequences, 2016-05-11 +# Approved 2017-05-12 + +KEYCAP NUMBER SIGN;0023 FE0F 20E3 +KEYCAP ASTERISK;002A FE0F 20E3 +KEYCAP DIGIT ZERO;0030 FE0F 20E3 +KEYCAP DIGIT ONE;0031 FE0F 20E3 +KEYCAP DIGIT TWO;0032 FE0F 20E3 +KEYCAP DIGIT THREE;0033 FE0F 20E3 +KEYCAP DIGIT FOUR;0034 FE0F 20E3 +KEYCAP DIGIT FIVE;0035 FE0F 20E3 +KEYCAP DIGIT SIX;0036 FE0F 20E3 +KEYCAP DIGIT SEVEN;0037 FE0F 20E3 +KEYCAP DIGIT EIGHT;0038 FE0F 20E3 +KEYCAP DIGIT NINE;0039 FE0F 20E3 + +# Latin letter plus accent combinations. +# These are part of the original set of approved named sequences +# for Unicode 4.1. 2005. + LATIN CAPITAL LETTER A WITH MACRON AND GRAVE;0100 0300 LATIN SMALL LETTER A WITH MACRON AND GRAVE;0101 0300 LATIN CAPITAL LETTER E WITH VERTICAL LINE BELOW;0045 0329 @@ -463,7 +487,16 @@ SINHALA CONSONANT SIGN YANSAYA;0DCA 200D 0DBA SINHALA CONSONANT SIGN RAKAARAANSAYA;0DCA 200D 0DBB SINHALA CONSONANT SIGN REPAYA;0DBB 0DCA 200D +# Georgian letter plus accent sequence. +# This is part of the original set of approved named sequences +# for Unicode 4.1. 2005. + GEORGIAN LETTER U-BRJGU;10E3 0302 + +# Khmer subjoined forms and other sequences. +# These are part of the original set of approved named sequences +# for Unicode 4.1. 2005. + KHMER CONSONANT SIGN COENG KA;17D2 1780 KHMER CONSONANT SIGN COENG KHA;17D2 1781 KHMER CONSONANT SIGN COENG KO;17D2 1782 @@ -508,6 +541,9 @@ KHMER VOWEL SIGN AAM;17B6 17C6 # Entries for JIS X 0213 compatibility mapping. # Provisional 2008-11-07, Approved 2010-05-14 +# +# Two of these were part of the original set of approved named sequences +# for Unicode 4.1. 2005. HIRAGANA LETTER BIDAKUON NGA;304B 309A HIRAGANA LETTER BIDAKUON NGI;304D 309A diff --git a/gnu/usr.bin/perl/lib/unicore/NamedSqProv.txt b/gnu/usr.bin/perl/lib/unicore/NamedSqProv.txt index cc1d5e8a3b1..707341773be 100644 --- a/gnu/usr.bin/perl/lib/unicore/NamedSqProv.txt +++ b/gnu/usr.bin/perl/lib/unicore/NamedSqProv.txt @@ -1,5 +1,10 @@ -# NamedSequencesProv-8.0.0.txt -# Date: 2015-05-11, 23:40:00 GMT [KW, LI] +# NamedSequencesProv-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # Provisional Unicode Named Character Sequences # @@ -7,9 +12,6 @@ # sequences which have been designated to be provisional, # rather than fully approved. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # Format: # Name of Sequence; Code Point Sequence for USI # @@ -24,7 +26,7 @@ # in this data file, would correspond to an ISO/IEC 10646 USI # as follows: # -# <1000, 1001, 1002> +# <1000, 1001, 1002> # # For more information, see UAX #34: Unicode Named Character # Sequences, at http://www.unicode.org/unicode/reports/tr34/ @@ -38,21 +40,7 @@ # Provisional entries for NamedSequences.txt. -# Named keycap sequences for telephone keypad (used for emoji) -# Added to provisional named sequences, 2015-05-05 - -KEYCAP NUMBER SIGN;0023 20E3 -KEYCAP ASTERISK;002A 20E3 -KEYCAP DIGIT ZERO;0030 20E3 -KEYCAP DIGIT ONE;0031 20E3 -KEYCAP DIGIT TWO;0032 20E3 -KEYCAP DIGIT THREE;0033 20E3 -KEYCAP DIGIT FOUR;0034 20E3 -KEYCAP DIGIT FIVE;0035 20E3 -KEYCAP DIGIT SIX;0036 20E3 -KEYCAP DIGIT SEVEN;0037 20E3 -KEYCAP DIGIT EIGHT;0038 20E3 -KEYCAP DIGIT NINE;0039 20E3 +# Currently there are no provisional entries. # ================================================ @@ -64,7 +52,7 @@ KEYCAP DIGIT NINE;0039 20E3 # GURMUKHI PARI YA;0A4D 0A2F # Entry removed 2006-05-18: -# +# # LATIN SMALL LETTER A WITH ACUTE AND OGONEK;00E1 0328 # # This entry was removed because the sequence was not in NFC, diff --git a/gnu/usr.bin/perl/lib/unicore/NamesList.txt b/gnu/usr.bin/perl/lib/unicore/NamesList.txt index 2f84c230fe3..ebfd9391906 100644 --- a/gnu/usr.bin/perl/lib/unicore/NamesList.txt +++ b/gnu/usr.bin/perl/lib/unicore/NamesList.txt @@ -1,14 +1,14 @@ ; charset=UTF-8 -@@@ The Unicode Standard 8.0.0 -@@@+ U80M150527.lst - Unicode 8.0.0 final names list. +@@@ The Unicode Standard 10.0.0 +@@@+ U10M170525.lst + Unicode 10.0.0 final names list. This file is semi-automatically derived from UnicodeData.txt and a set of manually created annotations using a script to select or suppress information from the data file. The rules used for this process are aimed at readability for the human reader, at the expense of some details; therefore, this file should not be parsed for machine-readable information. -@+ Copyright (c) 1991-2015 Unicode, Inc. +@+ © 2017 Unicode®, Inc. For terms of use, see http://www.unicode.org/terms_of_use.html @@ 0000 C0 Controls and Basic Latin (Basic Latin) 007F @@+ @@ -121,8 +121,6 @@ x (l b bar symbol - 2114) x (viewdata square - 2317) x (music sharp sign - 266F) - ~ 0023 FE0E text style - ~ 0023 FE0F emoji style 0024 DOLLAR SIGN = milréis, escudo * used for many peso currencies in Latin America and elsewhere @@ -198,35 +196,16 @@ x (division slash - 2215) @ ASCII digits 0030 DIGIT ZERO - ~ 0030 FE0E text style - ~ 0030 FE0F emoji style + ~ 0030 FE00 short diagonal stroke form 0031 DIGIT ONE - ~ 0031 FE0E text style - ~ 0031 FE0F emoji style 0032 DIGIT TWO - ~ 0032 FE0E text style - ~ 0032 FE0F emoji style 0033 DIGIT THREE - ~ 0033 FE0E text style - ~ 0033 FE0F emoji style 0034 DIGIT FOUR - ~ 0034 FE0E text style - ~ 0034 FE0F emoji style 0035 DIGIT FIVE - ~ 0035 FE0E text style - ~ 0035 FE0F emoji style 0036 DIGIT SIX - ~ 0036 FE0E text style - ~ 0036 FE0F emoji style 0037 DIGIT SEVEN - ~ 0037 FE0E text style - ~ 0037 FE0F emoji style 0038 DIGIT EIGHT - ~ 0038 FE0E text style - ~ 0038 FE0F emoji style 0039 DIGIT NINE - ~ 0039 FE0E text style - ~ 0039 FE0F emoji style @ ASCII punctuation and symbols 003A COLON * also used to denote division or scale; for that mathematical use 2236 is preferred @@ -503,7 +482,7 @@ x (turkish lira sign - 20BA) x (roman semuncia sign - 10192) 00A4 CURRENCY SIGN - * other currency symbol characters: 20A0-20BA + * other currency symbol characters: 20A0-20BF x (dollar sign - 0024) 00A5 YEN SIGN = yuan sign @@ -520,8 +499,6 @@ 00A9 COPYRIGHT SIGN x (sound recording copyright - 2117) x (circled latin capital letter c - 24B8) - ~ 00A9 FE0E text style - ~ 00A9 FE0F emoji style 00AA FEMININE ORDINAL INDICATOR * Spanish # <super> 0061 @@ -540,8 +517,6 @@ 00AE REGISTERED SIGN = registered trade mark sign (1.0) x (circled latin capital letter r - 24C7) - ~ 00AE FE0E text style - ~ 00AE FE0F emoji style 00AF MACRON = overline, APL overbar * this is a spacing character @@ -614,16 +589,15 @@ * usually closing, sometimes opening x (much greater-than - 226B) x (right double angle bracket - 300B) +@ Vulgar fractions +@+ The fraction bar for these may be rendered horizontally or at a slant. For other fraction characters, see 2150-215E. 00BC VULGAR FRACTION ONE QUARTER - * bar may be horizontal or slanted - * other fraction characters: 2153-215E # <fraction> 0031 2044 0034 00BD VULGAR FRACTION ONE HALF - * bar may be horizontal or slanted # <fraction> 0031 2044 0032 00BE VULGAR FRACTION THREE QUARTERS - * bar may be horizontal or slanted # <fraction> 0033 2044 0034 +@ Punctuation 00BF INVERTED QUESTION MARK = turned question mark * Spanish @@ -644,7 +618,7 @@ x (angstrom sign - 212B) : 0041 030A 00C6 LATIN CAPITAL LETTER AE - = latin capital ligature ae (1.0) + = latin capital ligature ae (1.1) 00C7 LATIN CAPITAL LETTER C WITH CEDILLA : 0043 0327 00C8 LATIN CAPITAL LETTER E WITH GRAVE @@ -664,7 +638,7 @@ 00CF LATIN CAPITAL LETTER I WITH DIAERESIS : 0049 0308 00D0 LATIN CAPITAL LETTER ETH - x (latin small letter eth - 00F0) + * lowercase is 00F0 x (latin capital letter d with stroke - 0110) x (latin capital letter african d - 0189) 00D1 LATIN CAPITAL LETTER N WITH TILDE @@ -702,9 +676,9 @@ = Eszett * German * uppercase is "SS" + * nonstandard uppercase is 1E9E * typographically the glyph for this character can be based on a ligature of 017F with either 0073 or with an old-style glyph for 007A (the latter similar in appearance to 0292). Both forms exist interchangeably today. x (greek small letter beta - 03B2) - x (latin capital letter sharp s - 1E9E) 00E0 LATIN SMALL LETTER A WITH GRAVE : 0061 0300 00E1 LATIN SMALL LETTER A WITH ACUTE @@ -720,7 +694,7 @@ * Danish, Norwegian, Swedish, Walloon : 0061 030A 00E6 LATIN SMALL LETTER AE - = latin small ligature ae (1.0) + = latin small ligature ae (1.1) = ash (from Old English æsc) * Danish, Norwegian, Icelandic, Faroese, Old English, French, IPA x (latin small ligature oe - 0153) @@ -746,7 +720,7 @@ : 0069 0308 00F0 LATIN SMALL LETTER ETH * Icelandic, Faroese, Old English, IPA - x (latin capital letter eth - 00D0) + * uppercase is 00D0 x (greek small letter delta - 03B4) x (partial differential - 2202) 00F1 LATIN SMALL LETTER N WITH TILDE @@ -796,9 +770,8 @@ x (runic letter thurisaz thurs thorn - 16A6) 00FF LATIN SMALL LETTER Y WITH DIAERESIS * French, medieval Hungarian orthography - x (latin capital letter y with diaeresis - 0178) + * uppercase is 0178 : 0079 0308 -@~ ! @@ 0100 Latin Extended-A 017F @ European Latin 0100 LATIN CAPITAL LETTER A WITH MACRON @@ -1133,7 +1106,7 @@ : 0079 0302 0178 LATIN CAPITAL LETTER Y WITH DIAERESIS * French, Igbo - x (latin small letter y with diaeresis - 00FF) + * lowercase is 00FF : 0059 0308 0179 LATIN CAPITAL LETTER Z WITH ACUTE : 005A 0301 @@ -1665,30 +1638,33 @@ 0234 LATIN SMALL LETTER L WITH CURL 0235 LATIN SMALL LETTER N WITH CURL 0236 LATIN SMALL LETTER T WITH CURL -@ Miscellaneous additions +@ Miscellaneous addition 0237 LATIN SMALL LETTER DOTLESS J x (mathematical italic small dotless j - 1D6A5) +@ Additions for Africanist linguistics 0238 LATIN SMALL LETTER DB DIGRAPH - * used in Africanist linguistics 0239 LATIN SMALL LETTER QP DIGRAPH - * used in Africanist linguistics +@ Additions for Sencoten 023A LATIN CAPITAL LETTER A WITH STROKE - * Sencoten * lowercase is 2C65 023B LATIN CAPITAL LETTER C WITH STROKE - * Sencoten 023C LATIN SMALL LETTER C WITH STROKE - * used in Americanist linguistics + * also used in Americanist linguistics 023D LATIN CAPITAL LETTER L WITH BAR - * Sencoten * lowercase is 019A 023E LATIN CAPITAL LETTER T WITH DIAGONAL STROKE - * Sencoten * lowercase is 2C66 +@ Additions for Africanist linguistics +@+ These letters were used in a Shona orthography from 1931 to 1955. 023F LATIN SMALL LETTER S WITH SWASH TAIL + * voiceless labio-alveolar fricative * uppercase is 2C7E + x (latin small letter s with hook - 0282) 0240 LATIN SMALL LETTER Z WITH SWASH TAIL + * voiced labio-alveolar fricative * uppercase is 2C7F + x (latin small letter z with retroflex hook - 0290) +@ Miscellaneous additions 0241 LATIN CAPITAL LETTER GLOTTAL STOP 0242 LATIN SMALL LETTER GLOTTAL STOP * casing use in Chipewyan, Dogrib, Slavey (Canadian aboriginal orthographies) @@ -1826,7 +1802,8 @@ 026A LATIN LETTER SMALL CAPITAL I * semi-high front unrounded vowel * preferred IPA alternate for 0269 - * uppercase is 0197 + * uppercase is A7AE + * glyph should have top and bottom serifs even in sans serif IPA font designs, to avoid confusion with lowercase l 026B LATIN SMALL LETTER L WITH MIDDLE TILDE * velarized voiced alveolar lateral approximant * uppercase is 2C62 @@ -2287,6 +2264,7 @@ 02F1 MODIFIER LETTER LOW LEFT ARROWHEAD 02F2 MODIFIER LETTER LOW RIGHT ARROWHEAD 02F3 MODIFIER LETTER LOW RING + x (combining ring below - 0325) 02F4 MODIFIER LETTER MIDDLE GRAVE ACCENT 02F5 MODIFIER LETTER MIDDLE DOUBLE GRAVE ACCENT 02F6 MODIFIER LETTER MIDDLE DOUBLE ACUTE ACCENT @@ -2374,6 +2352,7 @@ 0310 COMBINING CANDRABINDU x (devanagari sign candrabindu - 0901) 0311 COMBINING INVERTED BREVE + x (combining cyrillic palatalization - 0484) x (combining cyrillic pokrytie - 0487) 0312 COMBINING TURNED COMMA ABOVE = cedilla above @@ -2435,6 +2414,7 @@ * IPA: voiceless * vocalic (in Latin transliteration of Indic sonorants) * Madurese + x (modifier letter low ring - 02F3) 0326 COMBINING COMMA BELOW * Romanian, Latvian, Livonian 0327 COMBINING CEDILLA @@ -2492,8 +2472,13 @@ @ Additions 0339 COMBINING RIGHT HALF RING BELOW 033A COMBINING INVERTED BRIDGE BELOW + * IPA: apical + x (combining wide inverted bridge below - 1DF9) 033B COMBINING SQUARE BELOW + * IPA: laminal + * preferred glyph shape is a horizontal rectangle for IPA usage 033C COMBINING SEAGULL BELOW + * IPA: linguolabial 033D COMBINING X ABOVE 033E COMBINING VERTICAL TILDE = yerik @@ -2564,12 +2549,13 @@ @ Miscellaneous additions 0358 COMBINING DOT ABOVE RIGHT * Latin transliterations of the Southern Min dialects of Chinese + x (combining dot above left - 1DF8) 0359 COMBINING ASTERISK BELOW x (low asterisk - 204E) 035A COMBINING DOUBLE RING BELOW * Kharoshthi transliteration 035B COMBINING ZIGZAG ABOVE - * Latin abbreviation, Lithuanian phonetics and mediaevalist transcriptions + * Latin abbreviation, Lithuanian phonetics and medievalist transcriptions @ Double diacritics 035C COMBINING DOUBLE BREVE BELOW = ligature tie below, papyrological hyphen @@ -2602,6 +2588,7 @@ 036E COMBINING LATIN SMALL LETTER V 036F COMBINING LATIN SMALL LETTER X @@ 0370 Greek and Coptic 03FF +@+ Casing relationships between Greek letters are complex and not self-evident from inspection of the charts. See the core specification for details. @ Archaic letters 0370 GREEK CAPITAL LETTER HETA x (latin capital letter half h - 2C75) @@ -2647,6 +2634,7 @@ x (combining vertical line above - 030D) # 0020 0301 0385 GREEK DIALYTIKA TONOS + * compatibility decomposition (NFKD) is 0020 0308 0301 : 00A8 0301 @ Letter 0386 GREEK CAPITAL LETTER ALPHA WITH TONOS @@ -3081,14 +3069,16 @@ : 0474 030F 0477 CYRILLIC SMALL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT : 0475 030F +@ Historic digraphs +@+ These characters may be rendered as either digraph or monograph forms, with preferred alternative representations. 0478 CYRILLIC CAPITAL LETTER UK - * may be rendered as either monograph or digraph form - * for "digraph uk" the preferred spelling is 041E 0443 + * for "digraph onik" the preferred spelling is 041E 0443 * for "monograph uk" the preferred character is A64A x (cyrillic capital letter u - 0423) 0479 CYRILLIC SMALL LETTER UK - * for "digraph uk" the preferred spelling is 043E 0443 + * for "digraph onik" the preferred spelling is 043E 0443 * for "monograph uk" the preferred character is A64B +@ Historic letters 047A CYRILLIC CAPITAL LETTER ROUND OMEGA 047B CYRILLIC SMALL LETTER ROUND OMEGA 047C CYRILLIC CAPITAL LETTER OMEGA WITH TITLO @@ -3096,6 +3086,7 @@ * despite its name, this character does not have a titlo, nor is it composed of an omega plus a diacritic x (cyrillic capital letter broad omega - A64C) 047D CYRILLIC SMALL LETTER OMEGA WITH TITLO + x (greek small letter omega with psili and perispomeni - 1F66) 047E CYRILLIC CAPITAL LETTER OT 047F CYRILLIC SMALL LETTER OT 0480 CYRILLIC CAPITAL LETTER KOPPA @@ -3103,16 +3094,18 @@ @ Historic miscellaneous 0482 CYRILLIC THOUSANDS SIGN 0483 COMBINING CYRILLIC TITLO - * not used with letter titlos + * not used with titlo letters x (combining cyrillic vzmet - A66F) 0484 COMBINING CYRILLIC PALATALIZATION - x (combining vertical tilde - 033E) + * not used for kamora + x (modifier letter apostrophe - 02BC) + x (combining inverted breve - 0311) 0485 COMBINING CYRILLIC DASIA PNEUMATA x (combining reversed comma above - 0314) 0486 COMBINING CYRILLIC PSILI PNEUMATA x (combining comma above - 0313) 0487 COMBINING CYRILLIC POKRYTIE - * used only with letter titlos + * used only with titlo letters * also attested in Glagolitic x (combining inverted breve - 0311) x (combining cyrillic vzmet - A66F) @@ -3164,6 +3157,7 @@ 04A4 CYRILLIC CAPITAL LIGATURE EN GHE 04A5 CYRILLIC SMALL LIGATURE EN GHE * Altay, Mari, Yakut + * also used for soft en in Old Church Slavonic * this is not a decomposable ligature 04A6 CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK 04A7 CYRILLIC SMALL LETTER PE WITH MIDDLE HOOK @@ -3867,7 +3861,7 @@ @ Archaic letters 066E ARABIC LETTER DOTLESS BEH 066F ARABIC LETTER DOTLESS QAF -@ Point +@ Tashkil 0670 ARABIC LETTER SUPERSCRIPT ALEF * actually a vowel sign, despite the name @ Extended Arabic letters @@ -4184,6 +4178,7 @@ 0709 SYRIAC SUBLINEAR COLON SKEWED RIGHT % SYRIAC SUBLINEAR COLON SKEWED LEFT * marks the end of a real or rhetorical question + * character name is a misnomer 070A SYRIAC CONTRACTION * a contraction mark, mostly used in East Syriac * placed at the end of an incomplete word @@ -4469,10 +4464,13 @@ 07EF NKO COMBINING LONG HIGH TONE 07F0 NKO COMBINING LONG LOW TONE 07F1 NKO COMBINING LONG RISING TONE +@ Other diacritics 07F2 NKO COMBINING NASALIZATION MARK x (combining dot below - 0323) 07F3 NKO COMBINING DOUBLE DOT ABOVE x (combining diaeresis - 0308) +@ Tonal apostrophes +@+ These apostrophes mark elision of a vowel while preserving the tonal information of the syllable. 07F4 NKO HIGH TONE APOSTROPHE x (modifier letter apostrophe - 02BC) 07F5 NKO LOW TONE APOSTROPHE @@ -4611,8 +4609,33 @@ 085B MANDAIC GEMINATION MARK @ Punctuation 085E MANDAIC PUNCTUATION +@@ 0860 Syriac Supplement 086F +@ Syriac letters +@+ Used for writing Suriyani Malayalam, which is also known as Garshuni (Karshoni) and Syriac Malayalam. +0860 SYRIAC LETTER MALAYALAM NGA + x (malayalam letter nga - 0D19) +0861 SYRIAC LETTER MALAYALAM JA + x (malayalam letter ja - 0D1C) +0862 SYRIAC LETTER MALAYALAM NYA + x (malayalam letter nya - 0D1E) +0863 SYRIAC LETTER MALAYALAM TTA + x (malayalam letter tta - 0D1F) +0864 SYRIAC LETTER MALAYALAM NNA + x (malayalam letter nna - 0D23) +0865 SYRIAC LETTER MALAYALAM NNNA + x (malayalam letter nnna - 0D29) +0866 SYRIAC LETTER MALAYALAM BHA + x (malayalam letter bha - 0D2D) +0867 SYRIAC LETTER MALAYALAM RA + x (malayalam letter ra - 0D30) +0868 SYRIAC LETTER MALAYALAM LLA + x (malayalam letter lla - 0D33) +0869 SYRIAC LETTER MALAYALAM LLLA + x (malayalam letter llla - 0D34) +086A SYRIAC LETTER MALAYALAM SSA + x (malayalam letter ssa - 0D37) @@ 08A0 Arabic Extended-A 08FF -@ Extended Arabic letters for African languages +@ Arabic letters for African languages 08A0 ARABIC LETTER BEH WITH SMALL V BELOW 08A1 ARABIC LETTER BEH WITH HAMZA ABOVE * Adamawa Fulfulde (Cameroon) @@ -4647,7 +4670,7 @@ 08AF ARABIC LETTER SAD WITH THREE DOTS BELOW * Belarusian 08B0 ARABIC LETTER GAF WITH INVERTED STROKE - * Crimean Tatar, Chechen, Lak + * Crimean Tatar, Chechen, Lak 08B1 ARABIC LETTER STRAIGHT WAW * Tatar @ Arabic letter for Berber @@ -4655,6 +4678,42 @@ @ Arabic letters for Arwi 08B3 ARABIC LETTER AIN WITH THREE DOTS BELOW 08B4 ARABIC LETTER KAF WITH DOT BELOW +@ Arabic letters for Bravanese +08B6 ARABIC LETTER BEH WITH SMALL MEEM ABOVE +08B7 ARABIC LETTER PEH WITH SMALL MEEM ABOVE +08B8 ARABIC LETTER TEH WITH SMALL TEH ABOVE +08B9 ARABIC LETTER REH WITH SMALL NOON ABOVE +08BA ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE +@ Arabic letters for Warsh orthography +@+ The Warsh orthography is the most widespread tradition for the Arabic script in North and West Africa. +08BB ARABIC LETTER AFRICAN FEH + * initial and medial forms have one dot below + x (arabic letter dotless feh - 06A1) + x (arabic letter feh with dot moved below - 06A2) +08BC ARABIC LETTER AFRICAN QAF + * initial and medial forms have one dot above + x (arabic letter dotless qaf - 066F) + x (arabic letter qaf with dot above - 06A7) +08BD ARABIC LETTER AFRICAN NOON + * initial and medial forms have one dot above + x (arabic letter noon ghunna - 06BA) + x (arabic letter noon - 0646) +@ Pakistani Quranic marks +08D4 ARABIC SMALL HIGH WORD AR-RUB +08D5 ARABIC SMALL HIGH SAD +08D6 ARABIC SMALL HIGH AIN +08D7 ARABIC SMALL HIGH QAF +08D8 ARABIC SMALL HIGH NOON WITH KASRA +08D9 ARABIC SMALL LOW NOON WITH KASRA +08DA ARABIC SMALL HIGH WORD ATH-THALATHA +08DB ARABIC SMALL HIGH WORD AS-SAJDA +08DC ARABIC SMALL HIGH WORD AN-NISF +08DD ARABIC SMALL HIGH WORD SAKTA +08DE ARABIC SMALL HIGH WORD QIF +08DF ARABIC SMALL HIGH WORD WAQFA +08E0 ARABIC SMALL HIGH FOOTNOTE MARKER +08E1 ARABIC SMALL HIGH SIGN SAFHA +08E2 ARABIC DISPUTED END OF AYAH @ Extended vowel sign for Arwi 08E3 ARABIC TURNED DAMMA BELOW @ Extended vowel signs for Rohingya @@ -4671,7 +4730,7 @@ 08ED ARABIC TONE ONE DOT BELOW 08EE ARABIC TONE TWO DOTS BELOW 08EF ARABIC TONE LOOP BELOW -@ Koranic annotation signs +@ Quranic annotation signs 08F0 ARABIC OPEN FATHATAN = successive fathatan 08F1 ARABIC OPEN DAMMATAN @@ -4868,6 +4927,7 @@ = deergh viram @ Digits 0966 DEVANAGARI DIGIT ZERO + * also used to represent an anusvara following digits indicating secondary svara-s in Samavedic texts 0967 DEVANAGARI DIGIT ONE 0968 DEVANAGARI DIGIT TWO 0969 DEVANAGARI DIGIT THREE @@ -5055,6 +5115,9 @@ * written before the name of a deceased person @ Historic currency sign 09FB BENGALI GANDA MARK +@ Signs +09FC BENGALI LETTER VEDIC ANUSVARA +09FD BENGALI ABBREVIATION SIGN @@ 0A00 Gurmukhi 0A7F @ Various signs 0A01 GURMUKHI SIGN ADAK BINDI @@ -5175,6 +5238,7 @@ 0A74 GURMUKHI EK ONKAR * God is One 0A75 GURMUKHI SIGN YAKASH + * some fonts use an alternate glyph shaped more like the lower part of 0A2F @@ 0A80 Gujarati 0AFF @ Various signs 0A81 GUJARATI SIGN CANDRABINDU @@ -5285,6 +5349,14 @@ 0AF9 GUJARATI LETTER ZHA * used in transliteration of Avestan x (devanagari letter zha - 0979) +@ Transliteration signs +@+ Used for the transliteration of the Arabic script into Gujarati by Ismaili Khoja communities. +0AFA GUJARATI SIGN SUKUN +0AFB GUJARATI SIGN SHADDA +0AFC GUJARATI SIGN MADDAH +0AFD GUJARATI SIGN THREE-DOT NUKTA ABOVE +0AFE GUJARATI SIGN CIRCLE NUKTA ABOVE +0AFF GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE @@ 0B00 Oriya 0B7F @+ As of 2012, the name "Oriya" for this script and language is officially spelled "Odia" in India. That change in spelling does not affect the Unicode block or character names, which are constrained by stability guarantees. @ Various signs @@ -5666,6 +5738,7 @@ 0C7F TELUGU SIGN TUUMU @@ 0C80 Kannada 0CFF @ Various signs +0C80 KANNADA SIGN SPACING CANDRABINDU 0C81 KANNADA SIGN CANDRABINDU 0C82 KANNADA SIGN ANUSVARA 0C83 KANNADA SIGN VISARGA @@ -5783,8 +5856,10 @@ x (vedic sign upadhmaniya - 1CF6) @@ 0D00 Malayalam 0D7F @ Various signs +0D00 MALAYALAM SIGN COMBINING ANUSVARA ABOVE 0D01 MALAYALAM SIGN CANDRABINDU 0D02 MALAYALAM SIGN ANUSVARA + * used in Prakrit language texts to indicate gemination of the following consonant 0D03 MALAYALAM SIGN VISARGA @ Independent vowels 0D05 MALAYALAM LETTER A @@ -5859,6 +5934,9 @@ 0D39 MALAYALAM LETTER HA 0D3A MALAYALAM LETTER TTTA * historic use only +@ Variant shape viramas +0D3B MALAYALAM SIGN VERTICAL BAR VIRAMA +0D3C MALAYALAM SIGN CIRCULAR VIRAMA @ Addition for Sanskrit 0D3D MALAYALAM SIGN AVAGRAHA = praslesham @@ -5893,10 +5971,34 @@ @ Dot reph 0D4E MALAYALAM LETTER DOT REPH * not used in reformed modern Malayalam orthography -@ Various signs +@ Measurement symbol +0D4F MALAYALAM SIGN PARA + * used historically to measure rice +@ Chillu letters +0D54 MALAYALAM LETTER CHILLU M +0D55 MALAYALAM LETTER CHILLU Y +0D56 MALAYALAM LETTER CHILLU LLL +@ Dependent vowel sign 0D57 MALAYALAM AU LENGTH MARK * used alone to write the /au/ dependent vowel in modern texts x (malayalam vowel sign au - 0D4C) +@ Minor fractions +@+ Some minor fractions are represented by letters. +@+ The fraction one three-hundred and twentieth "muntiri" is denoted by the syllable "pta" (0D2A 0D4D 0D24). +0D58 MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH + = arakaani +0D59 MALAYALAM FRACTION ONE FORTIETH + = aramaa +0D5A MALAYALAM FRACTION THREE EIGHTIETHS + = muunnukaani +0D5B MALAYALAM FRACTION ONE TWENTIETH + = orumaa +0D5C MALAYALAM FRACTION ONE TENTH + = rantumaa +0D5D MALAYALAM FRACTION THREE TWENTIETHS + = muunnumaa +0D5E MALAYALAM FRACTION ONE FIFTH + = naalumaa @ Additional historic vowel 0D5F MALAYALAM LETTER ARCHAIC II @ Additional vowels for Sanskrit @@ -5933,6 +6035,12 @@ = ara 0D75 MALAYALAM FRACTION THREE QUARTERS = mukkaal +0D76 MALAYALAM FRACTION ONE SIXTEENTH + = maakaani +0D77 MALAYALAM FRACTION ONE EIGHTH + = arakkaal +0D78 MALAYALAM FRACTION THREE SIXTEENTHS + = muntaani @ Date mark 0D79 MALAYALAM DATE MARK @ Chillu letters @@ -6753,10 +6861,13 @@ @@ 1000 Myanmar 109F @ Consonants 1000 MYANMAR LETTER KA + ~ 1000 FE00 dotted form 1001 MYANMAR LETTER KHA 1002 MYANMAR LETTER GA + ~ 1002 FE00 dotted form 1003 MYANMAR LETTER GHA 1004 MYANMAR LETTER NGA + ~ 1004 FE00 dotted form 1005 MYANMAR LETTER CA 1006 MYANMAR LETTER CHA 1007 MYANMAR LETTER JA @@ -6769,19 +6880,26 @@ 100E MYANMAR LETTER DDHA 100F MYANMAR LETTER NNA 1010 MYANMAR LETTER TA + ~ 1010 FE00 dotted form 1011 MYANMAR LETTER THA + ~ 1011 FE00 dotted form 1012 MYANMAR LETTER DA 1013 MYANMAR LETTER DHA 1014 MYANMAR LETTER NA 1015 MYANMAR LETTER PA + ~ 1015 FE00 dotted form 1016 MYANMAR LETTER PHA 1017 MYANMAR LETTER BA 1018 MYANMAR LETTER BHA 1019 MYANMAR LETTER MA + ~ 1019 FE00 dotted form 101A MYANMAR LETTER YA + ~ 101A FE00 dotted form 101B MYANMAR LETTER RA 101C MYANMAR LETTER LA + ~ 101C FE00 dotted form 101D MYANMAR LETTER WA + ~ 101D FE00 dotted form 101E MYANMAR LETTER SA 101F MYANMAR LETTER HA 1020 MYANMAR LETTER LLA @@ -6789,6 +6907,7 @@ 1021 MYANMAR LETTER A * also represents the glottal stop as a consonant 1022 MYANMAR LETTER SHAN A + ~ 1022 FE00 dotted form 1023 MYANMAR LETTER I 1024 MYANMAR LETTER II 1025 MYANMAR LETTER U @@ -6807,6 +6926,7 @@ 1030 MYANMAR VOWEL SIGN UU 1031 MYANMAR VOWEL SIGN E * stands to the left of the consonant + ~ 1031 FE00 dotted form 1032 MYANMAR VOWEL SIGN AI 1033 MYANMAR VOWEL SIGN MON II 1034 MYANMAR VOWEL SIGN MON O @@ -6895,17 +7015,21 @@ 1074 MYANMAR VOWEL SIGN KAYAH EE @ Extensions for Shan 1075 MYANMAR LETTER SHAN KA + ~ 1075 FE00 dotted form 1076 MYANMAR LETTER SHAN KHA 1077 MYANMAR LETTER SHAN GA 1078 MYANMAR LETTER SHAN CA + ~ 1078 FE00 dotted form 1079 MYANMAR LETTER SHAN ZA 107A MYANMAR LETTER SHAN NYA + ~ 107A FE00 dotted form 107B MYANMAR LETTER SHAN DA 107C MYANMAR LETTER SHAN NA 107D MYANMAR LETTER SHAN PHA 107E MYANMAR LETTER SHAN FA 107F MYANMAR LETTER SHAN BA 1080 MYANMAR LETTER SHAN THA + ~ 1080 FE00 dotted form 1081 MYANMAR LETTER SHAN HA 1082 MYANMAR CONSONANT SIGN SHAN MEDIAL WA 1083 MYANMAR VOWEL SIGN SHAN AA @@ -6942,6 +7066,7 @@ @ Shan symbols 109E MYANMAR SYMBOL SHAN ONE 109F MYANMAR SYMBOL SHAN EXCLAMATION +@~ ! @@ 10A0 Georgian 10FF @ Capital letters (Khutsuri) @+ This is the uppercase of the old ecclesiastical alphabet. The style shown in the code charts is known as Asomtavruli. See the Georgian Supplement block for lowercase Nuskhuri. @@ -7037,6 +7162,7 @@ 10FA GEORGIAN LETTER AIN @ Punctuation 10FB GEORGIAN PARAGRAPH SEPARATOR + x (three dot punctuation - 2056) @ Modifier letter 10FC MODIFIER LETTER GEORGIAN NAR # <super> 10DC @@ -7377,13 +7503,13 @@ 11EA HANGUL JONGSEONG SIOS-PIEUP 11EB HANGUL JONGSEONG PANSIOS 11EC HANGUL JONGSEONG IEUNG-KIYEOK - = yesieung-kiyeok + % HANGUL JONGSEONG YESIEUNG-KIYEOK 11ED HANGUL JONGSEONG IEUNG-SSANGKIYEOK - = yesieung-ssangkiyeok + % HANGUL JONGSEONG YESIEUNG-SSANGKIYEOK 11EE HANGUL JONGSEONG SSANGIEUNG - = ssangyesieung + % HANGUL JONGSEONG SSANGYESIEUNG 11EF HANGUL JONGSEONG IEUNG-KHIEUKH - = yesieung-khieukh + % HANGUL JONGSEONG YESIEUNG-KHIEUKH 11F0 HANGUL JONGSEONG YESIEUNG 11F1 HANGUL JONGSEONG YESIEUNG-SIOS 11F2 HANGUL JONGSEONG YESIEUNG-PANSIOS @@ -9115,6 +9241,7 @@ @@ 1800 Mongolian 18AF @@+ @ Punctuation +@+ Additional birgas are encoded in the Mongolian Supplement block at 11660-1167F. 1800 MONGOLIAN BIRGA x (tibetan mark initial yig mgo mdun ma - 0F04) 1801 MONGOLIAN ELLIPSIS @@ -9127,9 +9254,11 @@ * not a format control character, but simply a hyphen for Todo x (soft hyphen - 00AD) 1807 MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER + ~ 1807 ALT1 first form (medial) 1808 MONGOLIAN MANCHU COMMA 1809 MONGOLIAN MANCHU FULL STOP 180A MONGOLIAN NIRUGU + ~ 180A ALT1 first form (medial) @ Format controls 180B MONGOLIAN FREE VARIATION SELECTOR ONE * abbreviated FVS1 @@ -9151,211 +9280,482 @@ 1818 MONGOLIAN DIGIT EIGHT 1819 MONGOLIAN DIGIT NINE @ Basic letters +@+ Cross-references show commonly used Cyrillic transliterations. 1820 MONGOLIAN LETTER A x (cyrillic small letter a - 0430) + ~ 1820 ALT1 first form (initial) + ~ 1820 ALT1 first form (medial) + ~ 1820 ALT1 first form (final) ~ 1820 180B second form (isolate) ~ 1820 180B second form (medial) ~ 1820 180B second form (final) ~ 1820 180C third form (medial) 1821 MONGOLIAN LETTER E x (cyrillic small letter e - 044D) + ~ 1821 ALT1 first form (initial) + ~ 1821 ALT1 first form (medial) + ~ 1821 ALT1 first form (final) ~ 1821 180B second form (initial) ~ 1821 180B second form (final) 1822 MONGOLIAN LETTER I x (cyrillic small letter i - 0438) + ~ 1822 ALT1 first form (initial) + ~ 1822 ALT1 first form (medial) + ~ 1822 ALT1 first form (final) ~ 1822 180B second form (medial) 1823 MONGOLIAN LETTER O x (cyrillic small letter o - 043E) + ~ 1823 ALT1 first form (initial) + ~ 1823 ALT1 first form (medial) + ~ 1823 ALT1 first form (final) ~ 1823 180B second form (medial) ~ 1823 180B second form (final) 1824 MONGOLIAN LETTER U x (cyrillic small letter u - 0443) + ~ 1824 ALT1 first form (isolate) + ~ 1824 ALT1 first form (initial) + ~ 1824 ALT1 first form (medial) + ~ 1824 ALT1 first form (final) ~ 1824 180B second form (medial) 1825 MONGOLIAN LETTER OE x (cyrillic small letter barred o - 04E9) + ~ 1825 ALT1 first form (initial) + ~ 1825 ALT1 first form (medial) + ~ 1825 ALT1 first form (final) ~ 1825 180B second form (medial) ~ 1825 180B second form (final) ~ 1825 180C third form (medial) 1826 MONGOLIAN LETTER UE x (cyrillic small letter straight u - 04AF) + ~ 1826 ALT1 first form (isolate) + ~ 1826 ALT1 first form (initial) + ~ 1826 ALT1 first form (medial) + ~ 1826 ALT1 first form (final) ~ 1826 180B second form (isolate) ~ 1826 180B second form (medial) ~ 1826 180B second form (final) ~ 1826 180C third form (medial) 1827 MONGOLIAN LETTER EE + ~ 1827 ALT1 first form (initial) + ~ 1827 ALT1 first form (medial) + ~ 1827 ALT1 first form (final) 1828 MONGOLIAN LETTER NA x (cyrillic small letter en - 043D) + ~ 1828 ALT1 first form (initial) + ~ 1828 ALT1 first form (medial) + ~ 1828 ALT1 first form (final) ~ 1828 180B second form (initial) ~ 1828 180B second form (medial) ~ 1828 180C third form (medial) - ~ 1828 180D separate form (medial) + ~ 1828 180D fourth form (medial) 1829 MONGOLIAN LETTER ANG + ~ 1829 ALT1 first form (initial) + ~ 1829 ALT1 first form (medial) + ~ 1829 ALT1 first form (final) 182A MONGOLIAN LETTER BA x (cyrillic small letter be - 0431) - ~ 182A 180B alternative form (final) + ~ 182A ALT1 first form (initial) + ~ 182A ALT1 first form (medial) + ~ 182A ALT1 first form (final) + ~ 182A 180B second form (final) 182B MONGOLIAN LETTER PA x (cyrillic small letter pe - 043F) + ~ 182B ALT1 first form (initial) + ~ 182B ALT1 first form (medial) + ~ 182B ALT1 first form (final) 182C MONGOLIAN LETTER QA x (cyrillic small letter ha - 0445) + ~ 182C ALT1 first form (initial) + ~ 182C ALT1 first form (medial) + ~ 182C ALT1 first form (final) + ~ 182C 180B second form (isolate) ~ 182C 180B second form (initial) ~ 182C 180B second form (medial) - ~ 182C 180B feminine second form (isolate) ~ 182C 180C third form (medial) ~ 182C 180D fourth form (medial) 182D MONGOLIAN LETTER GA x (cyrillic small letter ghe - 0433) + ~ 182D ALT1 first form (initial) + ~ 182D ALT1 first form (medial) + ~ 182D ALT1 first form (final) ~ 182D 180B second form (initial) ~ 182D 180B second form (medial) - ~ 182D 180B feminine form (final) + ~ 182D 180B second form (final) ~ 182D 180C third form (medial) - ~ 182D 180D feminine form (medial) + ~ 182D 180D fourth form (medial) 182E MONGOLIAN LETTER MA x (cyrillic small letter em - 043C) + ~ 182E ALT1 first form (initial) + ~ 182E ALT1 first form (medial) + ~ 182E ALT1 first form (final) 182F MONGOLIAN LETTER LA x (cyrillic small letter el - 043B) + ~ 182F ALT1 first form (initial) + ~ 182F ALT1 first form (medial) + ~ 182F ALT1 first form (final) 1830 MONGOLIAN LETTER SA x (cyrillic small letter es - 0441) + ~ 1830 ALT1 first form (initial) + ~ 1830 ALT1 first form (medial) + ~ 1830 ALT1 first form (final) ~ 1830 180B second form (final) ~ 1830 180C third form (final) 1831 MONGOLIAN LETTER SHA x (cyrillic small letter sha - 0448) + ~ 1831 ALT1 first form (initial) + ~ 1831 ALT1 first form (medial) + ~ 1831 ALT1 first form (final) 1832 MONGOLIAN LETTER TA x (cyrillic small letter te - 0442) + ~ 1832 ALT1 first form (initial) + ~ 1832 ALT1 first form (medial) + ~ 1832 ALT1 first form (final) ~ 1832 180B second form (medial) 1833 MONGOLIAN LETTER DA x (cyrillic small letter de - 0434) + ~ 1833 ALT1 first form (initial) + ~ 1833 ALT1 first form (medial) + ~ 1833 ALT1 first form (final) ~ 1833 180B second form (initial) ~ 1833 180B second form (medial) ~ 1833 180B second form (final) 1834 MONGOLIAN LETTER CHA x (cyrillic small letter che - 0447) + ~ 1834 ALT1 first form (initial) + ~ 1834 ALT1 first form (medial) + ~ 1834 ALT1 first form (final) 1835 MONGOLIAN LETTER JA x (cyrillic small letter zhe - 0436) + ~ 1835 ALT1 first form (initial) + ~ 1835 ALT1 first form (medial) + ~ 1835 ALT1 first form (final) ~ 1835 180B second form (medial) 1836 MONGOLIAN LETTER YA x (cyrillic small letter short i - 0439) + ~ 1836 ALT1 first form (initial) + ~ 1836 ALT1 first form (medial) + ~ 1836 ALT1 first form (final) ~ 1836 180B second form (initial) ~ 1836 180B second form (medial) ~ 1836 180C third form (medial) 1837 MONGOLIAN LETTER RA x (cyrillic small letter er - 0440) + ~ 1837 ALT1 first form (initial) + ~ 1837 ALT1 first form (medial) + ~ 1837 ALT1 first form (final) 1838 MONGOLIAN LETTER WA x (cyrillic small letter ve - 0432) + ~ 1838 ALT1 first form (initial) + ~ 1838 ALT1 first form (medial) + ~ 1838 ALT1 first form (final) ~ 1838 180B second form (final) 1839 MONGOLIAN LETTER FA x (cyrillic small letter ef - 0444) + ~ 1839 ALT1 first form (initial) + ~ 1839 ALT1 first form (medial) + ~ 1839 ALT1 first form (final) 183A MONGOLIAN LETTER KA x (cyrillic small letter ha - 0445) + ~ 183A ALT1 first form (initial) + ~ 183A ALT1 first form (medial) + ~ 183A ALT1 first form (final) 183B MONGOLIAN LETTER KHA x (cyrillic small letter ka - 043A) + ~ 183B ALT1 first form (initial) + ~ 183B ALT1 first form (medial) + ~ 183B ALT1 first form (final) 183C MONGOLIAN LETTER TSA x (cyrillic small letter tse - 0446) + ~ 183C ALT1 first form (initial) + ~ 183C ALT1 first form (medial) + ~ 183C ALT1 first form (final) 183D MONGOLIAN LETTER ZA x (cyrillic small letter ze - 0437) + ~ 183D ALT1 first form (initial) + ~ 183D ALT1 first form (medial) + ~ 183D ALT1 first form (final) 183E MONGOLIAN LETTER HAA x (cyrillic small letter ha - 0445) + ~ 183E ALT1 first form (initial) + ~ 183E ALT1 first form (medial) + ~ 183E ALT1 first form (final) 183F MONGOLIAN LETTER ZRA x (cyrillic small letter zhe - 0436) + ~ 183F ALT1 first form (initial) + ~ 183F ALT1 first form (medial) + ~ 183F ALT1 first form (final) 1840 MONGOLIAN LETTER LHA + ~ 1840 ALT1 first form (initial) + ~ 1840 ALT1 first form (medial) + ~ 1840 ALT1 first form (final) 1841 MONGOLIAN LETTER ZHI + ~ 1841 ALT1 first form (initial) + ~ 1841 ALT1 first form (medial) + ~ 1841 ALT1 first form (final) 1842 MONGOLIAN LETTER CHI + ~ 1842 ALT1 first form (initial) + ~ 1842 ALT1 first form (medial) + ~ 1842 ALT1 first form (final) @ Todo letters 1843 MONGOLIAN LETTER TODO LONG VOWEL SIGN + ~ 1843 ALT1 first form (initial) + ~ 1843 ALT1 first form (medial) + ~ 1843 ALT1 first form (final) 1844 MONGOLIAN LETTER TODO E + ~ 1844 ALT1 first form (initial) + ~ 1844 ALT1 first form (medial) + ~ 1844 ALT1 first form (final) ~ 1844 180B second form (medial) 1845 MONGOLIAN LETTER TODO I + ~ 1845 ALT1 first form (initial) + ~ 1845 ALT1 first form (medial) + ~ 1845 ALT1 first form (final) ~ 1845 180B second form (medial) 1846 MONGOLIAN LETTER TODO O + ~ 1846 ALT1 first form (initial) + ~ 1846 ALT1 first form (medial) + ~ 1846 ALT1 first form (final) ~ 1846 180B second form (medial) 1847 MONGOLIAN LETTER TODO U + ~ 1847 ALT1 first form (initial) + ~ 1847 ALT1 first form (medial) + ~ 1847 ALT1 first form (final) ~ 1847 180B second form (isolate) ~ 1847 180B second form (medial) ~ 1847 180B second form (final) ~ 1847 180C third form (medial) 1848 MONGOLIAN LETTER TODO OE + ~ 1848 ALT1 first form (initial) + ~ 1848 ALT1 first form (medial) + ~ 1848 ALT1 first form (final) ~ 1848 180B second form (medial) 1849 MONGOLIAN LETTER TODO UE + ~ 1849 ALT1 first form (initial) + ~ 1849 ALT1 first form (medial) + ~ 1849 ALT1 first form (final) ~ 1849 180B second form (isolate) ~ 1849 180B second form (medial) 184A MONGOLIAN LETTER TODO ANG + ~ 184A ALT1 first form (initial) + ~ 184A ALT1 first form (medial) + ~ 184A ALT1 first form (final) 184B MONGOLIAN LETTER TODO BA + ~ 184B ALT1 first form (initial) + ~ 184B ALT1 first form (medial) + ~ 184B ALT1 first form (final) 184C MONGOLIAN LETTER TODO PA + ~ 184C ALT1 first form (initial) + ~ 184C ALT1 first form (medial) + ~ 184C ALT1 first form (final) 184D MONGOLIAN LETTER TODO QA - ~ 184D 180B feminine form (initial) - ~ 184D 180B feminine form (medial) + ~ 184D ALT1 first form (initial) + ~ 184D ALT1 first form (medial) + ~ 184D ALT1 first form (final) + ~ 184D 180B second form (initial) + ~ 184D 180B second form (medial) 184E MONGOLIAN LETTER TODO GA + ~ 184E ALT1 first form (initial) + ~ 184E ALT1 first form (medial) + ~ 184E ALT1 first form (final) ~ 184E 180B second form (medial) 184F MONGOLIAN LETTER TODO MA + ~ 184F ALT1 first form (initial) + ~ 184F ALT1 first form (medial) + ~ 184F ALT1 first form (final) 1850 MONGOLIAN LETTER TODO TA + ~ 1850 ALT1 first form (initial) + ~ 1850 ALT1 first form (medial) + ~ 1850 ALT1 first form (final) 1851 MONGOLIAN LETTER TODO DA + ~ 1851 ALT1 first form (initial) + ~ 1851 ALT1 first form (medial) + ~ 1851 ALT1 first form (final) 1852 MONGOLIAN LETTER TODO CHA + ~ 1852 ALT1 first form (initial) + ~ 1852 ALT1 first form (medial) + ~ 1852 ALT1 first form (final) 1853 MONGOLIAN LETTER TODO JA + ~ 1853 ALT1 first form (initial) + ~ 1853 ALT1 first form (medial) + ~ 1853 ALT1 first form (final) 1854 MONGOLIAN LETTER TODO TSA + ~ 1854 ALT1 first form (initial) + ~ 1854 ALT1 first form (medial) + ~ 1854 ALT1 first form (final) 1855 MONGOLIAN LETTER TODO YA + ~ 1855 ALT1 first form (initial) + ~ 1855 ALT1 first form (medial) + ~ 1855 ALT1 first form (final) 1856 MONGOLIAN LETTER TODO WA + ~ 1856 ALT1 first form (initial) + ~ 1856 ALT1 first form (medial) + ~ 1856 ALT1 first form (final) 1857 MONGOLIAN LETTER TODO KA + ~ 1857 ALT1 first form (initial) + ~ 1857 ALT1 first form (medial) + ~ 1857 ALT1 first form (final) 1858 MONGOLIAN LETTER TODO GAA + ~ 1858 ALT1 first form (initial) + ~ 1858 ALT1 first form (medial) + ~ 1858 ALT1 first form (final) 1859 MONGOLIAN LETTER TODO HAA + ~ 1859 ALT1 first form (initial) + ~ 1859 ALT1 first form (medial) + ~ 1859 ALT1 first form (final) 185A MONGOLIAN LETTER TODO JIA + ~ 185A ALT1 first form (initial) + ~ 185A ALT1 first form (medial) + ~ 185A ALT1 first form (final) 185B MONGOLIAN LETTER TODO NIA + ~ 185B ALT1 first form (initial) + ~ 185B ALT1 first form (medial) + ~ 185B ALT1 first form (final) 185C MONGOLIAN LETTER TODO DZA + ~ 185C ALT1 first form (initial) + ~ 185C ALT1 first form (medial) + ~ 185C ALT1 first form (final) @ Sibe letters 185D MONGOLIAN LETTER SIBE E + ~ 185D ALT1 first form (isolate) + ~ 185D ALT1 first form (initial) + ~ 185D ALT1 first form (medial) + ~ 185D ALT1 first form (final) ~ 185D 180B second form (medial) ~ 185D 180B second form (final) 185E MONGOLIAN LETTER SIBE I + ~ 185E ALT1 first form (isolate) + ~ 185E ALT1 first form (initial) + ~ 185E ALT1 first form (medial) + ~ 185E ALT1 first form (final) ~ 185E 180B second form (medial) ~ 185E 180B second form (final) ~ 185E 180C third form (medial) ~ 185E 180C third form (final) 185F MONGOLIAN LETTER SIBE IY + ~ 185F ALT1 first form (initial) + ~ 185F ALT1 first form (medial) + ~ 185F ALT1 first form (final) 1860 MONGOLIAN LETTER SIBE UE + ~ 1860 ALT1 first form (initial) + ~ 1860 ALT1 first form (medial) + ~ 1860 ALT1 first form (final) ~ 1860 180B second form (medial) ~ 1860 180B second form (final) 1861 MONGOLIAN LETTER SIBE U + ~ 1861 ALT1 first form (isolate) + ~ 1861 ALT1 first form (initial) + ~ 1861 ALT1 first form (medial) + ~ 1861 ALT1 first form (final) 1862 MONGOLIAN LETTER SIBE ANG + ~ 1862 ALT1 first form (initial) + ~ 1862 ALT1 first form (medial) + ~ 1862 ALT1 first form (final) 1863 MONGOLIAN LETTER SIBE KA + ~ 1863 ALT1 first form (initial) + ~ 1863 ALT1 first form (medial) + ~ 1863 ALT1 first form (final) ~ 1863 180B second form (medial) 1864 MONGOLIAN LETTER SIBE GA + ~ 1864 ALT1 first form (initial) + ~ 1864 ALT1 first form (medial) + ~ 1864 ALT1 first form (final) 1865 MONGOLIAN LETTER SIBE HA + ~ 1865 ALT1 first form (initial) + ~ 1865 ALT1 first form (medial) + ~ 1865 ALT1 first form (final) 1866 MONGOLIAN LETTER SIBE PA + ~ 1866 ALT1 first form (initial) + ~ 1866 ALT1 first form (medial) + ~ 1866 ALT1 first form (final) 1867 MONGOLIAN LETTER SIBE SHA + ~ 1867 ALT1 first form (initial) + ~ 1867 ALT1 first form (medial) + ~ 1867 ALT1 first form (final) 1868 MONGOLIAN LETTER SIBE TA + ~ 1868 ALT1 first form (initial) + ~ 1868 ALT1 first form (medial) + ~ 1868 ALT1 first form (final) ~ 1868 180B second form (initial) ~ 1868 180B second form (medial) ~ 1868 180C third form (medial) 1869 MONGOLIAN LETTER SIBE DA + ~ 1869 ALT1 first form (initial) + ~ 1869 ALT1 first form (medial) + ~ 1869 ALT1 first form (final) ~ 1869 180B second form (initial) ~ 1869 180B second form (medial) 186A MONGOLIAN LETTER SIBE JA + ~ 186A ALT1 first form (initial) + ~ 186A ALT1 first form (medial) + ~ 186A ALT1 first form (final) 186B MONGOLIAN LETTER SIBE FA + ~ 186B ALT1 first form (initial) + ~ 186B ALT1 first form (medial) + ~ 186B ALT1 first form (final) 186C MONGOLIAN LETTER SIBE GAA + ~ 186C ALT1 first form (initial) + ~ 186C ALT1 first form (medial) + ~ 186C ALT1 first form (final) 186D MONGOLIAN LETTER SIBE HAA + ~ 186D ALT1 first form (initial) + ~ 186D ALT1 first form (medial) + ~ 186D ALT1 first form (final) 186E MONGOLIAN LETTER SIBE TSA + ~ 186E ALT1 first form (initial) + ~ 186E ALT1 first form (medial) + ~ 186E ALT1 first form (final) 186F MONGOLIAN LETTER SIBE ZA + ~ 186F ALT1 first form (initial) + ~ 186F ALT1 first form (medial) + ~ 186F ALT1 first form (final) ~ 186F 180B second form (initial) ~ 186F 180B second form (medial) 1870 MONGOLIAN LETTER SIBE RAA + ~ 1870 ALT1 first form (initial) + ~ 1870 ALT1 first form (medial) + ~ 1870 ALT1 first form (final) 1871 MONGOLIAN LETTER SIBE CHA + ~ 1871 ALT1 first form (initial) + ~ 1871 ALT1 first form (medial) + ~ 1871 ALT1 first form (final) 1872 MONGOLIAN LETTER SIBE ZHA + ~ 1872 ALT1 first form (initial) + ~ 1872 ALT1 first form (medial) + ~ 1872 ALT1 first form (final) @ Manchu letters 1873 MONGOLIAN LETTER MANCHU I + ~ 1873 ALT1 first form (isolate) + ~ 1873 ALT1 first form (initial) + ~ 1873 ALT1 first form (medial) + ~ 1873 ALT1 first form (final) ~ 1873 180B second form (medial) ~ 1873 180B second form (final) ~ 1873 180C third form (medial) ~ 1873 180C third form (final) ~ 1873 180D fourth form (medial) 1874 MONGOLIAN LETTER MANCHU KA + ~ 1874 ALT1 first form (initial) + ~ 1874 ALT1 first form (medial) + ~ 1874 ALT1 first form (final) ~ 1874 180B second form (medial) - ~ 1874 180B feminine first final form (final) - ~ 1874 180C feminine first medial form (medial) - ~ 1874 180C feminine second final form (final) - ~ 1874 180D feminine second medial form (medial) + ~ 1874 180B second form (final) + ~ 1874 180C third form (medial) + ~ 1874 180C third form (final) + ~ 1874 180D fourth form (medial) 1875 MONGOLIAN LETTER MANCHU RA + ~ 1875 ALT1 first form (initial) + ~ 1875 ALT1 first form (medial) + ~ 1875 ALT1 first form (final) 1876 MONGOLIAN LETTER MANCHU FA + ~ 1876 ALT1 first form (initial) + ~ 1876 ALT1 first form (medial) + ~ 1876 ALT1 first form (final) ~ 1876 180B second form (initial) ~ 1876 180B second form (medial) 1877 MONGOLIAN LETTER MANCHU ZHA + ~ 1877 ALT1 first form (initial) + ~ 1877 ALT1 first form (medial) + ~ 1877 ALT1 first form (final) @ Extensions for Sanskrit and Tibetan 1880 MONGOLIAN LETTER ALI GALI ANUSVARA ONE x (tibetan sign sna ldan - 0F83) @@ -9372,49 +9772,154 @@ x (tibetan mark paluta - 0F85) 1886 MONGOLIAN LETTER ALI GALI THREE BALUDA 1887 MONGOLIAN LETTER ALI GALI A + ~ 1887 ALT1 first form (initial) + ~ 1887 ALT1 first form (medial) + ~ 1887 ALT1 first form (final) ~ 1887 180B second form (isolate) ~ 1887 180B second form (final) ~ 1887 180C third form (final) ~ 1887 180D fourth form (final) 1888 MONGOLIAN LETTER ALI GALI I + ~ 1888 ALT1 first form (initial) + ~ 1888 ALT1 first form (medial) + ~ 1888 ALT1 first form (final) ~ 1888 180B second form (final) 1889 MONGOLIAN LETTER ALI GALI KA + ~ 1889 ALT1 first form (initial) + ~ 1889 ALT1 first form (medial) + ~ 1889 ALT1 first form (final) 188A MONGOLIAN LETTER ALI GALI NGA + ~ 188A ALT1 first form (initial) + ~ 188A ALT1 first form (medial) + ~ 188A ALT1 first form (final) ~ 188A 180B second form (initial) ~ 188A 180B second form (medial) 188B MONGOLIAN LETTER ALI GALI CA + ~ 188B ALT1 first form (initial) + ~ 188B ALT1 first form (medial) + ~ 188B ALT1 first form (final) 188C MONGOLIAN LETTER ALI GALI TTA + ~ 188C ALT1 first form (initial) + ~ 188C ALT1 first form (medial) + ~ 188C ALT1 first form (final) 188D MONGOLIAN LETTER ALI GALI TTHA + ~ 188D ALT1 first form (initial) + ~ 188D ALT1 first form (medial) + ~ 188D ALT1 first form (final) 188E MONGOLIAN LETTER ALI GALI DDA + ~ 188E ALT1 first form (initial) + ~ 188E ALT1 first form (medial) + ~ 188E ALT1 first form (final) 188F MONGOLIAN LETTER ALI GALI NNA + ~ 188F ALT1 first form (initial) + ~ 188F ALT1 first form (medial) + ~ 188F ALT1 first form (final) 1890 MONGOLIAN LETTER ALI GALI TA + ~ 1890 ALT1 first form (initial) + ~ 1890 ALT1 first form (medial) + ~ 1890 ALT1 first form (final) 1891 MONGOLIAN LETTER ALI GALI DA + ~ 1891 ALT1 first form (initial) + ~ 1891 ALT1 first form (medial) + ~ 1891 ALT1 first form (final) 1892 MONGOLIAN LETTER ALI GALI PA + ~ 1892 ALT1 first form (initial) + ~ 1892 ALT1 first form (medial) + ~ 1892 ALT1 first form (final) 1893 MONGOLIAN LETTER ALI GALI PHA + ~ 1893 ALT1 first form (initial) + ~ 1893 ALT1 first form (medial) + ~ 1893 ALT1 first form (final) 1894 MONGOLIAN LETTER ALI GALI SSA + ~ 1894 ALT1 first form (initial) + ~ 1894 ALT1 first form (medial) + ~ 1894 ALT1 first form (final) 1895 MONGOLIAN LETTER ALI GALI ZHA + ~ 1895 ALT1 first form (initial) + ~ 1895 ALT1 first form (medial) + ~ 1895 ALT1 first form (final) 1896 MONGOLIAN LETTER ALI GALI ZA + ~ 1896 ALT1 first form (initial) + ~ 1896 ALT1 first form (medial) + ~ 1896 ALT1 first form (final) 1897 MONGOLIAN LETTER ALI GALI AH + ~ 1897 ALT1 first form (initial) + ~ 1897 ALT1 first form (medial) + ~ 1897 ALT1 first form (final) 1898 MONGOLIAN LETTER TODO ALI GALI TA + ~ 1898 ALT1 first form (initial) + ~ 1898 ALT1 first form (medial) + ~ 1898 ALT1 first form (final) 1899 MONGOLIAN LETTER TODO ALI GALI ZHA + ~ 1899 ALT1 first form (initial) + ~ 1899 ALT1 first form (medial) + ~ 1899 ALT1 first form (final) 189A MONGOLIAN LETTER MANCHU ALI GALI GHA + ~ 189A ALT1 first form (initial) + ~ 189A ALT1 first form (medial) + ~ 189A ALT1 first form (final) 189B MONGOLIAN LETTER MANCHU ALI GALI NGA + ~ 189B ALT1 first form (initial) + ~ 189B ALT1 first form (medial) + ~ 189B ALT1 first form (final) 189C MONGOLIAN LETTER MANCHU ALI GALI CA + ~ 189C ALT1 first form (initial) + ~ 189C ALT1 first form (medial) + ~ 189C ALT1 first form (final) 189D MONGOLIAN LETTER MANCHU ALI GALI JHA + ~ 189D ALT1 first form (initial) + ~ 189D ALT1 first form (medial) + ~ 189D ALT1 first form (final) 189E MONGOLIAN LETTER MANCHU ALI GALI TTA + ~ 189E ALT1 first form (initial) + ~ 189E ALT1 first form (medial) + ~ 189E ALT1 first form (final) 189F MONGOLIAN LETTER MANCHU ALI GALI DDHA + ~ 189F ALT1 first form (initial) + ~ 189F ALT1 first form (medial) + ~ 189F ALT1 first form (final) 18A0 MONGOLIAN LETTER MANCHU ALI GALI TA + ~ 18A0 ALT1 first form (initial) + ~ 18A0 ALT1 first form (medial) + ~ 18A0 ALT1 first form (final) 18A1 MONGOLIAN LETTER MANCHU ALI GALI DHA + ~ 18A1 ALT1 first form (initial) + ~ 18A1 ALT1 first form (medial) + ~ 18A1 ALT1 first form (final) 18A2 MONGOLIAN LETTER MANCHU ALI GALI SSA + ~ 18A2 ALT1 first form (initial) + ~ 18A2 ALT1 first form (medial) + ~ 18A2 ALT1 first form (final) 18A3 MONGOLIAN LETTER MANCHU ALI GALI CYA + ~ 18A3 ALT1 first form (initial) + ~ 18A3 ALT1 first form (medial) + ~ 18A3 ALT1 first form (final) 18A4 MONGOLIAN LETTER MANCHU ALI GALI ZHA + ~ 18A4 ALT1 first form (initial) + ~ 18A4 ALT1 first form (medial) + ~ 18A4 ALT1 first form (final) 18A5 MONGOLIAN LETTER MANCHU ALI GALI ZA + ~ 18A5 ALT1 first form (initial) + ~ 18A5 ALT1 first form (medial) + ~ 18A5 ALT1 first form (final) 18A6 MONGOLIAN LETTER ALI GALI HALF U + ~ 18A6 ALT1 first form (initial) + ~ 18A6 ALT1 first form (medial) + ~ 18A6 ALT1 first form (final) 18A7 MONGOLIAN LETTER ALI GALI HALF YA + ~ 18A7 ALT1 first form (initial) + ~ 18A7 ALT1 first form (medial) + ~ 18A7 ALT1 first form (final) 18A8 MONGOLIAN LETTER MANCHU ALI GALI BHA + ~ 18A8 ALT1 first form (initial) + ~ 18A8 ALT1 first form (medial) + ~ 18A8 ALT1 first form (final) 18A9 MONGOLIAN LETTER ALI GALI DAGALGA 18AA MONGOLIAN LETTER MANCHU ALI GALI LHA -@~ Standardized Variation Sequences + ~ 18AA ALT1 first form (initial) + ~ 18AA ALT1 first form (medial) + ~ 18AA ALT1 first form (final) +@@@~ Contextual Variants and Standardized Variation Sequences @+ Unlike other blocks, these variation sequences use the script-specific variation selectors for Mongolian. @@ 18B0 Unified Canadian Aboriginal Syllabics Extended 18FF @ Syllables for Moose Cree @@ -9675,6 +10180,7 @@ 19A9 NEW TAI LUE LETTER LOW XVA 19AA NEW TAI LUE LETTER HIGH SUA 19AB NEW TAI LUE LETTER LOW SUA + * a labialized consonant cluster @ Vowel signs 19B0 NEW TAI LUE VOWEL SIGN VOWEL SHORTENER 19B1 NEW TAI LUE VOWEL SIGN AA @@ -10347,7 +10853,7 @@ 1BEE BATAK VOWEL SIGN U = boruta 1BEF BATAK VOWEL SIGN U FOR SIMALUNGUN SA - = haboritan for simalungun sa + = haboritan for simalungun sa @ Dependent consonant signs 1BF0 BATAK CONSONANT SIGN NG = amisara @@ -10505,6 +11011,26 @@ @ Punctuation 1C7E OL CHIKI PUNCTUATION MUCAAD 1C7F OL CHIKI PUNCTUATION DOUBLE MUCAAD +@@ 1C80 Cyrillic Extended-C 1C8F +@ Historic letter variants +1C80 CYRILLIC SMALL LETTER ROUNDED VE + x (cyrillic small letter ve - 0432) +1C81 CYRILLIC SMALL LETTER LONG-LEGGED DE + x (cyrillic small letter de - 0434) +1C82 CYRILLIC SMALL LETTER NARROW O + x (cyrillic small letter o - 043E) +1C83 CYRILLIC SMALL LETTER WIDE ES + x (cyrillic small letter es - 0441) +1C84 CYRILLIC SMALL LETTER TALL TE +1C85 CYRILLIC SMALL LETTER THREE-LEGGED TE + x (cyrillic small letter te - 0442) +1C86 CYRILLIC SMALL LETTER TALL HARD SIGN + x (cyrillic small letter hard sign - 044A) +1C87 CYRILLIC SMALL LETTER TALL YAT + x (cyrillic small letter yat - 0463) +1C88 CYRILLIC SMALL LETTER UNBLENDED UK + x (cyrillic small letter uk - 0479) + x (cyrillic small letter monograph uk - A64B) @@ 1CC0 Sundanese Supplement 1CCF @ Punctuation 1CC0 SUNDANESE PUNCTUATION BINDU SURYA @@ -10616,6 +11142,9 @@ * marks a bilabial fricative occurring only before unvoiced labial stops x (kannada sign upadhmaniya - 0CF2) x (tibetan sign mchu can - 0F89) +1CF7 VEDIC SIGN ATIKRAMA + = vaidika saamagaana atikrama + * indicates skipping of a svara @ Signs for Jaiminiya Sama Veda 1CF8 VEDIC TONE RING ABOVE 1CF9 VEDIC TONE DOUBLE RING ABOVE @@ -11055,6 +11584,17 @@ 1DF4 COMBINING LATIN SMALL LETTER U WITH DIAERESIS @ Diacritic for American lexicography 1DF5 COMBINING UP TACK ABOVE +@ Typicon marks +1DF6 COMBINING KAVYKA ABOVE RIGHT +1DF7 COMBINING KAVYKA ABOVE LEFT + x (combining cyrillic kavyka - A67C) +1DF8 COMBINING DOT ABOVE LEFT + x (combining dot above right - 0358) +1DF9 COMBINING WIDE INVERTED BRIDGE BELOW + x (combining inverted bridge below - 033A) +@ Miscellaneous mark +1DFB COMBINING DELETION MARK + * used for "mhusaa" in Newa scribal tradition @ Double diacritic mark for UPA 1DFC COMBINING DOUBLE INVERTED BREVE BELOW @ Miscellaneous mark @@ -12325,8 +12865,6 @@ @ Double punctuation for vertical text 203C DOUBLE EXCLAMATION MARK x (exclamation mark - 0021) - ~ 203C FE0E text style - ~ 203C FE0F emoji style # 0021 0021 @ General punctuation 203D INTERROBANG @@ -12362,8 +12900,6 @@ 2048 QUESTION EXCLAMATION MARK # 003F 0021 2049 EXCLAMATION QUESTION MARK - ~ 2049 FE0E text style - ~ 2049 FE0F emoji style # 0021 003F @ General punctuation 204A TIRONIAN SIGN ET @@ -12402,6 +12938,7 @@ x (heavy eight teardrop-spoked propeller asterisk - 274B) @ Archaic punctuation 2056 THREE DOT PUNCTUATION + x (georgian paragraph separator - 10FB) @ General punctuation 2057 QUADRUPLE PRIME # 2032 2032 2032 2032 @@ -12464,7 +13001,6 @@ 206D ACTIVATE ARABIC FORM SHAPING 206E NATIONAL DIGIT SHAPES 206F NOMINAL DIGIT SHAPES -@~ ! @@ 2070 Superscripts and Subscripts 209F @ Superscripts @+ See also superscript Latin letters in the Spacing Modifier Letters block starting at 02B0. @@ -12646,7 +13182,7 @@ x (cent sign - 00A2) x (latin capital letter c with stroke - 023B) 20B6 LIVRE TOURNOIS SIGN - * used in France from 13th-18th centuries + * used in France from 13th-18th centuries 20B7 SPESMILO SIGN * historical international currency associated with Esperanto 20B8 TENGE SIGN @@ -12669,6 +13205,7 @@ * Russia 20BE LARI SIGN * Georgia +20BF BITCOIN SIGN @@ 20D0 Combining Diacritical Marks for Symbols 20FF @ Combining diacritical marks for symbols 20D0 COMBINING LEFT HARPOON ABOVE @@ -12835,15 +13372,13 @@ 2120 SERVICE MARK # <super> 0053 004D 2121 TELEPHONE SIGN - * typical forms for this symbol may use lower case, small caps or superscripted letter shapes + * typical forms for this symbol may use lowercase, small caps or superscripted letter shapes x (black telephone - 260E) x (telephone location sign - 2706) x (telephone receiver - 1F4DE) # 0054 0045 004C 2122 TRADE MARK SIGN x (circled wz - 1F12E) - ~ 2122 FE0E text style - ~ 2122 FE0F emoji style # <super> 0054 004D 2123 VERSICLE 2124 DOUBLE-STRUCK CAPITAL Z @@ -12925,13 +13460,11 @@ 2139 INFORMATION SOURCE * intended for use with 20DD x (circled information source - 1F6C8) - ~ 2139 FE0E text style - ~ 2139 FE0F emoji style # <font> 0069 latin small letter i 213A ROTATED CAPITAL Q * a binding signature mark 213B FACSIMILE SIGN - * typical forms for this symbol may use lower case, small caps or superscripted letter shapes + * typical forms for this symbol may use lowercase, small caps or superscripted letter shapes x (telephone sign - 2121) x (fax machine - 1F4E0) # 0046 0041 0058 @@ -12985,7 +13518,6 @@ x (greek small letter digamma - 03DD) @ Biblical editorial symbol 214F SYMBOL FOR SAMARITAN SOURCE -@~ ! @@ 2150 Number Forms 218F @ Fractions @+ Other fraction number forms are found in the Latin-1 Supplement block. @@ -13135,23 +13667,11 @@ * IPA: ingressive airflow 2194 LEFT RIGHT ARROW = z notation relation - ~ 2194 FE0E text style - ~ 2194 FE0F emoji style 2195 UP DOWN ARROW - ~ 2195 FE0E text style - ~ 2195 FE0F emoji style 2196 NORTH WEST ARROW - ~ 2196 FE0E text style - ~ 2196 FE0F emoji style 2197 NORTH EAST ARROW - ~ 2197 FE0E text style - ~ 2197 FE0F emoji style 2198 SOUTH EAST ARROW - ~ 2198 FE0E text style - ~ 2198 FE0F emoji style 2199 SOUTH WEST ARROW - ~ 2199 FE0E text style - ~ 2199 FE0F emoji style @ Arrows with modifications 219A LEFTWARDS ARROW WITH STROKE * negation of 2190 @@ -13184,11 +13704,7 @@ = depth symbol 21A8 UP DOWN ARROW WITH BASE 21A9 LEFTWARDS ARROW WITH HOOK - ~ 21A9 FE0E text style - ~ 21A9 FE0F emoji style 21AA RIGHTWARDS ARROW WITH HOOK - ~ 21AA FE0E text style - ~ 21AA FE0F emoji style 21AB LEFTWARDS ARROW WITH LOOP 21AC RIGHTWARDS ARROW WITH LOOP 21AD LEFT RIGHT WAVE ARROW @@ -13326,7 +13842,6 @@ 21FD LEFTWARDS OPEN-HEADED ARROW 21FE RIGHTWARDS OPEN-HEADED ARROW 21FF LEFT RIGHT OPEN-HEADED ARROW -@~ ! @@ 2200 Mathematical Operators 22FF @@+ @ Miscellaneous mathematical symbols @@ -13344,6 +13859,7 @@ * used in linguistics to indicate a null morpheme or phonological "zero" x (latin capital letter o with stroke - 00D8) x (diameter sign - 2300) + ~ 2205 FE00 zero with long diagonal stroke overlay form 2206 INCREMENT = Laplace operator = forward difference @@ -13425,7 +13941,7 @@ @ Miscellaneous mathematical symbol 221E INFINITY @ Angles -@+ Other angle symbols are found at 299B-29AF. +@+ Other angle symbols are found at 299B-29AF. 221F RIGHT ANGLE 2220 ANGLE x (acute angle - 299F) @@ -13465,11 +13981,7 @@ @ Integrals 222B INTEGRAL x (latin small letter esh - 0283) -;experimenting with variant syntax -; ~ 222B ALT1 slanted style 222C DOUBLE INTEGRAL -;experimenting with variant syntax -; ~ 222C ALT1 slanted style # 222B 222B 222D TRIPLE INTEGRAL x (quadruple integral operator - 2A0C) @@ -13948,12 +14460,8 @@ 231A WATCH x (alarm clock - 23F0) x (clock face one oclock - 1F550) - ~ 231A FE0E text style - ~ 231A FE0F emoji style 231B HOURGLASS = alchemical symbol for hour - ~ 231B FE0E text style - ~ 231B FE0F emoji style @ Quine corners @+ These form a set of four quine corners, for quincuncial arrangement. They are also used in upper and lower pairs in mathematic, or more rarely in editorial usage as alternatives to half brackets. 231C TOP LEFT CORNER @@ -14219,9 +14727,10 @@ 23B8 LEFT VERTICAL BOX LINE 23B9 RIGHT VERTICAL BOX LINE @ Scan lines for terminal graphics -@+ The scan line numbers here refer to old, low-resolution technology for terminals, with only 9 scan lines per fixed-size character glyph. Even-numbered scan lines are unified with box-drawing graphics. +@+ The scan line numbers here refer to old, low-resolution technology for terminals, with only 9 scan lines per fixed-size character glyph. 23BA HORIZONTAL SCAN LINE-1 23BB HORIZONTAL SCAN LINE-3 + * scan line-5 is unified with the box-drawing graphic character 2500 23BC HORIZONTAL SCAN LINE-7 23BD HORIZONTAL SCAN LINE-9 @ Dentistry notation symbols @@ -14323,18 +14832,22 @@ 23F4 BLACK MEDIUM LEFT-POINTING TRIANGLE = reverse, back * preferred to 25C0 black left-pointing triangle + x (black medium left-pointing triangle centred - 2BC7) x (black left-pointing isosceles right triangle - 1F780) 23F5 BLACK MEDIUM RIGHT-POINTING TRIANGLE = forward * preferred to 25B6 black right-pointing triangle + x (black medium right-pointing triangle centred - 2BC8) x (black right-pointing isosceles right triangle - 1F782) 23F6 BLACK MEDIUM UP-POINTING TRIANGLE = increase * preferred to 25B2 black up-pointing triangle + x (black medium up-pointing triangle centred - 2BC5) x (black up-pointing isosceles right triangle - 1F781) 23F7 BLACK MEDIUM DOWN-POINTING TRIANGLE = decrease * preferred to 25BC black down-pointing triangle + x (black medium down-pointing triangle centred - 2BC6) x (black down-pointing isosceles right triangle - 1F783) 23F8 DOUBLE VERTICAL BAR = pause @@ -14345,7 +14858,20 @@ 23FA BLACK CIRCLE FOR RECORD = record x (medium black circle - 26AB) -@~ ! +@ Power symbols from ISO 7000:2012 +23FB POWER SYMBOL +@+ * IEC 5009 standby symbol +@+ * IEEE 1621 power symbol +23FC POWER ON-OFF SYMBOL +@+ * IEC 5010 power on-off symbol +23FD POWER ON SYMBOL + * use 2B58 for power off symbol + x (heavy circle - 2B58) +@ Power symbol from IEEE 1621-2004 +23FE POWER SLEEP SYMBOL + x (last quarter moon - 263E) +@ Miscellaneous symbol +23FF OBSERVER EYE SYMBOL @@ 2400 Control Pictures 243F @+ The diagonal lettering glyphs are only exemplary; alternate representations may be, and often are used in the visible display of control codes. @ Graphic pictures for control codes @@ -14411,7 +14937,7 @@ = unique asterisk x (bowtie - 22C8) @ MICR -@+ These magnetic ink character recognition symbols are used on checks. The are derived from the E-13B font and are standardized in ISO 1004:1995. The Unicode character names include several misnomers. +@+ These magnetic ink character recognition symbols are used on checks. They are derived from the E-13B font and are standardized in ISO 1004:1995. The Unicode character names include several misnomers. 2446 OCR BRANCH BANK IDENTIFICATION = transit 2447 OCR AMOUNT OF CHECK @@ -14550,7 +15076,7 @@ 249B NUMBER TWENTY FULL STOP # 0032 0030 002E @ Parenthesized Latin letters -@+ See also the uppercase set starting at 1F100. +@+ See also the uppercase set starting at 1F100. Parenthesized Latin letters do not have case mappings. 249C PARENTHESIZED LATIN SMALL LETTER A # 0028 0061 0029 249D PARENTHESIZED LATIN SMALL LETTER B @@ -14630,8 +15156,6 @@ 24C1 CIRCLED LATIN CAPITAL LETTER L # <circle> 004C 24C2 CIRCLED LATIN CAPITAL LETTER M - ~ 24C2 FE0E text style - ~ 24C2 FE0F emoji style # <circle> 004D 24C3 CIRCLED LATIN CAPITAL LETTER N # <circle> 004E @@ -14741,7 +15265,6 @@ @ Additional white on black circled number 24FF NEGATIVE CIRCLED DIGIT ZERO x (dingbat negative circled digit one - 2776) -@~ ! @@ 2500 Box Drawing 257F @+ All of these characters are intended for compatibility with character cell graphic sets in use prior to 1990. @ Light and heavy solid lines @@ -14981,12 +15504,8 @@ 25AA BLACK SMALL SQUARE = square bullet x (black very small square - 2B1D) - ~ 25AA FE0E text style - ~ 25AA FE0F emoji style 25AB WHITE SMALL SQUARE x (white very small square - 2B1E) - ~ 25AB FE0E text style - ~ 25AB FE0F emoji style 25AC BLACK RECTANGLE 25AD WHITE RECTANGLE 25AE BLACK VERTICAL RECTANGLE @@ -14999,7 +15518,7 @@ 25B1 WHITE PARALLELOGRAM 25B2 BLACK UP-POINTING TRIANGLE x (black medium up-pointing triangle - 23F6) - x (mountain - 26F0) + x (black medium up-pointing triangle centred - 2BC5) x (up-pointing red triangle - 1F53A) 25B3 WHITE UP-POINTING TRIANGLE = trine @@ -15012,8 +15531,7 @@ 25B5 WHITE UP-POINTING SMALL TRIANGLE 25B6 BLACK RIGHT-POINTING TRIANGLE x (black medium right-pointing triangle - 23F5) - ~ 25B6 FE0E text style - ~ 25B6 FE0F emoji style + x (black medium right-pointing triangle centred - 2BC8) 25B7 WHITE RIGHT-POINTING TRIANGLE = z notation range restriction 25B8 BLACK RIGHT-POINTING SMALL TRIANGLE @@ -15025,6 +15543,7 @@ x (contains as normal subgroup - 22B3) 25BC BLACK DOWN-POINTING TRIANGLE x (black medium down-pointing triangle - 23F7) + x (black medium down-pointing triangle centred - 2BC6) x (down-pointing red triangle - 1F53B) 25BD WHITE DOWN-POINTING TRIANGLE = Hamilton operator @@ -15036,8 +15555,7 @@ 25BF WHITE DOWN-POINTING SMALL TRIANGLE 25C0 BLACK LEFT-POINTING TRIANGLE x (black medium left-pointing triangle - 23F4) - ~ 25C0 FE0E text style - ~ 25C0 FE0F emoji style + x (black medium left-pointing triangle centred - 2BC7) 25C1 WHITE LEFT-POINTING TRIANGLE = z notation domain restriction 25C2 BLACK LEFT-POINTING SMALL TRIANGLE @@ -15144,24 +15662,15 @@ = always (modal operator) x (white square - 25A1) x (white square with leftwards tick - 27E4) - ~ 25FB FE0E text style - ~ 25FB FE0F emoji style 25FC BLACK MEDIUM SQUARE x (black square for stop - 23F9) x (black square - 25A0) - ~ 25FC FE0E text style - ~ 25FC FE0F emoji style 25FD WHITE MEDIUM SMALL SQUARE x (white small square - 25AB) - ~ 25FD FE0E text style - ~ 25FD FE0F emoji style 25FE BLACK MEDIUM SMALL SQUARE x (black small square - 25AA) - ~ 25FE FE0E text style - ~ 25FE FE0F emoji style 25FF LOWER RIGHT TRIANGLE x (right triangle - 22BF) -@~ ! @@ 2600 Miscellaneous Symbols 26FF @@+ @ Weather and astrological symbols @@ -15169,12 +15678,8 @@ = clear weather x (sun - 2609) x (high brightness symbol - 1F506) - ~ 2600 FE0E text style - ~ 2600 FE0F emoji style 2601 CLOUD = cloudy weather - ~ 2601 FE0E text style - ~ 2601 FE0F emoji style 2602 UMBRELLA = rainy weather x (closed umbrella - 1F302) @@ -15183,8 +15688,11 @@ 2604 COMET 2605 BLACK STAR x (star operator - 22C6) + x (black small star - 2B51) + x (light five pointed black star - 1F7C9) 2606 WHITE STAR x (stress outlined white star - 2729) + x (white medium star - 2B50) x (glowing star - 1F31F) 2607 LIGHTNING 2608 THUNDERSTORM @@ -15208,16 +15716,12 @@ x (telephone location sign - 2706) x (telephone receiver - 1F4DE) x (black touchtone telephone - 1F57F) - ~ 260E FE0E text style - ~ 260E FE0F emoji style 260F WHITE TELEPHONE x (white touchtone telephone - 1F57E) 2610 BALLOT BOX x (white square - 25A1) 2611 BALLOT BOX WITH CHECK x (ballot box with bold check - 1F5F9) - ~ 2611 FE0E text style - ~ 2611 FE0F emoji style 2612 BALLOT BOX WITH X x (squared times - 22A0) x (ballot box with light x - 2BBD) @@ -15230,8 +15734,6 @@ @ Weather symbol 2614 UMBRELLA WITH RAIN DROPS = showery weather - ~ 2614 FE0E text style - ~ 2614 FE0F emoji style @ Miscellaneous symbol 2615 HOT BEVERAGE = tea or coffee, depending on locale @@ -15239,8 +15741,6 @@ x (watch - 231A) x (hourglass - 231B) x (teacup without handle - 1F375) - ~ 2615 FE0E text style - ~ 2615 FE0F emoji style @ Japanese chess symbols 2616 WHITE SHOGI PIECE 2617 BLACK SHOGI PIECE @@ -15259,8 +15759,6 @@ x (sideways white left pointing index - 1F598) 261D WHITE UP POINTING INDEX x (sideways white up pointing index - 1F59E) - ~ 261D FE0E text style - ~ 261D FE0F emoji style 261E WHITE RIGHT POINTING INDEX = fist (typographic term) x (sideways white right pointing index - 1F599) @@ -15286,6 +15784,8 @@ x (coptic symbol khi ro - 2CE9) 2628 CROSS OF LORRAINE 2629 CROSS OF JERUSALEM + = simple cross potent + * contrasts with the actual cross of Jerusalem, which adds a small crosslet at each corner x (alchemical symbol for vinegar - 1F70A) 262A STAR AND CRESCENT 262B FARSI SYMBOL @@ -15323,8 +15823,6 @@ 263A WHITE SMILING FACE x (slightly smiling face - 1F642) = have a nice day! - ~ 263A FE0E text style - ~ 263A FE0F emoji style 263B BLACK SMILING FACE @ Miscellaneous symbol 263C WHITE SUN WITH RAYS @@ -15337,6 +15835,7 @@ = alchemical symbol for silver 263E LAST QUARTER MOON = alchemical symbol for silver + x (power sleep symbol - 23FE) x (crescent moon - 1F319) 263F MERCURY = alchemical symbol for quicksilver @@ -15363,53 +15862,30 @@ = alchemical symbol for bismuth/tinglass 2647 PLUTO @ Zodiacal symbols +@+ See also Asian zodiacal symbols among the animal symbols in the range 1F400-1F418. 2648 ARIES x (ram - 1F40F) - ~ 2648 FE0E text style - ~ 2648 FE0F emoji style 2649 TAURUS - ~ 2649 FE0E text style - ~ 2649 FE0F emoji style 264A GEMINI - ~ 264A FE0E text style - ~ 264A FE0F emoji style 264B CANCER x (crab - 1F980) - ~ 264B FE0E text style - ~ 264B FE0F emoji style 264C LEO x (lion face - 1F981) - ~ 264C FE0E text style - ~ 264C FE0F emoji style 264D VIRGO = minim (alternate glyph) - ~ 264D FE0E text style - ~ 264D FE0F emoji style 264E LIBRA x (scales - 2696) x (alchemical symbol for sublimation - 1F75E) - ~ 264E FE0E text style - ~ 264E FE0F emoji style 264F SCORPIUS = scorpio = minim, drop x (scorpion - 1F982) - ~ 264F FE0E text style - ~ 264F FE0F emoji style 2650 SAGITTARIUS x (bow and arrow - 1F3F9) - ~ 2650 FE0E text style - ~ 2650 FE0F emoji style 2651 CAPRICORN - ~ 2651 FE0E text style - ~ 2651 FE0F emoji style 2652 AQUARIUS x (amphora - 1F3FA) - ~ 2652 FE0E text style - ~ 2652 FE0F emoji style 2653 PISCES - ~ 2653 FE0E text style - ~ 2653 FE0F emoji style @ Chess symbols 2654 WHITE CHESS KING 2655 WHITE CHESS QUEEN @@ -15425,33 +15901,24 @@ 265F BLACK CHESS PAWN @ Playing card symbols 2660 BLACK SPADE SUIT - ~ 2660 FE0E text style - ~ 2660 FE0F emoji style 2661 WHITE HEART SUIT 2662 WHITE DIAMOND SUIT x (white diamond - 25C7) x (lozenge - 25CA) 2663 BLACK CLUB SUIT x (shamrock - 2618) - ~ 2663 FE0E text style - ~ 2663 FE0F emoji style 2664 WHITE SPADE SUIT 2665 BLACK HEART SUIT = valentine x (heavy black heart - 2764) x (heart with tip on the left - 1F394) x (blue heart - 1F499) - ~ 2665 FE0E text style - ~ 2665 FE0F emoji style + x (black heart - 1F5A4) 2666 BLACK DIAMOND SUIT x (black diamond - 25C6) - ~ 2666 FE0E text style - ~ 2666 FE0F emoji style 2667 WHITE CLUB SUIT @ Miscellaneous symbol 2668 HOT SPRINGS - ~ 2668 FE0E text style - ~ 2668 FE0F emoji style @ Musical symbols 2669 QUARTER NOTE = crotchet @@ -15496,8 +15963,6 @@ * used together with other text and labels to indicate the type of material to be recycled 267B BLACK UNIVERSAL RECYCLING SYMBOL x (clockwise rightwards and leftwards open circle arrows - 1F501) - ~ 267B FE0E text style - ~ 267B FE0F emoji style 267C RECYCLED PAPER SYMBOL * used to indicate 100% recycled paper content 267D PARTIALLY-RECYCLED PAPER SYMBOL @@ -15505,8 +15970,6 @@ @ Miscellaneous symbols 267E PERMANENT PAPER SIGN 267F WHEELCHAIR SYMBOL - ~ 267F FE0E text style - ~ 267F FE0F emoji style @ Dice 2680 DIE FACE-1 x (game die - 1F3B2) @@ -15539,10 +16002,9 @@ x (hammer and wrench - 1F6E0) 2693 ANCHOR = nautical term, harbor (on maps) - ~ 2693 FE0E text style - ~ 2693 FE0F emoji style 2694 CROSSED SWORDS = military term, battleground (on maps), killed in action + x (fencer - 1F93A) 2695 STAFF OF AESCULAPIUS = medical term * both inclined or upright renderings of this symbol are common @@ -15580,14 +16042,11 @@ x (three rays right - 1F5E7) @ Miscellaneous symbols 26A0 WARNING SIGN - ~ 26A0 FE0E text style - ~ 26A0 FE0F emoji style + x (octagonal sign - 1F6D1) 26A1 HIGH VOLTAGE SIGN = thunder = lightning symbol x (lightning mood - 1F5F2) - ~ 26A1 FE0E text style - ~ 26A1 FE0F emoji style @ Gender symbols 26A2 DOUBLED FEMALE SIGN = lesbianism @@ -15617,13 +16076,9 @@ = engaged, betrothed * base for male or female sign x (medium bold white circle - 1F785) - ~ 26AA FE0E text style - ~ 26AA FE0F emoji style 26AB MEDIUM BLACK CIRCLE * UI symbol for record function x (black circle for record - 23FA) - ~ 26AB FE0E text style - ~ 26AB FE0F emoji style 26AC MEDIUM SMALL WHITE CIRCLE = engaged, betrothed (genealogy) * can represent wedding ring @@ -15651,6 +16106,7 @@ 26B8 BLACK MOON LILITH 26B9 SEXTILE x (asterisk - 002A) + x (six pointed black star - 2736) x (alchemical symbol for sal-ammoniac - 1F739) 26BA SEMISEXTILE x (xor - 22BB) @@ -15660,11 +16116,7 @@ @ Sport symbols @+ See other sport symbols in the Miscellaneous Symbols and Pictographs block. 26BD SOCCER BALL - ~ 26BD FE0E text style - ~ 26BD FE0F emoji style 26BE BASEBALL - ~ 26BE FE0E text style - ~ 26BE FE0F emoji style @ Miscellaneous symbol from ARIB STD B24 26BF SQUARED KEY = parental lock @@ -15677,13 +16129,9 @@ @ Weather symbols from ARIB STD B24 26C4 SNOWMAN WITHOUT SNOW = light snow - ~ 26C4 FE0E text style - ~ 26C4 FE0F emoji style 26C5 SUN BEHIND CLOUD = partly cloudy x (white sun with small cloud - 1F324) - ~ 26C5 FE0E text style - ~ 26C5 FE0F emoji style 26C6 RAIN = rainy weather 26C7 BLACK SNOWMAN @@ -15720,8 +16168,6 @@ = tyre chains required 26D4 NO ENTRY x (no entry sign - 1F6AB) - ~ 26D4 FE0E text style - ~ 26D4 FE0F emoji style 26D5 ALTERNATE ONE-WAY LEFT WAY TRAFFIC * left side traffic 26D6 BLACK TWO-WAY LEFT WAY TRAFFIC @@ -15773,8 +16219,6 @@ 26E9 SHINTO SHRINE = torii 26EA CHURCH - ~ 26EA FE0E text style - ~ 26EA FE0F emoji style 26EB CASTLE x (european castle - 1F3F0) 26EC HISTORIC SITE @@ -15787,7 +16231,6 @@ = power plant, power substation 26EF MAP SYMBOL FOR LIGHTHOUSE 26F0 MOUNTAIN - x (black up-pointing triangle - 25B2) x (snow capped mountain - 1F3D4) 26F1 UMBRELLA ON GROUND = bathing beach @@ -15795,21 +16238,15 @@ x (beach with umbrella - 1F3D6) 26F2 FOUNTAIN = park - ~ 26F2 FE0E text style - ~ 26F2 FE0F emoji style 26F3 FLAG IN HOLE = golf course x (triangular flag on post - 1F6A9) - ~ 26F3 FE0E text style - ~ 26F3 FE0F emoji style 26F4 FERRY = ferry boat terminal x (ship - 1F6A2) 26F5 SAILBOAT = marina or yacht harbour x (rowboat - 1F6A3) - ~ 26F5 FE0E text style - ~ 26F5 FE0F emoji style 26F6 SQUARE FOUR CORNERS = intersection 26F7 SKIER @@ -15822,23 +16259,18 @@ 26FA TENT = camping site x (camping - 1F3D5) - ~ 26FA FE0E text style - ~ 26FA FE0F emoji style 26FB JAPANESE BANK SYMBOL x (bank - 1F3E6) 26FC HEADSTONE GRAVEYARD SYMBOL = graveyard, memorial park, cemetery 26FD FUEL PUMP = petrol station, gas station - ~ 26FD FE0E text style - ~ 26FD FE0F emoji style 26FE CUP ON BLACK SQUARE = drive-in restaurant x (hot beverage - 2615) x (teacup without handle - 1F375) 26FF WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE = Japanese self-defence force site -@~ ! @@ 2700 Dingbats 27BF @+ ITC Zapf dingbats series 100. Some of the ITC Zapf dingbats have been unified with geometric shape characters. Gaps in the chart have subsequently been filled with other dingbat-like symbols. x (black telephone - 260E) @@ -15858,8 +16290,6 @@ * forms a pair with 2704 white scissors 2701 UPPER BLADE SCISSORS 2702 BLACK SCISSORS - ~ 2702 FE0E text style - ~ 2702 FE0F emoji style 2703 LOWER BLADE SCISSORS 2704 WHITE SCISSORS 2705 WHITE HEAVY CHECK MARK @@ -15870,13 +16300,9 @@ 2707 TAPE DRIVE 2708 AIRPLANE x (up-pointing airplane - 1F6E7) - ~ 2708 FE0E text style - ~ 2708 FE0F emoji style 2709 ENVELOPE x (incoming envelope - 1F4E8) x (back of envelope - 1F582) - ~ 2709 FE0E text style - ~ 2709 FE0F emoji style 270A RAISED FIST = rock in Rock, Paper, Scissors game x (fisted hand sign - 1F44A) @@ -15887,33 +16313,23 @@ 270C VICTORY HAND = scissors in Rock, Paper, Scissors game x (reversed victory hand - 1F594) - ~ 270C FE0E text style - ~ 270C FE0F emoji style 270D WRITING HAND x (left writing hand - 1F58E) 270E LOWER RIGHT PENCIL x (lower left pencil - 1F589) 270F PENCIL - ~ 270F FE0E text style - ~ 270F FE0F emoji style 2710 UPPER RIGHT PENCIL 2711 WHITE NIB x (lower left fountain pen - 1F58B) 2712 BLACK NIB - ~ 2712 FE0E text style - ~ 2712 FE0F emoji style 2713 CHECK MARK x (square root - 221A) x (light check mark - 1F5F8) 2714 HEAVY CHECK MARK - ~ 2714 FE0E text style - ~ 2714 FE0F emoji style 2715 MULTIPLICATION X x (multiplication sign - 00D7) x (box drawings light diagonal cross - 2573) 2716 HEAVY MULTIPLICATION X - ~ 2716 FE0E text style - ~ 2716 FE0F emoji style 2717 BALLOT X x (saltire - 2613) x (ballot script x - 1F5F4) @@ -15931,6 +16347,7 @@ 271F OUTLINED LATIN CROSS 2720 MALTESE CROSS * Historically, the Maltese cross took many forms; the shape shown in the Zapf Dingbats is similar to one known as the Cross Formée. + x (circled cross formee - 1F902) @ Stars and asterisks 2721 STAR OF DAVID x (six pointed star with middle dot - 1F52F) @@ -15959,15 +16376,11 @@ 2732 OPEN CENTRE ASTERISK 2733 EIGHT SPOKED ASTERISK x (light eight spoked asterisk - 1F7BB) - ~ 2733 FE0E text style - ~ 2733 FE0F emoji style 2734 EIGHT POINTED BLACK STAR - ~ 2734 FE0E text style - ~ 2734 FE0F emoji style 2735 EIGHT POINTED PINWHEEL STAR x (heavy eight pointed pinwheel star - 1F7D1) 2736 SIX POINTED BLACK STAR - = sextile + x (sextile - 26B9) 2737 EIGHT POINTED RECTILINEAR BLACK STAR x (medium eight pointed black star - 1F7CE) 2738 HEAVY EIGHT POINTED RECTILINEAR BLACK STAR @@ -15990,13 +16403,9 @@ 2742 CIRCLED OPEN CENTRE EIGHT POINTED STAR 2743 HEAVY TEARDROP-SPOKED PINWHEEL ASTERISK 2744 SNOWFLAKE - ~ 2744 FE0E text style - ~ 2744 FE0F emoji style 2745 TIGHT TRIFOLIATE SNOWFLAKE 2746 HEAVY CHEVRON SNOWFLAKE 2747 SPARKLE - ~ 2747 FE0E text style - ~ 2747 FE0F emoji style 2748 HEAVY SPARKLE 2749 BALLOON-SPOKED ASTERISK = jack @@ -16021,8 +16430,6 @@ 2756 BLACK DIAMOND MINUS WHITE X 2757 HEAVY EXCLAMATION MARK SYMBOL = obstacles on the road, ARIB STD B24 - ~ 2757 FE0E text style - ~ 2757 FE0F emoji style 2758 LIGHT VERTICAL BAR x (vertical line - 007C) 2759 MEDIUM VERTICAL BAR @@ -16050,8 +16457,6 @@ 2763 HEAVY HEART EXCLAMATION MARK ORNAMENT 2764 HEAVY BLACK HEART x (black heart suit - 2665) - ~ 2764 FE0E text style - ~ 2764 FE0F emoji style 2765 ROTATED HEAVY BLACK HEART BULLET @ Fleurons 2766 FLORAL HEART @@ -16140,8 +16545,6 @@ * fonts may harmonize this glyph with the style for other black arrows x (leftwards black arrow - 2B05) x (rightwards black arrow - 2B95) - ~ 27A1 FE0E text style - ~ 27A1 FE0F emoji style 27A2 THREE-D TOP-LIGHTED RIGHTWARDS ARROWHEAD x (three-d top-lighted rightwards equilateral arrowhead - 2B9A) 27A3 THREE-D BOTTOM-LIGHTED RIGHTWARDS ARROWHEAD @@ -16186,7 +16589,6 @@ 27BE OPEN-OUTLINED RIGHTWARDS ARROW @ Miscellaneous 27BF DOUBLE CURLY LOOP -@~ ! @@ 27C0 Miscellaneous Mathematical Symbols-A 27EF @ Miscellaneous symbols 27C0 THREE DIMENSIONAL ANGLE @@ -16715,11 +17117,7 @@ x (rightwards wave arrow - 219D) x (wave arrow pointing directly left - 2B3F) 2934 ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS - ~ 2934 FE0E text style - ~ 2934 FE0F emoji style 2935 ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS - ~ 2935 FE0E text style - ~ 2935 FE0F emoji style 2936 ARROW POINTING DOWNWARDS THEN CURVING LEFTWARDS 2937 ARROW POINTING DOWNWARDS THEN CURVING RIGHTWARDS 2938 RIGHT-SIDE ARC CLOCKWISE ARROW @@ -16812,7 +17210,6 @@ 297D RIGHT FISH TAIL 297E UP FISH TAIL 297F DOWN FISH TAIL -@~ ! @@ 2980 Miscellaneous Mathematical Symbols-B 29FF @ Miscellaneous mathematical symbols 2980 TRIPLE VERTICAL BAR DELIMITER @@ -16840,10 +17237,13 @@ 298A Z NOTATION RIGHT BINDING BRACKET 298B LEFT SQUARE BRACKET WITH UNDERBAR 298C RIGHT SQUARE BRACKET WITH UNDERBAR +@ Brackets with ticks +@+ For bidirectional processing, the brackets with ticks are paired on the basis of their left/right symmetric glyphs, rather than on the basis of an open/close pairing inferred from code point order. 298D LEFT SQUARE BRACKET WITH TICK IN TOP CORNER 298E RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER 298F LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER 2990 RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +@ Brackets 2991 LEFT ANGLE BRACKET WITH DOT 2992 RIGHT ANGLE BRACKET WITH DOT 2993 LEFT ARC LESS-THAN BRACKET @@ -16991,6 +17391,7 @@ 29E7 THERMODYNAMIC * vertical bar crossed by two horizontals x (not equal to - 2260) + x (group mark - 2BD2) 29E8 DOWN-POINTING TRIANGLE WITH LEFT HALF BLACK x (up-pointing triangle with left half black - 25ED) 29E9 DOWN-POINTING TRIANGLE WITH RIGHT HALF BLACK @@ -17464,14 +17865,8 @@ 2B05 LEFTWARDS BLACK ARROW x (black rightwards arrow - 27A1) x (rightwards black arrow - 2B95) - ~ 2B05 FE0E text style - ~ 2B05 FE0F emoji style 2B06 UPWARDS BLACK ARROW - ~ 2B06 FE0E text style - ~ 2B06 FE0F emoji style 2B07 DOWNWARDS BLACK ARROW - ~ 2B07 FE0E text style - ~ 2B07 FE0F emoji style 2B08 NORTH EAST BLACK ARROW 2B09 NORTH WEST BLACK ARROW 2B0A SOUTH EAST BLACK ARROW @@ -17499,12 +17894,8 @@ 2B1A DOTTED SQUARE 2B1B BLACK LARGE SQUARE x (black square - 25A0) - ~ 2B1B FE0E text style - ~ 2B1B FE0F emoji style 2B1C WHITE LARGE SQUARE x (white square - 25A1) - ~ 2B1C FE0E text style - ~ 2B1C FE0F emoji style 2B1D BLACK VERY SMALL SQUARE x (black small square - 25AA) 2B1E WHITE VERY SMALL SQUARE @@ -17613,11 +18004,11 @@ * slight fall or overall fall in tone when at the end of a word or at the beginning of a phrase, respectively @ Stars 2B50 WHITE MEDIUM STAR - x (star operator - 22C6) - ~ 2B50 FE0E text style - ~ 2B50 FE0F emoji style + x (white star - 2606) 2B51 BLACK SMALL STAR x (arabic five pointed star - 066D) + x (star operator - 22C6) + x (black star - 2605) 2B52 WHITE SMALL STAR @ Pentagons 2B53 BLACK RIGHT-POINTING PENTAGON @@ -17627,8 +18018,6 @@ = basic symbol for speed limit * forms a game tally pair with 274C x (large circle - 25EF) - ~ 2B55 FE0E text style - ~ 2B55 FE0F emoji style @ Dictionary and map symbols from ARIB STD B24 2B56 HEAVY OVAL WITH OVAL INSIDE = prefectural office @@ -17637,23 +18026,25 @@ x (bullseye - 25CE) 2B58 HEAVY CIRCLE = town or village office + = power off symbol + x (power on symbol - 23FD) x (white circle - 25CB) 2B59 HEAVY CIRCLED SALTIRE = police station x (n-ary circled times operator - 2A02) @ Intonation marks for Lithuanian dialectology 2B5A SLANTED NORTH ARROW WITH HOOKED HEAD - * increasing tone with falling trend at the end + * increasing tone with falling trend at the end 2B5B BACKSLANTED SOUTH ARROW WITH HOOKED TAIL * sharp rise and fall in tone 2B5C SLANTED NORTH ARROW WITH HORIZONTAL TAIL - * continued rise in tone + * continued rise in tone 2B5D BACKSLANTED SOUTH ARROW WITH HORIZONTAL TAIL * continued fall in tone 2B5E BENT ARROW POINTING DOWNWARDS THEN NORTH EAST * sharp fall in tone with rising trend at the end 2B5F SHORT BENT ARROW POINTING DOWNWARDS THEN NORTH EAST - * slight fall in tone with rising trend at the end + * slight fall in tone with rising trend at the end @ Triangle-headed arrows 2B60 LEFTWARDS TRIANGLE-HEADED ARROW x (leftwards arrow - 2190) @@ -17707,9 +18098,11 @@ = end 2B79 SOUTH WEST TRIANGLE-HEADED ARROW TO BAR 2B7A LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE + % LEFTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE 2B7B UPWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE = page up 2B7C RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE + % RIGHTWARDS TRIANGLE-HEADED ARROW WITH DOUBLE VERTICAL STROKE 2B7D DOWNWARDS TRIANGLE-HEADED ARROW WITH DOUBLE HORIZONTAL STROKE = page down @ Keyboard symbols @@ -17823,11 +18216,16 @@ 2BC1 BLACK DIAMOND CENTRED 2BC2 TURNED BLACK PENTAGON 2BC3 HORIZONTAL BLACK OCTAGON + x (octagonal sign - 1F6D1) 2BC4 BLACK OCTAGON 2BC5 BLACK MEDIUM UP-POINTING TRIANGLE CENTRED + x (black up-pointing triangle - 25B2) 2BC6 BLACK MEDIUM DOWN-POINTING TRIANGLE CENTRED + x (black down-pointing triangle - 25BC) 2BC7 BLACK MEDIUM LEFT-POINTING TRIANGLE CENTRED + x (black left-pointing triangle - 25C0) 2BC8 BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED + x (black right-pointing triangle - 25B6) @ Half circles 2BCA TOP HALF BLACK CIRCLE 2BCB BOTTOM HALF BLACK CIRCLE @@ -17846,6 +18244,10 @@ = query x (apl functional symbol quad question - 2370) x (replacement character - FFFD) +2BD2 GROUP MARK + * formerly used as a separator character for I/O operations + x (double dagger - 2021) + x (thermodynamic - 29E7) @ Two-headed arrow symbols @+ The following four arrow symbols are the preferred representation for fast cursor direction for ISO 9995-7. 2BEC LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS @@ -17857,7 +18259,6 @@ = fast cursor right 2BEF DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS = fast cursor down -@~ ! @@ 2C00 Glagolitic 2C5F @ Capital letters 2C00 GLAGOLITIC CAPITAL LETTER AZU @@ -18011,9 +18412,9 @@ # <super> 0056 @ Additions for Shona 2C7E LATIN CAPITAL LETTER S WITH SWASH TAIL - * lower case is 023F + * lowercase is 023F 2C7F LATIN CAPITAL LETTER Z WITH SWASH TAIL - * lower case is 0240 + * lowercase is 0240 @@ 2C80 Coptic 2CFF @+ Other Coptic letters derived from Demotic are encoded in the Greek and Coptic block. @ Bohairic Coptic letters @@ -18389,7 +18790,7 @@ 2DF3 COMBINING CYRILLIC LETTER SHCHA 2DF4 COMBINING CYRILLIC LETTER FITA 2DF5 COMBINING CYRILLIC LETTER ES-TE - * preferred representation is the sequence: 2DED 2DEE + * preferred representation is the sequence: 2DED 2DEE 2DF6 COMBINING CYRILLIC LETTER A x (combining latin small letter a - 0363) 2DF7 COMBINING CYRILLIC LETTER IE @@ -18571,6 +18972,18 @@ x (arabic comma - 060C) 2E42 DOUBLE LOW-REVERSED-9 QUOTATION MARK x (double low-9 quotation mark - 201E) +@ Dash +2E43 DASH WITH LEFT UPTURN +@ Miscellaneous punctuation +2E44 DOUBLE SUSPENSION MARK +@ Typicon punctuation +2E45 INVERTED LOW KAVYKA +2E46 INVERTED LOW KAVYKA WITH KAVYKA ABOVE + x (modifier breve with inverted breve - AB5B) +2E47 LOW KAVYKA + x (cyrillic kavyka - A67E) +2E48 LOW KAVYKA WITH DOT +2E49 DOUBLE STACKED COMMA @@ 2E80 CJK Radicals Supplement 2EFF @ CJK radicals supplement 2E80 CJK RADICAL REPEAT @@ -19301,6 +19714,7 @@ x (double prime - 2033) 3004 JAPANESE INDUSTRIAL STANDARD SYMBOL 3005 IDEOGRAPHIC ITERATION MARK + x (tangut iteration mark - 16FE0) 3006 IDEOGRAPHIC CLOSING MARK 3007 IDEOGRAPHIC NUMBER ZERO x (combining enclosing circle - 20DD) @@ -19395,19 +19809,20 @@ = single dot Bangjeom 302F HANGUL DOUBLE DOT TONE MARK = double dot Bangjeom -@ Other CJK symbols +@ Other CJK punctuation 3030 WAVY DASH x (wavy line - 2307) x (wave dash - 301C) - ~ 3030 FE0E text style - ~ 3030 FE0F emoji style +@ Kana repeat marks +@+ These characters are only used in vertical writing of Japanese. 3031 VERTICAL KANA REPEAT MARK 3032 VERTICAL KANA REPEAT WITH VOICED SOUND MARK - * the preceding two semantic characters are preferred to the following three glyphic forms + * implemented as glyphs that are two-em tall 3033 VERTICAL KANA REPEAT MARK UPPER HALF 3034 VERTICAL KANA REPEAT WITH VOICED SOUND MARK UPPER HALF - * the preceding two are glyphs used in conjunction with the following glyph + * implemented as glyphs that are one-em tall and that combine with the following character to form ligated two-em glyphs for the complete repeat marks 3035 VERTICAL KANA REPEAT MARK LOWER HALF +@ Other CJK symbols 3036 CIRCLED POSTAL MARK # 3012 postal mark 3037 IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL @@ -19425,15 +19840,12 @@ x (squared rising diagonal slash - 29C4) 303D PART ALTERNATION MARK * marks the start of a song part in Japanese - ~ 303D FE0E text style - ~ 303D FE0F emoji style @ Special CJK indicators @+ These are visibly displayed graphic characters, not invisible format control characters. 303E IDEOGRAPHIC VARIATION INDICATOR * visual indicator that the following ideograph is to be taken as a variant of the intended character 303F IDEOGRAPHIC HALF FILL SPACE * visual indicator of a screen space for half of an ideograph -@~ ! @@ 3040 Hiragana 309F @ Hiragana letters 3041 HIRAGANA LETTER SMALL A @@ -19764,9 +20176,11 @@ 312A BOPOMOFO LETTER V 312B BOPOMOFO LETTER NG 312C BOPOMOFO LETTER GN -@ Miscellaneous addition +@ Miscellaneous additions 312D BOPOMOFO LETTER IH * for analytic representation of apical vowel +312E BOPOMOFO LETTER O WITH DOT ABOVE + * early form of letter e @@ 3130 Hangul Compatibility Jamo 318F @ Consonant letters 3131 HANGUL LETTER KIYEOK @@ -20483,14 +20897,10 @@ 3296 CIRCLED IDEOGRAPH FINANCIAL # <circle> 8CA1 3297 CIRCLED IDEOGRAPH CONGRATULATION - ~ 3297 FE0E text style - ~ 3297 FE0F emoji style # <circle> 795D 3298 CIRCLED IDEOGRAPH LABOR # <circle> 52B4 3299 CIRCLED IDEOGRAPH SECRET - ~ 3299 FE0E text style - ~ 3299 FE0F emoji style # <circle> 79D8 329A CIRCLED IDEOGRAPH MALE # <circle> 7537 @@ -20700,7 +21110,6 @@ # <circle> 30F1 32FE CIRCLED KATAKANA WO # <circle> 30F2 -@~ ! @@ 3300 CJK Compatibility 33FF @ Squared Katakana words 3300 SQUARE APAATO @@ -20836,7 +21245,8 @@ * percent # <square> 30D1 30FC 30BB 30F3 30C8 332C SQUARE PAATU - * parts + * a mistaken, unused representation originally intended for the Thai baht currency sign + x (thai currency symbol baht - 0E3F) # <square> 30D1 30FC 30C4 332D SQUARE BAARERU * barrel @@ -21383,7 +21793,7 @@ 4DFD HEXAGRAM FOR SMALL PREPONDERANCE 4DFE HEXAGRAM FOR AFTER COMPLETION 4DFF HEXAGRAM FOR BEFORE COMPLETION -@@ 4E00 CJK Unified Ideographs 9FD5 +@@ 4E00 CJK Unified Ideographs 9FEA @@ A000 Yi Syllables A48F @@+ @ Syllables @@ -23107,12 +23517,15 @@ A67B COMBINING CYRILLIC LETTER OMEGA A67C COMBINING CYRILLIC KAVYKA * indicates an alternative reading to part of a word x (combining breve - 0306) + x (combining kavyka above right - 1DF6) + x (combining kavyka above left - 1DF7) A67D COMBINING CYRILLIC PAYEROK * may indicate an omitted yer x (combining vertical tilde - 033E) @ Punctuation mark A67E CYRILLIC KAVYKA * used to mark off word that has alternative reading + x (low kavyka - 2E47) @ Modifier letter A67F CYRILLIC PAYEROK * may indicate an omitted yer @@ -23447,7 +23860,7 @@ A78E LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT * used to transcribe Toda @ Transliteration letter A78F LATIN LETTER SINOLOGICAL DOT - * used for transliteration for Phags-Pa and phonetic transcription for Tangut + * used in transliteration of Phags-Pa and in phonetic transcription of Tangut x (middle dot - 00B7) @ Additional letters A790 LATIN CAPITAL LETTER N WITH DESCENDER @@ -23500,6 +23913,10 @@ A7AC LATIN CAPITAL LETTER SCRIPT G * lowercase is 0261 A7AD LATIN CAPITAL LETTER L WITH BELT * lowercase is 026C +@ Letter for West African languages +A7AE LATIN CAPITAL LETTER SMALL CAPITAL I + * lowercase is 026A + * also used in Unifon @ Letters for Americanist orthographies A7B0 LATIN CAPITAL LETTER TURNED K * lowercase is 029E @@ -23511,7 +23928,7 @@ A7B2 LATIN CAPITAL LETTER J WITH CROSSED-TAIL * lowercase is 029D @ Letter for German dialectology A7B3 LATIN CAPITAL LETTER CHI - * lower case is AB53 + * lowercase is AB53 x (greek capital letter chi - 03A7) @ Letters for African languages A7B4 LATIN CAPITAL LETTER BETA @@ -23854,6 +24271,8 @@ A8C2 SAURASHTRA VOWEL SIGN OO A8C3 SAURASHTRA VOWEL SIGN AU @ Virama A8C4 SAURASHTRA SIGN VIRAMA +@ Sign +A8C5 SAURASHTRA SIGN CANDRABINDU @ Punctuation A8CE SAURASHTRA DANDA A8CF SAURASHTRA DOUBLE DANDA @@ -23941,6 +24360,8 @@ A8FB DEVANAGARI HEADSTROKE A8FC DEVANAGARI SIGN SIDDHAM = siddhirastu * used at the beginning of texts as an invocation + x (tibetan mark initial yig mgo mdun ma - 0F04) + x (mongolian birga - 1800) x (sharada sign siddham - 111DB) A8FD DEVANAGARI JAIN OM @@ A900 Kayah Li A92F @@ -24357,21 +24778,31 @@ AA5F CHAM PUNCTUATION TRIPLE DANDA @@ AA60 Myanmar Extended-A AA7F @ Khamti Shan consonants AA60 MYANMAR LETTER KHAMTI GA + ~ AA60 FE00 dotted form AA61 MYANMAR LETTER KHAMTI CA + ~ AA61 FE00 dotted form AA62 MYANMAR LETTER KHAMTI CHA + ~ AA62 FE00 dotted form AA63 MYANMAR LETTER KHAMTI JA + ~ AA63 FE00 dotted form AA64 MYANMAR LETTER KHAMTI JHA + ~ AA64 FE00 dotted form AA65 MYANMAR LETTER KHAMTI NYA + ~ AA65 FE00 dotted form AA66 MYANMAR LETTER KHAMTI TTA + ~ AA66 FE00 dotted form AA67 MYANMAR LETTER KHAMTI TTHA AA68 MYANMAR LETTER KHAMTI DDA AA69 MYANMAR LETTER KHAMTI DDHA AA6A MYANMAR LETTER KHAMTI DHA AA6B MYANMAR LETTER KHAMTI NA + ~ AA6B FE00 dotted form AA6C MYANMAR LETTER KHAMTI SA + ~ AA6C FE00 dotted form AA6D MYANMAR LETTER KHAMTI HA AA6E MYANMAR LETTER KHAMTI HHA AA6F MYANMAR LETTER KHAMTI FA + ~ AA6F FE00 dotted form AA70 MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION x (myanmar modifier letter shan reduplication - A9E6) AA71 MYANMAR LETTER KHAMTI XA @@ -24386,6 +24817,7 @@ AA77 MYANMAR SYMBOL AITON EXCLAMATION AA78 MYANMAR SYMBOL AITON ONE AA79 MYANMAR SYMBOL AITON TWO AA7A MYANMAR LETTER AITON RA + ~ AA7A FE00 dotted form @ Pa'o Karen tone mark AA7B MYANMAR SIGN PAO KAREN TONE @ Tai Laing tone marks @@ -24394,6 +24826,7 @@ AA7D MYANMAR SIGN TAI LAING TONE-5 @ Shwe Palaung letters AA7E MYANMAR LETTER SHWE PALAUNG CHA AA7F MYANMAR LETTER SHWE PALAUNG SHA +@~ ! @@ AA80 Tai Viet AADF @ Consonants AA80 TAI VIET LETTER LOW KO @@ -24613,6 +25046,7 @@ AB5B MODIFIER BREVE WITH INVERTED BREVE x (breve - 02D8) x (close up - 2050) x (metrical breve - 23D1) + x (inverted low kavyka with kavyka above - 2E46) AB5C MODIFIER LETTER SMALL HENG # <super> A727 AB5D MODIFIER LETTER SMALL L WITH INVERTED LAZY S @@ -25011,6 +25445,9 @@ F92A CJK COMPATIBILITY IDEOGRAPH-F92A F92B CJK COMPATIBILITY IDEOGRAPH-F92B : 72FC F92C CJK COMPATIBILITY IDEOGRAPH-F92C + * a mapping change removed the original K0 source + x (cjk unified ideograph-90DE - 90DE) + x (cjk compatibility ideograph-FA2E - FA2E) : 90CE F92D CJK COMPATIBILITY IDEOGRAPH-F92D : 4F86 @@ -25291,7 +25728,9 @@ F9B6 CJK COMPATIBILITY IDEOGRAPH-F9B6 F9B7 CJK COMPATIBILITY IDEOGRAPH-F9B7 : 91B4 F9B8 CJK COMPATIBILITY IDEOGRAPH-F9B8 + * a mapping change removed the original K0 source x (cjk unified ideograph-96B7 - 96B7) + x (cjk compatibility ideograph-FA2F - FA2F) : 96B8 F9B9 CJK COMPATIBILITY IDEOGRAPH-F9B9 : 60E1 @@ -26956,6 +27395,7 @@ FD3D ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM # <isolated> 0627 064B @ Punctuation @+ For legacy reasons, these parentheses do not mirror in bidirectional display and do not have the Bidi_Paired_Bracket property. +@+ These parentheses also do not have compatibility decompositions and should not be considered presentation forms. FD3E ORNATE LEFT PARENTHESIS FD3F ORNATE RIGHT PARENTHESIS @ Ligatures (three elements) @@ -27241,6 +27681,8 @@ FDF3 ARABIC LIGATURE AKBAR ISOLATED FORM FDF4 ARABIC LIGATURE MOHAMMAD ISOLATED FORM # <isolated> 0645 062D 0645 062F FDF5 ARABIC LIGATURE SALAM ISOLATED FORM + * common abbreviation for sallallahou alayhe wasallam + x (arabic ligature sallallahou alayhe wasallam - FDFA) # <isolated> 0635 0644 0639 0645 FDF6 ARABIC LIGATURE RASOUL ISOLATED FORM # <isolated> 0631 0633 0648 0644 @@ -27258,10 +27700,11 @@ FDFB ARABIC LIGATURE JALLAJALALOUHOU FDFC RIAL SIGN # <isolated> 0631 06CC 0627 0644 @ Symbol +@+ The bismillah is treated as an atomic symbol, rather than as a word ligature. It has no decomposition. FDFD ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM @@ FE00 Variation Selectors FE0F @ Variation selectors -@+ Combining characters; in conjunction with the preceding character these indicate a predetermined choice of variant glyph +@+ These are combining characters; in conjunction with the preceding character they indicate a predetermined choice of variant glyph. FE00 VARIATION SELECTOR-1 * these are abbreviated VS1, and so on FE01 VARIATION SELECTOR-2 @@ -27277,8 +27720,12 @@ FE0A VARIATION SELECTOR-11 FE0B VARIATION SELECTOR-12 FE0C VARIATION SELECTOR-13 FE0D VARIATION SELECTOR-14 +@ Emoji-specific variation selectors +@+ For documentation about use of these with emoji, see UTS #51, Unicode Emoji. FE0E VARIATION SELECTOR-15 + = text variation selector FE0F VARIATION SELECTOR-16 + = emoji variation selector @@ FE10 Vertical Forms FE1F @+ These characters are compatibility characters needed to map to GB 18030. @ Glyphs for vertical variants @@ -27343,6 +27790,7 @@ FE2D COMBINING CONJOINING MACRON BELOW @+ These are used for supralineation in Church Slavonic texts. FE2E COMBINING CYRILLIC TITLO LEFT HALF FE2F COMBINING CYRILLIC TITLO RIGHT HALF + x (combining cyrillic titlo - 0483) @@ FE30 CJK Compatibility Forms FE4F @ Glyphs for vertical variants FE30 PRESENTATION FORM FOR VERTICAL TWO DOT LEADER @@ -28498,6 +28946,7 @@ FFFF <not a character> 100E6 LINEAR B IDEOGRAM VESSEL B207 100E7 LINEAR B IDEOGRAM VESSEL B208 100E8 LINEAR B IDEOGRAM VESSEL B209 + x (amphora - 1F3FA) 100E9 LINEAR B IDEOGRAM VESSEL B210 100EA LINEAR B IDEOGRAM VESSEL B211 100EB LINEAR B IDEOGRAM VESSEL B212 @@ -28661,9 +29110,13 @@ FFFF <not a character> 10189 GREEK TRYBLION BASE SIGN 1018A GREEK ZERO SIGN 1018B GREEK ONE QUARTER SIGN -@ Ancient Greek symbol +@ Ancient Greek symbols 1018C GREEK SINUSOID SIGN * designates year +1018D GREEK INDICTION SIGN + * timekeeping +1018E NOMISMA SIGN + * currency sign and marker of weight @@ 10190 Ancient Symbols 101CF @ Roman weights and measures 10190 ROMAN SEXTANS SIGN @@ -28898,6 +29351,10 @@ FFFF <not a character> 10321 OLD ITALIC NUMERAL FIVE 10322 OLD ITALIC NUMERAL TEN 10323 OLD ITALIC NUMERAL FIFTY +@ North Italic letters +1032D OLD ITALIC LETTER YE +1032E OLD ITALIC LETTER NORTHERN TSE +1032F OLD ITALIC LETTER SOUTHERN TSE @@ 10330 Gothic 1034F @ Letters 10330 GOTHIC LETTER AHSA @@ -29147,7 +29604,8 @@ FFFF <not a character> 1044E DESERET SMALL LETTER OI 1044F DESERET SMALL LETTER EW @@ 10450 Shavian 1047F -@ Consonants +@ Tall and deep letters (consonants) +@+ Shavian tall letters mostly represent voiceless obstruents, whereas the deep letters represent the voiced counterparts. 10450 SHAVIAN LETTER PEEP 10451 SHAVIAN LETTER TOT 10452 SHAVIAN LETTER KICK @@ -29157,7 +29615,9 @@ FFFF <not a character> 10456 SHAVIAN LETTER SURE 10457 SHAVIAN LETTER CHURCH 10458 SHAVIAN LETTER YEA + * voiced palatal approximant 10459 SHAVIAN LETTER HUNG + * voiced velar nasal 1045A SHAVIAN LETTER BIB 1045B SHAVIAN LETTER DEAD 1045C SHAVIAN LETTER GAG @@ -29167,10 +29627,13 @@ FFFF <not a character> 10460 SHAVIAN LETTER MEASURE 10461 SHAVIAN LETTER JUDGE 10462 SHAVIAN LETTER WOE + * voiced labiovelar approximant 10463 SHAVIAN LETTER HA-HA + * voiceless glottal fricative +@ Short letters +@+ Shavian short letters mostly represent vowels, but also include some nasals and liquids. 10464 SHAVIAN LETTER LOLL 10465 SHAVIAN LETTER MIME -@ Vowels 10466 SHAVIAN LETTER IF 10467 SHAVIAN LETTER EGG 10468 SHAVIAN LETTER ASH @@ -29189,6 +29652,8 @@ FFFF <not a character> 10475 SHAVIAN LETTER OOZE 10476 SHAVIAN LETTER OIL 10477 SHAVIAN LETTER AWE +@ Ligatures +@+ Shavian ligatures represent r-colored vowels or diphthongs. 10478 SHAVIAN LETTER ARE 10479 SHAVIAN LETTER OR 1047A SHAVIAN LETTER AIR @@ -29240,6 +29705,81 @@ FFFF <not a character> 104A7 OSMANYA DIGIT SEVEN 104A8 OSMANYA DIGIT EIGHT 104A9 OSMANYA DIGIT NINE +@@ 104B0 Osage 104FF +@ Uppercase letters +104B0 OSAGE CAPITAL LETTER A +104B1 OSAGE CAPITAL LETTER AI +104B2 OSAGE CAPITAL LETTER AIN +104B3 OSAGE CAPITAL LETTER AH +104B4 OSAGE CAPITAL LETTER BRA +104B5 OSAGE CAPITAL LETTER CHA +104B6 OSAGE CAPITAL LETTER EHCHA +104B7 OSAGE CAPITAL LETTER E +104B8 OSAGE CAPITAL LETTER EIN +104B9 OSAGE CAPITAL LETTER HA +104BA OSAGE CAPITAL LETTER HYA +104BB OSAGE CAPITAL LETTER I +104BC OSAGE CAPITAL LETTER KA +104BD OSAGE CAPITAL LETTER EHKA +104BE OSAGE CAPITAL LETTER KYA +104BF OSAGE CAPITAL LETTER LA +104C0 OSAGE CAPITAL LETTER MA +104C1 OSAGE CAPITAL LETTER NA +104C2 OSAGE CAPITAL LETTER O +104C3 OSAGE CAPITAL LETTER OIN +104C4 OSAGE CAPITAL LETTER PA +104C5 OSAGE CAPITAL LETTER EHPA +104C6 OSAGE CAPITAL LETTER SA +104C7 OSAGE CAPITAL LETTER SHA +104C8 OSAGE CAPITAL LETTER TA +104C9 OSAGE CAPITAL LETTER EHTA +104CA OSAGE CAPITAL LETTER TSA +104CB OSAGE CAPITAL LETTER EHTSA +104CC OSAGE CAPITAL LETTER TSHA +104CD OSAGE CAPITAL LETTER DHA +104CE OSAGE CAPITAL LETTER U +104CF OSAGE CAPITAL LETTER WA +104D0 OSAGE CAPITAL LETTER KHA +104D1 OSAGE CAPITAL LETTER GHA +104D2 OSAGE CAPITAL LETTER ZA +104D3 OSAGE CAPITAL LETTER ZHA +@ Lowercase letters +104D8 OSAGE SMALL LETTER A +104D9 OSAGE SMALL LETTER AI +104DA OSAGE SMALL LETTER AIN +104DB OSAGE SMALL LETTER AH +104DC OSAGE SMALL LETTER BRA +104DD OSAGE SMALL LETTER CHA +104DE OSAGE SMALL LETTER EHCHA +104DF OSAGE SMALL LETTER E +104E0 OSAGE SMALL LETTER EIN +104E1 OSAGE SMALL LETTER HA +104E2 OSAGE SMALL LETTER HYA +104E3 OSAGE SMALL LETTER I +104E4 OSAGE SMALL LETTER KA +104E5 OSAGE SMALL LETTER EHKA +104E6 OSAGE SMALL LETTER KYA +104E7 OSAGE SMALL LETTER LA +104E8 OSAGE SMALL LETTER MA +104E9 OSAGE SMALL LETTER NA +104EA OSAGE SMALL LETTER O +104EB OSAGE SMALL LETTER OIN +104EC OSAGE SMALL LETTER PA +104ED OSAGE SMALL LETTER EHPA +104EE OSAGE SMALL LETTER SA +104EF OSAGE SMALL LETTER SHA +104F0 OSAGE SMALL LETTER TA +104F1 OSAGE SMALL LETTER EHTA +104F2 OSAGE SMALL LETTER TSA +104F3 OSAGE SMALL LETTER EHTSA +104F4 OSAGE SMALL LETTER TSHA +104F5 OSAGE SMALL LETTER DHA +104F6 OSAGE SMALL LETTER U +104F7 OSAGE SMALL LETTER WA +104F8 OSAGE SMALL LETTER KHA +104F9 OSAGE SMALL LETTER GHA +104FA OSAGE SMALL LETTER ZA +104FB OSAGE SMALL LETTER ZHA @@ 10500 Elbasan 1052F @ Letters 10500 ELBASAN LETTER A @@ -29865,7 +30405,7 @@ FFFF <not a character> 1074F LINEAR A SIGN A712 Y x (runic letter wunjo wynn w - 16B9) 10750 LINEAR A SIGN A713 OMEGA - * used with 106A5 linear a sign a405-vas + * used with 106A5 linear a sign a405-vas 10751 LINEAR A SIGN A714 ABB 10752 LINEAR A SIGN A715 BB 10753 LINEAR A SIGN A717 DD @@ -30145,10 +30685,10 @@ FFFF <not a character> 1091B PHOENICIAN NUMBER THREE @ Punctuation 1091F PHOENICIAN WORD SEPARATOR + * sometimes shown with a glyph for a short vertical bar x (full stop - 002E) x (middle dot - 00B7) x (word separator middle dot - 2E31) - * sometimes shown with a glyph for a short vertical bar @@ 10920 Lydian 1093F @ Letters 10920 LYDIAN LETTER A @@ -31309,7 +31849,7 @@ FFFF <not a character> 1106F BRAHMI DIGIT NINE @ Number joiner 1107F BRAHMI NUMBER JOINER - * used to form ligatures between Brahmi numbers signifying multiplication + * a virama used to form ligatures between Brahmi numbers signifying multiplication @@ 11080 Kaithi 110CF @ Various signs 11080 KAITHI SIGN CANDRABINDU @@ -31543,6 +32083,7 @@ FFFF <not a character> x (myanmar sign virama - 1039) 11134 CHAKMA MAAYYAA * killer + * also used distinctly as a gemination mark which can occur with vowels x (myanmar sign asat - 103A) @ Digits 11136 CHAKMA DIGIT ZERO @@ -31825,6 +32366,9 @@ FFFF <not a character> * delimits larger chunks of text, such as paragraphs x (kaithi double section mark - 110BF) 1123D KHOJKI ABBREVIATION SIGN +@ Sign +1123E KHOJKI SIGN SUKUN + * used for Arabic transliteration @@ 11280 Multani 112AF @ Vowels 11280 MULTANI LETTER A @@ -31945,6 +32489,7 @@ FFFF <not a character> 112F8 KHUDAWADI DIGIT EIGHT 112F9 KHUDAWADI DIGIT NINE @@ 11300 Grantha 1137F +@+ The Grantha script uses digits from the Tamil block. @ Various signs 11300 GRANTHA SIGN COMBINING ANUSVARA ABOVE * used in Prakrit language Jain texts for the linguistic anusvara @@ -32050,8 +32595,140 @@ FFFF <not a character> 11372 COMBINING GRANTHA LETTER NA 11373 COMBINING GRANTHA LETTER VI 11374 COMBINING GRANTHA LETTER PA +@@ 11400 Newa 1147F +@+ This script is also known as Nepaalalipi, Nepalakshar, Newah Akhah, Pachumol, Prachalit, and other names. +@ Independent vowels +@+ Some of the vowels are only used for Sanskrit, and are not needed for Nepal Bhasa. +11400 NEWA LETTER A +11401 NEWA LETTER AA +11402 NEWA LETTER I +11403 NEWA LETTER II +11404 NEWA LETTER U +11405 NEWA LETTER UU +11406 NEWA LETTER VOCALIC R +11407 NEWA LETTER VOCALIC RR +11408 NEWA LETTER VOCALIC L +11409 NEWA LETTER VOCALIC LL +1140A NEWA LETTER E +1140B NEWA LETTER AI +1140C NEWA LETTER O +1140D NEWA LETTER AU +@ Consonants +@+ Six consonant letters involving ha are encoded for the representation of murmured resonants in Nepal Bhasa, a Tibeto-Burman language. Those letters are not used for the representation of Sanskrit in the Newa script. +1140E NEWA LETTER KA +1140F NEWA LETTER KHA +11410 NEWA LETTER GA +11411 NEWA LETTER GHA +11412 NEWA LETTER NGA +11413 NEWA LETTER NGHA + * murmured nasal for Nepal Bhasa language +11414 NEWA LETTER CA +11415 NEWA LETTER CHA +11416 NEWA LETTER JA +11417 NEWA LETTER JHA +11418 NEWA LETTER NYA +11419 NEWA LETTER NYHA + * murmured nasal for Nepal Bhasa language +1141A NEWA LETTER TTA +1141B NEWA LETTER TTHA +1141C NEWA LETTER DDA +1141D NEWA LETTER DDHA +1141E NEWA LETTER NNA +1141F NEWA LETTER TA +11420 NEWA LETTER THA +11421 NEWA LETTER DA +11422 NEWA LETTER DHA +11423 NEWA LETTER NA +11424 NEWA LETTER NHA + * murmured nasal for Nepal Bhasa language +11425 NEWA LETTER PA +11426 NEWA LETTER PHA +11427 NEWA LETTER BA +11428 NEWA LETTER BHA +11429 NEWA LETTER MA +1142A NEWA LETTER MHA + * murmured nasal for Nepal Bhasa language +1142B NEWA LETTER YA +1142C NEWA LETTER RA +1142D NEWA LETTER RHA + * murmured tap for Nepal Bhasa language +1142E NEWA LETTER LA +1142F NEWA LETTER LHA + * murmured lateral for Nepal Bhasa language +11430 NEWA LETTER WA +11431 NEWA LETTER SHA +11432 NEWA LETTER SSA +11433 NEWA LETTER SA +11434 NEWA LETTER HA +@ Dependent vowel signs +@+ Some of the vowel signs are only used for Sanskrit, and are not needed for Nepal Bhasa. +11435 NEWA VOWEL SIGN AA +11436 NEWA VOWEL SIGN I +11437 NEWA VOWEL SIGN II +11438 NEWA VOWEL SIGN U +11439 NEWA VOWEL SIGN UU +1143A NEWA VOWEL SIGN VOCALIC R +1143B NEWA VOWEL SIGN VOCALIC RR +1143C NEWA VOWEL SIGN VOCALIC L +1143D NEWA VOWEL SIGN VOCALIC LL +1143E NEWA VOWEL SIGN E +1143F NEWA VOWEL SIGN AI +11440 NEWA VOWEL SIGN O +11441 NEWA VOWEL SIGN AU +@ Various signs +11442 NEWA SIGN VIRAMA + = tutisaalaa +11443 NEWA SIGN CANDRABINDU + = milaaphuti +11444 NEWA SIGN ANUSVARA + = sinhaphuti +11445 NEWA SIGN VISARGA + = liphuti +11446 NEWA SIGN NUKTA +11447 NEWA SIGN AVAGRAHA + = sulaa +11448 NEWA SIGN FINAL ANUSVARA + = baadipu +@ Invocation signs +11449 NEWA OM +1144A NEWA SIDDHI +@ Punctuation +1144B NEWA DANDA + = dipu +1144C NEWA DOUBLE DANDA +1144D NEWA COMMA + = jhaasu +1144E NEWA GAP FILLER + = thaayjaayekaa +1144F NEWA ABBREVIATION SIGN +@ Digits +11450 NEWA DIGIT ZERO + = guli +11451 NEWA DIGIT ONE + = chi +11452 NEWA DIGIT TWO + = nasi +11453 NEWA DIGIT THREE + = swa +11454 NEWA DIGIT FOUR + = pi +11455 NEWA DIGIT FIVE + = njaa +11456 NEWA DIGIT SIX + = khu +11457 NEWA DIGIT SEVEN + = nhasa +11458 NEWA DIGIT EIGHT + = cyaa +11459 NEWA DIGIT NINE + = gu +@ Various signs +1145B NEWA PLACEHOLDER MARK + = jaayekaa +1145D NEWA INSERTION SIGN + = tansaa @@ 11480 Tirhuta 114DF -@+ The Tirhuta script is also known by the names 'Mithilakshara' and 'Maithili'. +@+ The Tirhuta script is also known by the names Mithilakshara and Maithili. @ Sign 11480 TIRHUTA ANJI @ Independent vowels @@ -32353,6 +33030,22 @@ FFFF <not a character> 11657 MODI DIGIT SEVEN 11658 MODI DIGIT EIGHT 11659 MODI DIGIT NINE +@@ 11660 Mongolian Supplement 1167F +@ Punctuation +11660 MONGOLIAN BIRGA WITH ORNAMENT + x (mongolian birga - 1800) +11661 MONGOLIAN ROTATED BIRGA +11662 MONGOLIAN DOUBLE BIRGA WITH ORNAMENT +11663 MONGOLIAN TRIPLE BIRGA WITH ORNAMENT +11664 MONGOLIAN BIRGA WITH DOUBLE ORNAMENT +11665 MONGOLIAN ROTATED BIRGA WITH ORNAMENT +11666 MONGOLIAN ROTATED BIRGA WITH DOUBLE ORNAMENT +11667 MONGOLIAN INVERTED BIRGA +11668 MONGOLIAN INVERTED BIRGA WITH DOUBLE ORNAMENT +11669 MONGOLIAN SWIRL BIRGA +1166A MONGOLIAN SWIRL BIRGA WITH ORNAMENT +1166B MONGOLIAN SWIRL BIRGA WITH DOUBLE ORNAMENT +1166C MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT @@ 11680 Takri 116CF @ Independent vowels 11680 TAKRI LETTER A @@ -32584,6 +33277,232 @@ FFFF <not a character> 118F2 WARANG CITI NUMBER NINETY @ Sign 118FF WARANG CITI OM +@@ 11A00 Zanabazar Square 11A4F +@+ The common Mongolian name for the script is Zanabazarin Dörböljin Useg. It is also known as Xewtee Dörböljin Bicig or in English as the Horizontal Square Script. +@ Vowel letter +11A00 ZANABAZAR SQUARE LETTER A + * used for representing independent vowels in combination with vowel signs +@ Vowel signs +11A01 ZANABAZAR SQUARE VOWEL SIGN I +11A02 ZANABAZAR SQUARE VOWEL SIGN UE +11A03 ZANABAZAR SQUARE VOWEL SIGN U +11A04 ZANABAZAR SQUARE VOWEL SIGN E +11A05 ZANABAZAR SQUARE VOWEL SIGN OE +11A06 ZANABAZAR SQUARE VOWEL SIGN O +11A07 ZANABAZAR SQUARE VOWEL SIGN AI + * also represents secondary vowel i +11A08 ZANABAZAR SQUARE VOWEL SIGN AU + * also represents secondary vowel u +11A09 ZANABAZAR SQUARE VOWEL SIGN REVERSED I + * used for Sanskrit vocalic sounds +@ Vowel length mark +11A0A ZANABAZAR SQUARE VOWEL LENGTH MARK +@ Consonants +11A0B ZANABAZAR SQUARE LETTER KA +11A0C ZANABAZAR SQUARE LETTER KHA +11A0D ZANABAZAR SQUARE LETTER GA +11A0E ZANABAZAR SQUARE LETTER GHA +11A0F ZANABAZAR SQUARE LETTER NGA +11A10 ZANABAZAR SQUARE LETTER CA +11A11 ZANABAZAR SQUARE LETTER CHA +11A12 ZANABAZAR SQUARE LETTER JA +11A13 ZANABAZAR SQUARE LETTER NYA +11A14 ZANABAZAR SQUARE LETTER TTA +11A15 ZANABAZAR SQUARE LETTER TTHA +11A16 ZANABAZAR SQUARE LETTER DDA +11A17 ZANABAZAR SQUARE LETTER DDHA +11A18 ZANABAZAR SQUARE LETTER NNA +11A19 ZANABAZAR SQUARE LETTER TA +11A1A ZANABAZAR SQUARE LETTER THA +11A1B ZANABAZAR SQUARE LETTER DA +11A1C ZANABAZAR SQUARE LETTER DHA +11A1D ZANABAZAR SQUARE LETTER NA +11A1E ZANABAZAR SQUARE LETTER PA +11A1F ZANABAZAR SQUARE LETTER PHA +11A20 ZANABAZAR SQUARE LETTER BA + * also used instead of non-initial 11A2D in conjuncts +11A21 ZANABAZAR SQUARE LETTER BHA +11A22 ZANABAZAR SQUARE LETTER MA +11A23 ZANABAZAR SQUARE LETTER TSA +11A24 ZANABAZAR SQUARE LETTER TSHA +11A25 ZANABAZAR SQUARE LETTER DZA +11A26 ZANABAZAR SQUARE LETTER DZHA +11A27 ZANABAZAR SQUARE LETTER ZHA +11A28 ZANABAZAR SQUARE LETTER ZA +11A29 ZANABAZAR SQUARE LETTER -A + * Mongolian aang + * Tibetan a-chung + x (tibetan letter -a - 0F60) +11A2A ZANABAZAR SQUARE LETTER YA +11A2B ZANABAZAR SQUARE LETTER RA +11A2C ZANABAZAR SQUARE LETTER LA +11A2D ZANABAZAR SQUARE LETTER VA +11A2E ZANABAZAR SQUARE LETTER SHA +11A2F ZANABAZAR SQUARE LETTER SSA +11A30 ZANABAZAR SQUARE LETTER SA +11A31 ZANABAZAR SQUARE LETTER HA +11A32 ZANABAZAR SQUARE LETTER KSSA +@ Final consonant mark +11A33 ZANABAZAR SQUARE FINAL CONSONANT MARK + * used for marking a syllable-final consonant in Mongolian + * indicates a syllabic boundary in Mongolian +@ Virama +11A34 ZANABAZAR SQUARE SIGN VIRAMA + * indicates a bare consonant in Sanskrit and Tibetan + * not used for conjunct formation + x (tibetan mark halanta - 0F84) +@ Candrabindu and candra ornaments +11A35 ZANABAZAR SQUARE SIGN CANDRABINDU + * indicates nasalization + x (tibetan sign sna ldan - 0F83) + x (mongolian letter ali gali anusvara one - 1880) +11A36 ZANABAZAR SQUARE SIGN CANDRABINDU WITH ORNAMENT + * used primarily with 11A3F +11A37 ZANABAZAR SQUARE SIGN CANDRA WITH ORNAMENT + * used primarily with 11A3F + x (tibetan sign nyi zla naa da - 0F82) +@ Signs for Sanskrit +11A38 ZANABAZAR SQUARE SIGN ANUSVARA + * indicates nasalization + x (tibetan sign rjes su nga ro - 0F7E) +11A39 ZANABAZAR SQUARE SIGN VISARGA + * indicates post-vocalic aspiration + x (tibetan sign rnam bcad - 0F7F) +@ Cluster-initial consonant +11A3A ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA + * initial form of 11A2B in Tibetan conjuncts +@ Cluster-final consonants +11A3B ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA + * final form of 11A2A in Tibetan conjuncts +11A3C ZANABAZAR SQUARE CLUSTER-FINAL LETTER RA + * final form of 11A2B in Tibetan conjuncts +11A3D ZANABAZAR SQUARE CLUSTER-FINAL LETTER LA + * final form of 11A2C in Tibetan conjuncts +11A3E ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA + * final form of 11A2D in Tibetan conjuncts +@ Head marks +11A3F ZANABAZAR SQUARE INITIAL HEAD MARK + x (tibetan mark initial brda rnying yig mgo mdun ma - 0FD3) + x (mongolian birga - 1800) +11A40 ZANABAZAR SQUARE CLOSING HEAD MARK + x (tibetan mark closing brda rnying yig mgo sgab ma - 0FD4) +@ Punctuation +11A41 ZANABAZAR SQUARE MARK TSHEG + x (tibetan mark intersyllabic tsheg - 0F0B) +11A42 ZANABAZAR SQUARE MARK SHAD + x (tibetan mark shad - 0F0D) +11A43 ZANABAZAR SQUARE MARK DOUBLE SHAD + x (tibetan mark nyis shad - 0F0E) +11A44 ZANABAZAR SQUARE MARK LONG TSHEG + x (tibetan mark gter tsheg - 0F14) +@ Head marks +11A45 ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK + x (tibetan mark initial yig mgo mdun ma - 0F04) +11A46 ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK + x (tibetan mark closing yig mgo sgab ma - 0F05) +@ Subjoiner +11A47 ZANABAZAR SQUARE SUBJOINER + * used for producing consonant conjuncts +@@ 11A50 Soyombo 11AAF +@ Vowel letter +11A50 SOYOMBO LETTER A + * used for representing independent vowels in combination with vowel signs +@ Vowel signs +11A51 SOYOMBO VOWEL SIGN I +11A52 SOYOMBO VOWEL SIGN UE +11A53 SOYOMBO VOWEL SIGN U +11A54 SOYOMBO VOWEL SIGN E +11A55 SOYOMBO VOWEL SIGN O +11A56 SOYOMBO VOWEL SIGN OE +11A57 SOYOMBO VOWEL SIGN AI +11A58 SOYOMBO VOWEL SIGN AU +11A59 SOYOMBO VOWEL SIGN VOCALIC R +11A5A SOYOMBO VOWEL SIGN VOCALIC L +@ Vowel length mark +11A5B SOYOMBO VOWEL LENGTH MARK +@ Consonants +11A5C SOYOMBO LETTER KA +11A5D SOYOMBO LETTER KHA +11A5E SOYOMBO LETTER GA +11A5F SOYOMBO LETTER GHA +11A60 SOYOMBO LETTER NGA +11A61 SOYOMBO LETTER CA +11A62 SOYOMBO LETTER CHA +11A63 SOYOMBO LETTER JA +11A64 SOYOMBO LETTER JHA +11A65 SOYOMBO LETTER NYA +11A66 SOYOMBO LETTER TTA +11A67 SOYOMBO LETTER TTHA +11A68 SOYOMBO LETTER DDA +11A69 SOYOMBO LETTER DDHA +11A6A SOYOMBO LETTER NNA +11A6B SOYOMBO LETTER TA +11A6C SOYOMBO LETTER THA +11A6D SOYOMBO LETTER DA +11A6E SOYOMBO LETTER DHA +11A6F SOYOMBO LETTER NA +11A70 SOYOMBO LETTER PA +11A71 SOYOMBO LETTER PHA +11A72 SOYOMBO LETTER BA +11A73 SOYOMBO LETTER BHA +11A74 SOYOMBO LETTER MA +11A75 SOYOMBO LETTER TSA +11A76 SOYOMBO LETTER TSHA +11A77 SOYOMBO LETTER DZA +11A78 SOYOMBO LETTER ZHA +11A79 SOYOMBO LETTER ZA +11A7A SOYOMBO LETTER -A +11A7B SOYOMBO LETTER YA +11A7C SOYOMBO LETTER RA +11A7D SOYOMBO LETTER LA +11A7E SOYOMBO LETTER VA +11A7F SOYOMBO LETTER SHA +11A80 SOYOMBO LETTER SSA +11A81 SOYOMBO LETTER SA +11A82 SOYOMBO LETTER HA +11A83 SOYOMBO LETTER KSSA +@ Cluster-initial letters +11A86 SOYOMBO CLUSTER-INITIAL LETTER RA +11A87 SOYOMBO CLUSTER-INITIAL LETTER LA +11A88 SOYOMBO CLUSTER-INITIAL LETTER SHA +11A89 SOYOMBO CLUSTER-INITIAL LETTER SA +@ Final consonant signs +11A8A SOYOMBO FINAL CONSONANT SIGN G +11A8B SOYOMBO FINAL CONSONANT SIGN K +11A8C SOYOMBO FINAL CONSONANT SIGN NG +11A8D SOYOMBO FINAL CONSONANT SIGN D +11A8E SOYOMBO FINAL CONSONANT SIGN N +11A8F SOYOMBO FINAL CONSONANT SIGN B +11A90 SOYOMBO FINAL CONSONANT SIGN M +11A91 SOYOMBO FINAL CONSONANT SIGN R +11A92 SOYOMBO FINAL CONSONANT SIGN L +11A93 SOYOMBO FINAL CONSONANT SIGN SH +11A94 SOYOMBO FINAL CONSONANT SIGN S +11A95 SOYOMBO FINAL CONSONANT SIGN -A + * Mongolian aang + * Tibetan a-chung + x (tibetan letter -a - 0F60) +@ Various signs +11A96 SOYOMBO SIGN ANUSVARA +11A97 SOYOMBO SIGN VISARGA +@ Gemination mark +11A98 SOYOMBO GEMINATION MARK +@ Subjoiner +11A99 SOYOMBO SUBJOINER + * used for producing consonant conjuncts +@ Punctuation +11A9A SOYOMBO MARK TSHEG +11A9B SOYOMBO MARK SHAD +11A9C SOYOMBO MARK DOUBLE SHAD +@ Head marks +11A9E SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME + * national symbol of Mongolia +11A9F SOYOMBO HEAD MARK WITH MOON AND SUN AND FLAME +11AA0 SOYOMBO HEAD MARK WITH MOON AND SUN +@ Terminal marks +11AA1 SOYOMBO TERMINAL MARK-1 +11AA2 SOYOMBO TERMINAL MARK-2 + = cintamani, candamani @@ 11AC0 Pau Cin Hau 11AFF @ Consonants 11AC0 PAU CIN HAU LETTER PA @@ -32646,6 +33565,276 @@ FFFF <not a character> 11AF6 PAU CIN HAU LOW-FALLING TONE LONG FINAL 11AF7 PAU CIN HAU LOW-FALLING TONE FINAL 11AF8 PAU CIN HAU GLOTTAL STOP FINAL +@@ 11C00 Bhaiksuki 11C6F +@ Independent vowels +11C00 BHAIKSUKI LETTER A +11C01 BHAIKSUKI LETTER AA +11C02 BHAIKSUKI LETTER I +11C03 BHAIKSUKI LETTER II +11C04 BHAIKSUKI LETTER U +11C05 BHAIKSUKI LETTER UU +11C06 BHAIKSUKI LETTER VOCALIC R +11C07 BHAIKSUKI LETTER VOCALIC RR +11C08 BHAIKSUKI LETTER VOCALIC L +11C0A BHAIKSUKI LETTER E +11C0B BHAIKSUKI LETTER AI +11C0C BHAIKSUKI LETTER O +11C0D BHAIKSUKI LETTER AU +@ Consonants +11C0E BHAIKSUKI LETTER KA +11C0F BHAIKSUKI LETTER KHA +11C10 BHAIKSUKI LETTER GA +11C11 BHAIKSUKI LETTER GHA +11C12 BHAIKSUKI LETTER NGA +11C13 BHAIKSUKI LETTER CA +11C14 BHAIKSUKI LETTER CHA +11C15 BHAIKSUKI LETTER JA +11C16 BHAIKSUKI LETTER JHA +11C17 BHAIKSUKI LETTER NYA +11C18 BHAIKSUKI LETTER TTA +11C19 BHAIKSUKI LETTER TTHA +11C1A BHAIKSUKI LETTER DDA +11C1B BHAIKSUKI LETTER DDHA +11C1C BHAIKSUKI LETTER NNA +11C1D BHAIKSUKI LETTER TA +11C1E BHAIKSUKI LETTER THA +11C1F BHAIKSUKI LETTER DA +11C20 BHAIKSUKI LETTER DHA +11C21 BHAIKSUKI LETTER NA +11C22 BHAIKSUKI LETTER PA +11C23 BHAIKSUKI LETTER PHA +11C24 BHAIKSUKI LETTER BA +11C25 BHAIKSUKI LETTER BHA +11C26 BHAIKSUKI LETTER MA +11C27 BHAIKSUKI LETTER YA +11C28 BHAIKSUKI LETTER RA +11C29 BHAIKSUKI LETTER LA +11C2A BHAIKSUKI LETTER VA +11C2B BHAIKSUKI LETTER SHA +11C2C BHAIKSUKI LETTER SSA +11C2D BHAIKSUKI LETTER SA +11C2E BHAIKSUKI LETTER HA +@ Dependent vowel signs +11C2F BHAIKSUKI VOWEL SIGN AA +11C30 BHAIKSUKI VOWEL SIGN I +11C31 BHAIKSUKI VOWEL SIGN II +11C32 BHAIKSUKI VOWEL SIGN U +11C33 BHAIKSUKI VOWEL SIGN UU +11C34 BHAIKSUKI VOWEL SIGN VOCALIC R +11C35 BHAIKSUKI VOWEL SIGN VOCALIC RR +11C36 BHAIKSUKI VOWEL SIGN VOCALIC L +11C38 BHAIKSUKI VOWEL SIGN E +11C39 BHAIKSUKI VOWEL SIGN AI +11C3A BHAIKSUKI VOWEL SIGN O +11C3B BHAIKSUKI VOWEL SIGN AU +@ Various signs +11C3C BHAIKSUKI SIGN CANDRABINDU +11C3D BHAIKSUKI SIGN ANUSVARA +11C3E BHAIKSUKI SIGN VISARGA +11C3F BHAIKSUKI SIGN VIRAMA +11C40 BHAIKSUKI SIGN AVAGRAHA +@ Punctuation +11C41 BHAIKSUKI DANDA +11C42 BHAIKSUKI DOUBLE DANDA +11C43 BHAIKSUKI WORD SEPARATOR +@ Gap fillers +11C44 BHAIKSUKI GAP FILLER-1 +11C45 BHAIKSUKI GAP FILLER-2 +@ Digits +11C50 BHAIKSUKI DIGIT ZERO +11C51 BHAIKSUKI DIGIT ONE +11C52 BHAIKSUKI DIGIT TWO +11C53 BHAIKSUKI DIGIT THREE +11C54 BHAIKSUKI DIGIT FOUR +11C55 BHAIKSUKI DIGIT FIVE +11C56 BHAIKSUKI DIGIT SIX +11C57 BHAIKSUKI DIGIT SEVEN +11C58 BHAIKSUKI DIGIT EIGHT +11C59 BHAIKSUKI DIGIT NINE +@ Numbers +11C5A BHAIKSUKI NUMBER ONE +11C5B BHAIKSUKI NUMBER TWO +11C5C BHAIKSUKI NUMBER THREE +11C5D BHAIKSUKI NUMBER FOUR +11C5E BHAIKSUKI NUMBER FIVE +11C5F BHAIKSUKI NUMBER SIX +11C60 BHAIKSUKI NUMBER SEVEN +11C61 BHAIKSUKI NUMBER EIGHT +11C62 BHAIKSUKI NUMBER NINE +11C63 BHAIKSUKI NUMBER TEN +11C64 BHAIKSUKI NUMBER TWENTY +11C65 BHAIKSUKI NUMBER THIRTY +11C66 BHAIKSUKI NUMBER FORTY +11C67 BHAIKSUKI NUMBER FIFTY +11C68 BHAIKSUKI NUMBER SIXTY +11C69 BHAIKSUKI NUMBER SEVENTY +11C6A BHAIKSUKI NUMBER EIGHTY +11C6B BHAIKSUKI NUMBER NINETY +11C6C BHAIKSUKI HUNDREDS UNIT MARK +@@ 11C70 Marchen 11CBF +@ Punctuation +11C70 MARCHEN HEAD MARK + x (left-facing svasti sign - 0FD6) +11C71 MARCHEN MARK SHAD +@ Letters +11C72 MARCHEN LETTER KA +11C73 MARCHEN LETTER KHA +11C74 MARCHEN LETTER GA +11C75 MARCHEN LETTER NGA +11C76 MARCHEN LETTER CA +11C77 MARCHEN LETTER CHA +11C78 MARCHEN LETTER JA +11C79 MARCHEN LETTER NYA +11C7A MARCHEN LETTER TA +11C7B MARCHEN LETTER THA +11C7C MARCHEN LETTER DA +11C7D MARCHEN LETTER NA +11C7E MARCHEN LETTER PA +11C7F MARCHEN LETTER PHA +11C80 MARCHEN LETTER BA +11C81 MARCHEN LETTER MA +11C82 MARCHEN LETTER TSA +11C83 MARCHEN LETTER TSHA +11C84 MARCHEN LETTER DZA +11C85 MARCHEN LETTER WA +11C86 MARCHEN LETTER ZHA +11C87 MARCHEN LETTER ZA +11C88 MARCHEN LETTER -A +11C89 MARCHEN LETTER YA +11C8A MARCHEN LETTER RA +11C8B MARCHEN LETTER LA +11C8C MARCHEN LETTER SHA +11C8D MARCHEN LETTER SA +11C8E MARCHEN LETTER HA +11C8F MARCHEN LETTER A +@ Subjoined letters +11C92 MARCHEN SUBJOINED LETTER KA +11C93 MARCHEN SUBJOINED LETTER KHA +11C94 MARCHEN SUBJOINED LETTER GA +11C95 MARCHEN SUBJOINED LETTER NGA +11C96 MARCHEN SUBJOINED LETTER CA +11C97 MARCHEN SUBJOINED LETTER CHA +11C98 MARCHEN SUBJOINED LETTER JA +11C99 MARCHEN SUBJOINED LETTER NYA +11C9A MARCHEN SUBJOINED LETTER TA +11C9B MARCHEN SUBJOINED LETTER THA +11C9C MARCHEN SUBJOINED LETTER DA +11C9D MARCHEN SUBJOINED LETTER NA +11C9E MARCHEN SUBJOINED LETTER PA +11C9F MARCHEN SUBJOINED LETTER PHA +11CA0 MARCHEN SUBJOINED LETTER BA +11CA1 MARCHEN SUBJOINED LETTER MA +11CA2 MARCHEN SUBJOINED LETTER TSA +11CA3 MARCHEN SUBJOINED LETTER TSHA +11CA4 MARCHEN SUBJOINED LETTER DZA +11CA5 MARCHEN SUBJOINED LETTER WA +11CA6 MARCHEN SUBJOINED LETTER ZHA +11CA7 MARCHEN SUBJOINED LETTER ZA +11CA9 MARCHEN SUBJOINED LETTER YA +11CAA MARCHEN SUBJOINED LETTER RA +11CAB MARCHEN SUBJOINED LETTER LA +11CAC MARCHEN SUBJOINED LETTER SHA +11CAD MARCHEN SUBJOINED LETTER SA +11CAE MARCHEN SUBJOINED LETTER HA +11CAF MARCHEN SUBJOINED LETTER A +@ Dependent vowel signs +11CB0 MARCHEN VOWEL SIGN AA +11CB1 MARCHEN VOWEL SIGN I +11CB2 MARCHEN VOWEL SIGN U +11CB3 MARCHEN VOWEL SIGN E +11CB4 MARCHEN VOWEL SIGN O +@ Various signs +11CB5 MARCHEN SIGN ANUSVARA +11CB6 MARCHEN SIGN CANDRABINDU +@@ 11D00 Masaram Gondi 11D5F +@ Vowels +11D00 MASARAM GONDI LETTER A +11D01 MASARAM GONDI LETTER AA +11D02 MASARAM GONDI LETTER I +11D03 MASARAM GONDI LETTER II +11D04 MASARAM GONDI LETTER U +11D05 MASARAM GONDI LETTER UU +11D06 MASARAM GONDI LETTER E +11D08 MASARAM GONDI LETTER AI +11D09 MASARAM GONDI LETTER O +11D0B MASARAM GONDI LETTER AU +@ Consonants +11D0C MASARAM GONDI LETTER KA +11D0D MASARAM GONDI LETTER KHA +11D0E MASARAM GONDI LETTER GA +11D0F MASARAM GONDI LETTER GHA +11D10 MASARAM GONDI LETTER NGA +11D11 MASARAM GONDI LETTER CA +11D12 MASARAM GONDI LETTER CHA +11D13 MASARAM GONDI LETTER JA +11D14 MASARAM GONDI LETTER JHA +11D15 MASARAM GONDI LETTER NYA +11D16 MASARAM GONDI LETTER TTA +11D17 MASARAM GONDI LETTER TTHA +11D18 MASARAM GONDI LETTER DDA +11D19 MASARAM GONDI LETTER DDHA +11D1A MASARAM GONDI LETTER NNA +11D1B MASARAM GONDI LETTER TA +11D1C MASARAM GONDI LETTER THA +11D1D MASARAM GONDI LETTER DA +11D1E MASARAM GONDI LETTER DHA +11D1F MASARAM GONDI LETTER NA +11D20 MASARAM GONDI LETTER PA +11D21 MASARAM GONDI LETTER PHA +11D22 MASARAM GONDI LETTER BA +11D23 MASARAM GONDI LETTER BHA +11D24 MASARAM GONDI LETTER MA +11D25 MASARAM GONDI LETTER YA +11D26 MASARAM GONDI LETTER RA +11D27 MASARAM GONDI LETTER LA +11D28 MASARAM GONDI LETTER VA +11D29 MASARAM GONDI LETTER SHA +11D2A MASARAM GONDI LETTER SSA +11D2B MASARAM GONDI LETTER SA +11D2C MASARAM GONDI LETTER HA +11D2D MASARAM GONDI LETTER LLA +@ Conjunct letters +11D2E MASARAM GONDI LETTER KSSA +11D2F MASARAM GONDI LETTER JNYA +11D30 MASARAM GONDI LETTER TRA +@ Dependent vowel signs +11D31 MASARAM GONDI VOWEL SIGN AA +11D32 MASARAM GONDI VOWEL SIGN I +11D33 MASARAM GONDI VOWEL SIGN II +11D34 MASARAM GONDI VOWEL SIGN U +11D35 MASARAM GONDI VOWEL SIGN UU +11D36 MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A MASARAM GONDI VOWEL SIGN E +11D3C MASARAM GONDI VOWEL SIGN AI +11D3D MASARAM GONDI VOWEL SIGN O +11D3F MASARAM GONDI VOWEL SIGN AU +@ Various signs +11D40 MASARAM GONDI SIGN ANUSVARA +11D41 MASARAM GONDI SIGN VISARGA +11D42 MASARAM GONDI SIGN NUKTA +11D43 MASARAM GONDI SIGN CANDRA + * used for transcribing foreign vowels +11D44 MASARAM GONDI SIGN HALANTA + * used for silencing the inherent vowel +@ Virama +11D45 MASARAM GONDI VIRAMA + * used for producing conjuncts +@ Cluster-specific consonant forms +11D46 MASARAM GONDI REPHA + * cluster-initial form of 11D26 +11D47 MASARAM GONDI RA-KARA + * cluster-final form of 11D26 +@ Digits +11D50 MASARAM GONDI DIGIT ZERO +11D51 MASARAM GONDI DIGIT ONE +11D52 MASARAM GONDI DIGIT TWO +11D53 MASARAM GONDI DIGIT THREE +11D54 MASARAM GONDI DIGIT FOUR +11D55 MASARAM GONDI DIGIT FIVE +11D56 MASARAM GONDI DIGIT SIX +11D57 MASARAM GONDI DIGIT SEVEN +11D58 MASARAM GONDI DIGIT EIGHT +11D59 MASARAM GONDI DIGIT NINE @@ 12000 Cuneiform 123FF @ Signs 12000 CUNEIFORM SIGN A @@ -35714,7 +36903,7 @@ FFFF <not a character> 14537 ANATOLIAN HIEROGLYPH A276 = frater2 14538 ANATOLIAN HIEROGLYPH A277 - = iudex.la, iudex+la + = iudex.la, iudex+la 14539 ANATOLIAN HIEROGLYPH A278 = syllabic li 1453A ANATOLIAN HIEROGLYPH A279 @@ -37109,11 +38298,11 @@ FFFF <not a character> 16F04 MIAO LETTER MA 16F05 MIAO LETTER MHA 16F06 MIAO LETTER ARCHAIC MA - * used in Pollard's early orthography + * used in Pollard's early orthography 16F07 MIAO LETTER FA 16F08 MIAO LETTER VA 16F09 MIAO LETTER VFA - * used in Black Yi + * used in Black Yi 16F0A MIAO LETTER TA * used for da in Dry Yi 16F0B MIAO LETTER DA @@ -37128,15 +38317,15 @@ FFFF <not a character> 16F12 MIAO LETTER YI NNA * used in Hei Yi 16F13 MIAO LETTER ARCHAIC NA - * used in Pollard's early orthography + * used in Pollard's early orthography 16F14 MIAO LETTER NNA 16F15 MIAO LETTER NNHA 16F16 MIAO LETTER LA 16F17 MIAO LETTER LYA - * used in Black Yi + * used in Black Yi 16F18 MIAO LETTER LHA 16F19 MIAO LETTER LHYA - * used in Black Yi + * used in Black Yi 16F1A MIAO LETTER TLHA 16F1B MIAO LETTER DLHA 16F1C MIAO LETTER TLHYA @@ -37151,7 +38340,7 @@ FFFF <not a character> 16F23 MIAO LETTER NGA 16F24 MIAO LETTER NGHA 16F25 MIAO LETTER ARCHAIC NGA - * used in Pollard's early orthography + * used in Pollard's early orthography 16F26 MIAO LETTER HA 16F27 MIAO LETTER XA @+ * archaic character used in a post-1949 reformed orthography @@ -37173,9 +38362,9 @@ FFFF <not a character> 16F33 MIAO LETTER SHA 16F34 MIAO LETTER SSA 16F35 MIAO LETTER ZHA - * used in Black Yi + * used in Black Yi 16F36 MIAO LETTER ZSHA - * used in Black Yi + * used in Black Yi 16F37 MIAO LETTER TSA * used for dza in Dry Yi 16F38 MIAO LETTER DZA @@ -37184,21 +38373,21 @@ FFFF <not a character> 16F3A MIAO LETTER SA 16F3B MIAO LETTER ZA 16F3C MIAO LETTER ZSA - * used in Black Yi + * used in Black Yi 16F3D MIAO LETTER ZZA 16F3E MIAO LETTER ZZSA - * used in Black Yi + * used in Black Yi 16F3F MIAO LETTER ARCHAIC ZZA - * used in Pollard's early orthography + * used in Pollard's early orthography 16F40 MIAO LETTER ZZYA - * used in Black Yi + * used in Black Yi 16F41 MIAO LETTER ZZSYA - * used in Black Yi + * used in Black Yi 16F42 MIAO LETTER WA 16F43 MIAO LETTER AH * glottal stop 16F44 MIAO LETTER HHA - * used in Black Yi + * used in Black Yi @ Modifiers 16F50 MIAO LETTER NASALIZATION 16F51 MIAO SIGN ASPIRATION @@ -37209,7 +38398,7 @@ FFFF <not a character> @ Vowels and finals 16F54 MIAO VOWEL SIGN A 16F55 MIAO VOWEL SIGN AA - * used in Eastern Lisu + * used in Eastern Lisu 16F56 MIAO VOWEL SIGN AHH * used in Gan Yi 16F57 MIAO VOWEL SIGN AN @@ -37232,7 +38421,7 @@ FFFF <not a character> 16F65 MIAO VOWEL SIGN IO 16F66 MIAO VOWEL SIGN IE 16F67 MIAO VOWEL SIGN II - * used in Eastern Lisu + * used in Eastern Lisu 16F68 MIAO VOWEL SIGN IU 16F69 MIAO VOWEL SIGN ING * also used for in @@ -37242,20 +38431,20 @@ FFFF <not a character> 16F6D MIAO VOWEL SIGN UANG * also used for uaw 16F6E MIAO VOWEL SIGN UU - * used in Eastern Lisu + * used in Eastern Lisu 16F6F MIAO VOWEL SIGN UEI 16F70 MIAO VOWEL SIGN UNG 16F71 MIAO VOWEL SIGN Y 16F72 MIAO VOWEL SIGN YI 16F73 MIAO VOWEL SIGN AE 16F74 MIAO VOWEL SIGN AEE - * used in Eastern Lisu + * used in Eastern Lisu 16F75 MIAO VOWEL SIGN ERR 16F76 MIAO VOWEL SIGN ROUNDED ERR - * used in Eastern Lisu + * used in Eastern Lisu 16F77 MIAO VOWEL SIGN ER 16F78 MIAO VOWEL SIGN ROUNDED ER - * used in Eastern Lisu + * used in Eastern Lisu 16F79 MIAO VOWEL SIGN AI 16F7A MIAO VOWEL SIGN EI 16F7B MIAO VOWEL SIGN AU @@ -37278,18 +38467,1813 @@ FFFF <not a character> 16F98 MIAO LETTER TONE-7 16F99 MIAO LETTER TONE-8 @ Archaic baseline tone marks -@+ These are archaic characters used in a post-1949 reformed orthography. +@+ These are archaic characters used in a post-1949 reformed orthography. 16F9A MIAO LETTER REFORMED TONE-1 16F9B MIAO LETTER REFORMED TONE-2 16F9C MIAO LETTER REFORMED TONE-4 16F9D MIAO LETTER REFORMED TONE-5 16F9E MIAO LETTER REFORMED TONE-6 16F9F MIAO LETTER REFORMED TONE-8 +@@ 16FE0 Ideographic Symbols and Punctuation 16FFF +@ Tangut mark +16FE0 TANGUT ITERATION MARK + x (ideographic iteration mark - 3005) +@ Nushu mark +16FE1 NUSHU ITERATION MARK +@@ 17000 Tangut 187EC +@@ 18800 Tangut Components 18AFF +@+ This is a superset of components used in various Tangut sources. Indexes of components (001..755) used for Tangut ideographs are shown in the Tangut block. +@ One-stroke components +18800 TANGUT COMPONENT-001 +18801 TANGUT COMPONENT-002 +18802 TANGUT COMPONENT-003 +18803 TANGUT COMPONENT-004 +18804 TANGUT COMPONENT-005 +18805 TANGUT COMPONENT-006 +18806 TANGUT COMPONENT-007 +18807 TANGUT COMPONENT-008 +18808 TANGUT COMPONENT-009 +18809 TANGUT COMPONENT-010 +@ Two-stroke components +1880A TANGUT COMPONENT-011 +1880B TANGUT COMPONENT-012 +1880C TANGUT COMPONENT-013 +1880D TANGUT COMPONENT-014 +1880E TANGUT COMPONENT-015 +1880F TANGUT COMPONENT-016 +18810 TANGUT COMPONENT-017 +18811 TANGUT COMPONENT-018 +18812 TANGUT COMPONENT-019 +18813 TANGUT COMPONENT-020 +18814 TANGUT COMPONENT-021 +18815 TANGUT COMPONENT-022 +18816 TANGUT COMPONENT-023 +18817 TANGUT COMPONENT-024 +18818 TANGUT COMPONENT-025 +18819 TANGUT COMPONENT-026 +1881A TANGUT COMPONENT-027 +1881B TANGUT COMPONENT-028 +1881C TANGUT COMPONENT-029 +1881D TANGUT COMPONENT-030 +1881E TANGUT COMPONENT-031 +1881F TANGUT COMPONENT-032 +18820 TANGUT COMPONENT-033 +18821 TANGUT COMPONENT-034 +18822 TANGUT COMPONENT-035 +18823 TANGUT COMPONENT-036 +18824 TANGUT COMPONENT-037 +18825 TANGUT COMPONENT-038 +@ Three-stroke components +18826 TANGUT COMPONENT-039 +18827 TANGUT COMPONENT-040 +18828 TANGUT COMPONENT-041 +18829 TANGUT COMPONENT-042 +1882A TANGUT COMPONENT-043 +1882B TANGUT COMPONENT-044 +1882C TANGUT COMPONENT-045 +1882D TANGUT COMPONENT-046 +1882E TANGUT COMPONENT-047 +1882F TANGUT COMPONENT-048 +18830 TANGUT COMPONENT-049 +18831 TANGUT COMPONENT-050 +18832 TANGUT COMPONENT-051 +18833 TANGUT COMPONENT-052 +18834 TANGUT COMPONENT-053 +18835 TANGUT COMPONENT-054 +18836 TANGUT COMPONENT-055 +18837 TANGUT COMPONENT-056 +18838 TANGUT COMPONENT-057 +18839 TANGUT COMPONENT-058 +1883A TANGUT COMPONENT-059 +1883B TANGUT COMPONENT-060 +1883C TANGUT COMPONENT-061 +1883D TANGUT COMPONENT-062 +1883E TANGUT COMPONENT-063 +1883F TANGUT COMPONENT-064 +18840 TANGUT COMPONENT-065 +18841 TANGUT COMPONENT-066 +18842 TANGUT COMPONENT-067 +18843 TANGUT COMPONENT-068 +18844 TANGUT COMPONENT-069 +18845 TANGUT COMPONENT-070 +18846 TANGUT COMPONENT-071 +18847 TANGUT COMPONENT-072 +18848 TANGUT COMPONENT-073 +18849 TANGUT COMPONENT-074 +1884A TANGUT COMPONENT-075 +1884B TANGUT COMPONENT-076 +1884C TANGUT COMPONENT-077 +1884D TANGUT COMPONENT-078 +1884E TANGUT COMPONENT-079 +1884F TANGUT COMPONENT-080 +18850 TANGUT COMPONENT-081 +18851 TANGUT COMPONENT-082 +18852 TANGUT COMPONENT-083 +18853 TANGUT COMPONENT-084 +18854 TANGUT COMPONENT-085 +18855 TANGUT COMPONENT-086 +18856 TANGUT COMPONENT-087 +18857 TANGUT COMPONENT-088 +18858 TANGUT COMPONENT-089 +18859 TANGUT COMPONENT-090 +1885A TANGUT COMPONENT-091 +1885B TANGUT COMPONENT-092 +1885C TANGUT COMPONENT-093 +1885D TANGUT COMPONENT-094 +1885E TANGUT COMPONENT-095 +1885F TANGUT COMPONENT-096 +@ Four-stroke components +18860 TANGUT COMPONENT-097 +18861 TANGUT COMPONENT-098 +18862 TANGUT COMPONENT-099 +18863 TANGUT COMPONENT-100 +18864 TANGUT COMPONENT-101 +18865 TANGUT COMPONENT-102 +18866 TANGUT COMPONENT-103 +18867 TANGUT COMPONENT-104 +18868 TANGUT COMPONENT-105 +18869 TANGUT COMPONENT-106 +1886A TANGUT COMPONENT-107 +1886B TANGUT COMPONENT-108 +1886C TANGUT COMPONENT-109 +1886D TANGUT COMPONENT-110 +1886E TANGUT COMPONENT-111 +1886F TANGUT COMPONENT-112 +18870 TANGUT COMPONENT-113 +18871 TANGUT COMPONENT-114 +18872 TANGUT COMPONENT-115 +18873 TANGUT COMPONENT-116 +18874 TANGUT COMPONENT-117 +18875 TANGUT COMPONENT-118 +18876 TANGUT COMPONENT-119 +18877 TANGUT COMPONENT-120 +18878 TANGUT COMPONENT-121 +18879 TANGUT COMPONENT-122 +1887A TANGUT COMPONENT-123 +1887B TANGUT COMPONENT-124 +1887C TANGUT COMPONENT-125 +1887D TANGUT COMPONENT-126 +1887E TANGUT COMPONENT-127 +1887F TANGUT COMPONENT-128 +18880 TANGUT COMPONENT-129 +18881 TANGUT COMPONENT-130 +18882 TANGUT COMPONENT-131 +18883 TANGUT COMPONENT-132 +18884 TANGUT COMPONENT-133 +18885 TANGUT COMPONENT-134 +18886 TANGUT COMPONENT-135 +18887 TANGUT COMPONENT-136 +18888 TANGUT COMPONENT-137 +18889 TANGUT COMPONENT-138 +1888A TANGUT COMPONENT-139 +1888B TANGUT COMPONENT-140 +1888C TANGUT COMPONENT-141 +1888D TANGUT COMPONENT-142 +1888E TANGUT COMPONENT-143 +1888F TANGUT COMPONENT-144 +18890 TANGUT COMPONENT-145 +18891 TANGUT COMPONENT-146 +18892 TANGUT COMPONENT-147 +18893 TANGUT COMPONENT-148 +18894 TANGUT COMPONENT-149 +18895 TANGUT COMPONENT-150 +18896 TANGUT COMPONENT-151 +18897 TANGUT COMPONENT-152 +18898 TANGUT COMPONENT-153 +18899 TANGUT COMPONENT-154 +1889A TANGUT COMPONENT-155 +1889B TANGUT COMPONENT-156 +1889C TANGUT COMPONENT-157 +1889D TANGUT COMPONENT-158 +1889E TANGUT COMPONENT-159 +1889F TANGUT COMPONENT-160 +188A0 TANGUT COMPONENT-161 +188A1 TANGUT COMPONENT-162 +188A2 TANGUT COMPONENT-163 +188A3 TANGUT COMPONENT-164 +188A4 TANGUT COMPONENT-165 +188A5 TANGUT COMPONENT-166 +188A6 TANGUT COMPONENT-167 +188A7 TANGUT COMPONENT-168 +188A8 TANGUT COMPONENT-169 +188A9 TANGUT COMPONENT-170 +188AA TANGUT COMPONENT-171 +188AB TANGUT COMPONENT-172 +188AC TANGUT COMPONENT-173 +188AD TANGUT COMPONENT-174 +188AE TANGUT COMPONENT-175 +188AF TANGUT COMPONENT-176 +188B0 TANGUT COMPONENT-177 +188B1 TANGUT COMPONENT-178 +188B2 TANGUT COMPONENT-179 +188B3 TANGUT COMPONENT-180 +188B4 TANGUT COMPONENT-181 +188B5 TANGUT COMPONENT-182 +188B6 TANGUT COMPONENT-183 +188B7 TANGUT COMPONENT-184 +188B8 TANGUT COMPONENT-185 +188B9 TANGUT COMPONENT-186 +188BA TANGUT COMPONENT-187 +188BB TANGUT COMPONENT-188 +188BC TANGUT COMPONENT-189 +188BD TANGUT COMPONENT-190 +188BE TANGUT COMPONENT-191 +188BF TANGUT COMPONENT-192 +188C0 TANGUT COMPONENT-193 +188C1 TANGUT COMPONENT-194 +188C2 TANGUT COMPONENT-195 +188C3 TANGUT COMPONENT-196 +188C4 TANGUT COMPONENT-197 +188C5 TANGUT COMPONENT-198 +188C6 TANGUT COMPONENT-199 +188C7 TANGUT COMPONENT-200 +188C8 TANGUT COMPONENT-201 +188C9 TANGUT COMPONENT-202 +188CA TANGUT COMPONENT-203 +188CB TANGUT COMPONENT-204 +@ Five-stroke components +188CC TANGUT COMPONENT-205 +188CD TANGUT COMPONENT-206 +188CE TANGUT COMPONENT-207 +188CF TANGUT COMPONENT-208 +188D0 TANGUT COMPONENT-209 +188D1 TANGUT COMPONENT-210 +188D2 TANGUT COMPONENT-211 +188D3 TANGUT COMPONENT-212 +188D4 TANGUT COMPONENT-213 +188D5 TANGUT COMPONENT-214 +188D6 TANGUT COMPONENT-215 +188D7 TANGUT COMPONENT-216 +188D8 TANGUT COMPONENT-217 +188D9 TANGUT COMPONENT-218 +188DA TANGUT COMPONENT-219 +188DB TANGUT COMPONENT-220 +188DC TANGUT COMPONENT-221 +188DD TANGUT COMPONENT-222 +188DE TANGUT COMPONENT-223 +188DF TANGUT COMPONENT-224 +188E0 TANGUT COMPONENT-225 +188E1 TANGUT COMPONENT-226 +188E2 TANGUT COMPONENT-227 +188E3 TANGUT COMPONENT-228 +188E4 TANGUT COMPONENT-229 +188E5 TANGUT COMPONENT-230 +188E6 TANGUT COMPONENT-231 +188E7 TANGUT COMPONENT-232 +188E8 TANGUT COMPONENT-233 +188E9 TANGUT COMPONENT-234 +188EA TANGUT COMPONENT-235 +188EB TANGUT COMPONENT-236 +188EC TANGUT COMPONENT-237 +188ED TANGUT COMPONENT-238 +188EE TANGUT COMPONENT-239 +188EF TANGUT COMPONENT-240 +188F0 TANGUT COMPONENT-241 +188F1 TANGUT COMPONENT-242 +188F2 TANGUT COMPONENT-243 +188F3 TANGUT COMPONENT-244 +188F4 TANGUT COMPONENT-245 +188F5 TANGUT COMPONENT-246 +188F6 TANGUT COMPONENT-247 +188F7 TANGUT COMPONENT-248 +188F8 TANGUT COMPONENT-249 +188F9 TANGUT COMPONENT-250 +188FA TANGUT COMPONENT-251 +188FB TANGUT COMPONENT-252 +188FC TANGUT COMPONENT-253 +188FD TANGUT COMPONENT-254 +188FE TANGUT COMPONENT-255 +188FF TANGUT COMPONENT-256 +18900 TANGUT COMPONENT-257 +18901 TANGUT COMPONENT-258 +18902 TANGUT COMPONENT-259 +18903 TANGUT COMPONENT-260 +18904 TANGUT COMPONENT-261 +18905 TANGUT COMPONENT-262 +18906 TANGUT COMPONENT-263 +18907 TANGUT COMPONENT-264 +18908 TANGUT COMPONENT-265 +18909 TANGUT COMPONENT-266 +1890A TANGUT COMPONENT-267 +1890B TANGUT COMPONENT-268 +1890C TANGUT COMPONENT-269 +1890D TANGUT COMPONENT-270 +1890E TANGUT COMPONENT-271 +1890F TANGUT COMPONENT-272 +18910 TANGUT COMPONENT-273 +18911 TANGUT COMPONENT-274 +18912 TANGUT COMPONENT-275 +18913 TANGUT COMPONENT-276 +18914 TANGUT COMPONENT-277 +18915 TANGUT COMPONENT-278 +18916 TANGUT COMPONENT-279 +18917 TANGUT COMPONENT-280 +18918 TANGUT COMPONENT-281 +18919 TANGUT COMPONENT-282 +1891A TANGUT COMPONENT-283 +1891B TANGUT COMPONENT-284 +1891C TANGUT COMPONENT-285 +1891D TANGUT COMPONENT-286 +1891E TANGUT COMPONENT-287 +1891F TANGUT COMPONENT-288 +18920 TANGUT COMPONENT-289 +18921 TANGUT COMPONENT-290 +18922 TANGUT COMPONENT-291 +18923 TANGUT COMPONENT-292 +18924 TANGUT COMPONENT-293 +18925 TANGUT COMPONENT-294 +18926 TANGUT COMPONENT-295 +18927 TANGUT COMPONENT-296 +18928 TANGUT COMPONENT-297 +18929 TANGUT COMPONENT-298 +1892A TANGUT COMPONENT-299 +1892B TANGUT COMPONENT-300 +1892C TANGUT COMPONENT-301 +1892D TANGUT COMPONENT-302 +1892E TANGUT COMPONENT-303 +1892F TANGUT COMPONENT-304 +18930 TANGUT COMPONENT-305 +18931 TANGUT COMPONENT-306 +18932 TANGUT COMPONENT-307 +18933 TANGUT COMPONENT-308 +18934 TANGUT COMPONENT-309 +18935 TANGUT COMPONENT-310 +18936 TANGUT COMPONENT-311 +18937 TANGUT COMPONENT-312 +18938 TANGUT COMPONENT-313 +18939 TANGUT COMPONENT-314 +1893A TANGUT COMPONENT-315 +1893B TANGUT COMPONENT-316 +1893C TANGUT COMPONENT-317 +1893D TANGUT COMPONENT-318 +1893E TANGUT COMPONENT-319 +1893F TANGUT COMPONENT-320 +18940 TANGUT COMPONENT-321 +18941 TANGUT COMPONENT-322 +18942 TANGUT COMPONENT-323 +18943 TANGUT COMPONENT-324 +18944 TANGUT COMPONENT-325 +18945 TANGUT COMPONENT-326 +18946 TANGUT COMPONENT-327 +18947 TANGUT COMPONENT-328 +18948 TANGUT COMPONENT-329 +18949 TANGUT COMPONENT-330 +1894A TANGUT COMPONENT-331 +1894B TANGUT COMPONENT-332 +1894C TANGUT COMPONENT-333 +1894D TANGUT COMPONENT-334 +1894E TANGUT COMPONENT-335 +1894F TANGUT COMPONENT-336 +18950 TANGUT COMPONENT-337 +18951 TANGUT COMPONENT-338 +18952 TANGUT COMPONENT-339 +18953 TANGUT COMPONENT-340 +18954 TANGUT COMPONENT-341 +18955 TANGUT COMPONENT-342 +18956 TANGUT COMPONENT-343 +18957 TANGUT COMPONENT-344 +18958 TANGUT COMPONENT-345 +@ Six-stroke components +18959 TANGUT COMPONENT-346 +1895A TANGUT COMPONENT-347 +1895B TANGUT COMPONENT-348 +1895C TANGUT COMPONENT-349 +1895D TANGUT COMPONENT-350 +1895E TANGUT COMPONENT-351 +1895F TANGUT COMPONENT-352 +18960 TANGUT COMPONENT-353 +18961 TANGUT COMPONENT-354 +18962 TANGUT COMPONENT-355 +18963 TANGUT COMPONENT-356 +18964 TANGUT COMPONENT-357 +18965 TANGUT COMPONENT-358 +18966 TANGUT COMPONENT-359 +18967 TANGUT COMPONENT-360 +18968 TANGUT COMPONENT-361 +18969 TANGUT COMPONENT-362 +1896A TANGUT COMPONENT-363 +1896B TANGUT COMPONENT-364 +1896C TANGUT COMPONENT-365 +1896D TANGUT COMPONENT-366 +1896E TANGUT COMPONENT-367 +1896F TANGUT COMPONENT-368 +18970 TANGUT COMPONENT-369 +18971 TANGUT COMPONENT-370 +18972 TANGUT COMPONENT-371 +18973 TANGUT COMPONENT-372 +18974 TANGUT COMPONENT-373 +18975 TANGUT COMPONENT-374 +18976 TANGUT COMPONENT-375 +18977 TANGUT COMPONENT-376 +18978 TANGUT COMPONENT-377 +18979 TANGUT COMPONENT-378 +1897A TANGUT COMPONENT-379 +1897B TANGUT COMPONENT-380 +1897C TANGUT COMPONENT-381 +1897D TANGUT COMPONENT-382 +1897E TANGUT COMPONENT-383 +1897F TANGUT COMPONENT-384 +18980 TANGUT COMPONENT-385 +18981 TANGUT COMPONENT-386 +18982 TANGUT COMPONENT-387 +18983 TANGUT COMPONENT-388 +18984 TANGUT COMPONENT-389 +18985 TANGUT COMPONENT-390 +18986 TANGUT COMPONENT-391 +18987 TANGUT COMPONENT-392 +18988 TANGUT COMPONENT-393 +18989 TANGUT COMPONENT-394 +1898A TANGUT COMPONENT-395 +1898B TANGUT COMPONENT-396 +1898C TANGUT COMPONENT-397 +1898D TANGUT COMPONENT-398 +1898E TANGUT COMPONENT-399 +1898F TANGUT COMPONENT-400 +18990 TANGUT COMPONENT-401 +18991 TANGUT COMPONENT-402 +18992 TANGUT COMPONENT-403 +18993 TANGUT COMPONENT-404 +18994 TANGUT COMPONENT-405 +18995 TANGUT COMPONENT-406 +18996 TANGUT COMPONENT-407 +18997 TANGUT COMPONENT-408 +18998 TANGUT COMPONENT-409 +18999 TANGUT COMPONENT-410 +1899A TANGUT COMPONENT-411 +1899B TANGUT COMPONENT-412 +1899C TANGUT COMPONENT-413 +1899D TANGUT COMPONENT-414 +1899E TANGUT COMPONENT-415 +1899F TANGUT COMPONENT-416 +189A0 TANGUT COMPONENT-417 +189A1 TANGUT COMPONENT-418 +189A2 TANGUT COMPONENT-419 +189A3 TANGUT COMPONENT-420 +189A4 TANGUT COMPONENT-421 +189A5 TANGUT COMPONENT-422 +189A6 TANGUT COMPONENT-423 +189A7 TANGUT COMPONENT-424 +189A8 TANGUT COMPONENT-425 +189A9 TANGUT COMPONENT-426 +189AA TANGUT COMPONENT-427 +189AB TANGUT COMPONENT-428 +189AC TANGUT COMPONENT-429 +189AD TANGUT COMPONENT-430 +189AE TANGUT COMPONENT-431 +189AF TANGUT COMPONENT-432 +189B0 TANGUT COMPONENT-433 +189B1 TANGUT COMPONENT-434 +189B2 TANGUT COMPONENT-435 +189B3 TANGUT COMPONENT-436 +189B4 TANGUT COMPONENT-437 +189B5 TANGUT COMPONENT-438 +189B6 TANGUT COMPONENT-439 +189B7 TANGUT COMPONENT-440 +189B8 TANGUT COMPONENT-441 +189B9 TANGUT COMPONENT-442 +189BA TANGUT COMPONENT-443 +189BB TANGUT COMPONENT-444 +189BC TANGUT COMPONENT-445 +189BD TANGUT COMPONENT-446 +189BE TANGUT COMPONENT-447 +189BF TANGUT COMPONENT-448 +189C0 TANGUT COMPONENT-449 +189C1 TANGUT COMPONENT-450 +189C2 TANGUT COMPONENT-451 +189C3 TANGUT COMPONENT-452 +189C4 TANGUT COMPONENT-453 +189C5 TANGUT COMPONENT-454 +189C6 TANGUT COMPONENT-455 +189C7 TANGUT COMPONENT-456 +189C8 TANGUT COMPONENT-457 +189C9 TANGUT COMPONENT-458 +189CA TANGUT COMPONENT-459 +189CB TANGUT COMPONENT-460 +189CC TANGUT COMPONENT-461 +189CD TANGUT COMPONENT-462 +189CE TANGUT COMPONENT-463 +189CF TANGUT COMPONENT-464 +189D0 TANGUT COMPONENT-465 +189D1 TANGUT COMPONENT-466 +189D2 TANGUT COMPONENT-467 +189D3 TANGUT COMPONENT-468 +189D4 TANGUT COMPONENT-469 +189D5 TANGUT COMPONENT-470 +189D6 TANGUT COMPONENT-471 +189D7 TANGUT COMPONENT-472 +189D8 TANGUT COMPONENT-473 +189D9 TANGUT COMPONENT-474 +189DA TANGUT COMPONENT-475 +@ Seven-stroke components +189DB TANGUT COMPONENT-476 +189DC TANGUT COMPONENT-477 +189DD TANGUT COMPONENT-478 +189DE TANGUT COMPONENT-479 +189DF TANGUT COMPONENT-480 +189E0 TANGUT COMPONENT-481 +189E1 TANGUT COMPONENT-482 +189E2 TANGUT COMPONENT-483 +189E3 TANGUT COMPONENT-484 +189E4 TANGUT COMPONENT-485 +189E5 TANGUT COMPONENT-486 +189E6 TANGUT COMPONENT-487 +189E7 TANGUT COMPONENT-488 +189E8 TANGUT COMPONENT-489 +189E9 TANGUT COMPONENT-490 +189EA TANGUT COMPONENT-491 +189EB TANGUT COMPONENT-492 +189EC TANGUT COMPONENT-493 +189ED TANGUT COMPONENT-494 +189EE TANGUT COMPONENT-495 +189EF TANGUT COMPONENT-496 +189F0 TANGUT COMPONENT-497 +189F1 TANGUT COMPONENT-498 +189F2 TANGUT COMPONENT-499 +189F3 TANGUT COMPONENT-500 +189F4 TANGUT COMPONENT-501 +189F5 TANGUT COMPONENT-502 +189F6 TANGUT COMPONENT-503 +189F7 TANGUT COMPONENT-504 +189F8 TANGUT COMPONENT-505 +189F9 TANGUT COMPONENT-506 +189FA TANGUT COMPONENT-507 +189FB TANGUT COMPONENT-508 +189FC TANGUT COMPONENT-509 +189FD TANGUT COMPONENT-510 +189FE TANGUT COMPONENT-511 +189FF TANGUT COMPONENT-512 +18A00 TANGUT COMPONENT-513 +18A01 TANGUT COMPONENT-514 +18A02 TANGUT COMPONENT-515 +18A03 TANGUT COMPONENT-516 +18A04 TANGUT COMPONENT-517 +18A05 TANGUT COMPONENT-518 +18A06 TANGUT COMPONENT-519 +18A07 TANGUT COMPONENT-520 +18A08 TANGUT COMPONENT-521 +18A09 TANGUT COMPONENT-522 +18A0A TANGUT COMPONENT-523 +18A0B TANGUT COMPONENT-524 +18A0C TANGUT COMPONENT-525 +18A0D TANGUT COMPONENT-526 +18A0E TANGUT COMPONENT-527 +18A0F TANGUT COMPONENT-528 +18A10 TANGUT COMPONENT-529 +18A11 TANGUT COMPONENT-530 +18A12 TANGUT COMPONENT-531 +18A13 TANGUT COMPONENT-532 +18A14 TANGUT COMPONENT-533 +18A15 TANGUT COMPONENT-534 +18A16 TANGUT COMPONENT-535 +18A17 TANGUT COMPONENT-536 +18A18 TANGUT COMPONENT-537 +18A19 TANGUT COMPONENT-538 +18A1A TANGUT COMPONENT-539 +18A1B TANGUT COMPONENT-540 +18A1C TANGUT COMPONENT-541 +18A1D TANGUT COMPONENT-542 +18A1E TANGUT COMPONENT-543 +18A1F TANGUT COMPONENT-544 +18A20 TANGUT COMPONENT-545 +18A21 TANGUT COMPONENT-546 +18A22 TANGUT COMPONENT-547 +18A23 TANGUT COMPONENT-548 +18A24 TANGUT COMPONENT-549 +18A25 TANGUT COMPONENT-550 +18A26 TANGUT COMPONENT-551 +18A27 TANGUT COMPONENT-552 +18A28 TANGUT COMPONENT-553 +18A29 TANGUT COMPONENT-554 +18A2A TANGUT COMPONENT-555 +18A2B TANGUT COMPONENT-556 +18A2C TANGUT COMPONENT-557 +18A2D TANGUT COMPONENT-558 +18A2E TANGUT COMPONENT-559 +18A2F TANGUT COMPONENT-560 +18A30 TANGUT COMPONENT-561 +18A31 TANGUT COMPONENT-562 +18A32 TANGUT COMPONENT-563 +18A33 TANGUT COMPONENT-564 +18A34 TANGUT COMPONENT-565 +18A35 TANGUT COMPONENT-566 +18A36 TANGUT COMPONENT-567 +18A37 TANGUT COMPONENT-568 +18A38 TANGUT COMPONENT-569 +18A39 TANGUT COMPONENT-570 +18A3A TANGUT COMPONENT-571 +18A3B TANGUT COMPONENT-572 +18A3C TANGUT COMPONENT-573 +18A3D TANGUT COMPONENT-574 +18A3E TANGUT COMPONENT-575 +18A3F TANGUT COMPONENT-576 +18A40 TANGUT COMPONENT-577 +@ Eight-stroke components +18A41 TANGUT COMPONENT-578 +18A42 TANGUT COMPONENT-579 +18A43 TANGUT COMPONENT-580 +18A44 TANGUT COMPONENT-581 +18A45 TANGUT COMPONENT-582 +18A46 TANGUT COMPONENT-583 +18A47 TANGUT COMPONENT-584 +18A48 TANGUT COMPONENT-585 +18A49 TANGUT COMPONENT-586 +18A4A TANGUT COMPONENT-587 +18A4B TANGUT COMPONENT-588 +18A4C TANGUT COMPONENT-589 +18A4D TANGUT COMPONENT-590 +18A4E TANGUT COMPONENT-591 +18A4F TANGUT COMPONENT-592 +18A50 TANGUT COMPONENT-593 +18A51 TANGUT COMPONENT-594 +18A52 TANGUT COMPONENT-595 +18A53 TANGUT COMPONENT-596 +18A54 TANGUT COMPONENT-597 +18A55 TANGUT COMPONENT-598 +18A56 TANGUT COMPONENT-599 +18A57 TANGUT COMPONENT-600 +18A58 TANGUT COMPONENT-601 +18A59 TANGUT COMPONENT-602 +18A5A TANGUT COMPONENT-603 +18A5B TANGUT COMPONENT-604 +18A5C TANGUT COMPONENT-605 +18A5D TANGUT COMPONENT-606 +18A5E TANGUT COMPONENT-607 +18A5F TANGUT COMPONENT-608 +18A60 TANGUT COMPONENT-609 +18A61 TANGUT COMPONENT-610 +18A62 TANGUT COMPONENT-611 +18A63 TANGUT COMPONENT-612 +18A64 TANGUT COMPONENT-613 +18A65 TANGUT COMPONENT-614 +18A66 TANGUT COMPONENT-615 +18A67 TANGUT COMPONENT-616 +18A68 TANGUT COMPONENT-617 +18A69 TANGUT COMPONENT-618 +18A6A TANGUT COMPONENT-619 +18A6B TANGUT COMPONENT-620 +18A6C TANGUT COMPONENT-621 +18A6D TANGUT COMPONENT-622 +18A6E TANGUT COMPONENT-623 +18A6F TANGUT COMPONENT-624 +18A70 TANGUT COMPONENT-625 +18A71 TANGUT COMPONENT-626 +18A72 TANGUT COMPONENT-627 +18A73 TANGUT COMPONENT-628 +18A74 TANGUT COMPONENT-629 +18A75 TANGUT COMPONENT-630 +18A76 TANGUT COMPONENT-631 +18A77 TANGUT COMPONENT-632 +18A78 TANGUT COMPONENT-633 +18A79 TANGUT COMPONENT-634 +18A7A TANGUT COMPONENT-635 +18A7B TANGUT COMPONENT-636 +18A7C TANGUT COMPONENT-637 +18A7D TANGUT COMPONENT-638 +18A7E TANGUT COMPONENT-639 +18A7F TANGUT COMPONENT-640 +18A80 TANGUT COMPONENT-641 +18A81 TANGUT COMPONENT-642 +18A82 TANGUT COMPONENT-643 +18A83 TANGUT COMPONENT-644 +18A84 TANGUT COMPONENT-645 +18A85 TANGUT COMPONENT-646 +18A86 TANGUT COMPONENT-647 +18A87 TANGUT COMPONENT-648 +18A88 TANGUT COMPONENT-649 +18A89 TANGUT COMPONENT-650 +18A8A TANGUT COMPONENT-651 +18A8B TANGUT COMPONENT-652 +18A8C TANGUT COMPONENT-653 +18A8D TANGUT COMPONENT-654 +18A8E TANGUT COMPONENT-655 +18A8F TANGUT COMPONENT-656 +18A90 TANGUT COMPONENT-657 +18A91 TANGUT COMPONENT-658 +18A92 TANGUT COMPONENT-659 +18A93 TANGUT COMPONENT-660 +18A94 TANGUT COMPONENT-661 +18A95 TANGUT COMPONENT-662 +18A96 TANGUT COMPONENT-663 +18A97 TANGUT COMPONENT-664 +18A98 TANGUT COMPONENT-665 +@ Nine-stroke components +18A99 TANGUT COMPONENT-666 +18A9A TANGUT COMPONENT-667 +18A9B TANGUT COMPONENT-668 +18A9C TANGUT COMPONENT-669 +18A9D TANGUT COMPONENT-670 +18A9E TANGUT COMPONENT-671 +18A9F TANGUT COMPONENT-672 +18AA0 TANGUT COMPONENT-673 +18AA1 TANGUT COMPONENT-674 +18AA2 TANGUT COMPONENT-675 +18AA3 TANGUT COMPONENT-676 +18AA4 TANGUT COMPONENT-677 +18AA5 TANGUT COMPONENT-678 +18AA6 TANGUT COMPONENT-679 +18AA7 TANGUT COMPONENT-680 +18AA8 TANGUT COMPONENT-681 +18AA9 TANGUT COMPONENT-682 +18AAA TANGUT COMPONENT-683 +18AAB TANGUT COMPONENT-684 +18AAC TANGUT COMPONENT-685 +18AAD TANGUT COMPONENT-686 +18AAE TANGUT COMPONENT-687 +18AAF TANGUT COMPONENT-688 +18AB0 TANGUT COMPONENT-689 +18AB1 TANGUT COMPONENT-690 +18AB2 TANGUT COMPONENT-691 +18AB3 TANGUT COMPONENT-692 +18AB4 TANGUT COMPONENT-693 +18AB5 TANGUT COMPONENT-694 +18AB6 TANGUT COMPONENT-695 +18AB7 TANGUT COMPONENT-696 +18AB8 TANGUT COMPONENT-697 +18AB9 TANGUT COMPONENT-698 +18ABA TANGUT COMPONENT-699 +18ABB TANGUT COMPONENT-700 +18ABC TANGUT COMPONENT-701 +18ABD TANGUT COMPONENT-702 +18ABE TANGUT COMPONENT-703 +18ABF TANGUT COMPONENT-704 +18AC0 TANGUT COMPONENT-705 +@ Ten-stroke components +18AC1 TANGUT COMPONENT-706 +18AC2 TANGUT COMPONENT-707 +18AC3 TANGUT COMPONENT-708 +18AC4 TANGUT COMPONENT-709 +18AC5 TANGUT COMPONENT-710 +18AC6 TANGUT COMPONENT-711 +18AC7 TANGUT COMPONENT-712 +18AC8 TANGUT COMPONENT-713 +18AC9 TANGUT COMPONENT-714 +18ACA TANGUT COMPONENT-715 +18ACB TANGUT COMPONENT-716 +18ACC TANGUT COMPONENT-717 +18ACD TANGUT COMPONENT-718 +18ACE TANGUT COMPONENT-719 +18ACF TANGUT COMPONENT-720 +18AD0 TANGUT COMPONENT-721 +18AD1 TANGUT COMPONENT-722 +18AD2 TANGUT COMPONENT-723 +18AD3 TANGUT COMPONENT-724 +18AD4 TANGUT COMPONENT-725 +@ Eleven-stroke components +18AD5 TANGUT COMPONENT-726 +18AD6 TANGUT COMPONENT-727 +18AD7 TANGUT COMPONENT-728 +18AD8 TANGUT COMPONENT-729 +18AD9 TANGUT COMPONENT-730 +18ADA TANGUT COMPONENT-731 +18ADB TANGUT COMPONENT-732 +18ADC TANGUT COMPONENT-733 +18ADD TANGUT COMPONENT-734 +18ADE TANGUT COMPONENT-735 +18ADF TANGUT COMPONENT-736 +18AE0 TANGUT COMPONENT-737 +18AE1 TANGUT COMPONENT-738 +18AE2 TANGUT COMPONENT-739 +@ Twelve-stroke components +18AE3 TANGUT COMPONENT-740 +18AE4 TANGUT COMPONENT-741 +18AE5 TANGUT COMPONENT-742 +18AE6 TANGUT COMPONENT-743 +18AE7 TANGUT COMPONENT-744 +18AE8 TANGUT COMPONENT-745 +18AE9 TANGUT COMPONENT-746 +18AEA TANGUT COMPONENT-747 +18AEB TANGUT COMPONENT-748 +@ Thirteen-stroke components +18AEC TANGUT COMPONENT-749 +18AED TANGUT COMPONENT-750 +18AEE TANGUT COMPONENT-751 +18AEF TANGUT COMPONENT-752 +18AF0 TANGUT COMPONENT-753 +18AF1 TANGUT COMPONENT-754 +@ Sixteen-stroke component +18AF2 TANGUT COMPONENT-755 @@ 1B000 Kana Supplement 1B0FF @ Historic Katakana 1B000 KATAKANA LETTER ARCHAIC E -@ Historic Hiragana +@ Historic Hiragana and Hentaigana 1B001 HIRAGANA LETTER ARCHAIC YE + % HENTAIGANA LETTER E-1 + * derived from 6C5F +@ Hentaigana +1B002 HENTAIGANA LETTER A-1 + * derived from 5B89 +1B003 HENTAIGANA LETTER A-2 + * derived from 611B +1B004 HENTAIGANA LETTER A-3 + * derived from 963F +1B005 HENTAIGANA LETTER A-WO + * derived from 60E1 +1B006 HENTAIGANA LETTER I-1 + * derived from 4EE5 +1B007 HENTAIGANA LETTER I-2 + * derived from 4F0A +1B008 HENTAIGANA LETTER I-3 + * derived from 610F +1B009 HENTAIGANA LETTER I-4 + * derived from 79FB +1B00A HENTAIGANA LETTER U-1 + * derived from 5B87 +1B00B HENTAIGANA LETTER U-2 + * derived from 5B87 +1B00C HENTAIGANA LETTER U-3 + * derived from 6182 +1B00D HENTAIGANA LETTER U-4 + * derived from 6709 +1B00E HENTAIGANA LETTER U-5 + * derived from 96F2 +1B00F HENTAIGANA LETTER E-2 + * derived from 76C8 +1B010 HENTAIGANA LETTER E-3 + * derived from 7E01 +1B011 HENTAIGANA LETTER E-4 + * derived from 8863 +1B012 HENTAIGANA LETTER E-5 + * derived from 8863 +1B013 HENTAIGANA LETTER E-6 + * derived from 8981 +1B014 HENTAIGANA LETTER O-1 + * derived from 65BC +1B015 HENTAIGANA LETTER O-2 + * derived from 65BC +1B016 HENTAIGANA LETTER O-3 + * derived from 96B1 +1B017 HENTAIGANA LETTER KA-1 + * derived from 4F73 +1B018 HENTAIGANA LETTER KA-2 + * derived from 52A0 +1B019 HENTAIGANA LETTER KA-3 + * derived from 53EF +1B01A HENTAIGANA LETTER KA-4 + * derived from 53EF +1B01B HENTAIGANA LETTER KA-5 + * derived from 5609 +1B01C HENTAIGANA LETTER KA-6 + * derived from 6211 +1B01D HENTAIGANA LETTER KA-7 + * derived from 6B5F +1B01E HENTAIGANA LETTER KA-8 + * derived from 8CC0 +1B01F HENTAIGANA LETTER KA-9 + * derived from 9591 +1B020 HENTAIGANA LETTER KA-10 + * derived from 9999 +1B021 HENTAIGANA LETTER KA-11 + * derived from 99D5 +1B022 HENTAIGANA LETTER KA-KE + * derived from 5BB6 +1B023 HENTAIGANA LETTER KI-1 + * derived from 559C +1B024 HENTAIGANA LETTER KI-2 + * derived from 5E7E +1B025 HENTAIGANA LETTER KI-3 + * derived from 5E7E +1B026 HENTAIGANA LETTER KI-4 + * derived from 652F +1B027 HENTAIGANA LETTER KI-5 + * derived from 6728 +1B028 HENTAIGANA LETTER KI-6 + * derived from 7948 +1B029 HENTAIGANA LETTER KI-7 + * derived from 8CB4 +1B02A HENTAIGANA LETTER KI-8 + * derived from 8D77 +1B02B HENTAIGANA LETTER KU-1 + * derived from 4E45 +1B02C HENTAIGANA LETTER KU-2 + * derived from 4E45 +1B02D HENTAIGANA LETTER KU-3 + * derived from 4E5D +1B02E HENTAIGANA LETTER KU-4 + * derived from 4F9B +1B02F HENTAIGANA LETTER KU-5 + * derived from 5036 +1B030 HENTAIGANA LETTER KU-6 + * derived from 5177 +1B031 HENTAIGANA LETTER KU-7 + * derived from 6C42 +1B032 HENTAIGANA LETTER KE-1 + * derived from 4ECB +1B033 HENTAIGANA LETTER KE-2 + * derived from 4ECB +1B034 HENTAIGANA LETTER KE-3 + * derived from 5E0C +1B035 HENTAIGANA LETTER KE-4 + * derived from 6C23 +1B036 HENTAIGANA LETTER KE-5 + * derived from 8A08 +1B037 HENTAIGANA LETTER KE-6 + * derived from 9063 +1B038 HENTAIGANA LETTER KO-1 + * derived from 53E4 +1B039 HENTAIGANA LETTER KO-2 + * derived from 6545 +1B03A HENTAIGANA LETTER KO-3 + * derived from 8A31 +1B03B HENTAIGANA LETTER KO-KI + * derived from 671F +1B03C HENTAIGANA LETTER SA-1 + * derived from 4E4D +1B03D HENTAIGANA LETTER SA-2 + * derived from 4F50 +1B03E HENTAIGANA LETTER SA-3 + * derived from 4F50 +1B03F HENTAIGANA LETTER SA-4 + * derived from 5DE6 +1B040 HENTAIGANA LETTER SA-5 + * derived from 5DEE +1B041 HENTAIGANA LETTER SA-6 + * derived from 6563 +1B042 HENTAIGANA LETTER SA-7 + * derived from 659C +1B043 HENTAIGANA LETTER SA-8 + * derived from 6C99 +1B044 HENTAIGANA LETTER SI-1 + * derived from 4E4B +1B045 HENTAIGANA LETTER SI-2 + * derived from 4E4B +1B046 HENTAIGANA LETTER SI-3 + * derived from 4E8B +1B047 HENTAIGANA LETTER SI-4 + * derived from 56DB +1B048 HENTAIGANA LETTER SI-5 + * derived from 5FD7 +1B049 HENTAIGANA LETTER SI-6 + * derived from 65B0 +1B04A HENTAIGANA LETTER SU-1 + * derived from 53D7 +1B04B HENTAIGANA LETTER SU-2 + * derived from 58FD +1B04C HENTAIGANA LETTER SU-3 + * derived from 6578 +1B04D HENTAIGANA LETTER SU-4 + * derived from 6578 +1B04E HENTAIGANA LETTER SU-5 + * derived from 6625 +1B04F HENTAIGANA LETTER SU-6 + * derived from 6625 +1B050 HENTAIGANA LETTER SU-7 + * derived from 9808 +1B051 HENTAIGANA LETTER SU-8 + * derived from 9808 +1B052 HENTAIGANA LETTER SE-1 + * derived from 4E16 +1B053 HENTAIGANA LETTER SE-2 + * derived from 4E16 +1B054 HENTAIGANA LETTER SE-3 + * derived from 4E16 +1B055 HENTAIGANA LETTER SE-4 + * derived from 52E2 +1B056 HENTAIGANA LETTER SE-5 + * derived from 8072 +1B057 HENTAIGANA LETTER SO-1 + * derived from 6240 +1B058 HENTAIGANA LETTER SO-2 + * derived from 6240 +1B059 HENTAIGANA LETTER SO-3 + * derived from 66FE +1B05A HENTAIGANA LETTER SO-4 + * derived from 66FE +1B05B HENTAIGANA LETTER SO-5 + * derived from 695A +1B05C HENTAIGANA LETTER SO-6 + * derived from 8607 +1B05D HENTAIGANA LETTER SO-7 + * derived from 8655 +1B05E HENTAIGANA LETTER TA-1 + * derived from 5802 +1B05F HENTAIGANA LETTER TA-2 + * derived from 591A +1B060 HENTAIGANA LETTER TA-3 + * derived from 591A +1B061 HENTAIGANA LETTER TA-4 + * derived from 7576 +1B062 HENTAIGANA LETTER TI-1 + * derived from 5343 +1B063 HENTAIGANA LETTER TI-2 + * derived from 5730 +1B064 HENTAIGANA LETTER TI-3 + * derived from 667A +1B065 HENTAIGANA LETTER TI-4 + * derived from 77E5 +1B066 HENTAIGANA LETTER TI-5 + * derived from 77E5 +1B067 HENTAIGANA LETTER TI-6 + * derived from 81F4 +1B068 HENTAIGANA LETTER TI-7 + * derived from 9072 +1B069 HENTAIGANA LETTER TU-1 + * derived from 5DDD +1B06A HENTAIGANA LETTER TU-2 + * derived from 5DDD +1B06B HENTAIGANA LETTER TU-3 + * derived from 6D25 +1B06C HENTAIGANA LETTER TU-4 + * derived from 90FD +1B06D HENTAIGANA LETTER TU-TO + * derived from 5F92 +1B06E HENTAIGANA LETTER TE-1 + * derived from 4EAD +1B06F HENTAIGANA LETTER TE-2 + * derived from 4F4E +1B070 HENTAIGANA LETTER TE-3 + * derived from 50B3 +1B071 HENTAIGANA LETTER TE-4 + * derived from 5929 +1B072 HENTAIGANA LETTER TE-5 + * derived from 5929 +1B073 HENTAIGANA LETTER TE-6 + * derived from 5929 +1B074 HENTAIGANA LETTER TE-7 + * derived from 5E1D +1B075 HENTAIGANA LETTER TE-8 + * derived from 5F16 +1B076 HENTAIGANA LETTER TE-9 + * derived from 8F49 +1B077 HENTAIGANA LETTER TO-1 + * derived from 571F +1B078 HENTAIGANA LETTER TO-2 + * derived from 5EA6 +1B079 HENTAIGANA LETTER TO-3 + * derived from 6771 +1B07A HENTAIGANA LETTER TO-4 + * derived from 767B +1B07B HENTAIGANA LETTER TO-5 + * derived from 767B +1B07C HENTAIGANA LETTER TO-6 + * derived from 7825 +1B07D HENTAIGANA LETTER TO-RA + * derived from 7B49 +1B07E HENTAIGANA LETTER NA-1 + * derived from 5357 +1B07F HENTAIGANA LETTER NA-2 + * derived from 540D +1B080 HENTAIGANA LETTER NA-3 + * derived from 5948 +1B081 HENTAIGANA LETTER NA-4 + * derived from 5948 +1B082 HENTAIGANA LETTER NA-5 + * derived from 5948 +1B083 HENTAIGANA LETTER NA-6 + * derived from 83DC +1B084 HENTAIGANA LETTER NA-7 + * derived from 90A3 +1B085 HENTAIGANA LETTER NA-8 + * derived from 90A3 +1B086 HENTAIGANA LETTER NA-9 + * derived from 96E3 +1B087 HENTAIGANA LETTER NI-1 + * derived from 4E39 +1B088 HENTAIGANA LETTER NI-2 + * derived from 4E8C +1B089 HENTAIGANA LETTER NI-3 + * derived from 4EC1 +1B08A HENTAIGANA LETTER NI-4 + * derived from 5152 +1B08B HENTAIGANA LETTER NI-5 + * derived from 723E +1B08C HENTAIGANA LETTER NI-6 + * derived from 723E +1B08D HENTAIGANA LETTER NI-7 + * derived from 8033 +1B08E HENTAIGANA LETTER NI-TE + * derived from 800C +1B08F HENTAIGANA LETTER NU-1 + * derived from 52AA +1B090 HENTAIGANA LETTER NU-2 + * derived from 5974 +1B091 HENTAIGANA LETTER NU-3 + * derived from 6012 +1B092 HENTAIGANA LETTER NE-1 + * derived from 5E74 +1B093 HENTAIGANA LETTER NE-2 + * derived from 5E74 +1B094 HENTAIGANA LETTER NE-3 + * derived from 5E74 +1B095 HENTAIGANA LETTER NE-4 + * derived from 6839 +1B096 HENTAIGANA LETTER NE-5 + * derived from 71B1 +1B097 HENTAIGANA LETTER NE-6 + * derived from 79B0 +1B098 HENTAIGANA LETTER NE-KO + * derived from 5B50 +1B099 HENTAIGANA LETTER NO-1 + * derived from 4E43 +1B09A HENTAIGANA LETTER NO-2 + * derived from 6FC3 +1B09B HENTAIGANA LETTER NO-3 + * derived from 80FD +1B09C HENTAIGANA LETTER NO-4 + * derived from 80FD +1B09D HENTAIGANA LETTER NO-5 + * derived from 8FB2 +1B09E HENTAIGANA LETTER HA-1 + * derived from 516B +1B09F HENTAIGANA LETTER HA-2 + * derived from 534A +1B0A0 HENTAIGANA LETTER HA-3 + * derived from 5A46 +1B0A1 HENTAIGANA LETTER HA-4 + * derived from 6CE2 +1B0A2 HENTAIGANA LETTER HA-5 + * derived from 76E4 +1B0A3 HENTAIGANA LETTER HA-6 + * derived from 76E4 +1B0A4 HENTAIGANA LETTER HA-7 + * derived from 7834 +1B0A5 HENTAIGANA LETTER HA-8 + * derived from 8005 +1B0A6 HENTAIGANA LETTER HA-9 + * derived from 8005 +1B0A7 HENTAIGANA LETTER HA-10 + * derived from 8449 +1B0A8 HENTAIGANA LETTER HA-11 + * derived from 9817 +1B0A9 HENTAIGANA LETTER HI-1 + * derived from 60B2 +1B0AA HENTAIGANA LETTER HI-2 + * derived from 65E5 +1B0AB HENTAIGANA LETTER HI-3 + * derived from 6BD4 +1B0AC HENTAIGANA LETTER HI-4 + * derived from 907F +1B0AD HENTAIGANA LETTER HI-5 + * derived from 975E +1B0AE HENTAIGANA LETTER HI-6 + * derived from 98DB +1B0AF HENTAIGANA LETTER HI-7 + * derived from 98DB +1B0B0 HENTAIGANA LETTER HU-1 + * derived from 4E0D +1B0B1 HENTAIGANA LETTER HU-2 + * derived from 5A66 +1B0B2 HENTAIGANA LETTER HU-3 + * derived from 5E03 +1B0B3 HENTAIGANA LETTER HE-1 + * derived from 500D +1B0B4 HENTAIGANA LETTER HE-2 + * derived from 5F0A +1B0B5 HENTAIGANA LETTER HE-3 + * derived from 5F0A +1B0B6 HENTAIGANA LETTER HE-4 + * derived from 904D +1B0B7 HENTAIGANA LETTER HE-5 + * derived from 908A +1B0B8 HENTAIGANA LETTER HE-6 + * derived from 908A +1B0B9 HENTAIGANA LETTER HE-7 + * derived from 90E8 +1B0BA HENTAIGANA LETTER HO-1 + * derived from 4FDD +1B0BB HENTAIGANA LETTER HO-2 + * derived from 4FDD +1B0BC HENTAIGANA LETTER HO-3 + * derived from 5831 +1B0BD HENTAIGANA LETTER HO-4 + * derived from 5949 +1B0BE HENTAIGANA LETTER HO-5 + * derived from 5BF6 +1B0BF HENTAIGANA LETTER HO-6 + * derived from 672C +1B0C0 HENTAIGANA LETTER HO-7 + * derived from 672C +1B0C1 HENTAIGANA LETTER HO-8 + * derived from 8C50 +1B0C2 HENTAIGANA LETTER MA-1 + * derived from 4E07 +1B0C3 HENTAIGANA LETTER MA-2 + * derived from 672B +1B0C4 HENTAIGANA LETTER MA-3 + * derived from 672B +1B0C5 HENTAIGANA LETTER MA-4 + * derived from 6EFF +1B0C6 HENTAIGANA LETTER MA-5 + * derived from 6EFF +1B0C7 HENTAIGANA LETTER MA-6 + * derived from 842C +1B0C8 HENTAIGANA LETTER MA-7 + * derived from 9EBB +1B0C9 HENTAIGANA LETTER MI-1 + * derived from 4E09 +1B0CA HENTAIGANA LETTER MI-2 + * derived from 5FAE +1B0CB HENTAIGANA LETTER MI-3 + * derived from 7F8E +1B0CC HENTAIGANA LETTER MI-4 + * derived from 7F8E +1B0CD HENTAIGANA LETTER MI-5 + * derived from 7F8E +1B0CE HENTAIGANA LETTER MI-6 + * derived from 898B +1B0CF HENTAIGANA LETTER MI-7 + * derived from 8EAB +1B0D0 HENTAIGANA LETTER MU-1 + * derived from 6B66 +1B0D1 HENTAIGANA LETTER MU-2 + * derived from 7121 +1B0D2 HENTAIGANA LETTER MU-3 + * derived from 725F +1B0D3 HENTAIGANA LETTER MU-4 + * derived from 821E +1B0D4 HENTAIGANA LETTER ME-1 + * derived from 514D +1B0D5 HENTAIGANA LETTER ME-2 + * derived from 9762 +1B0D6 HENTAIGANA LETTER ME-MA + * derived from 99AC +1B0D7 HENTAIGANA LETTER MO-1 + * derived from 6BCD +1B0D8 HENTAIGANA LETTER MO-2 + * derived from 6BDB +1B0D9 HENTAIGANA LETTER MO-3 + * derived from 6BDB +1B0DA HENTAIGANA LETTER MO-4 + * derived from 6BDB +1B0DB HENTAIGANA LETTER MO-5 + * derived from 8302 +1B0DC HENTAIGANA LETTER MO-6 + * derived from 88F3 +1B0DD HENTAIGANA LETTER YA-1 + * derived from 4E5F +1B0DE HENTAIGANA LETTER YA-2 + * derived from 4E5F +1B0DF HENTAIGANA LETTER YA-3 + * derived from 5C4B +1B0E0 HENTAIGANA LETTER YA-4 + * derived from 8036 +1B0E1 HENTAIGANA LETTER YA-5 + * derived from 8036 +1B0E2 HENTAIGANA LETTER YA-YO + * derived from 591C +1B0E3 HENTAIGANA LETTER YU-1 + * derived from 6E38 +1B0E4 HENTAIGANA LETTER YU-2 + * derived from 7531 +1B0E5 HENTAIGANA LETTER YU-3 + * derived from 7531 +1B0E6 HENTAIGANA LETTER YU-4 + * derived from 904A +1B0E7 HENTAIGANA LETTER YO-1 + * derived from 4EE3 +1B0E8 HENTAIGANA LETTER YO-2 + * derived from 4F59 +1B0E9 HENTAIGANA LETTER YO-3 + * derived from 8207 +1B0EA HENTAIGANA LETTER YO-4 + * derived from 8207 +1B0EB HENTAIGANA LETTER YO-5 + * derived from 8207 +1B0EC HENTAIGANA LETTER YO-6 + * derived from 9918 +1B0ED HENTAIGANA LETTER RA-1 + * derived from 7F85 +1B0EE HENTAIGANA LETTER RA-2 + * derived from 826F +1B0EF HENTAIGANA LETTER RA-3 + * derived from 826F +1B0F0 HENTAIGANA LETTER RA-4 + * derived from 826F +1B0F1 HENTAIGANA LETTER RI-1 + * derived from 5229 +1B0F2 HENTAIGANA LETTER RI-2 + * derived from 5229 +1B0F3 HENTAIGANA LETTER RI-3 + * derived from 674E +1B0F4 HENTAIGANA LETTER RI-4 + * derived from 68A8 +1B0F5 HENTAIGANA LETTER RI-5 + * derived from 7406 +1B0F6 HENTAIGANA LETTER RI-6 + * derived from 91CC +1B0F7 HENTAIGANA LETTER RI-7 + * derived from 96E2 +1B0F8 HENTAIGANA LETTER RU-1 + * derived from 6D41 +1B0F9 HENTAIGANA LETTER RU-2 + * derived from 7559 +1B0FA HENTAIGANA LETTER RU-3 + * derived from 7559 +1B0FB HENTAIGANA LETTER RU-4 + * derived from 7559 +1B0FC HENTAIGANA LETTER RU-5 + * derived from 7D2F +1B0FD HENTAIGANA LETTER RU-6 + * derived from 985E +1B0FE HENTAIGANA LETTER RE-1 + * derived from 79AE +1B0FF HENTAIGANA LETTER RE-2 + * derived from 79AE +@@ 1B100 Kana Extended-A 1B12F +@ Hentaigana +1B100 HENTAIGANA LETTER RE-3 + * derived from 9023 +1B101 HENTAIGANA LETTER RE-4 + * derived from 9E97 +1B102 HENTAIGANA LETTER RO-1 + * derived from 5442 +1B103 HENTAIGANA LETTER RO-2 + * derived from 5442 +1B104 HENTAIGANA LETTER RO-3 + * derived from 5A41 +1B105 HENTAIGANA LETTER RO-4 + * derived from 6A13 +1B106 HENTAIGANA LETTER RO-5 + * derived from 8DEF +1B107 HENTAIGANA LETTER RO-6 + * derived from 9732 +1B108 HENTAIGANA LETTER WA-1 + * derived from 502D +1B109 HENTAIGANA LETTER WA-2 + * derived from 548C +1B10A HENTAIGANA LETTER WA-3 + * derived from 548C +1B10B HENTAIGANA LETTER WA-4 + * derived from 738B +1B10C HENTAIGANA LETTER WA-5 + * derived from 738B +1B10D HENTAIGANA LETTER WI-1 + * derived from 4E95 +1B10E HENTAIGANA LETTER WI-2 + * derived from 4E95 +1B10F HENTAIGANA LETTER WI-3 + * derived from 5C45 +1B110 HENTAIGANA LETTER WI-4 + * derived from 7232 +1B111 HENTAIGANA LETTER WI-5 + * derived from 907A +1B112 HENTAIGANA LETTER WE-1 + * derived from 60E0 +1B113 HENTAIGANA LETTER WE-2 + * derived from 885E +1B114 HENTAIGANA LETTER WE-3 + * derived from 885E +1B115 HENTAIGANA LETTER WE-4 + * derived from 885E +1B116 HENTAIGANA LETTER WO-1 + * derived from 4E4E +1B117 HENTAIGANA LETTER WO-2 + * derived from 4E4E +1B118 HENTAIGANA LETTER WO-3 + * derived from 5C3E +1B119 HENTAIGANA LETTER WO-4 + * derived from 7DD2 +1B11A HENTAIGANA LETTER WO-5 + * derived from 8D8A +1B11B HENTAIGANA LETTER WO-6 + * derived from 9060 +1B11C HENTAIGANA LETTER WO-7 + * derived from 9060 +1B11D HENTAIGANA LETTER N-MU-MO-1 + * derived from 65E0 +1B11E HENTAIGANA LETTER N-MU-MO-2 + * derived from 65E0 +@@ 1B170 Nushu 1B2FF +@+ A more accurate spelling of the name of this script is Nüshu. +@ One-stroke character +1B170 NUSHU CHARACTER-1B170 + x 4E00 +@ Two-stroke characters +1B171 NUSHU CHARACTER-1B171 + x 4E8C +1B172 NUSHU CHARACTER-1B172 +1B173 NUSHU CHARACTER-1B173 +1B174 NUSHU CHARACTER-1B174 +1B175 NUSHU CHARACTER-1B175 +1B176 NUSHU CHARACTER-1B176 +1B177 NUSHU CHARACTER-1B177 +@ Three-stroke characters +1B178 NUSHU CHARACTER-1B178 + x 6C34 +1B179 NUSHU CHARACTER-1B179 +1B17A NUSHU CHARACTER-1B17A +1B17B NUSHU CHARACTER-1B17B +1B17C NUSHU CHARACTER-1B17C +1B17D NUSHU CHARACTER-1B17D +1B17E NUSHU CHARACTER-1B17E +1B17F NUSHU CHARACTER-1B17F +1B180 NUSHU CHARACTER-1B180 + x 571F +1B181 NUSHU CHARACTER-1B181 +1B182 NUSHU CHARACTER-1B182 +1B183 NUSHU CHARACTER-1B183 + x 5DE5 +1B184 NUSHU CHARACTER-1B184 +1B185 NUSHU CHARACTER-1B185 + x 4E2A +1B186 NUSHU CHARACTER-1B186 +1B187 NUSHU CHARACTER-1B187 +1B188 NUSHU CHARACTER-1B188 +1B189 NUSHU CHARACTER-1B189 +1B18A NUSHU CHARACTER-1B18A + x 4E09 +@ Four-stroke characters +1B18B NUSHU CHARACTER-1B18B +1B18C NUSHU CHARACTER-1B18C +1B18D NUSHU CHARACTER-1B18D +1B18E NUSHU CHARACTER-1B18E +1B18F NUSHU CHARACTER-1B18F +1B190 NUSHU CHARACTER-1B190 +1B191 NUSHU CHARACTER-1B191 +1B192 NUSHU CHARACTER-1B192 +1B193 NUSHU CHARACTER-1B193 +1B194 NUSHU CHARACTER-1B194 + x 592B +1B195 NUSHU CHARACTER-1B195 + x 706B +1B196 NUSHU CHARACTER-1B196 +1B197 NUSHU CHARACTER-1B197 +1B198 NUSHU CHARACTER-1B198 +1B199 NUSHU CHARACTER-1B199 +1B19A NUSHU CHARACTER-1B19A +1B19B NUSHU CHARACTER-1B19B +1B19C NUSHU CHARACTER-1B19C +1B19D NUSHU CHARACTER-1B19D +1B19E NUSHU CHARACTER-1B19E +1B19F NUSHU CHARACTER-1B19F +1B1A0 NUSHU CHARACTER-1B1A0 +1B1A1 NUSHU CHARACTER-1B1A1 + x 4EA1 +1B1A2 NUSHU CHARACTER-1B1A2 +1B1A3 NUSHU CHARACTER-1B1A3 +1B1A4 NUSHU CHARACTER-1B1A4 +1B1A5 NUSHU CHARACTER-1B1A5 +1B1A6 NUSHU CHARACTER-1B1A6 +1B1A7 NUSHU CHARACTER-1B1A7 + x 738B +@ Five-stroke characters +1B1A8 NUSHU CHARACTER-1B1A8 + x 672A +1B1A9 NUSHU CHARACTER-1B1A9 +1B1AA NUSHU CHARACTER-1B1AA +1B1AB NUSHU CHARACTER-1B1AB + x 5185 +1B1AC NUSHU CHARACTER-1B1AC +1B1AD NUSHU CHARACTER-1B1AD +1B1AE NUSHU CHARACTER-1B1AE +1B1AF NUSHU CHARACTER-1B1AF +1B1B0 NUSHU CHARACTER-1B1B0 +1B1B1 NUSHU CHARACTER-1B1B1 +1B1B2 NUSHU CHARACTER-1B1B2 +1B1B3 NUSHU CHARACTER-1B1B3 +1B1B4 NUSHU CHARACTER-1B1B4 +1B1B5 NUSHU CHARACTER-1B1B5 +1B1B6 NUSHU CHARACTER-1B1B6 +1B1B7 NUSHU CHARACTER-1B1B7 +1B1B8 NUSHU CHARACTER-1B1B8 +1B1B9 NUSHU CHARACTER-1B1B9 +1B1BA NUSHU CHARACTER-1B1BA +1B1BB NUSHU CHARACTER-1B1BB +1B1BC NUSHU CHARACTER-1B1BC +1B1BD NUSHU CHARACTER-1B1BD +1B1BE NUSHU CHARACTER-1B1BE +1B1BF NUSHU CHARACTER-1B1BF +1B1C0 NUSHU CHARACTER-1B1C0 +1B1C1 NUSHU CHARACTER-1B1C1 +1B1C2 NUSHU CHARACTER-1B1C2 +1B1C3 NUSHU CHARACTER-1B1C3 +1B1C4 NUSHU CHARACTER-1B1C4 +1B1C5 NUSHU CHARACTER-1B1C5 +1B1C6 NUSHU CHARACTER-1B1C6 +1B1C7 NUSHU CHARACTER-1B1C7 +1B1C8 NUSHU CHARACTER-1B1C8 +1B1C9 NUSHU CHARACTER-1B1C9 +1B1CA NUSHU CHARACTER-1B1CA +1B1CB NUSHU CHARACTER-1B1CB +1B1CC NUSHU CHARACTER-1B1CC + x 540E +1B1CD NUSHU CHARACTER-1B1CD +1B1CE NUSHU CHARACTER-1B1CE +1B1CF NUSHU CHARACTER-1B1CF +1B1D0 NUSHU CHARACTER-1B1D0 +1B1D1 NUSHU CHARACTER-1B1D1 +1B1D2 NUSHU CHARACTER-1B1D2 +1B1D3 NUSHU CHARACTER-1B1D3 +1B1D4 NUSHU CHARACTER-1B1D4 +1B1D5 NUSHU CHARACTER-1B1D5 +1B1D6 NUSHU CHARACTER-1B1D6 +1B1D7 NUSHU CHARACTER-1B1D7 +1B1D8 NUSHU CHARACTER-1B1D8 +1B1D9 NUSHU CHARACTER-1B1D9 +1B1DA NUSHU CHARACTER-1B1DA +1B1DB NUSHU CHARACTER-1B1DB +1B1DC NUSHU CHARACTER-1B1DC +1B1DD NUSHU CHARACTER-1B1DD +@ Six-stroke characters +1B1DE NUSHU CHARACTER-1B1DE +1B1DF NUSHU CHARACTER-1B1DF +1B1E0 NUSHU CHARACTER-1B1E0 +1B1E1 NUSHU CHARACTER-1B1E1 +1B1E2 NUSHU CHARACTER-1B1E2 +1B1E3 NUSHU CHARACTER-1B1E3 +1B1E4 NUSHU CHARACTER-1B1E4 +1B1E5 NUSHU CHARACTER-1B1E5 +1B1E6 NUSHU CHARACTER-1B1E6 +1B1E7 NUSHU CHARACTER-1B1E7 +1B1E8 NUSHU CHARACTER-1B1E8 +1B1E9 NUSHU CHARACTER-1B1E9 +1B1EA NUSHU CHARACTER-1B1EA +1B1EB NUSHU CHARACTER-1B1EB +1B1EC NUSHU CHARACTER-1B1EC +1B1ED NUSHU CHARACTER-1B1ED +1B1EE NUSHU CHARACTER-1B1EE +1B1EF NUSHU CHARACTER-1B1EF +1B1F0 NUSHU CHARACTER-1B1F0 + x 53E4 +1B1F1 NUSHU CHARACTER-1B1F1 +1B1F2 NUSHU CHARACTER-1B1F2 +1B1F3 NUSHU CHARACTER-1B1F3 +1B1F4 NUSHU CHARACTER-1B1F4 +1B1F5 NUSHU CHARACTER-1B1F5 +1B1F6 NUSHU CHARACTER-1B1F6 +1B1F7 NUSHU CHARACTER-1B1F7 +1B1F8 NUSHU CHARACTER-1B1F8 +1B1F9 NUSHU CHARACTER-1B1F9 +1B1FA NUSHU CHARACTER-1B1FA +1B1FB NUSHU CHARACTER-1B1FB +1B1FC NUSHU CHARACTER-1B1FC +1B1FD NUSHU CHARACTER-1B1FD +1B1FE NUSHU CHARACTER-1B1FE +1B1FF NUSHU CHARACTER-1B1FF +1B200 NUSHU CHARACTER-1B200 +1B201 NUSHU CHARACTER-1B201 + x 591A +1B202 NUSHU CHARACTER-1B202 +1B203 NUSHU CHARACTER-1B203 +1B204 NUSHU CHARACTER-1B204 +1B205 NUSHU CHARACTER-1B205 + x 7532 +1B206 NUSHU CHARACTER-1B206 +1B207 NUSHU CHARACTER-1B207 +1B208 NUSHU CHARACTER-1B208 +1B209 NUSHU CHARACTER-1B209 +1B20A NUSHU CHARACTER-1B20A + x 53CC +1B20B NUSHU CHARACTER-1B20B +1B20C NUSHU CHARACTER-1B20C +1B20D NUSHU CHARACTER-1B20D +1B20E NUSHU CHARACTER-1B20E + x 7530 +1B20F NUSHU CHARACTER-1B20F +1B210 NUSHU CHARACTER-1B210 +1B211 NUSHU CHARACTER-1B211 +1B212 NUSHU CHARACTER-1B212 +1B213 NUSHU CHARACTER-1B213 + x 5723 +1B214 NUSHU CHARACTER-1B214 +1B215 NUSHU CHARACTER-1B215 +@ Seven-stroke characters +1B216 NUSHU CHARACTER-1B216 + x 65E9 +1B217 NUSHU CHARACTER-1B217 +1B218 NUSHU CHARACTER-1B218 +1B219 NUSHU CHARACTER-1B219 +1B21A NUSHU CHARACTER-1B21A +1B21B NUSHU CHARACTER-1B21B +1B21C NUSHU CHARACTER-1B21C +1B21D NUSHU CHARACTER-1B21D +1B21E NUSHU CHARACTER-1B21E +1B21F NUSHU CHARACTER-1B21F +1B220 NUSHU CHARACTER-1B220 +1B221 NUSHU CHARACTER-1B221 +1B222 NUSHU CHARACTER-1B222 +1B223 NUSHU CHARACTER-1B223 +1B224 NUSHU CHARACTER-1B224 +1B225 NUSHU CHARACTER-1B225 +1B226 NUSHU CHARACTER-1B226 +1B227 NUSHU CHARACTER-1B227 +1B228 NUSHU CHARACTER-1B228 +1B229 NUSHU CHARACTER-1B229 +1B22A NUSHU CHARACTER-1B22A +1B22B NUSHU CHARACTER-1B22B +1B22C NUSHU CHARACTER-1B22C +1B22D NUSHU CHARACTER-1B22D +1B22E NUSHU CHARACTER-1B22E + x 6286 +1B22F NUSHU CHARACTER-1B22F +1B230 NUSHU CHARACTER-1B230 +1B231 NUSHU CHARACTER-1B231 +1B232 NUSHU CHARACTER-1B232 +1B233 NUSHU CHARACTER-1B233 +1B234 NUSHU CHARACTER-1B234 +1B235 NUSHU CHARACTER-1B235 +1B236 NUSHU CHARACTER-1B236 +1B237 NUSHU CHARACTER-1B237 +1B238 NUSHU CHARACTER-1B238 +1B239 NUSHU CHARACTER-1B239 +1B23A NUSHU CHARACTER-1B23A +1B23B NUSHU CHARACTER-1B23B +1B23C NUSHU CHARACTER-1B23C +1B23D NUSHU CHARACTER-1B23D +1B23E NUSHU CHARACTER-1B23E +1B23F NUSHU CHARACTER-1B23F +1B240 NUSHU CHARACTER-1B240 +1B241 NUSHU CHARACTER-1B241 +1B242 NUSHU CHARACTER-1B242 +1B243 NUSHU CHARACTER-1B243 +@ Eight-stroke characters +1B244 NUSHU CHARACTER-1B244 + x 91CC +1B245 NUSHU CHARACTER-1B245 +1B246 NUSHU CHARACTER-1B246 +1B247 NUSHU CHARACTER-1B247 +1B248 NUSHU CHARACTER-1B248 +1B249 NUSHU CHARACTER-1B249 +1B24A NUSHU CHARACTER-1B24A +1B24B NUSHU CHARACTER-1B24B +1B24C NUSHU CHARACTER-1B24C +1B24D NUSHU CHARACTER-1B24D +1B24E NUSHU CHARACTER-1B24E +1B24F NUSHU CHARACTER-1B24F +1B250 NUSHU CHARACTER-1B250 +1B251 NUSHU CHARACTER-1B251 +1B252 NUSHU CHARACTER-1B252 +1B253 NUSHU CHARACTER-1B253 +1B254 NUSHU CHARACTER-1B254 +1B255 NUSHU CHARACTER-1B255 +1B256 NUSHU CHARACTER-1B256 +1B257 NUSHU CHARACTER-1B257 +1B258 NUSHU CHARACTER-1B258 +1B259 NUSHU CHARACTER-1B259 +1B25A NUSHU CHARACTER-1B25A +1B25B NUSHU CHARACTER-1B25B +1B25C NUSHU CHARACTER-1B25C +1B25D NUSHU CHARACTER-1B25D +1B25E NUSHU CHARACTER-1B25E +1B25F NUSHU CHARACTER-1B25F +1B260 NUSHU CHARACTER-1B260 +1B261 NUSHU CHARACTER-1B261 +1B262 NUSHU CHARACTER-1B262 +1B263 NUSHU CHARACTER-1B263 +1B264 NUSHU CHARACTER-1B264 +1B265 NUSHU CHARACTER-1B265 + x 53F7 +1B266 NUSHU CHARACTER-1B266 +1B267 NUSHU CHARACTER-1B267 +1B268 NUSHU CHARACTER-1B268 +1B269 NUSHU CHARACTER-1B269 +1B26A NUSHU CHARACTER-1B26A +1B26B NUSHU CHARACTER-1B26B +1B26C NUSHU CHARACTER-1B26C +1B26D NUSHU CHARACTER-1B26D +1B26E NUSHU CHARACTER-1B26E +1B26F NUSHU CHARACTER-1B26F +1B270 NUSHU CHARACTER-1B270 +1B271 NUSHU CHARACTER-1B271 +1B272 NUSHU CHARACTER-1B272 +1B273 NUSHU CHARACTER-1B273 +1B274 NUSHU CHARACTER-1B274 +1B275 NUSHU CHARACTER-1B275 +1B276 NUSHU CHARACTER-1B276 +1B277 NUSHU CHARACTER-1B277 +1B278 NUSHU CHARACTER-1B278 +1B279 NUSHU CHARACTER-1B279 +1B27A NUSHU CHARACTER-1B27A +1B27B NUSHU CHARACTER-1B27B +1B27C NUSHU CHARACTER-1B27C +1B27D NUSHU CHARACTER-1B27D +1B27E NUSHU CHARACTER-1B27E +1B27F NUSHU CHARACTER-1B27F +1B280 NUSHU CHARACTER-1B280 +1B281 NUSHU CHARACTER-1B281 +1B282 NUSHU CHARACTER-1B282 +1B283 NUSHU CHARACTER-1B283 +@ Nine-stroke characters +1B284 NUSHU CHARACTER-1B284 +1B285 NUSHU CHARACTER-1B285 +1B286 NUSHU CHARACTER-1B286 +1B287 NUSHU CHARACTER-1B287 +1B288 NUSHU CHARACTER-1B288 +1B289 NUSHU CHARACTER-1B289 +1B28A NUSHU CHARACTER-1B28A +1B28B NUSHU CHARACTER-1B28B +1B28C NUSHU CHARACTER-1B28C +1B28D NUSHU CHARACTER-1B28D +1B28E NUSHU CHARACTER-1B28E +1B28F NUSHU CHARACTER-1B28F +1B290 NUSHU CHARACTER-1B290 +1B291 NUSHU CHARACTER-1B291 +1B292 NUSHU CHARACTER-1B292 +1B293 NUSHU CHARACTER-1B293 +1B294 NUSHU CHARACTER-1B294 +1B295 NUSHU CHARACTER-1B295 +1B296 NUSHU CHARACTER-1B296 +1B297 NUSHU CHARACTER-1B297 +1B298 NUSHU CHARACTER-1B298 +1B299 NUSHU CHARACTER-1B299 +1B29A NUSHU CHARACTER-1B29A +1B29B NUSHU CHARACTER-1B29B +1B29C NUSHU CHARACTER-1B29C +1B29D NUSHU CHARACTER-1B29D +1B29E NUSHU CHARACTER-1B29E +1B29F NUSHU CHARACTER-1B29F +1B2A0 NUSHU CHARACTER-1B2A0 +1B2A1 NUSHU CHARACTER-1B2A1 +1B2A2 NUSHU CHARACTER-1B2A2 +1B2A3 NUSHU CHARACTER-1B2A3 + x 82F1 +1B2A4 NUSHU CHARACTER-1B2A4 +1B2A5 NUSHU CHARACTER-1B2A5 +1B2A6 NUSHU CHARACTER-1B2A6 +1B2A7 NUSHU CHARACTER-1B2A7 +1B2A8 NUSHU CHARACTER-1B2A8 +1B2A9 NUSHU CHARACTER-1B2A9 +1B2AA NUSHU CHARACTER-1B2AA +1B2AB NUSHU CHARACTER-1B2AB +1B2AC NUSHU CHARACTER-1B2AC +1B2AD NUSHU CHARACTER-1B2AD +1B2AE NUSHU CHARACTER-1B2AE +1B2AF NUSHU CHARACTER-1B2AF +@ Ten-stroke characters +1B2B0 NUSHU CHARACTER-1B2B0 +1B2B1 NUSHU CHARACTER-1B2B1 +1B2B2 NUSHU CHARACTER-1B2B2 +1B2B3 NUSHU CHARACTER-1B2B3 +1B2B4 NUSHU CHARACTER-1B2B4 +1B2B5 NUSHU CHARACTER-1B2B5 +1B2B6 NUSHU CHARACTER-1B2B6 +1B2B7 NUSHU CHARACTER-1B2B7 +1B2B8 NUSHU CHARACTER-1B2B8 +1B2B9 NUSHU CHARACTER-1B2B9 +1B2BA NUSHU CHARACTER-1B2BA +1B2BB NUSHU CHARACTER-1B2BB +1B2BC NUSHU CHARACTER-1B2BC +1B2BD NUSHU CHARACTER-1B2BD +1B2BE NUSHU CHARACTER-1B2BE +1B2BF NUSHU CHARACTER-1B2BF +1B2C0 NUSHU CHARACTER-1B2C0 +1B2C1 NUSHU CHARACTER-1B2C1 + x 9580 +1B2C2 NUSHU CHARACTER-1B2C2 +1B2C3 NUSHU CHARACTER-1B2C3 +1B2C4 NUSHU CHARACTER-1B2C4 +1B2C5 NUSHU CHARACTER-1B2C5 +1B2C6 NUSHU CHARACTER-1B2C6 +1B2C7 NUSHU CHARACTER-1B2C7 +1B2C8 NUSHU CHARACTER-1B2C8 +1B2C9 NUSHU CHARACTER-1B2C9 +1B2CA NUSHU CHARACTER-1B2CA +1B2CB NUSHU CHARACTER-1B2CB +1B2CC NUSHU CHARACTER-1B2CC +1B2CD NUSHU CHARACTER-1B2CD +@ Eleven-stroke characters +1B2CE NUSHU CHARACTER-1B2CE +1B2CF NUSHU CHARACTER-1B2CF +1B2D0 NUSHU CHARACTER-1B2D0 +1B2D1 NUSHU CHARACTER-1B2D1 + x 57CB +1B2D2 NUSHU CHARACTER-1B2D2 +1B2D3 NUSHU CHARACTER-1B2D3 +1B2D4 NUSHU CHARACTER-1B2D4 +1B2D5 NUSHU CHARACTER-1B2D5 +1B2D6 NUSHU CHARACTER-1B2D6 + x 83AB +1B2D7 NUSHU CHARACTER-1B2D7 +1B2D8 NUSHU CHARACTER-1B2D8 +1B2D9 NUSHU CHARACTER-1B2D9 +1B2DA NUSHU CHARACTER-1B2DA +1B2DB NUSHU CHARACTER-1B2DB +1B2DC NUSHU CHARACTER-1B2DC +1B2DD NUSHU CHARACTER-1B2DD +1B2DE NUSHU CHARACTER-1B2DE +1B2DF NUSHU CHARACTER-1B2DF +1B2E0 NUSHU CHARACTER-1B2E0 +@ Twelve-stroke characters +1B2E1 NUSHU CHARACTER-1B2E1 +1B2E2 NUSHU CHARACTER-1B2E2 +1B2E3 NUSHU CHARACTER-1B2E3 +1B2E4 NUSHU CHARACTER-1B2E4 +1B2E5 NUSHU CHARACTER-1B2E5 +1B2E6 NUSHU CHARACTER-1B2E6 +1B2E7 NUSHU CHARACTER-1B2E7 +1B2E8 NUSHU CHARACTER-1B2E8 +1B2E9 NUSHU CHARACTER-1B2E9 +1B2EA NUSHU CHARACTER-1B2EA +1B2EB NUSHU CHARACTER-1B2EB +1B2EC NUSHU CHARACTER-1B2EC +1B2ED NUSHU CHARACTER-1B2ED +@ Thirteen-stroke characters +1B2EE NUSHU CHARACTER-1B2EE +1B2EF NUSHU CHARACTER-1B2EF +1B2F0 NUSHU CHARACTER-1B2F0 +1B2F1 NUSHU CHARACTER-1B2F1 +1B2F2 NUSHU CHARACTER-1B2F2 +1B2F3 NUSHU CHARACTER-1B2F3 +@ Fourteen-stroke characters +1B2F4 NUSHU CHARACTER-1B2F4 +1B2F5 NUSHU CHARACTER-1B2F5 +1B2F6 NUSHU CHARACTER-1B2F6 +@ Fifteen-stroke characters +1B2F7 NUSHU CHARACTER-1B2F7 +1B2F8 NUSHU CHARACTER-1B2F8 +1B2F9 NUSHU CHARACTER-1B2F9 +@ Sixteen-stroke characters +1B2FA NUSHU CHARACTER-1B2FA +1B2FB NUSHU CHARACTER-1B2FB @@ 1BC00 Duployan 1BC9F @ Non-joining consonants 1BC00 DUPLOYAN LETTER H @@ -37633,7 +40617,7 @@ FFFF <not a character> * Romanian str-/-str 1BC79 DUPLOYAN AFFIX ATTACHED TAIL * orientating character - * French suffix -sionaire + * French suffix -sionnaire 1BC7A DUPLOYAN AFFIX ATTACHED E HOOK * glyph is retrograde and opens up or down, depending on preceding letter * French suffix -te @@ -37705,12 +40689,12 @@ FFFF <not a character> 1BC93 DUPLOYAN AFFIX LOW LONG GRAVE * Pernin extra- 1BC94 DUPLOYAN AFFIX LOW DOT - * French suffix -ie + * French suffix -ié * French iterative number * Romanian affix inter- * not Romanian millions - see 0323 combining dot below and 0324 combining diaeresis below 1BC95 DUPLOYAN AFFIX LOW CIRCLE - * French suffix -iere + * French suffix -ière * French percent x (modifier letter low ring - 02F3) 1BC96 DUPLOYAN AFFIX LOW LINE @@ -38524,7 +41508,7 @@ FFFF <not a character> @ Monogram 1D300 MONOGRAM FOR EARTH = ren - * usually associated with human (Chinese ren), rather than earth + * usually associated with human (Chinese rén), rather than earth (Chinese dì) x (monogram for yang - 268A) x (monogram for yin - 268B) @ Digrams @@ -39282,9 +42266,9 @@ FFFF <not a character> 1D537 MATHEMATICAL FRAKTUR SMALL Z # <font> 007A latin small letter z @ Double-struck symbols -@+ This style is sometimes known as open-face or blackboard-bold. Double-struck symbols already encoded in the Letterlike Symbols block and omitted here to avoid duplicate encoding. Considerable variation in font style is acceptable, as long as the glyphs retain the visual element of doubled strokes. +@+ This style is sometimes known as open-face or blackboard-bold. Double-struck symbols already encoded in the Letterlike Symbols block are omitted here to avoid duplicate encoding. Considerable variation in font style is acceptable, as long as the glyphs retain the visual element of doubled strokes. 1D538 MATHEMATICAL DOUBLE-STRUCK CAPITAL A - * a glyph variant with doubled stroke on the right exists + * a glyph variant with doubled stroke on the left exists # <font> 0041 latin capital letter a 1D539 MATHEMATICAL DOUBLE-STRUCK CAPITAL B # <font> 0042 latin capital letter b @@ -41425,6 +44409,46 @@ FFFF <not a character> 1DAAD SIGNWRITING ROTATION MODIFIER-14 1DAAE SIGNWRITING ROTATION MODIFIER-15 1DAAF SIGNWRITING ROTATION MODIFIER-16 +@@ 1E000 Glagolitic Supplement 1E02F +@ Combining letters +1E000 COMBINING GLAGOLITIC LETTER AZU +1E001 COMBINING GLAGOLITIC LETTER BUKY +1E002 COMBINING GLAGOLITIC LETTER VEDE +1E003 COMBINING GLAGOLITIC LETTER GLAGOLI +1E004 COMBINING GLAGOLITIC LETTER DOBRO +1E005 COMBINING GLAGOLITIC LETTER YESTU +1E006 COMBINING GLAGOLITIC LETTER ZHIVETE +1E008 COMBINING GLAGOLITIC LETTER ZEMLJA +1E009 COMBINING GLAGOLITIC LETTER IZHE +1E00A COMBINING GLAGOLITIC LETTER INITIAL IZHE +1E00B COMBINING GLAGOLITIC LETTER I +1E00C COMBINING GLAGOLITIC LETTER DJERVI +1E00D COMBINING GLAGOLITIC LETTER KAKO +1E00E COMBINING GLAGOLITIC LETTER LJUDIJE +1E00F COMBINING GLAGOLITIC LETTER MYSLITE +1E010 COMBINING GLAGOLITIC LETTER NASHI +1E011 COMBINING GLAGOLITIC LETTER ONU +1E012 COMBINING GLAGOLITIC LETTER POKOJI +1E013 COMBINING GLAGOLITIC LETTER RITSI +1E014 COMBINING GLAGOLITIC LETTER SLOVO +1E015 COMBINING GLAGOLITIC LETTER TVRIDO +1E016 COMBINING GLAGOLITIC LETTER UKU +1E017 COMBINING GLAGOLITIC LETTER FRITU +1E018 COMBINING GLAGOLITIC LETTER HERU +1E01B COMBINING GLAGOLITIC LETTER SHTA +1E01C COMBINING GLAGOLITIC LETTER TSI +1E01D COMBINING GLAGOLITIC LETTER CHRIVI +1E01E COMBINING GLAGOLITIC LETTER SHA +1E01F COMBINING GLAGOLITIC LETTER YERU +1E020 COMBINING GLAGOLITIC LETTER YERI +1E021 COMBINING GLAGOLITIC LETTER YATI +1E023 COMBINING GLAGOLITIC LETTER YU +1E024 COMBINING GLAGOLITIC LETTER SMALL YUS +1E026 COMBINING GLAGOLITIC LETTER YO +1E027 COMBINING GLAGOLITIC LETTER IOTATED SMALL YUS +1E028 COMBINING GLAGOLITIC LETTER BIG YUS +1E029 COMBINING GLAGOLITIC LETTER IOTATED BIG YUS +1E02A COMBINING GLAGOLITIC LETTER FITA @@ 1E800 Mende Kikakui 1E8DF @ Syllables in k- 1E800 MENDE KIKAKUI SYLLABLE M001 KI @@ -41691,6 +44715,102 @@ FFFF <not a character> 1E8D4 MENDE KIKAKUI COMBINING NUMBER TEN THOUSANDS 1E8D5 MENDE KIKAKUI COMBINING NUMBER HUNDRED THOUSANDS 1E8D6 MENDE KIKAKUI COMBINING NUMBER MILLIONS +@@ 1E900 Adlam 1E95F +@ Capital letters +1E900 ADLAM CAPITAL LETTER ALIF +1E901 ADLAM CAPITAL LETTER DAALI +1E902 ADLAM CAPITAL LETTER LAAM +1E903 ADLAM CAPITAL LETTER MIIM +1E904 ADLAM CAPITAL LETTER BA +1E905 ADLAM CAPITAL LETTER SINNYIIYHE +1E906 ADLAM CAPITAL LETTER PE +1E907 ADLAM CAPITAL LETTER BHE +1E908 ADLAM CAPITAL LETTER RA +1E909 ADLAM CAPITAL LETTER E +1E90A ADLAM CAPITAL LETTER FA +1E90B ADLAM CAPITAL LETTER I +1E90C ADLAM CAPITAL LETTER O +1E90D ADLAM CAPITAL LETTER DHA +1E90E ADLAM CAPITAL LETTER YHE +1E90F ADLAM CAPITAL LETTER WAW +1E910 ADLAM CAPITAL LETTER NUN +1E911 ADLAM CAPITAL LETTER KAF +1E912 ADLAM CAPITAL LETTER YA +1E913 ADLAM CAPITAL LETTER U +1E914 ADLAM CAPITAL LETTER JIIM +1E915 ADLAM CAPITAL LETTER CHI +1E916 ADLAM CAPITAL LETTER HA +1E917 ADLAM CAPITAL LETTER QAAF +1E918 ADLAM CAPITAL LETTER GA +1E919 ADLAM CAPITAL LETTER NYA +1E91A ADLAM CAPITAL LETTER TU +1E91B ADLAM CAPITAL LETTER NHA +@ Supplementary capital letters +1E91C ADLAM CAPITAL LETTER VA +1E91D ADLAM CAPITAL LETTER KHA +1E91E ADLAM CAPITAL LETTER GBE +1E91F ADLAM CAPITAL LETTER ZAL +1E920 ADLAM CAPITAL LETTER KPO +1E921 ADLAM CAPITAL LETTER SHA +@ Small letters +1E922 ADLAM SMALL LETTER ALIF +1E923 ADLAM SMALL LETTER DAALI +1E924 ADLAM SMALL LETTER LAAM +1E925 ADLAM SMALL LETTER MIIM +1E926 ADLAM SMALL LETTER BA +1E927 ADLAM SMALL LETTER SINNYIIYHE +1E928 ADLAM SMALL LETTER PE +1E929 ADLAM SMALL LETTER BHE +1E92A ADLAM SMALL LETTER RA +1E92B ADLAM SMALL LETTER E +1E92C ADLAM SMALL LETTER FA +1E92D ADLAM SMALL LETTER I +1E92E ADLAM SMALL LETTER O +1E92F ADLAM SMALL LETTER DHA +1E930 ADLAM SMALL LETTER YHE +1E931 ADLAM SMALL LETTER WAW +1E932 ADLAM SMALL LETTER NUN +1E933 ADLAM SMALL LETTER KAF +1E934 ADLAM SMALL LETTER YA +1E935 ADLAM SMALL LETTER U +1E936 ADLAM SMALL LETTER JIIM +1E937 ADLAM SMALL LETTER CHI +1E938 ADLAM SMALL LETTER HA +1E939 ADLAM SMALL LETTER QAAF +1E93A ADLAM SMALL LETTER GA +1E93B ADLAM SMALL LETTER NYA +1E93C ADLAM SMALL LETTER TU +1E93D ADLAM SMALL LETTER NHA +@ Supplementary small letters +1E93E ADLAM SMALL LETTER VA +1E93F ADLAM SMALL LETTER KHA +1E940 ADLAM SMALL LETTER GBE +1E941 ADLAM SMALL LETTER ZAL +1E942 ADLAM SMALL LETTER KPO +1E943 ADLAM SMALL LETTER SHA +@ Diacritical marks +1E944 ADLAM ALIF LENGTHENER +1E945 ADLAM VOWEL LENGTHENER +1E946 ADLAM GEMINATION MARK +1E947 ADLAM HAMZA +1E948 ADLAM CONSONANT MODIFIER +1E949 ADLAM GEMINATE CONSONANT MODIFIER +1E94A ADLAM NUKTA + * called hoortobbhere when drawn above and lestobbhere when drawn below the base character +@ Digits +1E950 ADLAM DIGIT ZERO +1E951 ADLAM DIGIT ONE +1E952 ADLAM DIGIT TWO +1E953 ADLAM DIGIT THREE +1E954 ADLAM DIGIT FOUR +1E955 ADLAM DIGIT FIVE +1E956 ADLAM DIGIT SIX +1E957 ADLAM DIGIT SEVEN +1E958 ADLAM DIGIT EIGHT +1E959 ADLAM DIGIT NINE +@ Punctuation +1E95E ADLAM INITIAL EXCLAMATION MARK +1E95F ADLAM INITIAL QUESTION MARK @@ 1EE00 Arabic Mathematical Alphabetic Symbols 1EEFF @ Isolated symbols 1EE00 ARABIC MATHEMATICAL ALEF @@ -42049,8 +45169,6 @@ FFFF <not a character> @ Dragon tiles 1F004 MAHJONG TILE RED DRAGON = hongzhong - ~ 1F004 FE0E text style - ~ 1F004 FE0F emoji style 1F005 MAHJONG TILE GREEN DRAGON = qingfa 1F006 MAHJONG TILE WHITE DRAGON @@ -42106,7 +45224,6 @@ FFFF <not a character> 1F02A MAHJONG TILE JOKER = baida 1F02B MAHJONG TILE BACK -@~ ! @@ 1F030 Domino Tiles 1F09F @ Horizontal tiles 1F030 DOMINO TILE HORIZONTAL BACK @@ -42379,7 +45496,7 @@ FFFF <not a character> 1F10B DINGBAT CIRCLED SANS-SERIF DIGIT ZERO 1F10C DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO @ Parenthesized Latin letters -@+ This set provides uppercase versions of the set starting at 249C. +@+ This set provides uppercase versions of the set starting at 249C. Parenthesized Latin letters do not have case mappings. 1F110 PARENTHESIZED LATIN CAPITAL LETTER A # 0028 0041 0029 1F111 PARENTHESIZED LATIN CAPITAL LETTER B @@ -42590,12 +45707,8 @@ FFFF <not a character> @+ The square edges may be slightly rounded. 1F170 NEGATIVE SQUARED LATIN CAPITAL LETTER A = blood type A - ~ 1F170 FE0E text style - ~ 1F170 FE0F emoji style 1F171 NEGATIVE SQUARED LATIN CAPITAL LETTER B = blood type B - ~ 1F171 FE0E text style - ~ 1F171 FE0F emoji style 1F172 NEGATIVE SQUARED LATIN CAPITAL LETTER C = centre, city centre 1F173 NEGATIVE SQUARED LATIN CAPITAL LETTER D @@ -42617,12 +45730,8 @@ FFFF <not a character> 1F17D NEGATIVE SQUARED LATIN CAPITAL LETTER N 1F17E NEGATIVE SQUARED LATIN CAPITAL LETTER O = blood type O - ~ 1F17E FE0E text style - ~ 1F17E FE0F emoji style 1F17F NEGATIVE SQUARED LATIN CAPITAL LETTER P = parking space empty-full (ARIB STD B24) - ~ 1F17F FE0E text style - ~ 1F17F FE0F emoji style 1F180 NEGATIVE SQUARED LATIN CAPITAL LETTER Q 1F181 NEGATIVE SQUARED LATIN CAPITAL LETTER R 1F182 NEGATIVE SQUARED LATIN CAPITAL LETTER S @@ -42666,6 +45775,37 @@ FFFF <not a character> = new information, update 1F19A SQUARED VS = versus +@ Squared Latin letter sequences from ARIB STD B62 +1F19B SQUARED THREE D +1F19C SQUARED SECOND SCREEN +1F19D SQUARED TWO K +1F19E SQUARED FOUR K +1F19F SQUARED EIGHT K +1F1A0 SQUARED FIVE POINT ONE + * denotes 5.1-channel surround sound +1F1A1 SQUARED SEVEN POINT ONE + * denotes 7.1-channel surround sound +1F1A2 SQUARED TWENTY-TWO POINT TWO + * denotes 22.2-channel surround sound +1F1A3 SQUARED SIXTY P + * denotes 60Hz frame rate with progressive scanning +1F1A4 SQUARED ONE HUNDRED TWENTY P + * denotes 120Hz frame rate with progressive scanning +1F1A5 SQUARED LATIN SMALL LETTER D + = data +1F1A6 SQUARED HC + = hybrid cast +1F1A7 SQUARED HDR + = high dynamic range +1F1A8 SQUARED HI-RES + = high resolution +1F1A9 SQUARED LOSSLESS +1F1AA SQUARED SHV + = super high vision +1F1AB SQUARED UHD + = ultra-high definition +1F1AC SQUARED VOD + = video on demand @ Regional indicator symbols @+ These characters can be used in pairs to represent regional codes. In some emoji implementations, certain pairs may be recognized and displayed by alternate means; for instance, an implementation might recognize F + R and display this combination with a symbol representing the flag of France. 1F1E6 REGIONAL INDICATOR SYMBOL LETTER A @@ -42694,7 +45834,6 @@ FFFF <not a character> 1F1FD REGIONAL INDICATOR SYMBOL LETTER X 1F1FE REGIONAL INDICATOR SYMBOL LETTER Y 1F1FF REGIONAL INDICATOR SYMBOL LETTER Z -@~ ! @@ 1F200 Enclosed Ideographic Supplement 1F2FF @ Squared hiragana from ARIB STD B24 1F200 SQUARE HIRAGANA HOKA @@ -42707,8 +45846,6 @@ FFFF <not a character> 1F202 SQUARED KATAKANA SA = service sign x (circled katakana sa - 32DA) - ~ 1F202 FE0E text style - ~ 1F202 FE0F emoji style # <square> 30B5 @ Squared ideographs and kana from ARIB STD B24 1F210 SQUARED CJK UNIFIED IDEOGRAPH-624B @@ -42745,8 +45882,6 @@ FFFF <not a character> 1F21A SQUARED CJK UNIFIED IDEOGRAPH-7121 = free broadcasting service = non-existence sign - ~ 1F21A FE0E text style - ~ 1F21A FE0F emoji style # <square> 7121 1F21B SQUARED CJK UNIFIED IDEOGRAPH-6599 = pay broadcasting service @@ -42811,8 +45946,6 @@ FFFF <not a character> 1F22F SQUARED CJK UNIFIED IDEOGRAPH-6307 = designated hitter = reserved sign - ~ 1F22F FE0E text style - ~ 1F22F FE0F emoji style # <square> 6307 1F230 SQUARED CJK UNIFIED IDEOGRAPH-8D70 = runner @@ -42840,8 +45973,6 @@ FFFF <not a character> 1F237 SQUARED CJK UNIFIED IDEOGRAPH-6708 = monthly sign x (circled ideograph moon - 328A) - ~ 1F237 FE0E text style - ~ 1F237 FE0F emoji style # <square> 6708 1F238 SQUARED CJK UNIFIED IDEOGRAPH-7533 = application sign @@ -42852,6 +45983,9 @@ FFFF <not a character> 1F23A SQUARED CJK UNIFIED IDEOGRAPH-55B6 = in business sign # <square> 55B6 +1F23B SQUARED CJK UNIFIED IDEOGRAPH-914D + = program delivery over network (ARIB STD B62) + # <square> 914D @ Ideographs with tortoise shell brackets from ARIB STD B24 1F240 TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C = home run @@ -42887,7 +46021,28 @@ FFFF <not a character> 1F251 CIRCLED IDEOGRAPH ACCEPT = accept sign # <circle> 53EF -@~ ! +@ Symbols for Chinese folk religion +1F260 ROUNDED SYMBOL FOR FU + * luck + x 798F +1F261 ROUNDED SYMBOL FOR LU + * prosperity + x 797F + x 7984 +1F262 ROUNDED SYMBOL FOR SHOU + * longevity + x 58FD + x 5BFF +1F263 ROUNDED SYMBOL FOR XI + * happiness + x 559C +1F264 ROUNDED SYMBOL FOR SHUANGXI + * double happiness, love and marriage + x 56CD +1F265 ROUNDED SYMBOL FOR CAI + * wealth + x 8CA1 + x 8D22 @@ 1F300 Miscellaneous Symbols and Pictographs 1F5FF @ Weather, landscape, and sky symbols 1F300 CYCLONE @@ -42904,6 +46059,7 @@ FFFF <not a character> 1F308 RAINBOW 1F309 BRIDGE AT NIGHT 1F30A WATER WAVE + = tsunami, tidal wave 1F30B VOLCANO 1F30C MILKY WAY @ Globe symbols @@ -42987,6 +46143,7 @@ FFFF <not a character> x (flower - 2698) 1F338 CHERRY BLOSSOM 1F339 ROSE + x (wilted flower - 1F940) 1F33A HIBISCUS 1F33B SUNFLOWER 1F33C BLOSSOM @@ -43063,6 +46220,7 @@ FFFF <not a character> * glyph may show a fork and spoon * glyph may show a crossed fork and knife x (fork and knife with plate - 1F37D) + x (spoon - 1F944) @ Beverage symbols 1F375 TEACUP WITHOUT HANDLE x (hot beverage - 2615) @@ -43072,10 +46230,12 @@ FFFF <not a character> 1F378 COCKTAIL GLASS = lounge x (couch and lamp - 1F6CB) + x (tumbler glass - 1F943) 1F379 TROPICAL DRINK 1F37A BEER MUG 1F37B CLINKING BEER MUGS = cheers + x (clinking glasses - 1F942) 1F37C BABY BOTTLE @ Accommodation symbol 1F37D FORK AND KNIFE WITH PLATE @@ -43094,6 +46254,7 @@ FFFF <not a character> 1F384 CHRISTMAS TREE 1F385 FATHER CHRISTMAS = Santa Claus + x (mother christmas - 1F936) 1F386 FIREWORKS 1F387 FIREWORK SPARKLER * long, stick-like firework that looks like a burning incense stick @@ -43128,7 +46289,7 @@ FFFF <not a character> 1F397 REMINDER RIBBON @ Musical symbols 1F398 MUSICAL KEYBOARD WITH JACKS - = midi, midi keyboard + = midi, midi keyboard, master keyboard with plugs x (musical keyboard - 1F3B9) 1F399 STUDIO MICROPHONE = microphone @@ -43191,7 +46352,6 @@ FFFF <not a character> x (bullseye - 25CE) 1F3B0 SLOT MACHINE 1F3B1 BILLIARDS - * sometimes depicted as just an 8-ball 1F3B2 GAME DIE 1F3B3 BOWLING 1F3B4 FLOWER PLAYING CARDS @@ -43212,8 +46372,12 @@ FFFF <not a character> 1F3BC MUSICAL SCORE x (musical symbol g clef - 1D11E) @ Sport symbols -@+ See other sport symbols in the Miscelleaneous Symbols block. +@+ See other sport symbols in the Miscellaneous Symbols block. 1F3BD RUNNING SHIRT WITH SASH + = ekiden (Japanese) + * running shirt with separate sash signifies long-distance relay running + * symbol is generalized to represent athletics + * glyph may be shown with a sash, a stripe, or neither 1F3BE TENNIS RACQUET AND BALL = tennis 1F3BF SKI AND SKI BOOT @@ -43229,6 +46393,7 @@ FFFF <not a character> 1F3C4 SURFER = surfing 1F3C5 SPORTS MEDAL + x (first place medal - 1F947) 1F3C6 TROPHY 1F3C7 HORSE RACING 1F3C8 AMERICAN FOOTBALL @@ -43247,7 +46412,7 @@ FFFF <not a character> 1F3D1 FIELD HOCKEY STICK AND BALL 1F3D2 ICE HOCKEY STICK AND PUCK 1F3D3 TABLE TENNIS PADDLE AND BALL -@ Buiding and map symbols +@ Building and map symbols 1F3D4 SNOW CAPPED MOUNTAIN x (mountain - 26F0) 1F3D5 CAMPING @@ -43269,7 +46434,6 @@ FFFF <not a character> 1F3DB CLASSICAL BUILDING = public building 1F3DC DESERT - = desert x (cactus - 1F335) 1F3DD DESERT ISLAND = island @@ -43328,12 +46492,14 @@ FFFF <not a character> @ Sport symbols 1F3F8 BADMINTON RACQUET AND SHUTTLECOCK 1F3F9 BOW AND ARROW - * used for Sagittarius + = archery + * also used for Sagittarius x (sagittarius - 2650) @ Miscellaneous symbol 1F3FA AMPHORA * used for Aquarius x (aquarius - 2652) + x (linear b ideogram vessel b209 - 100E8) @ Emoji modifiers 1F3FB EMOJI MODIFIER FITZPATRICK TYPE-1-2 1F3FC EMOJI MODIFIER FITZPATRICK TYPE-3 @@ -43371,6 +46537,7 @@ FFFF <not a character> 1F40D SNAKE * sixth of the signs of the Asian zodiac 1F40E HORSE + = equestrian sports * seventh of the signs of the Asian zodiac 1F40F RAM * eighth of the signs of the Asian zodiac @@ -43408,6 +46575,7 @@ FFFF <not a character> 1F420 TROPICAL FISH 1F421 BLOWFISH 1F422 TURTLE + = tortoise, terrapin 1F423 HATCHING CHICK 1F424 BABY CHICK 1F425 FRONT-FACING BABY CHICK @@ -43508,8 +46676,10 @@ FFFF <not a character> = accounts 1F466 BOY 1F467 GIRL + x (child - 1F9D2) 1F468 MAN 1F469 WOMAN + x (adult - 1F9D1) 1F46A FAMILY = rated for family 1F46B MAN AND WOMAN HOLDING HANDS @@ -43520,23 +46690,27 @@ FFFF <not a character> 1F46F WOMAN WITH BUNNY EARS * most popularly depicted as two women dancing 1F470 BRIDE WITH VEIL + x (man in tuxedo - 1F935) 1F471 PERSON WITH BLOND HAIR 1F472 MAN WITH GUA PI MAO 1F473 MAN WITH TURBAN * may be shown with or without a beard 1F474 OLDER MAN 1F475 OLDER WOMAN + x (older adult - 1F9D3) 1F476 BABY 1F477 CONSTRUCTION WORKER * the helmet may show a green cross, used as a safety reminder in Japan x (helmet with white cross - 26D1) @ Fairy tale symbols 1F478 PRINCESS + x (prince - 1F934) 1F479 JAPANESE OGRE 1F47A JAPANESE GOBLIN 1F47B GHOST 1F47C BABY ANGEL 1F47D EXTRATERRESTRIAL ALIEN + x (flying saucer - 1F6F8) 1F47E ALIEN MONSTER x (robot face - 1F916) 1F47F IMP @@ -43548,6 +46722,7 @@ FFFF <not a character> 1F482 GUARDSMAN 1F483 DANCER * also used for "let's party" + x (man dancing - 1F57A) @ Personal care symbols 1F484 LIPSTICK 1F485 NAIL POLISH @@ -43586,6 +46761,7 @@ FFFF <not a character> x (white heart suit - 2661) x (black heart suit - 2665) x (heavy black heart - 2764) + x (orange heart - 1F9E1) 1F49A GREEN HEART 1F49B YELLOW HEART 1F49C PURPLE HEART @@ -43613,7 +46789,7 @@ FFFF <not a character> = running dash, briffits 1F4A9 PILE OF POO = dog dirt - * may be depicted with a friendly face + * may be depicted with or without a friendly face 1F4AA FLEXED BICEPS = strong, muscled 1F4AB DIZZY SYMBOL @@ -43847,9 +47023,11 @@ FFFF <not a character> = Japanese kitchen knife x (dagger knife - 1F5E1) 1F52B PISTOL + = handgun, revolver 1F52C MICROSCOPE 1F52D TELESCOPE 1F52E CRYSTAL BALL +@ Miscellaneous symbols 1F52F SIX POINTED STAR WITH MIDDLE DOT x (star of david - 2721) 1F530 JAPANESE SYMBOL FOR BEGINNER @@ -43981,6 +47159,10 @@ FFFF <not a character> 1F578 SPIDER WEB @ Game symbol 1F579 JOYSTICK +@ Role symbol +1F57A MAN DANCING + * forms a gender pair with 1F483 + x (dancer - 1F483) @ Communication symbols 1F57B LEFT HAND TELEPHONE RECEIVER x (telephone receiver - 1F4DE) @@ -44045,6 +47227,7 @@ FFFF <not a character> x (victory hand - 270C) 1F595 REVERSED HAND WITH MIDDLE FINGER EXTENDED 1F596 RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS + = Vulcan salute 1F597 WHITE DOWN POINTING LEFT HAND INDEX x (white down pointing index - 261F) x (white down pointing backhand index - 1F447) @@ -44068,6 +47251,10 @@ FFFF <not a character> x (white up pointing backhand index - 1F446) 1F5A3 BLACK DOWN POINTING BACKHAND INDEX x (white down pointing backhand index - 1F447) +@ Heart symbol +1F5A4 BLACK HEART + * unequivocally represented as black in all variants + x (black heart suit - 2665) @ Computer symbols 1F5A5 DESKTOP COMPUTER = tower computer @@ -44318,7 +47505,6 @@ FFFF <not a character> 1F634 SLEEPING FACE 1F635 DIZZY FACE 1F636 FACE WITHOUT MOUTH - * used for the South Wind in some Mahjong annotation x (white circle with two dots - 2687) 1F637 FACE WITH MEDICAL MASK @ Cat faces @@ -44345,6 +47531,7 @@ FFFF <not a character> * conveys "no deal" or "not ok", not anger; the inverse of 1F646 face with ok gesture 1F646 FACE WITH OK GESTURE 1F647 PERSON BOWING DEEPLY + * most commonly depicted as Japanese-style bowing while seated (dogeza) 1F648 SEE-NO-EVIL MONKEY 1F649 HEAR-NO-EVIL MONKEY 1F64A SPEAK-NO-EVIL MONKEY @@ -44390,7 +47577,7 @@ FFFF <not a character> 1F668 HOLLOW QUILT SQUARE ORNAMENT 1F669 HOLLOW QUILT SQUARE ORNAMENT IN BLACK SQUARE 1F66A SOLID QUILT SQUARE ORNAMENT - = fourfold knot ornament + = fourfold knot ornament 1F66B SOLID QUILT SQUARE ORNAMENT IN BLACK SQUARE = inverse fourfold knot ornament @ Rocket ornaments @@ -44402,7 +47589,7 @@ FFFF <not a character> 1F66F DOWNWARDS ROCKET @ Ampersand and ligature et ornaments 1F670 SCRIPT LIGATURE ET ORNAMENT - = italic ampersand lower case + = italic ampersand lowercase x (tironian sign et - 204A) 1F671 HEAVY SCRIPT LIGATURE ET ORNAMENT 1F672 LIGATURE OPEN ET ORNAMENT @@ -44557,8 +47744,19 @@ FFFF <not a character> 1F6CE BELLHOP BELL = reception, services 1F6CF BED -@ Signage +@ Signage and other symbols 1F6D0 PLACE OF WORSHIP +1F6D1 OCTAGONAL SIGN + = stop sign + * may contain text indicating stop + x (warning sign - 26A0) + x (heavy white down-pointing triangle - 26DB) + x (horizontal black octagon - 2BC3) +1F6D2 SHOPPING TROLLEY + = shopping cart +@ Map symbols +1F6D3 STUPA +1F6D4 PAGODA @ Miscellaneous symbols 1F6E0 HAMMER AND WRENCH = tools, repair facility @@ -44598,6 +47796,14 @@ FFFF <not a character> 1F6F3 PASSENGER SHIP = cruise line vacation x (ship - 1F6A2) +1F6F4 SCOOTER +1F6F5 MOTOR SCOOTER +1F6F6 CANOE +1F6F7 SLED + = sledge, toboggan +1F6F8 FLYING SAUCER + = UFO + x (extraterrestrial alien - 1F47D) @@ 1F700 Alchemical Symbols 1F77F @ Symbols for Aristotelian elements 1F700 ALCHEMICAL SYMBOL FOR QUINTESSENCE @@ -44838,11 +48044,10 @@ FFFF <not a character> 1F784 BLACK SLIGHTLY SMALL CIRCLE @ White circles @+ Adjective refers to the thickness of the ring. -@+ Constitute a set as follows: 25CB, 2B58, 1F785-1F789. +@+ Constitute a set as follows: 25CB, 2B58, 1F785-1F789 1F785 MEDIUM BOLD WHITE CIRCLE x (medium white circle - 26AA) 1F786 BOLD WHITE CIRCLE - = very heavy circle 1F787 HEAVY WHITE CIRCLE 1F788 VERY HEAVY WHITE CIRCLE 1F789 EXTREMELY HEAVY WHITE CIRCLE @@ -45151,6 +48356,20 @@ FFFF <not a character> 1F8AC WHITE ARROW SHAFT WIDTH ONE 1F8AD WHITE ARROW SHAFT WIDTH TWO THIRDS @@ 1F900 Supplemental Symbols and Pictographs 1F9FF +@ Typicon symbols +1F900 CIRCLED CROSS FORMEE WITH FOUR DOTS +1F901 CIRCLED CROSS FORMEE WITH TWO DOTS +1F902 CIRCLED CROSS FORMEE + x (maltese cross - 2720) +1F903 LEFT HALF CIRCLE WITH FOUR DOTS +1F904 LEFT HALF CIRCLE WITH THREE DOTS +1F905 LEFT HALF CIRCLE WITH TWO DOTS +1F906 LEFT HALF CIRCLE WITH DOT +1F907 LEFT HALF CIRCLE +1F908 DOWNWARD FACING HOOK +1F909 DOWNWARD FACING NOTCHED HOOK +1F90A DOWNWARD FACING HOOK WITH DOT +1F90B DOWNWARD FACING NOTCHED HOOK WITH DOT @ Emoticon faces 1F910 ZIPPER-MOUTH FACE 1F911 MONEY-MOUTH FACE @@ -45161,8 +48380,135 @@ FFFF <not a character> 1F916 ROBOT FACE x (alien monster - 1F47E) 1F917 HUGGING FACE -@ Hand symbol +@ Hand symbols 1F918 SIGN OF THE HORNS +1F919 CALL ME HAND +1F91A RAISED BACK OF HAND +1F91B LEFT-FACING FIST +1F91C RIGHT-FACING FIST +1F91D HANDSHAKE +1F91E HAND WITH INDEX AND MIDDLE FINGERS CROSSED +1F91F I LOVE YOU HAND SIGN + * can be abbreviated ILY +@ Emoticon faces +1F920 FACE WITH COWBOY HAT +1F921 CLOWN FACE +1F922 NAUSEATED FACE +1F923 ROLLING ON THE FLOOR LAUGHING + = rofl, rotfl +1F924 DROOLING FACE +1F925 LYING FACE +1F926 FACE PALM + = frustration, disbelief +1F927 SNEEZING FACE + = Gesundheit +1F928 FACE WITH ONE EYEBROW RAISED +1F929 GRINNING FACE WITH STAR EYES +1F92A GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE +1F92B FACE WITH FINGER COVERING CLOSED LIPS +1F92C SERIOUS FACE WITH SYMBOLS COVERING MOUTH +1F92D SMILING FACE WITH SMILING EYES AND HAND COVERING MOUTH +1F92E FACE WITH OPEN MOUTH VOMITING +1F92F SHOCKED FACE WITH EXPLODING HEAD +@ Portrait and role symbols +1F930 PREGNANT WOMAN +1F931 BREAST-FEEDING +1F932 PALMS UP TOGETHER +1F933 SELFIE + * typically used with face or human figure on the left +1F934 PRINCE + x (princess - 1F478) +1F935 MAN IN TUXEDO + * appearance for groom, may be paired with 1F470 + x (bride with veil - 1F470) +1F936 MOTHER CHRISTMAS + = Mrs. Claus + x (father christmas - 1F385) +1F937 SHRUG +1F938 PERSON DOING CARTWHEEL + = gymnastics +1F939 JUGGLING +1F93A FENCER + = fencing + x (crossed swords - 2694) +1F93B MODERN PENTATHLON +1F93C WRESTLERS + = wrestling +1F93D WATER POLO +1F93E HANDBALL +@ Miscellaneous symbols +1F940 WILTED FLOWER + x (rose - 1F339) +1F941 DRUM WITH DRUMSTICKS +1F942 CLINKING GLASSES + = celebration, formal toasting + x (clinking beer mugs - 1F37B) +1F943 TUMBLER GLASS + = whisky + * typically shown with ice + x (cocktail glass - 1F378) +1F944 SPOON + x (fork and knife - 1F374) +1F945 GOAL NET +1F946 RIFLE + = marksmanship, shooting, hunting +1F947 FIRST PLACE MEDAL + = gold medal + x (sports medal - 1F3C5) +1F948 SECOND PLACE MEDAL + = silver medal +1F949 THIRD PLACE MEDAL + = bronze medal +1F94A BOXING GLOVE + = boxing +1F94B MARTIAL ARTS UNIFORM + = judo, karate, taekwondo +1F94C CURLING STONE +@ Food symbols +1F950 CROISSANT +1F951 AVOCADO +1F952 CUCUMBER + = pickle +1F953 BACON +1F954 POTATO +1F955 CARROT +1F956 BAGUETTE BREAD + = French bread +1F957 GREEN SALAD +1F958 SHALLOW PAN OF FOOD + = paella, casserole +1F959 STUFFED FLATBREAD + = döner kebab, falafel, gyro, shawarma +1F95A EGG + = chicken egg +1F95B GLASS OF MILK + = milk +1F95C PEANUTS +1F95D KIWIFRUIT +1F95E PANCAKES + = hotcakes, crêpes, blini + * sweet or savory +1F95F DUMPLING + = potsticker, gyooza, jiaozi, pierogi, empanada +1F960 FORTUNE COOKIE +1F961 TAKEOUT BOX + = take-away box, oyster pail +1F962 CHOPSTICKS + = kuaizi, hashi, jeotgarak +1F963 BOWL WITH SPOON + * can indicate breakfast, cereal, congee, etc. +1F964 CUP WITH STRAW + * can indicate soda, juice, etc. +1F965 COCONUT +1F966 BROCCOLI +1F967 PIE + * may be sweet or savory +1F968 PRETZEL + * can indicate twistiness, intricacy +1F969 CUT OF MEAT + = porkchop, chop, steak +1F96A SANDWICH +1F96B CANNED FOOD @ Animal symbols 1F980 CRAB * used for Cancer @@ -45175,8 +48521,74 @@ FFFF <not a character> x (scorpius - 264F) 1F983 TURKEY 1F984 UNICORN FACE +1F985 EAGLE +1F986 DUCK +1F987 BAT +1F988 SHARK +1F989 OWL +1F98A FOX FACE +1F98B BUTTERFLY +1F98C DEER +1F98D GORILLA +1F98E LIZARD +1F98F RHINOCEROS +1F990 SHRIMP +1F991 SQUID +1F992 GIRAFFE FACE +1F993 ZEBRA FACE +1F994 HEDGEHOG +1F995 SAUROPOD + * includes Brontosaurus, Diplodocus, Brachiosaurus +1F996 T-REX + = Tyrannosaurus rex +1F997 CRICKET @ Food symbol 1F9C0 CHEESE WEDGE +@ Portrait and role symbols +1F9D0 FACE WITH MONOCLE +1F9D1 ADULT + * no specified gender + x (man - 1F468) + x (woman - 1F469) +1F9D2 CHILD + * no specified gender + x (boy - 1F466) + x (girl - 1F467) +1F9D3 OLDER ADULT + * no specified gender + x (older man - 1F474) + x (older woman - 1F475) +1F9D4 BEARDED PERSON +1F9D5 PERSON WITH HEADSCARF + = woman's headscarf, hijab +1F9D6 PERSON IN STEAMY ROOM + = sauna, steam room +1F9D7 PERSON CLIMBING +1F9D8 PERSON IN LOTUS POSITION + = yoga, meditation +@ Fantasy beings +1F9D9 MAGE + = wizard, witch, sorcerer, sorceress +1F9DA FAIRY +1F9DB VAMPIRE +1F9DC MERPERSON + = mermaid, merman +1F9DD ELF +1F9DE GENIE +1F9DF ZOMBIE +@ Miscellaneous symbols +1F9E0 BRAIN +1F9E1 ORANGE HEART + x (blue heart - 1F499) + x (green heart - 1F49A) + x (yellow heart - 1F49B) + x (purple heart - 1F49C) +1F9E2 BILLED CAP + = baseball cap +1F9E3 SCARF +1F9E4 GLOVES +1F9E5 COAT +1F9E6 SOCKS @@ 1FF80 Unassigned 1FFFF @ Noncharacters @+ These codes are intended for process-internal uses. @@ -45186,6 +48598,7 @@ FFFF <not a character> @@ 2A700 CJK Unified Ideographs Extension C 2B734 @@ 2B740 CJK Unified Ideographs Extension D 2B81D @@ 2B820 CJK Unified Ideographs Extension E 2CEA1 +@@ 2CEB0 CJK Unified Ideographs Extension F 2EBE0 @@ 2F800 CJK Compatibility Ideographs Supplement 2FA1F @ Duplicate characters from CNS 11643-1992 2F800 CJK COMPATIBILITY IDEOGRAPH-2F800 @@ -46447,10 +49860,10 @@ E007D TAG RIGHT CURLY BRACKET E007E TAG TILDE @ Stateful tag terminator E007F CANCEL TAG - * This character is deprecated, and its use is strongly discouraged. @@ E0100 Variation Selectors Supplement E01EF -@+ These complete the set started at FE00 to FE0F -@ Variation selectors +@+ These complete the set started at FE00 to FE0F. +@ Ideographic-specific variation selectors +@+ For documentation about use of these with ideographs, see UTS #37, Unicode Ideographic Variation Database. E0100 VARIATION SELECTOR-17 * these are abbreviated VS17, and so on E0101 VARIATION SELECTOR-18 diff --git a/gnu/usr.bin/perl/lib/unicore/NormalizationCorrections.txt b/gnu/usr.bin/perl/lib/unicore/NormalizationCorrections.txt index 04fc10d11c3..f7fc35e52c2 100644 --- a/gnu/usr.bin/perl/lib/unicore/NormalizationCorrections.txt +++ b/gnu/usr.bin/perl/lib/unicore/NormalizationCorrections.txt @@ -1,12 +1,14 @@ -# NormalizationCorrections-8.0.0.txt -# Date: 2015-03-07, 01:30:00 GMT [KW, LI] +# NormalizationCorrections-10.0.0.txt +# Date: 2017-04-13, 01:00:00 GMT [KW, LI] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ # # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # The normalization stability policy of the Unicode Consortium # ordinarily precludes any change to the decomposition # for any character, once established in a relevant version @@ -25,7 +27,7 @@ # # Currently this list has exactly six entries in it, one for the # typo found and corrected in Corrigendum #3, and five for -# the typos and misidentifications found and corrected in +# the typos and misidentifications found and corrected in # Corrigendum #4. All efforts # will be made to keep the entries limited to just those fixes. # @@ -35,7 +37,7 @@ # Field 2: Corrected decomposition # Field 3: Version of Unicode for which the correction was # entered into UnicodeData.txt, in n.n.n format. -# Comment: Indicates the Unicode Corrigendum which documents +# Comment: Indicates the Unicode Corrigendum which documents # the correction # # For more information, see UAX #15, Unicode Normalization Forms. diff --git a/gnu/usr.bin/perl/lib/unicore/PropList.txt b/gnu/usr.bin/perl/lib/unicore/PropList.txt index 2eb2926e072..9a2d0e4b1c6 100644 --- a/gnu/usr.bin/perl/lib/unicore/PropList.txt +++ b/gnu/usr.bin/perl/lib/unicore/PropList.txt @@ -1,10 +1,11 @@ -# PropList-8.0.0.txt -# Date: 2015-05-16, 17:50:38 GMT [MD] +# PropList-10.0.0.txt +# Date: 2017-03-10, 08:25:30 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -192,10 +193,17 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 111DE..111DF ; Terminal_Punctuation # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2 11238..1123C ; Terminal_Punctuation # Po [5] KHOJKI DANDA..KHOJKI DOUBLE SECTION MARK 112A9 ; Terminal_Punctuation # Po MULTANI SECTION MARK +1144B..1144D ; Terminal_Punctuation # Po [3] NEWA DANDA..NEWA COMMA +1145B ; Terminal_Punctuation # Po NEWA PLACEHOLDER MARK 115C2..115C5 ; Terminal_Punctuation # Po [4] SIDDHAM DANDA..SIDDHAM SEPARATOR BAR 115C9..115D7 ; Terminal_Punctuation # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; Terminal_Punctuation # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; Terminal_Punctuation # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; Terminal_Punctuation # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; Terminal_Punctuation # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD +11AA1..11AA2 ; Terminal_Punctuation # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 +11C41..11C43 ; Terminal_Punctuation # Po [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR +11C71 ; Terminal_Punctuation # Po MARCHEN MARK SHAD 12470..12474 ; Terminal_Punctuation # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 16A6E..16A6F ; Terminal_Punctuation # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Terminal_Punctuation # Po BASSA VAH FULL STOP @@ -204,7 +212,7 @@ FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA 1BC9F ; Terminal_Punctuation # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; Terminal_Punctuation # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 238 +# Total code points: 252 # ================================================ @@ -429,6 +437,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 081B..0823 ; Other_Alphabetic # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; Other_Alphabetic # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082C ; Other_Alphabetic # Mn [4] SAMARITAN VOWEL SIGN LONG I..SAMARITAN VOWEL SIGN SUKUN +08D4..08DF ; Other_Alphabetic # Mn [12] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH WORD WAQFA 08E3..08E9 ; Other_Alphabetic # Mn [7] ARABIC TURNED DAMMA BELOW..ARABIC CURLY KASRATAN 08F0..0902 ; Other_Alphabetic # Mn [19] ARABIC OPEN FATHATAN..DEVANAGARI SIGN ANUSVARA 0903 ; Other_Alphabetic # Mc DEVANAGARI SIGN VISARGA @@ -465,6 +474,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 0AC9 ; Other_Alphabetic # Mc GUJARATI VOWEL SIGN CANDRA O 0ACB..0ACC ; Other_Alphabetic # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0AE2..0AE3 ; Other_Alphabetic # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFC ; Other_Alphabetic # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH 0B01 ; Other_Alphabetic # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Other_Alphabetic # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3E ; Other_Alphabetic # Mc ORIYA VOWEL SIGN AA @@ -502,7 +512,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 0CCC ; Other_Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Other_Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Other_Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Other_Alphabetic # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Other_Alphabetic # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Other_Alphabetic # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D3E..0D40 ; Other_Alphabetic # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Other_Alphabetic # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -556,6 +566,7 @@ FF41..FF46 ; Hex_Digit # L& [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 17BE..17C5 ; Other_Alphabetic # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU 17C6 ; Other_Alphabetic # Mn KHMER SIGN NIKAHIT 17C7..17C8 ; Other_Alphabetic # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +1885..1886 ; Other_Alphabetic # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Other_Alphabetic # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Other_Alphabetic # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1923..1926 ; Other_Alphabetic # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU @@ -613,6 +624,7 @@ A825..A826 ; Other_Alphabetic # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NA A827 ; Other_Alphabetic # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; Other_Alphabetic # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; Other_Alphabetic # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU +A8C5 ; Other_Alphabetic # Mn SAURASHTRA SIGN CANDRABINDU A926..A92A ; Other_Alphabetic # Mn [5] KAYAH LI VOWEL UE..KAYAH LI VOWEL O A947..A951 ; Other_Alphabetic # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A952 ; Other_Alphabetic # Mc REJANG CONSONANT SIGN H @@ -671,6 +683,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11232..11233 ; Other_Alphabetic # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU 11234 ; Other_Alphabetic # Mn KHOJKI SIGN ANUSVARA 11237 ; Other_Alphabetic # Mn KHOJKI SIGN SHADDA +1123E ; Other_Alphabetic # Mn KHOJKI SIGN SUKUN 112DF ; Other_Alphabetic # Mn KHUDAWADI SIGN ANUSVARA 112E0..112E2 ; Other_Alphabetic # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II 112E3..112E8 ; Other_Alphabetic # Mn [6] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN AU @@ -683,6 +696,11 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1134B..1134C ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN OO..GRANTHA VOWEL SIGN AU 11357 ; Other_Alphabetic # Mc GRANTHA AU LENGTH MARK 11362..11363 ; Other_Alphabetic # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11435..11437 ; Other_Alphabetic # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Other_Alphabetic # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Other_Alphabetic # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11443..11444 ; Other_Alphabetic # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA +11445 ; Other_Alphabetic # Mc NEWA SIGN VISARGA 114B0..114B2 ; Other_Alphabetic # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Other_Alphabetic # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; Other_Alphabetic # Mc TIRHUTA VOWEL SIGN E @@ -712,14 +730,48 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 11722..11725 ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Other_Alphabetic # Mc AHOM VOWEL SIGN E 11727..1172A ; Other_Alphabetic # Mn [4] AHOM VOWEL SIGN AW..AHOM VOWEL SIGN AM +11A01..11A06 ; Other_Alphabetic # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Other_Alphabetic # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Other_Alphabetic # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A35..11A38 ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Other_Alphabetic # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Other_Alphabetic # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A51..11A56 ; Other_Alphabetic # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Other_Alphabetic # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Other_Alphabetic # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Other_Alphabetic # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Other_Alphabetic # Mc SOYOMBO SIGN VISARGA +11C2F ; Other_Alphabetic # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Other_Alphabetic # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Other_Alphabetic # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Other_Alphabetic # Mc BHAIKSUKI SIGN VISARGA +11C92..11CA7 ; Other_Alphabetic # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Other_Alphabetic # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Other_Alphabetic # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Other_Alphabetic # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Other_Alphabetic # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Other_Alphabetic # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Other_Alphabetic # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Other_Alphabetic # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Other_Alphabetic # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; Other_Alphabetic # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; Other_Alphabetic # Mn MASARAM GONDI SIGN CANDRA +11D47 ; Other_Alphabetic # Mn MASARAM GONDI RA-KARA 16B30..16B36 ; Other_Alphabetic # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Other_Alphabetic # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 1BC9E ; Other_Alphabetic # Mn DUPLOYAN DOUBLE MARK +1E000..1E006 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Other_Alphabetic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Other_Alphabetic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Other_Alphabetic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Other_Alphabetic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E947 ; Other_Alphabetic # Mn ADLAM HAMZA 1F130..1F149 ; Other_Alphabetic # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1116 +# Total code points: 1300 # ================================================ @@ -728,16 +780,20 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 3021..3029 ; Ideographic # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE 3038..303A ; Ideographic # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 3400..4DB5 ; Ideographic # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Ideographic # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Ideographic # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA F900..FA6D ; Ideographic # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 +17000..187EC ; Ideographic # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; Ideographic # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6D6 ; Ideographic # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Ideographic # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 81404 +# Total code points: 96174 # ================================================ @@ -793,12 +849,14 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 0A4D ; Diacritic # Mn GURMUKHI SIGN VIRAMA 0ABC ; Diacritic # Mn GUJARATI SIGN NUKTA 0ACD ; Diacritic # Mn GUJARATI SIGN VIRAMA +0AFD..0AFF ; Diacritic # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B3C ; Diacritic # Mn ORIYA SIGN NUKTA 0B4D ; Diacritic # Mn ORIYA SIGN VIRAMA 0BCD ; Diacritic # Mn TAMIL SIGN VIRAMA 0C4D ; Diacritic # Mn TELUGU SIGN VIRAMA 0CBC ; Diacritic # Mn KANNADA SIGN NUKTA 0CCD ; Diacritic # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; Diacritic # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; Diacritic # Mn MALAYALAM SIGN VIRAMA 0DCA ; Diacritic # Mn SINHALA SIGN AL-LAKUNA 0E47..0E4C ; Diacritic # Mn [6] THAI CHARACTER MAITAIKHU..THAI CHARACTER THANTHAKHAT @@ -838,10 +896,11 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 1CE2..1CE8 ; Diacritic # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL 1CED ; Diacritic # Mn VEDIC SIGN TIRYAK 1CF4 ; Diacritic # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Diacritic # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Diacritic # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D2C..1D6A ; Diacritic # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1DC4..1DCF ; Diacritic # Mn [12] COMBINING MACRON-ACUTE..COMBINING ZIGZAG BELOW -1DF5 ; Diacritic # Mn COMBINING UP TACK ABOVE +1DF5..1DF9 ; Diacritic # Mn [5] COMBINING UP TACK ABOVE..COMBINING WIDE INVERTED BRIDGE BELOW 1DFD..1DFF ; Diacritic # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1FBD ; Diacritic # Sk GREEK KORONIS 1FBF..1FC1 ; Diacritic # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI @@ -906,12 +965,20 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1134D ; Diacritic # Mc GRANTHA SIGN VIRAMA 11366..1136C ; Diacritic # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Diacritic # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11442 ; Diacritic # Mn NEWA SIGN VIRAMA +11446 ; Diacritic # Mn NEWA SIGN NUKTA 114C2..114C3 ; Diacritic # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA 115BF..115C0 ; Diacritic # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA 1163F ; Diacritic # Mn MODI SIGN VIRAMA 116B6 ; Diacritic # Mc TAKRI SIGN VIRAMA 116B7 ; Diacritic # Mn TAKRI SIGN NUKTA 1172B ; Diacritic # Mn AHOM SIGN KILLER +11A34 ; Diacritic # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; Diacritic # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; Diacritic # Mn SOYOMBO SUBJOINER +11C3F ; Diacritic # Mn BHAIKSUKI SIGN VIRAMA +11D42 ; Diacritic # Mn MASARAM GONDI SIGN NUKTA +11D44..11D45 ; Diacritic # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA 16AF0..16AF4 ; Diacritic # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16F8F..16F92 ; Diacritic # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; Diacritic # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 @@ -921,8 +988,10 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1D185..1D18B ; Diacritic # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1D1AA..1D1AD ; Diacritic # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO 1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK +1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 773 +# Total code points: 798 # ================================================ @@ -951,9 +1020,12 @@ AAF3..AAF4 ; Extender # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETE FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 1135D ; Extender # Lo GRANTHA SIGN PLUTA 115C6..115C8 ; Extender # Po [3] SIDDHAM REPETITION MARK-1..SIDDHAM REPETITION MARK-3 +11A98 ; Extender # Mn SOYOMBO GEMINATION MARK 16B42..16B43 ; Extender # Lm [2] PAHAWH HMONG SIGN VOS NRUA..PAHAWH HMONG SIGN IB YAM +16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 38 +# Total code points: 44 # ================================================ @@ -1027,7 +1099,7 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] <noncharacter-FFFFE>..<noncha 0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK 0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA 0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA -200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +200C ; Other_Grapheme_Extend # Cf ZERO WIDTH NON-JOINER 302E..302F ; Other_Grapheme_Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 1133E ; Other_Grapheme_Extend # Mc GRANTHA VOWEL SIGN AA @@ -1037,8 +1109,9 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND 115AF ; Other_Grapheme_Extend # Mc SIDDHAM VOWEL SIGN AA 1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM 1D16E..1D172 ; Other_Grapheme_Extend # Mc [5] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-5 +E0020..E007F ; Other_Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 30 +# Total code points: 125 # ================================================ @@ -1064,7 +1137,7 @@ FF9E..FF9F ; Other_Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND # ================================================ 3400..4DB5 ; Unified_Ideograph # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Unified_Ideograph # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Unified_Ideograph # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA FA0E..FA0F ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA0E..CJK COMPATIBILITY IDEOGRAPH-FA0F FA11 ; Unified_Ideograph # Lo CJK COMPATIBILITY IDEOGRAPH-FA11 FA13..FA14 ; Unified_Ideograph # Lo [2] CJK COMPATIBILITY IDEOGRAPH-FA13..CJK COMPATIBILITY IDEOGRAPH-FA14 @@ -1076,8 +1149,9 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C 2A700..2B734 ; Unified_Ideograph # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 -# Total code points: 80388 +# Total code points: 87882 # ================================================ @@ -1106,9 +1180,8 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] <reserved-E01F0>. 2329 ; Deprecated # Ps LEFT-POINTING ANGLE BRACKET 232A ; Deprecated # Pe RIGHT-POINTING ANGLE BRACKET E0001 ; Deprecated # Cf LANGUAGE TAG -E007F ; Deprecated # Cf CANCEL TAG -# Total code points: 16 +# Total code points: 15 # ================================================ @@ -1160,11 +1233,12 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET # ================================================ +1885..1886 ; Other_ID_Start # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 2118 ; Other_ID_Start # Sm SCRIPT CAPITAL P 212E ; Other_ID_Start # So ESTIMATED SYMBOL 309B..309C ; Other_ID_Start # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK -# Total code points: 4 +# Total code points: 6 # ================================================ @@ -1177,72 +1251,76 @@ AABB..AABC ; Logical_Order_Exception # Lo [2] TAI VIET VOWEL AUE..TAI VIET # ================================================ -0021 ; STerm # Po EXCLAMATION MARK -002E ; STerm # Po FULL STOP -003F ; STerm # Po QUESTION MARK -0589 ; STerm # Po ARMENIAN FULL STOP -061F ; STerm # Po ARABIC QUESTION MARK -06D4 ; STerm # Po ARABIC FULL STOP -0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP -07F9 ; STerm # Po NKO EXCLAMATION MARK -0964..0965 ; STerm # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA -104A..104B ; STerm # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION -1362 ; STerm # Po ETHIOPIC FULL STOP -1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR -166E ; STerm # Po CANADIAN SYLLABICS FULL STOP -1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION -1803 ; STerm # Po MONGOLIAN FULL STOP -1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP -1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK -1AA8..1AAB ; STerm # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU -1B5A..1B5B ; STerm # Po [2] BALINESE PANTI..BALINESE PAMADA -1B5E..1B5F ; STerm # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN -1C3B..1C3C ; STerm # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL -1C7E..1C7F ; STerm # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD -203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG -2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK -2E2E ; STerm # Po REVERSED QUESTION MARK -2E3C ; STerm # Po STENOGRAPHIC FULL STOP -3002 ; STerm # Po IDEOGRAPHIC FULL STOP -A4FF ; STerm # Po LISU PUNCTUATION FULL STOP -A60E..A60F ; STerm # Po [2] VAI FULL STOP..VAI QUESTION MARK -A6F3 ; STerm # Po BAMUM FULL STOP -A6F7 ; STerm # Po BAMUM QUESTION MARK -A876..A877 ; STerm # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD -A8CE..A8CF ; STerm # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA -A92F ; STerm # Po KAYAH LI SIGN SHYA -A9C8..A9C9 ; STerm # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI -AA5D..AA5F ; STerm # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA -AAF0..AAF1 ; STerm # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM -ABEB ; STerm # Po MEETEI MAYEK CHEIKHEI -FE52 ; STerm # Po SMALL FULL STOP -FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK -FF01 ; STerm # Po FULLWIDTH EXCLAMATION MARK -FF0E ; STerm # Po FULLWIDTH FULL STOP -FF1F ; STerm # Po FULLWIDTH QUESTION MARK -FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP -10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA -11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA -110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA -11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK -111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA -111CD ; STerm # Po SHARADA SUTRA MARK -111DE..111DF ; STerm # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2 -11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA -1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK -112A9 ; STerm # Po MULTANI SECTION MARK -115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA -115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES -11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA -1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI -16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA -16AF5 ; STerm # Po BASSA VAH FULL STOP -16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB -16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS -1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP -1DA88 ; STerm # Po SIGNWRITING FULL STOP - -# Total code points: 120 +0021 ; Sentence_Terminal # Po EXCLAMATION MARK +002E ; Sentence_Terminal # Po FULL STOP +003F ; Sentence_Terminal # Po QUESTION MARK +0589 ; Sentence_Terminal # Po ARMENIAN FULL STOP +061F ; Sentence_Terminal # Po ARABIC QUESTION MARK +06D4 ; Sentence_Terminal # Po ARABIC FULL STOP +0700..0702 ; Sentence_Terminal # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP +07F9 ; Sentence_Terminal # Po NKO EXCLAMATION MARK +0964..0965 ; Sentence_Terminal # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +104A..104B ; Sentence_Terminal # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION +1362 ; Sentence_Terminal # Po ETHIOPIC FULL STOP +1367..1368 ; Sentence_Terminal # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR +166E ; Sentence_Terminal # Po CANADIAN SYLLABICS FULL STOP +1735..1736 ; Sentence_Terminal # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION +1803 ; Sentence_Terminal # Po MONGOLIAN FULL STOP +1809 ; Sentence_Terminal # Po MONGOLIAN MANCHU FULL STOP +1944..1945 ; Sentence_Terminal # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK +1AA8..1AAB ; Sentence_Terminal # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU +1B5A..1B5B ; Sentence_Terminal # Po [2] BALINESE PANTI..BALINESE PAMADA +1B5E..1B5F ; Sentence_Terminal # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN +1C3B..1C3C ; Sentence_Terminal # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL +1C7E..1C7F ; Sentence_Terminal # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +203C..203D ; Sentence_Terminal # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG +2047..2049 ; Sentence_Terminal # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK +2E2E ; Sentence_Terminal # Po REVERSED QUESTION MARK +2E3C ; Sentence_Terminal # Po STENOGRAPHIC FULL STOP +3002 ; Sentence_Terminal # Po IDEOGRAPHIC FULL STOP +A4FF ; Sentence_Terminal # Po LISU PUNCTUATION FULL STOP +A60E..A60F ; Sentence_Terminal # Po [2] VAI FULL STOP..VAI QUESTION MARK +A6F3 ; Sentence_Terminal # Po BAMUM FULL STOP +A6F7 ; Sentence_Terminal # Po BAMUM QUESTION MARK +A876..A877 ; Sentence_Terminal # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD +A8CE..A8CF ; Sentence_Terminal # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA +A92F ; Sentence_Terminal # Po KAYAH LI SIGN SHYA +A9C8..A9C9 ; Sentence_Terminal # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI +AA5D..AA5F ; Sentence_Terminal # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA +AAF0..AAF1 ; Sentence_Terminal # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM +ABEB ; Sentence_Terminal # Po MEETEI MAYEK CHEIKHEI +FE52 ; Sentence_Terminal # Po SMALL FULL STOP +FE56..FE57 ; Sentence_Terminal # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK +FF01 ; Sentence_Terminal # Po FULLWIDTH EXCLAMATION MARK +FF0E ; Sentence_Terminal # Po FULLWIDTH FULL STOP +FF1F ; Sentence_Terminal # Po FULLWIDTH QUESTION MARK +FF61 ; Sentence_Terminal # Po HALFWIDTH IDEOGRAPHIC FULL STOP +10A56..10A57 ; Sentence_Terminal # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA +11047..11048 ; Sentence_Terminal # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA +110BE..110C1 ; Sentence_Terminal # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +11141..11143 ; Sentence_Terminal # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK +111C5..111C6 ; Sentence_Terminal # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA +111CD ; Sentence_Terminal # Po SHARADA SUTRA MARK +111DE..111DF ; Sentence_Terminal # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2 +11238..11239 ; Sentence_Terminal # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA +1123B..1123C ; Sentence_Terminal # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK +112A9 ; Sentence_Terminal # Po MULTANI SECTION MARK +1144B..1144C ; Sentence_Terminal # Po [2] NEWA DANDA..NEWA DOUBLE DANDA +115C2..115C3 ; Sentence_Terminal # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA +115C9..115D7 ; Sentence_Terminal # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES +11641..11642 ; Sentence_Terminal # Po [2] MODI DANDA..MODI DOUBLE DANDA +1173C..1173E ; Sentence_Terminal # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; Sentence_Terminal # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; Sentence_Terminal # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD +11C41..11C42 ; Sentence_Terminal # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA +16A6E..16A6F ; Sentence_Terminal # Po [2] MRO DANDA..MRO DOUBLE DANDA +16AF5 ; Sentence_Terminal # Po BASSA VAH FULL STOP +16B37..16B38 ; Sentence_Terminal # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB +16B44 ; Sentence_Terminal # Po PAHAWH HMONG SIGN XAUS +1BC9F ; Sentence_Terminal # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1DA88 ; Sentence_Terminal # Po SIGNWRITING FULL STOP + +# Total code points: 128 # ================================================ @@ -1359,9 +1437,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 239B..23B3 ; Pattern_Syntax # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Pattern_Syntax # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Pattern_Syntax # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; Pattern_Syntax # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -23FB..23FF ; Pattern_Syntax # Cn [5] <reserved-23FB>..<reserved-23FF> -2400..2426 ; Pattern_Syntax # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Pattern_Syntax # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2427..243F ; Pattern_Syntax # Cn [25] <reserved-2427>..<reserved-243F> 2440..244A ; Pattern_Syntax # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 244B..245F ; Pattern_Syntax # Cn [21] <reserved-244B>..<reserved-245F> @@ -1449,8 +1525,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2BBA..2BBC ; Pattern_Syntax # Cn [3] <reserved-2BBA>..<reserved-2BBC> 2BBD..2BC8 ; Pattern_Syntax # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED 2BC9 ; Pattern_Syntax # Cn <reserved-2BC9> -2BCA..2BD1 ; Pattern_Syntax # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN -2BD2..2BEB ; Pattern_Syntax # Cn [26] <reserved-2BD2>..<reserved-2BEB> +2BCA..2BD2 ; Pattern_Syntax # So [9] TOP HALF BLACK CIRCLE..GROUP MARK +2BD3..2BEB ; Pattern_Syntax # Cn [25] <reserved-2BD3>..<reserved-2BEB> 2BEC..2BEF ; Pattern_Syntax # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2BF0..2BFF ; Pattern_Syntax # Cn [16] <reserved-2BF0>..<reserved-2BFF> 2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER @@ -1490,7 +1566,8 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2E40 ; Pattern_Syntax # Pd DOUBLE HYPHEN 2E41 ; Pattern_Syntax # Po REVERSED COMMA 2E42 ; Pattern_Syntax # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK -2E43..2E7F ; Pattern_Syntax # Cn [61] <reserved-2E43>..<reserved-2E7F> +2E43..2E49 ; Pattern_Syntax # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA +2E4A..2E7F ; Pattern_Syntax # Cn [54] <reserved-2E4A>..<reserved-2E7F> 3001..3003 ; Pattern_Syntax # Po [3] IDEOGRAPHIC COMMA..DITTO MARK 3008 ; Pattern_Syntax # Ps LEFT ANGLE BRACKET 3009 ; Pattern_Syntax # Pe RIGHT ANGLE BRACKET @@ -1522,4 +1599,20 @@ FE45..FE46 ; Pattern_Syntax # Po [2] SESAME DOT..WHITE SESAME DOT # Total code points: 2760 +# ================================================ + +0600..0605 ; Prepended_Concatenation_Mark # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE +06DD ; Prepended_Concatenation_Mark # Cf ARABIC END OF AYAH +070F ; Prepended_Concatenation_Mark # Cf SYRIAC ABBREVIATION MARK +08E2 ; Prepended_Concatenation_Mark # Cf ARABIC DISPUTED END OF AYAH +110BD ; Prepended_Concatenation_Mark # Cf KAITHI NUMBER SIGN + +# Total code points: 10 + +# ================================================ + +1F1E6..1F1FF ; Regional_Indicator # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z + +# Total code points: 26 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/PropValueAliases.txt b/gnu/usr.bin/perl/lib/unicore/PropValueAliases.txt index 595744668b0..e9b3548cac1 100644 --- a/gnu/usr.bin/perl/lib/unicore/PropValueAliases.txt +++ b/gnu/usr.bin/perl/lib/unicore/PropValueAliases.txt @@ -1,10 +1,11 @@ -# PropertyValueAliases-8.0.0.txt -# Date: 2015-03-11, 22:29:33 GMT [MD] +# PropertyValueAliases-10.0.0.txt +# Date: 2017-05-17, 08:45:34 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # This file contains aliases for property values used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression @@ -78,6 +79,8 @@ age; 6.2 ; V6_2 age; 6.3 ; V6_3 age; 7.0 ; V7_0 age; 8.0 ; V8_0 +age; 9.0 ; V9_0 +age; 10.0 ; V10_0 age; NA ; Unassigned # Alphabetic (Alpha) @@ -138,6 +141,7 @@ bpt; o ; Open # Block (blk) +blk; Adlam ; Adlam blk; Aegean_Numbers ; Aegean_Numbers blk; Ahom ; Ahom blk; Alchemical ; Alchemical_Symbols @@ -162,6 +166,7 @@ blk; Bamum_Sup ; Bamum_Supplement blk; Bassa_Vah ; Bassa_Vah blk; Batak ; Batak blk; Bengali ; Bengali +blk; Bhaiksuki ; Bhaiksuki blk; Block_Elements ; Block_Elements blk; Bopomofo ; Bopomofo blk; Bopomofo_Ext ; Bopomofo_Extended @@ -187,6 +192,7 @@ blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E +blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement blk; CJK_Strokes ; CJK_Strokes blk; CJK_Symbols ; CJK_Symbols_And_Punctuation @@ -202,6 +208,7 @@ blk; Cypriot_Syllabary ; Cypriot_Syllabary blk; Cyrillic ; Cyrillic blk; Cyrillic_Ext_A ; Cyrillic_Extended_A blk; Cyrillic_Ext_B ; Cyrillic_Extended_B +blk; Cyrillic_Ext_C ; Cyrillic_Extended_C blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary blk; Deseret ; Deseret blk; Devanagari ; Devanagari @@ -230,6 +237,7 @@ blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended blk; Georgian ; Georgian blk; Georgian_Sup ; Georgian_Supplement blk; Glagolitic ; Glagolitic +blk; Glagolitic_Sup ; Glagolitic_Supplement blk; Gothic ; Gothic blk; Grantha ; Grantha blk; Greek ; Greek_And_Coptic @@ -246,6 +254,7 @@ blk; High_PU_Surrogates ; High_Private_Use_Surrogates blk; High_Surrogates ; High_Surrogates blk; Hiragana ; Hiragana blk; IDC ; Ideographic_Description_Characters +blk; Ideographic_Symbols ; Ideographic_Symbols_And_Punctuation blk; Imperial_Aramaic ; Imperial_Aramaic blk; Indic_Number_Forms ; Common_Indic_Number_Forms blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi @@ -256,6 +265,7 @@ blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B blk; Javanese ; Javanese blk; Kaithi ; Kaithi +blk; Kana_Ext_A ; Kana_Extended_A blk; Kana_Sup ; Kana_Supplement blk; Kanbun ; Kanbun blk; Kangxi ; Kangxi_Radicals @@ -291,6 +301,8 @@ blk; Mahjong ; Mahjong_Tiles blk; Malayalam ; Malayalam blk; Mandaic ; Mandaic blk; Manichaean ; Manichaean +blk; Marchen ; Marchen +blk; Masaram_Gondi ; Masaram_Gondi blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols blk; Math_Operators ; Mathematical_Operators blk; Meetei_Mayek ; Meetei_Mayek @@ -309,6 +321,7 @@ blk; Modi ; Modi blk; Modifier_Letters ; Spacing_Modifier_Letters blk; Modifier_Tone_Letters ; Modifier_Tone_Letters blk; Mongolian ; Mongolian +blk; Mongolian_Sup ; Mongolian_Supplement blk; Mro ; Mro blk; Multani ; Multani blk; Music ; Musical_Symbols @@ -318,8 +331,10 @@ blk; Myanmar_Ext_B ; Myanmar_Extended_B blk; Nabataean ; Nabataean blk; NB ; No_Block blk; New_Tai_Lue ; New_Tai_Lue +blk; Newa ; Newa blk; NKo ; NKo blk; Number_Forms ; Number_Forms +blk; Nushu ; Nushu blk; OCR ; Optical_Character_Recognition blk; Ogham ; Ogham blk; Ol_Chiki ; Ol_Chiki @@ -332,6 +347,7 @@ blk; Old_South_Arabian ; Old_South_Arabian blk; Old_Turkic ; Old_Turkic blk; Oriya ; Oriya blk; Ornamental_Dingbats ; Ornamental_Dingbats +blk; Osage ; Osage blk; Osmanya ; Osmanya blk; Pahawh_Hmong ; Pahawh_Hmong blk; Palmyrene ; Palmyrene @@ -358,6 +374,7 @@ blk; Sinhala ; Sinhala blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers blk; Small_Forms ; Small_Form_Variants blk; Sora_Sompeng ; Sora_Sompeng +blk; Soyombo ; Soyombo blk; Specials ; Specials blk; Sundanese ; Sundanese blk; Sundanese_Sup ; Sundanese_Supplement @@ -373,6 +390,7 @@ blk; Super_And_Sub ; Superscripts_And_Subscripts blk; Sutton_SignWriting ; Sutton_SignWriting blk; Syloti_Nagri ; Syloti_Nagri blk; Syriac ; Syriac +blk; Syriac_Sup ; Syriac_Supplement blk; Tagalog ; Tagalog blk; Tagbanwa ; Tagbanwa blk; Tags ; Tags @@ -382,6 +400,8 @@ blk; Tai_Viet ; Tai_Viet blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols blk; Takri ; Takri blk; Tamil ; Tamil +blk; Tangut ; Tangut +blk; Tangut_Components ; Tangut_Components blk; Telugu ; Telugu blk; Thaana ; Thaana blk; Thai ; Thai @@ -401,6 +421,7 @@ blk; Warang_Citi ; Warang_Citi blk; Yi_Radicals ; Yi_Radicals blk; Yi_Syllables ; Yi_Syllables blk; Yijing ; Yijing_Hexagram_Symbols +blk; Zanabazar_Square ; Zanabazar_Square # Canonical_Combining_Class (ccc) @@ -650,7 +671,11 @@ Gr_Base; Y ; Yes ; T GCB; CN ; Control GCB; CR ; CR +GCB; EB ; E_Base +GCB; EBG ; E_Base_GAZ +GCB; EM ; E_Modifier GCB; EX ; Extend +GCB; GAZ ; Glue_After_Zwj GCB; L ; L GCB; LF ; LF GCB; LV ; LV @@ -661,6 +686,7 @@ GCB; SM ; SpacingMark GCB; T ; T GCB; V ; V GCB; XX ; Other +GCB; ZWJ ; ZWJ # Grapheme_Extend (Gr_Ext) @@ -723,6 +749,7 @@ Ideo; Y ; Yes ; T # Indic_Positional_Category (InPC) InPC; Bottom ; Bottom +InPC; Bottom_And_Left ; Bottom_And_Left InPC; Bottom_And_Right ; Bottom_And_Right InPC; Left ; Left InPC; Left_And_Right ; Left_And_Right @@ -838,6 +865,9 @@ Join_C; Y ; Yes ; T # Joining_Group (jg) +jg ; African_Feh ; African_Feh +jg ; African_Noon ; African_Noon +jg ; African_Qaf ; African_Qaf jg ; Ain ; Ain jg ; Alaph ; Alaph jg ; Alef ; Alef @@ -864,6 +894,17 @@ jg ; Khaph ; Khaph jg ; Knotted_Heh ; Knotted_Heh jg ; Lam ; Lam jg ; Lamadh ; Lamadh +jg ; Malayalam_Bha ; Malayalam_Bha +jg ; Malayalam_Ja ; Malayalam_Ja +jg ; Malayalam_Lla ; Malayalam_Lla +jg ; Malayalam_Llla ; Malayalam_Llla +jg ; Malayalam_Nga ; Malayalam_Nga +jg ; Malayalam_Nna ; Malayalam_Nna +jg ; Malayalam_Nnna ; Malayalam_Nnna +jg ; Malayalam_Nya ; Malayalam_Nya +jg ; Malayalam_Ra ; Malayalam_Ra +jg ; Malayalam_Ssa ; Malayalam_Ssa +jg ; Malayalam_Tta ; Malayalam_Tta jg ; Manichaean_Aleph ; Manichaean_Aleph jg ; Manichaean_Ayin ; Manichaean_Ayin jg ; Manichaean_Beth ; Manichaean_Beth @@ -948,6 +989,8 @@ lb ; CL ; Close_Punctuation lb ; CM ; Combining_Mark lb ; CP ; Close_Parenthesis lb ; CR ; Carriage_Return +lb ; EB ; E_Base +lb ; EM ; E_Modifier lb ; EX ; Exclamation lb ; GL ; Glue lb ; H2 ; H2 @@ -976,6 +1019,7 @@ lb ; SY ; Break_Symbols lb ; WJ ; Word_Joiner lb ; XX ; Unknown lb ; ZW ; ZWSpace +lb ; ZWJ ; ZWJ # Logical_Order_Exception (LOE) @@ -1096,6 +1140,11 @@ Pat_Syn; Y ; Yes ; T Pat_WS; N ; No ; F ; False Pat_WS; Y ; Yes ; T ; True +# Prepended_Concatenation_Mark (PCM) + +PCM; N ; No ; F ; False +PCM; Y ; Yes ; T ; True + # Quotation_Mark (QMark) QMark; N ; No ; F ; False @@ -1106,13 +1155,14 @@ QMark; Y ; Yes ; T Radical; N ; No ; F ; False Radical; Y ; Yes ; T ; True -# STerm (STerm) +# Regional_Indicator (RI) -STerm; N ; No ; F ; False -STerm; Y ; Yes ; T ; True +RI ; N ; No ; F ; False +RI ; Y ; Yes ; T ; True # Script (sc) +sc ; Adlm ; Adlam sc ; Aghb ; Caucasian_Albanian sc ; Ahom ; Ahom sc ; Arab ; Arabic @@ -1124,6 +1174,7 @@ sc ; Bamu ; Bamum sc ; Bass ; Bassa_Vah sc ; Batk ; Batak sc ; Beng ; Bengali +sc ; Bhks ; Bhaiksuki sc ; Bopo ; Bopomofo sc ; Brah ; Brahmi sc ; Brai ; Braille @@ -1145,6 +1196,7 @@ sc ; Elba ; Elbasan sc ; Ethi ; Ethiopic sc ; Geor ; Georgian sc ; Glag ; Glagolitic +sc ; Gonm ; Masaram_Gondi sc ; Goth ; Gothic sc ; Gran ; Grantha sc ; Grek ; Greek @@ -1182,6 +1234,7 @@ sc ; Lydi ; Lydian sc ; Mahj ; Mahajani sc ; Mand ; Mandaic sc ; Mani ; Manichaean +sc ; Marc ; Marchen sc ; Mend ; Mende_Kikakui sc ; Merc ; Meroitic_Cursive sc ; Mero ; Meroitic_Hieroglyphs @@ -1194,11 +1247,14 @@ sc ; Mult ; Multani sc ; Mymr ; Myanmar sc ; Narb ; Old_North_Arabian sc ; Nbat ; Nabataean +sc ; Newa ; Newa sc ; Nkoo ; Nko +sc ; Nshu ; Nushu sc ; Ogam ; Ogham sc ; Olck ; Ol_Chiki sc ; Orkh ; Old_Turkic sc ; Orya ; Oriya +sc ; Osge ; Osage sc ; Osma ; Osmanya sc ; Palm ; Palmyrene sc ; Pauc ; Pau_Cin_Hau @@ -1221,6 +1277,7 @@ sc ; Sidd ; Siddham sc ; Sind ; Khudawadi sc ; Sinh ; Sinhala sc ; Sora ; Sora_Sompeng +sc ; Soyo ; Soyombo sc ; Sund ; Sundanese sc ; Sylo ; Syloti_Nagri sc ; Syrc ; Syriac @@ -1229,6 +1286,7 @@ sc ; Takr ; Takri sc ; Tale ; Tai_Le sc ; Talu ; New_Tai_Lue sc ; Taml ; Tamil +sc ; Tang ; Tangut sc ; Tavt ; Tai_Viet sc ; Telu ; Telugu sc ; Tfng ; Tifinagh @@ -1243,6 +1301,7 @@ sc ; Wara ; Warang_Citi sc ; Xpeo ; Old_Persian sc ; Xsux ; Cuneiform sc ; Yiii ; Yi +sc ; Zanb ; Zanabazar_Square sc ; Zinh ; Inherited ; Qaai sc ; Zyyy ; Common sc ; Zzzz ; Unknown @@ -1269,6 +1328,11 @@ SB ; ST ; STerm SB ; UP ; Upper SB ; XX ; Other +# Sentence_Terminal (STerm) + +STerm; N ; No ; F ; False +STerm; Y ; Yes ; T ; True + # Simple_Case_Folding (scf) # @missing: 0000..10FFFF; Simple_Case_Folding; <code point> @@ -1322,6 +1386,13 @@ Upper; Y ; Yes ; T VS ; N ; No ; F ; False VS ; Y ; Yes ; T ; True +# Vertical_Orientation (vo) + +vo ; R ; Rotated +vo ; Tr ; Transformed_Rotated +vo ; Tu ; Transformed_Upright +vo ; U ; Upright + # White_Space (WSpace) WSpace; N ; No ; F ; False @@ -1331,9 +1402,13 @@ WSpace; Y ; Yes ; T WB ; CR ; CR WB ; DQ ; Double_Quote +WB ; EB ; E_Base +WB ; EBG ; E_Base_GAZ +WB ; EM ; E_Modifier WB ; EX ; ExtendNumLet WB ; Extend ; Extend WB ; FO ; Format +WB ; GAZ ; Glue_After_Zwj WB ; HL ; Hebrew_Letter WB ; KA ; Katakana WB ; LE ; ALetter @@ -1346,6 +1421,7 @@ WB ; NU ; Numeric WB ; RI ; Regional_Indicator WB ; SQ ; Single_Quote WB ; XX ; Other +WB ; ZWJ ; ZWJ # XID_Continue (XIDC) diff --git a/gnu/usr.bin/perl/lib/unicore/PropertyAliases.txt b/gnu/usr.bin/perl/lib/unicore/PropertyAliases.txt index 18dff7162ad..f2e26ba05e0 100644 --- a/gnu/usr.bin/perl/lib/unicore/PropertyAliases.txt +++ b/gnu/usr.bin/perl/lib/unicore/PropertyAliases.txt @@ -1,10 +1,11 @@ -# PropertyAliases-8.0.0.txt -# Date: 2015-02-14, 10:26:09 GMT [MD] +# PropertyAliases-10.0.0.txt +# Date: 2017-02-14, 04:26:16 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # This file contains aliases for properties used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression @@ -122,6 +123,7 @@ NFKC_QC ; NFKC_Quick_Check NFKD_QC ; NFKD_Quick_Check nt ; Numeric_Type SB ; Sentence_Break +vo ; Vertical_Orientation WB ; Word_Break # ================================================ @@ -171,10 +173,12 @@ OMath ; Other_Math OUpper ; Other_Uppercase Pat_Syn ; Pattern_Syntax Pat_WS ; Pattern_White_Space +PCM ; Prepended_Concatenation_Mark QMark ; Quotation_Mark Radical ; Radical +RI ; Regional_Indicator SD ; Soft_Dotted -STerm ; STerm +STerm ; Sentence_Terminal Term ; Terminal_Punctuation UIdeo ; Unified_Ideograph Upper ; Uppercase @@ -188,6 +192,6 @@ XO_NFKC ; Expands_On_NFKC XO_NFKD ; Expands_On_NFKD # ================================================ -# Total: 117 +# Total: 120 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/README.perl b/gnu/usr.bin/perl/lib/unicore/README.perl index f892334d452..74caf48e026 100644 --- a/gnu/usr.bin/perl/lib/unicore/README.perl +++ b/gnu/usr.bin/perl/lib/unicore/README.perl @@ -61,6 +61,7 @@ mv extracted/DerivedJoiningType.txt extracted/DJoinType.txt mv extracted/DerivedLineBreak.txt extracted/DLineBreak.txt mv extracted/DerivedNumericType.txt extracted/DNumType.txt mv extracted/DerivedNumericValues.txt extracted/DNumValues.txt +mv extracted/DerivedName.txt extracted/DName.txt rmdir extracted 2>/dev/null # Will fail if non-empty, but if it is empty # was an early release that didn't have it. diff --git a/gnu/usr.bin/perl/lib/unicore/ReadMe.txt b/gnu/usr.bin/perl/lib/unicore/ReadMe.txt index fc4a9044b7e..1ba7a9d9da2 100644 --- a/gnu/usr.bin/perl/lib/unicore/ReadMe.txt +++ b/gnu/usr.bin/perl/lib/unicore/ReadMe.txt @@ -1,7 +1,6 @@ -# Date: 2015-06-16, 20:24:00 GMT [KW] -# # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. +# Date: 2017-06-18, 23:32:00 GMT [KW] +# © 2017 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # For documentation, see the following: @@ -9,9 +8,7 @@ # UAX #38, "Unicode Han Database (Unihan)" # UAX #44, "Unicode Character Database." # -# The UAXes can be accessed at http://www.unicode.org/versions/Unicode8.0.0/ +# The UAXes can be accessed at http://www.unicode.org/versions/Unicode10.0.0/ This directory contains the final data files -for the Unicode Character Database, for Version 8.0.0 of the Unicode -Standard. - +for the Unicode Character Database, for Version 10.0.0 of the Unicode Standard. diff --git a/gnu/usr.bin/perl/lib/unicore/ScriptExtensions.txt b/gnu/usr.bin/perl/lib/unicore/ScriptExtensions.txt index b0cda87c9e6..4dd151313a7 100644 --- a/gnu/usr.bin/perl/lib/unicore/ScriptExtensions.txt +++ b/gnu/usr.bin/perl/lib/unicore/ScriptExtensions.txt @@ -1,10 +1,11 @@ -# ScriptExtensions-8.0.0.txt -# Date: 2015-05-14, 22:31:55 GMT [MD] +# ScriptExtensions-10.0.0.txt +# Date: 2017-05-31, 01:07:00 GMT [RP] +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # The Script_Extensions property indicates which characters are commonly used # with more than one script, but with a limited number of scripts. @@ -38,6 +39,14 @@ # ================================================ +# Script_Extensions=Beng + +1CF7 ; Beng # Mc VEDIC SIGN ATIKRAMA + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Deva 1CD1 ; Deva # Mn VEDIC TONE SHARA @@ -76,9 +85,24 @@ # Script_Extensions=Hani +3006 ; Hani # Lo IDEOGRAPHIC CLOSING MARK +303E..303F ; Hani # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE +3190..3191 ; Hani # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK +3192..3195 ; Hani # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK +3196..319F ; Hani # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK +31C0..31E3 ; Hani # So [36] CJK STROKE T..CJK STROKE Q +3220..3229 ; Hani # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN +322A..3247 ; Hani # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO +3280..3289 ; Hani # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN +328A..32B0 ; Hani # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT +32C0..32CB ; Hani # So [12] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DECEMBER +3358..3370 ; Hani # So [25] IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO..IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR TWENTY-FOUR +337B..337F ; Hani # So [5] SQUARE ERA NAME HEISEI..SQUARE CORPORATION +33E0..33FE ; Hani # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE 1D360..1D371 ; Hani # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE +1F250..1F251 ; Hani # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -# Total code points: 18 +# Total code points: 237 # ================================================ @@ -126,6 +150,14 @@ FDFD ; Arab Thaa # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHE # ================================================ +# Script_Extensions=Beng Deva + +A8F1 ; Beng Deva # Mn COMBINING DEVANAGARI SIGN AVAGRAHA + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Bopo Hani 302A..302D ; Bopo Hani # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK @@ -145,19 +177,20 @@ A9CF ; Bugi Java # Lm JAVANESE PANGRANGKEP # Script_Extensions=Cprt Linb 10100..10102 ; Cprt Linb # Po [3] AEGEAN WORD SEPARATOR LINE..AEGEAN CHECK MARK -10107..10133 ; Cprt Linb # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND 10137..1013F ; Cprt Linb # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT -# Total code points: 57 +# Total code points: 12 # ================================================ # Script_Extensions=Cyrl Glag +0484 ; Cyrl Glag # Mn COMBINING CYRILLIC PALATALIZATION 0487 ; Cyrl Glag # Mn COMBINING CYRILLIC POKRYTIE +2E43 ; Cyrl Glag # Po DASH WITH LEFT UPTURN A66F ; Cyrl Glag # Mn COMBINING CYRILLIC VZMET -# Total code points: 2 +# Total code points: 4 # ================================================ @@ -217,14 +250,26 @@ A8F3 ; Deva Taml # Lo DEVANAGARI SIGN CANDRABINDU VIRAMA # ================================================ +# Script_Extensions=Geor Latn + +10FB ; Geor Latn # Po GEORGIAN PARAGRAPH SEPARATOR + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Gran Taml 0BAA ; Gran Taml # Lo TAMIL LETTER PA 0BB5 ; Gran Taml # Lo TAMIL LETTER VA 0BE6..0BEF ; Gran Taml # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE 0BF0..0BF2 ; Gran Taml # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND +11301 ; Gran Taml # Mn GRANTHA SIGN CANDRABINDU +11303 ; Gran Taml # Mc GRANTHA SIGN VISARGA +1133C ; Gran Taml # Mn GRANTHA SIGN NUKTA -# Total code points: 15 + +# Total code points: 18 # ================================================ @@ -271,9 +316,10 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW 060C ; Arab Syrc Thaa # Po ARABIC COMMA 061B ; Arab Syrc Thaa # Po ARABIC SEMICOLON +061C ; Arab Syrc Thaa # Cf ARABIC LETTER MARK 061F ; Arab Syrc Thaa # Po ARABIC QUESTION MARK -# Total code points: 3 +# Total code points: 4 # ================================================ @@ -293,6 +339,14 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW # ================================================ +# Script_Extensions=Cprt Lina Linb + +10107..10133 ; Cprt Lina Linb # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND + +# Total code points: 45 + +# ================================================ + # Script_Extensions=Deva Gran Latn 20F0 ; Deva Gran Latn # Mn COMBINING ASTERISK ABOVE @@ -311,14 +365,10 @@ FF9E..FF9F ; Hira Kana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFW # Script_Extensions=Hani Hira Kana -3006 ; Hani Hira Kana # Lo IDEOGRAPHIC CLOSING MARK 303C ; Hani Hira Kana # Lo MASU MARK 303D ; Hani Hira Kana # Po PART ALTERNATION MARK -3190..3191 ; Hani Hira Kana # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK -3192..3195 ; Hani Hira Kana # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK -3196..319F ; Hani Hira Kana # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK -# Total code points: 19 +# Total code points: 2 # ================================================ @@ -338,14 +388,6 @@ A92E ; Kali Latn Mymr # Po KAYAH LI SIGN CWI # ================================================ -# Script_Extensions=Arab Mand Mani Phlp Syrc - -0640 ; Arab Mand Mani Phlp Syrc # Lm ARABIC TATWEEL - -# Total code points: 1 - -# ================================================ - # Script_Extensions=Bopo Hang Hani Hira Kana 3003 ; Bopo Hang Hani Hira Kana # Po DITTO MARK @@ -355,19 +397,9 @@ A92E ; Kali Latn Mymr # Po KAYAH LI SIGN CWI 301E..301F ; Bopo Hang Hani Hira Kana # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK 3030 ; Bopo Hang Hani Hira Kana # Pd WAVY DASH 3037 ; Bopo Hang Hani Hira Kana # So IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL -303E..303F ; Bopo Hang Hani Hira Kana # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE -31C0..31E3 ; Bopo Hang Hani Hira Kana # So [36] CJK STROKE T..CJK STROKE Q -3220..3229 ; Bopo Hang Hani Hira Kana # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN -322A..3243 ; Bopo Hang Hani Hira Kana # So [26] PARENTHESIZED IDEOGRAPH MOON..PARENTHESIZED IDEOGRAPH REACH -3280..3289 ; Bopo Hang Hani Hira Kana # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN -328A..32B0 ; Bopo Hang Hani Hira Kana # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT -32C0..32CB ; Bopo Hang Hani Hira Kana # So [12] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DECEMBER -3358..3370 ; Bopo Hang Hani Hira Kana # So [25] IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR ZERO..IDEOGRAPHIC TELEGRAPH SYMBOL FOR HOUR TWENTY-FOUR -337B..337F ; Bopo Hang Hani Hira Kana # So [5] SQUARE ERA NAME HEISEI..SQUARE CORPORATION -33E0..33FE ; Bopo Hang Hani Hira Kana # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE FE45..FE46 ; Bopo Hang Hani Hira Kana # Po [2] SESAME DOT..WHITE SESAME DOT -# Total code points: 206 +# Total code points: 10 # ================================================ @@ -379,6 +411,14 @@ FE45..FE46 ; Bopo Hang Hani Hira Kana # Po [2] SESAME DOT..WHITE SESAME DOT # ================================================ +# Script_Extensions=Adlm Arab Mand Mani Phlp Syrc + +0640 ; Adlm Arab Mand Mani Phlp Syrc # Lm ARABIC TATWEEL + +# Total code points: 1 + +# ================================================ + # Script_Extensions=Bopo Hang Hani Hira Kana Yiii 3001..3002 ; Bopo Hang Hani Hira Kana Yiii # Po [2] IDEOGRAPHIC COMMA..IDEOGRAPHIC FULL STOP @@ -412,12 +452,19 @@ FF64..FF65 ; Bopo Hang Hani Hira Kana Yiii # Po [2] HALFWIDTH IDEOGRAPHIC C # Script_Extensions=Deva Gujr Guru Kthi Mahj Modi Sind Takr Tirh -A830..A835 ; Deva Gujr Guru Kthi Mahj Modi Sind Takr Tirh # No [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE SIXTEENTHS A836..A837 ; Deva Gujr Guru Kthi Mahj Modi Sind Takr Tirh # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK A838 ; Deva Gujr Guru Kthi Mahj Modi Sind Takr Tirh # Sc NORTH INDIC RUPEE MARK A839 ; Deva Gujr Guru Kthi Mahj Modi Sind Takr Tirh # So NORTH INDIC QUANTITY MARK -# Total code points: 10 +# Total code points: 4 + +# ================================================ + +# Script_Extensions=Deva Gujr Guru Knda Kthi Mahj Modi Sind Takr Tirh + +A830..A835 ; Deva Gujr Guru Knda Kthi Mahj Modi Sind Takr Tirh # No [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE SIXTEENTHS + +# Total code points: 6 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/Scripts.txt b/gnu/usr.bin/perl/lib/unicore/Scripts.txt index 7e42740407c..72319448e96 100644 --- a/gnu/usr.bin/perl/lib/unicore/Scripts.txt +++ b/gnu/usr.bin/perl/lib/unicore/Scripts.txt @@ -1,10 +1,11 @@ -# Scripts-8.0.0.txt -# Date: 2015-03-11, 22:29:42 GMT [MD] +# Scripts-10.0.0.txt +# Date: 2017-03-11, 06:40:37 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # For more information, see: # UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ # Especially the sections: @@ -92,10 +93,10 @@ 0605 ; Common # Cf ARABIC NUMBER MARK ABOVE 060C ; Common # Po ARABIC COMMA 061B ; Common # Po ARABIC SEMICOLON -061C ; Common # Cf ARABIC LETTER MARK 061F ; Common # Po ARABIC QUESTION MARK 0640 ; Common # Lm ARABIC TATWEEL 06DD ; Common # Cf ARABIC END OF AYAH +08E2 ; Common # Cf ARABIC DISPUTED END OF AYAH 0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT 0FD5..0FD8 ; Common # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS @@ -110,6 +111,7 @@ 1CEE..1CF1 ; Common # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; Common # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; Common # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; Common # Mc VEDIC SIGN ATIKRAMA 2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE 200B ; Common # Cf ZERO WIDTH SPACE 200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -153,7 +155,7 @@ 208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN 208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS -20A0..20BE ; Common # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Common # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT 2102 ; Common # L& DOUBLE-STRUCK CAPITAL C 2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA @@ -223,8 +225,7 @@ 239B..23B3 ; Common # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; Common # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; Common # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; Common # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; Common # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; Common # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -309,7 +310,7 @@ 2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; Common # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; Common # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; Common # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; Common # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; Common # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER 2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET @@ -348,6 +349,7 @@ 2E40 ; Common # Pd DOUBLE HYPHEN 2E41 ; Common # Po REVERSED COMMA 2E42 ; Common # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; Common # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID 3000 ; Common # Zs IDEOGRAPHIC SPACE 3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK @@ -572,19 +574,18 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F100..1F10C ; Common # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F110..1F12E ; Common # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F16B ; Common # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN -1F170..1F19A ; Common # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; Common # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F1FF ; Common # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z 1F201..1F202 ; Common # So [2] SQUARED KATAKANA KOKO..SQUARED KATAKANA SA -1F210..1F23A ; Common # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; Common # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; Common # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; Common # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; Common # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; Common # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; Common # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579 ; Common # So [378] RAT..JOYSTICK -1F57B..1F5A3 ; Common # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; Common # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP +1F400..1F6D4 ; Common # So [725] RAT..PAGODA 1F6E0..1F6EC ; Common # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; Common # So [4] SATELLITE..PASSENGER SHIP +1F6F0..1F6F8 ; Common # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; Common # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; Common # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; Common # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -592,13 +593,17 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR 1F850..1F859 ; Common # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; Common # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; Common # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; Common # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; Common # So [5] CRAB..UNICORN FACE +1F900..1F90B ; Common # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; Common # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; Common # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; Common # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; Common # So [24] CRAB..CRICKET 1F9C0 ; Common # So CHEESE WEDGE +1F9D0..1F9E6 ; Common # So [23] FACE WITH MONOCLE..SOCKS E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 7179 +# Total code points: 7363 # ================================================ @@ -641,7 +646,7 @@ A770 ; Latin # Lm MODIFIER LETTER US A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; Latin # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; Latin # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; Latin # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -654,7 +659,7 @@ FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z -# Total code points: 1349 +# Total code points: 1350 # ================================================ @@ -708,13 +713,13 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA 10175..10178 ; Greek # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189 ; Greek # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B ; Greek # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C ; Greek # So GREEK SINUSOID SIGN +1018C..1018E ; Greek # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 101A0 ; Greek # So GREEK SYMBOL TAU RHO 1D200..1D241 ; Greek # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D242..1D244 ; Greek # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME 1D245 ; Greek # So GREEK MUSICAL LEIMMA -# Total code points: 516 +# Total code points: 518 # ================================================ @@ -724,6 +729,7 @@ AB65 ; Greek # L& GREEK LETTER SMALL CAPITAL OMEGA 0487 ; Cyrillic # Mn COMBINING CYRILLIC POKRYTIE 0488..0489 ; Cyrillic # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN 048A..052F ; Cyrillic # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER +1C80..1C88 ; Cyrillic # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D2B ; Cyrillic # L& CYRILLIC LETTER SMALL CAPITAL EL 1D78 ; Cyrillic # Lm MODIFIER LETTER CYRILLIC EN 2DE0..2DFF ; Cyrillic # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS @@ -740,7 +746,7 @@ A69C..A69D ; Cyrillic # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER A69E..A69F ; Cyrillic # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E FE2E..FE2F ; Cyrillic # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF -# Total code points: 434 +# Total code points: 443 # ================================================ @@ -791,6 +797,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 060D ; Arabic # Po ARABIC DATE SEPARATOR 060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA 0610..061A ; Arabic # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; Arabic # Cf ARABIC LETTER MARK 061E ; Arabic # Po ARABIC TRIPLE DOT PUNCTUATION MARK 0620..063F ; Arabic # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH @@ -815,6 +822,8 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V 0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE 08A0..08B4 ; Arabic # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; Arabic # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; Arabic # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC1 ; Arabic # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW @@ -862,7 +871,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1257 +# Total code points: 1280 # ================================================ @@ -873,8 +882,9 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 0712..072F ; Syriac # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH 0730..074A ; Syriac # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 074D..074F ; Syriac # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE +0860..086A ; Syriac # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -# Total code points: 77 +# Total code points: 88 # ================================================ @@ -944,8 +954,10 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; Bengali # So BENGALI ISSHAR 09FB ; Bengali # Sc BENGALI GANDA MARK +09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; Bengali # Po BENGALI ABBREVIATION SIGN -# Total code points: 93 +# Total code points: 95 # ================================================ @@ -998,8 +1010,9 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 0AF0 ; Gujarati # Po GUJARATI ABBREVIATION SIGN 0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN 0AF9 ; Gujarati # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; Gujarati # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE -# Total code points: 85 +# Total code points: 91 # ================================================ @@ -1086,6 +1099,7 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM # ================================================ +0C80 ; Kannada # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; Kannada # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -1109,15 +1123,16 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -# Total code points: 87 +# Total code points: 88 # ================================================ -0D01 ; Malayalam # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Malayalam # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Malayalam # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; Malayalam # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; Malayalam # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; Malayalam # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; Malayalam # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; Malayalam # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Malayalam # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -1125,15 +1140,18 @@ A8FD ; Devanagari # Lo DEVANAGARI JAIN OM 0D4A..0D4C ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA 0D4E ; Malayalam # Lo MALAYALAM LETTER DOT REPH +0D4F ; Malayalam # So MALAYALAM SIGN PARA +0D54..0D56 ; Malayalam # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E ; Malayalam # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; Malayalam # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; Malayalam # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0D66..0D6F ; Malayalam # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75 ; Malayalam # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; Malayalam # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79 ; Malayalam # So MALAYALAM DATE MARK 0D7A..0D7F ; Malayalam # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K -# Total code points: 100 +# Total code points: 117 # ================================================ @@ -1436,21 +1454,24 @@ AB70..ABBF ; Cherokee # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETT 1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; Mongolian # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; Mongolian # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; Mongolian # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; Mongolian # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 ; Mongolian # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA ; Mongolian # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +11660..1166C ; Mongolian # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT -# Total code points: 153 +# Total code points: 166 # ================================================ 3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE 309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK 309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI -1B001 ; Hiragana # Lo HIRAGANA LETTER ARCHAIC YE +1B001..1B11E ; Hiragana # Lo [286] HIRAGANA LETTER ARCHAIC YE..HENTAIGANA LETTER N-MU-MO-2 1F200 ; Hiragana # So SQUARE HIRAGANA HOKA -# Total code points: 91 +# Total code points: 376 # ================================================ @@ -1469,10 +1490,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK # ================================================ 02EA..02EB ; Bopomofo # Sk [2] MODIFIER LETTER YIN DEPARTING TONE MARK..MODIFIER LETTER YANG DEPARTING TONE MARK -3105..312D ; Bopomofo # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Bopomofo # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 31A0..31BA ; Bopomofo # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY -# Total code points: 70 +# Total code points: 71 # ================================================ @@ -1485,16 +1506,17 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY 303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK 3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Han # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Han # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA F900..FA6D ; Han # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D FA70..FAD9 ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Han # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 81734 +# Total code points: 89228 # ================================================ @@ -1509,8 +1531,9 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE 10300..1031F ; Old_Italic # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; Old_Italic # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY +1032D..1032F ; Old_Italic # Lo [3] OLD ITALIC LETTER YE..OLD ITALIC LETTER SOUTHERN TSE -# Total code points: 36 +# Total code points: 39 # ================================================ @@ -1542,8 +1565,8 @@ A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE 1CED ; Inherited # Mn VEDIC SIGN TIRYAK 1CF4 ; Inherited # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Inherited # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Inherited # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Inherited # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; Inherited # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Inherited # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -1562,7 +1585,7 @@ FE20..FE2D ; Inherited # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CON 1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 563 +# Total code points: 568 # ================================================ @@ -1705,8 +1728,13 @@ E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-2 2C00..2C2E ; Glagolitic # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; Glagolitic # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE +1E000..1E006 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Glagolitic # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Glagolitic # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Glagolitic # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Glagolitic # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA -# Total code points: 94 +# Total code points: 132 # ================================================ @@ -1872,11 +1900,11 @@ A62A..A62B ; Vai # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO A880..A881 ; Saurashtra # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; Saurashtra # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; Saurashtra # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; Saurashtra # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Saurashtra # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8CE..A8CF ; Saurashtra # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A8D0..A8D9 ; Saurashtra # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE -# Total code points: 81 +# Total code points: 82 # ================================================ @@ -2314,8 +2342,9 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 11235 ; Khojki # Mc KHOJKI SIGN VIRAMA 11236..11237 ; Khojki # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 11238..1123D ; Khojki # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN +1123E ; Khojki # Mn KHOJKI SIGN SUKUN -# Total code points: 61 +# Total code points: 62 # ================================================ @@ -2536,4 +2565,129 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 672 +# ================================================ + +1E900..1E943 ; Adlam # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A ; Adlam # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959 ; Adlam # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; Adlam # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK + +# Total code points: 87 + +# ================================================ + +11C00..11C08 ; Bhaiksuki # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; Bhaiksuki # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; Bhaiksuki # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Bhaiksuki # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Bhaiksuki # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Bhaiksuki # Mc BHAIKSUKI SIGN VISARGA +11C3F ; Bhaiksuki # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; Bhaiksuki # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; Bhaiksuki # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; Bhaiksuki # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; Bhaiksuki # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK + +# Total code points: 97 + +# ================================================ + +11C70..11C71 ; Marchen # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; Marchen # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; Marchen # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Marchen # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Marchen # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Marchen # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Marchen # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Marchen # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Marchen # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU + +# Total code points: 68 + +# ================================================ + +11400..11434 ; Newa # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; Newa # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Newa # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Newa # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; Newa # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; Newa # Mc NEWA SIGN VISARGA +11446 ; Newa # Mn NEWA SIGN NUKTA +11447..1144A ; Newa # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; Newa # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; Newa # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; Newa # Po NEWA PLACEHOLDER MARK +1145D ; Newa # Po NEWA INSERTION SIGN + +# Total code points: 92 + +# ================================================ + +104B0..104D3 ; Osage # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; Osage # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA + +# Total code points: 72 + +# ================================================ + +16FE0 ; Tangut # Lm TANGUT ITERATION MARK +17000..187EC ; Tangut # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; Tangut # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 + +# Total code points: 6881 + +# ================================================ + +11D00..11D06 ; Masaram_Gondi # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Masaram_Gondi # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Masaram_Gondi # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; Masaram_Gondi # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Masaram_Gondi # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Masaram_Gondi # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Masaram_Gondi # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; Masaram_Gondi # Lo MASARAM GONDI REPHA +11D47 ; Masaram_Gondi # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; Masaram_Gondi # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE + +# Total code points: 75 + +# ================================================ + +16FE1 ; Nushu # Lm NUSHU ITERATION MARK +1B170..1B2FB ; Nushu # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB + +# Total code points: 397 + +# ================================================ + +11A50 ; Soyombo # Lo SOYOMBO LETTER A +11A51..11A56 ; Soyombo # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Soyombo # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Soyombo # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; Soyombo # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Soyombo # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; Soyombo # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Soyombo # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Soyombo # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C ; Soyombo # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Soyombo # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 + +# Total code points: 80 + +# ================================================ + +11A00 ; Zanabazar_Square # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Zanabazar_Square # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Zanabazar_Square # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; Zanabazar_Square # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; Zanabazar_Square # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Zanabazar_Square # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; Zanabazar_Square # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; Zanabazar_Square # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; Zanabazar_Square # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47 ; Zanabazar_Square # Mn ZANABAZAR SQUARE SUBJOINER + +# Total code points: 72 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/SpecialCasing.txt b/gnu/usr.bin/perl/lib/unicore/SpecialCasing.txt index 8de6462f18c..b9ba0d81c16 100644 --- a/gnu/usr.bin/perl/lib/unicore/SpecialCasing.txt +++ b/gnu/usr.bin/perl/lib/unicore/SpecialCasing.txt @@ -1,10 +1,11 @@ -# SpecialCasing-8.0.0.txt -# Date: 2014-12-16, 23:08:04 GMT [MD] +# SpecialCasing-10.0.0.txt +# Date: 2017-04-14, 05:40:43 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2014 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # # Special Casing # @@ -196,7 +197,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH # ================================================================================ # Conditional Mappings -# The remainder of this file provides conditional casing data used to produce +# The remainder of this file provides conditional casing data used to produce # full case mappings. # ================================================================================ # Language-Insensitive Mappings diff --git a/gnu/usr.bin/perl/lib/unicore/StandardizedVariants.txt b/gnu/usr.bin/perl/lib/unicore/StandardizedVariants.txt index f36a0ed699e..769c998dc5c 100644 --- a/gnu/usr.bin/perl/lib/unicore/StandardizedVariants.txt +++ b/gnu/usr.bin/perl/lib/unicore/StandardizedVariants.txt @@ -1,5 +1,7 @@ -# StandardizedVariants-8.0.0.txt -# Date: 2015-02-10, 15:25:00 GMT [KW, LI] +# StandardizedVariants-10.0.0.txt +# Date: 2017-05-02, 01:00:00 GMT [KW, LI, RP] +# © 2017 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Specification of the variation sequences that are defined in the # Unicode Standard. @@ -7,25 +9,31 @@ # This file is a normative contributory data file in the # Unicode Character Database. # -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# # Standardized variation sequences are defined in this file. +# # Ideographic variation sequences are defined according to the registration # process specified in UTS #37, and are listed in the Ideographic -# Variation Database. Only those two types of variation sequences +# Variation Database. +# +# Emoji variation sequences are defined in the file +# emoji-variation-sequences.txt, documented in UTS #51, Unicode Emoji. +# +# Only those three types of variation sequences # are sanctioned for use by conformant implementations. # In all other cases, use of a variation selector character does # not change the visual appearance of the preceding base character # from what it would have had in the absence of the variation selector. # -# For more information on standardized variation sequences, -# see Section 23.4, Variation Selectors, -# in The Unicode Standard, Version 8.0. +# For more information on standardized variation sequences, +# see Section 23.4, Variation Selectors, +# in The Unicode Standard, Version 10.0. # # For more information on the Ideographic Variation Database, # see http://www.unicode.org/ivd/ # +# For more information on emoji variation sequences, +# see http://www.unicode.org/reports/tr51/ +# # Format: # Field 0: the variation sequence # Field 1: the description of the desired appearance @@ -36,7 +44,9 @@ # Mathematical -2229 FE00; with serifs; # INTERSECTION +0030 FE00; short diagonal stroke form; # DIGIT ZERO +2205 FE00; zero with long diagonal stroke overlay form; # EMPTY SET +2229 FE00; with serifs; # INTERSECTION 222A FE00; with serifs; # UNION 2268 FE00; with vertical stroke; # LESS-THAN BUT NOT EQUAL TO 2269 FE00; with vertical stroke; # GREATER-THAN BUT NOT EQUAL TO @@ -66,6 +76,36 @@ 2ACB FE00; with stroke through bottom members; # SUBSET OF ABOVE NOT EQUAL TO 2ACC FE00; with stroke through bottom members; # SUPERSET OF ABOVE NOT EQUAL TO +# Myanmar + +1000 FE00; dotted form; # MYANMAR LETTER KA +1002 FE00; dotted form; # MYANMAR LETTER GA +1004 FE00; dotted form; # MYANMAR LETTER NGA +1010 FE00; dotted form; # MYANMAR LETTER TA +1011 FE00; dotted form; # MYANMAR LETTER THA +1015 FE00; dotted form; # MYANMAR LETTER PA +1019 FE00; dotted form; # MYANMAR LETTER MA +101A FE00; dotted form; # MYANMAR LETTER YA +101C FE00; dotted form; # MYANMAR LETTER LA +101D FE00; dotted form; # MYANMAR LETTER WA +1022 FE00; dotted form; # MYANMAR LETTER SHAN A +1031 FE00; dotted form; # MYANMAR VOWEL SIGN E +1075 FE00; dotted form; # MYANMAR LETTER SHAN KA +1078 FE00; dotted form; # MYANMAR LETTER SHAN CA +107A FE00; dotted form; # MYANMAR LETTER SHAN NYA +1080 FE00; dotted form; # MYANMAR LETTER SHAN THA +AA60 FE00; dotted form; # MYANMAR LETTER KHAMTI GA +AA61 FE00; dotted form; # MYANMAR LETTER KHAMTI CA +AA62 FE00; dotted form; # MYANMAR LETTER KHAMTI CHA +AA63 FE00; dotted form; # MYANMAR LETTER KHAMTI JA +AA64 FE00; dotted form; # MYANMAR LETTER KHAMTI JHA +AA65 FE00; dotted form; # MYANMAR LETTER KHAMTI NYA +AA66 FE00; dotted form; # MYANMAR LETTER KHAMTI TTA +AA6B FE00; dotted form; # MYANMAR LETTER KHAMTI NA +AA6C FE00; dotted form; # MYANMAR LETTER KHAMTI SA +AA6F FE00; dotted form; # MYANMAR LETTER KHAMTI FA +AA7A FE00; dotted form; # MYANMAR LETTER AITON RA + # Phags-pa A856 FE00; phags-pa letter reversed shaping small a; # PHAGS-PA LETTER SMALL A @@ -86,43 +126,41 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L # Mongolian 1820 180B; second form; isolate medial final # MONGOLIAN LETTER A -1820 180C; third form; medial # MONGOLIAN LETTER A +1820 180C; third form; medial # MONGOLIAN LETTER A 1821 180B; second form; initial final # MONGOLIAN LETTER E 1822 180B; second form; medial # MONGOLIAN LETTER I -1823 180B; second form; medial final # MONGOLIAN LETTER O -1824 180B; second form; medial # MONGOLIAN LETTER U -1825 180B; second form; medial final # MONGOLIAN LETTER OE -1825 180C; third form; medial # MONGOLIAN LETTER OE -1826 180B; second form; isolate medial final # MONGOLIAN LETTER UE -1826 180C; third form; medial # MONGOLIAN LETTER UE +1823 180B; second form; medial final # MONGOLIAN LETTER O +1824 180B; second form; medial # MONGOLIAN LETTER U +1825 180B; second form; medial final # MONGOLIAN LETTER OE +1825 180C; third form; medial # MONGOLIAN LETTER OE +1826 180B; second form; isolate medial final # MONGOLIAN LETTER UE +1826 180C; third form; medial # MONGOLIAN LETTER UE 1828 180B; second form; initial medial # MONGOLIAN LETTER NA 1828 180C; third form; medial # MONGOLIAN LETTER NA -1828 180D; separate form; medial # MONGOLIAN LETTER NA -182A 180B; alternative form; final # MONGOLIAN LETTER BA -182C 180B; second form; initial medial # MONGOLIAN LETTER QA -182C 180B; feminine second form; isolate # MONGOLIAN LETTER QA +1828 180D; fourth form; medial # MONGOLIAN LETTER NA +182A 180B; second form; final # MONGOLIAN LETTER BA +182C 180B; second form; isolate initial medial # MONGOLIAN LETTER QA 182C 180C; third form; medial # MONGOLIAN LETTER QA 182C 180D; fourth form; medial # MONGOLIAN LETTER QA -182D 180B; second form; initial medial # MONGOLIAN LETTER GA -182D 180B; feminine form; final # MONGOLIAN LETTER GA +182D 180B; second form; initial medial final # MONGOLIAN LETTER GA 182D 180C; third form; medial # MONGOLIAN LETTER GA -182D 180D; feminine form; medial # MONGOLIAN LETTER GA +182D 180D; fourth form; medial # MONGOLIAN LETTER GA 1830 180B; second form; final # MONGOLIAN LETTER SA 1830 180C; third form; final # MONGOLIAN LETTER SA -1832 180B; second form; medial # MONGOLIAN LETTER TA +1832 180B; second form; medial # MONGOLIAN LETTER TA 1833 180B; second form; initial medial final # MONGOLIAN LETTER DA 1835 180B; second form; medial # MONGOLIAN LETTER JA -1836 180B; second form; initial medial # # MONGOLIAN LETTER YA +1836 180B; second form; initial medial # MONGOLIAN LETTER YA 1836 180C; third form; medial # MONGOLIAN LETTER YA 1838 180B; second form; final # MONGOLIAN LETTER WA 1844 180B; second form; medial # MONGOLIAN LETTER TODO E -1845 180B; second form; medial # MONGOLIAN LETTER TODO I +1845 180B; second form; medial # MONGOLIAN LETTER TODO I 1846 180B; second form; medial # MONGOLIAN LETTER TODO O 1847 180B; second form; isolate medial final # MONGOLIAN LETTER TODO U 1847 180C; third form; medial # MONGOLIAN LETTER TODO U 1848 180B; second form; medial # MONGOLIAN LETTER TODO OE 1849 180B; second form; isolate medial # MONGOLIAN LETTER TODO UE -184D 180B; feminine form; initial medial # MONGOLIAN LETTER TODO QA +184D 180B; second form; initial medial # MONGOLIAN LETTER TODO QA 184E 180B; second form; medial # MONGOLIAN LETTER TODO GA 185D 180B; second form; medial final # MONGOLIAN LETTER SIBE E 185E 180B; second form; medial final # MONGOLIAN LETTER SIBE I @@ -136,258 +174,18 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L 1873 180B; second form; medial final # MONGOLIAN LETTER MANCHU I 1873 180C; third form; medial final # MONGOLIAN LETTER MANCHU I 1873 180D; fourth form; medial # MONGOLIAN LETTER MANCHU I -1874 180B; second form; medial # MONGOLIAN LETTER MANCHU KA -1874 180B; feminine first final form; final # MONGOLIAN LETTER MANCHU KA -1874 180C; feminine first medial form; medial # MONGOLIAN LETTER MANCHU KA -1874 180C; feminine second final form; final # MONGOLIAN LETTER MANCHU KA -1874 180D; feminine second medial form; medial # MONGOLIAN LETTER MANCHU KA +1874 180B; second form; medial final # MONGOLIAN LETTER MANCHU KA +1874 180C; third form; medial final # MONGOLIAN LETTER MANCHU KA +1874 180D; fourth form; medial # MONGOLIAN LETTER MANCHU KA 1876 180B; second form; initial medial # MONGOLIAN LETTER MANCHU FA 1880 180B; second form; # MONGOLIAN LETTER ALI GALI ANUSVARA ONE 1881 180B; second form; # MONGOLIAN LETTER ALI GALI VISARGA ONE 1887 180B; second form; isolate final # MONGOLIAN LETTER ALI GALI A 1887 180C; third form; final # MONGOLIAN LETTER ALI GALI A 1887 180D; fourth form; final # MONGOLIAN LETTER ALI GALI A -1888 180B; second form; final # MONGOLIAN LETTER ALI GALI I +1888 180B; second form; final # MONGOLIAN LETTER ALI GALI I 188A 180B; second form; initial medial # MONGOLIAN LETTER ALI GALI NGA -# Emoji variation sequences for use as part of keycap symbols - -0023 FE0E; text style; # NUMBER SIGN -0023 FE0F; emoji style; # NUMBER SIGN -0030 FE0E; text style; # DIGIT ZERO -0030 FE0F; emoji style; # DIGIT ZERO -0031 FE0E; text style; # DIGIT ONE -0031 FE0F; emoji style; # DIGIT ONE -0032 FE0E; text style; # DIGIT TWO -0032 FE0F; emoji style; # DIGIT TWO -0033 FE0E; text style; # DIGIT THREE -0033 FE0F; emoji style; # DIGIT THREE -0034 FE0E; text style; # DIGIT FOUR -0034 FE0F; emoji style; # DIGIT FOUR -0035 FE0E; text style; # DIGIT FIVE -0035 FE0F; emoji style; # DIGIT FIVE -0036 FE0E; text style; # DIGIT SIX -0036 FE0F; emoji style; # DIGIT SIX -0037 FE0E; text style; # DIGIT SEVEN -0037 FE0F; emoji style; # DIGIT SEVEN -0038 FE0E; text style; # DIGIT EIGHT -0038 FE0F; emoji style; # DIGIT EIGHT -0039 FE0E; text style; # DIGIT NINE -0039 FE0F; emoji style; # DIGIT NINE - -# Emoji variation sequences - -00A9 FE0E; text style; # COPYRIGHT SIGN -00A9 FE0F; emoji style; # COPYRIGHT SIGN -00AE FE0E; text style; # REGISTERED SIGN -00AE FE0F; emoji style; # REGISTERED SIGN -203C FE0E; text style; # DOUBLE EXCLAMATION MARK -203C FE0F; emoji style; # DOUBLE EXCLAMATION MARK -2049 FE0E; text style; # EXCLAMATION QUESTION MARK -2049 FE0F; emoji style; # EXCLAMATION QUESTION MARK -2122 FE0E; text style; # TRADE MARK SIGN -2122 FE0F; emoji style; # TRADE MARK SIGN -2139 FE0E; text style; # INFORMATION SOURCE -2139 FE0F; emoji style; # INFORMATION SOURCE -2194 FE0E; text style; # LEFT RIGHT ARROW -2194 FE0F; emoji style; # LEFT RIGHT ARROW -2195 FE0E; text style; # UP DOWN ARROW -2195 FE0F; emoji style; # UP DOWN ARROW -2196 FE0E; text style; # NORTH WEST ARROW -2196 FE0F; emoji style; # NORTH WEST ARROW -2197 FE0E; text style; # NORTH EAST ARROW -2197 FE0F; emoji style; # NORTH EAST ARROW -2198 FE0E; text style; # SOUTH EAST ARROW -2198 FE0F; emoji style; # SOUTH EAST ARROW -2199 FE0E; text style; # SOUTH WEST ARROW -2199 FE0F; emoji style; # SOUTH WEST ARROW -21A9 FE0E; text style; # LEFTWARDS ARROW WITH HOOK -21A9 FE0F; emoji style; # LEFTWARDS ARROW WITH HOOK -21AA FE0E; text style; # RIGHTWARDS ARROW WITH HOOK -21AA FE0F; emoji style; # RIGHTWARDS ARROW WITH HOOK -231A FE0E; text style; # WATCH -231A FE0F; emoji style; # WATCH -231B FE0E; text style; # HOURGLASS -231B FE0F; emoji style; # HOURGLASS -24C2 FE0E; text style; # CIRCLED LATIN CAPITAL LETTER M -24C2 FE0F; emoji style; # CIRCLED LATIN CAPITAL LETTER M -25AA FE0E; text style; # BLACK SMALL SQUARE -25AA FE0F; emoji style; # BLACK SMALL SQUARE -25AB FE0E; text style; # WHITE SMALL SQUARE -25AB FE0F; emoji style; # WHITE SMALL SQUARE -25B6 FE0E; text style; # BLACK RIGHT-POINTING TRIANGLE -25B6 FE0F; emoji style; # BLACK RIGHT-POINTING TRIANGLE -25C0 FE0E; text style; # BLACK LEFT-POINTING TRIANGLE -25C0 FE0F; emoji style; # BLACK LEFT-POINTING TRIANGLE -25FB FE0E; text style; # WHITE MEDIUM SQUARE -25FB FE0F; emoji style; # WHITE MEDIUM SQUARE -25FC FE0E; text style; # BLACK MEDIUM SQUARE -25FC FE0F; emoji style; # BLACK MEDIUM SQUARE -25FD FE0E; text style; # WHITE MEDIUM SMALL SQUARE -25FD FE0F; emoji style; # WHITE MEDIUM SMALL SQUARE -25FE FE0E; text style; # BLACK MEDIUM SMALL SQUARE -25FE FE0F; emoji style; # BLACK MEDIUM SMALL SQUARE -2600 FE0E; text style; # BLACK SUN WITH RAYS -2600 FE0F; emoji style; # BLACK SUN WITH RAYS -2601 FE0E; text style; # CLOUD -2601 FE0F; emoji style; # CLOUD -260E FE0E; text style; # BLACK TELEPHONE -260E FE0F; emoji style; # BLACK TELEPHONE -2611 FE0E; text style; # BALLOT BOX WITH CHECK -2611 FE0F; emoji style; # BALLOT BOX WITH CHECK -2614 FE0E; text style; # UMBRELLA WITH RAIN DROPS -2614 FE0F; emoji style; # UMBRELLA WITH RAIN DROPS -2615 FE0E; text style; # HOT BEVERAGE -2615 FE0F; emoji style; # HOT BEVERAGE -261D FE0E; text style; # WHITE UP POINTING INDEX -261D FE0F; emoji style; # WHITE UP POINTING INDEX -263A FE0E; text style; # WHITE SMILING FACE -263A FE0F; emoji style; # WHITE SMILING FACE -2648 FE0E; text style; # ARIES -2648 FE0F; emoji style; # ARIES -2649 FE0E; text style; # TAURUS -2649 FE0F; emoji style; # TAURUS -264A FE0E; text style; # GEMINI -264A FE0F; emoji style; # GEMINI -264B FE0E; text style; # CANCER -264B FE0F; emoji style; # CANCER -264C FE0E; text style; # LEO -264C FE0F; emoji style; # LEO -264D FE0E; text style; # VIRGO -264D FE0F; emoji style; # VIRGO -264E FE0E; text style; # LIBRA -264E FE0F; emoji style; # LIBRA -264F FE0E; text style; # SCORPIUS -264F FE0F; emoji style; # SCORPIUS -2650 FE0E; text style; # SAGITTARIUS -2650 FE0F; emoji style; # SAGITTARIUS -2651 FE0E; text style; # CAPRICORN -2651 FE0F; emoji style; # CAPRICORN -2652 FE0E; text style; # AQUARIUS -2652 FE0F; emoji style; # AQUARIUS -2653 FE0E; text style; # PISCES -2653 FE0F; emoji style; # PISCES -2660 FE0E; text style; # BLACK SPADE SUIT -2660 FE0F; emoji style; # BLACK SPADE SUIT -2663 FE0E; text style; # BLACK CLUB SUIT -2663 FE0F; emoji style; # BLACK CLUB SUIT -2665 FE0E; text style; # BLACK HEART SUIT -2665 FE0F; emoji style; # BLACK HEART SUIT -2666 FE0E; text style; # BLACK DIAMOND SUIT -2666 FE0F; emoji style; # BLACK DIAMOND SUIT -2668 FE0E; text style; # HOT SPRINGS -2668 FE0F; emoji style; # HOT SPRINGS -267B FE0E; text style; # BLACK UNIVERSAL RECYCLING SYMBOL -267B FE0F; emoji style; # BLACK UNIVERSAL RECYCLING SYMBOL -267F FE0E; text style; # WHEELCHAIR SYMBOL -267F FE0F; emoji style; # WHEELCHAIR SYMBOL -2693 FE0E; text style; # ANCHOR -2693 FE0F; emoji style; # ANCHOR -26A0 FE0E; text style; # WARNING SIGN -26A0 FE0F; emoji style; # WARNING SIGN -26A1 FE0E; text style; # HIGH VOLTAGE SIGN -26A1 FE0F; emoji style; # HIGH VOLTAGE SIGN -26AA FE0E; text style; # MEDIUM WHITE CIRCLE -26AA FE0F; emoji style; # MEDIUM WHITE CIRCLE -26AB FE0E; text style; # MEDIUM BLACK CIRCLE -26AB FE0F; emoji style; # MEDIUM BLACK CIRCLE -26BD FE0E; text style; # SOCCER BALL -26BD FE0F; emoji style; # SOCCER BALL -26BE FE0E; text style; # BASEBALL -26BE FE0F; emoji style; # BASEBALL -26C4 FE0E; text style; # SNOWMAN WITHOUT SNOW -26C4 FE0F; emoji style; # SNOWMAN WITHOUT SNOW -26C5 FE0E; text style; # SUN BEHIND CLOUD -26C5 FE0F; emoji style; # SUN BEHIND CLOUD -26D4 FE0E; text style; # NO ENTRY -26D4 FE0F; emoji style; # NO ENTRY -26EA FE0E; text style; # CHURCH -26EA FE0F; emoji style; # CHURCH -26F2 FE0E; text style; # FOUNTAIN -26F2 FE0F; emoji style; # FOUNTAIN -26F3 FE0E; text style; # FLAG IN HOLE -26F3 FE0F; emoji style; # FLAG IN HOLE -26F5 FE0E; text style; # SAILBOAT -26F5 FE0F; emoji style; # SAILBOAT -26FA FE0E; text style; # TENT -26FA FE0F; emoji style; # TENT -26FD FE0E; text style; # FUEL PUMP -26FD FE0F; emoji style; # FUEL PUMP -2702 FE0E; text style; # BLACK SCISSORS -2702 FE0F; emoji style; # BLACK SCISSORS -2708 FE0E; text style; # AIRPLANE -2708 FE0F; emoji style; # AIRPLANE -2709 FE0E; text style; # ENVELOPE -2709 FE0F; emoji style; # ENVELOPE -270C FE0E; text style; # VICTORY HAND -270C FE0F; emoji style; # VICTORY HAND -270F FE0E; text style; # PENCIL -270F FE0F; emoji style; # PENCIL -2712 FE0E; text style; # BLACK NIB -2712 FE0F; emoji style; # BLACK NIB -2714 FE0E; text style; # HEAVY CHECK MARK -2714 FE0F; emoji style; # HEAVY CHECK MARK -2716 FE0E; text style; # HEAVY MULTIPLICATION X -2716 FE0F; emoji style; # HEAVY MULTIPLICATION X -2733 FE0E; text style; # EIGHT SPOKED ASTERISK -2733 FE0F; emoji style; # EIGHT SPOKED ASTERISK -2734 FE0E; text style; # EIGHT POINTED BLACK STAR -2734 FE0F; emoji style; # EIGHT POINTED BLACK STAR -2744 FE0E; text style; # SNOWFLAKE -2744 FE0F; emoji style; # SNOWFLAKE -2747 FE0E; text style; # SPARKLE -2747 FE0F; emoji style; # SPARKLE -2757 FE0E; text style; # HEAVY EXCLAMATION MARK SYMBOL -2757 FE0F; emoji style; # HEAVY EXCLAMATION MARK SYMBOL -2764 FE0E; text style; # HEAVY BLACK HEART -2764 FE0F; emoji style; # HEAVY BLACK HEART -27A1 FE0E; text style; # BLACK RIGHTWARDS ARROW -27A1 FE0F; emoji style; # BLACK RIGHTWARDS ARROW -2934 FE0E; text style; # ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS -2934 FE0F; emoji style; # ARROW POINTING RIGHTWARDS THEN CURVING UPWARDS -2935 FE0E; text style; # ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS -2935 FE0F; emoji style; # ARROW POINTING RIGHTWARDS THEN CURVING DOWNWARDS -2B05 FE0E; text style; # LEFTWARDS BLACK ARROW -2B05 FE0F; emoji style; # LEFTWARDS BLACK ARROW -2B06 FE0E; text style; # UPWARDS BLACK ARROW -2B06 FE0F; emoji style; # UPWARDS BLACK ARROW -2B07 FE0E; text style; # DOWNWARDS BLACK ARROW -2B07 FE0F; emoji style; # DOWNWARDS BLACK ARROW -2B1B FE0E; text style; # BLACK LARGE SQUARE -2B1B FE0F; emoji style; # BLACK LARGE SQUARE -2B1C FE0E; text style; # WHITE LARGE SQUARE -2B1C FE0F; emoji style; # WHITE LARGE SQUARE -2B50 FE0E; text style; # WHITE MEDIUM STAR -2B50 FE0F; emoji style; # WHITE MEDIUM STAR -2B55 FE0E; text style; # HEAVY LARGE CIRCLE -2B55 FE0F; emoji style; # HEAVY LARGE CIRCLE -3030 FE0E; text style; # WAVY DASH -3030 FE0F; emoji style; # WAVY DASH -303D FE0E; text style; # PART ALTERNATION MARK -303D FE0F; emoji style; # PART ALTERNATION MARK -3297 FE0E; text style; # CIRCLED IDEOGRAPH CONGRATULATION -3297 FE0F; emoji style; # CIRCLED IDEOGRAPH CONGRATULATION -3299 FE0E; text style; # CIRCLED IDEOGRAPH SECRET -3299 FE0F; emoji style; # CIRCLED IDEOGRAPH SECRET -1F004 FE0E; text style; # MAHJONG TILE RED DRAGON -1F004 FE0F; emoji style; # MAHJONG TILE RED DRAGON -1F170 FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER A -1F170 FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER A -1F171 FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER B -1F171 FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER B -1F17E FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER O -1F17E FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER O -1F17F FE0E; text style; # NEGATIVE SQUARED LATIN CAPITAL LETTER P -1F17F FE0F; emoji style; # NEGATIVE SQUARED LATIN CAPITAL LETTER P -1F202 FE0E; text style; # SQUARED KATAKANA SA -1F202 FE0F; emoji style; # SQUARED KATAKANA SA -1F21A FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-7121 -1F21A FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-7121 -1F22F FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 -1F22F FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-6307 -1F237 FE0E; text style; # SQUARED CJK UNIFIED IDEOGRAPH-6708 -1F237 FE0F; emoji style; # SQUARED CJK UNIFIED IDEOGRAPH-6708 - # CJK compatibility ideographs # Note: In the entries for CJK compatibility ideographs, field 1 diff --git a/gnu/usr.bin/perl/lib/unicore/UnicodeData.txt b/gnu/usr.bin/perl/lib/unicore/UnicodeData.txt index aa0e914f843..d89c64f526a 100644 --- a/gnu/usr.bin/perl/lib/unicore/UnicodeData.txt +++ b/gnu/usr.bin/perl/lib/unicore/UnicodeData.txt @@ -616,7 +616,7 @@ 0267;LATIN SMALL LETTER HENG WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER HENG HOOK;;;; 0268;LATIN SMALL LETTER I WITH STROKE;Ll;0;L;;;;;N;LATIN SMALL LETTER BARRED I;;0197;;0197 0269;LATIN SMALL LETTER IOTA;Ll;0;L;;;;;N;;;0196;;0196 -026A;LATIN LETTER SMALL CAPITAL I;Ll;0;L;;;;;N;;;;; +026A;LATIN LETTER SMALL CAPITAL I;Ll;0;L;;;;;N;;;A7AE;;A7AE 026B;LATIN SMALL LETTER L WITH MIDDLE TILDE;Ll;0;L;;;;;N;;;2C62;;2C62 026C;LATIN SMALL LETTER L WITH BELT;Ll;0;L;;;;;N;LATIN SMALL LETTER L BELT;;A7AD;;A7AD 026D;LATIN SMALL LETTER L WITH RETROFLEX HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER L RETROFLEX HOOK;;;; @@ -2072,6 +2072,17 @@ 085A;MANDAIC VOCALIZATION MARK;Mn;220;NSM;;;;;N;;;;; 085B;MANDAIC GEMINATION MARK;Mn;220;NSM;;;;;N;;;;; 085E;MANDAIC PUNCTUATION;Po;0;R;;;;;N;;;;; +0860;SYRIAC LETTER MALAYALAM NGA;Lo;0;AL;;;;;N;;;;; +0861;SYRIAC LETTER MALAYALAM JA;Lo;0;AL;;;;;N;;;;; +0862;SYRIAC LETTER MALAYALAM NYA;Lo;0;AL;;;;;N;;;;; +0863;SYRIAC LETTER MALAYALAM TTA;Lo;0;AL;;;;;N;;;;; +0864;SYRIAC LETTER MALAYALAM NNA;Lo;0;AL;;;;;N;;;;; +0865;SYRIAC LETTER MALAYALAM NNNA;Lo;0;AL;;;;;N;;;;; +0866;SYRIAC LETTER MALAYALAM BHA;Lo;0;AL;;;;;N;;;;; +0867;SYRIAC LETTER MALAYALAM RA;Lo;0;AL;;;;;N;;;;; +0868;SYRIAC LETTER MALAYALAM LLA;Lo;0;AL;;;;;N;;;;; +0869;SYRIAC LETTER MALAYALAM LLLA;Lo;0;AL;;;;;N;;;;; +086A;SYRIAC LETTER MALAYALAM SSA;Lo;0;AL;;;;;N;;;;; 08A0;ARABIC LETTER BEH WITH SMALL V BELOW;Lo;0;AL;;;;;N;;;;; 08A1;ARABIC LETTER BEH WITH HAMZA ABOVE;Lo;0;AL;;;;;N;;;;; 08A2;ARABIC LETTER JEEM WITH TWO DOTS ABOVE;Lo;0;AL;;;;;N;;;;; @@ -2093,6 +2104,29 @@ 08B2;ARABIC LETTER ZAIN WITH INVERTED V ABOVE;Lo;0;AL;;;;;N;;;;; 08B3;ARABIC LETTER AIN WITH THREE DOTS BELOW;Lo;0;AL;;;;;N;;;;; 08B4;ARABIC LETTER KAF WITH DOT BELOW;Lo;0;AL;;;;;N;;;;; +08B6;ARABIC LETTER BEH WITH SMALL MEEM ABOVE;Lo;0;AL;;;;;N;;;;; +08B7;ARABIC LETTER PEH WITH SMALL MEEM ABOVE;Lo;0;AL;;;;;N;;;;; +08B8;ARABIC LETTER TEH WITH SMALL TEH ABOVE;Lo;0;AL;;;;;N;;;;; +08B9;ARABIC LETTER REH WITH SMALL NOON ABOVE;Lo;0;AL;;;;;N;;;;; +08BA;ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE;Lo;0;AL;;;;;N;;;;; +08BB;ARABIC LETTER AFRICAN FEH;Lo;0;AL;;;;;N;;;;; +08BC;ARABIC LETTER AFRICAN QAF;Lo;0;AL;;;;;N;;;;; +08BD;ARABIC LETTER AFRICAN NOON;Lo;0;AL;;;;;N;;;;; +08D4;ARABIC SMALL HIGH WORD AR-RUB;Mn;230;NSM;;;;;N;;;;; +08D5;ARABIC SMALL HIGH SAD;Mn;230;NSM;;;;;N;;;;; +08D6;ARABIC SMALL HIGH AIN;Mn;230;NSM;;;;;N;;;;; +08D7;ARABIC SMALL HIGH QAF;Mn;230;NSM;;;;;N;;;;; +08D8;ARABIC SMALL HIGH NOON WITH KASRA;Mn;230;NSM;;;;;N;;;;; +08D9;ARABIC SMALL LOW NOON WITH KASRA;Mn;230;NSM;;;;;N;;;;; +08DA;ARABIC SMALL HIGH WORD ATH-THALATHA;Mn;230;NSM;;;;;N;;;;; +08DB;ARABIC SMALL HIGH WORD AS-SAJDA;Mn;230;NSM;;;;;N;;;;; +08DC;ARABIC SMALL HIGH WORD AN-NISF;Mn;230;NSM;;;;;N;;;;; +08DD;ARABIC SMALL HIGH WORD SAKTA;Mn;230;NSM;;;;;N;;;;; +08DE;ARABIC SMALL HIGH WORD QIF;Mn;230;NSM;;;;;N;;;;; +08DF;ARABIC SMALL HIGH WORD WAQFA;Mn;230;NSM;;;;;N;;;;; +08E0;ARABIC SMALL HIGH FOOTNOTE MARKER;Mn;230;NSM;;;;;N;;;;; +08E1;ARABIC SMALL HIGH SIGN SAFHA;Mn;230;NSM;;;;;N;;;;; +08E2;ARABIC DISPUTED END OF AYAH;Cf;0;AN;;;;;N;;;;; 08E3;ARABIC TURNED DAMMA BELOW;Mn;220;NSM;;;;;N;;;;; 08E4;ARABIC CURLY FATHA;Mn;230;NSM;;;;;N;;;;; 08E5;ARABIC CURLY DAMMA;Mn;230;NSM;;;;;N;;;;; @@ -2343,6 +2377,8 @@ 09F9;BENGALI CURRENCY DENOMINATOR SIXTEEN;No;0;L;;;;16;N;;;;; 09FA;BENGALI ISSHAR;So;0;L;;;;;N;;;;; 09FB;BENGALI GANDA MARK;Sc;0;ET;;;;;N;;;;; +09FC;BENGALI LETTER VEDIC ANUSVARA;Lo;0;L;;;;;N;;;;; +09FD;BENGALI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0A01;GURMUKHI SIGN ADAK BINDI;Mn;0;NSM;;;;;N;;;;; 0A02;GURMUKHI SIGN BINDI;Mn;0;NSM;;;;;N;;;;; 0A03;GURMUKHI SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2507,6 +2543,12 @@ 0AF0;GUJARATI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0AF1;GUJARATI RUPEE SIGN;Sc;0;ET;;;;;N;;;;; 0AF9;GUJARATI LETTER ZHA;Lo;0;L;;;;;N;;;;; +0AFA;GUJARATI SIGN SUKUN;Mn;0;NSM;;;;;N;;;;; +0AFB;GUJARATI SIGN SHADDA;Mn;0;NSM;;;;;N;;;;; +0AFC;GUJARATI SIGN MADDAH;Mn;0;NSM;;;;;N;;;;; +0AFD;GUJARATI SIGN THREE-DOT NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; +0AFE;GUJARATI SIGN CIRCLE NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; +0AFF;GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE;Mn;0;NSM;;;;;N;;;;; 0B01;ORIYA SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 0B02;ORIYA SIGN ANUSVARA;Mc;0;L;;;;;N;;;;; 0B03;ORIYA SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2765,6 +2807,7 @@ 0C7D;TELUGU FRACTION DIGIT TWO FOR EVEN POWERS OF FOUR;No;0;ON;;;;2;N;;;;; 0C7E;TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR;No;0;ON;;;;3;N;;;;; 0C7F;TELUGU SIGN TUUMU;So;0;L;;;;;N;;;;; +0C80;KANNADA SIGN SPACING CANDRABINDU;Lo;0;L;;;;;N;;;;; 0C81;KANNADA SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 0C82;KANNADA SIGN ANUSVARA;Mc;0;L;;;;;N;;;;; 0C83;KANNADA SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2852,6 +2895,7 @@ 0CEF;KANNADA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 0CF1;KANNADA SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;; 0CF2;KANNADA SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;; +0D00;MALAYALAM SIGN COMBINING ANUSVARA ABOVE;Mn;0;NSM;;;;;N;;;;; 0D01;MALAYALAM SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; 0D02;MALAYALAM SIGN ANUSVARA;Mc;0;L;;;;;N;;;;; 0D03;MALAYALAM SIGN VISARGA;Mc;0;L;;;;;N;;;;; @@ -2907,6 +2951,8 @@ 0D38;MALAYALAM LETTER SA;Lo;0;L;;;;;N;;;;; 0D39;MALAYALAM LETTER HA;Lo;0;L;;;;;N;;;;; 0D3A;MALAYALAM LETTER TTTA;Lo;0;L;;;;;N;;;;; +0D3B;MALAYALAM SIGN VERTICAL BAR VIRAMA;Mn;9;NSM;;;;;N;;;;; +0D3C;MALAYALAM SIGN CIRCULAR VIRAMA;Mn;9;NSM;;;;;N;;;;; 0D3D;MALAYALAM SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;; 0D3E;MALAYALAM VOWEL SIGN AA;Mc;0;L;;;;;N;;;;; 0D3F;MALAYALAM VOWEL SIGN I;Mc;0;L;;;;;N;;;;; @@ -2923,7 +2969,18 @@ 0D4C;MALAYALAM VOWEL SIGN AU;Mc;0;L;0D46 0D57;;;;N;;;;; 0D4D;MALAYALAM SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; 0D4E;MALAYALAM LETTER DOT REPH;Lo;0;L;;;;;N;;;;; +0D4F;MALAYALAM SIGN PARA;So;0;L;;;;;N;;;;; +0D54;MALAYALAM LETTER CHILLU M;Lo;0;L;;;;;N;;;;; +0D55;MALAYALAM LETTER CHILLU Y;Lo;0;L;;;;;N;;;;; +0D56;MALAYALAM LETTER CHILLU LLL;Lo;0;L;;;;;N;;;;; 0D57;MALAYALAM AU LENGTH MARK;Mc;0;L;;;;;N;;;;; +0D58;MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH;No;0;L;;;;1/160;N;;;;; +0D59;MALAYALAM FRACTION ONE FORTIETH;No;0;L;;;;1/40;N;;;;; +0D5A;MALAYALAM FRACTION THREE EIGHTIETHS;No;0;L;;;;3/80;N;;;;; +0D5B;MALAYALAM FRACTION ONE TWENTIETH;No;0;L;;;;1/20;N;;;;; +0D5C;MALAYALAM FRACTION ONE TENTH;No;0;L;;;;1/10;N;;;;; +0D5D;MALAYALAM FRACTION THREE TWENTIETHS;No;0;L;;;;3/20;N;;;;; +0D5E;MALAYALAM FRACTION ONE FIFTH;No;0;L;;;;1/5;N;;;;; 0D5F;MALAYALAM LETTER ARCHAIC II;Lo;0;L;;;;;N;;;;; 0D60;MALAYALAM LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; 0D61;MALAYALAM LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;; @@ -2945,6 +3002,9 @@ 0D73;MALAYALAM FRACTION ONE QUARTER;No;0;L;;;;1/4;N;;;;; 0D74;MALAYALAM FRACTION ONE HALF;No;0;L;;;;1/2;N;;;;; 0D75;MALAYALAM FRACTION THREE QUARTERS;No;0;L;;;;3/4;N;;;;; +0D76;MALAYALAM FRACTION ONE SIXTEENTH;No;0;L;;;;1/16;N;;;;; +0D77;MALAYALAM FRACTION ONE EIGHTH;No;0;L;;;;1/8;N;;;;; +0D78;MALAYALAM FRACTION THREE SIXTEENTHS;No;0;L;;;;3/16;N;;;;; 0D79;MALAYALAM DATE MARK;So;0;L;;;;;N;;;;; 0D7A;MALAYALAM LETTER CHILLU NN;Lo;0;L;;;;;N;;;;; 0D7B;MALAYALAM LETTER CHILLU N;Lo;0;L;;;;;N;;;;; @@ -5458,8 +5518,8 @@ 1882;MONGOLIAN LETTER ALI GALI DAMARU;Lo;0;L;;;;;N;;;;; 1883;MONGOLIAN LETTER ALI GALI UBADAMA;Lo;0;L;;;;;N;;;;; 1884;MONGOLIAN LETTER ALI GALI INVERTED UBADAMA;Lo;0;L;;;;;N;;;;; -1885;MONGOLIAN LETTER ALI GALI BALUDA;Lo;0;L;;;;;N;;;;; -1886;MONGOLIAN LETTER ALI GALI THREE BALUDA;Lo;0;L;;;;;N;;;;; +1885;MONGOLIAN LETTER ALI GALI BALUDA;Mn;0;NSM;;;;;N;;;;; +1886;MONGOLIAN LETTER ALI GALI THREE BALUDA;Mn;0;NSM;;;;;N;;;;; 1887;MONGOLIAN LETTER ALI GALI A;Lo;0;L;;;;;N;;;;; 1888;MONGOLIAN LETTER ALI GALI I;Lo;0;L;;;;;N;;;;; 1889;MONGOLIAN LETTER ALI GALI KA;Lo;0;L;;;;;N;;;;; @@ -6319,6 +6379,15 @@ 1C7D;OL CHIKI AHAD;Lm;0;L;;;;;N;;;;; 1C7E;OL CHIKI PUNCTUATION MUCAAD;Po;0;L;;;;;N;;;;; 1C7F;OL CHIKI PUNCTUATION DOUBLE MUCAAD;Po;0;L;;;;;N;;;;; +1C80;CYRILLIC SMALL LETTER ROUNDED VE;Ll;0;L;;;;;N;;;0412;;0412 +1C81;CYRILLIC SMALL LETTER LONG-LEGGED DE;Ll;0;L;;;;;N;;;0414;;0414 +1C82;CYRILLIC SMALL LETTER NARROW O;Ll;0;L;;;;;N;;;041E;;041E +1C83;CYRILLIC SMALL LETTER WIDE ES;Ll;0;L;;;;;N;;;0421;;0421 +1C84;CYRILLIC SMALL LETTER TALL TE;Ll;0;L;;;;;N;;;0422;;0422 +1C85;CYRILLIC SMALL LETTER THREE-LEGGED TE;Ll;0;L;;;;;N;;;0422;;0422 +1C86;CYRILLIC SMALL LETTER TALL HARD SIGN;Ll;0;L;;;;;N;;;042A;;042A +1C87;CYRILLIC SMALL LETTER TALL YAT;Ll;0;L;;;;;N;;;0462;;0462 +1C88;CYRILLIC SMALL LETTER UNBLENDED UK;Ll;0;L;;;;;N;;;A64A;;A64A 1CC0;SUNDANESE PUNCTUATION BINDU SURYA;Po;0;L;;;;;N;;;;; 1CC1;SUNDANESE PUNCTUATION BINDU PANGLONG;Po;0;L;;;;;N;;;;; 1CC2;SUNDANESE PUNCTUATION BINDU PURNAMA;Po;0;L;;;;;N;;;;; @@ -6366,6 +6435,7 @@ 1CF4;VEDIC TONE CANDRA ABOVE;Mn;230;NSM;;;;;N;;;;; 1CF5;VEDIC SIGN JIHVAMULIYA;Lo;0;L;;;;;N;;;;; 1CF6;VEDIC SIGN UPADHMANIYA;Lo;0;L;;;;;N;;;;; +1CF7;VEDIC SIGN ATIKRAMA;Mc;0;L;;;;;N;;;;; 1CF8;VEDIC TONE RING ABOVE;Mn;230;NSM;;;;;N;;;;; 1CF9;VEDIC TONE DOUBLE RING ABOVE;Mn;230;NSM;;;;;N;;;;; 1D00;LATIN LETTER SMALL CAPITAL A;Ll;0;L;;;;;N;;;;; @@ -6614,6 +6684,11 @@ 1DF3;COMBINING LATIN SMALL LETTER O WITH DIAERESIS;Mn;230;NSM;;;;;N;;;;; 1DF4;COMBINING LATIN SMALL LETTER U WITH DIAERESIS;Mn;230;NSM;;;;;N;;;;; 1DF5;COMBINING UP TACK ABOVE;Mn;230;NSM;;;;;N;;;;; +1DF6;COMBINING KAVYKA ABOVE RIGHT;Mn;232;NSM;;;;;N;;;;; +1DF7;COMBINING KAVYKA ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; +1DF8;COMBINING DOT ABOVE LEFT;Mn;228;NSM;;;;;N;;;;; +1DF9;COMBINING WIDE INVERTED BRIDGE BELOW;Mn;220;NSM;;;;;N;;;;; +1DFB;COMBINING DELETION MARK;Mn;230;NSM;;;;;N;;;;; 1DFC;COMBINING DOUBLE INVERTED BREVE BELOW;Mn;233;NSM;;;;;N;;;;; 1DFD;COMBINING ALMOST EQUAL TO BELOW;Mn;220;NSM;;;;;N;;;;; 1DFE;COMBINING LEFT ARROWHEAD ABOVE;Mn;230;NSM;;;;;N;;;;; @@ -7291,6 +7366,7 @@ 20BC;MANAT SIGN;Sc;0;ET;;;;;N;;;;; 20BD;RUBLE SIGN;Sc;0;ET;;;;;N;;;;; 20BE;LARI SIGN;Sc;0;ET;;;;;N;;;;; +20BF;BITCOIN SIGN;Sc;0;ET;;;;;N;;;;; 20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;; 20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;; 20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;; @@ -8083,6 +8159,11 @@ 23F8;DOUBLE VERTICAL BAR;So;0;ON;;;;;N;;;;; 23F9;BLACK SQUARE FOR STOP;So;0;ON;;;;;N;;;;; 23FA;BLACK CIRCLE FOR RECORD;So;0;ON;;;;;N;;;;; +23FB;POWER SYMBOL;So;0;ON;;;;;N;;;;; +23FC;POWER ON-OFF SYMBOL;So;0;ON;;;;;N;;;;; +23FD;POWER ON SYMBOL;So;0;ON;;;;;N;;;;; +23FE;POWER SLEEP SYMBOL;So;0;ON;;;;;N;;;;; +23FF;OBSERVER EYE SYMBOL;So;0;ON;;;;;N;;;;; 2400;SYMBOL FOR NULL;So;0;ON;;;;;N;GRAPHIC FOR NULL;;;; 2401;SYMBOL FOR START OF HEADING;So;0;ON;;;;;N;GRAPHIC FOR START OF HEADING;;;; 2402;SYMBOL FOR START OF TEXT;So;0;ON;;;;;N;GRAPHIC FOR START OF TEXT;;;; @@ -10031,6 +10112,7 @@ 2BCF;ROTATED WHITE FOUR POINTED CUSP;So;0;ON;;;;;N;;;;; 2BD0;SQUARE POSITION INDICATOR;So;0;ON;;;;;N;;;;; 2BD1;UNCERTAINTY SIGN;So;0;ON;;;;;N;;;;; +2BD2;GROUP MARK;So;0;ON;;;;;N;;;;; 2BEC;LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; 2BED;UPWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; 2BEE;RIGHTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS;So;0;ON;;;;;N;;;;; @@ -10561,6 +10643,13 @@ 2E40;DOUBLE HYPHEN;Pd;0;ON;;;;;N;;;;; 2E41;REVERSED COMMA;Po;0;ON;;;;;N;;;;; 2E42;DOUBLE LOW-REVERSED-9 QUOTATION MARK;Ps;0;ON;;;;;N;;;;; +2E43;DASH WITH LEFT UPTURN;Po;0;ON;;;;;N;;;;; +2E44;DOUBLE SUSPENSION MARK;Po;0;ON;;;;;N;;;;; +2E45;INVERTED LOW KAVYKA;Po;0;ON;;;;;N;;;;; +2E46;INVERTED LOW KAVYKA WITH KAVYKA ABOVE;Po;0;ON;;;;;N;;;;; +2E47;LOW KAVYKA;Po;0;ON;;;;;N;;;;; +2E48;LOW KAVYKA WITH DOT;Po;0;ON;;;;;N;;;;; +2E49;DOUBLE STACKED COMMA;Po;0;ON;;;;;N;;;;; 2E80;CJK RADICAL REPEAT;So;0;ON;;;;;N;;;;; 2E81;CJK RADICAL CLIFF;So;0;ON;;;;;N;;;;; 2E82;CJK RADICAL SECOND ONE;So;0;ON;;;;;N;;;;; @@ -11196,6 +11285,7 @@ 312B;BOPOMOFO LETTER NG;Lo;0;L;;;;;N;;;;; 312C;BOPOMOFO LETTER GN;Lo;0;L;;;;;N;;;;; 312D;BOPOMOFO LETTER IH;Lo;0;L;;;;;N;;;;; +312E;BOPOMOFO LETTER O WITH DOT ABOVE;Lo;0;L;;;;;N;;;;; 3131;HANGUL LETTER KIYEOK;Lo;0;L;<compat> 1100;;;;N;HANGUL LETTER GIYEOG;;;; 3132;HANGUL LETTER SSANGKIYEOK;Lo;0;L;<compat> 1101;;;;N;HANGUL LETTER SSANG GIYEOG;;;; 3133;HANGUL LETTER KIYEOK-SIOS;Lo;0;L;<compat> 11AA;;;;N;HANGUL LETTER GIYEOG SIOS;;;; @@ -11962,7 +12052,7 @@ 4DFE;HEXAGRAM FOR AFTER COMPLETION;So;0;ON;;;;;N;;;;; 4DFF;HEXAGRAM FOR BEFORE COMPLETION;So;0;ON;;;;;N;;;;; 4E00;<CJK Ideograph, First>;Lo;0;L;;;;;N;;;;; -9FD5;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; +9FEA;<CJK Ideograph, Last>;Lo;0;L;;;;;N;;;;; A000;YI SYLLABLE IT;Lo;0;L;;;;;N;;;;; A001;YI SYLLABLE IX;Lo;0;L;;;;;N;;;;; A002;YI SYLLABLE I;Lo;0;L;;;;;N;;;;; @@ -13889,6 +13979,7 @@ A7AA;LATIN CAPITAL LETTER H WITH HOOK;Lu;0;L;;;;;N;;;;0266; A7AB;LATIN CAPITAL LETTER REVERSED OPEN E;Lu;0;L;;;;;N;;;;025C; A7AC;LATIN CAPITAL LETTER SCRIPT G;Lu;0;L;;;;;N;;;;0261; A7AD;LATIN CAPITAL LETTER L WITH BELT;Lu;0;L;;;;;N;;;;026C; +A7AE;LATIN CAPITAL LETTER SMALL CAPITAL I;Lu;0;L;;;;;N;;;;026A; A7B0;LATIN CAPITAL LETTER TURNED K;Lu;0;L;;;;;N;;;;029E; A7B1;LATIN CAPITAL LETTER TURNED T;Lu;0;L;;;;;N;;;;0287; A7B2;LATIN CAPITAL LETTER J WITH CROSSED-TAIL;Lu;0;L;;;;;N;;;;029D; @@ -14085,6 +14176,7 @@ A8C1;SAURASHTRA VOWEL SIGN O;Mc;0;L;;;;;N;;;;; A8C2;SAURASHTRA VOWEL SIGN OO;Mc;0;L;;;;;N;;;;; A8C3;SAURASHTRA VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; A8C4;SAURASHTRA SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +A8C5;SAURASHTRA SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; A8CE;SAURASHTRA DANDA;Po;0;L;;;;;N;;;;; A8CF;SAURASHTRA DOUBLE DANDA;Po;0;L;;;;;N;;;;; A8D0;SAURASHTRA DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; @@ -16834,6 +16926,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1018A;GREEK ZERO SIGN;No;0;ON;;;;0;N;;;;; 1018B;GREEK ONE QUARTER SIGN;No;0;ON;;;;1/4;N;;;;; 1018C;GREEK SINUSOID SIGN;So;0;ON;;;;;N;;;;; +1018D;GREEK INDICTION SIGN;So;0;L;;;;;N;;;;; +1018E;NOMISMA SIGN;So;0;L;;;;;N;;;;; 10190;ROMAN SEXTANS SIGN;So;0;ON;;;;;N;;;;; 10191;ROMAN UNCIA SIGN;So;0;ON;;;;;N;;;;; 10192;ROMAN SEMUNCIA SIGN;So;0;ON;;;;;N;;;;; @@ -17035,6 +17129,9 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10321;OLD ITALIC NUMERAL FIVE;No;0;L;;;;5;N;;;;; 10322;OLD ITALIC NUMERAL TEN;No;0;L;;;;10;N;;;;; 10323;OLD ITALIC NUMERAL FIFTY;No;0;L;;;;50;N;;;;; +1032D;OLD ITALIC LETTER YE;Lo;0;L;;;;;N;;;;; +1032E;OLD ITALIC LETTER NORTHERN TSE;Lo;0;L;;;;;N;;;;; +1032F;OLD ITALIC LETTER SOUTHERN TSE;Lo;0;L;;;;;N;;;;; 10330;GOTHIC LETTER AHSA;Lo;0;L;;;;;N;;;;; 10331;GOTHIC LETTER BAIRKAN;Lo;0;L;;;;;N;;;;; 10332;GOTHIC LETTER GIBA;Lo;0;L;;;;;N;;;;; @@ -17354,6 +17451,78 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 104A7;OSMANYA DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 104A8;OSMANYA DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 104A9;OSMANYA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +104B0;OSAGE CAPITAL LETTER A;Lu;0;L;;;;;N;;;;104D8; +104B1;OSAGE CAPITAL LETTER AI;Lu;0;L;;;;;N;;;;104D9; +104B2;OSAGE CAPITAL LETTER AIN;Lu;0;L;;;;;N;;;;104DA; +104B3;OSAGE CAPITAL LETTER AH;Lu;0;L;;;;;N;;;;104DB; +104B4;OSAGE CAPITAL LETTER BRA;Lu;0;L;;;;;N;;;;104DC; +104B5;OSAGE CAPITAL LETTER CHA;Lu;0;L;;;;;N;;;;104DD; +104B6;OSAGE CAPITAL LETTER EHCHA;Lu;0;L;;;;;N;;;;104DE; +104B7;OSAGE CAPITAL LETTER E;Lu;0;L;;;;;N;;;;104DF; +104B8;OSAGE CAPITAL LETTER EIN;Lu;0;L;;;;;N;;;;104E0; +104B9;OSAGE CAPITAL LETTER HA;Lu;0;L;;;;;N;;;;104E1; +104BA;OSAGE CAPITAL LETTER HYA;Lu;0;L;;;;;N;;;;104E2; +104BB;OSAGE CAPITAL LETTER I;Lu;0;L;;;;;N;;;;104E3; +104BC;OSAGE CAPITAL LETTER KA;Lu;0;L;;;;;N;;;;104E4; +104BD;OSAGE CAPITAL LETTER EHKA;Lu;0;L;;;;;N;;;;104E5; +104BE;OSAGE CAPITAL LETTER KYA;Lu;0;L;;;;;N;;;;104E6; +104BF;OSAGE CAPITAL LETTER LA;Lu;0;L;;;;;N;;;;104E7; +104C0;OSAGE CAPITAL LETTER MA;Lu;0;L;;;;;N;;;;104E8; +104C1;OSAGE CAPITAL LETTER NA;Lu;0;L;;;;;N;;;;104E9; +104C2;OSAGE CAPITAL LETTER O;Lu;0;L;;;;;N;;;;104EA; +104C3;OSAGE CAPITAL LETTER OIN;Lu;0;L;;;;;N;;;;104EB; +104C4;OSAGE CAPITAL LETTER PA;Lu;0;L;;;;;N;;;;104EC; +104C5;OSAGE CAPITAL LETTER EHPA;Lu;0;L;;;;;N;;;;104ED; +104C6;OSAGE CAPITAL LETTER SA;Lu;0;L;;;;;N;;;;104EE; +104C7;OSAGE CAPITAL LETTER SHA;Lu;0;L;;;;;N;;;;104EF; +104C8;OSAGE CAPITAL LETTER TA;Lu;0;L;;;;;N;;;;104F0; +104C9;OSAGE CAPITAL LETTER EHTA;Lu;0;L;;;;;N;;;;104F1; +104CA;OSAGE CAPITAL LETTER TSA;Lu;0;L;;;;;N;;;;104F2; +104CB;OSAGE CAPITAL LETTER EHTSA;Lu;0;L;;;;;N;;;;104F3; +104CC;OSAGE CAPITAL LETTER TSHA;Lu;0;L;;;;;N;;;;104F4; +104CD;OSAGE CAPITAL LETTER DHA;Lu;0;L;;;;;N;;;;104F5; +104CE;OSAGE CAPITAL LETTER U;Lu;0;L;;;;;N;;;;104F6; +104CF;OSAGE CAPITAL LETTER WA;Lu;0;L;;;;;N;;;;104F7; +104D0;OSAGE CAPITAL LETTER KHA;Lu;0;L;;;;;N;;;;104F8; +104D1;OSAGE CAPITAL LETTER GHA;Lu;0;L;;;;;N;;;;104F9; +104D2;OSAGE CAPITAL LETTER ZA;Lu;0;L;;;;;N;;;;104FA; +104D3;OSAGE CAPITAL LETTER ZHA;Lu;0;L;;;;;N;;;;104FB; +104D8;OSAGE SMALL LETTER A;Ll;0;L;;;;;N;;;104B0;;104B0 +104D9;OSAGE SMALL LETTER AI;Ll;0;L;;;;;N;;;104B1;;104B1 +104DA;OSAGE SMALL LETTER AIN;Ll;0;L;;;;;N;;;104B2;;104B2 +104DB;OSAGE SMALL LETTER AH;Ll;0;L;;;;;N;;;104B3;;104B3 +104DC;OSAGE SMALL LETTER BRA;Ll;0;L;;;;;N;;;104B4;;104B4 +104DD;OSAGE SMALL LETTER CHA;Ll;0;L;;;;;N;;;104B5;;104B5 +104DE;OSAGE SMALL LETTER EHCHA;Ll;0;L;;;;;N;;;104B6;;104B6 +104DF;OSAGE SMALL LETTER E;Ll;0;L;;;;;N;;;104B7;;104B7 +104E0;OSAGE SMALL LETTER EIN;Ll;0;L;;;;;N;;;104B8;;104B8 +104E1;OSAGE SMALL LETTER HA;Ll;0;L;;;;;N;;;104B9;;104B9 +104E2;OSAGE SMALL LETTER HYA;Ll;0;L;;;;;N;;;104BA;;104BA +104E3;OSAGE SMALL LETTER I;Ll;0;L;;;;;N;;;104BB;;104BB +104E4;OSAGE SMALL LETTER KA;Ll;0;L;;;;;N;;;104BC;;104BC +104E5;OSAGE SMALL LETTER EHKA;Ll;0;L;;;;;N;;;104BD;;104BD +104E6;OSAGE SMALL LETTER KYA;Ll;0;L;;;;;N;;;104BE;;104BE +104E7;OSAGE SMALL LETTER LA;Ll;0;L;;;;;N;;;104BF;;104BF +104E8;OSAGE SMALL LETTER MA;Ll;0;L;;;;;N;;;104C0;;104C0 +104E9;OSAGE SMALL LETTER NA;Ll;0;L;;;;;N;;;104C1;;104C1 +104EA;OSAGE SMALL LETTER O;Ll;0;L;;;;;N;;;104C2;;104C2 +104EB;OSAGE SMALL LETTER OIN;Ll;0;L;;;;;N;;;104C3;;104C3 +104EC;OSAGE SMALL LETTER PA;Ll;0;L;;;;;N;;;104C4;;104C4 +104ED;OSAGE SMALL LETTER EHPA;Ll;0;L;;;;;N;;;104C5;;104C5 +104EE;OSAGE SMALL LETTER SA;Ll;0;L;;;;;N;;;104C6;;104C6 +104EF;OSAGE SMALL LETTER SHA;Ll;0;L;;;;;N;;;104C7;;104C7 +104F0;OSAGE SMALL LETTER TA;Ll;0;L;;;;;N;;;104C8;;104C8 +104F1;OSAGE SMALL LETTER EHTA;Ll;0;L;;;;;N;;;104C9;;104C9 +104F2;OSAGE SMALL LETTER TSA;Ll;0;L;;;;;N;;;104CA;;104CA +104F3;OSAGE SMALL LETTER EHTSA;Ll;0;L;;;;;N;;;104CB;;104CB +104F4;OSAGE SMALL LETTER TSHA;Ll;0;L;;;;;N;;;104CC;;104CC +104F5;OSAGE SMALL LETTER DHA;Ll;0;L;;;;;N;;;104CD;;104CD +104F6;OSAGE SMALL LETTER U;Ll;0;L;;;;;N;;;104CE;;104CE +104F7;OSAGE SMALL LETTER WA;Ll;0;L;;;;;N;;;104CF;;104CF +104F8;OSAGE SMALL LETTER KHA;Ll;0;L;;;;;N;;;104D0;;104D0 +104F9;OSAGE SMALL LETTER GHA;Ll;0;L;;;;;N;;;104D1;;104D1 +104FA;OSAGE SMALL LETTER ZA;Ll;0;L;;;;;N;;;104D2;;104D2 +104FB;OSAGE SMALL LETTER ZHA;Ll;0;L;;;;;N;;;104D3;;104D3 10500;ELBASAN LETTER A;Lo;0;L;;;;;N;;;;; 10501;ELBASAN LETTER BE;Lo;0;L;;;;;N;;;;; 10502;ELBASAN LETTER CE;Lo;0;L;;;;;N;;;;; @@ -19180,6 +19349,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1123B;KHOJKI SECTION MARK;Po;0;L;;;;;N;;;;; 1123C;KHOJKI DOUBLE SECTION MARK;Po;0;L;;;;;N;;;;; 1123D;KHOJKI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; +1123E;KHOJKI SIGN SUKUN;Mn;0;NSM;;;;;N;;;;; 11280;MULTANI LETTER A;Lo;0;L;;;;;N;;;;; 11281;MULTANI LETTER I;Lo;0;L;;;;;N;;;;; 11282;MULTANI LETTER U;Lo;0;L;;;;;N;;;;; @@ -19372,6 +19542,98 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11372;COMBINING GRANTHA LETTER NA;Mn;230;NSM;;;;;N;;;;; 11373;COMBINING GRANTHA LETTER VI;Mn;230;NSM;;;;;N;;;;; 11374;COMBINING GRANTHA LETTER PA;Mn;230;NSM;;;;;N;;;;; +11400;NEWA LETTER A;Lo;0;L;;;;;N;;;;; +11401;NEWA LETTER AA;Lo;0;L;;;;;N;;;;; +11402;NEWA LETTER I;Lo;0;L;;;;;N;;;;; +11403;NEWA LETTER II;Lo;0;L;;;;;N;;;;; +11404;NEWA LETTER U;Lo;0;L;;;;;N;;;;; +11405;NEWA LETTER UU;Lo;0;L;;;;;N;;;;; +11406;NEWA LETTER VOCALIC R;Lo;0;L;;;;;N;;;;; +11407;NEWA LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; +11408;NEWA LETTER VOCALIC L;Lo;0;L;;;;;N;;;;; +11409;NEWA LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;; +1140A;NEWA LETTER E;Lo;0;L;;;;;N;;;;; +1140B;NEWA LETTER AI;Lo;0;L;;;;;N;;;;; +1140C;NEWA LETTER O;Lo;0;L;;;;;N;;;;; +1140D;NEWA LETTER AU;Lo;0;L;;;;;N;;;;; +1140E;NEWA LETTER KA;Lo;0;L;;;;;N;;;;; +1140F;NEWA LETTER KHA;Lo;0;L;;;;;N;;;;; +11410;NEWA LETTER GA;Lo;0;L;;;;;N;;;;; +11411;NEWA LETTER GHA;Lo;0;L;;;;;N;;;;; +11412;NEWA LETTER NGA;Lo;0;L;;;;;N;;;;; +11413;NEWA LETTER NGHA;Lo;0;L;;;;;N;;;;; +11414;NEWA LETTER CA;Lo;0;L;;;;;N;;;;; +11415;NEWA LETTER CHA;Lo;0;L;;;;;N;;;;; +11416;NEWA LETTER JA;Lo;0;L;;;;;N;;;;; +11417;NEWA LETTER JHA;Lo;0;L;;;;;N;;;;; +11418;NEWA LETTER NYA;Lo;0;L;;;;;N;;;;; +11419;NEWA LETTER NYHA;Lo;0;L;;;;;N;;;;; +1141A;NEWA LETTER TTA;Lo;0;L;;;;;N;;;;; +1141B;NEWA LETTER TTHA;Lo;0;L;;;;;N;;;;; +1141C;NEWA LETTER DDA;Lo;0;L;;;;;N;;;;; +1141D;NEWA LETTER DDHA;Lo;0;L;;;;;N;;;;; +1141E;NEWA LETTER NNA;Lo;0;L;;;;;N;;;;; +1141F;NEWA LETTER TA;Lo;0;L;;;;;N;;;;; +11420;NEWA LETTER THA;Lo;0;L;;;;;N;;;;; +11421;NEWA LETTER DA;Lo;0;L;;;;;N;;;;; +11422;NEWA LETTER DHA;Lo;0;L;;;;;N;;;;; +11423;NEWA LETTER NA;Lo;0;L;;;;;N;;;;; +11424;NEWA LETTER NHA;Lo;0;L;;;;;N;;;;; +11425;NEWA LETTER PA;Lo;0;L;;;;;N;;;;; +11426;NEWA LETTER PHA;Lo;0;L;;;;;N;;;;; +11427;NEWA LETTER BA;Lo;0;L;;;;;N;;;;; +11428;NEWA LETTER BHA;Lo;0;L;;;;;N;;;;; +11429;NEWA LETTER MA;Lo;0;L;;;;;N;;;;; +1142A;NEWA LETTER MHA;Lo;0;L;;;;;N;;;;; +1142B;NEWA LETTER YA;Lo;0;L;;;;;N;;;;; +1142C;NEWA LETTER RA;Lo;0;L;;;;;N;;;;; +1142D;NEWA LETTER RHA;Lo;0;L;;;;;N;;;;; +1142E;NEWA LETTER LA;Lo;0;L;;;;;N;;;;; +1142F;NEWA LETTER LHA;Lo;0;L;;;;;N;;;;; +11430;NEWA LETTER WA;Lo;0;L;;;;;N;;;;; +11431;NEWA LETTER SHA;Lo;0;L;;;;;N;;;;; +11432;NEWA LETTER SSA;Lo;0;L;;;;;N;;;;; +11433;NEWA LETTER SA;Lo;0;L;;;;;N;;;;; +11434;NEWA LETTER HA;Lo;0;L;;;;;N;;;;; +11435;NEWA VOWEL SIGN AA;Mc;0;L;;;;;N;;;;; +11436;NEWA VOWEL SIGN I;Mc;0;L;;;;;N;;;;; +11437;NEWA VOWEL SIGN II;Mc;0;L;;;;;N;;;;; +11438;NEWA VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11439;NEWA VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;; +1143A;NEWA VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +1143B;NEWA VOWEL SIGN VOCALIC RR;Mn;0;NSM;;;;;N;;;;; +1143C;NEWA VOWEL SIGN VOCALIC L;Mn;0;NSM;;;;;N;;;;; +1143D;NEWA VOWEL SIGN VOCALIC LL;Mn;0;NSM;;;;;N;;;;; +1143E;NEWA VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +1143F;NEWA VOWEL SIGN AI;Mn;0;NSM;;;;;N;;;;; +11440;NEWA VOWEL SIGN O;Mc;0;L;;;;;N;;;;; +11441;NEWA VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; +11442;NEWA SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +11443;NEWA SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11444;NEWA SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11445;NEWA SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11446;NEWA SIGN NUKTA;Mn;7;NSM;;;;;N;;;;; +11447;NEWA SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;; +11448;NEWA SIGN FINAL ANUSVARA;Lo;0;L;;;;;N;;;;; +11449;NEWA OM;Lo;0;L;;;;;N;;;;; +1144A;NEWA SIDDHI;Lo;0;L;;;;;N;;;;; +1144B;NEWA DANDA;Po;0;L;;;;;N;;;;; +1144C;NEWA DOUBLE DANDA;Po;0;L;;;;;N;;;;; +1144D;NEWA COMMA;Po;0;L;;;;;N;;;;; +1144E;NEWA GAP FILLER;Po;0;L;;;;;N;;;;; +1144F;NEWA ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; +11450;NEWA DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +11451;NEWA DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +11452;NEWA DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +11453;NEWA DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +11454;NEWA DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +11455;NEWA DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +11456;NEWA DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +11457;NEWA DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +11458;NEWA DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +11459;NEWA DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +1145B;NEWA PLACEHOLDER MARK;Po;0;L;;;;;N;;;;; +1145D;NEWA INSERTION SIGN;Po;0;L;;;;;N;;;;; 11480;TIRHUTA ANJI;Lo;0;L;;;;;N;;;;; 11481;TIRHUTA LETTER A;Lo;0;L;;;;;N;;;;; 11482;TIRHUTA LETTER AA;Lo;0;L;;;;;N;;;;; @@ -19625,6 +19887,19 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11657;MODI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 11658;MODI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 11659;MODI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +11660;MONGOLIAN BIRGA WITH ORNAMENT;Po;0;ON;;;;;N;;;;; +11661;MONGOLIAN ROTATED BIRGA;Po;0;ON;;;;;N;;;;; +11662;MONGOLIAN DOUBLE BIRGA WITH ORNAMENT;Po;0;ON;;;;;N;;;;; +11663;MONGOLIAN TRIPLE BIRGA WITH ORNAMENT;Po;0;ON;;;;;N;;;;; +11664;MONGOLIAN BIRGA WITH DOUBLE ORNAMENT;Po;0;ON;;;;;N;;;;; +11665;MONGOLIAN ROTATED BIRGA WITH ORNAMENT;Po;0;ON;;;;;N;;;;; +11666;MONGOLIAN ROTATED BIRGA WITH DOUBLE ORNAMENT;Po;0;ON;;;;;N;;;;; +11667;MONGOLIAN INVERTED BIRGA;Po;0;ON;;;;;N;;;;; +11668;MONGOLIAN INVERTED BIRGA WITH DOUBLE ORNAMENT;Po;0;ON;;;;;N;;;;; +11669;MONGOLIAN SWIRL BIRGA;Po;0;ON;;;;;N;;;;; +1166A;MONGOLIAN SWIRL BIRGA WITH ORNAMENT;Po;0;ON;;;;;N;;;;; +1166B;MONGOLIAN SWIRL BIRGA WITH DOUBLE ORNAMENT;Po;0;ON;;;;;N;;;;; +1166C;MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT;Po;0;ON;;;;;N;;;;; 11680;TAKRI LETTER A;Lo;0;L;;;;;N;;;;; 11681;TAKRI LETTER AA;Lo;0;L;;;;;N;;;;; 11682;TAKRI LETTER I;Lo;0;L;;;;;N;;;;; @@ -19832,6 +20107,158 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 118F1;WARANG CITI NUMBER EIGHTY;No;0;L;;;;80;N;;;;; 118F2;WARANG CITI NUMBER NINETY;No;0;L;;;;90;N;;;;; 118FF;WARANG CITI OM;Lo;0;L;;;;;N;;;;; +11A00;ZANABAZAR SQUARE LETTER A;Lo;0;L;;;;;N;;;;; +11A01;ZANABAZAR SQUARE VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11A02;ZANABAZAR SQUARE VOWEL SIGN UE;Mn;0;NSM;;;;;N;;;;; +11A03;ZANABAZAR SQUARE VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11A04;ZANABAZAR SQUARE VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11A05;ZANABAZAR SQUARE VOWEL SIGN OE;Mn;0;NSM;;;;;N;;;;; +11A06;ZANABAZAR SQUARE VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11A07;ZANABAZAR SQUARE VOWEL SIGN AI;Mc;0;L;;;;;N;;;;; +11A08;ZANABAZAR SQUARE VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; +11A09;ZANABAZAR SQUARE VOWEL SIGN REVERSED I;Mn;0;NSM;;;;;N;;;;; +11A0A;ZANABAZAR SQUARE VOWEL LENGTH MARK;Mn;0;NSM;;;;;N;;;;; +11A0B;ZANABAZAR SQUARE LETTER KA;Lo;0;L;;;;;N;;;;; +11A0C;ZANABAZAR SQUARE LETTER KHA;Lo;0;L;;;;;N;;;;; +11A0D;ZANABAZAR SQUARE LETTER GA;Lo;0;L;;;;;N;;;;; +11A0E;ZANABAZAR SQUARE LETTER GHA;Lo;0;L;;;;;N;;;;; +11A0F;ZANABAZAR SQUARE LETTER NGA;Lo;0;L;;;;;N;;;;; +11A10;ZANABAZAR SQUARE LETTER CA;Lo;0;L;;;;;N;;;;; +11A11;ZANABAZAR SQUARE LETTER CHA;Lo;0;L;;;;;N;;;;; +11A12;ZANABAZAR SQUARE LETTER JA;Lo;0;L;;;;;N;;;;; +11A13;ZANABAZAR SQUARE LETTER NYA;Lo;0;L;;;;;N;;;;; +11A14;ZANABAZAR SQUARE LETTER TTA;Lo;0;L;;;;;N;;;;; +11A15;ZANABAZAR SQUARE LETTER TTHA;Lo;0;L;;;;;N;;;;; +11A16;ZANABAZAR SQUARE LETTER DDA;Lo;0;L;;;;;N;;;;; +11A17;ZANABAZAR SQUARE LETTER DDHA;Lo;0;L;;;;;N;;;;; +11A18;ZANABAZAR SQUARE LETTER NNA;Lo;0;L;;;;;N;;;;; +11A19;ZANABAZAR SQUARE LETTER TA;Lo;0;L;;;;;N;;;;; +11A1A;ZANABAZAR SQUARE LETTER THA;Lo;0;L;;;;;N;;;;; +11A1B;ZANABAZAR SQUARE LETTER DA;Lo;0;L;;;;;N;;;;; +11A1C;ZANABAZAR SQUARE LETTER DHA;Lo;0;L;;;;;N;;;;; +11A1D;ZANABAZAR SQUARE LETTER NA;Lo;0;L;;;;;N;;;;; +11A1E;ZANABAZAR SQUARE LETTER PA;Lo;0;L;;;;;N;;;;; +11A1F;ZANABAZAR SQUARE LETTER PHA;Lo;0;L;;;;;N;;;;; +11A20;ZANABAZAR SQUARE LETTER BA;Lo;0;L;;;;;N;;;;; +11A21;ZANABAZAR SQUARE LETTER BHA;Lo;0;L;;;;;N;;;;; +11A22;ZANABAZAR SQUARE LETTER MA;Lo;0;L;;;;;N;;;;; +11A23;ZANABAZAR SQUARE LETTER TSA;Lo;0;L;;;;;N;;;;; +11A24;ZANABAZAR SQUARE LETTER TSHA;Lo;0;L;;;;;N;;;;; +11A25;ZANABAZAR SQUARE LETTER DZA;Lo;0;L;;;;;N;;;;; +11A26;ZANABAZAR SQUARE LETTER DZHA;Lo;0;L;;;;;N;;;;; +11A27;ZANABAZAR SQUARE LETTER ZHA;Lo;0;L;;;;;N;;;;; +11A28;ZANABAZAR SQUARE LETTER ZA;Lo;0;L;;;;;N;;;;; +11A29;ZANABAZAR SQUARE LETTER -A;Lo;0;L;;;;;N;;;;; +11A2A;ZANABAZAR SQUARE LETTER YA;Lo;0;L;;;;;N;;;;; +11A2B;ZANABAZAR SQUARE LETTER RA;Lo;0;L;;;;;N;;;;; +11A2C;ZANABAZAR SQUARE LETTER LA;Lo;0;L;;;;;N;;;;; +11A2D;ZANABAZAR SQUARE LETTER VA;Lo;0;L;;;;;N;;;;; +11A2E;ZANABAZAR SQUARE LETTER SHA;Lo;0;L;;;;;N;;;;; +11A2F;ZANABAZAR SQUARE LETTER SSA;Lo;0;L;;;;;N;;;;; +11A30;ZANABAZAR SQUARE LETTER SA;Lo;0;L;;;;;N;;;;; +11A31;ZANABAZAR SQUARE LETTER HA;Lo;0;L;;;;;N;;;;; +11A32;ZANABAZAR SQUARE LETTER KSSA;Lo;0;L;;;;;N;;;;; +11A33;ZANABAZAR SQUARE FINAL CONSONANT MARK;Mn;0;NSM;;;;;N;;;;; +11A34;ZANABAZAR SQUARE SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; +11A35;ZANABAZAR SQUARE SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11A36;ZANABAZAR SQUARE SIGN CANDRABINDU WITH ORNAMENT;Mn;0;NSM;;;;;N;;;;; +11A37;ZANABAZAR SQUARE SIGN CANDRA WITH ORNAMENT;Mn;0;NSM;;;;;N;;;;; +11A38;ZANABAZAR SQUARE SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11A39;ZANABAZAR SQUARE SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11A3A;ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA;Lo;0;L;;;;;N;;;;; +11A3B;ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA;Mn;0;NSM;;;;;N;;;;; +11A3C;ZANABAZAR SQUARE CLUSTER-FINAL LETTER RA;Mn;0;NSM;;;;;N;;;;; +11A3D;ZANABAZAR SQUARE CLUSTER-FINAL LETTER LA;Mn;0;NSM;;;;;N;;;;; +11A3E;ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA;Mn;0;NSM;;;;;N;;;;; +11A3F;ZANABAZAR SQUARE INITIAL HEAD MARK;Po;0;L;;;;;N;;;;; +11A40;ZANABAZAR SQUARE CLOSING HEAD MARK;Po;0;L;;;;;N;;;;; +11A41;ZANABAZAR SQUARE MARK TSHEG;Po;0;L;;;;;N;;;;; +11A42;ZANABAZAR SQUARE MARK SHAD;Po;0;L;;;;;N;;;;; +11A43;ZANABAZAR SQUARE MARK DOUBLE SHAD;Po;0;L;;;;;N;;;;; +11A44;ZANABAZAR SQUARE MARK LONG TSHEG;Po;0;L;;;;;N;;;;; +11A45;ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK;Po;0;L;;;;;N;;;;; +11A46;ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK;Po;0;L;;;;;N;;;;; +11A47;ZANABAZAR SQUARE SUBJOINER;Mn;9;NSM;;;;;N;;;;; +11A50;SOYOMBO LETTER A;Lo;0;L;;;;;N;;;;; +11A51;SOYOMBO VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11A52;SOYOMBO VOWEL SIGN UE;Mn;0;NSM;;;;;N;;;;; +11A53;SOYOMBO VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11A54;SOYOMBO VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11A55;SOYOMBO VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11A56;SOYOMBO VOWEL SIGN OE;Mn;0;NSM;;;;;N;;;;; +11A57;SOYOMBO VOWEL SIGN AI;Mc;0;L;;;;;N;;;;; +11A58;SOYOMBO VOWEL SIGN AU;Mc;0;L;;;;;N;;;;; +11A59;SOYOMBO VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +11A5A;SOYOMBO VOWEL SIGN VOCALIC L;Mn;0;NSM;;;;;N;;;;; +11A5B;SOYOMBO VOWEL LENGTH MARK;Mn;0;NSM;;;;;N;;;;; +11A5C;SOYOMBO LETTER KA;Lo;0;L;;;;;N;;;;; +11A5D;SOYOMBO LETTER KHA;Lo;0;L;;;;;N;;;;; +11A5E;SOYOMBO LETTER GA;Lo;0;L;;;;;N;;;;; +11A5F;SOYOMBO LETTER GHA;Lo;0;L;;;;;N;;;;; +11A60;SOYOMBO LETTER NGA;Lo;0;L;;;;;N;;;;; +11A61;SOYOMBO LETTER CA;Lo;0;L;;;;;N;;;;; +11A62;SOYOMBO LETTER CHA;Lo;0;L;;;;;N;;;;; +11A63;SOYOMBO LETTER JA;Lo;0;L;;;;;N;;;;; +11A64;SOYOMBO LETTER JHA;Lo;0;L;;;;;N;;;;; +11A65;SOYOMBO LETTER NYA;Lo;0;L;;;;;N;;;;; +11A66;SOYOMBO LETTER TTA;Lo;0;L;;;;;N;;;;; +11A67;SOYOMBO LETTER TTHA;Lo;0;L;;;;;N;;;;; +11A68;SOYOMBO LETTER DDA;Lo;0;L;;;;;N;;;;; +11A69;SOYOMBO LETTER DDHA;Lo;0;L;;;;;N;;;;; +11A6A;SOYOMBO LETTER NNA;Lo;0;L;;;;;N;;;;; +11A6B;SOYOMBO LETTER TA;Lo;0;L;;;;;N;;;;; +11A6C;SOYOMBO LETTER THA;Lo;0;L;;;;;N;;;;; +11A6D;SOYOMBO LETTER DA;Lo;0;L;;;;;N;;;;; +11A6E;SOYOMBO LETTER DHA;Lo;0;L;;;;;N;;;;; +11A6F;SOYOMBO LETTER NA;Lo;0;L;;;;;N;;;;; +11A70;SOYOMBO LETTER PA;Lo;0;L;;;;;N;;;;; +11A71;SOYOMBO LETTER PHA;Lo;0;L;;;;;N;;;;; +11A72;SOYOMBO LETTER BA;Lo;0;L;;;;;N;;;;; +11A73;SOYOMBO LETTER BHA;Lo;0;L;;;;;N;;;;; +11A74;SOYOMBO LETTER MA;Lo;0;L;;;;;N;;;;; +11A75;SOYOMBO LETTER TSA;Lo;0;L;;;;;N;;;;; +11A76;SOYOMBO LETTER TSHA;Lo;0;L;;;;;N;;;;; +11A77;SOYOMBO LETTER DZA;Lo;0;L;;;;;N;;;;; +11A78;SOYOMBO LETTER ZHA;Lo;0;L;;;;;N;;;;; +11A79;SOYOMBO LETTER ZA;Lo;0;L;;;;;N;;;;; +11A7A;SOYOMBO LETTER -A;Lo;0;L;;;;;N;;;;; +11A7B;SOYOMBO LETTER YA;Lo;0;L;;;;;N;;;;; +11A7C;SOYOMBO LETTER RA;Lo;0;L;;;;;N;;;;; +11A7D;SOYOMBO LETTER LA;Lo;0;L;;;;;N;;;;; +11A7E;SOYOMBO LETTER VA;Lo;0;L;;;;;N;;;;; +11A7F;SOYOMBO LETTER SHA;Lo;0;L;;;;;N;;;;; +11A80;SOYOMBO LETTER SSA;Lo;0;L;;;;;N;;;;; +11A81;SOYOMBO LETTER SA;Lo;0;L;;;;;N;;;;; +11A82;SOYOMBO LETTER HA;Lo;0;L;;;;;N;;;;; +11A83;SOYOMBO LETTER KSSA;Lo;0;L;;;;;N;;;;; +11A86;SOYOMBO CLUSTER-INITIAL LETTER RA;Lo;0;L;;;;;N;;;;; +11A87;SOYOMBO CLUSTER-INITIAL LETTER LA;Lo;0;L;;;;;N;;;;; +11A88;SOYOMBO CLUSTER-INITIAL LETTER SHA;Lo;0;L;;;;;N;;;;; +11A89;SOYOMBO CLUSTER-INITIAL LETTER SA;Lo;0;L;;;;;N;;;;; +11A8A;SOYOMBO FINAL CONSONANT SIGN G;Mn;0;NSM;;;;;N;;;;; +11A8B;SOYOMBO FINAL CONSONANT SIGN K;Mn;0;NSM;;;;;N;;;;; +11A8C;SOYOMBO FINAL CONSONANT SIGN NG;Mn;0;NSM;;;;;N;;;;; +11A8D;SOYOMBO FINAL CONSONANT SIGN D;Mn;0;NSM;;;;;N;;;;; +11A8E;SOYOMBO FINAL CONSONANT SIGN N;Mn;0;NSM;;;;;N;;;;; +11A8F;SOYOMBO FINAL CONSONANT SIGN B;Mn;0;NSM;;;;;N;;;;; +11A90;SOYOMBO FINAL CONSONANT SIGN M;Mn;0;NSM;;;;;N;;;;; +11A91;SOYOMBO FINAL CONSONANT SIGN R;Mn;0;NSM;;;;;N;;;;; +11A92;SOYOMBO FINAL CONSONANT SIGN L;Mn;0;NSM;;;;;N;;;;; +11A93;SOYOMBO FINAL CONSONANT SIGN SH;Mn;0;NSM;;;;;N;;;;; +11A94;SOYOMBO FINAL CONSONANT SIGN S;Mn;0;NSM;;;;;N;;;;; +11A95;SOYOMBO FINAL CONSONANT SIGN -A;Mn;0;NSM;;;;;N;;;;; +11A96;SOYOMBO SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11A97;SOYOMBO SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11A98;SOYOMBO GEMINATION MARK;Mn;0;NSM;;;;;N;;;;; +11A99;SOYOMBO SUBJOINER;Mn;9;NSM;;;;;N;;;;; +11A9A;SOYOMBO MARK TSHEG;Po;0;L;;;;;N;;;;; +11A9B;SOYOMBO MARK SHAD;Po;0;L;;;;;N;;;;; +11A9C;SOYOMBO MARK DOUBLE SHAD;Po;0;L;;;;;N;;;;; +11A9E;SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME;Po;0;L;;;;;N;;;;; +11A9F;SOYOMBO HEAD MARK WITH MOON AND SUN AND FLAME;Po;0;L;;;;;N;;;;; +11AA0;SOYOMBO HEAD MARK WITH MOON AND SUN;Po;0;L;;;;;N;;;;; +11AA1;SOYOMBO TERMINAL MARK-1;Po;0;L;;;;;N;;;;; +11AA2;SOYOMBO TERMINAL MARK-2;Po;0;L;;;;;N;;;;; 11AC0;PAU CIN HAU LETTER PA;Lo;0;L;;;;;N;;;;; 11AC1;PAU CIN HAU LETTER KA;Lo;0;L;;;;;N;;;;; 11AC2;PAU CIN HAU LETTER LA;Lo;0;L;;;;;N;;;;; @@ -19889,6 +20316,246 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 11AF6;PAU CIN HAU LOW-FALLING TONE LONG FINAL;Lo;0;L;;;;;N;;;;; 11AF7;PAU CIN HAU LOW-FALLING TONE FINAL;Lo;0;L;;;;;N;;;;; 11AF8;PAU CIN HAU GLOTTAL STOP FINAL;Lo;0;L;;;;;N;;;;; +11C00;BHAIKSUKI LETTER A;Lo;0;L;;;;;N;;;;; +11C01;BHAIKSUKI LETTER AA;Lo;0;L;;;;;N;;;;; +11C02;BHAIKSUKI LETTER I;Lo;0;L;;;;;N;;;;; +11C03;BHAIKSUKI LETTER II;Lo;0;L;;;;;N;;;;; +11C04;BHAIKSUKI LETTER U;Lo;0;L;;;;;N;;;;; +11C05;BHAIKSUKI LETTER UU;Lo;0;L;;;;;N;;;;; +11C06;BHAIKSUKI LETTER VOCALIC R;Lo;0;L;;;;;N;;;;; +11C07;BHAIKSUKI LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; +11C08;BHAIKSUKI LETTER VOCALIC L;Lo;0;L;;;;;N;;;;; +11C0A;BHAIKSUKI LETTER E;Lo;0;L;;;;;N;;;;; +11C0B;BHAIKSUKI LETTER AI;Lo;0;L;;;;;N;;;;; +11C0C;BHAIKSUKI LETTER O;Lo;0;L;;;;;N;;;;; +11C0D;BHAIKSUKI LETTER AU;Lo;0;L;;;;;N;;;;; +11C0E;BHAIKSUKI LETTER KA;Lo;0;L;;;;;N;;;;; +11C0F;BHAIKSUKI LETTER KHA;Lo;0;L;;;;;N;;;;; +11C10;BHAIKSUKI LETTER GA;Lo;0;L;;;;;N;;;;; +11C11;BHAIKSUKI LETTER GHA;Lo;0;L;;;;;N;;;;; +11C12;BHAIKSUKI LETTER NGA;Lo;0;L;;;;;N;;;;; +11C13;BHAIKSUKI LETTER CA;Lo;0;L;;;;;N;;;;; +11C14;BHAIKSUKI LETTER CHA;Lo;0;L;;;;;N;;;;; +11C15;BHAIKSUKI LETTER JA;Lo;0;L;;;;;N;;;;; +11C16;BHAIKSUKI LETTER JHA;Lo;0;L;;;;;N;;;;; +11C17;BHAIKSUKI LETTER NYA;Lo;0;L;;;;;N;;;;; +11C18;BHAIKSUKI LETTER TTA;Lo;0;L;;;;;N;;;;; +11C19;BHAIKSUKI LETTER TTHA;Lo;0;L;;;;;N;;;;; +11C1A;BHAIKSUKI LETTER DDA;Lo;0;L;;;;;N;;;;; +11C1B;BHAIKSUKI LETTER DDHA;Lo;0;L;;;;;N;;;;; +11C1C;BHAIKSUKI LETTER NNA;Lo;0;L;;;;;N;;;;; +11C1D;BHAIKSUKI LETTER TA;Lo;0;L;;;;;N;;;;; +11C1E;BHAIKSUKI LETTER THA;Lo;0;L;;;;;N;;;;; +11C1F;BHAIKSUKI LETTER DA;Lo;0;L;;;;;N;;;;; +11C20;BHAIKSUKI LETTER DHA;Lo;0;L;;;;;N;;;;; +11C21;BHAIKSUKI LETTER NA;Lo;0;L;;;;;N;;;;; +11C22;BHAIKSUKI LETTER PA;Lo;0;L;;;;;N;;;;; +11C23;BHAIKSUKI LETTER PHA;Lo;0;L;;;;;N;;;;; +11C24;BHAIKSUKI LETTER BA;Lo;0;L;;;;;N;;;;; +11C25;BHAIKSUKI LETTER BHA;Lo;0;L;;;;;N;;;;; +11C26;BHAIKSUKI LETTER MA;Lo;0;L;;;;;N;;;;; +11C27;BHAIKSUKI LETTER YA;Lo;0;L;;;;;N;;;;; +11C28;BHAIKSUKI LETTER RA;Lo;0;L;;;;;N;;;;; +11C29;BHAIKSUKI LETTER LA;Lo;0;L;;;;;N;;;;; +11C2A;BHAIKSUKI LETTER VA;Lo;0;L;;;;;N;;;;; +11C2B;BHAIKSUKI LETTER SHA;Lo;0;L;;;;;N;;;;; +11C2C;BHAIKSUKI LETTER SSA;Lo;0;L;;;;;N;;;;; +11C2D;BHAIKSUKI LETTER SA;Lo;0;L;;;;;N;;;;; +11C2E;BHAIKSUKI LETTER HA;Lo;0;L;;;;;N;;;;; +11C2F;BHAIKSUKI VOWEL SIGN AA;Mc;0;L;;;;;N;;;;; +11C30;BHAIKSUKI VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11C31;BHAIKSUKI VOWEL SIGN II;Mn;0;NSM;;;;;N;;;;; +11C32;BHAIKSUKI VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11C33;BHAIKSUKI VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;; +11C34;BHAIKSUKI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +11C35;BHAIKSUKI VOWEL SIGN VOCALIC RR;Mn;0;NSM;;;;;N;;;;; +11C36;BHAIKSUKI VOWEL SIGN VOCALIC L;Mn;0;NSM;;;;;N;;;;; +11C38;BHAIKSUKI VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11C39;BHAIKSUKI VOWEL SIGN AI;Mn;0;NSM;;;;;N;;;;; +11C3A;BHAIKSUKI VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11C3B;BHAIKSUKI VOWEL SIGN AU;Mn;0;NSM;;;;;N;;;;; +11C3C;BHAIKSUKI SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11C3D;BHAIKSUKI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11C3E;BHAIKSUKI SIGN VISARGA;Mc;0;L;;;;;N;;;;; +11C3F;BHAIKSUKI SIGN VIRAMA;Mn;9;L;;;;;N;;;;; +11C40;BHAIKSUKI SIGN AVAGRAHA;Lo;0;L;;;;;N;;;;; +11C41;BHAIKSUKI DANDA;Po;0;L;;;;;N;;;;; +11C42;BHAIKSUKI DOUBLE DANDA;Po;0;L;;;;;N;;;;; +11C43;BHAIKSUKI WORD SEPARATOR;Po;0;L;;;;;N;;;;; +11C44;BHAIKSUKI GAP FILLER-1;Po;0;L;;;;;N;;;;; +11C45;BHAIKSUKI GAP FILLER-2;Po;0;L;;;;;N;;;;; +11C50;BHAIKSUKI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +11C51;BHAIKSUKI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +11C52;BHAIKSUKI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +11C53;BHAIKSUKI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +11C54;BHAIKSUKI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +11C55;BHAIKSUKI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +11C56;BHAIKSUKI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +11C57;BHAIKSUKI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +11C58;BHAIKSUKI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +11C59;BHAIKSUKI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +11C5A;BHAIKSUKI NUMBER ONE;No;0;L;;;;1;N;;;;; +11C5B;BHAIKSUKI NUMBER TWO;No;0;L;;;;2;N;;;;; +11C5C;BHAIKSUKI NUMBER THREE;No;0;L;;;;3;N;;;;; +11C5D;BHAIKSUKI NUMBER FOUR;No;0;L;;;;4;N;;;;; +11C5E;BHAIKSUKI NUMBER FIVE;No;0;L;;;;5;N;;;;; +11C5F;BHAIKSUKI NUMBER SIX;No;0;L;;;;6;N;;;;; +11C60;BHAIKSUKI NUMBER SEVEN;No;0;L;;;;7;N;;;;; +11C61;BHAIKSUKI NUMBER EIGHT;No;0;L;;;;8;N;;;;; +11C62;BHAIKSUKI NUMBER NINE;No;0;L;;;;9;N;;;;; +11C63;BHAIKSUKI NUMBER TEN;No;0;L;;;;10;N;;;;; +11C64;BHAIKSUKI NUMBER TWENTY;No;0;L;;;;20;N;;;;; +11C65;BHAIKSUKI NUMBER THIRTY;No;0;L;;;;30;N;;;;; +11C66;BHAIKSUKI NUMBER FORTY;No;0;L;;;;40;N;;;;; +11C67;BHAIKSUKI NUMBER FIFTY;No;0;L;;;;50;N;;;;; +11C68;BHAIKSUKI NUMBER SIXTY;No;0;L;;;;60;N;;;;; +11C69;BHAIKSUKI NUMBER SEVENTY;No;0;L;;;;70;N;;;;; +11C6A;BHAIKSUKI NUMBER EIGHTY;No;0;L;;;;80;N;;;;; +11C6B;BHAIKSUKI NUMBER NINETY;No;0;L;;;;90;N;;;;; +11C6C;BHAIKSUKI HUNDREDS UNIT MARK;No;0;L;;;;100;N;;;;; +11C70;MARCHEN HEAD MARK;Po;0;L;;;;;N;;;;; +11C71;MARCHEN MARK SHAD;Po;0;L;;;;;N;;;;; +11C72;MARCHEN LETTER KA;Lo;0;L;;;;;N;;;;; +11C73;MARCHEN LETTER KHA;Lo;0;L;;;;;N;;;;; +11C74;MARCHEN LETTER GA;Lo;0;L;;;;;N;;;;; +11C75;MARCHEN LETTER NGA;Lo;0;L;;;;;N;;;;; +11C76;MARCHEN LETTER CA;Lo;0;L;;;;;N;;;;; +11C77;MARCHEN LETTER CHA;Lo;0;L;;;;;N;;;;; +11C78;MARCHEN LETTER JA;Lo;0;L;;;;;N;;;;; +11C79;MARCHEN LETTER NYA;Lo;0;L;;;;;N;;;;; +11C7A;MARCHEN LETTER TA;Lo;0;L;;;;;N;;;;; +11C7B;MARCHEN LETTER THA;Lo;0;L;;;;;N;;;;; +11C7C;MARCHEN LETTER DA;Lo;0;L;;;;;N;;;;; +11C7D;MARCHEN LETTER NA;Lo;0;L;;;;;N;;;;; +11C7E;MARCHEN LETTER PA;Lo;0;L;;;;;N;;;;; +11C7F;MARCHEN LETTER PHA;Lo;0;L;;;;;N;;;;; +11C80;MARCHEN LETTER BA;Lo;0;L;;;;;N;;;;; +11C81;MARCHEN LETTER MA;Lo;0;L;;;;;N;;;;; +11C82;MARCHEN LETTER TSA;Lo;0;L;;;;;N;;;;; +11C83;MARCHEN LETTER TSHA;Lo;0;L;;;;;N;;;;; +11C84;MARCHEN LETTER DZA;Lo;0;L;;;;;N;;;;; +11C85;MARCHEN LETTER WA;Lo;0;L;;;;;N;;;;; +11C86;MARCHEN LETTER ZHA;Lo;0;L;;;;;N;;;;; +11C87;MARCHEN LETTER ZA;Lo;0;L;;;;;N;;;;; +11C88;MARCHEN LETTER -A;Lo;0;L;;;;;N;;;;; +11C89;MARCHEN LETTER YA;Lo;0;L;;;;;N;;;;; +11C8A;MARCHEN LETTER RA;Lo;0;L;;;;;N;;;;; +11C8B;MARCHEN LETTER LA;Lo;0;L;;;;;N;;;;; +11C8C;MARCHEN LETTER SHA;Lo;0;L;;;;;N;;;;; +11C8D;MARCHEN LETTER SA;Lo;0;L;;;;;N;;;;; +11C8E;MARCHEN LETTER HA;Lo;0;L;;;;;N;;;;; +11C8F;MARCHEN LETTER A;Lo;0;L;;;;;N;;;;; +11C92;MARCHEN SUBJOINED LETTER KA;Mn;0;NSM;;;;;N;;;;; +11C93;MARCHEN SUBJOINED LETTER KHA;Mn;0;NSM;;;;;N;;;;; +11C94;MARCHEN SUBJOINED LETTER GA;Mn;0;NSM;;;;;N;;;;; +11C95;MARCHEN SUBJOINED LETTER NGA;Mn;0;NSM;;;;;N;;;;; +11C96;MARCHEN SUBJOINED LETTER CA;Mn;0;NSM;;;;;N;;;;; +11C97;MARCHEN SUBJOINED LETTER CHA;Mn;0;NSM;;;;;N;;;;; +11C98;MARCHEN SUBJOINED LETTER JA;Mn;0;NSM;;;;;N;;;;; +11C99;MARCHEN SUBJOINED LETTER NYA;Mn;0;NSM;;;;;N;;;;; +11C9A;MARCHEN SUBJOINED LETTER TA;Mn;0;NSM;;;;;N;;;;; +11C9B;MARCHEN SUBJOINED LETTER THA;Mn;0;NSM;;;;;N;;;;; +11C9C;MARCHEN SUBJOINED LETTER DA;Mn;0;NSM;;;;;N;;;;; +11C9D;MARCHEN SUBJOINED LETTER NA;Mn;0;NSM;;;;;N;;;;; +11C9E;MARCHEN SUBJOINED LETTER PA;Mn;0;NSM;;;;;N;;;;; +11C9F;MARCHEN SUBJOINED LETTER PHA;Mn;0;NSM;;;;;N;;;;; +11CA0;MARCHEN SUBJOINED LETTER BA;Mn;0;NSM;;;;;N;;;;; +11CA1;MARCHEN SUBJOINED LETTER MA;Mn;0;NSM;;;;;N;;;;; +11CA2;MARCHEN SUBJOINED LETTER TSA;Mn;0;NSM;;;;;N;;;;; +11CA3;MARCHEN SUBJOINED LETTER TSHA;Mn;0;NSM;;;;;N;;;;; +11CA4;MARCHEN SUBJOINED LETTER DZA;Mn;0;NSM;;;;;N;;;;; +11CA5;MARCHEN SUBJOINED LETTER WA;Mn;0;NSM;;;;;N;;;;; +11CA6;MARCHEN SUBJOINED LETTER ZHA;Mn;0;NSM;;;;;N;;;;; +11CA7;MARCHEN SUBJOINED LETTER ZA;Mn;0;NSM;;;;;N;;;;; +11CA9;MARCHEN SUBJOINED LETTER YA;Mc;0;L;;;;;N;;;;; +11CAA;MARCHEN SUBJOINED LETTER RA;Mn;0;NSM;;;;;N;;;;; +11CAB;MARCHEN SUBJOINED LETTER LA;Mn;0;NSM;;;;;N;;;;; +11CAC;MARCHEN SUBJOINED LETTER SHA;Mn;0;NSM;;;;;N;;;;; +11CAD;MARCHEN SUBJOINED LETTER SA;Mn;0;NSM;;;;;N;;;;; +11CAE;MARCHEN SUBJOINED LETTER HA;Mn;0;NSM;;;;;N;;;;; +11CAF;MARCHEN SUBJOINED LETTER A;Mn;0;NSM;;;;;N;;;;; +11CB0;MARCHEN VOWEL SIGN AA;Mn;0;NSM;;;;;N;;;;; +11CB1;MARCHEN VOWEL SIGN I;Mc;0;L;;;;;N;;;;; +11CB2;MARCHEN VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11CB3;MARCHEN VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11CB4;MARCHEN VOWEL SIGN O;Mc;0;L;;;;;N;;;;; +11CB5;MARCHEN SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11CB6;MARCHEN SIGN CANDRABINDU;Mn;0;NSM;;;;;N;;;;; +11D00;MASARAM GONDI LETTER A;Lo;0;L;;;;;N;;;;; +11D01;MASARAM GONDI LETTER AA;Lo;0;L;;;;;N;;;;; +11D02;MASARAM GONDI LETTER I;Lo;0;L;;;;;N;;;;; +11D03;MASARAM GONDI LETTER II;Lo;0;L;;;;;N;;;;; +11D04;MASARAM GONDI LETTER U;Lo;0;L;;;;;N;;;;; +11D05;MASARAM GONDI LETTER UU;Lo;0;L;;;;;N;;;;; +11D06;MASARAM GONDI LETTER E;Lo;0;L;;;;;N;;;;; +11D08;MASARAM GONDI LETTER AI;Lo;0;L;;;;;N;;;;; +11D09;MASARAM GONDI LETTER O;Lo;0;L;;;;;N;;;;; +11D0B;MASARAM GONDI LETTER AU;Lo;0;L;;;;;N;;;;; +11D0C;MASARAM GONDI LETTER KA;Lo;0;L;;;;;N;;;;; +11D0D;MASARAM GONDI LETTER KHA;Lo;0;L;;;;;N;;;;; +11D0E;MASARAM GONDI LETTER GA;Lo;0;L;;;;;N;;;;; +11D0F;MASARAM GONDI LETTER GHA;Lo;0;L;;;;;N;;;;; +11D10;MASARAM GONDI LETTER NGA;Lo;0;L;;;;;N;;;;; +11D11;MASARAM GONDI LETTER CA;Lo;0;L;;;;;N;;;;; +11D12;MASARAM GONDI LETTER CHA;Lo;0;L;;;;;N;;;;; +11D13;MASARAM GONDI LETTER JA;Lo;0;L;;;;;N;;;;; +11D14;MASARAM GONDI LETTER JHA;Lo;0;L;;;;;N;;;;; +11D15;MASARAM GONDI LETTER NYA;Lo;0;L;;;;;N;;;;; +11D16;MASARAM GONDI LETTER TTA;Lo;0;L;;;;;N;;;;; +11D17;MASARAM GONDI LETTER TTHA;Lo;0;L;;;;;N;;;;; +11D18;MASARAM GONDI LETTER DDA;Lo;0;L;;;;;N;;;;; +11D19;MASARAM GONDI LETTER DDHA;Lo;0;L;;;;;N;;;;; +11D1A;MASARAM GONDI LETTER NNA;Lo;0;L;;;;;N;;;;; +11D1B;MASARAM GONDI LETTER TA;Lo;0;L;;;;;N;;;;; +11D1C;MASARAM GONDI LETTER THA;Lo;0;L;;;;;N;;;;; +11D1D;MASARAM GONDI LETTER DA;Lo;0;L;;;;;N;;;;; +11D1E;MASARAM GONDI LETTER DHA;Lo;0;L;;;;;N;;;;; +11D1F;MASARAM GONDI LETTER NA;Lo;0;L;;;;;N;;;;; +11D20;MASARAM GONDI LETTER PA;Lo;0;L;;;;;N;;;;; +11D21;MASARAM GONDI LETTER PHA;Lo;0;L;;;;;N;;;;; +11D22;MASARAM GONDI LETTER BA;Lo;0;L;;;;;N;;;;; +11D23;MASARAM GONDI LETTER BHA;Lo;0;L;;;;;N;;;;; +11D24;MASARAM GONDI LETTER MA;Lo;0;L;;;;;N;;;;; +11D25;MASARAM GONDI LETTER YA;Lo;0;L;;;;;N;;;;; +11D26;MASARAM GONDI LETTER RA;Lo;0;L;;;;;N;;;;; +11D27;MASARAM GONDI LETTER LA;Lo;0;L;;;;;N;;;;; +11D28;MASARAM GONDI LETTER VA;Lo;0;L;;;;;N;;;;; +11D29;MASARAM GONDI LETTER SHA;Lo;0;L;;;;;N;;;;; +11D2A;MASARAM GONDI LETTER SSA;Lo;0;L;;;;;N;;;;; +11D2B;MASARAM GONDI LETTER SA;Lo;0;L;;;;;N;;;;; +11D2C;MASARAM GONDI LETTER HA;Lo;0;L;;;;;N;;;;; +11D2D;MASARAM GONDI LETTER LLA;Lo;0;L;;;;;N;;;;; +11D2E;MASARAM GONDI LETTER KSSA;Lo;0;L;;;;;N;;;;; +11D2F;MASARAM GONDI LETTER JNYA;Lo;0;L;;;;;N;;;;; +11D30;MASARAM GONDI LETTER TRA;Lo;0;L;;;;;N;;;;; +11D31;MASARAM GONDI VOWEL SIGN AA;Mn;0;NSM;;;;;N;;;;; +11D32;MASARAM GONDI VOWEL SIGN I;Mn;0;NSM;;;;;N;;;;; +11D33;MASARAM GONDI VOWEL SIGN II;Mn;0;NSM;;;;;N;;;;; +11D34;MASARAM GONDI VOWEL SIGN U;Mn;0;NSM;;;;;N;;;;; +11D35;MASARAM GONDI VOWEL SIGN UU;Mn;0;NSM;;;;;N;;;;; +11D36;MASARAM GONDI VOWEL SIGN VOCALIC R;Mn;0;NSM;;;;;N;;;;; +11D3A;MASARAM GONDI VOWEL SIGN E;Mn;0;NSM;;;;;N;;;;; +11D3C;MASARAM GONDI VOWEL SIGN AI;Mn;0;NSM;;;;;N;;;;; +11D3D;MASARAM GONDI VOWEL SIGN O;Mn;0;NSM;;;;;N;;;;; +11D3F;MASARAM GONDI VOWEL SIGN AU;Mn;0;NSM;;;;;N;;;;; +11D40;MASARAM GONDI SIGN ANUSVARA;Mn;0;NSM;;;;;N;;;;; +11D41;MASARAM GONDI SIGN VISARGA;Mn;0;NSM;;;;;N;;;;; +11D42;MASARAM GONDI SIGN NUKTA;Mn;7;NSM;;;;;N;;;;; +11D43;MASARAM GONDI SIGN CANDRA;Mn;0;NSM;;;;;N;;;;; +11D44;MASARAM GONDI SIGN HALANTA;Mn;9;NSM;;;;;N;;;;; +11D45;MASARAM GONDI VIRAMA;Mn;9;NSM;;;;;N;;;;; +11D46;MASARAM GONDI REPHA;Lo;0;L;;;;;N;;;;; +11D47;MASARAM GONDI RA-KARA;Mn;0;NSM;;;;;N;;;;; +11D50;MASARAM GONDI DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +11D51;MASARAM GONDI DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +11D52;MASARAM GONDI DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +11D53;MASARAM GONDI DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +11D54;MASARAM GONDI DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +11D55;MASARAM GONDI DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +11D56;MASARAM GONDI DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +11D57;MASARAM GONDI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +11D58;MASARAM GONDI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +11D59;MASARAM GONDI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; 12000;CUNEIFORM SIGN A;Lo;0;L;;;;;N;;;;; 12001;CUNEIFORM SIGN A TIMES A;Lo;0;L;;;;;N;;;;; 12002;CUNEIFORM SIGN A TIMES BAD;Lo;0;L;;;;;N;;;;; @@ -23685,8 +24352,1448 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 16F9D;MIAO LETTER REFORMED TONE-5;Lm;0;L;;;;;N;;;;; 16F9E;MIAO LETTER REFORMED TONE-6;Lm;0;L;;;;;N;;;;; 16F9F;MIAO LETTER REFORMED TONE-8;Lm;0;L;;;;;N;;;;; +16FE0;TANGUT ITERATION MARK;Lm;0;L;;;;;N;;;;; +16FE1;NUSHU ITERATION MARK;Lm;0;L;;;;;N;;;;; +17000;<Tangut Ideograph, First>;Lo;0;L;;;;;N;;;;; +187EC;<Tangut Ideograph, Last>;Lo;0;L;;;;;N;;;;; +18800;TANGUT COMPONENT-001;Lo;0;L;;;;;N;;;;; +18801;TANGUT COMPONENT-002;Lo;0;L;;;;;N;;;;; +18802;TANGUT COMPONENT-003;Lo;0;L;;;;;N;;;;; +18803;TANGUT COMPONENT-004;Lo;0;L;;;;;N;;;;; +18804;TANGUT COMPONENT-005;Lo;0;L;;;;;N;;;;; +18805;TANGUT COMPONENT-006;Lo;0;L;;;;;N;;;;; +18806;TANGUT COMPONENT-007;Lo;0;L;;;;;N;;;;; +18807;TANGUT COMPONENT-008;Lo;0;L;;;;;N;;;;; +18808;TANGUT COMPONENT-009;Lo;0;L;;;;;N;;;;; +18809;TANGUT COMPONENT-010;Lo;0;L;;;;;N;;;;; +1880A;TANGUT COMPONENT-011;Lo;0;L;;;;;N;;;;; +1880B;TANGUT COMPONENT-012;Lo;0;L;;;;;N;;;;; +1880C;TANGUT COMPONENT-013;Lo;0;L;;;;;N;;;;; +1880D;TANGUT COMPONENT-014;Lo;0;L;;;;;N;;;;; +1880E;TANGUT COMPONENT-015;Lo;0;L;;;;;N;;;;; +1880F;TANGUT COMPONENT-016;Lo;0;L;;;;;N;;;;; +18810;TANGUT COMPONENT-017;Lo;0;L;;;;;N;;;;; +18811;TANGUT COMPONENT-018;Lo;0;L;;;;;N;;;;; +18812;TANGUT COMPONENT-019;Lo;0;L;;;;;N;;;;; +18813;TANGUT COMPONENT-020;Lo;0;L;;;;;N;;;;; +18814;TANGUT COMPONENT-021;Lo;0;L;;;;;N;;;;; +18815;TANGUT COMPONENT-022;Lo;0;L;;;;;N;;;;; +18816;TANGUT COMPONENT-023;Lo;0;L;;;;;N;;;;; +18817;TANGUT COMPONENT-024;Lo;0;L;;;;;N;;;;; +18818;TANGUT COMPONENT-025;Lo;0;L;;;;;N;;;;; +18819;TANGUT COMPONENT-026;Lo;0;L;;;;;N;;;;; +1881A;TANGUT COMPONENT-027;Lo;0;L;;;;;N;;;;; +1881B;TANGUT COMPONENT-028;Lo;0;L;;;;;N;;;;; +1881C;TANGUT COMPONENT-029;Lo;0;L;;;;;N;;;;; +1881D;TANGUT COMPONENT-030;Lo;0;L;;;;;N;;;;; +1881E;TANGUT COMPONENT-031;Lo;0;L;;;;;N;;;;; +1881F;TANGUT COMPONENT-032;Lo;0;L;;;;;N;;;;; +18820;TANGUT COMPONENT-033;Lo;0;L;;;;;N;;;;; +18821;TANGUT COMPONENT-034;Lo;0;L;;;;;N;;;;; +18822;TANGUT COMPONENT-035;Lo;0;L;;;;;N;;;;; +18823;TANGUT COMPONENT-036;Lo;0;L;;;;;N;;;;; +18824;TANGUT COMPONENT-037;Lo;0;L;;;;;N;;;;; +18825;TANGUT COMPONENT-038;Lo;0;L;;;;;N;;;;; +18826;TANGUT COMPONENT-039;Lo;0;L;;;;;N;;;;; +18827;TANGUT COMPONENT-040;Lo;0;L;;;;;N;;;;; +18828;TANGUT COMPONENT-041;Lo;0;L;;;;;N;;;;; +18829;TANGUT COMPONENT-042;Lo;0;L;;;;;N;;;;; +1882A;TANGUT COMPONENT-043;Lo;0;L;;;;;N;;;;; +1882B;TANGUT COMPONENT-044;Lo;0;L;;;;;N;;;;; +1882C;TANGUT COMPONENT-045;Lo;0;L;;;;;N;;;;; +1882D;TANGUT COMPONENT-046;Lo;0;L;;;;;N;;;;; +1882E;TANGUT COMPONENT-047;Lo;0;L;;;;;N;;;;; +1882F;TANGUT COMPONENT-048;Lo;0;L;;;;;N;;;;; +18830;TANGUT COMPONENT-049;Lo;0;L;;;;;N;;;;; +18831;TANGUT COMPONENT-050;Lo;0;L;;;;;N;;;;; +18832;TANGUT COMPONENT-051;Lo;0;L;;;;;N;;;;; +18833;TANGUT COMPONENT-052;Lo;0;L;;;;;N;;;;; +18834;TANGUT COMPONENT-053;Lo;0;L;;;;;N;;;;; +18835;TANGUT COMPONENT-054;Lo;0;L;;;;;N;;;;; +18836;TANGUT COMPONENT-055;Lo;0;L;;;;;N;;;;; +18837;TANGUT COMPONENT-056;Lo;0;L;;;;;N;;;;; +18838;TANGUT COMPONENT-057;Lo;0;L;;;;;N;;;;; +18839;TANGUT COMPONENT-058;Lo;0;L;;;;;N;;;;; +1883A;TANGUT COMPONENT-059;Lo;0;L;;;;;N;;;;; +1883B;TANGUT COMPONENT-060;Lo;0;L;;;;;N;;;;; +1883C;TANGUT COMPONENT-061;Lo;0;L;;;;;N;;;;; +1883D;TANGUT COMPONENT-062;Lo;0;L;;;;;N;;;;; +1883E;TANGUT COMPONENT-063;Lo;0;L;;;;;N;;;;; +1883F;TANGUT COMPONENT-064;Lo;0;L;;;;;N;;;;; +18840;TANGUT COMPONENT-065;Lo;0;L;;;;;N;;;;; +18841;TANGUT COMPONENT-066;Lo;0;L;;;;;N;;;;; +18842;TANGUT COMPONENT-067;Lo;0;L;;;;;N;;;;; +18843;TANGUT COMPONENT-068;Lo;0;L;;;;;N;;;;; +18844;TANGUT COMPONENT-069;Lo;0;L;;;;;N;;;;; +18845;TANGUT COMPONENT-070;Lo;0;L;;;;;N;;;;; +18846;TANGUT COMPONENT-071;Lo;0;L;;;;;N;;;;; +18847;TANGUT COMPONENT-072;Lo;0;L;;;;;N;;;;; +18848;TANGUT COMPONENT-073;Lo;0;L;;;;;N;;;;; +18849;TANGUT COMPONENT-074;Lo;0;L;;;;;N;;;;; +1884A;TANGUT COMPONENT-075;Lo;0;L;;;;;N;;;;; +1884B;TANGUT COMPONENT-076;Lo;0;L;;;;;N;;;;; +1884C;TANGUT COMPONENT-077;Lo;0;L;;;;;N;;;;; +1884D;TANGUT COMPONENT-078;Lo;0;L;;;;;N;;;;; +1884E;TANGUT COMPONENT-079;Lo;0;L;;;;;N;;;;; +1884F;TANGUT COMPONENT-080;Lo;0;L;;;;;N;;;;; +18850;TANGUT COMPONENT-081;Lo;0;L;;;;;N;;;;; +18851;TANGUT COMPONENT-082;Lo;0;L;;;;;N;;;;; +18852;TANGUT COMPONENT-083;Lo;0;L;;;;;N;;;;; +18853;TANGUT COMPONENT-084;Lo;0;L;;;;;N;;;;; +18854;TANGUT COMPONENT-085;Lo;0;L;;;;;N;;;;; +18855;TANGUT COMPONENT-086;Lo;0;L;;;;;N;;;;; +18856;TANGUT COMPONENT-087;Lo;0;L;;;;;N;;;;; +18857;TANGUT COMPONENT-088;Lo;0;L;;;;;N;;;;; +18858;TANGUT COMPONENT-089;Lo;0;L;;;;;N;;;;; +18859;TANGUT COMPONENT-090;Lo;0;L;;;;;N;;;;; +1885A;TANGUT COMPONENT-091;Lo;0;L;;;;;N;;;;; +1885B;TANGUT COMPONENT-092;Lo;0;L;;;;;N;;;;; +1885C;TANGUT COMPONENT-093;Lo;0;L;;;;;N;;;;; +1885D;TANGUT COMPONENT-094;Lo;0;L;;;;;N;;;;; +1885E;TANGUT COMPONENT-095;Lo;0;L;;;;;N;;;;; +1885F;TANGUT COMPONENT-096;Lo;0;L;;;;;N;;;;; +18860;TANGUT COMPONENT-097;Lo;0;L;;;;;N;;;;; +18861;TANGUT COMPONENT-098;Lo;0;L;;;;;N;;;;; +18862;TANGUT COMPONENT-099;Lo;0;L;;;;;N;;;;; +18863;TANGUT COMPONENT-100;Lo;0;L;;;;;N;;;;; +18864;TANGUT COMPONENT-101;Lo;0;L;;;;;N;;;;; +18865;TANGUT COMPONENT-102;Lo;0;L;;;;;N;;;;; +18866;TANGUT COMPONENT-103;Lo;0;L;;;;;N;;;;; +18867;TANGUT COMPONENT-104;Lo;0;L;;;;;N;;;;; +18868;TANGUT COMPONENT-105;Lo;0;L;;;;;N;;;;; +18869;TANGUT COMPONENT-106;Lo;0;L;;;;;N;;;;; +1886A;TANGUT COMPONENT-107;Lo;0;L;;;;;N;;;;; +1886B;TANGUT COMPONENT-108;Lo;0;L;;;;;N;;;;; +1886C;TANGUT COMPONENT-109;Lo;0;L;;;;;N;;;;; +1886D;TANGUT COMPONENT-110;Lo;0;L;;;;;N;;;;; +1886E;TANGUT COMPONENT-111;Lo;0;L;;;;;N;;;;; +1886F;TANGUT COMPONENT-112;Lo;0;L;;;;;N;;;;; +18870;TANGUT COMPONENT-113;Lo;0;L;;;;;N;;;;; +18871;TANGUT COMPONENT-114;Lo;0;L;;;;;N;;;;; +18872;TANGUT COMPONENT-115;Lo;0;L;;;;;N;;;;; +18873;TANGUT COMPONENT-116;Lo;0;L;;;;;N;;;;; +18874;TANGUT COMPONENT-117;Lo;0;L;;;;;N;;;;; +18875;TANGUT COMPONENT-118;Lo;0;L;;;;;N;;;;; +18876;TANGUT COMPONENT-119;Lo;0;L;;;;;N;;;;; +18877;TANGUT COMPONENT-120;Lo;0;L;;;;;N;;;;; +18878;TANGUT COMPONENT-121;Lo;0;L;;;;;N;;;;; +18879;TANGUT COMPONENT-122;Lo;0;L;;;;;N;;;;; +1887A;TANGUT COMPONENT-123;Lo;0;L;;;;;N;;;;; +1887B;TANGUT COMPONENT-124;Lo;0;L;;;;;N;;;;; +1887C;TANGUT COMPONENT-125;Lo;0;L;;;;;N;;;;; +1887D;TANGUT COMPONENT-126;Lo;0;L;;;;;N;;;;; +1887E;TANGUT COMPONENT-127;Lo;0;L;;;;;N;;;;; +1887F;TANGUT COMPONENT-128;Lo;0;L;;;;;N;;;;; +18880;TANGUT COMPONENT-129;Lo;0;L;;;;;N;;;;; +18881;TANGUT COMPONENT-130;Lo;0;L;;;;;N;;;;; +18882;TANGUT COMPONENT-131;Lo;0;L;;;;;N;;;;; +18883;TANGUT COMPONENT-132;Lo;0;L;;;;;N;;;;; +18884;TANGUT COMPONENT-133;Lo;0;L;;;;;N;;;;; +18885;TANGUT COMPONENT-134;Lo;0;L;;;;;N;;;;; +18886;TANGUT COMPONENT-135;Lo;0;L;;;;;N;;;;; +18887;TANGUT COMPONENT-136;Lo;0;L;;;;;N;;;;; +18888;TANGUT COMPONENT-137;Lo;0;L;;;;;N;;;;; +18889;TANGUT COMPONENT-138;Lo;0;L;;;;;N;;;;; +1888A;TANGUT COMPONENT-139;Lo;0;L;;;;;N;;;;; +1888B;TANGUT COMPONENT-140;Lo;0;L;;;;;N;;;;; +1888C;TANGUT COMPONENT-141;Lo;0;L;;;;;N;;;;; +1888D;TANGUT COMPONENT-142;Lo;0;L;;;;;N;;;;; +1888E;TANGUT COMPONENT-143;Lo;0;L;;;;;N;;;;; +1888F;TANGUT COMPONENT-144;Lo;0;L;;;;;N;;;;; +18890;TANGUT COMPONENT-145;Lo;0;L;;;;;N;;;;; +18891;TANGUT COMPONENT-146;Lo;0;L;;;;;N;;;;; +18892;TANGUT COMPONENT-147;Lo;0;L;;;;;N;;;;; +18893;TANGUT COMPONENT-148;Lo;0;L;;;;;N;;;;; +18894;TANGUT COMPONENT-149;Lo;0;L;;;;;N;;;;; +18895;TANGUT COMPONENT-150;Lo;0;L;;;;;N;;;;; +18896;TANGUT COMPONENT-151;Lo;0;L;;;;;N;;;;; +18897;TANGUT COMPONENT-152;Lo;0;L;;;;;N;;;;; +18898;TANGUT COMPONENT-153;Lo;0;L;;;;;N;;;;; +18899;TANGUT COMPONENT-154;Lo;0;L;;;;;N;;;;; +1889A;TANGUT COMPONENT-155;Lo;0;L;;;;;N;;;;; +1889B;TANGUT COMPONENT-156;Lo;0;L;;;;;N;;;;; +1889C;TANGUT COMPONENT-157;Lo;0;L;;;;;N;;;;; +1889D;TANGUT COMPONENT-158;Lo;0;L;;;;;N;;;;; +1889E;TANGUT COMPONENT-159;Lo;0;L;;;;;N;;;;; +1889F;TANGUT COMPONENT-160;Lo;0;L;;;;;N;;;;; +188A0;TANGUT COMPONENT-161;Lo;0;L;;;;;N;;;;; +188A1;TANGUT COMPONENT-162;Lo;0;L;;;;;N;;;;; +188A2;TANGUT COMPONENT-163;Lo;0;L;;;;;N;;;;; +188A3;TANGUT COMPONENT-164;Lo;0;L;;;;;N;;;;; +188A4;TANGUT COMPONENT-165;Lo;0;L;;;;;N;;;;; +188A5;TANGUT COMPONENT-166;Lo;0;L;;;;;N;;;;; +188A6;TANGUT COMPONENT-167;Lo;0;L;;;;;N;;;;; +188A7;TANGUT COMPONENT-168;Lo;0;L;;;;;N;;;;; +188A8;TANGUT COMPONENT-169;Lo;0;L;;;;;N;;;;; +188A9;TANGUT COMPONENT-170;Lo;0;L;;;;;N;;;;; +188AA;TANGUT COMPONENT-171;Lo;0;L;;;;;N;;;;; +188AB;TANGUT COMPONENT-172;Lo;0;L;;;;;N;;;;; +188AC;TANGUT COMPONENT-173;Lo;0;L;;;;;N;;;;; +188AD;TANGUT COMPONENT-174;Lo;0;L;;;;;N;;;;; +188AE;TANGUT COMPONENT-175;Lo;0;L;;;;;N;;;;; +188AF;TANGUT COMPONENT-176;Lo;0;L;;;;;N;;;;; +188B0;TANGUT COMPONENT-177;Lo;0;L;;;;;N;;;;; +188B1;TANGUT COMPONENT-178;Lo;0;L;;;;;N;;;;; +188B2;TANGUT COMPONENT-179;Lo;0;L;;;;;N;;;;; +188B3;TANGUT COMPONENT-180;Lo;0;L;;;;;N;;;;; +188B4;TANGUT COMPONENT-181;Lo;0;L;;;;;N;;;;; +188B5;TANGUT COMPONENT-182;Lo;0;L;;;;;N;;;;; +188B6;TANGUT COMPONENT-183;Lo;0;L;;;;;N;;;;; +188B7;TANGUT COMPONENT-184;Lo;0;L;;;;;N;;;;; +188B8;TANGUT COMPONENT-185;Lo;0;L;;;;;N;;;;; +188B9;TANGUT COMPONENT-186;Lo;0;L;;;;;N;;;;; +188BA;TANGUT COMPONENT-187;Lo;0;L;;;;;N;;;;; +188BB;TANGUT COMPONENT-188;Lo;0;L;;;;;N;;;;; +188BC;TANGUT COMPONENT-189;Lo;0;L;;;;;N;;;;; +188BD;TANGUT COMPONENT-190;Lo;0;L;;;;;N;;;;; +188BE;TANGUT COMPONENT-191;Lo;0;L;;;;;N;;;;; +188BF;TANGUT COMPONENT-192;Lo;0;L;;;;;N;;;;; +188C0;TANGUT COMPONENT-193;Lo;0;L;;;;;N;;;;; +188C1;TANGUT COMPONENT-194;Lo;0;L;;;;;N;;;;; +188C2;TANGUT COMPONENT-195;Lo;0;L;;;;;N;;;;; +188C3;TANGUT COMPONENT-196;Lo;0;L;;;;;N;;;;; +188C4;TANGUT COMPONENT-197;Lo;0;L;;;;;N;;;;; +188C5;TANGUT COMPONENT-198;Lo;0;L;;;;;N;;;;; +188C6;TANGUT COMPONENT-199;Lo;0;L;;;;;N;;;;; +188C7;TANGUT COMPONENT-200;Lo;0;L;;;;;N;;;;; +188C8;TANGUT COMPONENT-201;Lo;0;L;;;;;N;;;;; +188C9;TANGUT COMPONENT-202;Lo;0;L;;;;;N;;;;; +188CA;TANGUT COMPONENT-203;Lo;0;L;;;;;N;;;;; +188CB;TANGUT COMPONENT-204;Lo;0;L;;;;;N;;;;; +188CC;TANGUT COMPONENT-205;Lo;0;L;;;;;N;;;;; +188CD;TANGUT COMPONENT-206;Lo;0;L;;;;;N;;;;; +188CE;TANGUT COMPONENT-207;Lo;0;L;;;;;N;;;;; +188CF;TANGUT COMPONENT-208;Lo;0;L;;;;;N;;;;; +188D0;TANGUT COMPONENT-209;Lo;0;L;;;;;N;;;;; +188D1;TANGUT COMPONENT-210;Lo;0;L;;;;;N;;;;; +188D2;TANGUT COMPONENT-211;Lo;0;L;;;;;N;;;;; +188D3;TANGUT COMPONENT-212;Lo;0;L;;;;;N;;;;; +188D4;TANGUT COMPONENT-213;Lo;0;L;;;;;N;;;;; +188D5;TANGUT COMPONENT-214;Lo;0;L;;;;;N;;;;; +188D6;TANGUT COMPONENT-215;Lo;0;L;;;;;N;;;;; +188D7;TANGUT COMPONENT-216;Lo;0;L;;;;;N;;;;; +188D8;TANGUT COMPONENT-217;Lo;0;L;;;;;N;;;;; +188D9;TANGUT COMPONENT-218;Lo;0;L;;;;;N;;;;; +188DA;TANGUT COMPONENT-219;Lo;0;L;;;;;N;;;;; +188DB;TANGUT COMPONENT-220;Lo;0;L;;;;;N;;;;; +188DC;TANGUT COMPONENT-221;Lo;0;L;;;;;N;;;;; +188DD;TANGUT COMPONENT-222;Lo;0;L;;;;;N;;;;; +188DE;TANGUT COMPONENT-223;Lo;0;L;;;;;N;;;;; +188DF;TANGUT COMPONENT-224;Lo;0;L;;;;;N;;;;; +188E0;TANGUT COMPONENT-225;Lo;0;L;;;;;N;;;;; +188E1;TANGUT COMPONENT-226;Lo;0;L;;;;;N;;;;; +188E2;TANGUT COMPONENT-227;Lo;0;L;;;;;N;;;;; +188E3;TANGUT COMPONENT-228;Lo;0;L;;;;;N;;;;; +188E4;TANGUT COMPONENT-229;Lo;0;L;;;;;N;;;;; +188E5;TANGUT COMPONENT-230;Lo;0;L;;;;;N;;;;; +188E6;TANGUT COMPONENT-231;Lo;0;L;;;;;N;;;;; +188E7;TANGUT COMPONENT-232;Lo;0;L;;;;;N;;;;; +188E8;TANGUT COMPONENT-233;Lo;0;L;;;;;N;;;;; +188E9;TANGUT COMPONENT-234;Lo;0;L;;;;;N;;;;; +188EA;TANGUT COMPONENT-235;Lo;0;L;;;;;N;;;;; +188EB;TANGUT COMPONENT-236;Lo;0;L;;;;;N;;;;; +188EC;TANGUT COMPONENT-237;Lo;0;L;;;;;N;;;;; +188ED;TANGUT COMPONENT-238;Lo;0;L;;;;;N;;;;; +188EE;TANGUT COMPONENT-239;Lo;0;L;;;;;N;;;;; +188EF;TANGUT COMPONENT-240;Lo;0;L;;;;;N;;;;; +188F0;TANGUT COMPONENT-241;Lo;0;L;;;;;N;;;;; +188F1;TANGUT COMPONENT-242;Lo;0;L;;;;;N;;;;; +188F2;TANGUT COMPONENT-243;Lo;0;L;;;;;N;;;;; +188F3;TANGUT COMPONENT-244;Lo;0;L;;;;;N;;;;; +188F4;TANGUT COMPONENT-245;Lo;0;L;;;;;N;;;;; +188F5;TANGUT COMPONENT-246;Lo;0;L;;;;;N;;;;; +188F6;TANGUT COMPONENT-247;Lo;0;L;;;;;N;;;;; +188F7;TANGUT COMPONENT-248;Lo;0;L;;;;;N;;;;; +188F8;TANGUT COMPONENT-249;Lo;0;L;;;;;N;;;;; +188F9;TANGUT COMPONENT-250;Lo;0;L;;;;;N;;;;; +188FA;TANGUT COMPONENT-251;Lo;0;L;;;;;N;;;;; +188FB;TANGUT COMPONENT-252;Lo;0;L;;;;;N;;;;; +188FC;TANGUT COMPONENT-253;Lo;0;L;;;;;N;;;;; +188FD;TANGUT COMPONENT-254;Lo;0;L;;;;;N;;;;; +188FE;TANGUT COMPONENT-255;Lo;0;L;;;;;N;;;;; +188FF;TANGUT COMPONENT-256;Lo;0;L;;;;;N;;;;; +18900;TANGUT COMPONENT-257;Lo;0;L;;;;;N;;;;; +18901;TANGUT COMPONENT-258;Lo;0;L;;;;;N;;;;; +18902;TANGUT COMPONENT-259;Lo;0;L;;;;;N;;;;; +18903;TANGUT COMPONENT-260;Lo;0;L;;;;;N;;;;; +18904;TANGUT COMPONENT-261;Lo;0;L;;;;;N;;;;; +18905;TANGUT COMPONENT-262;Lo;0;L;;;;;N;;;;; +18906;TANGUT COMPONENT-263;Lo;0;L;;;;;N;;;;; +18907;TANGUT COMPONENT-264;Lo;0;L;;;;;N;;;;; +18908;TANGUT COMPONENT-265;Lo;0;L;;;;;N;;;;; +18909;TANGUT COMPONENT-266;Lo;0;L;;;;;N;;;;; +1890A;TANGUT COMPONENT-267;Lo;0;L;;;;;N;;;;; +1890B;TANGUT COMPONENT-268;Lo;0;L;;;;;N;;;;; +1890C;TANGUT COMPONENT-269;Lo;0;L;;;;;N;;;;; +1890D;TANGUT COMPONENT-270;Lo;0;L;;;;;N;;;;; +1890E;TANGUT COMPONENT-271;Lo;0;L;;;;;N;;;;; +1890F;TANGUT COMPONENT-272;Lo;0;L;;;;;N;;;;; +18910;TANGUT COMPONENT-273;Lo;0;L;;;;;N;;;;; +18911;TANGUT COMPONENT-274;Lo;0;L;;;;;N;;;;; +18912;TANGUT COMPONENT-275;Lo;0;L;;;;;N;;;;; +18913;TANGUT COMPONENT-276;Lo;0;L;;;;;N;;;;; +18914;TANGUT COMPONENT-277;Lo;0;L;;;;;N;;;;; +18915;TANGUT COMPONENT-278;Lo;0;L;;;;;N;;;;; +18916;TANGUT COMPONENT-279;Lo;0;L;;;;;N;;;;; +18917;TANGUT COMPONENT-280;Lo;0;L;;;;;N;;;;; +18918;TANGUT COMPONENT-281;Lo;0;L;;;;;N;;;;; +18919;TANGUT COMPONENT-282;Lo;0;L;;;;;N;;;;; +1891A;TANGUT COMPONENT-283;Lo;0;L;;;;;N;;;;; +1891B;TANGUT COMPONENT-284;Lo;0;L;;;;;N;;;;; +1891C;TANGUT COMPONENT-285;Lo;0;L;;;;;N;;;;; +1891D;TANGUT COMPONENT-286;Lo;0;L;;;;;N;;;;; +1891E;TANGUT COMPONENT-287;Lo;0;L;;;;;N;;;;; +1891F;TANGUT COMPONENT-288;Lo;0;L;;;;;N;;;;; +18920;TANGUT COMPONENT-289;Lo;0;L;;;;;N;;;;; +18921;TANGUT COMPONENT-290;Lo;0;L;;;;;N;;;;; +18922;TANGUT COMPONENT-291;Lo;0;L;;;;;N;;;;; +18923;TANGUT COMPONENT-292;Lo;0;L;;;;;N;;;;; +18924;TANGUT COMPONENT-293;Lo;0;L;;;;;N;;;;; +18925;TANGUT COMPONENT-294;Lo;0;L;;;;;N;;;;; +18926;TANGUT COMPONENT-295;Lo;0;L;;;;;N;;;;; +18927;TANGUT COMPONENT-296;Lo;0;L;;;;;N;;;;; +18928;TANGUT COMPONENT-297;Lo;0;L;;;;;N;;;;; +18929;TANGUT COMPONENT-298;Lo;0;L;;;;;N;;;;; +1892A;TANGUT COMPONENT-299;Lo;0;L;;;;;N;;;;; +1892B;TANGUT COMPONENT-300;Lo;0;L;;;;;N;;;;; +1892C;TANGUT COMPONENT-301;Lo;0;L;;;;;N;;;;; +1892D;TANGUT COMPONENT-302;Lo;0;L;;;;;N;;;;; +1892E;TANGUT COMPONENT-303;Lo;0;L;;;;;N;;;;; +1892F;TANGUT COMPONENT-304;Lo;0;L;;;;;N;;;;; +18930;TANGUT COMPONENT-305;Lo;0;L;;;;;N;;;;; +18931;TANGUT COMPONENT-306;Lo;0;L;;;;;N;;;;; +18932;TANGUT COMPONENT-307;Lo;0;L;;;;;N;;;;; +18933;TANGUT COMPONENT-308;Lo;0;L;;;;;N;;;;; +18934;TANGUT COMPONENT-309;Lo;0;L;;;;;N;;;;; +18935;TANGUT COMPONENT-310;Lo;0;L;;;;;N;;;;; +18936;TANGUT COMPONENT-311;Lo;0;L;;;;;N;;;;; +18937;TANGUT COMPONENT-312;Lo;0;L;;;;;N;;;;; +18938;TANGUT COMPONENT-313;Lo;0;L;;;;;N;;;;; +18939;TANGUT COMPONENT-314;Lo;0;L;;;;;N;;;;; +1893A;TANGUT COMPONENT-315;Lo;0;L;;;;;N;;;;; +1893B;TANGUT COMPONENT-316;Lo;0;L;;;;;N;;;;; +1893C;TANGUT COMPONENT-317;Lo;0;L;;;;;N;;;;; +1893D;TANGUT COMPONENT-318;Lo;0;L;;;;;N;;;;; +1893E;TANGUT COMPONENT-319;Lo;0;L;;;;;N;;;;; +1893F;TANGUT COMPONENT-320;Lo;0;L;;;;;N;;;;; +18940;TANGUT COMPONENT-321;Lo;0;L;;;;;N;;;;; +18941;TANGUT COMPONENT-322;Lo;0;L;;;;;N;;;;; +18942;TANGUT COMPONENT-323;Lo;0;L;;;;;N;;;;; +18943;TANGUT COMPONENT-324;Lo;0;L;;;;;N;;;;; +18944;TANGUT COMPONENT-325;Lo;0;L;;;;;N;;;;; +18945;TANGUT COMPONENT-326;Lo;0;L;;;;;N;;;;; +18946;TANGUT COMPONENT-327;Lo;0;L;;;;;N;;;;; +18947;TANGUT COMPONENT-328;Lo;0;L;;;;;N;;;;; +18948;TANGUT COMPONENT-329;Lo;0;L;;;;;N;;;;; +18949;TANGUT COMPONENT-330;Lo;0;L;;;;;N;;;;; +1894A;TANGUT COMPONENT-331;Lo;0;L;;;;;N;;;;; +1894B;TANGUT COMPONENT-332;Lo;0;L;;;;;N;;;;; +1894C;TANGUT COMPONENT-333;Lo;0;L;;;;;N;;;;; +1894D;TANGUT COMPONENT-334;Lo;0;L;;;;;N;;;;; +1894E;TANGUT COMPONENT-335;Lo;0;L;;;;;N;;;;; +1894F;TANGUT COMPONENT-336;Lo;0;L;;;;;N;;;;; +18950;TANGUT COMPONENT-337;Lo;0;L;;;;;N;;;;; +18951;TANGUT COMPONENT-338;Lo;0;L;;;;;N;;;;; +18952;TANGUT COMPONENT-339;Lo;0;L;;;;;N;;;;; +18953;TANGUT COMPONENT-340;Lo;0;L;;;;;N;;;;; +18954;TANGUT COMPONENT-341;Lo;0;L;;;;;N;;;;; +18955;TANGUT COMPONENT-342;Lo;0;L;;;;;N;;;;; +18956;TANGUT COMPONENT-343;Lo;0;L;;;;;N;;;;; +18957;TANGUT COMPONENT-344;Lo;0;L;;;;;N;;;;; +18958;TANGUT COMPONENT-345;Lo;0;L;;;;;N;;;;; +18959;TANGUT COMPONENT-346;Lo;0;L;;;;;N;;;;; +1895A;TANGUT COMPONENT-347;Lo;0;L;;;;;N;;;;; +1895B;TANGUT COMPONENT-348;Lo;0;L;;;;;N;;;;; +1895C;TANGUT COMPONENT-349;Lo;0;L;;;;;N;;;;; +1895D;TANGUT COMPONENT-350;Lo;0;L;;;;;N;;;;; +1895E;TANGUT COMPONENT-351;Lo;0;L;;;;;N;;;;; +1895F;TANGUT COMPONENT-352;Lo;0;L;;;;;N;;;;; +18960;TANGUT COMPONENT-353;Lo;0;L;;;;;N;;;;; +18961;TANGUT COMPONENT-354;Lo;0;L;;;;;N;;;;; +18962;TANGUT COMPONENT-355;Lo;0;L;;;;;N;;;;; +18963;TANGUT COMPONENT-356;Lo;0;L;;;;;N;;;;; +18964;TANGUT COMPONENT-357;Lo;0;L;;;;;N;;;;; +18965;TANGUT COMPONENT-358;Lo;0;L;;;;;N;;;;; +18966;TANGUT COMPONENT-359;Lo;0;L;;;;;N;;;;; +18967;TANGUT COMPONENT-360;Lo;0;L;;;;;N;;;;; +18968;TANGUT COMPONENT-361;Lo;0;L;;;;;N;;;;; +18969;TANGUT COMPONENT-362;Lo;0;L;;;;;N;;;;; +1896A;TANGUT COMPONENT-363;Lo;0;L;;;;;N;;;;; +1896B;TANGUT COMPONENT-364;Lo;0;L;;;;;N;;;;; +1896C;TANGUT COMPONENT-365;Lo;0;L;;;;;N;;;;; +1896D;TANGUT COMPONENT-366;Lo;0;L;;;;;N;;;;; +1896E;TANGUT COMPONENT-367;Lo;0;L;;;;;N;;;;; +1896F;TANGUT COMPONENT-368;Lo;0;L;;;;;N;;;;; +18970;TANGUT COMPONENT-369;Lo;0;L;;;;;N;;;;; +18971;TANGUT COMPONENT-370;Lo;0;L;;;;;N;;;;; +18972;TANGUT COMPONENT-371;Lo;0;L;;;;;N;;;;; +18973;TANGUT COMPONENT-372;Lo;0;L;;;;;N;;;;; +18974;TANGUT COMPONENT-373;Lo;0;L;;;;;N;;;;; +18975;TANGUT COMPONENT-374;Lo;0;L;;;;;N;;;;; +18976;TANGUT COMPONENT-375;Lo;0;L;;;;;N;;;;; +18977;TANGUT COMPONENT-376;Lo;0;L;;;;;N;;;;; +18978;TANGUT COMPONENT-377;Lo;0;L;;;;;N;;;;; +18979;TANGUT COMPONENT-378;Lo;0;L;;;;;N;;;;; +1897A;TANGUT COMPONENT-379;Lo;0;L;;;;;N;;;;; +1897B;TANGUT COMPONENT-380;Lo;0;L;;;;;N;;;;; +1897C;TANGUT COMPONENT-381;Lo;0;L;;;;;N;;;;; +1897D;TANGUT COMPONENT-382;Lo;0;L;;;;;N;;;;; +1897E;TANGUT COMPONENT-383;Lo;0;L;;;;;N;;;;; +1897F;TANGUT COMPONENT-384;Lo;0;L;;;;;N;;;;; +18980;TANGUT COMPONENT-385;Lo;0;L;;;;;N;;;;; +18981;TANGUT COMPONENT-386;Lo;0;L;;;;;N;;;;; +18982;TANGUT COMPONENT-387;Lo;0;L;;;;;N;;;;; +18983;TANGUT COMPONENT-388;Lo;0;L;;;;;N;;;;; +18984;TANGUT COMPONENT-389;Lo;0;L;;;;;N;;;;; +18985;TANGUT COMPONENT-390;Lo;0;L;;;;;N;;;;; +18986;TANGUT COMPONENT-391;Lo;0;L;;;;;N;;;;; +18987;TANGUT COMPONENT-392;Lo;0;L;;;;;N;;;;; +18988;TANGUT COMPONENT-393;Lo;0;L;;;;;N;;;;; +18989;TANGUT COMPONENT-394;Lo;0;L;;;;;N;;;;; +1898A;TANGUT COMPONENT-395;Lo;0;L;;;;;N;;;;; +1898B;TANGUT COMPONENT-396;Lo;0;L;;;;;N;;;;; +1898C;TANGUT COMPONENT-397;Lo;0;L;;;;;N;;;;; +1898D;TANGUT COMPONENT-398;Lo;0;L;;;;;N;;;;; +1898E;TANGUT COMPONENT-399;Lo;0;L;;;;;N;;;;; +1898F;TANGUT COMPONENT-400;Lo;0;L;;;;;N;;;;; +18990;TANGUT COMPONENT-401;Lo;0;L;;;;;N;;;;; +18991;TANGUT COMPONENT-402;Lo;0;L;;;;;N;;;;; +18992;TANGUT COMPONENT-403;Lo;0;L;;;;;N;;;;; +18993;TANGUT COMPONENT-404;Lo;0;L;;;;;N;;;;; +18994;TANGUT COMPONENT-405;Lo;0;L;;;;;N;;;;; +18995;TANGUT COMPONENT-406;Lo;0;L;;;;;N;;;;; +18996;TANGUT COMPONENT-407;Lo;0;L;;;;;N;;;;; +18997;TANGUT COMPONENT-408;Lo;0;L;;;;;N;;;;; +18998;TANGUT COMPONENT-409;Lo;0;L;;;;;N;;;;; +18999;TANGUT COMPONENT-410;Lo;0;L;;;;;N;;;;; +1899A;TANGUT COMPONENT-411;Lo;0;L;;;;;N;;;;; +1899B;TANGUT COMPONENT-412;Lo;0;L;;;;;N;;;;; +1899C;TANGUT COMPONENT-413;Lo;0;L;;;;;N;;;;; +1899D;TANGUT COMPONENT-414;Lo;0;L;;;;;N;;;;; +1899E;TANGUT COMPONENT-415;Lo;0;L;;;;;N;;;;; +1899F;TANGUT COMPONENT-416;Lo;0;L;;;;;N;;;;; +189A0;TANGUT COMPONENT-417;Lo;0;L;;;;;N;;;;; +189A1;TANGUT COMPONENT-418;Lo;0;L;;;;;N;;;;; +189A2;TANGUT COMPONENT-419;Lo;0;L;;;;;N;;;;; +189A3;TANGUT COMPONENT-420;Lo;0;L;;;;;N;;;;; +189A4;TANGUT COMPONENT-421;Lo;0;L;;;;;N;;;;; +189A5;TANGUT COMPONENT-422;Lo;0;L;;;;;N;;;;; +189A6;TANGUT COMPONENT-423;Lo;0;L;;;;;N;;;;; +189A7;TANGUT COMPONENT-424;Lo;0;L;;;;;N;;;;; +189A8;TANGUT COMPONENT-425;Lo;0;L;;;;;N;;;;; +189A9;TANGUT COMPONENT-426;Lo;0;L;;;;;N;;;;; +189AA;TANGUT COMPONENT-427;Lo;0;L;;;;;N;;;;; +189AB;TANGUT COMPONENT-428;Lo;0;L;;;;;N;;;;; +189AC;TANGUT COMPONENT-429;Lo;0;L;;;;;N;;;;; +189AD;TANGUT COMPONENT-430;Lo;0;L;;;;;N;;;;; +189AE;TANGUT COMPONENT-431;Lo;0;L;;;;;N;;;;; +189AF;TANGUT COMPONENT-432;Lo;0;L;;;;;N;;;;; +189B0;TANGUT COMPONENT-433;Lo;0;L;;;;;N;;;;; +189B1;TANGUT COMPONENT-434;Lo;0;L;;;;;N;;;;; +189B2;TANGUT COMPONENT-435;Lo;0;L;;;;;N;;;;; +189B3;TANGUT COMPONENT-436;Lo;0;L;;;;;N;;;;; +189B4;TANGUT COMPONENT-437;Lo;0;L;;;;;N;;;;; +189B5;TANGUT COMPONENT-438;Lo;0;L;;;;;N;;;;; +189B6;TANGUT COMPONENT-439;Lo;0;L;;;;;N;;;;; +189B7;TANGUT COMPONENT-440;Lo;0;L;;;;;N;;;;; +189B8;TANGUT COMPONENT-441;Lo;0;L;;;;;N;;;;; +189B9;TANGUT COMPONENT-442;Lo;0;L;;;;;N;;;;; +189BA;TANGUT COMPONENT-443;Lo;0;L;;;;;N;;;;; +189BB;TANGUT COMPONENT-444;Lo;0;L;;;;;N;;;;; +189BC;TANGUT COMPONENT-445;Lo;0;L;;;;;N;;;;; +189BD;TANGUT COMPONENT-446;Lo;0;L;;;;;N;;;;; +189BE;TANGUT COMPONENT-447;Lo;0;L;;;;;N;;;;; +189BF;TANGUT COMPONENT-448;Lo;0;L;;;;;N;;;;; +189C0;TANGUT COMPONENT-449;Lo;0;L;;;;;N;;;;; +189C1;TANGUT COMPONENT-450;Lo;0;L;;;;;N;;;;; +189C2;TANGUT COMPONENT-451;Lo;0;L;;;;;N;;;;; +189C3;TANGUT COMPONENT-452;Lo;0;L;;;;;N;;;;; +189C4;TANGUT COMPONENT-453;Lo;0;L;;;;;N;;;;; +189C5;TANGUT COMPONENT-454;Lo;0;L;;;;;N;;;;; +189C6;TANGUT COMPONENT-455;Lo;0;L;;;;;N;;;;; +189C7;TANGUT COMPONENT-456;Lo;0;L;;;;;N;;;;; +189C8;TANGUT COMPONENT-457;Lo;0;L;;;;;N;;;;; +189C9;TANGUT COMPONENT-458;Lo;0;L;;;;;N;;;;; +189CA;TANGUT COMPONENT-459;Lo;0;L;;;;;N;;;;; +189CB;TANGUT COMPONENT-460;Lo;0;L;;;;;N;;;;; +189CC;TANGUT COMPONENT-461;Lo;0;L;;;;;N;;;;; +189CD;TANGUT COMPONENT-462;Lo;0;L;;;;;N;;;;; +189CE;TANGUT COMPONENT-463;Lo;0;L;;;;;N;;;;; +189CF;TANGUT COMPONENT-464;Lo;0;L;;;;;N;;;;; +189D0;TANGUT COMPONENT-465;Lo;0;L;;;;;N;;;;; +189D1;TANGUT COMPONENT-466;Lo;0;L;;;;;N;;;;; +189D2;TANGUT COMPONENT-467;Lo;0;L;;;;;N;;;;; +189D3;TANGUT COMPONENT-468;Lo;0;L;;;;;N;;;;; +189D4;TANGUT COMPONENT-469;Lo;0;L;;;;;N;;;;; +189D5;TANGUT COMPONENT-470;Lo;0;L;;;;;N;;;;; +189D6;TANGUT COMPONENT-471;Lo;0;L;;;;;N;;;;; +189D7;TANGUT COMPONENT-472;Lo;0;L;;;;;N;;;;; +189D8;TANGUT COMPONENT-473;Lo;0;L;;;;;N;;;;; +189D9;TANGUT COMPONENT-474;Lo;0;L;;;;;N;;;;; +189DA;TANGUT COMPONENT-475;Lo;0;L;;;;;N;;;;; +189DB;TANGUT COMPONENT-476;Lo;0;L;;;;;N;;;;; +189DC;TANGUT COMPONENT-477;Lo;0;L;;;;;N;;;;; +189DD;TANGUT COMPONENT-478;Lo;0;L;;;;;N;;;;; +189DE;TANGUT COMPONENT-479;Lo;0;L;;;;;N;;;;; +189DF;TANGUT COMPONENT-480;Lo;0;L;;;;;N;;;;; +189E0;TANGUT COMPONENT-481;Lo;0;L;;;;;N;;;;; +189E1;TANGUT COMPONENT-482;Lo;0;L;;;;;N;;;;; +189E2;TANGUT COMPONENT-483;Lo;0;L;;;;;N;;;;; +189E3;TANGUT COMPONENT-484;Lo;0;L;;;;;N;;;;; +189E4;TANGUT COMPONENT-485;Lo;0;L;;;;;N;;;;; +189E5;TANGUT COMPONENT-486;Lo;0;L;;;;;N;;;;; +189E6;TANGUT COMPONENT-487;Lo;0;L;;;;;N;;;;; +189E7;TANGUT COMPONENT-488;Lo;0;L;;;;;N;;;;; +189E8;TANGUT COMPONENT-489;Lo;0;L;;;;;N;;;;; +189E9;TANGUT COMPONENT-490;Lo;0;L;;;;;N;;;;; +189EA;TANGUT COMPONENT-491;Lo;0;L;;;;;N;;;;; +189EB;TANGUT COMPONENT-492;Lo;0;L;;;;;N;;;;; +189EC;TANGUT COMPONENT-493;Lo;0;L;;;;;N;;;;; +189ED;TANGUT COMPONENT-494;Lo;0;L;;;;;N;;;;; +189EE;TANGUT COMPONENT-495;Lo;0;L;;;;;N;;;;; +189EF;TANGUT COMPONENT-496;Lo;0;L;;;;;N;;;;; +189F0;TANGUT COMPONENT-497;Lo;0;L;;;;;N;;;;; +189F1;TANGUT COMPONENT-498;Lo;0;L;;;;;N;;;;; +189F2;TANGUT COMPONENT-499;Lo;0;L;;;;;N;;;;; +189F3;TANGUT COMPONENT-500;Lo;0;L;;;;;N;;;;; +189F4;TANGUT COMPONENT-501;Lo;0;L;;;;;N;;;;; +189F5;TANGUT COMPONENT-502;Lo;0;L;;;;;N;;;;; +189F6;TANGUT COMPONENT-503;Lo;0;L;;;;;N;;;;; +189F7;TANGUT COMPONENT-504;Lo;0;L;;;;;N;;;;; +189F8;TANGUT COMPONENT-505;Lo;0;L;;;;;N;;;;; +189F9;TANGUT COMPONENT-506;Lo;0;L;;;;;N;;;;; +189FA;TANGUT COMPONENT-507;Lo;0;L;;;;;N;;;;; +189FB;TANGUT COMPONENT-508;Lo;0;L;;;;;N;;;;; +189FC;TANGUT COMPONENT-509;Lo;0;L;;;;;N;;;;; +189FD;TANGUT COMPONENT-510;Lo;0;L;;;;;N;;;;; +189FE;TANGUT COMPONENT-511;Lo;0;L;;;;;N;;;;; +189FF;TANGUT COMPONENT-512;Lo;0;L;;;;;N;;;;; +18A00;TANGUT COMPONENT-513;Lo;0;L;;;;;N;;;;; +18A01;TANGUT COMPONENT-514;Lo;0;L;;;;;N;;;;; +18A02;TANGUT COMPONENT-515;Lo;0;L;;;;;N;;;;; +18A03;TANGUT COMPONENT-516;Lo;0;L;;;;;N;;;;; +18A04;TANGUT COMPONENT-517;Lo;0;L;;;;;N;;;;; +18A05;TANGUT COMPONENT-518;Lo;0;L;;;;;N;;;;; +18A06;TANGUT COMPONENT-519;Lo;0;L;;;;;N;;;;; +18A07;TANGUT COMPONENT-520;Lo;0;L;;;;;N;;;;; +18A08;TANGUT COMPONENT-521;Lo;0;L;;;;;N;;;;; +18A09;TANGUT COMPONENT-522;Lo;0;L;;;;;N;;;;; +18A0A;TANGUT COMPONENT-523;Lo;0;L;;;;;N;;;;; +18A0B;TANGUT COMPONENT-524;Lo;0;L;;;;;N;;;;; +18A0C;TANGUT COMPONENT-525;Lo;0;L;;;;;N;;;;; +18A0D;TANGUT COMPONENT-526;Lo;0;L;;;;;N;;;;; +18A0E;TANGUT COMPONENT-527;Lo;0;L;;;;;N;;;;; +18A0F;TANGUT COMPONENT-528;Lo;0;L;;;;;N;;;;; +18A10;TANGUT COMPONENT-529;Lo;0;L;;;;;N;;;;; +18A11;TANGUT COMPONENT-530;Lo;0;L;;;;;N;;;;; +18A12;TANGUT COMPONENT-531;Lo;0;L;;;;;N;;;;; +18A13;TANGUT COMPONENT-532;Lo;0;L;;;;;N;;;;; +18A14;TANGUT COMPONENT-533;Lo;0;L;;;;;N;;;;; +18A15;TANGUT COMPONENT-534;Lo;0;L;;;;;N;;;;; +18A16;TANGUT COMPONENT-535;Lo;0;L;;;;;N;;;;; +18A17;TANGUT COMPONENT-536;Lo;0;L;;;;;N;;;;; +18A18;TANGUT COMPONENT-537;Lo;0;L;;;;;N;;;;; +18A19;TANGUT COMPONENT-538;Lo;0;L;;;;;N;;;;; +18A1A;TANGUT COMPONENT-539;Lo;0;L;;;;;N;;;;; +18A1B;TANGUT COMPONENT-540;Lo;0;L;;;;;N;;;;; +18A1C;TANGUT COMPONENT-541;Lo;0;L;;;;;N;;;;; +18A1D;TANGUT COMPONENT-542;Lo;0;L;;;;;N;;;;; +18A1E;TANGUT COMPONENT-543;Lo;0;L;;;;;N;;;;; +18A1F;TANGUT COMPONENT-544;Lo;0;L;;;;;N;;;;; +18A20;TANGUT COMPONENT-545;Lo;0;L;;;;;N;;;;; +18A21;TANGUT COMPONENT-546;Lo;0;L;;;;;N;;;;; +18A22;TANGUT COMPONENT-547;Lo;0;L;;;;;N;;;;; +18A23;TANGUT COMPONENT-548;Lo;0;L;;;;;N;;;;; +18A24;TANGUT COMPONENT-549;Lo;0;L;;;;;N;;;;; +18A25;TANGUT COMPONENT-550;Lo;0;L;;;;;N;;;;; +18A26;TANGUT COMPONENT-551;Lo;0;L;;;;;N;;;;; +18A27;TANGUT COMPONENT-552;Lo;0;L;;;;;N;;;;; +18A28;TANGUT COMPONENT-553;Lo;0;L;;;;;N;;;;; +18A29;TANGUT COMPONENT-554;Lo;0;L;;;;;N;;;;; +18A2A;TANGUT COMPONENT-555;Lo;0;L;;;;;N;;;;; +18A2B;TANGUT COMPONENT-556;Lo;0;L;;;;;N;;;;; +18A2C;TANGUT COMPONENT-557;Lo;0;L;;;;;N;;;;; +18A2D;TANGUT COMPONENT-558;Lo;0;L;;;;;N;;;;; +18A2E;TANGUT COMPONENT-559;Lo;0;L;;;;;N;;;;; +18A2F;TANGUT COMPONENT-560;Lo;0;L;;;;;N;;;;; +18A30;TANGUT COMPONENT-561;Lo;0;L;;;;;N;;;;; +18A31;TANGUT COMPONENT-562;Lo;0;L;;;;;N;;;;; +18A32;TANGUT COMPONENT-563;Lo;0;L;;;;;N;;;;; +18A33;TANGUT COMPONENT-564;Lo;0;L;;;;;N;;;;; +18A34;TANGUT COMPONENT-565;Lo;0;L;;;;;N;;;;; +18A35;TANGUT COMPONENT-566;Lo;0;L;;;;;N;;;;; +18A36;TANGUT COMPONENT-567;Lo;0;L;;;;;N;;;;; +18A37;TANGUT COMPONENT-568;Lo;0;L;;;;;N;;;;; +18A38;TANGUT COMPONENT-569;Lo;0;L;;;;;N;;;;; +18A39;TANGUT COMPONENT-570;Lo;0;L;;;;;N;;;;; +18A3A;TANGUT COMPONENT-571;Lo;0;L;;;;;N;;;;; +18A3B;TANGUT COMPONENT-572;Lo;0;L;;;;;N;;;;; +18A3C;TANGUT COMPONENT-573;Lo;0;L;;;;;N;;;;; +18A3D;TANGUT COMPONENT-574;Lo;0;L;;;;;N;;;;; +18A3E;TANGUT COMPONENT-575;Lo;0;L;;;;;N;;;;; +18A3F;TANGUT COMPONENT-576;Lo;0;L;;;;;N;;;;; +18A40;TANGUT COMPONENT-577;Lo;0;L;;;;;N;;;;; +18A41;TANGUT COMPONENT-578;Lo;0;L;;;;;N;;;;; +18A42;TANGUT COMPONENT-579;Lo;0;L;;;;;N;;;;; +18A43;TANGUT COMPONENT-580;Lo;0;L;;;;;N;;;;; +18A44;TANGUT COMPONENT-581;Lo;0;L;;;;;N;;;;; +18A45;TANGUT COMPONENT-582;Lo;0;L;;;;;N;;;;; +18A46;TANGUT COMPONENT-583;Lo;0;L;;;;;N;;;;; +18A47;TANGUT COMPONENT-584;Lo;0;L;;;;;N;;;;; +18A48;TANGUT COMPONENT-585;Lo;0;L;;;;;N;;;;; +18A49;TANGUT COMPONENT-586;Lo;0;L;;;;;N;;;;; +18A4A;TANGUT COMPONENT-587;Lo;0;L;;;;;N;;;;; +18A4B;TANGUT COMPONENT-588;Lo;0;L;;;;;N;;;;; +18A4C;TANGUT COMPONENT-589;Lo;0;L;;;;;N;;;;; +18A4D;TANGUT COMPONENT-590;Lo;0;L;;;;;N;;;;; +18A4E;TANGUT COMPONENT-591;Lo;0;L;;;;;N;;;;; +18A4F;TANGUT COMPONENT-592;Lo;0;L;;;;;N;;;;; +18A50;TANGUT COMPONENT-593;Lo;0;L;;;;;N;;;;; +18A51;TANGUT COMPONENT-594;Lo;0;L;;;;;N;;;;; +18A52;TANGUT COMPONENT-595;Lo;0;L;;;;;N;;;;; +18A53;TANGUT COMPONENT-596;Lo;0;L;;;;;N;;;;; +18A54;TANGUT COMPONENT-597;Lo;0;L;;;;;N;;;;; +18A55;TANGUT COMPONENT-598;Lo;0;L;;;;;N;;;;; +18A56;TANGUT COMPONENT-599;Lo;0;L;;;;;N;;;;; +18A57;TANGUT COMPONENT-600;Lo;0;L;;;;;N;;;;; +18A58;TANGUT COMPONENT-601;Lo;0;L;;;;;N;;;;; +18A59;TANGUT COMPONENT-602;Lo;0;L;;;;;N;;;;; +18A5A;TANGUT COMPONENT-603;Lo;0;L;;;;;N;;;;; +18A5B;TANGUT COMPONENT-604;Lo;0;L;;;;;N;;;;; +18A5C;TANGUT COMPONENT-605;Lo;0;L;;;;;N;;;;; +18A5D;TANGUT COMPONENT-606;Lo;0;L;;;;;N;;;;; +18A5E;TANGUT COMPONENT-607;Lo;0;L;;;;;N;;;;; +18A5F;TANGUT COMPONENT-608;Lo;0;L;;;;;N;;;;; +18A60;TANGUT COMPONENT-609;Lo;0;L;;;;;N;;;;; +18A61;TANGUT COMPONENT-610;Lo;0;L;;;;;N;;;;; +18A62;TANGUT COMPONENT-611;Lo;0;L;;;;;N;;;;; +18A63;TANGUT COMPONENT-612;Lo;0;L;;;;;N;;;;; +18A64;TANGUT COMPONENT-613;Lo;0;L;;;;;N;;;;; +18A65;TANGUT COMPONENT-614;Lo;0;L;;;;;N;;;;; +18A66;TANGUT COMPONENT-615;Lo;0;L;;;;;N;;;;; +18A67;TANGUT COMPONENT-616;Lo;0;L;;;;;N;;;;; +18A68;TANGUT COMPONENT-617;Lo;0;L;;;;;N;;;;; +18A69;TANGUT COMPONENT-618;Lo;0;L;;;;;N;;;;; +18A6A;TANGUT COMPONENT-619;Lo;0;L;;;;;N;;;;; +18A6B;TANGUT COMPONENT-620;Lo;0;L;;;;;N;;;;; +18A6C;TANGUT COMPONENT-621;Lo;0;L;;;;;N;;;;; +18A6D;TANGUT COMPONENT-622;Lo;0;L;;;;;N;;;;; +18A6E;TANGUT COMPONENT-623;Lo;0;L;;;;;N;;;;; +18A6F;TANGUT COMPONENT-624;Lo;0;L;;;;;N;;;;; +18A70;TANGUT COMPONENT-625;Lo;0;L;;;;;N;;;;; +18A71;TANGUT COMPONENT-626;Lo;0;L;;;;;N;;;;; +18A72;TANGUT COMPONENT-627;Lo;0;L;;;;;N;;;;; +18A73;TANGUT COMPONENT-628;Lo;0;L;;;;;N;;;;; +18A74;TANGUT COMPONENT-629;Lo;0;L;;;;;N;;;;; +18A75;TANGUT COMPONENT-630;Lo;0;L;;;;;N;;;;; +18A76;TANGUT COMPONENT-631;Lo;0;L;;;;;N;;;;; +18A77;TANGUT COMPONENT-632;Lo;0;L;;;;;N;;;;; +18A78;TANGUT COMPONENT-633;Lo;0;L;;;;;N;;;;; +18A79;TANGUT COMPONENT-634;Lo;0;L;;;;;N;;;;; +18A7A;TANGUT COMPONENT-635;Lo;0;L;;;;;N;;;;; +18A7B;TANGUT COMPONENT-636;Lo;0;L;;;;;N;;;;; +18A7C;TANGUT COMPONENT-637;Lo;0;L;;;;;N;;;;; +18A7D;TANGUT COMPONENT-638;Lo;0;L;;;;;N;;;;; +18A7E;TANGUT COMPONENT-639;Lo;0;L;;;;;N;;;;; +18A7F;TANGUT COMPONENT-640;Lo;0;L;;;;;N;;;;; +18A80;TANGUT COMPONENT-641;Lo;0;L;;;;;N;;;;; +18A81;TANGUT COMPONENT-642;Lo;0;L;;;;;N;;;;; +18A82;TANGUT COMPONENT-643;Lo;0;L;;;;;N;;;;; +18A83;TANGUT COMPONENT-644;Lo;0;L;;;;;N;;;;; +18A84;TANGUT COMPONENT-645;Lo;0;L;;;;;N;;;;; +18A85;TANGUT COMPONENT-646;Lo;0;L;;;;;N;;;;; +18A86;TANGUT COMPONENT-647;Lo;0;L;;;;;N;;;;; +18A87;TANGUT COMPONENT-648;Lo;0;L;;;;;N;;;;; +18A88;TANGUT COMPONENT-649;Lo;0;L;;;;;N;;;;; +18A89;TANGUT COMPONENT-650;Lo;0;L;;;;;N;;;;; +18A8A;TANGUT COMPONENT-651;Lo;0;L;;;;;N;;;;; +18A8B;TANGUT COMPONENT-652;Lo;0;L;;;;;N;;;;; +18A8C;TANGUT COMPONENT-653;Lo;0;L;;;;;N;;;;; +18A8D;TANGUT COMPONENT-654;Lo;0;L;;;;;N;;;;; +18A8E;TANGUT COMPONENT-655;Lo;0;L;;;;;N;;;;; +18A8F;TANGUT COMPONENT-656;Lo;0;L;;;;;N;;;;; +18A90;TANGUT COMPONENT-657;Lo;0;L;;;;;N;;;;; +18A91;TANGUT COMPONENT-658;Lo;0;L;;;;;N;;;;; +18A92;TANGUT COMPONENT-659;Lo;0;L;;;;;N;;;;; +18A93;TANGUT COMPONENT-660;Lo;0;L;;;;;N;;;;; +18A94;TANGUT COMPONENT-661;Lo;0;L;;;;;N;;;;; +18A95;TANGUT COMPONENT-662;Lo;0;L;;;;;N;;;;; +18A96;TANGUT COMPONENT-663;Lo;0;L;;;;;N;;;;; +18A97;TANGUT COMPONENT-664;Lo;0;L;;;;;N;;;;; +18A98;TANGUT COMPONENT-665;Lo;0;L;;;;;N;;;;; +18A99;TANGUT COMPONENT-666;Lo;0;L;;;;;N;;;;; +18A9A;TANGUT COMPONENT-667;Lo;0;L;;;;;N;;;;; +18A9B;TANGUT COMPONENT-668;Lo;0;L;;;;;N;;;;; +18A9C;TANGUT COMPONENT-669;Lo;0;L;;;;;N;;;;; +18A9D;TANGUT COMPONENT-670;Lo;0;L;;;;;N;;;;; +18A9E;TANGUT COMPONENT-671;Lo;0;L;;;;;N;;;;; +18A9F;TANGUT COMPONENT-672;Lo;0;L;;;;;N;;;;; +18AA0;TANGUT COMPONENT-673;Lo;0;L;;;;;N;;;;; +18AA1;TANGUT COMPONENT-674;Lo;0;L;;;;;N;;;;; +18AA2;TANGUT COMPONENT-675;Lo;0;L;;;;;N;;;;; +18AA3;TANGUT COMPONENT-676;Lo;0;L;;;;;N;;;;; +18AA4;TANGUT COMPONENT-677;Lo;0;L;;;;;N;;;;; +18AA5;TANGUT COMPONENT-678;Lo;0;L;;;;;N;;;;; +18AA6;TANGUT COMPONENT-679;Lo;0;L;;;;;N;;;;; +18AA7;TANGUT COMPONENT-680;Lo;0;L;;;;;N;;;;; +18AA8;TANGUT COMPONENT-681;Lo;0;L;;;;;N;;;;; +18AA9;TANGUT COMPONENT-682;Lo;0;L;;;;;N;;;;; +18AAA;TANGUT COMPONENT-683;Lo;0;L;;;;;N;;;;; +18AAB;TANGUT COMPONENT-684;Lo;0;L;;;;;N;;;;; +18AAC;TANGUT COMPONENT-685;Lo;0;L;;;;;N;;;;; +18AAD;TANGUT COMPONENT-686;Lo;0;L;;;;;N;;;;; +18AAE;TANGUT COMPONENT-687;Lo;0;L;;;;;N;;;;; +18AAF;TANGUT COMPONENT-688;Lo;0;L;;;;;N;;;;; +18AB0;TANGUT COMPONENT-689;Lo;0;L;;;;;N;;;;; +18AB1;TANGUT COMPONENT-690;Lo;0;L;;;;;N;;;;; +18AB2;TANGUT COMPONENT-691;Lo;0;L;;;;;N;;;;; +18AB3;TANGUT COMPONENT-692;Lo;0;L;;;;;N;;;;; +18AB4;TANGUT COMPONENT-693;Lo;0;L;;;;;N;;;;; +18AB5;TANGUT COMPONENT-694;Lo;0;L;;;;;N;;;;; +18AB6;TANGUT COMPONENT-695;Lo;0;L;;;;;N;;;;; +18AB7;TANGUT COMPONENT-696;Lo;0;L;;;;;N;;;;; +18AB8;TANGUT COMPONENT-697;Lo;0;L;;;;;N;;;;; +18AB9;TANGUT COMPONENT-698;Lo;0;L;;;;;N;;;;; +18ABA;TANGUT COMPONENT-699;Lo;0;L;;;;;N;;;;; +18ABB;TANGUT COMPONENT-700;Lo;0;L;;;;;N;;;;; +18ABC;TANGUT COMPONENT-701;Lo;0;L;;;;;N;;;;; +18ABD;TANGUT COMPONENT-702;Lo;0;L;;;;;N;;;;; +18ABE;TANGUT COMPONENT-703;Lo;0;L;;;;;N;;;;; +18ABF;TANGUT COMPONENT-704;Lo;0;L;;;;;N;;;;; +18AC0;TANGUT COMPONENT-705;Lo;0;L;;;;;N;;;;; +18AC1;TANGUT COMPONENT-706;Lo;0;L;;;;;N;;;;; +18AC2;TANGUT COMPONENT-707;Lo;0;L;;;;;N;;;;; +18AC3;TANGUT COMPONENT-708;Lo;0;L;;;;;N;;;;; +18AC4;TANGUT COMPONENT-709;Lo;0;L;;;;;N;;;;; +18AC5;TANGUT COMPONENT-710;Lo;0;L;;;;;N;;;;; +18AC6;TANGUT COMPONENT-711;Lo;0;L;;;;;N;;;;; +18AC7;TANGUT COMPONENT-712;Lo;0;L;;;;;N;;;;; +18AC8;TANGUT COMPONENT-713;Lo;0;L;;;;;N;;;;; +18AC9;TANGUT COMPONENT-714;Lo;0;L;;;;;N;;;;; +18ACA;TANGUT COMPONENT-715;Lo;0;L;;;;;N;;;;; +18ACB;TANGUT COMPONENT-716;Lo;0;L;;;;;N;;;;; +18ACC;TANGUT COMPONENT-717;Lo;0;L;;;;;N;;;;; +18ACD;TANGUT COMPONENT-718;Lo;0;L;;;;;N;;;;; +18ACE;TANGUT COMPONENT-719;Lo;0;L;;;;;N;;;;; +18ACF;TANGUT COMPONENT-720;Lo;0;L;;;;;N;;;;; +18AD0;TANGUT COMPONENT-721;Lo;0;L;;;;;N;;;;; +18AD1;TANGUT COMPONENT-722;Lo;0;L;;;;;N;;;;; +18AD2;TANGUT COMPONENT-723;Lo;0;L;;;;;N;;;;; +18AD3;TANGUT COMPONENT-724;Lo;0;L;;;;;N;;;;; +18AD4;TANGUT COMPONENT-725;Lo;0;L;;;;;N;;;;; +18AD5;TANGUT COMPONENT-726;Lo;0;L;;;;;N;;;;; +18AD6;TANGUT COMPONENT-727;Lo;0;L;;;;;N;;;;; +18AD7;TANGUT COMPONENT-728;Lo;0;L;;;;;N;;;;; +18AD8;TANGUT COMPONENT-729;Lo;0;L;;;;;N;;;;; +18AD9;TANGUT COMPONENT-730;Lo;0;L;;;;;N;;;;; +18ADA;TANGUT COMPONENT-731;Lo;0;L;;;;;N;;;;; +18ADB;TANGUT COMPONENT-732;Lo;0;L;;;;;N;;;;; +18ADC;TANGUT COMPONENT-733;Lo;0;L;;;;;N;;;;; +18ADD;TANGUT COMPONENT-734;Lo;0;L;;;;;N;;;;; +18ADE;TANGUT COMPONENT-735;Lo;0;L;;;;;N;;;;; +18ADF;TANGUT COMPONENT-736;Lo;0;L;;;;;N;;;;; +18AE0;TANGUT COMPONENT-737;Lo;0;L;;;;;N;;;;; +18AE1;TANGUT COMPONENT-738;Lo;0;L;;;;;N;;;;; +18AE2;TANGUT COMPONENT-739;Lo;0;L;;;;;N;;;;; +18AE3;TANGUT COMPONENT-740;Lo;0;L;;;;;N;;;;; +18AE4;TANGUT COMPONENT-741;Lo;0;L;;;;;N;;;;; +18AE5;TANGUT COMPONENT-742;Lo;0;L;;;;;N;;;;; +18AE6;TANGUT COMPONENT-743;Lo;0;L;;;;;N;;;;; +18AE7;TANGUT COMPONENT-744;Lo;0;L;;;;;N;;;;; +18AE8;TANGUT COMPONENT-745;Lo;0;L;;;;;N;;;;; +18AE9;TANGUT COMPONENT-746;Lo;0;L;;;;;N;;;;; +18AEA;TANGUT COMPONENT-747;Lo;0;L;;;;;N;;;;; +18AEB;TANGUT COMPONENT-748;Lo;0;L;;;;;N;;;;; +18AEC;TANGUT COMPONENT-749;Lo;0;L;;;;;N;;;;; +18AED;TANGUT COMPONENT-750;Lo;0;L;;;;;N;;;;; +18AEE;TANGUT COMPONENT-751;Lo;0;L;;;;;N;;;;; +18AEF;TANGUT COMPONENT-752;Lo;0;L;;;;;N;;;;; +18AF0;TANGUT COMPONENT-753;Lo;0;L;;;;;N;;;;; +18AF1;TANGUT COMPONENT-754;Lo;0;L;;;;;N;;;;; +18AF2;TANGUT COMPONENT-755;Lo;0;L;;;;;N;;;;; 1B000;KATAKANA LETTER ARCHAIC E;Lo;0;L;;;;;N;;;;; 1B001;HIRAGANA LETTER ARCHAIC YE;Lo;0;L;;;;;N;;;;; +1B002;HENTAIGANA LETTER A-1;Lo;0;L;;;;;N;;;;; +1B003;HENTAIGANA LETTER A-2;Lo;0;L;;;;;N;;;;; +1B004;HENTAIGANA LETTER A-3;Lo;0;L;;;;;N;;;;; +1B005;HENTAIGANA LETTER A-WO;Lo;0;L;;;;;N;;;;; +1B006;HENTAIGANA LETTER I-1;Lo;0;L;;;;;N;;;;; +1B007;HENTAIGANA LETTER I-2;Lo;0;L;;;;;N;;;;; +1B008;HENTAIGANA LETTER I-3;Lo;0;L;;;;;N;;;;; +1B009;HENTAIGANA LETTER I-4;Lo;0;L;;;;;N;;;;; +1B00A;HENTAIGANA LETTER U-1;Lo;0;L;;;;;N;;;;; +1B00B;HENTAIGANA LETTER U-2;Lo;0;L;;;;;N;;;;; +1B00C;HENTAIGANA LETTER U-3;Lo;0;L;;;;;N;;;;; +1B00D;HENTAIGANA LETTER U-4;Lo;0;L;;;;;N;;;;; +1B00E;HENTAIGANA LETTER U-5;Lo;0;L;;;;;N;;;;; +1B00F;HENTAIGANA LETTER E-2;Lo;0;L;;;;;N;;;;; +1B010;HENTAIGANA LETTER E-3;Lo;0;L;;;;;N;;;;; +1B011;HENTAIGANA LETTER E-4;Lo;0;L;;;;;N;;;;; +1B012;HENTAIGANA LETTER E-5;Lo;0;L;;;;;N;;;;; +1B013;HENTAIGANA LETTER E-6;Lo;0;L;;;;;N;;;;; +1B014;HENTAIGANA LETTER O-1;Lo;0;L;;;;;N;;;;; +1B015;HENTAIGANA LETTER O-2;Lo;0;L;;;;;N;;;;; +1B016;HENTAIGANA LETTER O-3;Lo;0;L;;;;;N;;;;; +1B017;HENTAIGANA LETTER KA-1;Lo;0;L;;;;;N;;;;; +1B018;HENTAIGANA LETTER KA-2;Lo;0;L;;;;;N;;;;; +1B019;HENTAIGANA LETTER KA-3;Lo;0;L;;;;;N;;;;; +1B01A;HENTAIGANA LETTER KA-4;Lo;0;L;;;;;N;;;;; +1B01B;HENTAIGANA LETTER KA-5;Lo;0;L;;;;;N;;;;; +1B01C;HENTAIGANA LETTER KA-6;Lo;0;L;;;;;N;;;;; +1B01D;HENTAIGANA LETTER KA-7;Lo;0;L;;;;;N;;;;; +1B01E;HENTAIGANA LETTER KA-8;Lo;0;L;;;;;N;;;;; +1B01F;HENTAIGANA LETTER KA-9;Lo;0;L;;;;;N;;;;; +1B020;HENTAIGANA LETTER KA-10;Lo;0;L;;;;;N;;;;; +1B021;HENTAIGANA LETTER KA-11;Lo;0;L;;;;;N;;;;; +1B022;HENTAIGANA LETTER KA-KE;Lo;0;L;;;;;N;;;;; +1B023;HENTAIGANA LETTER KI-1;Lo;0;L;;;;;N;;;;; +1B024;HENTAIGANA LETTER KI-2;Lo;0;L;;;;;N;;;;; +1B025;HENTAIGANA LETTER KI-3;Lo;0;L;;;;;N;;;;; +1B026;HENTAIGANA LETTER KI-4;Lo;0;L;;;;;N;;;;; +1B027;HENTAIGANA LETTER KI-5;Lo;0;L;;;;;N;;;;; +1B028;HENTAIGANA LETTER KI-6;Lo;0;L;;;;;N;;;;; +1B029;HENTAIGANA LETTER KI-7;Lo;0;L;;;;;N;;;;; +1B02A;HENTAIGANA LETTER KI-8;Lo;0;L;;;;;N;;;;; +1B02B;HENTAIGANA LETTER KU-1;Lo;0;L;;;;;N;;;;; +1B02C;HENTAIGANA LETTER KU-2;Lo;0;L;;;;;N;;;;; +1B02D;HENTAIGANA LETTER KU-3;Lo;0;L;;;;;N;;;;; +1B02E;HENTAIGANA LETTER KU-4;Lo;0;L;;;;;N;;;;; +1B02F;HENTAIGANA LETTER KU-5;Lo;0;L;;;;;N;;;;; +1B030;HENTAIGANA LETTER KU-6;Lo;0;L;;;;;N;;;;; +1B031;HENTAIGANA LETTER KU-7;Lo;0;L;;;;;N;;;;; +1B032;HENTAIGANA LETTER KE-1;Lo;0;L;;;;;N;;;;; +1B033;HENTAIGANA LETTER KE-2;Lo;0;L;;;;;N;;;;; +1B034;HENTAIGANA LETTER KE-3;Lo;0;L;;;;;N;;;;; +1B035;HENTAIGANA LETTER KE-4;Lo;0;L;;;;;N;;;;; +1B036;HENTAIGANA LETTER KE-5;Lo;0;L;;;;;N;;;;; +1B037;HENTAIGANA LETTER KE-6;Lo;0;L;;;;;N;;;;; +1B038;HENTAIGANA LETTER KO-1;Lo;0;L;;;;;N;;;;; +1B039;HENTAIGANA LETTER KO-2;Lo;0;L;;;;;N;;;;; +1B03A;HENTAIGANA LETTER KO-3;Lo;0;L;;;;;N;;;;; +1B03B;HENTAIGANA LETTER KO-KI;Lo;0;L;;;;;N;;;;; +1B03C;HENTAIGANA LETTER SA-1;Lo;0;L;;;;;N;;;;; +1B03D;HENTAIGANA LETTER SA-2;Lo;0;L;;;;;N;;;;; +1B03E;HENTAIGANA LETTER SA-3;Lo;0;L;;;;;N;;;;; +1B03F;HENTAIGANA LETTER SA-4;Lo;0;L;;;;;N;;;;; +1B040;HENTAIGANA LETTER SA-5;Lo;0;L;;;;;N;;;;; +1B041;HENTAIGANA LETTER SA-6;Lo;0;L;;;;;N;;;;; +1B042;HENTAIGANA LETTER SA-7;Lo;0;L;;;;;N;;;;; +1B043;HENTAIGANA LETTER SA-8;Lo;0;L;;;;;N;;;;; +1B044;HENTAIGANA LETTER SI-1;Lo;0;L;;;;;N;;;;; +1B045;HENTAIGANA LETTER SI-2;Lo;0;L;;;;;N;;;;; +1B046;HENTAIGANA LETTER SI-3;Lo;0;L;;;;;N;;;;; +1B047;HENTAIGANA LETTER SI-4;Lo;0;L;;;;;N;;;;; +1B048;HENTAIGANA LETTER SI-5;Lo;0;L;;;;;N;;;;; +1B049;HENTAIGANA LETTER SI-6;Lo;0;L;;;;;N;;;;; +1B04A;HENTAIGANA LETTER SU-1;Lo;0;L;;;;;N;;;;; +1B04B;HENTAIGANA LETTER SU-2;Lo;0;L;;;;;N;;;;; +1B04C;HENTAIGANA LETTER SU-3;Lo;0;L;;;;;N;;;;; +1B04D;HENTAIGANA LETTER SU-4;Lo;0;L;;;;;N;;;;; +1B04E;HENTAIGANA LETTER SU-5;Lo;0;L;;;;;N;;;;; +1B04F;HENTAIGANA LETTER SU-6;Lo;0;L;;;;;N;;;;; +1B050;HENTAIGANA LETTER SU-7;Lo;0;L;;;;;N;;;;; +1B051;HENTAIGANA LETTER SU-8;Lo;0;L;;;;;N;;;;; +1B052;HENTAIGANA LETTER SE-1;Lo;0;L;;;;;N;;;;; +1B053;HENTAIGANA LETTER SE-2;Lo;0;L;;;;;N;;;;; +1B054;HENTAIGANA LETTER SE-3;Lo;0;L;;;;;N;;;;; +1B055;HENTAIGANA LETTER SE-4;Lo;0;L;;;;;N;;;;; +1B056;HENTAIGANA LETTER SE-5;Lo;0;L;;;;;N;;;;; +1B057;HENTAIGANA LETTER SO-1;Lo;0;L;;;;;N;;;;; +1B058;HENTAIGANA LETTER SO-2;Lo;0;L;;;;;N;;;;; +1B059;HENTAIGANA LETTER SO-3;Lo;0;L;;;;;N;;;;; +1B05A;HENTAIGANA LETTER SO-4;Lo;0;L;;;;;N;;;;; +1B05B;HENTAIGANA LETTER SO-5;Lo;0;L;;;;;N;;;;; +1B05C;HENTAIGANA LETTER SO-6;Lo;0;L;;;;;N;;;;; +1B05D;HENTAIGANA LETTER SO-7;Lo;0;L;;;;;N;;;;; +1B05E;HENTAIGANA LETTER TA-1;Lo;0;L;;;;;N;;;;; +1B05F;HENTAIGANA LETTER TA-2;Lo;0;L;;;;;N;;;;; +1B060;HENTAIGANA LETTER TA-3;Lo;0;L;;;;;N;;;;; +1B061;HENTAIGANA LETTER TA-4;Lo;0;L;;;;;N;;;;; +1B062;HENTAIGANA LETTER TI-1;Lo;0;L;;;;;N;;;;; +1B063;HENTAIGANA LETTER TI-2;Lo;0;L;;;;;N;;;;; +1B064;HENTAIGANA LETTER TI-3;Lo;0;L;;;;;N;;;;; +1B065;HENTAIGANA LETTER TI-4;Lo;0;L;;;;;N;;;;; +1B066;HENTAIGANA LETTER TI-5;Lo;0;L;;;;;N;;;;; +1B067;HENTAIGANA LETTER TI-6;Lo;0;L;;;;;N;;;;; +1B068;HENTAIGANA LETTER TI-7;Lo;0;L;;;;;N;;;;; +1B069;HENTAIGANA LETTER TU-1;Lo;0;L;;;;;N;;;;; +1B06A;HENTAIGANA LETTER TU-2;Lo;0;L;;;;;N;;;;; +1B06B;HENTAIGANA LETTER TU-3;Lo;0;L;;;;;N;;;;; +1B06C;HENTAIGANA LETTER TU-4;Lo;0;L;;;;;N;;;;; +1B06D;HENTAIGANA LETTER TU-TO;Lo;0;L;;;;;N;;;;; +1B06E;HENTAIGANA LETTER TE-1;Lo;0;L;;;;;N;;;;; +1B06F;HENTAIGANA LETTER TE-2;Lo;0;L;;;;;N;;;;; +1B070;HENTAIGANA LETTER TE-3;Lo;0;L;;;;;N;;;;; +1B071;HENTAIGANA LETTER TE-4;Lo;0;L;;;;;N;;;;; +1B072;HENTAIGANA LETTER TE-5;Lo;0;L;;;;;N;;;;; +1B073;HENTAIGANA LETTER TE-6;Lo;0;L;;;;;N;;;;; +1B074;HENTAIGANA LETTER TE-7;Lo;0;L;;;;;N;;;;; +1B075;HENTAIGANA LETTER TE-8;Lo;0;L;;;;;N;;;;; +1B076;HENTAIGANA LETTER TE-9;Lo;0;L;;;;;N;;;;; +1B077;HENTAIGANA LETTER TO-1;Lo;0;L;;;;;N;;;;; +1B078;HENTAIGANA LETTER TO-2;Lo;0;L;;;;;N;;;;; +1B079;HENTAIGANA LETTER TO-3;Lo;0;L;;;;;N;;;;; +1B07A;HENTAIGANA LETTER TO-4;Lo;0;L;;;;;N;;;;; +1B07B;HENTAIGANA LETTER TO-5;Lo;0;L;;;;;N;;;;; +1B07C;HENTAIGANA LETTER TO-6;Lo;0;L;;;;;N;;;;; +1B07D;HENTAIGANA LETTER TO-RA;Lo;0;L;;;;;N;;;;; +1B07E;HENTAIGANA LETTER NA-1;Lo;0;L;;;;;N;;;;; +1B07F;HENTAIGANA LETTER NA-2;Lo;0;L;;;;;N;;;;; +1B080;HENTAIGANA LETTER NA-3;Lo;0;L;;;;;N;;;;; +1B081;HENTAIGANA LETTER NA-4;Lo;0;L;;;;;N;;;;; +1B082;HENTAIGANA LETTER NA-5;Lo;0;L;;;;;N;;;;; +1B083;HENTAIGANA LETTER NA-6;Lo;0;L;;;;;N;;;;; +1B084;HENTAIGANA LETTER NA-7;Lo;0;L;;;;;N;;;;; +1B085;HENTAIGANA LETTER NA-8;Lo;0;L;;;;;N;;;;; +1B086;HENTAIGANA LETTER NA-9;Lo;0;L;;;;;N;;;;; +1B087;HENTAIGANA LETTER NI-1;Lo;0;L;;;;;N;;;;; +1B088;HENTAIGANA LETTER NI-2;Lo;0;L;;;;;N;;;;; +1B089;HENTAIGANA LETTER NI-3;Lo;0;L;;;;;N;;;;; +1B08A;HENTAIGANA LETTER NI-4;Lo;0;L;;;;;N;;;;; +1B08B;HENTAIGANA LETTER NI-5;Lo;0;L;;;;;N;;;;; +1B08C;HENTAIGANA LETTER NI-6;Lo;0;L;;;;;N;;;;; +1B08D;HENTAIGANA LETTER NI-7;Lo;0;L;;;;;N;;;;; +1B08E;HENTAIGANA LETTER NI-TE;Lo;0;L;;;;;N;;;;; +1B08F;HENTAIGANA LETTER NU-1;Lo;0;L;;;;;N;;;;; +1B090;HENTAIGANA LETTER NU-2;Lo;0;L;;;;;N;;;;; +1B091;HENTAIGANA LETTER NU-3;Lo;0;L;;;;;N;;;;; +1B092;HENTAIGANA LETTER NE-1;Lo;0;L;;;;;N;;;;; +1B093;HENTAIGANA LETTER NE-2;Lo;0;L;;;;;N;;;;; +1B094;HENTAIGANA LETTER NE-3;Lo;0;L;;;;;N;;;;; +1B095;HENTAIGANA LETTER NE-4;Lo;0;L;;;;;N;;;;; +1B096;HENTAIGANA LETTER NE-5;Lo;0;L;;;;;N;;;;; +1B097;HENTAIGANA LETTER NE-6;Lo;0;L;;;;;N;;;;; +1B098;HENTAIGANA LETTER NE-KO;Lo;0;L;;;;;N;;;;; +1B099;HENTAIGANA LETTER NO-1;Lo;0;L;;;;;N;;;;; +1B09A;HENTAIGANA LETTER NO-2;Lo;0;L;;;;;N;;;;; +1B09B;HENTAIGANA LETTER NO-3;Lo;0;L;;;;;N;;;;; +1B09C;HENTAIGANA LETTER NO-4;Lo;0;L;;;;;N;;;;; +1B09D;HENTAIGANA LETTER NO-5;Lo;0;L;;;;;N;;;;; +1B09E;HENTAIGANA LETTER HA-1;Lo;0;L;;;;;N;;;;; +1B09F;HENTAIGANA LETTER HA-2;Lo;0;L;;;;;N;;;;; +1B0A0;HENTAIGANA LETTER HA-3;Lo;0;L;;;;;N;;;;; +1B0A1;HENTAIGANA LETTER HA-4;Lo;0;L;;;;;N;;;;; +1B0A2;HENTAIGANA LETTER HA-5;Lo;0;L;;;;;N;;;;; +1B0A3;HENTAIGANA LETTER HA-6;Lo;0;L;;;;;N;;;;; +1B0A4;HENTAIGANA LETTER HA-7;Lo;0;L;;;;;N;;;;; +1B0A5;HENTAIGANA LETTER HA-8;Lo;0;L;;;;;N;;;;; +1B0A6;HENTAIGANA LETTER HA-9;Lo;0;L;;;;;N;;;;; +1B0A7;HENTAIGANA LETTER HA-10;Lo;0;L;;;;;N;;;;; +1B0A8;HENTAIGANA LETTER HA-11;Lo;0;L;;;;;N;;;;; +1B0A9;HENTAIGANA LETTER HI-1;Lo;0;L;;;;;N;;;;; +1B0AA;HENTAIGANA LETTER HI-2;Lo;0;L;;;;;N;;;;; +1B0AB;HENTAIGANA LETTER HI-3;Lo;0;L;;;;;N;;;;; +1B0AC;HENTAIGANA LETTER HI-4;Lo;0;L;;;;;N;;;;; +1B0AD;HENTAIGANA LETTER HI-5;Lo;0;L;;;;;N;;;;; +1B0AE;HENTAIGANA LETTER HI-6;Lo;0;L;;;;;N;;;;; +1B0AF;HENTAIGANA LETTER HI-7;Lo;0;L;;;;;N;;;;; +1B0B0;HENTAIGANA LETTER HU-1;Lo;0;L;;;;;N;;;;; +1B0B1;HENTAIGANA LETTER HU-2;Lo;0;L;;;;;N;;;;; +1B0B2;HENTAIGANA LETTER HU-3;Lo;0;L;;;;;N;;;;; +1B0B3;HENTAIGANA LETTER HE-1;Lo;0;L;;;;;N;;;;; +1B0B4;HENTAIGANA LETTER HE-2;Lo;0;L;;;;;N;;;;; +1B0B5;HENTAIGANA LETTER HE-3;Lo;0;L;;;;;N;;;;; +1B0B6;HENTAIGANA LETTER HE-4;Lo;0;L;;;;;N;;;;; +1B0B7;HENTAIGANA LETTER HE-5;Lo;0;L;;;;;N;;;;; +1B0B8;HENTAIGANA LETTER HE-6;Lo;0;L;;;;;N;;;;; +1B0B9;HENTAIGANA LETTER HE-7;Lo;0;L;;;;;N;;;;; +1B0BA;HENTAIGANA LETTER HO-1;Lo;0;L;;;;;N;;;;; +1B0BB;HENTAIGANA LETTER HO-2;Lo;0;L;;;;;N;;;;; +1B0BC;HENTAIGANA LETTER HO-3;Lo;0;L;;;;;N;;;;; +1B0BD;HENTAIGANA LETTER HO-4;Lo;0;L;;;;;N;;;;; +1B0BE;HENTAIGANA LETTER HO-5;Lo;0;L;;;;;N;;;;; +1B0BF;HENTAIGANA LETTER HO-6;Lo;0;L;;;;;N;;;;; +1B0C0;HENTAIGANA LETTER HO-7;Lo;0;L;;;;;N;;;;; +1B0C1;HENTAIGANA LETTER HO-8;Lo;0;L;;;;;N;;;;; +1B0C2;HENTAIGANA LETTER MA-1;Lo;0;L;;;;;N;;;;; +1B0C3;HENTAIGANA LETTER MA-2;Lo;0;L;;;;;N;;;;; +1B0C4;HENTAIGANA LETTER MA-3;Lo;0;L;;;;;N;;;;; +1B0C5;HENTAIGANA LETTER MA-4;Lo;0;L;;;;;N;;;;; +1B0C6;HENTAIGANA LETTER MA-5;Lo;0;L;;;;;N;;;;; +1B0C7;HENTAIGANA LETTER MA-6;Lo;0;L;;;;;N;;;;; +1B0C8;HENTAIGANA LETTER MA-7;Lo;0;L;;;;;N;;;;; +1B0C9;HENTAIGANA LETTER MI-1;Lo;0;L;;;;;N;;;;; +1B0CA;HENTAIGANA LETTER MI-2;Lo;0;L;;;;;N;;;;; +1B0CB;HENTAIGANA LETTER MI-3;Lo;0;L;;;;;N;;;;; +1B0CC;HENTAIGANA LETTER MI-4;Lo;0;L;;;;;N;;;;; +1B0CD;HENTAIGANA LETTER MI-5;Lo;0;L;;;;;N;;;;; +1B0CE;HENTAIGANA LETTER MI-6;Lo;0;L;;;;;N;;;;; +1B0CF;HENTAIGANA LETTER MI-7;Lo;0;L;;;;;N;;;;; +1B0D0;HENTAIGANA LETTER MU-1;Lo;0;L;;;;;N;;;;; +1B0D1;HENTAIGANA LETTER MU-2;Lo;0;L;;;;;N;;;;; +1B0D2;HENTAIGANA LETTER MU-3;Lo;0;L;;;;;N;;;;; +1B0D3;HENTAIGANA LETTER MU-4;Lo;0;L;;;;;N;;;;; +1B0D4;HENTAIGANA LETTER ME-1;Lo;0;L;;;;;N;;;;; +1B0D5;HENTAIGANA LETTER ME-2;Lo;0;L;;;;;N;;;;; +1B0D6;HENTAIGANA LETTER ME-MA;Lo;0;L;;;;;N;;;;; +1B0D7;HENTAIGANA LETTER MO-1;Lo;0;L;;;;;N;;;;; +1B0D8;HENTAIGANA LETTER MO-2;Lo;0;L;;;;;N;;;;; +1B0D9;HENTAIGANA LETTER MO-3;Lo;0;L;;;;;N;;;;; +1B0DA;HENTAIGANA LETTER MO-4;Lo;0;L;;;;;N;;;;; +1B0DB;HENTAIGANA LETTER MO-5;Lo;0;L;;;;;N;;;;; +1B0DC;HENTAIGANA LETTER MO-6;Lo;0;L;;;;;N;;;;; +1B0DD;HENTAIGANA LETTER YA-1;Lo;0;L;;;;;N;;;;; +1B0DE;HENTAIGANA LETTER YA-2;Lo;0;L;;;;;N;;;;; +1B0DF;HENTAIGANA LETTER YA-3;Lo;0;L;;;;;N;;;;; +1B0E0;HENTAIGANA LETTER YA-4;Lo;0;L;;;;;N;;;;; +1B0E1;HENTAIGANA LETTER YA-5;Lo;0;L;;;;;N;;;;; +1B0E2;HENTAIGANA LETTER YA-YO;Lo;0;L;;;;;N;;;;; +1B0E3;HENTAIGANA LETTER YU-1;Lo;0;L;;;;;N;;;;; +1B0E4;HENTAIGANA LETTER YU-2;Lo;0;L;;;;;N;;;;; +1B0E5;HENTAIGANA LETTER YU-3;Lo;0;L;;;;;N;;;;; +1B0E6;HENTAIGANA LETTER YU-4;Lo;0;L;;;;;N;;;;; +1B0E7;HENTAIGANA LETTER YO-1;Lo;0;L;;;;;N;;;;; +1B0E8;HENTAIGANA LETTER YO-2;Lo;0;L;;;;;N;;;;; +1B0E9;HENTAIGANA LETTER YO-3;Lo;0;L;;;;;N;;;;; +1B0EA;HENTAIGANA LETTER YO-4;Lo;0;L;;;;;N;;;;; +1B0EB;HENTAIGANA LETTER YO-5;Lo;0;L;;;;;N;;;;; +1B0EC;HENTAIGANA LETTER YO-6;Lo;0;L;;;;;N;;;;; +1B0ED;HENTAIGANA LETTER RA-1;Lo;0;L;;;;;N;;;;; +1B0EE;HENTAIGANA LETTER RA-2;Lo;0;L;;;;;N;;;;; +1B0EF;HENTAIGANA LETTER RA-3;Lo;0;L;;;;;N;;;;; +1B0F0;HENTAIGANA LETTER RA-4;Lo;0;L;;;;;N;;;;; +1B0F1;HENTAIGANA LETTER RI-1;Lo;0;L;;;;;N;;;;; +1B0F2;HENTAIGANA LETTER RI-2;Lo;0;L;;;;;N;;;;; +1B0F3;HENTAIGANA LETTER RI-3;Lo;0;L;;;;;N;;;;; +1B0F4;HENTAIGANA LETTER RI-4;Lo;0;L;;;;;N;;;;; +1B0F5;HENTAIGANA LETTER RI-5;Lo;0;L;;;;;N;;;;; +1B0F6;HENTAIGANA LETTER RI-6;Lo;0;L;;;;;N;;;;; +1B0F7;HENTAIGANA LETTER RI-7;Lo;0;L;;;;;N;;;;; +1B0F8;HENTAIGANA LETTER RU-1;Lo;0;L;;;;;N;;;;; +1B0F9;HENTAIGANA LETTER RU-2;Lo;0;L;;;;;N;;;;; +1B0FA;HENTAIGANA LETTER RU-3;Lo;0;L;;;;;N;;;;; +1B0FB;HENTAIGANA LETTER RU-4;Lo;0;L;;;;;N;;;;; +1B0FC;HENTAIGANA LETTER RU-5;Lo;0;L;;;;;N;;;;; +1B0FD;HENTAIGANA LETTER RU-6;Lo;0;L;;;;;N;;;;; +1B0FE;HENTAIGANA LETTER RE-1;Lo;0;L;;;;;N;;;;; +1B0FF;HENTAIGANA LETTER RE-2;Lo;0;L;;;;;N;;;;; +1B100;HENTAIGANA LETTER RE-3;Lo;0;L;;;;;N;;;;; +1B101;HENTAIGANA LETTER RE-4;Lo;0;L;;;;;N;;;;; +1B102;HENTAIGANA LETTER RO-1;Lo;0;L;;;;;N;;;;; +1B103;HENTAIGANA LETTER RO-2;Lo;0;L;;;;;N;;;;; +1B104;HENTAIGANA LETTER RO-3;Lo;0;L;;;;;N;;;;; +1B105;HENTAIGANA LETTER RO-4;Lo;0;L;;;;;N;;;;; +1B106;HENTAIGANA LETTER RO-5;Lo;0;L;;;;;N;;;;; +1B107;HENTAIGANA LETTER RO-6;Lo;0;L;;;;;N;;;;; +1B108;HENTAIGANA LETTER WA-1;Lo;0;L;;;;;N;;;;; +1B109;HENTAIGANA LETTER WA-2;Lo;0;L;;;;;N;;;;; +1B10A;HENTAIGANA LETTER WA-3;Lo;0;L;;;;;N;;;;; +1B10B;HENTAIGANA LETTER WA-4;Lo;0;L;;;;;N;;;;; +1B10C;HENTAIGANA LETTER WA-5;Lo;0;L;;;;;N;;;;; +1B10D;HENTAIGANA LETTER WI-1;Lo;0;L;;;;;N;;;;; +1B10E;HENTAIGANA LETTER WI-2;Lo;0;L;;;;;N;;;;; +1B10F;HENTAIGANA LETTER WI-3;Lo;0;L;;;;;N;;;;; +1B110;HENTAIGANA LETTER WI-4;Lo;0;L;;;;;N;;;;; +1B111;HENTAIGANA LETTER WI-5;Lo;0;L;;;;;N;;;;; +1B112;HENTAIGANA LETTER WE-1;Lo;0;L;;;;;N;;;;; +1B113;HENTAIGANA LETTER WE-2;Lo;0;L;;;;;N;;;;; +1B114;HENTAIGANA LETTER WE-3;Lo;0;L;;;;;N;;;;; +1B115;HENTAIGANA LETTER WE-4;Lo;0;L;;;;;N;;;;; +1B116;HENTAIGANA LETTER WO-1;Lo;0;L;;;;;N;;;;; +1B117;HENTAIGANA LETTER WO-2;Lo;0;L;;;;;N;;;;; +1B118;HENTAIGANA LETTER WO-3;Lo;0;L;;;;;N;;;;; +1B119;HENTAIGANA LETTER WO-4;Lo;0;L;;;;;N;;;;; +1B11A;HENTAIGANA LETTER WO-5;Lo;0;L;;;;;N;;;;; +1B11B;HENTAIGANA LETTER WO-6;Lo;0;L;;;;;N;;;;; +1B11C;HENTAIGANA LETTER WO-7;Lo;0;L;;;;;N;;;;; +1B11D;HENTAIGANA LETTER N-MU-MO-1;Lo;0;L;;;;;N;;;;; +1B11E;HENTAIGANA LETTER N-MU-MO-2;Lo;0;L;;;;;N;;;;; +1B170;NUSHU CHARACTER-1B170;Lo;0;L;;;;;N;;;;; +1B171;NUSHU CHARACTER-1B171;Lo;0;L;;;;;N;;;;; +1B172;NUSHU CHARACTER-1B172;Lo;0;L;;;;;N;;;;; +1B173;NUSHU CHARACTER-1B173;Lo;0;L;;;;;N;;;;; +1B174;NUSHU CHARACTER-1B174;Lo;0;L;;;;;N;;;;; +1B175;NUSHU CHARACTER-1B175;Lo;0;L;;;;;N;;;;; +1B176;NUSHU CHARACTER-1B176;Lo;0;L;;;;;N;;;;; +1B177;NUSHU CHARACTER-1B177;Lo;0;L;;;;;N;;;;; +1B178;NUSHU CHARACTER-1B178;Lo;0;L;;;;;N;;;;; +1B179;NUSHU CHARACTER-1B179;Lo;0;L;;;;;N;;;;; +1B17A;NUSHU CHARACTER-1B17A;Lo;0;L;;;;;N;;;;; +1B17B;NUSHU CHARACTER-1B17B;Lo;0;L;;;;;N;;;;; +1B17C;NUSHU CHARACTER-1B17C;Lo;0;L;;;;;N;;;;; +1B17D;NUSHU CHARACTER-1B17D;Lo;0;L;;;;;N;;;;; +1B17E;NUSHU CHARACTER-1B17E;Lo;0;L;;;;;N;;;;; +1B17F;NUSHU CHARACTER-1B17F;Lo;0;L;;;;;N;;;;; +1B180;NUSHU CHARACTER-1B180;Lo;0;L;;;;;N;;;;; +1B181;NUSHU CHARACTER-1B181;Lo;0;L;;;;;N;;;;; +1B182;NUSHU CHARACTER-1B182;Lo;0;L;;;;;N;;;;; +1B183;NUSHU CHARACTER-1B183;Lo;0;L;;;;;N;;;;; +1B184;NUSHU CHARACTER-1B184;Lo;0;L;;;;;N;;;;; +1B185;NUSHU CHARACTER-1B185;Lo;0;L;;;;;N;;;;; +1B186;NUSHU CHARACTER-1B186;Lo;0;L;;;;;N;;;;; +1B187;NUSHU CHARACTER-1B187;Lo;0;L;;;;;N;;;;; +1B188;NUSHU CHARACTER-1B188;Lo;0;L;;;;;N;;;;; +1B189;NUSHU CHARACTER-1B189;Lo;0;L;;;;;N;;;;; +1B18A;NUSHU CHARACTER-1B18A;Lo;0;L;;;;;N;;;;; +1B18B;NUSHU CHARACTER-1B18B;Lo;0;L;;;;;N;;;;; +1B18C;NUSHU CHARACTER-1B18C;Lo;0;L;;;;;N;;;;; +1B18D;NUSHU CHARACTER-1B18D;Lo;0;L;;;;;N;;;;; +1B18E;NUSHU CHARACTER-1B18E;Lo;0;L;;;;;N;;;;; +1B18F;NUSHU CHARACTER-1B18F;Lo;0;L;;;;;N;;;;; +1B190;NUSHU CHARACTER-1B190;Lo;0;L;;;;;N;;;;; +1B191;NUSHU CHARACTER-1B191;Lo;0;L;;;;;N;;;;; +1B192;NUSHU CHARACTER-1B192;Lo;0;L;;;;;N;;;;; +1B193;NUSHU CHARACTER-1B193;Lo;0;L;;;;;N;;;;; +1B194;NUSHU CHARACTER-1B194;Lo;0;L;;;;;N;;;;; +1B195;NUSHU CHARACTER-1B195;Lo;0;L;;;;;N;;;;; +1B196;NUSHU CHARACTER-1B196;Lo;0;L;;;;;N;;;;; +1B197;NUSHU CHARACTER-1B197;Lo;0;L;;;;;N;;;;; +1B198;NUSHU CHARACTER-1B198;Lo;0;L;;;;;N;;;;; +1B199;NUSHU CHARACTER-1B199;Lo;0;L;;;;;N;;;;; +1B19A;NUSHU CHARACTER-1B19A;Lo;0;L;;;;;N;;;;; +1B19B;NUSHU CHARACTER-1B19B;Lo;0;L;;;;;N;;;;; +1B19C;NUSHU CHARACTER-1B19C;Lo;0;L;;;;;N;;;;; +1B19D;NUSHU CHARACTER-1B19D;Lo;0;L;;;;;N;;;;; +1B19E;NUSHU CHARACTER-1B19E;Lo;0;L;;;;;N;;;;; +1B19F;NUSHU CHARACTER-1B19F;Lo;0;L;;;;;N;;;;; +1B1A0;NUSHU CHARACTER-1B1A0;Lo;0;L;;;;;N;;;;; +1B1A1;NUSHU CHARACTER-1B1A1;Lo;0;L;;;;;N;;;;; +1B1A2;NUSHU CHARACTER-1B1A2;Lo;0;L;;;;;N;;;;; +1B1A3;NUSHU CHARACTER-1B1A3;Lo;0;L;;;;;N;;;;; +1B1A4;NUSHU CHARACTER-1B1A4;Lo;0;L;;;;;N;;;;; +1B1A5;NUSHU CHARACTER-1B1A5;Lo;0;L;;;;;N;;;;; +1B1A6;NUSHU CHARACTER-1B1A6;Lo;0;L;;;;;N;;;;; +1B1A7;NUSHU CHARACTER-1B1A7;Lo;0;L;;;;;N;;;;; +1B1A8;NUSHU CHARACTER-1B1A8;Lo;0;L;;;;;N;;;;; +1B1A9;NUSHU CHARACTER-1B1A9;Lo;0;L;;;;;N;;;;; +1B1AA;NUSHU CHARACTER-1B1AA;Lo;0;L;;;;;N;;;;; +1B1AB;NUSHU CHARACTER-1B1AB;Lo;0;L;;;;;N;;;;; +1B1AC;NUSHU CHARACTER-1B1AC;Lo;0;L;;;;;N;;;;; +1B1AD;NUSHU CHARACTER-1B1AD;Lo;0;L;;;;;N;;;;; +1B1AE;NUSHU CHARACTER-1B1AE;Lo;0;L;;;;;N;;;;; +1B1AF;NUSHU CHARACTER-1B1AF;Lo;0;L;;;;;N;;;;; +1B1B0;NUSHU CHARACTER-1B1B0;Lo;0;L;;;;;N;;;;; +1B1B1;NUSHU CHARACTER-1B1B1;Lo;0;L;;;;;N;;;;; +1B1B2;NUSHU CHARACTER-1B1B2;Lo;0;L;;;;;N;;;;; +1B1B3;NUSHU CHARACTER-1B1B3;Lo;0;L;;;;;N;;;;; +1B1B4;NUSHU CHARACTER-1B1B4;Lo;0;L;;;;;N;;;;; +1B1B5;NUSHU CHARACTER-1B1B5;Lo;0;L;;;;;N;;;;; +1B1B6;NUSHU CHARACTER-1B1B6;Lo;0;L;;;;;N;;;;; +1B1B7;NUSHU CHARACTER-1B1B7;Lo;0;L;;;;;N;;;;; +1B1B8;NUSHU CHARACTER-1B1B8;Lo;0;L;;;;;N;;;;; +1B1B9;NUSHU CHARACTER-1B1B9;Lo;0;L;;;;;N;;;;; +1B1BA;NUSHU CHARACTER-1B1BA;Lo;0;L;;;;;N;;;;; +1B1BB;NUSHU CHARACTER-1B1BB;Lo;0;L;;;;;N;;;;; +1B1BC;NUSHU CHARACTER-1B1BC;Lo;0;L;;;;;N;;;;; +1B1BD;NUSHU CHARACTER-1B1BD;Lo;0;L;;;;;N;;;;; +1B1BE;NUSHU CHARACTER-1B1BE;Lo;0;L;;;;;N;;;;; +1B1BF;NUSHU CHARACTER-1B1BF;Lo;0;L;;;;;N;;;;; +1B1C0;NUSHU CHARACTER-1B1C0;Lo;0;L;;;;;N;;;;; +1B1C1;NUSHU CHARACTER-1B1C1;Lo;0;L;;;;;N;;;;; +1B1C2;NUSHU CHARACTER-1B1C2;Lo;0;L;;;;;N;;;;; +1B1C3;NUSHU CHARACTER-1B1C3;Lo;0;L;;;;;N;;;;; +1B1C4;NUSHU CHARACTER-1B1C4;Lo;0;L;;;;;N;;;;; +1B1C5;NUSHU CHARACTER-1B1C5;Lo;0;L;;;;;N;;;;; +1B1C6;NUSHU CHARACTER-1B1C6;Lo;0;L;;;;;N;;;;; +1B1C7;NUSHU CHARACTER-1B1C7;Lo;0;L;;;;;N;;;;; +1B1C8;NUSHU CHARACTER-1B1C8;Lo;0;L;;;;;N;;;;; +1B1C9;NUSHU CHARACTER-1B1C9;Lo;0;L;;;;;N;;;;; +1B1CA;NUSHU CHARACTER-1B1CA;Lo;0;L;;;;;N;;;;; +1B1CB;NUSHU CHARACTER-1B1CB;Lo;0;L;;;;;N;;;;; +1B1CC;NUSHU CHARACTER-1B1CC;Lo;0;L;;;;;N;;;;; +1B1CD;NUSHU CHARACTER-1B1CD;Lo;0;L;;;;;N;;;;; +1B1CE;NUSHU CHARACTER-1B1CE;Lo;0;L;;;;;N;;;;; +1B1CF;NUSHU CHARACTER-1B1CF;Lo;0;L;;;;;N;;;;; +1B1D0;NUSHU CHARACTER-1B1D0;Lo;0;L;;;;;N;;;;; +1B1D1;NUSHU CHARACTER-1B1D1;Lo;0;L;;;;;N;;;;; +1B1D2;NUSHU CHARACTER-1B1D2;Lo;0;L;;;;;N;;;;; +1B1D3;NUSHU CHARACTER-1B1D3;Lo;0;L;;;;;N;;;;; +1B1D4;NUSHU CHARACTER-1B1D4;Lo;0;L;;;;;N;;;;; +1B1D5;NUSHU CHARACTER-1B1D5;Lo;0;L;;;;;N;;;;; +1B1D6;NUSHU CHARACTER-1B1D6;Lo;0;L;;;;;N;;;;; +1B1D7;NUSHU CHARACTER-1B1D7;Lo;0;L;;;;;N;;;;; +1B1D8;NUSHU CHARACTER-1B1D8;Lo;0;L;;;;;N;;;;; +1B1D9;NUSHU CHARACTER-1B1D9;Lo;0;L;;;;;N;;;;; +1B1DA;NUSHU CHARACTER-1B1DA;Lo;0;L;;;;;N;;;;; +1B1DB;NUSHU CHARACTER-1B1DB;Lo;0;L;;;;;N;;;;; +1B1DC;NUSHU CHARACTER-1B1DC;Lo;0;L;;;;;N;;;;; +1B1DD;NUSHU CHARACTER-1B1DD;Lo;0;L;;;;;N;;;;; +1B1DE;NUSHU CHARACTER-1B1DE;Lo;0;L;;;;;N;;;;; +1B1DF;NUSHU CHARACTER-1B1DF;Lo;0;L;;;;;N;;;;; +1B1E0;NUSHU CHARACTER-1B1E0;Lo;0;L;;;;;N;;;;; +1B1E1;NUSHU CHARACTER-1B1E1;Lo;0;L;;;;;N;;;;; +1B1E2;NUSHU CHARACTER-1B1E2;Lo;0;L;;;;;N;;;;; +1B1E3;NUSHU CHARACTER-1B1E3;Lo;0;L;;;;;N;;;;; +1B1E4;NUSHU CHARACTER-1B1E4;Lo;0;L;;;;;N;;;;; +1B1E5;NUSHU CHARACTER-1B1E5;Lo;0;L;;;;;N;;;;; +1B1E6;NUSHU CHARACTER-1B1E6;Lo;0;L;;;;;N;;;;; +1B1E7;NUSHU CHARACTER-1B1E7;Lo;0;L;;;;;N;;;;; +1B1E8;NUSHU CHARACTER-1B1E8;Lo;0;L;;;;;N;;;;; +1B1E9;NUSHU CHARACTER-1B1E9;Lo;0;L;;;;;N;;;;; +1B1EA;NUSHU CHARACTER-1B1EA;Lo;0;L;;;;;N;;;;; +1B1EB;NUSHU CHARACTER-1B1EB;Lo;0;L;;;;;N;;;;; +1B1EC;NUSHU CHARACTER-1B1EC;Lo;0;L;;;;;N;;;;; +1B1ED;NUSHU CHARACTER-1B1ED;Lo;0;L;;;;;N;;;;; +1B1EE;NUSHU CHARACTER-1B1EE;Lo;0;L;;;;;N;;;;; +1B1EF;NUSHU CHARACTER-1B1EF;Lo;0;L;;;;;N;;;;; +1B1F0;NUSHU CHARACTER-1B1F0;Lo;0;L;;;;;N;;;;; +1B1F1;NUSHU CHARACTER-1B1F1;Lo;0;L;;;;;N;;;;; +1B1F2;NUSHU CHARACTER-1B1F2;Lo;0;L;;;;;N;;;;; +1B1F3;NUSHU CHARACTER-1B1F3;Lo;0;L;;;;;N;;;;; +1B1F4;NUSHU CHARACTER-1B1F4;Lo;0;L;;;;;N;;;;; +1B1F5;NUSHU CHARACTER-1B1F5;Lo;0;L;;;;;N;;;;; +1B1F6;NUSHU CHARACTER-1B1F6;Lo;0;L;;;;;N;;;;; +1B1F7;NUSHU CHARACTER-1B1F7;Lo;0;L;;;;;N;;;;; +1B1F8;NUSHU CHARACTER-1B1F8;Lo;0;L;;;;;N;;;;; +1B1F9;NUSHU CHARACTER-1B1F9;Lo;0;L;;;;;N;;;;; +1B1FA;NUSHU CHARACTER-1B1FA;Lo;0;L;;;;;N;;;;; +1B1FB;NUSHU CHARACTER-1B1FB;Lo;0;L;;;;;N;;;;; +1B1FC;NUSHU CHARACTER-1B1FC;Lo;0;L;;;;;N;;;;; +1B1FD;NUSHU CHARACTER-1B1FD;Lo;0;L;;;;;N;;;;; +1B1FE;NUSHU CHARACTER-1B1FE;Lo;0;L;;;;;N;;;;; +1B1FF;NUSHU CHARACTER-1B1FF;Lo;0;L;;;;;N;;;;; +1B200;NUSHU CHARACTER-1B200;Lo;0;L;;;;;N;;;;; +1B201;NUSHU CHARACTER-1B201;Lo;0;L;;;;;N;;;;; +1B202;NUSHU CHARACTER-1B202;Lo;0;L;;;;;N;;;;; +1B203;NUSHU CHARACTER-1B203;Lo;0;L;;;;;N;;;;; +1B204;NUSHU CHARACTER-1B204;Lo;0;L;;;;;N;;;;; +1B205;NUSHU CHARACTER-1B205;Lo;0;L;;;;;N;;;;; +1B206;NUSHU CHARACTER-1B206;Lo;0;L;;;;;N;;;;; +1B207;NUSHU CHARACTER-1B207;Lo;0;L;;;;;N;;;;; +1B208;NUSHU CHARACTER-1B208;Lo;0;L;;;;;N;;;;; +1B209;NUSHU CHARACTER-1B209;Lo;0;L;;;;;N;;;;; +1B20A;NUSHU CHARACTER-1B20A;Lo;0;L;;;;;N;;;;; +1B20B;NUSHU CHARACTER-1B20B;Lo;0;L;;;;;N;;;;; +1B20C;NUSHU CHARACTER-1B20C;Lo;0;L;;;;;N;;;;; +1B20D;NUSHU CHARACTER-1B20D;Lo;0;L;;;;;N;;;;; +1B20E;NUSHU CHARACTER-1B20E;Lo;0;L;;;;;N;;;;; +1B20F;NUSHU CHARACTER-1B20F;Lo;0;L;;;;;N;;;;; +1B210;NUSHU CHARACTER-1B210;Lo;0;L;;;;;N;;;;; +1B211;NUSHU CHARACTER-1B211;Lo;0;L;;;;;N;;;;; +1B212;NUSHU CHARACTER-1B212;Lo;0;L;;;;;N;;;;; +1B213;NUSHU CHARACTER-1B213;Lo;0;L;;;;;N;;;;; +1B214;NUSHU CHARACTER-1B214;Lo;0;L;;;;;N;;;;; +1B215;NUSHU CHARACTER-1B215;Lo;0;L;;;;;N;;;;; +1B216;NUSHU CHARACTER-1B216;Lo;0;L;;;;;N;;;;; +1B217;NUSHU CHARACTER-1B217;Lo;0;L;;;;;N;;;;; +1B218;NUSHU CHARACTER-1B218;Lo;0;L;;;;;N;;;;; +1B219;NUSHU CHARACTER-1B219;Lo;0;L;;;;;N;;;;; +1B21A;NUSHU CHARACTER-1B21A;Lo;0;L;;;;;N;;;;; +1B21B;NUSHU CHARACTER-1B21B;Lo;0;L;;;;;N;;;;; +1B21C;NUSHU CHARACTER-1B21C;Lo;0;L;;;;;N;;;;; +1B21D;NUSHU CHARACTER-1B21D;Lo;0;L;;;;;N;;;;; +1B21E;NUSHU CHARACTER-1B21E;Lo;0;L;;;;;N;;;;; +1B21F;NUSHU CHARACTER-1B21F;Lo;0;L;;;;;N;;;;; +1B220;NUSHU CHARACTER-1B220;Lo;0;L;;;;;N;;;;; +1B221;NUSHU CHARACTER-1B221;Lo;0;L;;;;;N;;;;; +1B222;NUSHU CHARACTER-1B222;Lo;0;L;;;;;N;;;;; +1B223;NUSHU CHARACTER-1B223;Lo;0;L;;;;;N;;;;; +1B224;NUSHU CHARACTER-1B224;Lo;0;L;;;;;N;;;;; +1B225;NUSHU CHARACTER-1B225;Lo;0;L;;;;;N;;;;; +1B226;NUSHU CHARACTER-1B226;Lo;0;L;;;;;N;;;;; +1B227;NUSHU CHARACTER-1B227;Lo;0;L;;;;;N;;;;; +1B228;NUSHU CHARACTER-1B228;Lo;0;L;;;;;N;;;;; +1B229;NUSHU CHARACTER-1B229;Lo;0;L;;;;;N;;;;; +1B22A;NUSHU CHARACTER-1B22A;Lo;0;L;;;;;N;;;;; +1B22B;NUSHU CHARACTER-1B22B;Lo;0;L;;;;;N;;;;; +1B22C;NUSHU CHARACTER-1B22C;Lo;0;L;;;;;N;;;;; +1B22D;NUSHU CHARACTER-1B22D;Lo;0;L;;;;;N;;;;; +1B22E;NUSHU CHARACTER-1B22E;Lo;0;L;;;;;N;;;;; +1B22F;NUSHU CHARACTER-1B22F;Lo;0;L;;;;;N;;;;; +1B230;NUSHU CHARACTER-1B230;Lo;0;L;;;;;N;;;;; +1B231;NUSHU CHARACTER-1B231;Lo;0;L;;;;;N;;;;; +1B232;NUSHU CHARACTER-1B232;Lo;0;L;;;;;N;;;;; +1B233;NUSHU CHARACTER-1B233;Lo;0;L;;;;;N;;;;; +1B234;NUSHU CHARACTER-1B234;Lo;0;L;;;;;N;;;;; +1B235;NUSHU CHARACTER-1B235;Lo;0;L;;;;;N;;;;; +1B236;NUSHU CHARACTER-1B236;Lo;0;L;;;;;N;;;;; +1B237;NUSHU CHARACTER-1B237;Lo;0;L;;;;;N;;;;; +1B238;NUSHU CHARACTER-1B238;Lo;0;L;;;;;N;;;;; +1B239;NUSHU CHARACTER-1B239;Lo;0;L;;;;;N;;;;; +1B23A;NUSHU CHARACTER-1B23A;Lo;0;L;;;;;N;;;;; +1B23B;NUSHU CHARACTER-1B23B;Lo;0;L;;;;;N;;;;; +1B23C;NUSHU CHARACTER-1B23C;Lo;0;L;;;;;N;;;;; +1B23D;NUSHU CHARACTER-1B23D;Lo;0;L;;;;;N;;;;; +1B23E;NUSHU CHARACTER-1B23E;Lo;0;L;;;;;N;;;;; +1B23F;NUSHU CHARACTER-1B23F;Lo;0;L;;;;;N;;;;; +1B240;NUSHU CHARACTER-1B240;Lo;0;L;;;;;N;;;;; +1B241;NUSHU CHARACTER-1B241;Lo;0;L;;;;;N;;;;; +1B242;NUSHU CHARACTER-1B242;Lo;0;L;;;;;N;;;;; +1B243;NUSHU CHARACTER-1B243;Lo;0;L;;;;;N;;;;; +1B244;NUSHU CHARACTER-1B244;Lo;0;L;;;;;N;;;;; +1B245;NUSHU CHARACTER-1B245;Lo;0;L;;;;;N;;;;; +1B246;NUSHU CHARACTER-1B246;Lo;0;L;;;;;N;;;;; +1B247;NUSHU CHARACTER-1B247;Lo;0;L;;;;;N;;;;; +1B248;NUSHU CHARACTER-1B248;Lo;0;L;;;;;N;;;;; +1B249;NUSHU CHARACTER-1B249;Lo;0;L;;;;;N;;;;; +1B24A;NUSHU CHARACTER-1B24A;Lo;0;L;;;;;N;;;;; +1B24B;NUSHU CHARACTER-1B24B;Lo;0;L;;;;;N;;;;; +1B24C;NUSHU CHARACTER-1B24C;Lo;0;L;;;;;N;;;;; +1B24D;NUSHU CHARACTER-1B24D;Lo;0;L;;;;;N;;;;; +1B24E;NUSHU CHARACTER-1B24E;Lo;0;L;;;;;N;;;;; +1B24F;NUSHU CHARACTER-1B24F;Lo;0;L;;;;;N;;;;; +1B250;NUSHU CHARACTER-1B250;Lo;0;L;;;;;N;;;;; +1B251;NUSHU CHARACTER-1B251;Lo;0;L;;;;;N;;;;; +1B252;NUSHU CHARACTER-1B252;Lo;0;L;;;;;N;;;;; +1B253;NUSHU CHARACTER-1B253;Lo;0;L;;;;;N;;;;; +1B254;NUSHU CHARACTER-1B254;Lo;0;L;;;;;N;;;;; +1B255;NUSHU CHARACTER-1B255;Lo;0;L;;;;;N;;;;; +1B256;NUSHU CHARACTER-1B256;Lo;0;L;;;;;N;;;;; +1B257;NUSHU CHARACTER-1B257;Lo;0;L;;;;;N;;;;; +1B258;NUSHU CHARACTER-1B258;Lo;0;L;;;;;N;;;;; +1B259;NUSHU CHARACTER-1B259;Lo;0;L;;;;;N;;;;; +1B25A;NUSHU CHARACTER-1B25A;Lo;0;L;;;;;N;;;;; +1B25B;NUSHU CHARACTER-1B25B;Lo;0;L;;;;;N;;;;; +1B25C;NUSHU CHARACTER-1B25C;Lo;0;L;;;;;N;;;;; +1B25D;NUSHU CHARACTER-1B25D;Lo;0;L;;;;;N;;;;; +1B25E;NUSHU CHARACTER-1B25E;Lo;0;L;;;;;N;;;;; +1B25F;NUSHU CHARACTER-1B25F;Lo;0;L;;;;;N;;;;; +1B260;NUSHU CHARACTER-1B260;Lo;0;L;;;;;N;;;;; +1B261;NUSHU CHARACTER-1B261;Lo;0;L;;;;;N;;;;; +1B262;NUSHU CHARACTER-1B262;Lo;0;L;;;;;N;;;;; +1B263;NUSHU CHARACTER-1B263;Lo;0;L;;;;;N;;;;; +1B264;NUSHU CHARACTER-1B264;Lo;0;L;;;;;N;;;;; +1B265;NUSHU CHARACTER-1B265;Lo;0;L;;;;;N;;;;; +1B266;NUSHU CHARACTER-1B266;Lo;0;L;;;;;N;;;;; +1B267;NUSHU CHARACTER-1B267;Lo;0;L;;;;;N;;;;; +1B268;NUSHU CHARACTER-1B268;Lo;0;L;;;;;N;;;;; +1B269;NUSHU CHARACTER-1B269;Lo;0;L;;;;;N;;;;; +1B26A;NUSHU CHARACTER-1B26A;Lo;0;L;;;;;N;;;;; +1B26B;NUSHU CHARACTER-1B26B;Lo;0;L;;;;;N;;;;; +1B26C;NUSHU CHARACTER-1B26C;Lo;0;L;;;;;N;;;;; +1B26D;NUSHU CHARACTER-1B26D;Lo;0;L;;;;;N;;;;; +1B26E;NUSHU CHARACTER-1B26E;Lo;0;L;;;;;N;;;;; +1B26F;NUSHU CHARACTER-1B26F;Lo;0;L;;;;;N;;;;; +1B270;NUSHU CHARACTER-1B270;Lo;0;L;;;;;N;;;;; +1B271;NUSHU CHARACTER-1B271;Lo;0;L;;;;;N;;;;; +1B272;NUSHU CHARACTER-1B272;Lo;0;L;;;;;N;;;;; +1B273;NUSHU CHARACTER-1B273;Lo;0;L;;;;;N;;;;; +1B274;NUSHU CHARACTER-1B274;Lo;0;L;;;;;N;;;;; +1B275;NUSHU CHARACTER-1B275;Lo;0;L;;;;;N;;;;; +1B276;NUSHU CHARACTER-1B276;Lo;0;L;;;;;N;;;;; +1B277;NUSHU CHARACTER-1B277;Lo;0;L;;;;;N;;;;; +1B278;NUSHU CHARACTER-1B278;Lo;0;L;;;;;N;;;;; +1B279;NUSHU CHARACTER-1B279;Lo;0;L;;;;;N;;;;; +1B27A;NUSHU CHARACTER-1B27A;Lo;0;L;;;;;N;;;;; +1B27B;NUSHU CHARACTER-1B27B;Lo;0;L;;;;;N;;;;; +1B27C;NUSHU CHARACTER-1B27C;Lo;0;L;;;;;N;;;;; +1B27D;NUSHU CHARACTER-1B27D;Lo;0;L;;;;;N;;;;; +1B27E;NUSHU CHARACTER-1B27E;Lo;0;L;;;;;N;;;;; +1B27F;NUSHU CHARACTER-1B27F;Lo;0;L;;;;;N;;;;; +1B280;NUSHU CHARACTER-1B280;Lo;0;L;;;;;N;;;;; +1B281;NUSHU CHARACTER-1B281;Lo;0;L;;;;;N;;;;; +1B282;NUSHU CHARACTER-1B282;Lo;0;L;;;;;N;;;;; +1B283;NUSHU CHARACTER-1B283;Lo;0;L;;;;;N;;;;; +1B284;NUSHU CHARACTER-1B284;Lo;0;L;;;;;N;;;;; +1B285;NUSHU CHARACTER-1B285;Lo;0;L;;;;;N;;;;; +1B286;NUSHU CHARACTER-1B286;Lo;0;L;;;;;N;;;;; +1B287;NUSHU CHARACTER-1B287;Lo;0;L;;;;;N;;;;; +1B288;NUSHU CHARACTER-1B288;Lo;0;L;;;;;N;;;;; +1B289;NUSHU CHARACTER-1B289;Lo;0;L;;;;;N;;;;; +1B28A;NUSHU CHARACTER-1B28A;Lo;0;L;;;;;N;;;;; +1B28B;NUSHU CHARACTER-1B28B;Lo;0;L;;;;;N;;;;; +1B28C;NUSHU CHARACTER-1B28C;Lo;0;L;;;;;N;;;;; +1B28D;NUSHU CHARACTER-1B28D;Lo;0;L;;;;;N;;;;; +1B28E;NUSHU CHARACTER-1B28E;Lo;0;L;;;;;N;;;;; +1B28F;NUSHU CHARACTER-1B28F;Lo;0;L;;;;;N;;;;; +1B290;NUSHU CHARACTER-1B290;Lo;0;L;;;;;N;;;;; +1B291;NUSHU CHARACTER-1B291;Lo;0;L;;;;;N;;;;; +1B292;NUSHU CHARACTER-1B292;Lo;0;L;;;;;N;;;;; +1B293;NUSHU CHARACTER-1B293;Lo;0;L;;;;;N;;;;; +1B294;NUSHU CHARACTER-1B294;Lo;0;L;;;;;N;;;;; +1B295;NUSHU CHARACTER-1B295;Lo;0;L;;;;;N;;;;; +1B296;NUSHU CHARACTER-1B296;Lo;0;L;;;;;N;;;;; +1B297;NUSHU CHARACTER-1B297;Lo;0;L;;;;;N;;;;; +1B298;NUSHU CHARACTER-1B298;Lo;0;L;;;;;N;;;;; +1B299;NUSHU CHARACTER-1B299;Lo;0;L;;;;;N;;;;; +1B29A;NUSHU CHARACTER-1B29A;Lo;0;L;;;;;N;;;;; +1B29B;NUSHU CHARACTER-1B29B;Lo;0;L;;;;;N;;;;; +1B29C;NUSHU CHARACTER-1B29C;Lo;0;L;;;;;N;;;;; +1B29D;NUSHU CHARACTER-1B29D;Lo;0;L;;;;;N;;;;; +1B29E;NUSHU CHARACTER-1B29E;Lo;0;L;;;;;N;;;;; +1B29F;NUSHU CHARACTER-1B29F;Lo;0;L;;;;;N;;;;; +1B2A0;NUSHU CHARACTER-1B2A0;Lo;0;L;;;;;N;;;;; +1B2A1;NUSHU CHARACTER-1B2A1;Lo;0;L;;;;;N;;;;; +1B2A2;NUSHU CHARACTER-1B2A2;Lo;0;L;;;;;N;;;;; +1B2A3;NUSHU CHARACTER-1B2A3;Lo;0;L;;;;;N;;;;; +1B2A4;NUSHU CHARACTER-1B2A4;Lo;0;L;;;;;N;;;;; +1B2A5;NUSHU CHARACTER-1B2A5;Lo;0;L;;;;;N;;;;; +1B2A6;NUSHU CHARACTER-1B2A6;Lo;0;L;;;;;N;;;;; +1B2A7;NUSHU CHARACTER-1B2A7;Lo;0;L;;;;;N;;;;; +1B2A8;NUSHU CHARACTER-1B2A8;Lo;0;L;;;;;N;;;;; +1B2A9;NUSHU CHARACTER-1B2A9;Lo;0;L;;;;;N;;;;; +1B2AA;NUSHU CHARACTER-1B2AA;Lo;0;L;;;;;N;;;;; +1B2AB;NUSHU CHARACTER-1B2AB;Lo;0;L;;;;;N;;;;; +1B2AC;NUSHU CHARACTER-1B2AC;Lo;0;L;;;;;N;;;;; +1B2AD;NUSHU CHARACTER-1B2AD;Lo;0;L;;;;;N;;;;; +1B2AE;NUSHU CHARACTER-1B2AE;Lo;0;L;;;;;N;;;;; +1B2AF;NUSHU CHARACTER-1B2AF;Lo;0;L;;;;;N;;;;; +1B2B0;NUSHU CHARACTER-1B2B0;Lo;0;L;;;;;N;;;;; +1B2B1;NUSHU CHARACTER-1B2B1;Lo;0;L;;;;;N;;;;; +1B2B2;NUSHU CHARACTER-1B2B2;Lo;0;L;;;;;N;;;;; +1B2B3;NUSHU CHARACTER-1B2B3;Lo;0;L;;;;;N;;;;; +1B2B4;NUSHU CHARACTER-1B2B4;Lo;0;L;;;;;N;;;;; +1B2B5;NUSHU CHARACTER-1B2B5;Lo;0;L;;;;;N;;;;; +1B2B6;NUSHU CHARACTER-1B2B6;Lo;0;L;;;;;N;;;;; +1B2B7;NUSHU CHARACTER-1B2B7;Lo;0;L;;;;;N;;;;; +1B2B8;NUSHU CHARACTER-1B2B8;Lo;0;L;;;;;N;;;;; +1B2B9;NUSHU CHARACTER-1B2B9;Lo;0;L;;;;;N;;;;; +1B2BA;NUSHU CHARACTER-1B2BA;Lo;0;L;;;;;N;;;;; +1B2BB;NUSHU CHARACTER-1B2BB;Lo;0;L;;;;;N;;;;; +1B2BC;NUSHU CHARACTER-1B2BC;Lo;0;L;;;;;N;;;;; +1B2BD;NUSHU CHARACTER-1B2BD;Lo;0;L;;;;;N;;;;; +1B2BE;NUSHU CHARACTER-1B2BE;Lo;0;L;;;;;N;;;;; +1B2BF;NUSHU CHARACTER-1B2BF;Lo;0;L;;;;;N;;;;; +1B2C0;NUSHU CHARACTER-1B2C0;Lo;0;L;;;;;N;;;;; +1B2C1;NUSHU CHARACTER-1B2C1;Lo;0;L;;;;;N;;;;; +1B2C2;NUSHU CHARACTER-1B2C2;Lo;0;L;;;;;N;;;;; +1B2C3;NUSHU CHARACTER-1B2C3;Lo;0;L;;;;;N;;;;; +1B2C4;NUSHU CHARACTER-1B2C4;Lo;0;L;;;;;N;;;;; +1B2C5;NUSHU CHARACTER-1B2C5;Lo;0;L;;;;;N;;;;; +1B2C6;NUSHU CHARACTER-1B2C6;Lo;0;L;;;;;N;;;;; +1B2C7;NUSHU CHARACTER-1B2C7;Lo;0;L;;;;;N;;;;; +1B2C8;NUSHU CHARACTER-1B2C8;Lo;0;L;;;;;N;;;;; +1B2C9;NUSHU CHARACTER-1B2C9;Lo;0;L;;;;;N;;;;; +1B2CA;NUSHU CHARACTER-1B2CA;Lo;0;L;;;;;N;;;;; +1B2CB;NUSHU CHARACTER-1B2CB;Lo;0;L;;;;;N;;;;; +1B2CC;NUSHU CHARACTER-1B2CC;Lo;0;L;;;;;N;;;;; +1B2CD;NUSHU CHARACTER-1B2CD;Lo;0;L;;;;;N;;;;; +1B2CE;NUSHU CHARACTER-1B2CE;Lo;0;L;;;;;N;;;;; +1B2CF;NUSHU CHARACTER-1B2CF;Lo;0;L;;;;;N;;;;; +1B2D0;NUSHU CHARACTER-1B2D0;Lo;0;L;;;;;N;;;;; +1B2D1;NUSHU CHARACTER-1B2D1;Lo;0;L;;;;;N;;;;; +1B2D2;NUSHU CHARACTER-1B2D2;Lo;0;L;;;;;N;;;;; +1B2D3;NUSHU CHARACTER-1B2D3;Lo;0;L;;;;;N;;;;; +1B2D4;NUSHU CHARACTER-1B2D4;Lo;0;L;;;;;N;;;;; +1B2D5;NUSHU CHARACTER-1B2D5;Lo;0;L;;;;;N;;;;; +1B2D6;NUSHU CHARACTER-1B2D6;Lo;0;L;;;;;N;;;;; +1B2D7;NUSHU CHARACTER-1B2D7;Lo;0;L;;;;;N;;;;; +1B2D8;NUSHU CHARACTER-1B2D8;Lo;0;L;;;;;N;;;;; +1B2D9;NUSHU CHARACTER-1B2D9;Lo;0;L;;;;;N;;;;; +1B2DA;NUSHU CHARACTER-1B2DA;Lo;0;L;;;;;N;;;;; +1B2DB;NUSHU CHARACTER-1B2DB;Lo;0;L;;;;;N;;;;; +1B2DC;NUSHU CHARACTER-1B2DC;Lo;0;L;;;;;N;;;;; +1B2DD;NUSHU CHARACTER-1B2DD;Lo;0;L;;;;;N;;;;; +1B2DE;NUSHU CHARACTER-1B2DE;Lo;0;L;;;;;N;;;;; +1B2DF;NUSHU CHARACTER-1B2DF;Lo;0;L;;;;;N;;;;; +1B2E0;NUSHU CHARACTER-1B2E0;Lo;0;L;;;;;N;;;;; +1B2E1;NUSHU CHARACTER-1B2E1;Lo;0;L;;;;;N;;;;; +1B2E2;NUSHU CHARACTER-1B2E2;Lo;0;L;;;;;N;;;;; +1B2E3;NUSHU CHARACTER-1B2E3;Lo;0;L;;;;;N;;;;; +1B2E4;NUSHU CHARACTER-1B2E4;Lo;0;L;;;;;N;;;;; +1B2E5;NUSHU CHARACTER-1B2E5;Lo;0;L;;;;;N;;;;; +1B2E6;NUSHU CHARACTER-1B2E6;Lo;0;L;;;;;N;;;;; +1B2E7;NUSHU CHARACTER-1B2E7;Lo;0;L;;;;;N;;;;; +1B2E8;NUSHU CHARACTER-1B2E8;Lo;0;L;;;;;N;;;;; +1B2E9;NUSHU CHARACTER-1B2E9;Lo;0;L;;;;;N;;;;; +1B2EA;NUSHU CHARACTER-1B2EA;Lo;0;L;;;;;N;;;;; +1B2EB;NUSHU CHARACTER-1B2EB;Lo;0;L;;;;;N;;;;; +1B2EC;NUSHU CHARACTER-1B2EC;Lo;0;L;;;;;N;;;;; +1B2ED;NUSHU CHARACTER-1B2ED;Lo;0;L;;;;;N;;;;; +1B2EE;NUSHU CHARACTER-1B2EE;Lo;0;L;;;;;N;;;;; +1B2EF;NUSHU CHARACTER-1B2EF;Lo;0;L;;;;;N;;;;; +1B2F0;NUSHU CHARACTER-1B2F0;Lo;0;L;;;;;N;;;;; +1B2F1;NUSHU CHARACTER-1B2F1;Lo;0;L;;;;;N;;;;; +1B2F2;NUSHU CHARACTER-1B2F2;Lo;0;L;;;;;N;;;;; +1B2F3;NUSHU CHARACTER-1B2F3;Lo;0;L;;;;;N;;;;; +1B2F4;NUSHU CHARACTER-1B2F4;Lo;0;L;;;;;N;;;;; +1B2F5;NUSHU CHARACTER-1B2F5;Lo;0;L;;;;;N;;;;; +1B2F6;NUSHU CHARACTER-1B2F6;Lo;0;L;;;;;N;;;;; +1B2F7;NUSHU CHARACTER-1B2F7;Lo;0;L;;;;;N;;;;; +1B2F8;NUSHU CHARACTER-1B2F8;Lo;0;L;;;;;N;;;;; +1B2F9;NUSHU CHARACTER-1B2F9;Lo;0;L;;;;;N;;;;; +1B2FA;NUSHU CHARACTER-1B2FA;Lo;0;L;;;;;N;;;;; +1B2FB;NUSHU CHARACTER-1B2FB;Lo;0;L;;;;;N;;;;; 1BC00;DUPLOYAN LETTER H;Lo;0;L;;;;;N;;;;; 1BC01;DUPLOYAN LETTER X;Lo;0;L;;;;;N;;;;; 1BC02;DUPLOYAN LETTER P;Lo;0;L;;;;;N;;;;; @@ -26154,6 +28261,44 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1DAAD;SIGNWRITING ROTATION MODIFIER-14;Mn;0;NSM;;;;;N;;;;; 1DAAE;SIGNWRITING ROTATION MODIFIER-15;Mn;0;NSM;;;;;N;;;;; 1DAAF;SIGNWRITING ROTATION MODIFIER-16;Mn;0;NSM;;;;;N;;;;; +1E000;COMBINING GLAGOLITIC LETTER AZU;Mn;230;NSM;;;;;N;;;;; +1E001;COMBINING GLAGOLITIC LETTER BUKY;Mn;230;NSM;;;;;N;;;;; +1E002;COMBINING GLAGOLITIC LETTER VEDE;Mn;230;NSM;;;;;N;;;;; +1E003;COMBINING GLAGOLITIC LETTER GLAGOLI;Mn;230;NSM;;;;;N;;;;; +1E004;COMBINING GLAGOLITIC LETTER DOBRO;Mn;230;NSM;;;;;N;;;;; +1E005;COMBINING GLAGOLITIC LETTER YESTU;Mn;230;NSM;;;;;N;;;;; +1E006;COMBINING GLAGOLITIC LETTER ZHIVETE;Mn;230;NSM;;;;;N;;;;; +1E008;COMBINING GLAGOLITIC LETTER ZEMLJA;Mn;230;NSM;;;;;N;;;;; +1E009;COMBINING GLAGOLITIC LETTER IZHE;Mn;230;NSM;;;;;N;;;;; +1E00A;COMBINING GLAGOLITIC LETTER INITIAL IZHE;Mn;230;NSM;;;;;N;;;;; +1E00B;COMBINING GLAGOLITIC LETTER I;Mn;230;NSM;;;;;N;;;;; +1E00C;COMBINING GLAGOLITIC LETTER DJERVI;Mn;230;NSM;;;;;N;;;;; +1E00D;COMBINING GLAGOLITIC LETTER KAKO;Mn;230;NSM;;;;;N;;;;; +1E00E;COMBINING GLAGOLITIC LETTER LJUDIJE;Mn;230;NSM;;;;;N;;;;; +1E00F;COMBINING GLAGOLITIC LETTER MYSLITE;Mn;230;NSM;;;;;N;;;;; +1E010;COMBINING GLAGOLITIC LETTER NASHI;Mn;230;NSM;;;;;N;;;;; +1E011;COMBINING GLAGOLITIC LETTER ONU;Mn;230;NSM;;;;;N;;;;; +1E012;COMBINING GLAGOLITIC LETTER POKOJI;Mn;230;NSM;;;;;N;;;;; +1E013;COMBINING GLAGOLITIC LETTER RITSI;Mn;230;NSM;;;;;N;;;;; +1E014;COMBINING GLAGOLITIC LETTER SLOVO;Mn;230;NSM;;;;;N;;;;; +1E015;COMBINING GLAGOLITIC LETTER TVRIDO;Mn;230;NSM;;;;;N;;;;; +1E016;COMBINING GLAGOLITIC LETTER UKU;Mn;230;NSM;;;;;N;;;;; +1E017;COMBINING GLAGOLITIC LETTER FRITU;Mn;230;NSM;;;;;N;;;;; +1E018;COMBINING GLAGOLITIC LETTER HERU;Mn;230;NSM;;;;;N;;;;; +1E01B;COMBINING GLAGOLITIC LETTER SHTA;Mn;230;NSM;;;;;N;;;;; +1E01C;COMBINING GLAGOLITIC LETTER TSI;Mn;230;NSM;;;;;N;;;;; +1E01D;COMBINING GLAGOLITIC LETTER CHRIVI;Mn;230;NSM;;;;;N;;;;; +1E01E;COMBINING GLAGOLITIC LETTER SHA;Mn;230;NSM;;;;;N;;;;; +1E01F;COMBINING GLAGOLITIC LETTER YERU;Mn;230;NSM;;;;;N;;;;; +1E020;COMBINING GLAGOLITIC LETTER YERI;Mn;230;NSM;;;;;N;;;;; +1E021;COMBINING GLAGOLITIC LETTER YATI;Mn;230;NSM;;;;;N;;;;; +1E023;COMBINING GLAGOLITIC LETTER YU;Mn;230;NSM;;;;;N;;;;; +1E024;COMBINING GLAGOLITIC LETTER SMALL YUS;Mn;230;NSM;;;;;N;;;;; +1E026;COMBINING GLAGOLITIC LETTER YO;Mn;230;NSM;;;;;N;;;;; +1E027;COMBINING GLAGOLITIC LETTER IOTATED SMALL YUS;Mn;230;NSM;;;;;N;;;;; +1E028;COMBINING GLAGOLITIC LETTER BIG YUS;Mn;230;NSM;;;;;N;;;;; +1E029;COMBINING GLAGOLITIC LETTER IOTATED BIG YUS;Mn;230;NSM;;;;;N;;;;; +1E02A;COMBINING GLAGOLITIC LETTER FITA;Mn;230;NSM;;;;;N;;;;; 1E800;MENDE KIKAKUI SYLLABLE M001 KI;Lo;0;R;;;;;N;;;;; 1E801;MENDE KIKAKUI SYLLABLE M002 KA;Lo;0;R;;;;;N;;;;; 1E802;MENDE KIKAKUI SYLLABLE M003 KU;Lo;0;R;;;;;N;;;;; @@ -26367,6 +28512,93 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1E8D4;MENDE KIKAKUI COMBINING NUMBER TEN THOUSANDS;Mn;220;NSM;;;;;N;;;;; 1E8D5;MENDE KIKAKUI COMBINING NUMBER HUNDRED THOUSANDS;Mn;220;NSM;;;;;N;;;;; 1E8D6;MENDE KIKAKUI COMBINING NUMBER MILLIONS;Mn;220;NSM;;;;;N;;;;; +1E900;ADLAM CAPITAL LETTER ALIF;Lu;0;R;;;;;N;;;;1E922; +1E901;ADLAM CAPITAL LETTER DAALI;Lu;0;R;;;;;N;;;;1E923; +1E902;ADLAM CAPITAL LETTER LAAM;Lu;0;R;;;;;N;;;;1E924; +1E903;ADLAM CAPITAL LETTER MIIM;Lu;0;R;;;;;N;;;;1E925; +1E904;ADLAM CAPITAL LETTER BA;Lu;0;R;;;;;N;;;;1E926; +1E905;ADLAM CAPITAL LETTER SINNYIIYHE;Lu;0;R;;;;;N;;;;1E927; +1E906;ADLAM CAPITAL LETTER PE;Lu;0;R;;;;;N;;;;1E928; +1E907;ADLAM CAPITAL LETTER BHE;Lu;0;R;;;;;N;;;;1E929; +1E908;ADLAM CAPITAL LETTER RA;Lu;0;R;;;;;N;;;;1E92A; +1E909;ADLAM CAPITAL LETTER E;Lu;0;R;;;;;N;;;;1E92B; +1E90A;ADLAM CAPITAL LETTER FA;Lu;0;R;;;;;N;;;;1E92C; +1E90B;ADLAM CAPITAL LETTER I;Lu;0;R;;;;;N;;;;1E92D; +1E90C;ADLAM CAPITAL LETTER O;Lu;0;R;;;;;N;;;;1E92E; +1E90D;ADLAM CAPITAL LETTER DHA;Lu;0;R;;;;;N;;;;1E92F; +1E90E;ADLAM CAPITAL LETTER YHE;Lu;0;R;;;;;N;;;;1E930; +1E90F;ADLAM CAPITAL LETTER WAW;Lu;0;R;;;;;N;;;;1E931; +1E910;ADLAM CAPITAL LETTER NUN;Lu;0;R;;;;;N;;;;1E932; +1E911;ADLAM CAPITAL LETTER KAF;Lu;0;R;;;;;N;;;;1E933; +1E912;ADLAM CAPITAL LETTER YA;Lu;0;R;;;;;N;;;;1E934; +1E913;ADLAM CAPITAL LETTER U;Lu;0;R;;;;;N;;;;1E935; +1E914;ADLAM CAPITAL LETTER JIIM;Lu;0;R;;;;;N;;;;1E936; +1E915;ADLAM CAPITAL LETTER CHI;Lu;0;R;;;;;N;;;;1E937; +1E916;ADLAM CAPITAL LETTER HA;Lu;0;R;;;;;N;;;;1E938; +1E917;ADLAM CAPITAL LETTER QAAF;Lu;0;R;;;;;N;;;;1E939; +1E918;ADLAM CAPITAL LETTER GA;Lu;0;R;;;;;N;;;;1E93A; +1E919;ADLAM CAPITAL LETTER NYA;Lu;0;R;;;;;N;;;;1E93B; +1E91A;ADLAM CAPITAL LETTER TU;Lu;0;R;;;;;N;;;;1E93C; +1E91B;ADLAM CAPITAL LETTER NHA;Lu;0;R;;;;;N;;;;1E93D; +1E91C;ADLAM CAPITAL LETTER VA;Lu;0;R;;;;;N;;;;1E93E; +1E91D;ADLAM CAPITAL LETTER KHA;Lu;0;R;;;;;N;;;;1E93F; +1E91E;ADLAM CAPITAL LETTER GBE;Lu;0;R;;;;;N;;;;1E940; +1E91F;ADLAM CAPITAL LETTER ZAL;Lu;0;R;;;;;N;;;;1E941; +1E920;ADLAM CAPITAL LETTER KPO;Lu;0;R;;;;;N;;;;1E942; +1E921;ADLAM CAPITAL LETTER SHA;Lu;0;R;;;;;N;;;;1E943; +1E922;ADLAM SMALL LETTER ALIF;Ll;0;R;;;;;N;;;1E900;;1E900 +1E923;ADLAM SMALL LETTER DAALI;Ll;0;R;;;;;N;;;1E901;;1E901 +1E924;ADLAM SMALL LETTER LAAM;Ll;0;R;;;;;N;;;1E902;;1E902 +1E925;ADLAM SMALL LETTER MIIM;Ll;0;R;;;;;N;;;1E903;;1E903 +1E926;ADLAM SMALL LETTER BA;Ll;0;R;;;;;N;;;1E904;;1E904 +1E927;ADLAM SMALL LETTER SINNYIIYHE;Ll;0;R;;;;;N;;;1E905;;1E905 +1E928;ADLAM SMALL LETTER PE;Ll;0;R;;;;;N;;;1E906;;1E906 +1E929;ADLAM SMALL LETTER BHE;Ll;0;R;;;;;N;;;1E907;;1E907 +1E92A;ADLAM SMALL LETTER RA;Ll;0;R;;;;;N;;;1E908;;1E908 +1E92B;ADLAM SMALL LETTER E;Ll;0;R;;;;;N;;;1E909;;1E909 +1E92C;ADLAM SMALL LETTER FA;Ll;0;R;;;;;N;;;1E90A;;1E90A +1E92D;ADLAM SMALL LETTER I;Ll;0;R;;;;;N;;;1E90B;;1E90B +1E92E;ADLAM SMALL LETTER O;Ll;0;R;;;;;N;;;1E90C;;1E90C +1E92F;ADLAM SMALL LETTER DHA;Ll;0;R;;;;;N;;;1E90D;;1E90D +1E930;ADLAM SMALL LETTER YHE;Ll;0;R;;;;;N;;;1E90E;;1E90E +1E931;ADLAM SMALL LETTER WAW;Ll;0;R;;;;;N;;;1E90F;;1E90F +1E932;ADLAM SMALL LETTER NUN;Ll;0;R;;;;;N;;;1E910;;1E910 +1E933;ADLAM SMALL LETTER KAF;Ll;0;R;;;;;N;;;1E911;;1E911 +1E934;ADLAM SMALL LETTER YA;Ll;0;R;;;;;N;;;1E912;;1E912 +1E935;ADLAM SMALL LETTER U;Ll;0;R;;;;;N;;;1E913;;1E913 +1E936;ADLAM SMALL LETTER JIIM;Ll;0;R;;;;;N;;;1E914;;1E914 +1E937;ADLAM SMALL LETTER CHI;Ll;0;R;;;;;N;;;1E915;;1E915 +1E938;ADLAM SMALL LETTER HA;Ll;0;R;;;;;N;;;1E916;;1E916 +1E939;ADLAM SMALL LETTER QAAF;Ll;0;R;;;;;N;;;1E917;;1E917 +1E93A;ADLAM SMALL LETTER GA;Ll;0;R;;;;;N;;;1E918;;1E918 +1E93B;ADLAM SMALL LETTER NYA;Ll;0;R;;;;;N;;;1E919;;1E919 +1E93C;ADLAM SMALL LETTER TU;Ll;0;R;;;;;N;;;1E91A;;1E91A +1E93D;ADLAM SMALL LETTER NHA;Ll;0;R;;;;;N;;;1E91B;;1E91B +1E93E;ADLAM SMALL LETTER VA;Ll;0;R;;;;;N;;;1E91C;;1E91C +1E93F;ADLAM SMALL LETTER KHA;Ll;0;R;;;;;N;;;1E91D;;1E91D +1E940;ADLAM SMALL LETTER GBE;Ll;0;R;;;;;N;;;1E91E;;1E91E +1E941;ADLAM SMALL LETTER ZAL;Ll;0;R;;;;;N;;;1E91F;;1E91F +1E942;ADLAM SMALL LETTER KPO;Ll;0;R;;;;;N;;;1E920;;1E920 +1E943;ADLAM SMALL LETTER SHA;Ll;0;R;;;;;N;;;1E921;;1E921 +1E944;ADLAM ALIF LENGTHENER;Mn;230;NSM;;;;;N;;;;; +1E945;ADLAM VOWEL LENGTHENER;Mn;230;NSM;;;;;N;;;;; +1E946;ADLAM GEMINATION MARK;Mn;230;NSM;;;;;N;;;;; +1E947;ADLAM HAMZA;Mn;230;NSM;;;;;N;;;;; +1E948;ADLAM CONSONANT MODIFIER;Mn;230;NSM;;;;;N;;;;; +1E949;ADLAM GEMINATE CONSONANT MODIFIER;Mn;230;NSM;;;;;N;;;;; +1E94A;ADLAM NUKTA;Mn;7;NSM;;;;;N;;;;; +1E950;ADLAM DIGIT ZERO;Nd;0;R;;0;0;0;N;;;;; +1E951;ADLAM DIGIT ONE;Nd;0;R;;1;1;1;N;;;;; +1E952;ADLAM DIGIT TWO;Nd;0;R;;2;2;2;N;;;;; +1E953;ADLAM DIGIT THREE;Nd;0;R;;3;3;3;N;;;;; +1E954;ADLAM DIGIT FOUR;Nd;0;R;;4;4;4;N;;;;; +1E955;ADLAM DIGIT FIVE;Nd;0;R;;5;5;5;N;;;;; +1E956;ADLAM DIGIT SIX;Nd;0;R;;6;6;6;N;;;;; +1E957;ADLAM DIGIT SEVEN;Nd;0;R;;7;7;7;N;;;;; +1E958;ADLAM DIGIT EIGHT;Nd;0;R;;8;8;8;N;;;;; +1E959;ADLAM DIGIT NINE;Nd;0;R;;9;9;9;N;;;;; +1E95E;ADLAM INITIAL EXCLAMATION MARK;Po;0;R;;;;;N;;;;; +1E95F;ADLAM INITIAL QUESTION MARK;Po;0;R;;;;;N;;;;; 1EE00;ARABIC MATHEMATICAL ALEF;Lo;0;AL;<font> 0627;;;;N;;;;; 1EE01;ARABIC MATHEMATICAL BEH;Lo;0;AL;<font> 0628;;;;N;;;;; 1EE02;ARABIC MATHEMATICAL JEEM;Lo;0;AL;<font> 062C;;;;N;;;;; @@ -26883,6 +29115,24 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F198;SQUARED SOS;So;0;L;;;;;N;;;;; 1F199;SQUARED UP WITH EXCLAMATION MARK;So;0;L;;;;;N;;;;; 1F19A;SQUARED VS;So;0;L;;;;;N;;;;; +1F19B;SQUARED THREE D;So;0;L;;;;;N;;;;; +1F19C;SQUARED SECOND SCREEN;So;0;L;;;;;N;;;;; +1F19D;SQUARED TWO K;So;0;L;;;;;N;;;;; +1F19E;SQUARED FOUR K;So;0;L;;;;;N;;;;; +1F19F;SQUARED EIGHT K;So;0;L;;;;;N;;;;; +1F1A0;SQUARED FIVE POINT ONE;So;0;L;;;;;N;;;;; +1F1A1;SQUARED SEVEN POINT ONE;So;0;L;;;;;N;;;;; +1F1A2;SQUARED TWENTY-TWO POINT TWO;So;0;L;;;;;N;;;;; +1F1A3;SQUARED SIXTY P;So;0;L;;;;;N;;;;; +1F1A4;SQUARED ONE HUNDRED TWENTY P;So;0;L;;;;;N;;;;; +1F1A5;SQUARED LATIN SMALL LETTER D;So;0;L;;;;;N;;;;; +1F1A6;SQUARED HC;So;0;L;;;;;N;;;;; +1F1A7;SQUARED HDR;So;0;L;;;;;N;;;;; +1F1A8;SQUARED HI-RES;So;0;L;;;;;N;;;;; +1F1A9;SQUARED LOSSLESS;So;0;L;;;;;N;;;;; +1F1AA;SQUARED SHV;So;0;L;;;;;N;;;;; +1F1AB;SQUARED UHD;So;0;L;;;;;N;;;;; +1F1AC;SQUARED VOD;So;0;L;;;;;N;;;;; 1F1E6;REGIONAL INDICATOR SYMBOL LETTER A;So;0;L;;;;;N;;;;; 1F1E7;REGIONAL INDICATOR SYMBOL LETTER B;So;0;L;;;;;N;;;;; 1F1E8;REGIONAL INDICATOR SYMBOL LETTER C;So;0;L;;;;;N;;;;; @@ -26955,6 +29205,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F238;SQUARED CJK UNIFIED IDEOGRAPH-7533;So;0;L;<square> 7533;;;;N;;;;; 1F239;SQUARED CJK UNIFIED IDEOGRAPH-5272;So;0;L;<square> 5272;;;;N;;;;; 1F23A;SQUARED CJK UNIFIED IDEOGRAPH-55B6;So;0;L;<square> 55B6;;;;N;;;;; +1F23B;SQUARED CJK UNIFIED IDEOGRAPH-914D;So;0;L;<square> 914D;;;;N;;;;; 1F240;TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C;So;0;L;<compat> 3014 672C 3015;;;;N;;;;; 1F241;TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09;So;0;L;<compat> 3014 4E09 3015;;;;N;;;;; 1F242;TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E8C;So;0;L;<compat> 3014 4E8C 3015;;;;N;;;;; @@ -26966,6 +29217,12 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F248;TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557;So;0;L;<compat> 3014 6557 3015;;;;N;;;;; 1F250;CIRCLED IDEOGRAPH ADVANTAGE;So;0;L;<circle> 5F97;;;;N;;;;; 1F251;CIRCLED IDEOGRAPH ACCEPT;So;0;L;<circle> 53EF;;;;N;;;;; +1F260;ROUNDED SYMBOL FOR FU;So;0;ON;;;;;N;;;;; +1F261;ROUNDED SYMBOL FOR LU;So;0;ON;;;;;N;;;;; +1F262;ROUNDED SYMBOL FOR SHOU;So;0;ON;;;;;N;;;;; +1F263;ROUNDED SYMBOL FOR XI;So;0;ON;;;;;N;;;;; +1F264;ROUNDED SYMBOL FOR SHUANGXI;So;0;ON;;;;;N;;;;; +1F265;ROUNDED SYMBOL FOR CAI;So;0;ON;;;;;N;;;;; 1F300;CYCLONE;So;0;ON;;;;;N;;;;; 1F301;FOGGY;So;0;ON;;;;;N;;;;; 1F302;CLOSED UMBRELLA;So;0;ON;;;;;N;;;;; @@ -27600,6 +29857,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F577;SPIDER;So;0;ON;;;;;N;;;;; 1F578;SPIDER WEB;So;0;ON;;;;;N;;;;; 1F579;JOYSTICK;So;0;ON;;;;;N;;;;; +1F57A;MAN DANCING;So;0;ON;;;;;N;;;;; 1F57B;LEFT HAND TELEPHONE RECEIVER;So;0;ON;;;;;N;;;;; 1F57C;TELEPHONE RECEIVER WITH PAGE;So;0;ON;;;;;N;;;;; 1F57D;RIGHT HAND TELEPHONE RECEIVER;So;0;ON;;;;;N;;;;; @@ -27641,6 +29899,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F5A1;SIDEWAYS BLACK DOWN POINTING INDEX;So;0;ON;;;;;N;;;;; 1F5A2;BLACK UP POINTING BACKHAND INDEX;So;0;ON;;;;;N;;;;; 1F5A3;BLACK DOWN POINTING BACKHAND INDEX;So;0;ON;;;;;N;;;;; +1F5A4;BLACK HEART;So;0;ON;;;;;N;;;;; 1F5A5;DESKTOP COMPUTER;So;0;ON;;;;;N;;;;; 1F5A6;KEYBOARD AND MOUSE;So;0;ON;;;;;N;;;;; 1F5A7;THREE NETWORKED COMPUTERS;So;0;ON;;;;;N;;;;; @@ -27941,6 +30200,10 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F6CE;BELLHOP BELL;So;0;ON;;;;;N;;;;; 1F6CF;BED;So;0;ON;;;;;N;;;;; 1F6D0;PLACE OF WORSHIP;So;0;ON;;;;;N;;;;; +1F6D1;OCTAGONAL SIGN;So;0;ON;;;;;N;;;;; +1F6D2;SHOPPING TROLLEY;So;0;ON;;;;;N;;;;; +1F6D3;STUPA;So;0;ON;;;;;N;;;;; +1F6D4;PAGODA;So;0;ON;;;;;N;;;;; 1F6E0;HAMMER AND WRENCH;So;0;ON;;;;;N;;;;; 1F6E1;SHIELD;So;0;ON;;;;;N;;;;; 1F6E2;OIL DRUM;So;0;ON;;;;;N;;;;; @@ -27958,6 +30221,11 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F6F1;ONCOMING FIRE ENGINE;So;0;ON;;;;;N;;;;; 1F6F2;DIESEL LOCOMOTIVE;So;0;ON;;;;;N;;;;; 1F6F3;PASSENGER SHIP;So;0;ON;;;;;N;;;;; +1F6F4;SCOOTER;So;0;ON;;;;;N;;;;; +1F6F5;MOTOR SCOOTER;So;0;ON;;;;;N;;;;; +1F6F6;CANOE;So;0;ON;;;;;N;;;;; +1F6F7;SLED;So;0;ON;;;;;N;;;;; +1F6F8;FLYING SAUCER;So;0;ON;;;;;N;;;;; 1F700;ALCHEMICAL SYMBOL FOR QUINTESSENCE;So;0;ON;;;;;N;;;;; 1F701;ALCHEMICAL SYMBOL FOR AIR;So;0;ON;;;;;N;;;;; 1F702;ALCHEMICAL SYMBOL FOR FIRE;So;0;ON;;;;;N;;;;; @@ -28307,6 +30575,18 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F8AB;RIGHTWARDS FRONT-TILTED SHADOWED WHITE ARROW;So;0;ON;;;;;N;;;;; 1F8AC;WHITE ARROW SHAFT WIDTH ONE;So;0;ON;;;;;N;;;;; 1F8AD;WHITE ARROW SHAFT WIDTH TWO THIRDS;So;0;ON;;;;;N;;;;; +1F900;CIRCLED CROSS FORMEE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; +1F901;CIRCLED CROSS FORMEE WITH TWO DOTS;So;0;ON;;;;;N;;;;; +1F902;CIRCLED CROSS FORMEE;So;0;ON;;;;;N;;;;; +1F903;LEFT HALF CIRCLE WITH FOUR DOTS;So;0;ON;;;;;N;;;;; +1F904;LEFT HALF CIRCLE WITH THREE DOTS;So;0;ON;;;;;N;;;;; +1F905;LEFT HALF CIRCLE WITH TWO DOTS;So;0;ON;;;;;N;;;;; +1F906;LEFT HALF CIRCLE WITH DOT;So;0;ON;;;;;N;;;;; +1F907;LEFT HALF CIRCLE;So;0;ON;;;;;N;;;;; +1F908;DOWNWARD FACING HOOK;So;0;ON;;;;;N;;;;; +1F909;DOWNWARD FACING NOTCHED HOOK;So;0;ON;;;;;N;;;;; +1F90A;DOWNWARD FACING HOOK WITH DOT;So;0;ON;;;;;N;;;;; +1F90B;DOWNWARD FACING NOTCHED HOOK WITH DOT;So;0;ON;;;;;N;;;;; 1F910;ZIPPER-MOUTH FACE;So;0;ON;;;;;N;;;;; 1F911;MONEY-MOUTH FACE;So;0;ON;;;;;N;;;;; 1F912;FACE WITH THERMOMETER;So;0;ON;;;;;N;;;;; @@ -28316,12 +30596,133 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1F916;ROBOT FACE;So;0;ON;;;;;N;;;;; 1F917;HUGGING FACE;So;0;ON;;;;;N;;;;; 1F918;SIGN OF THE HORNS;So;0;ON;;;;;N;;;;; +1F919;CALL ME HAND;So;0;ON;;;;;N;;;;; +1F91A;RAISED BACK OF HAND;So;0;ON;;;;;N;;;;; +1F91B;LEFT-FACING FIST;So;0;ON;;;;;N;;;;; +1F91C;RIGHT-FACING FIST;So;0;ON;;;;;N;;;;; +1F91D;HANDSHAKE;So;0;ON;;;;;N;;;;; +1F91E;HAND WITH INDEX AND MIDDLE FINGERS CROSSED;So;0;ON;;;;;N;;;;; +1F91F;I LOVE YOU HAND SIGN;So;0;ON;;;;;N;;;;; +1F920;FACE WITH COWBOY HAT;So;0;ON;;;;;N;;;;; +1F921;CLOWN FACE;So;0;ON;;;;;N;;;;; +1F922;NAUSEATED FACE;So;0;ON;;;;;N;;;;; +1F923;ROLLING ON THE FLOOR LAUGHING;So;0;ON;;;;;N;;;;; +1F924;DROOLING FACE;So;0;ON;;;;;N;;;;; +1F925;LYING FACE;So;0;ON;;;;;N;;;;; +1F926;FACE PALM;So;0;ON;;;;;N;;;;; +1F927;SNEEZING FACE;So;0;ON;;;;;N;;;;; +1F928;FACE WITH ONE EYEBROW RAISED;So;0;ON;;;;;N;;;;; +1F929;GRINNING FACE WITH STAR EYES;So;0;ON;;;;;N;;;;; +1F92A;GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE;So;0;ON;;;;;N;;;;; +1F92B;FACE WITH FINGER COVERING CLOSED LIPS;So;0;ON;;;;;N;;;;; +1F92C;SERIOUS FACE WITH SYMBOLS COVERING MOUTH;So;0;ON;;;;;N;;;;; +1F92D;SMILING FACE WITH SMILING EYES AND HAND COVERING MOUTH;So;0;ON;;;;;N;;;;; +1F92E;FACE WITH OPEN MOUTH VOMITING;So;0;ON;;;;;N;;;;; +1F92F;SHOCKED FACE WITH EXPLODING HEAD;So;0;ON;;;;;N;;;;; +1F930;PREGNANT WOMAN;So;0;ON;;;;;N;;;;; +1F931;BREAST-FEEDING;So;0;ON;;;;;N;;;;; +1F932;PALMS UP TOGETHER;So;0;ON;;;;;N;;;;; +1F933;SELFIE;So;0;ON;;;;;N;;;;; +1F934;PRINCE;So;0;ON;;;;;N;;;;; +1F935;MAN IN TUXEDO;So;0;ON;;;;;N;;;;; +1F936;MOTHER CHRISTMAS;So;0;ON;;;;;N;;;;; +1F937;SHRUG;So;0;ON;;;;;N;;;;; +1F938;PERSON DOING CARTWHEEL;So;0;ON;;;;;N;;;;; +1F939;JUGGLING;So;0;ON;;;;;N;;;;; +1F93A;FENCER;So;0;ON;;;;;N;;;;; +1F93B;MODERN PENTATHLON;So;0;ON;;;;;N;;;;; +1F93C;WRESTLERS;So;0;ON;;;;;N;;;;; +1F93D;WATER POLO;So;0;ON;;;;;N;;;;; +1F93E;HANDBALL;So;0;ON;;;;;N;;;;; +1F940;WILTED FLOWER;So;0;ON;;;;;N;;;;; +1F941;DRUM WITH DRUMSTICKS;So;0;ON;;;;;N;;;;; +1F942;CLINKING GLASSES;So;0;ON;;;;;N;;;;; +1F943;TUMBLER GLASS;So;0;ON;;;;;N;;;;; +1F944;SPOON;So;0;ON;;;;;N;;;;; +1F945;GOAL NET;So;0;ON;;;;;N;;;;; +1F946;RIFLE;So;0;ON;;;;;N;;;;; +1F947;FIRST PLACE MEDAL;So;0;ON;;;;;N;;;;; +1F948;SECOND PLACE MEDAL;So;0;ON;;;;;N;;;;; +1F949;THIRD PLACE MEDAL;So;0;ON;;;;;N;;;;; +1F94A;BOXING GLOVE;So;0;ON;;;;;N;;;;; +1F94B;MARTIAL ARTS UNIFORM;So;0;ON;;;;;N;;;;; +1F94C;CURLING STONE;So;0;ON;;;;;N;;;;; +1F950;CROISSANT;So;0;ON;;;;;N;;;;; +1F951;AVOCADO;So;0;ON;;;;;N;;;;; +1F952;CUCUMBER;So;0;ON;;;;;N;;;;; +1F953;BACON;So;0;ON;;;;;N;;;;; +1F954;POTATO;So;0;ON;;;;;N;;;;; +1F955;CARROT;So;0;ON;;;;;N;;;;; +1F956;BAGUETTE BREAD;So;0;ON;;;;;N;;;;; +1F957;GREEN SALAD;So;0;ON;;;;;N;;;;; +1F958;SHALLOW PAN OF FOOD;So;0;ON;;;;;N;;;;; +1F959;STUFFED FLATBREAD;So;0;ON;;;;;N;;;;; +1F95A;EGG;So;0;ON;;;;;N;;;;; +1F95B;GLASS OF MILK;So;0;ON;;;;;N;;;;; +1F95C;PEANUTS;So;0;ON;;;;;N;;;;; +1F95D;KIWIFRUIT;So;0;ON;;;;;N;;;;; +1F95E;PANCAKES;So;0;ON;;;;;N;;;;; +1F95F;DUMPLING;So;0;ON;;;;;N;;;;; +1F960;FORTUNE COOKIE;So;0;ON;;;;;N;;;;; +1F961;TAKEOUT BOX;So;0;ON;;;;;N;;;;; +1F962;CHOPSTICKS;So;0;ON;;;;;N;;;;; +1F963;BOWL WITH SPOON;So;0;ON;;;;;N;;;;; +1F964;CUP WITH STRAW;So;0;ON;;;;;N;;;;; +1F965;COCONUT;So;0;ON;;;;;N;;;;; +1F966;BROCCOLI;So;0;ON;;;;;N;;;;; +1F967;PIE;So;0;ON;;;;;N;;;;; +1F968;PRETZEL;So;0;ON;;;;;N;;;;; +1F969;CUT OF MEAT;So;0;ON;;;;;N;;;;; +1F96A;SANDWICH;So;0;ON;;;;;N;;;;; +1F96B;CANNED FOOD;So;0;ON;;;;;N;;;;; 1F980;CRAB;So;0;ON;;;;;N;;;;; 1F981;LION FACE;So;0;ON;;;;;N;;;;; 1F982;SCORPION;So;0;ON;;;;;N;;;;; 1F983;TURKEY;So;0;ON;;;;;N;;;;; 1F984;UNICORN FACE;So;0;ON;;;;;N;;;;; +1F985;EAGLE;So;0;ON;;;;;N;;;;; +1F986;DUCK;So;0;ON;;;;;N;;;;; +1F987;BAT;So;0;ON;;;;;N;;;;; +1F988;SHARK;So;0;ON;;;;;N;;;;; +1F989;OWL;So;0;ON;;;;;N;;;;; +1F98A;FOX FACE;So;0;ON;;;;;N;;;;; +1F98B;BUTTERFLY;So;0;ON;;;;;N;;;;; +1F98C;DEER;So;0;ON;;;;;N;;;;; +1F98D;GORILLA;So;0;ON;;;;;N;;;;; +1F98E;LIZARD;So;0;ON;;;;;N;;;;; +1F98F;RHINOCEROS;So;0;ON;;;;;N;;;;; +1F990;SHRIMP;So;0;ON;;;;;N;;;;; +1F991;SQUID;So;0;ON;;;;;N;;;;; +1F992;GIRAFFE FACE;So;0;ON;;;;;N;;;;; +1F993;ZEBRA FACE;So;0;ON;;;;;N;;;;; +1F994;HEDGEHOG;So;0;ON;;;;;N;;;;; +1F995;SAUROPOD;So;0;ON;;;;;N;;;;; +1F996;T-REX;So;0;ON;;;;;N;;;;; +1F997;CRICKET;So;0;ON;;;;;N;;;;; 1F9C0;CHEESE WEDGE;So;0;ON;;;;;N;;;;; +1F9D0;FACE WITH MONOCLE;So;0;ON;;;;;N;;;;; +1F9D1;ADULT;So;0;ON;;;;;N;;;;; +1F9D2;CHILD;So;0;ON;;;;;N;;;;; +1F9D3;OLDER ADULT;So;0;ON;;;;;N;;;;; +1F9D4;BEARDED PERSON;So;0;ON;;;;;N;;;;; +1F9D5;PERSON WITH HEADSCARF;So;0;ON;;;;;N;;;;; +1F9D6;PERSON IN STEAMY ROOM;So;0;ON;;;;;N;;;;; +1F9D7;PERSON CLIMBING;So;0;ON;;;;;N;;;;; +1F9D8;PERSON IN LOTUS POSITION;So;0;ON;;;;;N;;;;; +1F9D9;MAGE;So;0;ON;;;;;N;;;;; +1F9DA;FAIRY;So;0;ON;;;;;N;;;;; +1F9DB;VAMPIRE;So;0;ON;;;;;N;;;;; +1F9DC;MERPERSON;So;0;ON;;;;;N;;;;; +1F9DD;ELF;So;0;ON;;;;;N;;;;; +1F9DE;GENIE;So;0;ON;;;;;N;;;;; +1F9DF;ZOMBIE;So;0;ON;;;;;N;;;;; +1F9E0;BRAIN;So;0;ON;;;;;N;;;;; +1F9E1;ORANGE HEART;So;0;ON;;;;;N;;;;; +1F9E2;BILLED CAP;So;0;ON;;;;;N;;;;; +1F9E3;SCARF;So;0;ON;;;;;N;;;;; +1F9E4;GLOVES;So;0;ON;;;;;N;;;;; +1F9E5;COAT;So;0;ON;;;;;N;;;;; +1F9E6;SOCKS;So;0;ON;;;;;N;;;;; 20000;<CJK Ideograph Extension B, First>;Lo;0;L;;;;;N;;;;; 2A6D6;<CJK Ideograph Extension B, Last>;Lo;0;L;;;;;N;;;;; 2A700;<CJK Ideograph Extension C, First>;Lo;0;L;;;;;N;;;;; @@ -28330,6 +30731,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 2B81D;<CJK Ideograph Extension D, Last>;Lo;0;L;;;;;N;;;;; 2B820;<CJK Ideograph Extension E, First>;Lo;0;L;;;;;N;;;;; 2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;; +2CEB0;<CJK Ideograph Extension F, First>;Lo;0;L;;;;;N;;;;; +2EBE0;<CJK Ideograph Extension F, Last>;Lo;0;L;;;;;N;;;;; 2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;; 2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;; 2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;; diff --git a/gnu/usr.bin/perl/lib/unicore/auxiliary/GCBTest.txt b/gnu/usr.bin/perl/lib/unicore/auxiliary/GCBTest.txt index a3ed239c95a..d7d8f90de07 100644 --- a/gnu/usr.bin/perl/lib/unicore/auxiliary/GCBTest.txt +++ b/gnu/usr.bin/perl/lib/unicore/auxiliary/GCBTest.txt @@ -1,22 +1,24 @@ -# GraphemeBreakTest-8.0.0.txt -# Date: 2015-02-13, 13:47:15 GMT [MD] +# GraphemeBreakTest-10.0.0.txt +# Date: 2017-04-14, 05:40:29 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # -# Default Grapheme Break Test +# Default Grapheme_Cluster_Break Test # # Format: -# <string> (# <comment>)? -# <string> contains hex Unicode code points, with -# ÷ wherever there is a break opportunity, and +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and # × wherever there is not. # <comment> the format can change, but currently it shows: # - the sample character name # - (x) the Grapheme_Cluster_Break property value for the sample character -# - [x] the rule that determines whether there is a break or not +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of GraphemeBreakTest.html # # These samples may be extended or changed in the future. # @@ -30,6 +32,8 @@ ÷ 0020 × 0308 ÷ 0001 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 0020 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 0020 × 0308 × 0300 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0020 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0020 × 0308 ÷ 0600 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 0020 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0020 × 0308 × 0903 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0020 ÷ 1100 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -42,8 +46,18 @@ ÷ 0020 × 0308 ÷ AC00 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 0020 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 0020 × 0308 ÷ AC01 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 0020 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0020 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0020 ÷ 261D ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0020 × 0308 ÷ 261D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0020 ÷ 1F3FB ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0020 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0020 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0020 × 0308 × 200D ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0020 ÷ 2640 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0020 × 0308 ÷ 2640 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0020 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 0020 × 0308 ÷ 1F466 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0020 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0020 × 0308 ÷ 0378 ÷ # ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0020 ÷ D800 ÷ # ÷ [0.2] SPACE (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -58,6 +72,8 @@ ÷ 000D ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 000D ÷ 0308 × 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 000D ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 000D ÷ 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 000D ÷ 0308 × 0903 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 000D ÷ 1100 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -70,8 +86,18 @@ ÷ 000D ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 000D ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 000D ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 000D ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 000D ÷ 261D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 000D ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 000D ÷ 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 000D ÷ 0308 × 200D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 000D ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000D ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] BOY (EBG) ÷ [0.3] +÷ 000D ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000D ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] ÷ 000D ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 000D ÷ D800 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3] @@ -86,6 +112,8 @@ ÷ 000A ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 000A ÷ 0308 × 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 000A ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 000A ÷ 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 000A ÷ 0308 × 0903 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 000A ÷ 1100 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -98,8 +126,18 @@ ÷ 000A ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 000A ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 000A ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 000A ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 000A ÷ 261D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 000A ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 000A ÷ 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 000A ÷ 0308 × 200D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 000A ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 000A ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] BOY (EBG) ÷ [0.3] +÷ 000A ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 000A ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] ÷ 000A ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 000A ÷ D800 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3] @@ -114,6 +152,8 @@ ÷ 0001 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 0001 ÷ 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 0001 ÷ 0308 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0001 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 0001 ÷ 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0001 ÷ 0308 × 0903 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0001 ÷ 1100 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -126,8 +166,18 @@ ÷ 0001 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 0001 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 0001 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 0001 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0001 ÷ 261D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0001 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0001 ÷ 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0001 ÷ 0308 × 200D ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0001 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0001 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3] +÷ 0001 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0001 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0001 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0001 ÷ D800 ÷ # ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3] @@ -142,6 +192,8 @@ ÷ 0300 × 0308 ÷ 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0300 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0300 × 0308 ÷ 0600 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 0300 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0300 × 0308 × 0903 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0300 ÷ 1100 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -154,12 +206,62 @@ ÷ 0300 × 0308 ÷ AC00 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 0300 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 0300 × 0308 ÷ AC01 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 0300 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0300 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0300 ÷ 261D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0300 × 0308 ÷ 261D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0300 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0300 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0300 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0300 × 0308 × 200D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0300 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0300 × 0308 ÷ 2640 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0300 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 0300 × 0308 ÷ 1F466 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0300 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0300 × 0308 ÷ 0378 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0300 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ 0300 × 0308 ÷ D800 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 0600 × 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] SPACE (Other) ÷ [0.3] +÷ 0600 × 0308 ÷ 0020 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 0600 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0600 × 0308 ÷ 000D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0600 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0600 × 0308 ÷ 000A ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0600 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 0600 × 0308 ÷ 0001 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 0600 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0600 × 0308 × 0300 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0600 × 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0600 × 0308 ÷ 0600 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0600 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 0600 × 0308 × 0903 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 0600 × 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 0600 × 0308 ÷ 1100 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 0600 × 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 0600 × 0308 ÷ 1160 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 0600 × 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 0600 × 0308 ÷ 11A8 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 0600 × AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 0600 × 0308 ÷ AC00 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 0600 × AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 0600 × 0308 ÷ AC01 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 0600 × 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0600 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0600 × 261D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0600 × 0308 ÷ 261D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0600 × 1F3FB ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0600 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0600 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0600 × 0308 × 200D ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0600 × 2640 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0600 × 0308 ÷ 2640 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0600 × 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] BOY (EBG) ÷ [0.3] +÷ 0600 × 0308 ÷ 1F466 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 0600 × 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] <reserved-0378> (Other) ÷ [0.3] +÷ 0600 × 0308 ÷ 0378 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 0600 ÷ D800 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 0600 × 0308 ÷ D800 ÷ # ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ 0903 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 0903 × 0308 ÷ 0020 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 0903 ÷ 000D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] @@ -170,6 +272,8 @@ ÷ 0903 × 0308 ÷ 0001 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 0903 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 0903 × 0308 × 0300 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0903 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0903 × 0308 ÷ 0600 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 0903 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0903 × 0308 × 0903 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0903 ÷ 1100 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -182,8 +286,18 @@ ÷ 0903 × 0308 ÷ AC00 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 0903 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 0903 × 0308 ÷ AC01 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 0903 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0903 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0903 ÷ 261D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0903 × 0308 ÷ 261D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0903 ÷ 1F3FB ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0903 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0903 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0903 × 0308 × 200D ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0903 ÷ 2640 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0903 × 0308 ÷ 2640 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0903 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 0903 × 0308 ÷ 1F466 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0903 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0903 × 0308 ÷ 0378 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0903 ÷ D800 ÷ # ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -198,6 +312,8 @@ ÷ 1100 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 1100 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 1100 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1100 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1100 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 1100 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 1100 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -210,8 +326,18 @@ ÷ 1100 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 1100 × AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 1100 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 1100 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1100 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1100 ÷ 261D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1100 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1100 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1100 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1100 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1100 × 0308 × 200D ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1100 ÷ 2640 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1100 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1100 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1100 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1100 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 1100 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 1100 ÷ D800 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -226,6 +352,8 @@ ÷ 1160 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 1160 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 1160 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1160 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1160 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 1160 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 1160 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 1160 ÷ 1100 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -238,8 +366,18 @@ ÷ 1160 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 1160 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 1160 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 1160 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1160 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1160 ÷ 261D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1160 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1160 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1160 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1160 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1160 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1160 ÷ 2640 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1160 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1160 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1160 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 1160 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 1160 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 1160 ÷ D800 ÷ # ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -254,6 +392,8 @@ ÷ 11A8 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 11A8 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 11A8 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 11A8 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 11A8 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 11A8 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 11A8 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -266,8 +406,18 @@ ÷ 11A8 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 11A8 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 11A8 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 11A8 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 11A8 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 11A8 ÷ 261D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 11A8 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 11A8 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 11A8 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 11A8 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 11A8 × 0308 × 200D ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 11A8 ÷ 2640 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 11A8 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 11A8 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 11A8 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 11A8 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 11A8 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 11A8 ÷ D800 ÷ # ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -282,6 +432,8 @@ ÷ AC00 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ AC00 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ AC00 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ AC00 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ AC00 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ AC00 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ AC00 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ AC00 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -294,8 +446,18 @@ ÷ AC00 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ AC00 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ AC00 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ AC00 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ AC00 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ AC00 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ AC00 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ AC00 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ AC00 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ AC00 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ AC00 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ AC00 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC00 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC00 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ AC00 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC00 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ AC00 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ AC00 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -310,6 +472,8 @@ ÷ AC01 × 0308 ÷ 0001 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ AC01 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ AC01 × 0308 × 0300 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ AC01 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ AC01 × 0308 ÷ 0600 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ AC01 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ AC01 × 0308 × 0903 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ AC01 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -322,40 +486,262 @@ ÷ AC01 × 0308 ÷ AC00 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ AC01 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ AC01 × 0308 ÷ AC01 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ AC01 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ AC01 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ AC01 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ AC01 × 0308 ÷ 261D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ AC01 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ AC01 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ AC01 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ AC01 × 0308 × 200D ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ AC01 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC01 × 0308 ÷ 2640 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ AC01 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ AC01 × 0308 ÷ 1F466 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ AC01 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ AC01 × 0308 ÷ 0378 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ AC01 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ AC01 × 0308 ÷ D800 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] -÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] SPACE (Other) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] -÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] -÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] -÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] -÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] -÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] -÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] -÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] -÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] -÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] -÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] -÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] -÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] -÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] -÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F1E6 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 0020 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F1E6 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 000D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F1E6 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 000A ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F1E6 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 0001 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F1E6 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F1E6 × 0308 × 0300 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F1E6 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 0600 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F1E6 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F1E6 × 0308 × 0903 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F1E6 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 1100 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F1E6 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 1160 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F1E6 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 11A8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F1E6 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ AC00 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F1E6 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ AC01 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F1E6 × 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F1E6 ÷ 261D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 261D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F1E6 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F1E6 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F1E6 × 0308 × 200D ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F1E6 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 2640 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F1E6 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 1F466 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F1E6 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ 0378 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F1E6 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F1E6 × 0308 ÷ D800 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 261D ÷ 0020 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 261D × 0308 ÷ 0020 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 261D ÷ 000D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 261D × 0308 ÷ 000D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 261D ÷ 000A ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 261D × 0308 ÷ 000A ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 261D ÷ 0001 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 261D × 0308 ÷ 0001 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 261D × 0300 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 261D × 0308 × 0300 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 261D ÷ 0600 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 261D × 0308 ÷ 0600 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 261D × 0903 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 261D × 0308 × 0903 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 261D ÷ 1100 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 261D × 0308 ÷ 1100 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 261D ÷ 1160 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 261D × 0308 ÷ 1160 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 261D ÷ 11A8 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 261D × 0308 ÷ 11A8 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 261D ÷ AC00 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 261D × 0308 ÷ AC00 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 261D ÷ AC01 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 261D × 0308 ÷ AC01 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 261D ÷ 1F1E6 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 261D × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 261D ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 261D × 0308 ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 261D × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 261D × 0308 × 1F3FB ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 261D × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 261D × 0308 × 200D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 261D ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 261D × 0308 ÷ 2640 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 261D ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 261D × 0308 ÷ 1F466 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 261D ÷ 0378 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 261D × 0308 ÷ 0378 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 261D ÷ D800 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 261D × 0308 ÷ D800 ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F3FB ÷ 0020 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 0020 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F3FB ÷ 000D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 000D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F3FB ÷ 000A ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 000A ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F3FB ÷ 0001 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 0001 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F3FB × 0300 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F3FB × 0308 × 0300 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F3FB ÷ 0600 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 0600 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F3FB × 0903 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F3FB × 0308 × 0903 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F3FB ÷ 1100 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 1100 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F3FB ÷ 1160 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 1160 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F3FB ÷ 11A8 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 11A8 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F3FB ÷ AC00 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F3FB × 0308 ÷ AC00 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F3FB ÷ AC01 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F3FB × 0308 ÷ AC01 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F3FB ÷ 1F1E6 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F3FB ÷ 261D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 261D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F3FB ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 1F3FB ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F3FB × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F3FB × 0308 × 200D ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F3FB ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 2640 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F3FB ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 1F466 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F3FB ÷ 0378 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F3FB × 0308 ÷ 0378 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F3FB ÷ D800 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F3FB × 0308 ÷ D800 ÷ # ÷ [0.2] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 200D ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 200D × 0308 ÷ 0020 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 200D ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 200D × 0308 ÷ 000D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 200D ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 200D × 0308 ÷ 000A ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 200D ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 200D × 0308 ÷ 0001 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 200D × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 200D × 0308 × 0300 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 200D ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 200D × 0308 ÷ 0600 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 200D × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 200D × 0308 × 0903 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 200D ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 200D × 0308 ÷ 1100 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 200D ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 200D × 0308 ÷ 1160 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 200D ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 200D × 0308 ÷ 11A8 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 200D ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 200D × 0308 ÷ AC00 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 200D ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 200D × 0308 ÷ AC01 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 200D ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 200D × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 200D ÷ 261D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 200D × 0308 ÷ 261D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 200D ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 200D × 0308 ÷ 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 200D × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 200D × 0308 × 200D ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 0308 ÷ 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) ÷ [0.3] +÷ 200D × 0308 ÷ 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 200D ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 200D × 0308 ÷ 0378 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 200D ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 200D × 0308 ÷ D800 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 2640 ÷ 0020 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 2640 × 0308 ÷ 0020 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 2640 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 × 0308 ÷ 000D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 2640 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 × 0308 ÷ 000A ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 2640 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 2640 × 0308 ÷ 0001 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 2640 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 2640 × 0308 × 0300 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 2640 ÷ 0600 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 2640 × 0308 ÷ 0600 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 2640 × 0903 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 2640 × 0308 × 0903 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 2640 ÷ 1100 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 2640 × 0308 ÷ 1100 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 2640 ÷ 1160 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 2640 × 0308 ÷ 1160 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 2640 ÷ 11A8 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 2640 × 0308 ÷ 11A8 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 2640 ÷ AC00 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 2640 × 0308 ÷ AC00 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 2640 ÷ AC01 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 2640 × 0308 ÷ AC01 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 2640 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 2640 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 × 0308 ÷ 261D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 2640 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 2640 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 2640 × 0308 × 200D ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 2640 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 × 0308 ÷ 2640 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 2640 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 × 0308 ÷ 1F466 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 2640 ÷ 0378 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 2640 × 0308 ÷ 0378 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 2640 ÷ D800 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 2640 × 0308 ÷ D800 ÷ # ÷ [0.2] FEMALE SIGN (Glue_After_Zwj) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F466 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F466 × 0308 ÷ 0020 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1F466 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F466 × 0308 ÷ 000D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 1F466 ÷ 000A ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F466 × 0308 ÷ 000A ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 1F466 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F466 × 0308 ÷ 0001 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] +÷ 1F466 × 0300 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F466 × 0308 × 0300 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 1F466 ÷ 0600 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F466 × 0308 ÷ 0600 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 1F466 × 0903 ÷ # ÷ [0.2] BOY (EBG) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F466 × 0308 × 0903 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] +÷ 1F466 ÷ 1100 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F466 × 0308 ÷ 1100 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F466 ÷ 1160 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F466 × 0308 ÷ 1160 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3] +÷ 1F466 ÷ 11A8 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F466 × 0308 ÷ 11A8 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3] +÷ 1F466 ÷ AC00 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F466 × 0308 ÷ AC00 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] +÷ 1F466 ÷ AC01 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F466 × 0308 ÷ AC01 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] +÷ 1F466 ÷ 1F1E6 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F466 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 1F466 ÷ 261D ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F466 × 0308 ÷ 261D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F466 × 0308 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 1F466 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F466 × 0308 × 200D ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 1F466 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 × 0308 ÷ 2640 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F466 × 0308 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 1F466 ÷ 0378 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F466 × 0308 ÷ 0378 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] +÷ 1F466 ÷ D800 ÷ # ÷ [0.2] BOY (EBG) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] +÷ 1F466 × 0308 ÷ D800 ÷ # ÷ [0.2] BOY (EBG) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] ÷ 0378 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 0378 × 0308 ÷ 0020 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] ÷ 0378 ÷ 000D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] @@ -366,6 +752,8 @@ ÷ 0378 × 0308 ÷ 0001 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ 0378 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ 0378 × 0308 × 0300 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ 0378 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ 0378 × 0308 ÷ 0600 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ 0378 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0378 × 0308 × 0903 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ 0378 ÷ 1100 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -378,8 +766,18 @@ ÷ 0378 × 0308 ÷ AC00 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ 0378 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ 0378 × 0308 ÷ AC01 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ 0378 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0378 × 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ 0378 ÷ 261D ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0378 × 0308 ÷ 261D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 0378 ÷ 1F3FB ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0378 × 0308 ÷ 1F3FB ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 0378 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0378 × 0308 × 200D ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0378 ÷ 2640 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0378 × 0308 ÷ 2640 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 0378 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] BOY (EBG) ÷ [0.3] +÷ 0378 × 0308 ÷ 1F466 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ 0378 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0378 × 0308 ÷ 0378 ÷ # ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ 0378 ÷ D800 ÷ # ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] @@ -394,6 +792,8 @@ ÷ D800 ÷ 0308 ÷ 0001 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3] ÷ D800 ÷ 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] ÷ D800 ÷ 0308 × 0300 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend) ÷ [0.3] +÷ D800 ÷ 0600 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 0600 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3] ÷ D800 ÷ 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ D800 ÷ 0308 × 0903 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3] ÷ D800 ÷ 1100 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] @@ -406,23 +806,45 @@ ÷ D800 ÷ 0308 ÷ AC00 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3] ÷ D800 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] ÷ D800 ÷ 0308 ÷ AC01 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3] -÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] -÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [0.3] +÷ D800 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 1F1E6 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3] +÷ D800 ÷ 261D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 261D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ D800 ÷ 1F3FB ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 1F3FB ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ D800 ÷ 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ D800 ÷ 0308 × 200D ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ D800 ÷ 2640 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 2640 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ D800 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] BOY (EBG) ÷ [0.3] +÷ D800 ÷ 0308 ÷ 1F466 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] BOY (EBG) ÷ [0.3] ÷ D800 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3] ÷ D800 ÷ 0308 ÷ 0378 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3] ÷ D800 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] <surrogate-D800> (Control) ÷ [0.3] ÷ D800 ÷ 0308 ÷ D800 ÷ # ÷ [0.2] <surrogate-D800> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [5.0] <surrogate-D800> (Control) ÷ [0.3] -÷ 0061 ÷ 1F1E6 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] -÷ 1F1F7 × 1F1FA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [0.3] -÷ 1F1F7 × 1F1FA × 1F1F8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) ÷ [0.3] -÷ 1F1F7 × 1F1FA × 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3] -÷ 1F1F7 × 1F1FA ÷ 200B ÷ 1F1F8 × 1F1EA ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER R (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER U (Regional_Indicator) ÷ [5.0] ZERO WIDTH SPACE (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER S (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER E (Regional_Indicator) ÷ [0.3] -÷ 1F1E6 × 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3] -÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3] -÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (Regional_Indicator) × [8.1] REGIONAL INDICATOR SYMBOL LETTER B (Regional_Indicator) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (Regional_Indicator) ÷ [0.3] -÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3] -÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 000D × 000A ÷ 0061 ÷ 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend) ÷ [0.3] +÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [0.3] +÷ 0020 × 200D ÷ 0646 ÷ # ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3] +÷ 0646 × 200D ÷ 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] SPACE (Other) ÷ [0.3] +÷ 1100 × 1100 ÷ # ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ AC00 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ AC01 × 11A8 ÷ 1100 ÷ # ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3] +÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 ÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 ÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 × 1F1E9 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER D (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 × 200D ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ) ÷ [0.3] +÷ 0061 × 0308 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 × 0903 ÷ 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 0061 ÷ 0600 × 0062 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) × [9.2] LATIN SMALL LETTER B (Other) ÷ [0.3] +÷ 261D × 1F3FB ÷ 261D ÷ # ÷ [0.2] WHITE UP POINTING INDEX (E_Base) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [999.0] WHITE UP POINTING INDEX (E_Base) ÷ [0.3] +÷ 1F466 × 1F3FB ÷ # ÷ [0.2] BOY (EBG) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 200D × 1F466 × 1F3FB ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) × [10.0] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (E_Modifier) ÷ [0.3] +÷ 200D × 2640 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] FEMALE SIGN (Glue_After_Zwj) ÷ [0.3] +÷ 200D × 1F466 ÷ # ÷ [0.2] ZERO WIDTH JOINER (ZWJ) × [11.0] BOY (EBG) ÷ [0.3] +÷ 1F466 ÷ 1F466 ÷ # ÷ [0.2] BOY (EBG) ÷ [999.0] BOY (EBG) ÷ [0.3] # -# Lines: 402 +# Lines: 822 # # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/auxiliary/GraphemeBreakProperty.txt b/gnu/usr.bin/perl/lib/unicore/auxiliary/GraphemeBreakProperty.txt index fba2ee8793d..32bb12e47e3 100644 --- a/gnu/usr.bin/perl/lib/unicore/auxiliary/GraphemeBreakProperty.txt +++ b/gnu/usr.bin/perl/lib/unicore/auxiliary/GraphemeBreakProperty.txt @@ -1,10 +1,11 @@ -# GraphemeBreakProperty-8.0.0.txt -# Date: 2015-02-13, 13:47:14 GMT [MD] +# GraphemeBreakProperty-10.0.0.txt +# Date: 2017-03-12, 07:03:41 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -17,6 +18,21 @@ # ================================================ +0600..0605 ; Prepend # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE +06DD ; Prepend # Cf ARABIC END OF AYAH +070F ; Prepend # Cf SYRIAC ABBREVIATION MARK +08E2 ; Prepend # Cf ARABIC DISPUTED END OF AYAH +0D4E ; Prepend # Lo MALAYALAM LETTER DOT REPH +110BD ; Prepend # Cf KAITHI NUMBER SIGN +111C2..111C3 ; Prepend # Lo [2] SHARADA SIGN JIHVAMULIYA..SHARADA SIGN UPADHMANIYA +11A3A ; Prepend # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A86..11A89 ; Prepend # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11D46 ; Prepend # Lo MASARAM GONDI REPHA + +# Total code points: 19 + +# ================================================ + 000D ; CR # Cc <control-000D> # Total code points: 1 @@ -34,10 +50,7 @@ 000E..001F ; Control # Cc [18] <control-000E>..<control-001F> 007F..009F ; Control # Cc [33] <control-007F>..<control-009F> 00AD ; Control # Cf SOFT HYPHEN -0600..0605 ; Control # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE 061C ; Control # Cf ARABIC LETTER MARK -06DD ; Control # Cf ARABIC END OF AYAH -070F ; Control # Cf SYRIAC ABBREVIATION MARK 180E ; Control # Cf MONGOLIAN VOWEL SEPARATOR 200B ; Control # Cf ZERO WIDTH SPACE 200E..200F ; Control # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -51,17 +64,15 @@ D800..DFFF ; Control # Cs [2048] <surrogate-D800>..<surrogate-DFFF> FEFF ; Control # Cf ZERO WIDTH NO-BREAK SPACE FFF0..FFF8 ; Control # Cn [9] <reserved-FFF0>..<reserved-FFF8> FFF9..FFFB ; Control # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR -110BD ; Control # Cf KAITHI NUMBER SIGN 1BCA0..1BCA3 ; Control # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Control # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0000 ; Control # Cn <reserved-E0000> E0001 ; Control # Cf LANGUAGE TAG E0002..E001F ; Control # Cn [30] <reserved-E0002>..<reserved-E001F> -E0020..E007F ; Control # Cf [96] TAG SPACE..CANCEL TAG E0080..E00FF ; Control # Cn [128] <reserved-E0080>..<reserved-E00FF> E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> -# Total code points: 6030 +# Total code points: 5925 # ================================================ @@ -89,6 +100,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE 093C ; Extend # Mn DEVANAGARI SIGN NUKTA @@ -117,6 +129,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B3C ; Extend # Mn ORIYA SIGN NUKTA 0B3E ; Extend # Mc ORIYA VOWEL SIGN AA @@ -145,7 +158,8 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E ; Extend # Mc MALAYALAM VOWEL SIGN AA 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA @@ -195,6 +209,7 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -233,9 +248,9 @@ E01F0..E0FFF ; Control # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW -200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -256,7 +271,7 @@ A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -309,6 +324,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Extend # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Extend # Mn KHOJKI SIGN SUKUN 112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -318,6 +334,9 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11357 ; Extend # Mc GRANTHA AU LENGTH MARK 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; Extend # Mn NEWA SIGN NUKTA 114B0 ; Extend # Mc TIRHUTA VOWEL SIGN AA 114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E @@ -339,6 +358,27 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -356,10 +396,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1610 +# Total code points: 1901 # ================================================ @@ -444,6 +491,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 1C34..1C35 ; SpacingMark # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG 1CE1 ; SpacingMark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF2..1CF3 ; SpacingMark # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF7 ; SpacingMark # Mc VEDIC SIGN ATIKRAMA A823..A824 ; SpacingMark # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A827 ; SpacingMark # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; SpacingMark # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA @@ -482,6 +530,9 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 11347..11348 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI 1134B..1134D ; SpacingMark # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA 11362..11363 ; SpacingMark # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11435..11437 ; SpacingMark # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11440..11441 ; SpacingMark # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11445 ; SpacingMark # Mc NEWA SIGN VISARGA 114B1..114B2 ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN I..TIRHUTA VOWEL SIGN II 114B9 ; SpacingMark # Mc TIRHUTA VOWEL SIGN E 114BB..114BC ; SpacingMark # Mc [2] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN O @@ -498,11 +549,20 @@ ABEC ; SpacingMark # Mc MEETEI MAYEK LUM IYEK 116B6 ; SpacingMark # Mc TAKRI SIGN VIRAMA 11720..11721 ; SpacingMark # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; SpacingMark # Mc AHOM VOWEL SIGN E +11A07..11A08 ; SpacingMark # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A39 ; SpacingMark # Mc ZANABAZAR SQUARE SIGN VISARGA +11A57..11A58 ; SpacingMark # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A97 ; SpacingMark # Mc SOYOMBO SIGN VISARGA +11C2F ; SpacingMark # Mc BHAIKSUKI VOWEL SIGN AA +11C3E ; SpacingMark # Mc BHAIKSUKI SIGN VISARGA +11CA9 ; SpacingMark # Mc MARCHEN SUBJOINED LETTER YA +11CB1 ; SpacingMark # Mc MARCHEN VOWEL SIGN I +11CB4 ; SpacingMark # Mc MARCHEN VOWEL SIGN O 16F51..16F7E ; SpacingMark # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 1D166 ; SpacingMark # Mc MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D ; SpacingMark # Mc MUSICAL SYMBOL COMBINING AUGMENTATION DOT -# Total code points: 330 +# Total code points: 348 # ================================================ @@ -1333,4 +1393,83 @@ D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH # Total code points: 10773 +# ================================================ + +261D ; E_Base # So WHITE UP POINTING INDEX +26F9 ; E_Base # So PERSON WITH BALL +270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND +1F385 ; E_Base # So FATHER CHRISTMAS +1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER +1F3C7 ; E_Base # So HORSE RACING +1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER +1F442..1F443 ; E_Base # So [2] EAR..NOSE +1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN +1F46E ; E_Base # So POLICE OFFICER +1F470..1F478 ; E_Base # So [9] BRIDE WITH VEIL..PRINCESS +1F47C ; E_Base # So BABY ANGEL +1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER +1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT +1F4AA ; E_Base # So FLEXED BICEPS +1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY +1F57A ; E_Base # So MAN DANCING +1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED +1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F645..1F647 ; E_Base # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY +1F64B..1F64F ; E_Base # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS +1F6A3 ; E_Base # So ROWBOAT +1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN +1F6C0 ; E_Base # So BATH +1F6CC ; E_Base # So SLEEPING ACCOMMODATION +1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN +1F926 ; E_Base # So FACE PALM +1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF + +# Total code points: 98 + +# ================================================ + +1F3FB..1F3FF ; E_Modifier # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 + +# Total code points: 5 + +# ================================================ + +200D ; ZWJ # Cf ZERO WIDTH JOINER + +# Total code points: 1 + +# ================================================ + +2640 ; Glue_After_Zwj # So FEMALE SIGN +2642 ; Glue_After_Zwj # So MALE SIGN +2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES +2708 ; Glue_After_Zwj # So AIRPLANE +2764 ; Glue_After_Zwj # So HEAVY BLACK HEART +1F308 ; Glue_After_Zwj # So RAINBOW +1F33E ; Glue_After_Zwj # So EAR OF RICE +1F373 ; Glue_After_Zwj # So COOKING +1F393 ; Glue_After_Zwj # So GRADUATION CAP +1F3A4 ; Glue_After_Zwj # So MICROPHONE +1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE +1F3EB ; Glue_After_Zwj # So SCHOOL +1F3ED ; Glue_After_Zwj # So FACTORY +1F48B ; Glue_After_Zwj # So KISS MARK +1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE +1F527 ; Glue_After_Zwj # So WRENCH +1F52C ; Glue_After_Zwj # So MICROSCOPE +1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE +1F680 ; Glue_After_Zwj # So ROCKET +1F692 ; Glue_After_Zwj # So FIRE ENGINE + +# Total code points: 22 + +# ================================================ + +1F466..1F469 ; E_Base_GAZ # So [4] BOY..WOMAN + +# Total code points: 4 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/auxiliary/SentenceBreakProperty.txt b/gnu/usr.bin/perl/lib/unicore/auxiliary/SentenceBreakProperty.txt index 8dd1abff0fd..cd698150f4b 100644 --- a/gnu/usr.bin/perl/lib/unicore/auxiliary/SentenceBreakProperty.txt +++ b/gnu/usr.bin/perl/lib/unicore/auxiliary/SentenceBreakProperty.txt @@ -1,10 +1,11 @@ -# SentenceBreakProperty-8.0.0.txt -# Date: 2015-03-11, 22:29:43 GMT [MD] +# SentenceBreakProperty-10.0.0.txt +# Date: 2017-03-08, 08:42:08 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -53,6 +54,7 @@ 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -95,6 +97,7 @@ 0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; Extend # Mn ORIYA SIGN NUKTA @@ -136,8 +139,9 @@ 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -207,6 +211,7 @@ 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU @@ -271,9 +276,10 @@ 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -299,7 +305,7 @@ A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -381,6 +387,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11234 ; Extend # Mn KHOJKI SIGN ANUSVARA 11235 ; Extend # Mc KHOJKI SIGN VIRAMA 11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Extend # Mn KHOJKI SIGN SUKUN 112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA 112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II 112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA @@ -396,6 +403,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; Extend # Mc NEWA SIGN VISARGA +11446 ; Extend # Mn NEWA SIGN NUKTA 114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E @@ -429,6 +442,36 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Extend # Mc AHOM VOWEL SIGN E 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Extend # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Extend # Mc BHAIKSUKI SIGN VISARGA +11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Extend # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Extend # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -447,10 +490,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1967 +# Total code points: 2277 # ================================================ @@ -467,6 +517,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 200B ; Format # Cf ZERO WIDTH SPACE 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -479,9 +530,8 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN 1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG -E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 148 +# Total code points: 53 # ================================================ @@ -776,6 +826,7 @@ E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG 052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Lower # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; Lower # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -1118,6 +1169,7 @@ FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE S FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Lower # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -1148,8 +1200,9 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1D7AA..1D7C2 ; Lower # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA +1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2172 +# Total code points: 2251 # ================================================ @@ -1745,11 +1798,12 @@ A7A2 ; Upper # L& LATIN CAPITAL LETTER K WITH OBLIQUE STROKE A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Upper # L& [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Upper # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Upper # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -1783,11 +1837,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1D756..1D76E ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA 1D790..1D7A8 ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7CA ; Upper # L& MATHEMATICAL BOLD CAPITAL DIGAMMA +1E900..1E921 ; Upper # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA 1F130..1F149 ; Upper # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1782 +# Total code points: 1853 # ================================================ @@ -1825,7 +1880,9 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; OLetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; OLetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; OLetter # Lo DEVANAGARI OM @@ -1843,6 +1900,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 09DC..09DD ; OLetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; OLetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; OLetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; OLetter # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; OLetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; OLetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; OLetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -1891,6 +1949,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; OLetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; OLetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; OLetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -1905,6 +1964,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0D12..0D3A ; OLetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; OLetter # Lo MALAYALAM SIGN AVAGRAHA 0D4E ; OLetter # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; OLetter # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D5F..0D61 ; OLetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D7A..0D7F ; OLetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; OLetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA @@ -1983,7 +2043,8 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1820..1842 ; OLetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; OLetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; OLetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; OLetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; OLetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; OLetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; OLetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; OLetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; OLetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -2035,12 +2096,12 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 30A1..30FA ; OLetter # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; OLetter # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; OLetter # Lo KATAKANA DIGRAPH KOTO -3105..312D ; OLetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; OLetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; OLetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; OLetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; OLetter # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; OLetter # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; OLetter # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; OLetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; OLetter # Lm YI SYLLABLE WU A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2138,7 +2199,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; OLetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; OLetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; OLetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; OLetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; OLetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; OLetter # Nl GOTHIC LETTER NINETY 10342..10349 ; OLetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; OLetter # Nl GOTHIC LETTER NINE HUNDRED @@ -2207,6 +2268,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA 11350 ; OLetter # Lo GRANTHA OM 1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; OLetter # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; OLetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; OLetter # Lo TIRHUTA OM @@ -2217,7 +2280,21 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 11700..11719 ; OLetter # Lo [26] AHOM LETTER KA..AHOM LETTER JHA 118FF ; OLetter # Lo WARANG CITI OM +11A00 ; OLetter # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; OLetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; OLetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; OLetter # Lo SOYOMBO LETTER A +11A5C..11A83 ; OLetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; OLetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; OLetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; OLetter # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; OLetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; OLetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; OLetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; OLetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; OLetter # Lo MASARAM GONDI REPHA 12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -2233,7 +2310,11 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; OLetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; OLetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; OLetter # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; OLetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; OLetter # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; OLetter # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; OLetter # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2276,9 +2357,10 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 2A700..2B734 ; OLetter # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 106002 +# Total code points: 121354 # ================================================ @@ -2325,16 +2407,20 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Numeric # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 542 +# Total code points: 582 # ================================================ @@ -2398,10 +2484,14 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA 1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK 112A9 ; STerm # Po MULTANI SECTION MARK +1144B..1144C ; STerm # Po [2] NEWA DANDA..NEWA DOUBLE DANDA 115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA 115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A42..11A43 ; STerm # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD +11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA 16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; STerm # Po BASSA VAH FULL STOP 16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB @@ -2409,7 +2499,7 @@ FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP 1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA88 ; STerm # Po SIGNWRITING FULL STOP -# Total code points: 117 +# Total code points: 125 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/auxiliary/WordBreakProperty.txt b/gnu/usr.bin/perl/lib/unicore/auxiliary/WordBreakProperty.txt index dc8e82020f2..4c5440a8941 100644 --- a/gnu/usr.bin/perl/lib/unicore/auxiliary/WordBreakProperty.txt +++ b/gnu/usr.bin/perl/lib/unicore/auxiliary/WordBreakProperty.txt @@ -1,10 +1,11 @@ -# WordBreakProperty-8.0.0.txt -# Date: 2015-02-14, 10:26:15 GMT [MD] +# WordBreakProperty-10.0.0.txt +# Date: 2017-03-10, 02:00:42 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -89,6 +90,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Extend # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -131,6 +133,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; Extend # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; Extend # Mn ORIYA SIGN NUKTA @@ -172,8 +175,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Extend # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -243,6 +247,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU @@ -307,10 +312,11 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1CED ; Extend # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; Extend # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Extend # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Extend # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW -200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -335,7 +341,7 @@ A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; Extend # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -417,6 +423,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11234 ; Extend # Mn KHOJKI SIGN ANUSVARA 11235 ; Extend # Mc KHOJKI SIGN VIRAMA 11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Extend # Mn KHOJKI SIGN SUKUN 112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA 112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II 112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA @@ -432,6 +439,12 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; Extend # Mc NEWA SIGN VISARGA +11446 ; Extend # Mn NEWA SIGN NUKTA 114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E @@ -465,6 +478,36 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11726 ; Extend # Mc AHOM VOWEL SIGN E 11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Extend # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; Extend # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; Extend # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Extend # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Extend # Mc BHAIKSUKI SIGN VISARGA +11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Extend # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Extend # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; Extend # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -483,10 +526,17 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1967 +# Total code points: 2276 # ================================================ @@ -501,6 +551,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -512,9 +563,8 @@ FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANN 1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP 1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE E0001 ; Format # Cf LANGUAGE TAG -E0020..E007F ; Format # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 147 +# Total code points: 52 # ================================================ @@ -551,10 +601,15 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0294 ; ALetter # Lo LATIN LETTER GLOTTAL STOP 0295..02AF ; ALetter # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ALetter # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP +02C2..02C5 ; ALetter # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; ALetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON +02D2..02D7 ; ALetter # Sk [6] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER MINUS SIGN +02DE..02DF ; ALetter # Sk [2] MODIFIER LETTER RHOTIC HOOK..MODIFIER LETTER CROSS ACCENT 02E0..02E4 ; ALetter # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP 02EC ; ALetter # Lm MODIFIER LETTER VOICING +02ED ; ALetter # Sk MODIFIER LETTER UNASPIRATED 02EE ; ALetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE +02EF..02FF ; ALetter # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW 0370..0373 ; ALetter # L& [4] GREEK CAPITAL LETTER HETA..GREEK SMALL LETTER ARCHAIC SAMPI 0374 ; ALetter # Lm GREEK NUMERAL SIGN 0376..0377 ; ALetter # L& [2] GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA..GREEK SMALL LETTER PAMPHYLIAN DIGAMMA @@ -594,7 +649,9 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0824 ; ALetter # Lm SAMARITAN MODIFIER LETTER SHORT A 0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; ALetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ALetter # Lo DEVANAGARI OM @@ -612,6 +669,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 09DC..09DD ; ALetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; ALetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ALetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; ALetter # Lo BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; ALetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ALetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ALetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -660,6 +718,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; ALetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; ALetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; ALetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -674,6 +733,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0D12..0D3A ; ALetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; ALetter # Lo MALAYALAM SIGN AVAGRAHA 0D4E ; ALetter # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; ALetter # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D5F..0D61 ; ALetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D7A..0D7F ; ALetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; ALetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA @@ -724,7 +784,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1820..1842 ; ALetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; ALetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; ALetter # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; ALetter # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; ALetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; ALetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; ALetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; ALetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; ALetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -738,6 +799,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1C4D..1C4F ; ALetter # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; ALetter # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; ALetter # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; ALetter # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CE9..1CEC ; ALetter # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL 1CEE..1CF1 ; ALetter # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF5..1CF6 ; ALetter # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA @@ -813,7 +875,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 3005 ; ALetter # Lm IDEOGRAPHIC ITERATION MARK 303B ; ALetter # Lm VERTICAL IDEOGRAPHIC ITERATION MARK 303C ; ALetter # Lo MASU MARK -3105..312D ; ALetter # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ALetter # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ALetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; ALetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY A000..A014 ; ALetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E @@ -833,13 +895,15 @@ A69C..A69D ; ALetter # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER A6A0..A6E5 ; ALetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI A6E6..A6EF ; ALetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM A717..A71F ; ALetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK +A720..A721 ; ALetter # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE A722..A76F ; ALetter # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON A770 ; ALetter # Lm MODIFIER LETTER US A771..A787 ; ALetter # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; ALetter # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; ALetter # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; ALetter # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -870,6 +934,7 @@ AB11..AB16 ; ALetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO AB20..AB26 ; ALetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO AB30..AB5A ; ALetter # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG +AB5B ; ALetter # Sk MODIFIER BREVE WITH INVERTED BREVE AB5C..AB5F ; ALetter # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB60..AB65 ; ALetter # L& [6] LATIN SMALL LETTER SAKHA YAT..GREEK LETTER SMALL CAPITAL OMEGA AB70..ABBF ; ALetter # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -904,7 +969,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10280..1029C ; ALetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; ALetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; ALetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; ALetter # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; ALetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; ALetter # Nl GOTHIC LETTER NINETY 10342..10349 ; ALetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; ALetter # Nl GOTHIC LETTER NINE HUNDRED @@ -915,6 +980,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 103D1..103D5 ; ALetter # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10400..1044F ; ALetter # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; ALetter # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +104B0..104D3 ; ALetter # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; ALetter # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ALetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ALetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 10600..10736 ; ALetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 @@ -976,6 +1043,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1133D ; ALetter # Lo GRANTHA SIGN AVAGRAHA 11350 ; ALetter # Lo GRANTHA OM 1135D..11361 ; ALetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; ALetter # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; ALetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; ALetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; ALetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; ALetter # Lo TIRHUTA OM @@ -986,7 +1055,21 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11680..116AA ; ALetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 118A0..118DF ; ALetter # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118FF ; ALetter # Lo WARANG CITI OM +11A00 ; ALetter # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; ALetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; ALetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; ALetter # Lo SOYOMBO LETTER A +11A5C..11A83 ; ALetter # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; ALetter # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; ALetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; ALetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; ALetter # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; ALetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; ALetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; ALetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; ALetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; ALetter # Lo MASARAM GONDI REPHA 12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1002,6 +1085,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F00..16F44 ; ALetter # Lo [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; ALetter # Lo MIAO LETTER NASALIZATION 16F93..16F9F ; ALetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 +16FE0..16FE1 ; ALetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1BC00..1BC6A ; ALetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ALetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ALetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1037,6 +1121,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D7AA..1D7C2 ; ALetter # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ALetter # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1E800..1E8C4 ; ALetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E900..1E943 ; ALetter # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1EE00..1EE03 ; ALetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; ALetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; ALetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1074,13 +1159,12 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 27697 +# Total code points: 28179 # ================================================ 003A ; MidLetter # Po COLON 00B7 ; MidLetter # Po MIDDLE DOT -02D7 ; MidLetter # Sk MODIFIER LETTER MINUS SIGN 0387 ; MidLetter # Po GREEK ANO TELEIA 05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM 2027 ; MidLetter # Po HYPHENATION POINT @@ -1088,7 +1172,7 @@ FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON FE55 ; MidLetter # Po SMALL COLON FF1A ; MidLetter # Po FULLWIDTH COLON -# Total code points: 9 +# Total code points: 8 # ================================================ @@ -1166,26 +1250,110 @@ ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT N 11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Numeric # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 541 +# Total code points: 581 # ================================================ 005F ; ExtendNumLet # Pc LOW LINE +202F ; ExtendNumLet # Zs NARROW NO-BREAK SPACE 203F..2040 ; ExtendNumLet # Pc [2] UNDERTIE..CHARACTER TIE 2054 ; ExtendNumLet # Pc INVERTED UNDERTIE FE33..FE34 ; ExtendNumLet # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE FE4D..FE4F ; ExtendNumLet # Pc [3] DASHED LOW LINE..WAVY LOW LINE FF3F ; ExtendNumLet # Pc FULLWIDTH LOW LINE -# Total code points: 10 +# Total code points: 11 + +# ================================================ + +261D ; E_Base # So WHITE UP POINTING INDEX +26F9 ; E_Base # So PERSON WITH BALL +270A..270D ; E_Base # So [4] RAISED FIST..WRITING HAND +1F385 ; E_Base # So FATHER CHRISTMAS +1F3C2..1F3C4 ; E_Base # So [3] SNOWBOARDER..SURFER +1F3C7 ; E_Base # So HORSE RACING +1F3CA..1F3CC ; E_Base # So [3] SWIMMER..GOLFER +1F442..1F443 ; E_Base # So [2] EAR..NOSE +1F446..1F450 ; E_Base # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN +1F46E ; E_Base # So POLICE OFFICER +1F470..1F478 ; E_Base # So [9] BRIDE WITH VEIL..PRINCESS +1F47C ; E_Base # So BABY ANGEL +1F481..1F483 ; E_Base # So [3] INFORMATION DESK PERSON..DANCER +1F485..1F487 ; E_Base # So [3] NAIL POLISH..HAIRCUT +1F4AA ; E_Base # So FLEXED BICEPS +1F574..1F575 ; E_Base # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY +1F57A ; E_Base # So MAN DANCING +1F590 ; E_Base # So RAISED HAND WITH FINGERS SPLAYED +1F595..1F596 ; E_Base # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F645..1F647 ; E_Base # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY +1F64B..1F64F ; E_Base # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS +1F6A3 ; E_Base # So ROWBOAT +1F6B4..1F6B6 ; E_Base # So [3] BICYCLIST..PEDESTRIAN +1F6C0 ; E_Base # So BATH +1F6CC ; E_Base # So SLEEPING ACCOMMODATION +1F918..1F91C ; E_Base # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; E_Base # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN +1F926 ; E_Base # So FACE PALM +1F930..1F939 ; E_Base # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; E_Base # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; E_Base # So [13] ADULT..ELF + +# Total code points: 98 + +# ================================================ + +1F3FB..1F3FF ; E_Modifier # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 + +# Total code points: 5 + +# ================================================ + +200D ; ZWJ # Cf ZERO WIDTH JOINER + +# Total code points: 1 + +# ================================================ + +2640 ; Glue_After_Zwj # So FEMALE SIGN +2642 ; Glue_After_Zwj # So MALE SIGN +2695..2696 ; Glue_After_Zwj # So [2] STAFF OF AESCULAPIUS..SCALES +2708 ; Glue_After_Zwj # So AIRPLANE +2764 ; Glue_After_Zwj # So HEAVY BLACK HEART +1F308 ; Glue_After_Zwj # So RAINBOW +1F33E ; Glue_After_Zwj # So EAR OF RICE +1F373 ; Glue_After_Zwj # So COOKING +1F393 ; Glue_After_Zwj # So GRADUATION CAP +1F3A4 ; Glue_After_Zwj # So MICROPHONE +1F3A8 ; Glue_After_Zwj # So ARTIST PALETTE +1F3EB ; Glue_After_Zwj # So SCHOOL +1F3ED ; Glue_After_Zwj # So FACTORY +1F48B ; Glue_After_Zwj # So KISS MARK +1F4BB..1F4BC ; Glue_After_Zwj # So [2] PERSONAL COMPUTER..BRIEFCASE +1F527 ; Glue_After_Zwj # So WRENCH +1F52C ; Glue_After_Zwj # So MICROSCOPE +1F5E8 ; Glue_After_Zwj # So LEFT SPEECH BUBBLE +1F680 ; Glue_After_Zwj # So ROCKET +1F692 ; Glue_After_Zwj # So FIRE ENGINE + +# Total code points: 22 + +# ================================================ + +1F466..1F469 ; E_Base_GAZ # So [4] BOY..WOMAN + +# Total code points: 4 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DBidiClass.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DBidiClass.txt index 9ec885e719a..ca9cc6ad9ae 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DBidiClass.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DBidiClass.txt @@ -1,10 +1,11 @@ -# DerivedBidiClass-8.0.0.txt -# Date: 2015-02-13, 13:47:08 GMT [MD] +# DerivedBidiClass-10.0.0.txt +# Date: 2017-03-08, 08:41:46 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -13,44 +14,21 @@ # reserved for right-to-left scripts are given either types R or AL. # # The unassigned code points that default to AL are in the ranges: -# [\u0600-\u07BF \u08A0-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U0001EE00-\U0001EEFF] +# [\u0600-\u07BF \u0860-\u086F \u08A0-\u08FF +# \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF \U0001EE00-\U0001EEFF] # -# Arabic: U+0600 - U+06FF -# Syriac: U+0700 - U+074F -# Arabic_Supplement: U+0750 - U+077F -# Thaana: U+0780 - U+07BF -# Arabic Extended-A: U+08A0 - U+08FF -# Arabic_Presentation_Forms_A: -# U+FB50 - U+FDCF -# U+FDF0 - U+FDFF -# Arabic_Presentation_Forms_B: -# U+FE70 - U+FEFF -# Arabic Mathematical Alphabetic Symbols: -# U+1EE00 - U+1EEFF +# This includes code points in the Arabic, Syriac, and Thaana blocks, among others. # # The unassigned code points that default to R are in the ranges: -# [\u0590-\u05FF \u07C0-\u089F \uFB1D-\uFB4F \U00010800-\U00010FFF \U0001E800-\U0001EDFF \U0001EF00-\U0001EFFF] +# [\u0590-\u05FF \u07C0-\u085F \u0870-\u089F \uFB1D-\uFB4F +# \U00010800-\U00010FFF \U0001E800-\U0001EDFF \U0001EF00-\U0001EFFF] # -# Hebrew: U+0590 - U+05FF -# NKo: U+07C0 - U+07FF -# Cypriot_Syllabary: U+10800 - U+1083F -# Phoenician: U+10900 - U+1091F -# Lydian: U+10920 - U+1093F -# Meroitic Hieroglyphs: -# U+10980 - U+1099F -# Meroitic Cursive: U+109A0 - U+109FF -# Kharoshthi: U+10A00 - U+10A5F -# and any others in the ranges: -# U+0800 - U+089F, -# U+FB1D - U+FB4F, -# U+10840 - U+10FFF, -# U+1E800 - U+1EDFF, -# U+1EF00 - U+1EFFF +# This includes code points in the Hebrew, NKo, and Phoenician blocks, among others. # # The unassigned code points that default to ET are in the range: # [\u20A0-\u20CF] # -# Currency Symbols: U+20A0 - U+20CF +# This consists of code points in the Currency Symbols block. # # The unassigned code points that default to BN have one of the following properties: # Default_Ignorable_Code_Point @@ -137,6 +115,8 @@ 09F0..09F1 ; L # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09F4..09F9 ; L # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; L # So BENGALI ISSHAR +09FC ; L # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; L # Po BENGALI ABBREVIATION SIGN 0A03 ; L # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; L # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; L # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -214,6 +194,7 @@ 0C60..0C61 ; L # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; L # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C7F ; L # So TELUGU SIGN TUUMU +0C80 ; L # Lo KANNADA SIGN SPACING CANDRABINDU 0C82..0C83 ; L # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; L # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; L # Lo [3] KANNADA LETTER E..KANNADA LETTER AI @@ -241,10 +222,13 @@ 0D46..0D48 ; L # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI 0D4A..0D4C ; L # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4E ; L # Lo MALAYALAM LETTER DOT REPH +0D4F ; L # So MALAYALAM SIGN PARA +0D54..0D56 ; L # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; L # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E ; L # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; L # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D66..0D6F ; L # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75 ; L # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; L # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79 ; L # So MALAYALAM DATE MARK 0D7A..0D7F ; L # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83 ; L # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -386,7 +370,8 @@ 1820..1842 ; L # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; L # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; L # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; L # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; L # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; L # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; L # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; L # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; L # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -449,6 +434,7 @@ 1C5A..1C77 ; L # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; L # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F ; L # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88 ; L # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7 ; L # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD3 ; L # Po VEDIC SIGN NIHSHVASA 1CE1 ; L # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -456,6 +442,7 @@ 1CEE..1CF1 ; L # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; L # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; L # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; L # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; L # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; L # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; L # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -546,7 +533,7 @@ 30A1..30FA ; L # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FC..30FE ; L # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; L # Lo KATAKANA DIGRAPH KOTO -3105..312D ; L # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; L # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; L # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; L # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; L # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -567,7 +554,7 @@ 337B..33DD ; L # So [99] SQUARE ERA NAME HEISEI..SQUARE WB 33E0..33FE ; L # So [31] IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY ONE..IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE 3400..4DB5 ; L # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; L # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; L # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; L # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; L # Lm YI SYLLABLE WU A016..A48C ; L # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -592,7 +579,7 @@ A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; L # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; L # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; L # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; L # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -715,12 +702,13 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 10102 ; L # Po AEGEAN CHECK MARK 10107..10133 ; L # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND 10137..1013F ; L # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT +1018D..1018E ; L # So [2] GREEK INDICTION SIGN..NOMISMA SIGN 101D0..101FC ; L # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 10280..1029C ; L # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; L # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; L # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; L # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; L # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; L # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; L # Nl GOTHIC LETTER NINETY 10342..10349 ; L # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; L # Nl GOTHIC LETTER NINE HUNDRED @@ -734,6 +722,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 10400..1044F ; L # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; L # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; L # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; L # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; L # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; L # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; L # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; L # Po CAUCASIAN ALBANIAN CITATION MARK @@ -805,6 +795,15 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 11357 ; L # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; L # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; L # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11400..11434 ; L # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; L # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11440..11441 ; L # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11445 ; L # Mc NEWA SIGN VISARGA +11447..1144A ; L # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; L # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; L # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; L # Po NEWA PLACEHOLDER MARK +1145D ; L # Po NEWA INSERTION SIGN 11480..114AF ; L # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; L # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B9 ; L # Mc TIRHUTA VOWEL SIGN E @@ -843,7 +842,39 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 118E0..118E9 ; L # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; L # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; L # Lo WARANG CITI OM +11A00 ; L # Lo ZANABAZAR SQUARE LETTER A +11A07..11A08 ; L # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A0B..11A32 ; L # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A39 ; L # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; L # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3F..11A46 ; L # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; L # Lo SOYOMBO LETTER A +11A57..11A58 ; L # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A5C..11A83 ; L # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; L # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A97 ; L # Mc SOYOMBO SIGN VISARGA +11A9A..11A9C ; L # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; L # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; L # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; L # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; L # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; L # Mc BHAIKSUKI VOWEL SIGN AA +11C3E ; L # Mc BHAIKSUKI SIGN VISARGA +11C3F ; L # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; L # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; L # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; L # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; L # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71 ; L # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; L # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11CA9 ; L # Mc MARCHEN SUBJOINED LETTER YA +11CB1 ; L # Mc MARCHEN VOWEL SIGN I +11CB4 ; L # Mc MARCHEN VOWEL SIGN O +11D00..11D06 ; L # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; L # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; L # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; L # Lo MASARAM GONDI REPHA +11D50..11D59 ; L # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; L # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; L # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; L # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -870,7 +901,11 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 16F50 ; L # Lo MIAO LETTER NASALIZATION 16F51..16F7E ; L # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F93..16F9F ; L # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; L # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; L # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; L # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; L # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; L # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; L # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; L # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; L # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; L # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -930,21 +965,22 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1DA87..1DA8B ; L # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1F110..1F12E ; L # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F169 ; L # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z -1F170..1F19A ; L # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; L # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F202 ; L # So [29] REGIONAL INDICATOR SYMBOL LETTER A..SQUARED KATAKANA SA -1F210..1F23A ; L # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; L # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; L # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; L # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT 20000..2A6D6 ; L # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; L # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; L # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; L # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; L # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; L # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; L # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 848999 code points not listed here. -# Total code points: 1097474 +# The above property value applies to 833103 code points not listed here. +# Total code points: 1097124 # ================================================ @@ -976,7 +1012,8 @@ F0000..FFFFD ; L # Co [65534] <private-use-F0000>..<private-use-FFFFD> 0840..0858 ; R # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085C..085D ; R # Cn [2] <reserved-085C>..<reserved-085D> 085E ; R # Po MANDAIC PUNCTUATION -085F..089F ; R # Cn [65] <reserved-085F>..<reserved-089F> +085F ; R # Cn <reserved-085F> +0870..089F ; R # Cn [48] <reserved-0870>..<reserved-089F> 200F ; R # Cf RIGHT-TO-LEFT MARK FB1D ; R # Lo HEBREW LETTER YOD WITH HIRIQ FB1F..FB28 ; R # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV @@ -1084,10 +1121,16 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E800..1E8C4 ; R # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C5..1E8C6 ; R # Cn [2] <reserved-1E8C5>..<reserved-1E8C6> 1E8C7..1E8CF ; R # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE -1E8D7..1EDFF ; R # Cn [1321] <reserved-1E8D7>..<reserved-1EDFF> +1E8D7..1E8FF ; R # Cn [41] <reserved-1E8D7>..<reserved-1E8FF> +1E900..1E943 ; R # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E94B..1E94F ; R # Cn [5] <reserved-1E94B>..<reserved-1E94F> +1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95A..1E95D ; R # Cn [4] <reserved-1E95A>..<reserved-1E95D> +1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK +1E960..1EDFF ; R # Cn [1184] <reserved-1E960>..<reserved-1EDFF> 1EF00..1EFFF ; R # Cn [256] <reserved-1EF00>..<reserved-1EFFF> -# Total code points: 4077 +# Total code points: 4054 # ================================================ @@ -1145,8 +1188,8 @@ FF0D ; ES # Pd FULLWIDTH HYPHEN-MINUS 0E3F ; ET # Sc THAI CURRENCY SYMBOL BAHT 17DB ; ET # Sc KHMER CURRENCY SYMBOL RIEL 2030..2034 ; ET # Po [5] PER MILLE SIGN..TRIPLE PRIME -20A0..20BE ; ET # Sc [31] EURO-CURRENCY SIGN..LARI SIGN -20BF..20CF ; ET # Cn [17] <reserved-20BF>..<reserved-20CF> +20A0..20BF ; ET # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN +20C0..20CF ; ET # Cn [16] <reserved-20C0>..<reserved-20CF> 212E ; ET # So ESTIMATED SYMBOL 2213 ; ET # Sm MINUS-OR-PLUS SIGN A838 ; ET # Sc NORTH INDIC RUPEE MARK @@ -1170,9 +1213,10 @@ FFE5..FFE6 ; ET # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 0660..0669 ; AN # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE 066B..066C ; AN # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR 06DD ; AN # Cf ARABIC END OF AYAH +08E2 ; AN # Cf ARABIC DISPUTED END OF AYAH 10E60..10E7E ; AN # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS -# Total code points: 50 +# Total code points: 51 # ================================================ @@ -1400,8 +1444,7 @@ FF1A ; CS # Po FULLWIDTH COLON 239B..23B3 ; ON # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; ON # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; ON # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; ON # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; ON # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; ON # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; ON # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..2487 ; ON # No [40] CIRCLED DIGIT ONE..PARENTHESIZED NUMBER TWENTY 24EA..24FF ; ON # No [22] CIRCLED DIGIT ZERO..NEGATIVE CIRCLED DIGIT ZERO @@ -1486,7 +1529,7 @@ FF1A ; CS # Po FULLWIDTH COLON 2B76..2B95 ; ON # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; ON # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; ON # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; ON # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; ON # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; ON # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2CE5..2CEA ; ON # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2CF9..2CFC ; ON # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER @@ -1529,6 +1572,7 @@ FF1A ; CS # Po FULLWIDTH COLON 2E40 ; ON # Pd DOUBLE HYPHEN 2E41 ; ON # Po REVERSED COMMA 2E42 ; ON # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; ON # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; ON # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; ON # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; ON # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1675,6 +1719,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1091F ; ON # Po PHOENICIAN WORD SEPARATOR 10B39..10B3F ; ON # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION 11052..11065 ; ON # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND +11660..1166C ; ON # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 1D200..1D241 ; ON # So [66] GREEK VOCAL NOTATION SYMBOL-1..GREEK INSTRUMENTAL NOTATION SYMBOL-54 1D245 ; ON # So GREEK MUSICAL LEIMMA 1D300..1D356 ; ON # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING @@ -1692,13 +1737,12 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F0D1..1F0F5 ; ON # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F10B..1F10C ; ON # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F16A..1F16B ; ON # So [2] RAISED MC SIGN..RAISED MD SIGN +1F260..1F265 ; ON # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; ON # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; ON # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579 ; ON # So [378] RAT..JOYSTICK -1F57B..1F5A3 ; ON # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; ON # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP +1F400..1F6D4 ; ON # So [725] RAT..PAGODA 1F6E0..1F6EC ; ON # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; ON # So [4] SATELLITE..PASSENGER SHIP +1F6F0..1F6F8 ; ON # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; ON # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; ON # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; ON # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -1706,11 +1750,15 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1F850..1F859 ; ON # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; ON # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; ON # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; ON # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; ON # So [5] CRAB..UNICORN FACE +1F900..1F90B ; ON # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; ON # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; ON # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; ON # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; ON # So [24] CRAB..CRICKET 1F9C0 ; ON # So CHEESE WEDGE +1F9D0..1F9E6 ; ON # So [23] FACE WITH MONOCLE..SOCKS -# Total code points: 5174 +# Total code points: 5350 # ================================================ @@ -1784,6 +1832,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0825..0827 ; NSM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; NSM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; NSM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; NSM # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; NSM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; NSM # Mn DEVANAGARI VOWEL SIGN OE 093C ; NSM # Mn DEVANAGARI SIGN NUKTA @@ -1810,6 +1859,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0AC7..0AC8 ; NSM # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; NSM # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; NSM # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; NSM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; NSM # Mn ORIYA SIGN CANDRABINDU 0B3C ; NSM # Mn ORIYA SIGN NUKTA 0B3F ; NSM # Mn ORIYA VOWEL SIGN I @@ -1830,7 +1880,8 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 0CBC ; NSM # Mn KANNADA SIGN NUKTA 0CCC..0CCD ; NSM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; NSM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; NSM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; NSM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; NSM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; NSM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; NSM # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; NSM # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -1876,6 +1927,7 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 17C9..17D3 ; NSM # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; NSM # Mn KHMER SIGN ATTHACAN 180B..180D ; NSM # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; NSM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; NSM # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; NSM # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; NSM # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -1914,8 +1966,8 @@ FFFFE..FFFFF ; BN # Cn [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 1CED ; NSM # Mn VEDIC SIGN TIRYAK 1CF4 ; NSM # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; NSM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; NSM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; NSM # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; NSM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; NSM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; NSM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; NSM # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; NSM # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -1935,7 +1987,7 @@ A802 ; NSM # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; NSM # Mn SYLOTI NAGRI SIGN HASANTA A80B ; NSM # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; NSM # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; NSM # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; NSM # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; NSM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; NSM # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; NSM # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -1987,6 +2039,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1122F..11231 ; NSM # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; NSM # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; NSM # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; NSM # Mn KHOJKI SIGN SUKUN 112DF ; NSM # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; NSM # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; NSM # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -1994,6 +2047,9 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 11340 ; NSM # Mn GRANTHA VOWEL SIGN II 11366..1136C ; NSM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; NSM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; NSM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; NSM # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; NSM # Mn NEWA SIGN NUKTA 114B3..114B8 ; NSM # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; NSM # Mn TIRHUTA VOWEL SIGN SHORT E 114BF..114C0 ; NSM # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA @@ -2012,6 +2068,26 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1171D..1171F ; NSM # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; NSM # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; NSM # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; NSM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; NSM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; NSM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; NSM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; NSM # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; NSM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; NSM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; NSM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; NSM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; NSM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; NSM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C92..11CA7 ; NSM # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; NSM # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; NSM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; NSM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; NSM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; NSM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; NSM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; NSM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; NSM # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; NSM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; NSM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; NSM # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2027,10 +2103,16 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1DA84 ; NSM # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; NSM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; NSM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; NSM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; NSM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; NSM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; NSM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; NSM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; NSM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1578 +# Total code points: 1773 # ================================================ @@ -2065,8 +2147,12 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 074D..07A5 ; AL # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU 07B1 ; AL # Lo THAANA LETTER NAA 07B2..07BF ; AL # Cn [14] <reserved-07B2>..<reserved-07BF> +0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +086B..086F ; AL # Cn [5] <reserved-086B>..<reserved-086F> 08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B5..08E2 ; AL # Cn [46] <reserved-08B5>..<reserved-08E2> +08B5 ; AL # Cn <reserved-08B5> +08B6..08BD ; AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08BE..08D3 ; AL # Cn [22] <reserved-08BE>..<reserved-08D3> FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC1 ; AL # Sk [16] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL SMALL TAH BELOW FBC2..FBD2 ; AL # Cn [17] <reserved-FBC2>..<reserved-FBD2> @@ -2151,7 +2237,7 @@ FEFD..FEFE ; AL # Cn [2] <reserved-FEFD>..<reserved-FEFE> 1EEBC..1EEEF ; AL # Cn [52] <reserved-1EEBC>..<reserved-1EEEF> 1EEF2..1EEFF ; AL # Cn [14] <reserved-1EEF2>..<reserved-1EEFF> -# Total code points: 1435 +# Total code points: 1436 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DBinaryProperties.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DBinaryProperties.txt index cb8b8f16d32..8036034e256 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DBinaryProperties.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DBinaryProperties.txt @@ -1,10 +1,11 @@ -# DerivedBinaryProperties-8.0.0.txt -# Date: 2015-02-13, 13:47:09 GMT [MD] +# DerivedBinaryProperties-10.0.0.txt +# Date: 2017-02-14, 04:26:02 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DCombiningClass.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DCombiningClass.txt index a81c56d0148..209fe980b75 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DCombiningClass.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DCombiningClass.txt @@ -1,10 +1,11 @@ -# DerivedCombiningClass-8.0.0.txt -# Date: 2015-02-13, 13:47:09 GMT [MD] +# DerivedCombiningClass-10.0.0.txt +# Date: 2017-03-08, 08:41:47 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -177,7 +178,10 @@ 0830..083E ; 0 # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; 0 # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; 0 # Po MANDAIC PUNCTUATION +0860..086A ; 0 # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; 0 # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; 0 # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08E2 ; 0 # Cf ARABIC DISPUTED END OF AYAH 0900..0902 ; 0 # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0903 ; 0 # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; 0 # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -221,6 +225,8 @@ 09F4..09F9 ; 0 # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; 0 # So BENGALI ISSHAR 09FB ; 0 # Sc BENGALI GANDA MARK +09FC ; 0 # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; 0 # Po BENGALI ABBREVIATION SIGN 0A01..0A02 ; 0 # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; 0 # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; 0 # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -262,6 +268,7 @@ 0AF0 ; 0 # Po GUJARATI ABBREVIATION SIGN 0AF1 ; 0 # Sc GUJARATI RUPEE SIGN 0AF9 ; 0 # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; 0 # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; 0 # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; 0 # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; 0 # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -326,6 +333,7 @@ 0C66..0C6F ; 0 # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C78..0C7E ; 0 # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; 0 # So TELUGU SIGN TUUMU +0C80 ; 0 # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; 0 # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; 0 # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; 0 # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -347,7 +355,7 @@ 0CE2..0CE3 ; 0 # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; 0 # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; 0 # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; 0 # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; 0 # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; 0 # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; 0 # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; 0 # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI @@ -358,11 +366,14 @@ 0D46..0D48 ; 0 # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI 0D4A..0D4C ; 0 # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4E ; 0 # Lo MALAYALAM LETTER DOT REPH +0D4F ; 0 # So MALAYALAM SIGN PARA +0D54..0D56 ; 0 # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; 0 # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E ; 0 # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; 0 # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; 0 # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0D66..0D6F ; 0 # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75 ; 0 # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; 0 # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79 ; 0 # So MALAYALAM DATE MARK 0D7A..0D7F ; 0 # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83 ; 0 # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -555,7 +566,9 @@ 1820..1842 ; 0 # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; 0 # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; 0 # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; 0 # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; 0 # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; 0 # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; 0 # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; 0 # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; 0 # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; 0 # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -642,6 +655,7 @@ 1C5A..1C77 ; 0 # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; 0 # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F ; 0 # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88 ; 0 # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7 ; 0 # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD3 ; 0 # Po VEDIC SIGN NIHSHVASA 1CE1 ; 0 # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA @@ -649,6 +663,7 @@ 1CEE..1CF1 ; 0 # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1CF2..1CF3 ; 0 # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF5..1CF6 ; 0 # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; 0 # Mc VEDIC SIGN ATIKRAMA 1D00..1D2B ; 0 # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; 0 # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI 1D6B..1D77 ; 0 # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G @@ -725,7 +740,7 @@ 208D ; 0 # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; 0 # Pe SUBSCRIPT RIGHT PARENTHESIS 2090..209C ; 0 # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T -20A0..20BE ; 0 # Sc [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; 0 # Sc [32] EURO-CURRENCY SIGN..BITCOIN SIGN 20DD..20E0 ; 0 # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E2..20E4 ; 0 # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE 2100..2101 ; 0 # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT @@ -801,8 +816,7 @@ 239B..23B3 ; 0 # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; 0 # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; 0 # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; 0 # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; 0 # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; 0 # So [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; 0 # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 2460..249B ; 0 # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP 249C..24E9 ; 0 # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z @@ -888,7 +902,7 @@ 2B76..2B95 ; 0 # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; 0 # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; 0 # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; 0 # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; 0 # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; 0 # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; 0 # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; 0 # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -953,6 +967,7 @@ 2E40 ; 0 # Pd DOUBLE HYPHEN 2E41 ; 0 # Po REVERSED COMMA 2E42 ; 0 # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; 0 # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 2E80..2E99 ; 0 # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; 0 # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; 0 # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1004,7 +1019,7 @@ 30FB ; 0 # Po KATAKANA MIDDLE DOT 30FC..30FE ; 0 # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; 0 # Lo KATAKANA DIGRAPH KOTO -3105..312D ; 0 # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; 0 # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; 0 # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; 0 # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; 0 # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1026,7 +1041,7 @@ 3300..33FF ; 0 # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; 0 # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DC0..4DFF ; 0 # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION -4E00..9FD5 ; 0 # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; 0 # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; 0 # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; 0 # Lm YI SYLLABLE WU A016..A48C ; 0 # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -1061,7 +1076,7 @@ A788 ; 0 # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; 0 # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; 0 # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; 0 # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; 0 # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; 0 # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1085,6 +1100,7 @@ A874..A877 ; 0 # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHA A880..A881 ; 0 # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; 0 # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; 0 # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU +A8C5 ; 0 # Mn SAURASHTRA SIGN CANDRABINDU A8CE..A8CF ; 0 # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A8D0..A8D9 ; 0 # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8F2..A8F7 ; 0 # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA @@ -1315,7 +1331,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10175..10178 ; 0 # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189 ; 0 # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B ; 0 # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C ; 0 # So GREEK SINUSOID SIGN +1018C..1018E ; 0 # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B ; 0 # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0 ; 0 # So GREEK SYMBOL TAU RHO 101D0..101FC ; 0 # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -1324,7 +1340,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 102E1..102FB ; 0 # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; 0 # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; 0 # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; 0 # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; 0 # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; 0 # Nl GOTHIC LETTER NINETY 10342..10349 ; 0 # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; 0 # Nl GOTHIC LETTER NINE HUNDRED @@ -1338,6 +1354,8 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10400..1044F ; 0 # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; 0 # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; 0 # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; 0 # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; 0 # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; 0 # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; 0 # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; 0 # Po CAUCASIAN ALBANIAN CITATION MARK @@ -1456,6 +1474,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11234 ; 0 # Mn KHOJKI SIGN ANUSVARA 11237 ; 0 # Mn KHOJKI SIGN SHADDA 11238..1123D ; 0 # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN +1123E ; 0 # Mn KHOJKI SIGN SUKUN 11280..11286 ; 0 # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; 0 # Lo MULTANI LETTER GHA 1128A..1128D ; 0 # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1485,6 +1504,17 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11357 ; 0 # Mc GRANTHA AU LENGTH MARK 1135D..11361 ; 0 # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11362..11363 ; 0 # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11400..11434 ; 0 # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; 0 # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; 0 # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; 0 # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11443..11444 ; 0 # Mn [2] NEWA SIGN CANDRABINDU..NEWA SIGN ANUSVARA +11445 ; 0 # Mc NEWA SIGN VISARGA +11447..1144A ; 0 # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; 0 # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; 0 # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; 0 # Po NEWA PLACEHOLDER MARK +1145D ; 0 # Po NEWA INSERTION SIGN 11480..114AF ; 0 # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; 0 # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; 0 # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -1516,6 +1546,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 11641..11643 ; 0 # Po [3] MODI DANDA..MODI ABBREVIATION SIGN 11644 ; 0 # Lo MODI SIGN HUVA 11650..11659 ; 0 # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C ; 0 # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11680..116AA ; 0 # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116AB ; 0 # Mn TAKRI SIGN ANUSVARA 116AC ; 0 # Mc TAKRI SIGN VISARGA @@ -1537,7 +1568,59 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 118E0..118E9 ; 0 # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; 0 # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; 0 # Lo WARANG CITI OM +11A00 ; 0 # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; 0 # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; 0 # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; 0 # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; 0 # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33 ; 0 # Mn ZANABAZAR SQUARE FINAL CONSONANT MARK +11A35..11A38 ; 0 # Mn [4] ZANABAZAR SQUARE SIGN CANDRABINDU..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; 0 # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; 0 # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; 0 # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; 0 # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; 0 # Lo SOYOMBO LETTER A +11A51..11A56 ; 0 # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; 0 # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; 0 # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; 0 # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; 0 # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; 0 # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; 0 # Mc SOYOMBO SIGN VISARGA +11A98 ; 0 # Mn SOYOMBO GEMINATION MARK +11A9A..11A9C ; 0 # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; 0 # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; 0 # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; 0 # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; 0 # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; 0 # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; 0 # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; 0 # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; 0 # Mc BHAIKSUKI SIGN VISARGA +11C40 ; 0 # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; 0 # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; 0 # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; 0 # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71 ; 0 # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; 0 # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; 0 # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; 0 # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; 0 # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; 0 # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; 0 # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; 0 # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; 0 # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; 0 # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; 0 # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; 0 # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; 0 # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; 0 # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; 0 # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D41 ; 0 # Mn [3] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI SIGN VISARGA +11D43 ; 0 # Mn MASARAM GONDI SIGN CANDRA +11D46 ; 0 # Lo MASARAM GONDI REPHA +11D47 ; 0 # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; 0 # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; 0 # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; 0 # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; 0 # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -1565,7 +1648,11 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 16F51..16F7E ; 0 # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 16F8F..16F92 ; 0 # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 16F93..16F9F ; 0 # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 -1B000..1B001 ; 0 # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; 0 # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; 0 # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; 0 # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; 0 # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; 0 # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; 0 # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; 0 # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; 0 # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1641,6 +1728,9 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1DAA1..1DAAF ; 0 # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 1E800..1E8C4 ; 0 # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; 0 # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE +1E900..1E943 ; 0 # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E950..1E959 ; 0 # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; 0 # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK 1EE00..1EE03 ; 0 # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; 0 # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; 0 # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1684,18 +1774,17 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F100..1F10C ; 0 # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F110..1F12E ; 0 # So [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F16B ; 0 # So [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN -1F170..1F19A ; 0 # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; 0 # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F202 ; 0 # So [29] REGIONAL INDICATOR SYMBOL LETTER A..SQUARED KATAKANA SA -1F210..1F23A ; 0 # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; 0 # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; 0 # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; 0 # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; 0 # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; 0 # So [251] CYCLONE..AMPHORA 1F3FB..1F3FF ; 0 # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579 ; 0 # So [378] RAT..JOYSTICK -1F57B..1F5A3 ; 0 # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; 0 # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP +1F400..1F6D4 ; 0 # So [725] RAT..PAGODA 1F6E0..1F6EC ; 0 # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; 0 # So [4] SATELLITE..PASSENGER SHIP +1F6F0..1F6F8 ; 0 # So [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; 0 # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; 0 # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; 0 # So [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -1703,13 +1792,18 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; 0 # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; 0 # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; 0 # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; 0 # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; 0 # So [5] CRAB..UNICORN FACE +1F900..1F90B ; 0 # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; 0 # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; 0 # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; 0 # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; 0 # So [24] CRAB..CRICKET 1F9C0 ; 0 # So CHEESE WEDGE +1F9D0..1F9E6 ; 0 # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; 0 # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A700..2B734 ; 0 # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; 0 # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; 0 # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; 0 # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; 0 # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D E0001 ; 0 # Cf LANGUAGE TAG E0020..E007F ; 0 # Cf [96] TAG SPACE..CANCEL TAG @@ -1717,8 +1811,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; 0 # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 855907 code points not listed here. -# Total code points: 1113361 +# The above property value applies to 839889 code points not listed here. +# Total code points: 1113286 # ================================================ @@ -1759,11 +1853,14 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 11236 ; 7 # Mn KHOJKI SIGN NUKTA 112E9 ; 7 # Mn KHUDAWADI SIGN NUKTA 1133C ; 7 # Mn GRANTHA SIGN NUKTA +11446 ; 7 # Mn NEWA SIGN NUKTA 114C3 ; 7 # Mn TIRHUTA SIGN NUKTA 115C0 ; 7 # Mn SIDDHAM SIGN NUKTA 116B7 ; 7 # Mn TAKRI SIGN NUKTA +11D42 ; 7 # Mn MASARAM GONDI SIGN NUKTA +1E94A ; 7 # Mn ADLAM NUKTA -# Total code points: 20 +# Total code points: 23 # ================================================ @@ -1785,6 +1882,7 @@ A9B3 ; 7 # Mn JAVANESE SIGN CECAK TELU 0BCD ; 9 # Mn TAMIL SIGN VIRAMA 0C4D ; 9 # Mn TELUGU SIGN VIRAMA 0CCD ; 9 # Mn KANNADA SIGN VIRAMA +0D3B..0D3C ; 9 # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D4D ; 9 # Mn MALAYALAM SIGN VIRAMA 0DCA ; 9 # Mn SINHALA SIGN AL-LAKUNA 0E3A ; 9 # Mn THAI CHARACTER PHINTHU @@ -1814,13 +1912,19 @@ ABED ; 9 # Mn MEETEI MAYEK APUN IYEK 11235 ; 9 # Mc KHOJKI SIGN VIRAMA 112EA ; 9 # Mn KHUDAWADI SIGN VIRAMA 1134D ; 9 # Mc GRANTHA SIGN VIRAMA +11442 ; 9 # Mn NEWA SIGN VIRAMA 114C2 ; 9 # Mn TIRHUTA SIGN VIRAMA 115BF ; 9 # Mn SIDDHAM SIGN VIRAMA 1163F ; 9 # Mn MODI SIGN VIRAMA 116B6 ; 9 # Mc TAKRI SIGN VIRAMA 1172B ; 9 # Mn AHOM SIGN KILLER +11A34 ; 9 # Mn ZANABAZAR SQUARE SIGN VIRAMA +11A47 ; 9 # Mn ZANABAZAR SQUARE SUBJOINER +11A99 ; 9 # Mn SOYOMBO SUBJOINER +11C3F ; 9 # Mn BHAIKSUKI SIGN VIRAMA +11D44..11D45 ; 9 # Mn [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA -# Total code points: 45 +# Total code points: 54 # ================================================ @@ -2216,6 +2320,7 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1DC2 ; 220 # Mn COMBINING SNAKE BELOW 1DCA ; 220 # Mn COMBINING LATIN SMALL LETTER R BELOW 1DCF ; 220 # Mn COMBINING ZIGZAG BELOW +1DF9 ; 220 # Mn COMBINING WIDE INVERTED BRIDGE BELOW 1DFD ; 220 # Mn COMBINING ALMOST EQUAL TO BELOW 1DFF ; 220 # Mn COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20E8 ; 220 # Mn COMBINING TRIPLE UNDERDOT @@ -2232,7 +2337,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1D18A..1D18B ; 220 # Mn [2] MUSICAL SYMBOL COMBINING DOUBLE TONGUE..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 153 +# Total code points: 154 # ================================================ @@ -2267,9 +2372,10 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 05AE ; 228 # Mn HEBREW ACCENT ZINOR 18A9 ; 228 # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1DF7..1DF8 ; 228 # Mn [2] COMBINING KAVYKA ABOVE LEFT..COMBINING DOT ABOVE LEFT 302B ; 228 # Mn IDEOGRAPHIC RISING TONE MARK -# Total code points: 3 +# Total code points: 5 # ================================================ @@ -2316,6 +2422,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 081B..0823 ; 230 # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A 0825..0827 ; 230 # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; 230 # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +08D4..08E1 ; 230 # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E4..08E5 ; 230 # Mn [2] ARABIC CURLY FATHA..ARABIC CURLY DAMMA 08E7..08E8 ; 230 # Mn [2] ARABIC CURLY FATHATAN..ARABIC CURLY DAMMATAN 08EA..08EC ; 230 # Mn [3] ARABIC TONE ONE DOT ABOVE..ARABIC TONE LOOP ABOVE @@ -2344,6 +2451,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1DC3..1DC9 ; 230 # Mn [7] COMBINING SUSPENSION MARK..COMBINING ACUTE-GRAVE-ACUTE 1DCB..1DCC ; 230 # Mn [2] COMBINING BREVE-MACRON..COMBINING MACRON-BREVE 1DD1..1DF5 ; 230 # Mn [37] COMBINING UR ABOVE..COMBINING UP TACK ABOVE +1DFB ; 230 # Mn COMBINING DELETION MARK 1DFE ; 230 # Mn COMBINING LEFT ARROWHEAD ABOVE 20D0..20D1 ; 230 # Mn [2] COMBINING LEFT HARPOON ABOVE..COMBINING RIGHT HARPOON ABOVE 20D4..20D7 ; 230 # Mn [4] COMBINING ANTICLOCKWISE ARROW ABOVE..COMBINING RIGHT ARROW ABOVE @@ -2377,8 +2485,14 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1D185..1D189 ; 230 # Mn [5] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING BEND 1D1AA..1D1AD ; 230 # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO 1D242..1D244 ; 230 # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1E000..1E006 ; 230 # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; 230 # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; 230 # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; 230 # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; 230 # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 402 +# Total code points: 461 # ================================================ @@ -2387,9 +2501,10 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 0315 ; 232 # Mn COMBINING COMMA ABOVE RIGHT 031A ; 232 # Mn COMBINING LEFT ANGLE ABOVE 0358 ; 232 # Mn COMBINING DOT ABOVE RIGHT +1DF6 ; 232 # Mn COMBINING KAVYKA ABOVE RIGHT 302C ; 232 # Mn IDEOGRAPHIC DEPARTING TONE MARK -# Total code points: 4 +# Total code points: 5 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DDecompositionType.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DDecompositionType.txt index 0d29e237a4a..96006dcd95c 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DDecompositionType.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DDecompositionType.txt @@ -1,10 +1,11 @@ -# DerivedDecompositionType-8.0.0.txt -# Date: 2015-02-13, 13:47:11 GMT [MD] +# DerivedDecompositionType-10.0.0.txt +# Date: 2017-02-14, 04:26:05 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -999,9 +1000,9 @@ FE6A..FE6B ; Small # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 1F130..1F14F ; Square # So [32] SQUARED LATIN CAPITAL LETTER A..SQUARED WC 1F190 ; Square # So SQUARE DJ 1F200..1F202 ; Square # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; Square # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; Square # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D -# Total code points: 284 +# Total code points: 285 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DEastAsianWidth.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DEastAsianWidth.txt index 5343f7ea2d7..b4180028f69 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DEastAsianWidth.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DEastAsianWidth.txt @@ -1,10 +1,11 @@ -# DerivedEastAsianWidth-8.0.0.txt -# Date: 2015-02-13, 13:47:11 GMT [MD] +# DerivedEastAsianWidth-10.0.0.txt +# Date: 2017-03-08, 08:41:49 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -195,7 +196,11 @@ 0840..0858 ; N # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0859..085B ; N # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 085E ; N # Po MANDAIC PUNCTUATION +0860..086A ; N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; N # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; N # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08D4..08E1 ; N # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E2 ; N # Cf ARABIC DISPUTED END OF AYAH 08E3..0902 ; N # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; N # Mc DEVANAGARI SIGN VISARGA 0904..0939 ; N # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -243,6 +248,8 @@ 09F4..09F9 ; N # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN 09FA ; N # So BENGALI ISSHAR 09FB ; N # Sc BENGALI GANDA MARK +09FC ; N # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; N # Po BENGALI ABBREVIATION SIGN 0A01..0A02 ; N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -287,6 +294,7 @@ 0AF0 ; N # Po GUJARATI ABBREVIATION SIGN 0AF1 ; N # Sc GUJARATI RUPEE SIGN 0AF9 ; N # Lo GUJARATI LETTER ZHA +0AFA..0AFF ; N # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; N # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; N # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B05..0B0C ; N # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L @@ -355,6 +363,7 @@ 0C66..0C6F ; N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C78..0C7E ; N # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; N # So TELUGU SIGN TUUMU +0C80 ; N # Lo KANNADA SIGN SPACING CANDRABINDU 0C81 ; N # Mn KANNADA SIGN CANDRABINDU 0C82..0C83 ; N # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA 0C85..0C8C ; N # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -377,11 +386,12 @@ 0CE2..0CE3 ; N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; N # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D01 ; N # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; N # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; N # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D05..0D0C ; N # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; N # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; N # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3B..0D3C ; N # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3D ; N # Lo MALAYALAM SIGN AVAGRAHA 0D3E..0D40 ; N # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; N # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR @@ -389,11 +399,14 @@ 0D4A..0D4C ; N # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU 0D4D ; N # Mn MALAYALAM SIGN VIRAMA 0D4E ; N # Lo MALAYALAM LETTER DOT REPH +0D4F ; N # So MALAYALAM SIGN PARA +0D54..0D56 ; N # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D57 ; N # Mc MALAYALAM AU LENGTH MARK +0D58..0D5E ; N # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; N # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D62..0D63 ; N # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL 0D66..0D6F ; N # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE -0D70..0D75 ; N # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; N # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D79 ; N # So MALAYALAM DATE MARK 0D7A..0D7F ; N # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D82..0D83 ; N # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA @@ -594,7 +607,9 @@ 1820..1842 ; N # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; N # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; N # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; N # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; N # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1885..1886 ; N # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +1887..18A8 ; N # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18A9 ; N # Mn MONGOLIAN LETTER ALI GALI DAGALGA 18AA ; N # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; N # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S @@ -692,6 +707,7 @@ 1C5A..1C77 ; N # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; N # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD 1C7E..1C7F ; N # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +1C80..1C88 ; N # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7 ; N # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD0..1CD2 ; N # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA 1CD3 ; N # Po VEDIC SIGN NIHSHVASA @@ -704,6 +720,7 @@ 1CF2..1CF3 ; N # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; N # Mn VEDIC TONE CANDRA ABOVE 1CF5..1CF6 ; N # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CF7 ; N # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; N # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 1D00..1D2B ; N # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D6A ; N # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI @@ -711,8 +728,8 @@ 1D78 ; N # Lm MODIFIER LETTER CYRILLIC EN 1D79..1D9A ; N # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK 1D9B..1DBF ; N # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA -1DC0..1DF5 ; N # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; N # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; N # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; N # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 1E00..1F15 ; N # L& [278] LATIN CAPITAL LETTER A WITH RING BELOW..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA 1F18..1F1D ; N # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA 1F20..1F45 ; N # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA @@ -784,7 +801,7 @@ 2090..209C ; N # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T 20A0..20A8 ; N # Sc [9] EURO-CURRENCY SIGN..RUPEE SIGN 20AA..20AB ; N # Sc [2] NEW SHEQEL SIGN..DONG SIGN -20AD..20BE ; N # Sc [18] KIP SIGN..LARI SIGN +20AD..20BF ; N # Sc [19] KIP SIGN..BITCOIN SIGN 20D0..20DC ; N # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; N # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH 20E1 ; N # Mn COMBINING LEFT RIGHT ARROW ABOVE @@ -883,7 +900,8 @@ 230A ; N # Ps LEFT FLOOR 230B ; N # Pe RIGHT FLOOR 230C..2311 ; N # So [6] BOTTOM RIGHT CROP..SQUARE LOZENGE -2313..231F ; N # So [13] SEGMENT..BOTTOM RIGHT CORNER +2313..2319 ; N # So [7] SEGMENT..TURNED NOT SIGN +231C..231F ; N # So [4] TOP LEFT CORNER..BOTTOM RIGHT CORNER 2320..2321 ; N # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL 2322..2328 ; N # So [7] FROWN..KEYBOARD 232B..237B ; N # So [81] ERASE TO THE LEFT..NOT CHECK MARK @@ -892,8 +910,10 @@ 239B..23B3 ; N # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; N # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; N # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23FA ; N # So [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; N # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..23E8 ; N # So [7] WHITE TRAPEZIUM..DECIMAL EXPONENT SYMBOL +23ED..23EF ; N # So [3] BLACK RIGHT-POINTING DOUBLE TRIANGLE WITH VERTICAL BAR..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR +23F1..23F2 ; N # So [2] STOPWATCH..TIMER CLOCK +23F4..2426 ; N # So [51] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; N # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24EA ; N # No CIRCLED DIGIT ZERO 254C..254F ; N # So [4] BOX DRAWINGS LIGHT DOUBLE DASH HORIZONTAL..BOX DRAWINGS HEAVY DOUBLE DASH VERTICAL @@ -911,7 +931,8 @@ 25D2..25E1 ; N # So [16] CIRCLE WITH LOWER HALF BLACK..LOWER HALF CIRCLE 25E6..25EE ; N # So [9] WHITE BULLET..UP-POINTING TRIANGLE WITH RIGHT HALF BLACK 25F0..25F7 ; N # So [8] WHITE SQUARE WITH UPPER LEFT QUADRANT..WHITE CIRCLE WITH UPPER RIGHT QUADRANT -25F8..25FF ; N # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE +25F8..25FC ; N # Sm [5] UPPER LEFT TRIANGLE..BLACK MEDIUM SQUARE +25FF ; N # Sm LOWER RIGHT TRIANGLE 2600..2604 ; N # So [5] BLACK SUN WITH RAYS..COMET 2607..2608 ; N # So [2] LIGHTNING..THUNDERSTORM 260A..260D ; N # So [4] ASCENDING NODE..OPPOSITION @@ -920,19 +941,29 @@ 261D ; N # So WHITE UP POINTING INDEX 261F..263F ; N # So [33] WHITE DOWN POINTING INDEX..MERCURY 2641 ; N # So EARTH -2643..265F ; N # So [29] JUPITER..BLACK CHESS PAWN +2643..2647 ; N # So [5] JUPITER..PLUTO +2654..265F ; N # So [12] WHITE CHESS KING..BLACK CHESS PAWN 2662 ; N # So WHITE DIAMOND SUIT 2666 ; N # So BLACK DIAMOND SUIT 266B ; N # So BEAMED EIGHTH NOTES 266E ; N # So MUSIC NATURAL SIGN -2670..269D ; N # So [46] WEST SYRIAC CROSS..OUTLINED WHITE STAR -26A0..26BD ; N # So [30] WARNING SIGN..SOCCER BALL +2670..267E ; N # So [15] WEST SYRIAC CROSS..PERMANENT PAPER SIGN +2680..2692 ; N # So [19] DIE FACE-1..HAMMER AND PICK +2694..269D ; N # So [10] CROSSED SWORDS..OUTLINED WHITE STAR +26A0 ; N # So WARNING SIGN +26A2..26A9 ; N # So [8] DOUBLED FEMALE SIGN..HORIZONTAL MALE WITH STROKE SIGN +26AC..26BC ; N # So [17] MEDIUM SMALL WHITE CIRCLE..SESQUIQUADRATE 26C0..26C3 ; N # So [4] WHITE DRAUGHTS MAN..BLACK DRAUGHTS KING -26CE ; N # So OPHIUCHUS 26E2 ; N # So ASTRONOMICAL SYMBOL FOR URANUS 26E4..26E7 ; N # So [4] PENTAGRAM..INVERTED PENTAGRAM -2700..273C ; N # So [61] BLACK SAFETY SCISSORS..OPEN CENTRE TEARDROP-SPOKED ASTERISK -273E..2756 ; N # So [25] SIX PETALLED BLACK AND WHITE FLORETTE..BLACK DIAMOND MINUS WHITE X +2700..2704 ; N # So [5] BLACK SAFETY SCISSORS..WHITE SCISSORS +2706..2709 ; N # So [4] TELEPHONE LOCATION SIGN..ENVELOPE +270C..2727 ; N # So [28] VICTORY HAND..WHITE FOUR POINTED STAR +2729..273C ; N # So [20] STRESS OUTLINED WHITE STAR..OPEN CENTRE TEARDROP-SPOKED ASTERISK +273E..274B ; N # So [14] SIX PETALLED BLACK AND WHITE FLORETTE..HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK +274D ; N # So SHADOWED WHITE CIRCLE +274F..2752 ; N # So [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE +2756 ; N # So BLACK DIAMOND MINUS WHITE X 2758..2767 ; N # So [16] LIGHT VERTICAL BAR..ROTATED FLORAL HEART BULLET 2768 ; N # Ps MEDIUM LEFT PARENTHESIS ORNAMENT 2769 ; N # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT @@ -949,7 +980,9 @@ 2774 ; N # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT 2775 ; N # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT 2780..2793 ; N # No [20] DINGBAT CIRCLED SANS-SERIF DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN -2794..27BF ; N # So [44] HEAVY WIDE-HEADED RIGHTWARDS ARROW..DOUBLE CURLY LOOP +2794 ; N # So HEAVY WIDE-HEADED RIGHTWARDS ARROW +2798..27AF ; N # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW +27B1..27BE ; N # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW 27C0..27C4 ; N # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET 27C5 ; N # Ps LEFT S-SHAPED BAG DELIMITER 27C6 ; N # Pe RIGHT S-SHAPED BAG DELIMITER @@ -988,16 +1021,18 @@ 29FC ; N # Ps LEFT-POINTING CURVED ANGLE BRACKET 29FD ; N # Pe RIGHT-POINTING CURVED ANGLE BRACKET 29FE..2AFF ; N # Sm [258] TINY..N-ARY WHITE VERTICAL BAR -2B00..2B2F ; N # So [48] NORTH EAST WHITE ARROW..WHITE VERTICAL ELLIPSE +2B00..2B1A ; N # So [27] NORTH EAST WHITE ARROW..DOTTED SQUARE +2B1D..2B2F ; N # So [19] BLACK VERY SMALL SQUARE..WHITE VERTICAL ELLIPSE 2B30..2B44 ; N # Sm [21] LEFT ARROW WITH SMALL CIRCLE..RIGHTWARDS ARROW THROUGH SUPERSET 2B45..2B46 ; N # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C ; N # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR -2B4D..2B54 ; N # So [8] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..WHITE RIGHT-POINTING PENTAGON +2B4D..2B4F ; N # So [3] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..SHORT BACKSLANTED SOUTH ARROW +2B51..2B54 ; N # So [4] BLACK SMALL STAR..WHITE RIGHT-POINTING PENTAGON 2B5A..2B73 ; N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; N # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; N # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; N # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; N # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; N # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; N # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; N # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1065,6 +1100,7 @@ 2E40 ; N # Pd DOUBLE HYPHEN 2E41 ; N # Po REVERSED COMMA 2E42 ; N # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E43..2E49 ; N # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 303F ; N # So IDEOGRAPHIC HALF FILL SPACE 4DC0..4DFF ; N # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION A4D0..A4F7 ; N # Lo [40] LISU LETTER BA..LISU LETTER OE @@ -1101,7 +1137,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; N # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; N # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; N # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1126,7 +1162,7 @@ A874..A877 ; N # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHA A880..A881 ; N # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A882..A8B3 ; N # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA A8B4..A8C3 ; N # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; N # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; N # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8CE..A8CF ; N # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A8D0..A8D9 ; N # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A8E0..A8F1 ; N # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA @@ -1269,7 +1305,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10175..10178 ; N # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189 ; N # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B ; N # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C ; N # So GREEK SINUSOID SIGN +1018C..1018E ; N # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B ; N # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0 ; N # So GREEK SYMBOL TAU RHO 101D0..101FC ; N # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -1280,7 +1316,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 102E1..102FB ; N # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; N # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; N # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; N # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; N # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; N # Nl GOTHIC LETTER NINETY 10342..10349 ; N # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; N # Nl GOTHIC LETTER NINE HUNDRED @@ -1295,6 +1331,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10400..1044F ; N # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; N # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO 104A0..104A9 ; N # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +104B0..104D3 ; N # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; N # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; N # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; N # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; N # Po CAUCASIAN ALBANIAN CITATION MARK @@ -1419,6 +1457,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11235 ; N # Mc KHOJKI SIGN VIRAMA 11236..11237 ; N # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 11238..1123D ; N # Po [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN +1123E ; N # Mn KHOJKI SIGN SUKUN 11280..11286 ; N # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; N # Lo MULTANI LETTER GHA 1128A..1128D ; N # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1451,6 +1490,18 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11362..11363 ; N # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; N # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; N # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11400..11434 ; N # Lo [53] NEWA LETTER A..NEWA LETTER HA +11435..11437 ; N # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; N # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; N # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; N # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; N # Mc NEWA SIGN VISARGA +11446 ; N # Mn NEWA SIGN NUKTA +11447..1144A ; N # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144B..1144F ; N # Po [5] NEWA DANDA..NEWA ABBREVIATION SIGN +11450..11459 ; N # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +1145B ; N # Po NEWA PLACEHOLDER MARK +1145D ; N # Po NEWA INSERTION SIGN 11480..114AF ; N # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114B0..114B2 ; N # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; N # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL @@ -1484,6 +1535,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 11641..11643 ; N # Po [3] MODI DANDA..MODI ABBREVIATION SIGN 11644 ; N # Lo MODI SIGN HUVA 11650..11659 ; N # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +11660..1166C ; N # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11680..116AA ; N # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA 116AB ; N # Mn TAKRI SIGN ANUSVARA 116AC ; N # Mc TAKRI SIGN VISARGA @@ -1507,7 +1559,59 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 118E0..118E9 ; N # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE 118EA..118F2 ; N # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; N # Lo WARANG CITI OM +11A00 ; N # Lo ZANABAZAR SQUARE LETTER A +11A01..11A06 ; N # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; N # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; N # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A0B..11A32 ; N # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A33..11A38 ; N # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; N # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3A ; N # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A3B..11A3E ; N # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A3F..11A46 ; N # Po [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A47 ; N # Mn ZANABAZAR SQUARE SUBJOINER +11A50 ; N # Lo SOYOMBO LETTER A +11A51..11A56 ; N # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; N # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; N # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A5C..11A83 ; N # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; N # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A8A..11A96 ; N # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; N # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; N # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11A9A..11A9C ; N # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; N # Po [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 11AC0..11AF8 ; N # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; N # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; N # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C2F ; N # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; N # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; N # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; N # Mc BHAIKSUKI SIGN VISARGA +11C3F ; N # Mn BHAIKSUKI SIGN VIRAMA +11C40 ; N # Lo BHAIKSUKI SIGN AVAGRAHA +11C41..11C45 ; N # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C50..11C59 ; N # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11C5A..11C6C ; N # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C70..11C71 ; N # Po [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD +11C72..11C8F ; N # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11C92..11CA7 ; N # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; N # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; N # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; N # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; N # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; N # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; N # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D00..11D06 ; N # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; N # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; N # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D31..11D36 ; N # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; N # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; N # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; N # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D46 ; N # Lo MASARAM GONDI REPHA +11D47 ; N # Mn MASARAM GONDI RA-KARA +11D50..11D59 ; N # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 12000..12399 ; N # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; N # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12470..12474 ; N # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON @@ -1617,9 +1721,18 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1DA87..1DA8B ; N # Po [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS 1DA9B..1DA9F ; N # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; N # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; N # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; N # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; N # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; N # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; N # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E800..1E8C4 ; N # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; N # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1E8D0..1E8D6 ; N # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E900..1E943 ; N # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA +1E944..1E94A ; N # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E950..1E959 ; N # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1E95E..1E95F ; N # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK 1EE00..1EE03 ; N # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; N # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; N # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1654,22 +1767,39 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1EEA5..1EEA9 ; N # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; N # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; N # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -1F000..1F02B ; N # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK +1F000..1F003 ; N # So [4] MAHJONG TILE EAST WIND..MAHJONG TILE NORTH WIND +1F005..1F02B ; N # So [39] MAHJONG TILE GREEN DRAGON..MAHJONG TILE BACK 1F030..1F093 ; N # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 1F0A0..1F0AE ; N # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES 1F0B1..1F0BF ; N # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER -1F0C1..1F0CF ; N # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER +1F0C1..1F0CE ; N # So [14] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD KING OF DIAMONDS 1F0D1..1F0F5 ; N # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F10B..1F10C ; N # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F12E ; N # So CIRCLED WZ 1F16A..1F16B ; N # So [2] RAISED MC SIGN..RAISED MD SIGN 1F1E6..1F1FF ; N # So [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z -1F300..1F3FA ; N # So [251] CYCLONE..AMPHORA -1F3FB..1F3FF ; N # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 -1F400..1F579 ; N # So [378] RAT..JOYSTICK -1F57B..1F5A3 ; N # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; N # So [300] DESKTOP COMPUTER..PLACE OF WORSHIP -1F6E0..1F6EC ; N # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING +1F321..1F32C ; N # So [12] THERMOMETER..WIND BLOWING FACE +1F336 ; N # So HOT PEPPER +1F37D ; N # So FORK AND KNIFE WITH PLATE +1F394..1F39F ; N # So [12] HEART WITH TIP ON THE LEFT..ADMISSION TICKETS +1F3CB..1F3CE ; N # So [4] WEIGHT LIFTER..RACING CAR +1F3D4..1F3DF ; N # So [12] SNOW CAPPED MOUNTAIN..STADIUM +1F3F1..1F3F3 ; N # So [3] WHITE PENNANT..WAVING WHITE FLAG +1F3F5..1F3F7 ; N # So [3] ROSETTE..LABEL +1F43F ; N # So CHIPMUNK +1F441 ; N # So EYE +1F4FD..1F4FE ; N # So [2] FILM PROJECTOR..PORTABLE STEREO +1F53E..1F54A ; N # So [13] LOWER RIGHT SHADOWED WHITE CIRCLE..DOVE OF PEACE +1F54F ; N # So BOWL OF HYGIEIA +1F568..1F579 ; N # So [18] RIGHT SPEAKER..JOYSTICK +1F57B..1F594 ; N # So [26] LEFT HAND TELEPHONE RECEIVER..REVERSED VICTORY HAND +1F597..1F5A3 ; N # So [13] WHITE DOWN POINTING LEFT HAND INDEX..BLACK DOWN POINTING BACKHAND INDEX +1F5A5..1F5FA ; N # So [86] DESKTOP COMPUTER..WORLD MAP +1F650..1F67F ; N # So [48] NORTH WEST POINTING LEAF..REVERSE CHECKER BOARD +1F6C6..1F6CB ; N # So [6] TRIANGLE WITH ROUNDED CORNERS..COUCH AND LAMP +1F6CD..1F6CF ; N # So [3] SHOPPING BAGS..BED +1F6D3..1F6D4 ; N # So [2] STUPA..PAGODA +1F6E0..1F6EA ; N # So [11] HAMMER AND WRENCH..NORTHEAST-POINTING AIRPLANE 1F6F0..1F6F3 ; N # So [4] SATELLITE..PASSENGER SHIP 1F700..1F773 ; N # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; N # So [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR @@ -1678,14 +1808,12 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1F850..1F859 ; N # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; N # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; N # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; N # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; N # So [5] CRAB..UNICORN FACE -1F9C0 ; N # So CHEESE WEDGE +1F900..1F90B ; N # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 778133 code points not listed here. -# Total code points: 801894 +# The above property value applies to 769609 code points not listed here. +# Total code points: 793401 # ================================================ @@ -1852,7 +1980,6 @@ E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG 2605..2606 ; A # So [2] BLACK STAR..WHITE STAR 2609 ; A # So SUN 260E..260F ; A # So [2] BLACK TELEPHONE..WHITE TELEPHONE -2614..2615 ; A # So [2] UMBRELLA WITH RAIN DROPS..HOT BEVERAGE 261C ; A # So WHITE LEFT POINTING INDEX 261E ; A # So WHITE RIGHT POINTING INDEX 2640 ; A # So FEMALE SIGN @@ -1863,15 +1990,20 @@ E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG 266C..266D ; A # So [2] BEAMED SIXTEENTH NOTES..MUSIC FLAT SIGN 266F ; A # Sm MUSIC SHARP SIGN 269E..269F ; A # So [2] THREE LINES CONVERGING RIGHT..THREE LINES CONVERGING LEFT -26BE..26BF ; A # So [2] BASEBALL..SQUARED KEY -26C4..26CD ; A # So [10] SNOWMAN WITHOUT SNOW..DISABLED CAR -26CF..26E1 ; A # So [19] PICK..RESTRICTED LEFT ENTRY-2 +26BF ; A # So SQUARED KEY +26C6..26CD ; A # So [8] RAIN..DISABLED CAR +26CF..26D3 ; A # So [5] PICK..CHAINS +26D5..26E1 ; A # So [13] ALTERNATE ONE-WAY LEFT WAY TRAFFIC..RESTRICTED LEFT ENTRY-2 26E3 ; A # So HEAVY CIRCLE WITH STROKE AND TWO DOTS ABOVE -26E8..26FF ; A # So [24] BLACK CROSS ON SHIELD..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE +26E8..26E9 ; A # So [2] BLACK CROSS ON SHIELD..SHINTO SHRINE +26EB..26F1 ; A # So [7] CASTLE..UMBRELLA ON GROUND +26F4 ; A # So FERRY +26F6..26F9 ; A # So [4] SQUARE FOUR CORNERS..PERSON WITH BALL +26FB..26FC ; A # So [2] JAPANESE BANK SYMBOL..HEADSTONE GRAVEYARD SYMBOL +26FE..26FF ; A # So [2] CUP ON BLACK SQUARE..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE 273D ; A # So HEAVY TEARDROP-SPOKED ASTERISK -2757 ; A # So HEAVY EXCLAMATION MARK SYMBOL 2776..277F ; A # No [10] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED NUMBER TEN -2B55..2B59 ; A # So [5] HEAVY LARGE CIRCLE..HEAVY CIRCLED SALTIRE +2B56..2B59 ; A # So [4] HEAVY OVAL WITH OVAL INSIDE..HEAVY CIRCLED SALTIRE 3248..324F ; A # No [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE E000..F8FF ; A # Co [6400] <private-use-E000>..<private-use-F8FF> FE00..FE0F ; A # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 @@ -1879,12 +2011,14 @@ FFFD ; A # So REPLACEMENT CHARACTER 1F100..1F10A ; A # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA 1F110..1F12D ; A # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD 1F130..1F169 ; A # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z -1F170..1F19A ; A # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F18D ; A # So [30] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED SA +1F18F..1F190 ; A # So [2] NEGATIVE SQUARED WC..SQUARE DJ +1F19B..1F1AC ; A # So [18] SQUARED THREE D..SQUARED VOD E0100..E01EF ; A # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; A # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; A # Co [65534] <private-use-100000>..<private-use-10FFFD> -# Total code points: 138746 +# Total code points: 138739 # ================================================ @@ -1915,8 +2049,41 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE # East_Asian_Width=Wide 1100..115F ; W # Lo [96] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG FILLER +231A..231B ; W # So [2] WATCH..HOURGLASS 2329 ; W # Ps LEFT-POINTING ANGLE BRACKET 232A ; W # Pe RIGHT-POINTING ANGLE BRACKET +23E9..23EC ; W # So [4] BLACK RIGHT-POINTING DOUBLE TRIANGLE..BLACK DOWN-POINTING DOUBLE TRIANGLE +23F0 ; W # So ALARM CLOCK +23F3 ; W # So HOURGLASS WITH FLOWING SAND +25FD..25FE ; W # Sm [2] WHITE MEDIUM SMALL SQUARE..BLACK MEDIUM SMALL SQUARE +2614..2615 ; W # So [2] UMBRELLA WITH RAIN DROPS..HOT BEVERAGE +2648..2653 ; W # So [12] ARIES..PISCES +267F ; W # So WHEELCHAIR SYMBOL +2693 ; W # So ANCHOR +26A1 ; W # So HIGH VOLTAGE SIGN +26AA..26AB ; W # So [2] MEDIUM WHITE CIRCLE..MEDIUM BLACK CIRCLE +26BD..26BE ; W # So [2] SOCCER BALL..BASEBALL +26C4..26C5 ; W # So [2] SNOWMAN WITHOUT SNOW..SUN BEHIND CLOUD +26CE ; W # So OPHIUCHUS +26D4 ; W # So NO ENTRY +26EA ; W # So CHURCH +26F2..26F3 ; W # So [2] FOUNTAIN..FLAG IN HOLE +26F5 ; W # So SAILBOAT +26FA ; W # So TENT +26FD ; W # So FUEL PUMP +2705 ; W # So WHITE HEAVY CHECK MARK +270A..270B ; W # So [2] RAISED FIST..RAISED HAND +2728 ; W # So SPARKLES +274C ; W # So CROSS MARK +274E ; W # So NEGATIVE SQUARED CROSS MARK +2753..2755 ; W # So [3] BLACK QUESTION MARK ORNAMENT..WHITE EXCLAMATION MARK ORNAMENT +2757 ; W # So HEAVY EXCLAMATION MARK SYMBOL +2795..2797 ; W # So [3] HEAVY PLUS SIGN..HEAVY DIVISION SIGN +27B0 ; W # So CURLY LOOP +27BF ; W # So DOUBLE CURLY LOOP +2B1B..2B1C ; W # So [2] BLACK LARGE SQUARE..WHITE LARGE SQUARE +2B50 ; W # So WHITE MEDIUM STAR +2B55 ; W # So HEAVY LARGE CIRCLE 2E80..2E99 ; W # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; W # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; W # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1970,7 +2137,7 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 30FB ; W # Po KATAKANA MIDDLE DOT 30FC..30FE ; W # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK 30FF ; W # Lo KATAKANA DIGRAPH KOTO -3105..312D ; W # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; W # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; W # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; W # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; W # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1991,8 +2158,8 @@ FFED..FFEE ; H # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3300..33FF ; W # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF ; W # Cn [10] <reserved-4DB6>..<reserved-4DBF> -4E00..9FD5 ; W # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF ; W # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA ; W # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF ; W # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014 ; W # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; W # Lm YI SYLLABLE WU A016..A48C ; W # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -2047,11 +2214,51 @@ FE64..FE66 ; W # Sm [3] SMALL LESS-THAN SIGN..SMALL EQUALS SIGN FE68 ; W # Po SMALL REVERSE SOLIDUS FE69 ; W # Sc SMALL DOLLAR SIGN FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT -1B000..1B001 ; W # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +16FE0..16FE1 ; W # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +17000..187EC ; W # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; W # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; W # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; W # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB +1F004 ; W # So MAHJONG TILE RED DRAGON +1F0CF ; W # So PLAYING CARD BLACK JOKER +1F18E ; W # So NEGATIVE SQUARED AB +1F191..1F19A ; W # So [10] SQUARED CL..SQUARED VS 1F200..1F202 ; W # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; W # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; W # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; W # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; W # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; W # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F300..1F320 ; W # So [33] CYCLONE..SHOOTING STAR +1F32D..1F335 ; W # So [9] HOT DOG..CACTUS +1F337..1F37C ; W # So [70] TULIP..BABY BOTTLE +1F37E..1F393 ; W # So [22] BOTTLE WITH POPPING CORK..GRADUATION CAP +1F3A0..1F3CA ; W # So [43] CAROUSEL HORSE..SWIMMER +1F3CF..1F3D3 ; W # So [5] CRICKET BAT AND BALL..TABLE TENNIS PADDLE AND BALL +1F3E0..1F3F0 ; W # So [17] HOUSE BUILDING..EUROPEAN CASTLE +1F3F4 ; W # So WAVING BLACK FLAG +1F3F8..1F3FA ; W # So [3] BADMINTON RACQUET AND SHUTTLECOCK..AMPHORA +1F3FB..1F3FF ; W # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 +1F400..1F43E ; W # So [63] RAT..PAW PRINTS +1F440 ; W # So EYES +1F442..1F4FC ; W # So [187] EAR..VIDEOCASSETTE +1F4FF..1F53D ; W # So [63] PRAYER BEADS..DOWN-POINTING SMALL RED TRIANGLE +1F54B..1F54E ; W # So [4] KAABA..MENORAH WITH NINE BRANCHES +1F550..1F567 ; W # So [24] CLOCK FACE ONE OCLOCK..CLOCK FACE TWELVE-THIRTY +1F57A ; W # So MAN DANCING +1F595..1F596 ; W # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F5A4 ; W # So BLACK HEART +1F5FB..1F64F ; W # So [85] MOUNT FUJI..PERSON WITH FOLDED HANDS +1F680..1F6C5 ; W # So [70] ROCKET..LEFT LUGGAGE +1F6CC ; W # So SLEEPING ACCOMMODATION +1F6D0..1F6D2 ; W # So [3] PLACE OF WORSHIP..SHOPPING TROLLEY +1F6EB..1F6EC ; W # So [2] AIRPLANE DEPARTURE..AIRPLANE ARRIVING +1F6F4..1F6F8 ; W # So [5] SCOOTER..FLYING SAUCER +1F910..1F93E ; W # So [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; W # So [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; W # So [28] CROISSANT..CANNED FOOD +1F980..1F997 ; W # So [24] CRAB..CRICKET +1F9C0 ; W # So CHEESE WEDGE +1F9D0..1F9E6 ; W # So [23] FACE WITH MONOCLE..SOCKS 20000..2A6D6 ; W # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF ; W # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734 ; W # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -2059,12 +2266,14 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 2B740..2B81D ; W # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; W # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; W # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF ; W # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; W # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0 ; W # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF ; W # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D ; W # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD ; W # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD ; W # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 173134 +# Total code points: 181634 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DGeneralCategory.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DGeneralCategory.txt index 77c9b389c9e..bc7f5e84ea0 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DGeneralCategory.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DGeneralCategory.txt @@ -1,10 +1,11 @@ -# DerivedGeneralCategory-8.0.0.txt -# Date: 2015-02-13, 13:47:11 GMT [MD] +# DerivedGeneralCategory-10.0.0.txt +# Date: 2017-03-08, 08:41:49 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -36,8 +37,10 @@ 082E..082F ; Cn # [2] <reserved-082E>..<reserved-082F> 083F ; Cn # <reserved-083F> 085C..085D ; Cn # [2] <reserved-085C>..<reserved-085D> -085F..089F ; Cn # [65] <reserved-085F>..<reserved-089F> -08B5..08E2 ; Cn # [46] <reserved-08B5>..<reserved-08E2> +085F ; Cn # <reserved-085F> +086B..089F ; Cn # [53] <reserved-086B>..<reserved-089F> +08B5 ; Cn # <reserved-08B5> +08BE..08D3 ; Cn # [22] <reserved-08BE>..<reserved-08D3> 0984 ; Cn # <reserved-0984> 098D..098E ; Cn # [2] <reserved-098D>..<reserved-098E> 0991..0992 ; Cn # [2] <reserved-0991>..<reserved-0992> @@ -51,7 +54,7 @@ 09D8..09DB ; Cn # [4] <reserved-09D8>..<reserved-09DB> 09DE ; Cn # <reserved-09DE> 09E4..09E5 ; Cn # [2] <reserved-09E4>..<reserved-09E5> -09FC..0A00 ; Cn # [5] <reserved-09FC>..<reserved-0A00> +09FE..0A00 ; Cn # [3] <reserved-09FE>..<reserved-0A00> 0A04 ; Cn # <reserved-0A04> 0A0B..0A0E ; Cn # [4] <reserved-0A0B>..<reserved-0A0E> 0A11..0A12 ; Cn # [2] <reserved-0A11>..<reserved-0A12> @@ -81,7 +84,7 @@ 0AD1..0ADF ; Cn # [15] <reserved-0AD1>..<reserved-0ADF> 0AE4..0AE5 ; Cn # [2] <reserved-0AE4>..<reserved-0AE5> 0AF2..0AF8 ; Cn # [7] <reserved-0AF2>..<reserved-0AF8> -0AFA..0B00 ; Cn # [7] <reserved-0AFA>..<reserved-0B00> +0B00 ; Cn # <reserved-0B00> 0B04 ; Cn # <reserved-0B04> 0B0D..0B0E ; Cn # [2] <reserved-0B0D>..<reserved-0B0E> 0B11..0B12 ; Cn # [2] <reserved-0B11>..<reserved-0B12> @@ -124,7 +127,6 @@ 0C5B..0C5F ; Cn # [5] <reserved-0C5B>..<reserved-0C5F> 0C64..0C65 ; Cn # [2] <reserved-0C64>..<reserved-0C65> 0C70..0C77 ; Cn # [8] <reserved-0C70>..<reserved-0C77> -0C80 ; Cn # <reserved-0C80> 0C84 ; Cn # <reserved-0C84> 0C8D ; Cn # <reserved-0C8D> 0C91 ; Cn # <reserved-0C91> @@ -138,17 +140,14 @@ 0CDF ; Cn # <reserved-0CDF> 0CE4..0CE5 ; Cn # [2] <reserved-0CE4>..<reserved-0CE5> 0CF0 ; Cn # <reserved-0CF0> -0CF3..0D00 ; Cn # [14] <reserved-0CF3>..<reserved-0D00> +0CF3..0CFF ; Cn # [13] <reserved-0CF3>..<reserved-0CFF> 0D04 ; Cn # <reserved-0D04> 0D0D ; Cn # <reserved-0D0D> 0D11 ; Cn # <reserved-0D11> -0D3B..0D3C ; Cn # [2] <reserved-0D3B>..<reserved-0D3C> 0D45 ; Cn # <reserved-0D45> 0D49 ; Cn # <reserved-0D49> -0D4F..0D56 ; Cn # [8] <reserved-0D4F>..<reserved-0D56> -0D58..0D5E ; Cn # [7] <reserved-0D58>..<reserved-0D5E> +0D50..0D53 ; Cn # [4] <reserved-0D50>..<reserved-0D53> 0D64..0D65 ; Cn # [2] <reserved-0D64>..<reserved-0D65> -0D76..0D78 ; Cn # [3] <reserved-0D76>..<reserved-0D78> 0D80..0D81 ; Cn # [2] <reserved-0D80>..<reserved-0D81> 0D84 ; Cn # <reserved-0D84> 0D97..0D99 ; Cn # [3] <reserved-0D97>..<reserved-0D99> @@ -249,11 +248,10 @@ 1BF4..1BFB ; Cn # [8] <reserved-1BF4>..<reserved-1BFB> 1C38..1C3A ; Cn # [3] <reserved-1C38>..<reserved-1C3A> 1C4A..1C4C ; Cn # [3] <reserved-1C4A>..<reserved-1C4C> -1C80..1CBF ; Cn # [64] <reserved-1C80>..<reserved-1CBF> +1C89..1CBF ; Cn # [55] <reserved-1C89>..<reserved-1CBF> 1CC8..1CCF ; Cn # [8] <reserved-1CC8>..<reserved-1CCF> -1CF7 ; Cn # <reserved-1CF7> 1CFA..1CFF ; Cn # [6] <reserved-1CFA>..<reserved-1CFF> -1DF6..1DFB ; Cn # [6] <reserved-1DF6>..<reserved-1DFB> +1DFA ; Cn # <reserved-1DFA> 1F16..1F17 ; Cn # [2] <reserved-1F16>..<reserved-1F17> 1F1E..1F1F ; Cn # [2] <reserved-1F1E>..<reserved-1F1F> 1F46..1F47 ; Cn # [2] <reserved-1F46>..<reserved-1F47> @@ -274,17 +272,16 @@ 2072..2073 ; Cn # [2] <reserved-2072>..<reserved-2073> 208F ; Cn # <reserved-208F> 209D..209F ; Cn # [3] <reserved-209D>..<reserved-209F> -20BF..20CF ; Cn # [17] <reserved-20BF>..<reserved-20CF> +20C0..20CF ; Cn # [16] <reserved-20C0>..<reserved-20CF> 20F1..20FF ; Cn # [15] <reserved-20F1>..<reserved-20FF> 218C..218F ; Cn # [4] <reserved-218C>..<reserved-218F> -23FB..23FF ; Cn # [5] <reserved-23FB>..<reserved-23FF> 2427..243F ; Cn # [25] <reserved-2427>..<reserved-243F> 244B..245F ; Cn # [21] <reserved-244B>..<reserved-245F> 2B74..2B75 ; Cn # [2] <reserved-2B74>..<reserved-2B75> 2B96..2B97 ; Cn # [2] <reserved-2B96>..<reserved-2B97> 2BBA..2BBC ; Cn # [3] <reserved-2BBA>..<reserved-2BBC> 2BC9 ; Cn # <reserved-2BC9> -2BD2..2BEB ; Cn # [26] <reserved-2BD2>..<reserved-2BEB> +2BD3..2BEB ; Cn # [25] <reserved-2BD3>..<reserved-2BEB> 2BF0..2BFF ; Cn # [16] <reserved-2BF0>..<reserved-2BFF> 2C2F ; Cn # <reserved-2C2F> 2C5F ; Cn # <reserved-2C5F> @@ -303,7 +300,7 @@ 2DCF ; Cn # <reserved-2DCF> 2DD7 ; Cn # <reserved-2DD7> 2DDF ; Cn # <reserved-2DDF> -2E43..2E7F ; Cn # [61] <reserved-2E43>..<reserved-2E7F> +2E4A..2E7F ; Cn # [54] <reserved-2E4A>..<reserved-2E7F> 2E9A ; Cn # <reserved-2E9A> 2EF4..2EFF ; Cn # [12] <reserved-2EF4>..<reserved-2EFF> 2FD6..2FEF ; Cn # [26] <reserved-2FD6>..<reserved-2FEF> @@ -311,24 +308,24 @@ 3040 ; Cn # <reserved-3040> 3097..3098 ; Cn # [2] <reserved-3097>..<reserved-3098> 3100..3104 ; Cn # [5] <reserved-3100>..<reserved-3104> -312E..3130 ; Cn # [3] <reserved-312E>..<reserved-3130> +312F..3130 ; Cn # [2] <reserved-312F>..<reserved-3130> 318F ; Cn # <reserved-318F> 31BB..31BF ; Cn # [5] <reserved-31BB>..<reserved-31BF> 31E4..31EF ; Cn # [12] <reserved-31E4>..<reserved-31EF> 321F ; Cn # <reserved-321F> 32FF ; Cn # <reserved-32FF> 4DB6..4DBF ; Cn # [10] <reserved-4DB6>..<reserved-4DBF> -9FD6..9FFF ; Cn # [42] <reserved-9FD6>..<reserved-9FFF> +9FEB..9FFF ; Cn # [21] <reserved-9FEB>..<reserved-9FFF> A48D..A48F ; Cn # [3] <reserved-A48D>..<reserved-A48F> A4C7..A4CF ; Cn # [9] <reserved-A4C7>..<reserved-A4CF> A62C..A63F ; Cn # [20] <reserved-A62C>..<reserved-A63F> A6F8..A6FF ; Cn # [8] <reserved-A6F8>..<reserved-A6FF> -A7AE..A7AF ; Cn # [2] <reserved-A7AE>..<reserved-A7AF> +A7AF ; Cn # <reserved-A7AF> A7B8..A7F6 ; Cn # [63] <reserved-A7B8>..<reserved-A7F6> A82C..A82F ; Cn # [4] <reserved-A82C>..<reserved-A82F> A83A..A83F ; Cn # [6] <reserved-A83A>..<reserved-A83F> A878..A87F ; Cn # [8] <reserved-A878>..<reserved-A87F> -A8C5..A8CD ; Cn # [9] <reserved-A8C5>..<reserved-A8CD> +A8C6..A8CD ; Cn # [8] <reserved-A8C6>..<reserved-A8CD> A8DA..A8DF ; Cn # [6] <reserved-A8DA>..<reserved-A8DF> A8FE..A8FF ; Cn # [2] <reserved-A8FE>..<reserved-A8FF> A954..A95E ; Cn # [11] <reserved-A954>..<reserved-A95E> @@ -390,21 +387,23 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 100FB..100FF ; Cn # [5] <reserved-100FB>..<reserved-100FF> 10103..10106 ; Cn # [4] <reserved-10103>..<reserved-10106> 10134..10136 ; Cn # [3] <reserved-10134>..<reserved-10136> -1018D..1018F ; Cn # [3] <reserved-1018D>..<reserved-1018F> +1018F ; Cn # <reserved-1018F> 1019C..1019F ; Cn # [4] <reserved-1019C>..<reserved-1019F> 101A1..101CF ; Cn # [47] <reserved-101A1>..<reserved-101CF> 101FE..1027F ; Cn # [130] <reserved-101FE>..<reserved-1027F> 1029D..1029F ; Cn # [3] <reserved-1029D>..<reserved-1029F> 102D1..102DF ; Cn # [15] <reserved-102D1>..<reserved-102DF> 102FC..102FF ; Cn # [4] <reserved-102FC>..<reserved-102FF> -10324..1032F ; Cn # [12] <reserved-10324>..<reserved-1032F> +10324..1032C ; Cn # [9] <reserved-10324>..<reserved-1032C> 1034B..1034F ; Cn # [5] <reserved-1034B>..<reserved-1034F> 1037B..1037F ; Cn # [5] <reserved-1037B>..<reserved-1037F> 1039E ; Cn # <reserved-1039E> 103C4..103C7 ; Cn # [4] <reserved-103C4>..<reserved-103C7> 103D6..103FF ; Cn # [42] <reserved-103D6>..<reserved-103FF> 1049E..1049F ; Cn # [2] <reserved-1049E>..<reserved-1049F> -104AA..104FF ; Cn # [86] <reserved-104AA>..<reserved-104FF> +104AA..104AF ; Cn # [6] <reserved-104AA>..<reserved-104AF> +104D4..104D7 ; Cn # [4] <reserved-104D4>..<reserved-104D7> +104FC..104FF ; Cn # [4] <reserved-104FC>..<reserved-104FF> 10528..1052F ; Cn # [8] <reserved-10528>..<reserved-1052F> 10564..1056E ; Cn # [11] <reserved-10564>..<reserved-1056E> 10570..105FF ; Cn # [144] <reserved-10570>..<reserved-105FF> @@ -460,7 +459,7 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 111E0 ; Cn # <reserved-111E0> 111F5..111FF ; Cn # [11] <reserved-111F5>..<reserved-111FF> 11212 ; Cn # <reserved-11212> -1123E..1127F ; Cn # [66] <reserved-1123E>..<reserved-1127F> +1123F..1127F ; Cn # [65] <reserved-1123F>..<reserved-1127F> 11287 ; Cn # <reserved-11287> 11289 ; Cn # <reserved-11289> 1128E ; Cn # <reserved-1128E> @@ -482,21 +481,43 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 11358..1135C ; Cn # [5] <reserved-11358>..<reserved-1135C> 11364..11365 ; Cn # [2] <reserved-11364>..<reserved-11365> 1136D..1136F ; Cn # [3] <reserved-1136D>..<reserved-1136F> -11375..1147F ; Cn # [267] <reserved-11375>..<reserved-1147F> +11375..113FF ; Cn # [139] <reserved-11375>..<reserved-113FF> +1145A ; Cn # <reserved-1145A> +1145C ; Cn # <reserved-1145C> +1145E..1147F ; Cn # [34] <reserved-1145E>..<reserved-1147F> 114C8..114CF ; Cn # [8] <reserved-114C8>..<reserved-114CF> 114DA..1157F ; Cn # [166] <reserved-114DA>..<reserved-1157F> 115B6..115B7 ; Cn # [2] <reserved-115B6>..<reserved-115B7> 115DE..115FF ; Cn # [34] <reserved-115DE>..<reserved-115FF> 11645..1164F ; Cn # [11] <reserved-11645>..<reserved-1164F> -1165A..1167F ; Cn # [38] <reserved-1165A>..<reserved-1167F> +1165A..1165F ; Cn # [6] <reserved-1165A>..<reserved-1165F> +1166D..1167F ; Cn # [19] <reserved-1166D>..<reserved-1167F> 116B8..116BF ; Cn # [8] <reserved-116B8>..<reserved-116BF> 116CA..116FF ; Cn # [54] <reserved-116CA>..<reserved-116FF> 1171A..1171C ; Cn # [3] <reserved-1171A>..<reserved-1171C> 1172C..1172F ; Cn # [4] <reserved-1172C>..<reserved-1172F> 11740..1189F ; Cn # [352] <reserved-11740>..<reserved-1189F> 118F3..118FE ; Cn # [12] <reserved-118F3>..<reserved-118FE> -11900..11ABF ; Cn # [448] <reserved-11900>..<reserved-11ABF> -11AF9..11FFF ; Cn # [1287] <reserved-11AF9>..<reserved-11FFF> +11900..119FF ; Cn # [256] <reserved-11900>..<reserved-119FF> +11A48..11A4F ; Cn # [8] <reserved-11A48>..<reserved-11A4F> +11A84..11A85 ; Cn # [2] <reserved-11A84>..<reserved-11A85> +11A9D ; Cn # <reserved-11A9D> +11AA3..11ABF ; Cn # [29] <reserved-11AA3>..<reserved-11ABF> +11AF9..11BFF ; Cn # [263] <reserved-11AF9>..<reserved-11BFF> +11C09 ; Cn # <reserved-11C09> +11C37 ; Cn # <reserved-11C37> +11C46..11C4F ; Cn # [10] <reserved-11C46>..<reserved-11C4F> +11C6D..11C6F ; Cn # [3] <reserved-11C6D>..<reserved-11C6F> +11C90..11C91 ; Cn # [2] <reserved-11C90>..<reserved-11C91> +11CA8 ; Cn # <reserved-11CA8> +11CB7..11CFF ; Cn # [73] <reserved-11CB7>..<reserved-11CFF> +11D07 ; Cn # <reserved-11D07> +11D0A ; Cn # <reserved-11D0A> +11D37..11D39 ; Cn # [3] <reserved-11D37>..<reserved-11D39> +11D3B ; Cn # <reserved-11D3B> +11D3E ; Cn # <reserved-11D3E> +11D48..11D4F ; Cn # [8] <reserved-11D48>..<reserved-11D4F> +11D5A..11FFF ; Cn # [678] <reserved-11D5A>..<reserved-11FFF> 1239A..123FF ; Cn # [102] <reserved-1239A>..<reserved-123FF> 1246F ; Cn # <reserved-1246F> 12475..1247F ; Cn # [11] <reserved-12475>..<reserved-1247F> @@ -516,8 +537,12 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 16B90..16EFF ; Cn # [880] <reserved-16B90>..<reserved-16EFF> 16F45..16F4F ; Cn # [11] <reserved-16F45>..<reserved-16F4F> 16F7F..16F8E ; Cn # [16] <reserved-16F7F>..<reserved-16F8E> -16FA0..1AFFF ; Cn # [16480] <reserved-16FA0>..<reserved-1AFFF> -1B002..1BBFF ; Cn # [3070] <reserved-1B002>..<reserved-1BBFF> +16FA0..16FDF ; Cn # [64] <reserved-16FA0>..<reserved-16FDF> +16FE2..16FFF ; Cn # [30] <reserved-16FE2>..<reserved-16FFF> +187ED..187FF ; Cn # [19] <reserved-187ED>..<reserved-187FF> +18AF3..1AFFF ; Cn # [9485] <reserved-18AF3>..<reserved-1AFFF> +1B11F..1B16F ; Cn # [81] <reserved-1B11F>..<reserved-1B16F> +1B2FC..1BBFF ; Cn # [2308] <reserved-1B2FC>..<reserved-1BBFF> 1BC6B..1BC6F ; Cn # [5] <reserved-1BC6B>..<reserved-1BC6F> 1BC7D..1BC7F ; Cn # [3] <reserved-1BC7D>..<reserved-1BC7F> 1BC89..1BC8F ; Cn # [7] <reserved-1BC89>..<reserved-1BC8F> @@ -551,9 +576,17 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1D7CC..1D7CD ; Cn # [2] <reserved-1D7CC>..<reserved-1D7CD> 1DA8C..1DA9A ; Cn # [15] <reserved-1DA8C>..<reserved-1DA9A> 1DAA0 ; Cn # <reserved-1DAA0> -1DAB0..1E7FF ; Cn # [3408] <reserved-1DAB0>..<reserved-1E7FF> +1DAB0..1DFFF ; Cn # [1360] <reserved-1DAB0>..<reserved-1DFFF> +1E007 ; Cn # <reserved-1E007> +1E019..1E01A ; Cn # [2] <reserved-1E019>..<reserved-1E01A> +1E022 ; Cn # <reserved-1E022> +1E025 ; Cn # <reserved-1E025> +1E02B..1E7FF ; Cn # [2005] <reserved-1E02B>..<reserved-1E7FF> 1E8C5..1E8C6 ; Cn # [2] <reserved-1E8C5>..<reserved-1E8C6> -1E8D7..1EDFF ; Cn # [1321] <reserved-1E8D7>..<reserved-1EDFF> +1E8D7..1E8FF ; Cn # [41] <reserved-1E8D7>..<reserved-1E8FF> +1E94B..1E94F ; Cn # [5] <reserved-1E94B>..<reserved-1E94F> +1E95A..1E95D ; Cn # [4] <reserved-1E95A>..<reserved-1E95D> +1E960..1EDFF ; Cn # [1184] <reserved-1E960>..<reserved-1EDFF> 1EE04 ; Cn # <reserved-1EE04> 1EE20 ; Cn # <reserved-1EE20> 1EE23 ; Cn # <reserved-1EE23> @@ -597,30 +630,34 @@ FFFE..FFFF ; Cn # [2] <noncharacter-FFFE>..<noncharacter-FFFF> 1F10D..1F10F ; Cn # [3] <reserved-1F10D>..<reserved-1F10F> 1F12F ; Cn # <reserved-1F12F> 1F16C..1F16F ; Cn # [4] <reserved-1F16C>..<reserved-1F16F> -1F19B..1F1E5 ; Cn # [75] <reserved-1F19B>..<reserved-1F1E5> +1F1AD..1F1E5 ; Cn # [57] <reserved-1F1AD>..<reserved-1F1E5> 1F203..1F20F ; Cn # [13] <reserved-1F203>..<reserved-1F20F> -1F23B..1F23F ; Cn # [5] <reserved-1F23B>..<reserved-1F23F> +1F23C..1F23F ; Cn # [4] <reserved-1F23C>..<reserved-1F23F> 1F249..1F24F ; Cn # [7] <reserved-1F249>..<reserved-1F24F> -1F252..1F2FF ; Cn # [174] <reserved-1F252>..<reserved-1F2FF> -1F57A ; Cn # <reserved-1F57A> -1F5A4 ; Cn # <reserved-1F5A4> -1F6D1..1F6DF ; Cn # [15] <reserved-1F6D1>..<reserved-1F6DF> +1F252..1F25F ; Cn # [14] <reserved-1F252>..<reserved-1F25F> +1F266..1F2FF ; Cn # [154] <reserved-1F266>..<reserved-1F2FF> +1F6D5..1F6DF ; Cn # [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6ED..1F6EF ; Cn # [3] <reserved-1F6ED>..<reserved-1F6EF> -1F6F4..1F6FF ; Cn # [12] <reserved-1F6F4>..<reserved-1F6FF> +1F6F9..1F6FF ; Cn # [7] <reserved-1F6F9>..<reserved-1F6FF> 1F774..1F77F ; Cn # [12] <reserved-1F774>..<reserved-1F77F> 1F7D5..1F7FF ; Cn # [43] <reserved-1F7D5>..<reserved-1F7FF> 1F80C..1F80F ; Cn # [4] <reserved-1F80C>..<reserved-1F80F> 1F848..1F84F ; Cn # [8] <reserved-1F848>..<reserved-1F84F> 1F85A..1F85F ; Cn # [6] <reserved-1F85A>..<reserved-1F85F> 1F888..1F88F ; Cn # [8] <reserved-1F888>..<reserved-1F88F> -1F8AE..1F90F ; Cn # [98] <reserved-1F8AE>..<reserved-1F90F> -1F919..1F97F ; Cn # [103] <reserved-1F919>..<reserved-1F97F> -1F985..1F9BF ; Cn # [59] <reserved-1F985>..<reserved-1F9BF> -1F9C1..1FFFF ; Cn # [1599] <reserved-1F9C1>..<noncharacter-1FFFF> +1F8AE..1F8FF ; Cn # [82] <reserved-1F8AE>..<reserved-1F8FF> +1F90C..1F90F ; Cn # [4] <reserved-1F90C>..<reserved-1F90F> +1F93F ; Cn # <reserved-1F93F> +1F94D..1F94F ; Cn # [3] <reserved-1F94D>..<reserved-1F94F> +1F96C..1F97F ; Cn # [20] <reserved-1F96C>..<reserved-1F97F> +1F998..1F9BF ; Cn # [40] <reserved-1F998>..<reserved-1F9BF> +1F9C1..1F9CF ; Cn # [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9E7..1FFFF ; Cn # [1561] <reserved-1F9E7>..<noncharacter-1FFFF> 2A6D7..2A6FF ; Cn # [41] <reserved-2A6D7>..<reserved-2A6FF> 2B735..2B73F ; Cn # [11] <reserved-2B735>..<reserved-2B73F> 2B81E..2B81F ; Cn # [2] <reserved-2B81E>..<reserved-2B81F> -2CEA2..2F7FF ; Cn # [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; Cn # [14] <reserved-2CEA2>..<reserved-2CEAF> +2EBE1..2F7FF ; Cn # [3103] <reserved-2EBE1>..<reserved-2F7FF> 2FA1E..E0000 ; Cn # [722403] <reserved-2FA1E>..<reserved-E0000> E0002..E001F ; Cn # [30] <reserved-E0002>..<reserved-E001F> E0080..E00FF ; Cn # [128] <reserved-E0080>..<reserved-E00FF> @@ -628,7 +665,7 @@ E01F0..EFFFF ; Cn # [65040] <reserved-E01F0>..<noncharacter-EFFFF> FFFFE..FFFFF ; Cn # [2] <noncharacter-FFFFE>..<noncharacter-FFFFF> 10FFFE..10FFFF; Cn # [2] <noncharacter-10FFFE>..<noncharacter-10FFFF> -# Total code points: 853859 +# Total code points: 837841 # ================================================ @@ -1221,11 +1258,12 @@ A7A2 ; Lu # LATIN CAPITAL LETTER K WITH OBLIQUE STROKE A7A4 ; Lu # LATIN CAPITAL LETTER N WITH OBLIQUE STROKE A7A6 ; Lu # LATIN CAPITAL LETTER R WITH OBLIQUE STROKE A7A8 ; Lu # LATIN CAPITAL LETTER S WITH OBLIQUE STROKE -A7AA..A7AD ; Lu # [4] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER L WITH BELT +A7AA..A7AE ; Lu # [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B4 ; Lu # [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA A7B6 ; Lu # LATIN CAPITAL LETTER OMEGA FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z 10400..10427 ; Lu # [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Lu # [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA 10C80..10CB2 ; Lu # [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 118A0..118BF ; Lu # [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO 1D400..1D419 ; Lu # [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z @@ -1259,8 +1297,9 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D756..1D76E ; Lu # [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA 1D790..1D7A8 ; Lu # [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA +1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1631 +# Total code points: 1702 # ================================================ @@ -1537,6 +1576,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 052F ; Ll # CYRILLIC SMALL LETTER EL WITH DESCENDER 0561..0587 ; Ll # [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN 13F8..13FD ; Ll # [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Ll # [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1D00..1D2B ; Ll # [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D6B..1D77 ; Ll # [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G 1D79..1D9A ; Ll # [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK @@ -1866,6 +1906,7 @@ FB00..FB06 ; Ll # [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; Ll # [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z 10428..1044F ; Ll # [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Ll # [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10CC0..10CF2 ; Ll # [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 118C0..118DF ; Ll # [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 1D41A..1D433 ; Ll # [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z @@ -1896,8 +1937,9 @@ FF41..FF5A ; Ll # [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL 1D7AA..1D7C2 ; Ll # [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7C9 ; Ll # [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CB ; Ll # MATHEMATICAL BOLD SMALL DIGAMMA +1E922..1E943 ; Ll # [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1984 +# Total code points: 2063 # ================================================ @@ -1976,8 +2018,9 @@ FF70 ; Lm # HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16F93..16F9F ; Lm # [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 +16FE0..16FE1 ; Lm # [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK -# Total code points: 248 +# Total code points: 250 # ================================================ @@ -2005,7 +2048,9 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 07CA..07EA ; Lo # [33] NKO LETTER A..NKO LETTER JONA RA 0800..0815 ; Lo # [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; Lo # [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; Lo # [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON 0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; Lo # DEVANAGARI SIGN AVAGRAHA 0950 ; Lo # DEVANAGARI OM @@ -2022,6 +2067,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 09DC..09DD ; Lo # [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; Lo # [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; Lo # [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; Lo # BENGALI LETTER VEDIC ANUSVARA 0A05..0A0A ; Lo # [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Lo # [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; Lo # [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -2070,6 +2116,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0C3D ; Lo # TELUGU SIGN AVAGRAHA 0C58..0C5A ; Lo # [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0C60..0C61 ; Lo # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; Lo # KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; Lo # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; Lo # [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; Lo # [23] KANNADA LETTER O..KANNADA LETTER NA @@ -2084,6 +2131,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0D12..0D3A ; Lo # [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; Lo # MALAYALAM SIGN AVAGRAHA 0D4E ; Lo # MALAYALAM LETTER DOT REPH +0D54..0D56 ; Lo # [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL 0D5F..0D61 ; Lo # [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL 0D7A..0D7F ; Lo # [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; Lo # [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA @@ -2156,7 +2204,8 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 17DC ; Lo # KHMER SIGN AVAKRAHASANYA 1820..1842 ; Lo # [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1844..1877 ; Lo # [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; Lo # [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; Lo # [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; Lo # [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; Lo # MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; Lo # [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; Lo # [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -2194,12 +2243,12 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 309F ; Lo # HIRAGANA DIGRAPH YORI 30A1..30FA ; Lo # [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO 30FF ; Lo # KATAKANA DIGRAPH KOTO -3105..312D ; Lo # [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; Lo # [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; Lo # [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 31A0..31BA ; Lo # [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY 31F0..31FF ; Lo # [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO 3400..4DB5 ; Lo # [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FD5 ; Lo # [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 +4E00..9FEA ; Lo # [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA A000..A014 ; Lo # [21] YI SYLLABLE IT..YI SYLLABLE E A016..A48C ; Lo # [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A4D0..A4F7 ; Lo # [40] LISU LETTER BA..LISU LETTER OE @@ -2283,7 +2332,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10280..1029C ; Lo # [29] LYCIAN LETTER A..LYCIAN LETTER X 102A0..102D0 ; Lo # [49] CARIAN LETTER A..CARIAN LETTER UUU3 10300..1031F ; Lo # [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS -10330..10340 ; Lo # [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; Lo # [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10342..10349 ; Lo # [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 10350..10375 ; Lo # [38] OLD PERMIC LETTER AN..OLD PERMIC LETTER IA 10380..1039D ; Lo # [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU @@ -2349,6 +2398,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1133D ; Lo # GRANTHA SIGN AVAGRAHA 11350 ; Lo # GRANTHA OM 1135D..11361 ; Lo # [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; Lo # [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; Lo # [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI 11480..114AF ; Lo # [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; Lo # [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; Lo # TIRHUTA OM @@ -2359,7 +2410,21 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 11680..116AA ; Lo # [43] TAKRI LETTER A..TAKRI LETTER RRA 11700..11719 ; Lo # [26] AHOM LETTER KA..AHOM LETTER JHA 118FF ; Lo # WARANG CITI OM +11A00 ; Lo # ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; Lo # [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; Lo # ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; Lo # SOYOMBO LETTER A +11A5C..11A83 ; Lo # [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; Lo # [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; Lo # [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; Lo # [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; Lo # [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; Lo # BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; Lo # [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; Lo # [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; Lo # [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; Lo # [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; Lo # MASARAM GONDI REPHA 12000..12399 ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12480..12543 ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU 13000..1342E ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 @@ -2372,7 +2437,10 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 16B7D..16B8F ; Lo # [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ 16F00..16F44 ; Lo # [69] MIAO LETTER PA..MIAO LETTER HHA 16F50 ; Lo # MIAO LETTER NASALIZATION -1B000..1B001 ; Lo # [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +17000..187EC ; Lo # [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; Lo # [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; Lo # [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; Lo # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1BC00..1BC6A ; Lo # [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; Lo # [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; Lo # [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -2415,9 +2483,10 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 2A700..2B734 ; Lo # [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 2B740..2B81D ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B820..2CEA1 ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; Lo # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 2F800..2FA1D ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 105697 +# Total code points: 121047 # ================================================ @@ -2446,6 +2515,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0825..0827 ; Mn # [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; Mn # [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; Mn # [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; Mn # [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Mn # [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; Mn # DEVANAGARI VOWEL SIGN OE 093C ; Mn # DEVANAGARI SIGN NUKTA @@ -2472,6 +2542,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0AC7..0AC8 ; Mn # [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; Mn # GUJARATI SIGN VIRAMA 0AE2..0AE3 ; Mn # [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Mn # [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; Mn # ORIYA SIGN CANDRABINDU 0B3C ; Mn # ORIYA SIGN NUKTA 0B3F ; Mn # ORIYA VOWEL SIGN I @@ -2494,7 +2565,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0CC6 ; Mn # KANNADA VOWEL SIGN E 0CCC..0CCD ; Mn # [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; Mn # [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; Mn # MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; Mn # [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; Mn # [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; Mn # [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; Mn # MALAYALAM SIGN VIRAMA 0D62..0D63 ; Mn # [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -2540,6 +2612,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 17C9..17D3 ; Mn # [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Mn # KHMER SIGN ATTHACAN 180B..180D ; Mn # [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; Mn # [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Mn # MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Mn # [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; Mn # [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -2577,8 +2650,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1CED ; Mn # VEDIC SIGN TIRYAK 1CF4 ; Mn # VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; Mn # [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; Mn # [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; Mn # [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; Mn # [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; Mn # [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 20D0..20DC ; Mn # [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20E1 ; Mn # COMBINING LEFT RIGHT ARROW ABOVE 20E5..20F0 ; Mn # [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE @@ -2595,7 +2668,7 @@ A802 ; Mn # SYLOTI NAGRI SIGN DVISVARA A806 ; Mn # SYLOTI NAGRI SIGN HASANTA A80B ; Mn # SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; Mn # [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; Mn # SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; Mn # [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; Mn # [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; Mn # [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; Mn # [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -2647,6 +2720,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1122F..11231 ; Mn # [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; Mn # KHOJKI SIGN ANUSVARA 11236..11237 ; Mn # [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Mn # KHOJKI SIGN SUKUN 112DF ; Mn # KHUDAWADI SIGN ANUSVARA 112E3..112EA ; Mn # [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; Mn # [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -2654,6 +2728,9 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 11340 ; Mn # GRANTHA VOWEL SIGN II 11366..1136C ; Mn # [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; Mn # [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; Mn # [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; Mn # [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; Mn # NEWA SIGN NUKTA 114B3..114B8 ; Mn # [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; Mn # TIRHUTA VOWEL SIGN SHORT E 114BF..114C0 ; Mn # [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA @@ -2672,6 +2749,27 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1171D..1171F ; Mn # [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; Mn # [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; Mn # [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; Mn # [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; Mn # [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Mn # [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; Mn # [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Mn # ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Mn # [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; Mn # [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Mn # [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; Mn # [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; Mn # [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Mn # [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; Mn # BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Mn # [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; Mn # [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; Mn # [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; Mn # [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Mn # [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Mn # MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Mn # [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Mn # [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Mn # MASARAM GONDI RA-KARA 16AF0..16AF4 ; Mn # [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; Mn # [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; Mn # [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -2687,10 +2785,16 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1DA84 ; Mn # SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; Mn # [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; Mn # [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Mn # [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Mn # [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Mn # [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Mn # [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Mn # [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1567 +# Total code points: 1763 # ================================================ @@ -2795,6 +2899,7 @@ A670..A672 ; Me # [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL 1C34..1C35 ; Mc # [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG 1CE1 ; Mc # VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA 1CF2..1CF3 ; Mc # [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF7 ; Mc # VEDIC SIGN ATIKRAMA 302E..302F ; Mc # [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK A823..A824 ; Mc # [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A827 ; Mc # SYLOTI NAGRI VOWEL SIGN OO @@ -2837,6 +2942,9 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 1134B..1134D ; Mc # [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA 11357 ; Mc # GRANTHA AU LENGTH MARK 11362..11363 ; Mc # [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11435..11437 ; Mc # [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11440..11441 ; Mc # [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11445 ; Mc # NEWA SIGN VISARGA 114B0..114B2 ; Mc # [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B9 ; Mc # TIRHUTA VOWEL SIGN E 114BB..114BE ; Mc # [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU @@ -2852,11 +2960,20 @@ ABEC ; Mc # MEETEI MAYEK LUM IYEK 116B6 ; Mc # TAKRI SIGN VIRAMA 11720..11721 ; Mc # [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA 11726 ; Mc # AHOM VOWEL SIGN E +11A07..11A08 ; Mc # [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A39 ; Mc # ZANABAZAR SQUARE SIGN VISARGA +11A57..11A58 ; Mc # [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A97 ; Mc # SOYOMBO SIGN VISARGA +11C2F ; Mc # BHAIKSUKI VOWEL SIGN AA +11C3E ; Mc # BHAIKSUKI SIGN VISARGA +11CA9 ; Mc # MARCHEN SUBJOINED LETTER YA +11CB1 ; Mc # MARCHEN VOWEL SIGN I +11CB4 ; Mc # MARCHEN VOWEL SIGN O 16F51..16F7E ; Mc # [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG 1D165..1D166 ; Mc # [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D16D..1D172 ; Mc # [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 -# Total code points: 383 +# Total code points: 401 # ================================================ @@ -2905,16 +3022,20 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11136..1113F ; Nd # [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; Nd # [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 112F0..112F9 ; Nd # [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Nd # [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; Nd # [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; Nd # [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Nd # [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Nd # [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Nd # [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11C50..11C59 ; Nd # [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Nd # [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Nd # [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Nd # [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Nd # [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 550 +# Total code points: 590 # ================================================ @@ -2946,7 +3067,8 @@ A6E6..A6EF ; Nl # [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM 0B72..0B77 ; No # [6] ORIYA FRACTION ONE QUARTER..ORIYA FRACTION THREE SIXTEENTHS 0BF0..0BF2 ; No # [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND 0C78..0C7E ; No # [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR -0D70..0D75 ; No # [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D58..0D5E ; No # [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH +0D70..0D78 ; No # [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0F2A..0F33 ; No # [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO 1369..137C ; No # [20] ETHIOPIC DIGIT ONE..ETHIOPIC NUMBER TEN THOUSAND 17F0..17F9 ; No # [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON @@ -2993,12 +3115,13 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 111E1..111F4 ; No # [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND 1173A..1173B ; No # [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 118EA..118F2 ; No # [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY +11C5A..11C6C ; No # [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK 16B5B..16B61 ; No # [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 1D360..1D371 ; No # [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE 1E8C7..1E8CF ; No # [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE 1F100..1F10C ; No # [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -# Total code points: 647 +# Total code points: 676 # ================================================ @@ -3048,6 +3171,7 @@ A830..A835 ; No # [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO 061C ; Cf # ARABIC LETTER MARK 06DD ; Cf # ARABIC END OF AYAH 070F ; Cf # SYRIAC ABBREVIATION MARK +08E2 ; Cf # ARABIC DISPUTED END OF AYAH 180E ; Cf # MONGOLIAN VOWEL SEPARATOR 200B..200F ; Cf # [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK 202A..202E ; Cf # [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -3061,7 +3185,7 @@ FFF9..FFFB ; Cf # [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION E0001 ; Cf # LANGUAGE TAG E0020..E007F ; Cf # [96] TAG SPACE..CANCEL TAG -# Total code points: 150 +# Total code points: 151 # ================================================ @@ -3315,6 +3439,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 085E ; Po # MANDAIC PUNCTUATION 0964..0965 ; Po # [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 0970 ; Po # DEVANAGARI ABBREVIATION SIGN +09FD ; Po # BENGALI ABBREVIATION SIGN 0AF0 ; Po # GUJARATI ABBREVIATION SIGN 0DF4 ; Po # SINHALA PUNCTUATION KUNDDALIYA 0E4F ; Po # THAI CHARACTER FONGMAN @@ -3366,6 +3491,7 @@ FF3F ; Pc # FULLWIDTH LOW LINE 2E30..2E39 ; Po # [10] RING POINT..TOP HALF SECTION SIGN 2E3C..2E3F ; Po # [4] STENOGRAPHIC FULL STOP..CAPITULUM 2E41 ; Po # REVERSED COMMA +2E43..2E49 ; Po # [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 3001..3003 ; Po # [3] IDEOGRAPHIC COMMA..DITTO MARK 303D ; Po # PART ALTERNATION MARK 30FB ; Po # KATAKANA MIDDLE DOT @@ -3429,10 +3555,19 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 111DD..111DF ; Po # [3] SHARADA CONTINUATION SIGN..SHARADA SECTION MARK-2 11238..1123D ; Po # [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN 112A9 ; Po # MULTANI SECTION MARK +1144B..1144F ; Po # [5] NEWA DANDA..NEWA ABBREVIATION SIGN +1145B ; Po # NEWA PLACEHOLDER MARK +1145D ; Po # NEWA INSERTION SIGN 114C6 ; Po # TIRHUTA ABBREVIATION SIGN 115C1..115D7 ; Po # [23] SIDDHAM SIGN SIDDHAM..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11643 ; Po # [3] MODI DANDA..MODI ABBREVIATION SIGN +11660..1166C ; Po # [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 1173C..1173E ; Po # [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A3F..11A46 ; Po # [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A9A..11A9C ; Po # [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11A9E..11AA2 ; Po # [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2 +11C41..11C45 ; Po # [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 +11C70..11C71 ; Po # [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD 12470..12474 ; Po # [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 16A6E..16A6F ; Po # [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; Po # BASSA VAH FULL STOP @@ -3440,8 +3575,9 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 16B44 ; Po # PAHAWH HMONG SIGN XAUS 1BC9F ; Po # DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 513 +# Total code points: 566 # ================================================ @@ -3528,7 +3664,7 @@ FFE9..FFEC ; Sm # [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW 0BF9 ; Sc # TAMIL RUPEE SIGN 0E3F ; Sc # THAI CURRENCY SYMBOL BAHT 17DB ; Sc # KHMER CURRENCY SYMBOL RIEL -20A0..20BE ; Sc # [31] EURO-CURRENCY SIGN..LARI SIGN +20A0..20BF ; Sc # [32] EURO-CURRENCY SIGN..BITCOIN SIGN A838 ; Sc # NORTH INDIC RUPEE MARK FDFC ; Sc # RIAL SIGN FE69 ; Sc # SMALL DOLLAR SIGN @@ -3536,7 +3672,7 @@ FF04 ; Sc # FULLWIDTH DOLLAR SIGN FFE0..FFE1 ; Sc # [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN FFE5..FFE6 ; Sc # [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN -# Total code points: 53 +# Total code points: 54 # ================================================ @@ -3594,6 +3730,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 0BF3..0BF8 ; So # [6] TAMIL DAY SIGN..TAMIL AS ABOVE SIGN 0BFA ; So # TAMIL NUMBER SIGN 0C7F ; So # TELUGU SIGN TUUMU +0D4F ; So # MALAYALAM SIGN PARA 0D79 ; So # MALAYALAM DATE MARK 0F01..0F03 ; So # [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA 0F13 ; So # TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN @@ -3642,8 +3779,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 232B..237B ; So # [81] ERASE TO THE LEFT..NOT CHECK MARK 237D..239A ; So # [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL 23B4..23DB ; So # [40] TOP SQUARE BRACKET..FUSE -23E2..23FA ; So # [25] WHITE TRAPEZIUM..BLACK CIRCLE FOR RECORD -2400..2426 ; So # [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23E2..2426 ; So # [69] WHITE TRAPEZIUM..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; So # [11] OCR HOOK..OCR DOUBLE BACKSLASH 249C..24E9 ; So # [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z 2500..25B6 ; So # [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE @@ -3659,7 +3795,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 2B76..2B95 ; So # [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; So # [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; So # [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; So # [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; So # [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; So # [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2CE5..2CEA ; So # [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP @@ -3694,7 +3830,7 @@ FFED..FFEE ; So # [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10137..1013F ; So # [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT 10179..10189 ; So # [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN -1018C ; So # GREEK SINUSOID SIGN +1018C..1018E ; So # [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B ; So # [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0 ; So # GREEK SYMBOL TAU RHO 101D0..101FC ; So # [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -3727,17 +3863,16 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F0D1..1F0F5 ; So # [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 1F110..1F12E ; So # [31] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED WZ 1F130..1F16B ; So # [60] SQUARED LATIN CAPITAL LETTER A..RAISED MD SIGN -1F170..1F19A ; So # [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; So # [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD 1F1E6..1F202 ; So # [29] REGIONAL INDICATOR SYMBOL LETTER A..SQUARED KATAKANA SA -1F210..1F23A ; So # [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F210..1F23B ; So # [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D 1F240..1F248 ; So # [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 1F250..1F251 ; So # [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT +1F260..1F265 ; So # [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI 1F300..1F3FA ; So # [251] CYCLONE..AMPHORA -1F400..1F579 ; So # [378] RAT..JOYSTICK -1F57B..1F5A3 ; So # [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F6D0 ; So # [300] DESKTOP COMPUTER..PLACE OF WORSHIP +1F400..1F6D4 ; So # [725] RAT..PAGODA 1F6E0..1F6EC ; So # [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; So # [4] SATELLITE..PASSENGER SHIP +1F6F0..1F6F8 ; So # [9] SATELLITE..FLYING SAUCER 1F700..1F773 ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE 1F780..1F7D4 ; So # [85] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..HEAVY TWELVE POINTED PINWHEEL STAR 1F800..1F80B ; So # [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD @@ -3745,11 +3880,15 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1F850..1F859 ; So # [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; So # [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; So # [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS -1F910..1F918 ; So # [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; So # [5] CRAB..UNICORN FACE +1F900..1F90B ; So # [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT +1F910..1F93E ; So # [47] ZIPPER-MOUTH FACE..HANDBALL +1F940..1F94C ; So # [13] WILTED FLOWER..CURLING STONE +1F950..1F96B ; So # [28] CROISSANT..CANNED FOOD +1F980..1F997 ; So # [24] CRAB..CRICKET 1F9C0 ; So # CHEESE WEDGE +1F9D0..1F9E6 ; So # [23] FACE WITH MONOCLE..SOCKS -# Total code points: 5677 +# Total code points: 5855 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DJoinGroup.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DJoinGroup.txt index 4fe657efb31..d1318f75fce 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DJoinGroup.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DJoinGroup.txt @@ -1,10 +1,11 @@ -# DerivedJoiningGroup-8.0.0.txt -# Date: 2015-02-13, 13:47:12 GMT [MD] +# DerivedJoiningGroup-10.0.0.txt +# Date: 2017-02-17, 04:46:04 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -50,8 +51,9 @@ 0679..0680 ; Beh # Lo [8] ARABIC LETTER TTEH..ARABIC LETTER BEHEH 0750..0756 ; Beh # Lo [7] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER BEH WITH SMALL V 08A0..08A1 ; Beh # Lo [2] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER BEH WITH HAMZA ABOVE +08B6..08B8 ; Beh # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE -# Total code points: 21 +# Total code points: 24 # ================================================ @@ -256,8 +258,9 @@ 0771 ; Reh # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS 08AA ; Reh # Lo ARABIC LETTER REH WITH LOOP 08B2 ; Reh # Lo ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; Reh # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE -# Total code points: 18 +# Total code points: 19 # ================================================ @@ -365,8 +368,9 @@ 06D0..06D1 ; Yeh # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW 0777 ; Yeh # Lo ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW 08A8..08A9 ; Yeh # Lo [2] ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08BA ; Yeh # Lo ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE -# Total code points: 10 +# Total code points: 11 # ================================================ @@ -611,4 +615,88 @@ # Total code points: 2 +# ================================================ + +08BB ; African_Feh # Lo ARABIC LETTER AFRICAN FEH + +# Total code points: 1 + +# ================================================ + +08BC ; African_Qaf # Lo ARABIC LETTER AFRICAN QAF + +# Total code points: 1 + +# ================================================ + +08BD ; African_Noon # Lo ARABIC LETTER AFRICAN NOON + +# Total code points: 1 + +# ================================================ + +0860 ; Malayalam_Nga # Lo SYRIAC LETTER MALAYALAM NGA + +# Total code points: 1 + +# ================================================ + +0861 ; Malayalam_Ja # Lo SYRIAC LETTER MALAYALAM JA + +# Total code points: 1 + +# ================================================ + +0862 ; Malayalam_Nya # Lo SYRIAC LETTER MALAYALAM NYA + +# Total code points: 1 + +# ================================================ + +0863 ; Malayalam_Tta # Lo SYRIAC LETTER MALAYALAM TTA + +# Total code points: 1 + +# ================================================ + +0864 ; Malayalam_Nna # Lo SYRIAC LETTER MALAYALAM NNA + +# Total code points: 1 + +# ================================================ + +0865 ; Malayalam_Nnna # Lo SYRIAC LETTER MALAYALAM NNNA + +# Total code points: 1 + +# ================================================ + +0866 ; Malayalam_Bha # Lo SYRIAC LETTER MALAYALAM BHA + +# Total code points: 1 + +# ================================================ + +0867 ; Malayalam_Ra # Lo SYRIAC LETTER MALAYALAM RA + +# Total code points: 1 + +# ================================================ + +0868 ; Malayalam_Lla # Lo SYRIAC LETTER MALAYALAM LLA + +# Total code points: 1 + +# ================================================ + +0869 ; Malayalam_Llla # Lo SYRIAC LETTER MALAYALAM LLLA + +# Total code points: 1 + +# ================================================ + +086A ; Malayalam_Ssa # Lo SYRIAC LETTER MALAYALAM SSA + +# Total code points: 1 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DJoinType.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DJoinType.txt index 3261fe00599..ea351f5eff5 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DJoinType.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DJoinType.txt @@ -1,10 +1,11 @@ -# DerivedJoiningType-8.0.0.txt -# Date: 2015-02-13, 13:47:12 GMT [MD] +# DerivedJoiningType-10.0.0.txt +# Date: 2017-03-08, 08:41:50 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -63,9 +64,14 @@ 0848 ; D # Lo MANDAIC LETTER ATT 084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR 0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA 08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE 08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE 08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON 1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER 1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN @@ -85,8 +91,9 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH 10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN 10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 426 +# Total code points: 507 # ================================================ @@ -124,9 +131,12 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT 0849 ; R # Lo MANDAIC LETTER AKSA 0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA 08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH 08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW 08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE 10AC5 ; R # Lo MANICHAEAN LETTER DALETH 10AC7 ; R # Lo MANICHAEAN LETTER WAW 10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN @@ -143,7 +153,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW 10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR -# Total code points: 111 +# Total code points: 115 # ================================================ @@ -186,6 +196,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; T # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 093A ; T # Mn DEVANAGARI VOWEL SIGN OE 093C ; T # Mn DEVANAGARI SIGN NUKTA @@ -212,6 +223,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI 0ACD ; T # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; T # Mn ORIYA SIGN CANDRABINDU 0B3C ; T # Mn ORIYA SIGN NUKTA 0B3F ; T # Mn ORIYA VOWEL SIGN I @@ -234,7 +246,8 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0CC6 ; T # Mn KANNADA VOWEL SIGN E 0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; T # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D4D ; T # Mn MALAYALAM SIGN VIRAMA 0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL @@ -280,6 +293,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; T # Mn KHMER SIGN ATTHACAN 180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O @@ -318,8 +332,8 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1CED ; T # Mn VEDIC SIGN TIRYAK 1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE 1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; T # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200B ; T # Cf ZERO WIDTH SPACE 200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE @@ -344,7 +358,7 @@ A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E -A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -399,6 +413,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI 11234 ; T # Mn KHOJKI SIGN ANUSVARA 11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN 112DF ; T # Mn KHUDAWADI SIGN ANUSVARA 112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA 11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU @@ -406,6 +421,9 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 11340 ; T # Mn GRANTHA VOWEL SIGN II 11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA 114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E 114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA @@ -424,6 +442,27 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA 11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU 11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; T # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; T # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW @@ -441,11 +480,17 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1716 +# Total code points: 1912 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DLineBreak.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DLineBreak.txt index bbdbac17ba0..aff9e19c0a7 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DLineBreak.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DLineBreak.txt @@ -1,10 +1,11 @@ -# DerivedLineBreak-8.0.0.txt -# Date: 2015-02-14, 10:26:02 GMT [MD] +# DerivedLineBreak-10.0.0.txt +# Date: 2017-03-08, 08:41:50 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -23,8 +24,8 @@ E000..F8FF ; XX # Co [6400] <private-use-E000>..<private-use-F8FF> F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; XX # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 776068 code points not listed here. -# Total code points: 913536 +# The above property value applies to 765432 code points not listed here. +# Total code points: 902900 # ================================================ @@ -113,8 +114,9 @@ FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET 13288 ; OP # Lo EGYPTIAN HIEROGLYPH O036C 13379 ; OP # Lo EGYPTIAN HIEROGLYPH V011A 145CE ; OP # Lo ANATOLIAN HIEROGLYPH A410 BEGIN LOGOGRAM MARK +1E95E..1E95F ; OP # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 85 +# Total code points: 87 # ================================================ @@ -281,9 +283,10 @@ FE54..FE55 ; NS # Po [2] SMALL SEMICOLON..SMALL COLON FF1A..FF1B ; NS # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON FF65 ; NS # Po HALFWIDTH KATAKANA MIDDLE DOT FF9E..FF9F ; NS # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +16FE0..16FE1 ; NS # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 1F679..1F67B ; NS # So [3] HEAVY INTERROBANG ORNAMENT..HEAVY SANS-SERIF INTERROBANG ORNAMENT -# Total code points: 29 +# Total code points: 31 # ================================================ @@ -312,8 +315,9 @@ FE56..FE57 ; EX # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK FF01 ; EX # Po FULLWIDTH EXCLAMATION MARK FF1F ; EX # Po FULLWIDTH QUESTION MARK 115C4..115C5 ; EX # Po [2] SIDDHAM SEPARATOR DOT..SIDDHAM SEPARATOR BAR +11C71 ; EX # Po MARCHEN MARK SHAD -# Total code points: 36 +# Total code points: 37 # ================================================ @@ -359,7 +363,8 @@ FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION 20A8..20B5 ; PR # Sc [14] RUPEE SIGN..CEDI SIGN 20B7..20BA ; PR # Sc [4] SPESMILO SIGN..TURKISH LIRA SIGN 20BC..20BD ; PR # Sc [2] MANAT SIGN..RUBLE SIGN -20BF..20CF ; PR # Cn [17] <reserved-20BF>..<reserved-20CF> +20BF ; PR # Sc BITCOIN SIGN +20C0..20CF ; PR # Cn [16] <reserved-20C0>..<reserved-20CF> 2116 ; PR # So NUMERO SIGN 2212..2213 ; PR # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN FE69 ; PR # Sc SMALL DOLLAR SIGN @@ -444,16 +449,20 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 11136..1113F ; NU # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; NU # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 112F0..112F9 ; NU # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; NU # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; NU # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; NU # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; NU # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; NU # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; NU # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11C50..11C59 ; NU # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; NU # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; NU # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; NU # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 542 +# Total code points: 582 # ================================================ @@ -561,7 +570,10 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0830..083E ; AL # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0840..0858 ; AL # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 085E ; AL # Po MANDAIC PUNCTUATION +0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 08A0..08B4 ; AL # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08BD ; AL # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +08E2 ; AL # Cf ARABIC DISPUTED END OF AYAH 0904..0939 ; AL # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; AL # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; AL # Lo DEVANAGARI OM @@ -582,6 +594,8 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 09F0..09F1 ; AL # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09F4..09F8 ; AL # No [5] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR 09FA ; AL # So BENGALI ISSHAR +09FC ; AL # Lo BENGALI LETTER VEDIC ANUSVARA +09FD ; AL # Po BENGALI ABBREVIATION SIGN 0A05..0A0A ; AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; AL # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; AL # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -638,6 +652,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0C60..0C61 ; AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C78..0C7E ; AL # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; AL # So TELUGU SIGN TUUMU +0C80 ; AL # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; AL # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L 0C8E..0C90 ; AL # Lo [3] KANNADA LETTER E..KANNADA LETTER AI 0C92..0CA8 ; AL # Lo [23] KANNADA LETTER O..KANNADA LETTER NA @@ -652,8 +667,11 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0D12..0D3A ; AL # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; AL # Lo MALAYALAM SIGN AVAGRAHA 0D4E ; AL # Lo MALAYALAM LETTER DOT REPH +0D4F ; AL # So MALAYALAM SIGN PARA +0D54..0D56 ; AL # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL +0D58..0D5E ; AL # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH 0D5F..0D61 ; AL # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL -0D70..0D75 ; AL # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D70..0D78 ; AL # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0D7A..0D7F ; AL # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K 0D85..0D96 ; AL # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA 0D9A..0DB1 ; AL # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA @@ -730,7 +748,8 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1820..1842 ; AL # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI 1843 ; AL # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 1844..1877 ; AL # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; AL # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +1880..1884 ; AL # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; AL # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; AL # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA 18B0..18F5 ; AL # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191E ; AL # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA @@ -751,6 +770,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1C4D..1C4F ; AL # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; AL # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; AL # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C80..1C88 ; AL # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK 1CC0..1CC7 ; AL # Po [8] SUNDANESE PUNCTUATION BINDU SURYA..SUNDANESE PUNCTUATION BINDU BA SATANGA 1CD3 ; AL # Po VEDIC SIGN NIHSHVASA 1CE9..1CEC ; AL # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL @@ -910,8 +930,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 23B4..23DB ; AL # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET 23E2..23EF ; AL # So [14] WHITE TRAPEZIUM..BLACK RIGHT-POINTING TRIANGLE WITH DOUBLE VERTICAL BAR -23F4..23FA ; AL # So [7] BLACK MEDIUM LEFT-POINTING TRIANGLE..BLACK CIRCLE FOR RECORD -2400..2426 ; AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +23F4..2426 ; AL # So [51] BLACK MEDIUM LEFT-POINTING TRIANGLE..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24FF ; AL # No NEGATIVE CIRCLED DIGIT ZERO 254C..254F ; AL # So [4] BOX DRAWINGS LIGHT DOUBLE DASH HORIZONTAL..BOX DRAWINGS HEAVY DOUBLE DASH VERTICAL @@ -953,7 +972,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 270E..2756 ; AL # So [73] LOWER RIGHT PENCIL..BLACK DIAMOND MINUS WHITE X 2758..275A ; AL # So [3] LIGHT VERTICAL BAR..HEAVY VERTICAL BAR 2761 ; AL # So CURVED STEM PARAGRAPH SIGN ORNAMENT -2764..2767 ; AL # So [4] HEAVY BLACK HEART..ROTATED FLORAL HEART BULLET +2765..2767 ; AL # So [3] ROTATED HEAVY BLACK HEART BULLET..ROTATED FLORAL HEART BULLET 2794..27BF ; AL # So [44] HEAVY WIDE-HEADED RIGHTWARDS ARROW..DOUBLE CURLY LOOP 27C0..27C4 ; AL # Sm [5] THREE DIMENSIONAL ANGLE..OPEN SUPERSET 27C7..27E5 ; AL # Sm [31] OR WITH DOT INSIDE..WHITE SQUARE WITH RIGHTWARDS TICK @@ -972,7 +991,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 2B76..2B95 ; AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW 2B98..2BB9 ; AL # So [34] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..UP ARROWHEAD IN A RECTANGLE BOX 2BBD..2BC8 ; AL # So [12] BALLOT BOX WITH LIGHT X..BLACK MEDIUM RIGHT-POINTING TRIANGLE CENTRED -2BCA..2BD1 ; AL # So [8] TOP HALF BLACK CIRCLE..UNCERTAINTY SIGN +2BCA..2BD2 ; AL # So [9] TOP HALF BLACK CIRCLE..GROUP MARK 2BEC..2BEF ; AL # So [4] LEFTWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS..DOWNWARDS TWO-HEADED ARROW WITH TRIANGLE ARROWHEADS 2C00..2C2E ; AL # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; AL # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE @@ -1032,7 +1051,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7AD ; AL # L& [30] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER L WITH BELT +A790..A7AE ; AL # L& [31] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER SMALL CAPITAL I A7B0..A7B7 ; AL # L& [8] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER OMEGA A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1089,13 +1108,6 @@ FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN IS FDFD ; AL # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM -FF66 ; AL # Lo HALFWIDTH KATAKANA LETTER WO -FF71..FF9D ; AL # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N -FFA0..FFBE ; AL # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH -FFC2..FFC7 ; AL # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E -FFCA..FFCF ; AL # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE -FFD2..FFD7 ; AL # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU -FFDA..FFDC ; AL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I FFE8 ; AL # So HALFWIDTH FORMS LIGHT VERTICAL FFE9..FFEC ; AL # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE @@ -1112,7 +1124,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10175..10178 ; AL # No [4] GREEK ONE HALF SIGN..GREEK THREE QUARTERS SIGN 10179..10189 ; AL # So [17] GREEK YEAR SIGN..GREEK TRYBLION BASE SIGN 1018A..1018B ; AL # No [2] GREEK ZERO SIGN..GREEK ONE QUARTER SIGN -1018C ; AL # So GREEK SINUSOID SIGN +1018C..1018E ; AL # So [3] GREEK SINUSOID SIGN..NOMISMA SIGN 10190..1019B ; AL # So [12] ROMAN SEXTANS SIGN..ROMAN CENTURIAL SIGN 101A0 ; AL # So GREEK SYMBOL TAU RHO 101D0..101FC ; AL # So [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND @@ -1121,7 +1133,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 102E1..102FB ; AL # No [27] COPTIC EPACT DIGIT ONE..COPTIC EPACT NUMBER NINE HUNDRED 10300..1031F ; AL # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS 10320..10323 ; AL # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -10330..10340 ; AL # Lo [17] GOTHIC LETTER AHSA..GOTHIC LETTER PAIRTHRA +1032D..10340 ; AL # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA 10341 ; AL # Nl GOTHIC LETTER NINETY 10342..10349 ; AL # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL 1034A ; AL # Nl GOTHIC LETTER NINE HUNDRED @@ -1132,6 +1144,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 103D1..103D5 ; AL # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED 10400..1044F ; AL # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW 10450..1049D ; AL # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +104B0..104D3 ; AL # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +104D8..104FB ; AL # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; AL # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; AL # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW 1056F ; AL # Po CAUCASIAN ALBANIAN CITATION MARK @@ -1228,6 +1242,10 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1133D ; AL # Lo GRANTHA SIGN AVAGRAHA 11350 ; AL # Lo GRANTHA OM 1135D..11361 ; AL # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; AL # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; AL # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1144F ; AL # Po NEWA ABBREVIATION SIGN +1145D ; AL # Po NEWA INSERTION SIGN 11480..114AF ; AL # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; AL # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C6 ; AL # Po TIRHUTA ABBREVIATION SIGN @@ -1242,7 +1260,24 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 118A0..118DF ; AL # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO 118EA..118F2 ; AL # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY 118FF ; AL # Lo WARANG CITI OM +11A00 ; AL # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; AL # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; AL # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A40 ; AL # Po ZANABAZAR SQUARE CLOSING HEAD MARK +11A46 ; AL # Po ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK +11A50 ; AL # Lo SOYOMBO LETTER A +11A5C..11A83 ; AL # Lo [40] SOYOMBO LETTER KA..SOYOMBO LETTER KSSA +11A86..11A89 ; AL # Lo [4] SOYOMBO CLUSTER-INITIAL LETTER RA..SOYOMBO CLUSTER-INITIAL LETTER SA 11AC0..11AF8 ; AL # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; AL # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; AL # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; AL # Lo BHAIKSUKI SIGN AVAGRAHA +11C5A..11C6C ; AL # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK +11C72..11C8F ; AL # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; AL # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; AL # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; AL # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; AL # Lo MASARAM GONDI REPHA 12000..12399 ; AL # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; AL # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; AL # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU @@ -1331,6 +1366,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1DA8B ; AL # Po SIGNWRITING PARENTHESIS 1E800..1E8C4 ; AL # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E8C7..1E8CF ; AL # No [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE +1E900..1E943 ; AL # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1EE00..1EE03 ; AL # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; AL # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; AL # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -1370,7 +1406,6 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F39C..1F39D ; AL # So [2] BEAMED ASCENDING MUSICAL NOTES..BEAMED DESCENDING MUSICAL NOTES 1F3B5..1F3B6 ; AL # So [2] MUSICAL NOTE..MULTIPLE MUSICAL NOTES 1F3BC ; AL # So MUSICAL SCORE -1F3FB..1F3FF ; AL # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 1F4A0 ; AL # So DIAMOND SHAPE WITH A DOT INSIDE 1F4A2 ; AL # So ANGER SYMBOL 1F4A4 ; AL # So SLEEPING SYMBOL @@ -1390,8 +1425,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1F850..1F859 ; AL # So [10] LEFTWARDS SANS-SERIF ARROW..UP DOWN SANS-SERIF ARROW 1F860..1F887 ; AL # So [40] WIDE-HEADED LEFTWARDS LIGHT BARB ARROW..WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW 1F890..1F8AD ; AL # So [30] LEFTWARDS TRIANGLE ARROWHEAD..WHITE ARROW SHAFT WIDTH TWO THIRDS +1F900..1F90B ; AL # So [12] CIRCLED CROSS FORMEE WITH FOUR DOTS..DOWNWARD FACING NOTCHED HOOK WITH DOT -# Total code points: 19294 +# Total code points: 19690 # ================================================ @@ -1402,7 +1438,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 2600..2603 ; ID # So [4] BLACK SUN WITH RAYS..SNOWMAN 2614..2615 ; ID # So [2] UMBRELLA WITH RAIN DROPS..HOT BEVERAGE 2618 ; ID # So SHAMROCK -261A..261F ; ID # So [6] BLACK LEFT POINTING INDEX..WHITE DOWN POINTING INDEX +261A..261C ; ID # So [3] BLACK LEFT POINTING INDEX..WHITE LEFT POINTING INDEX +261E..261F ; ID # So [2] WHITE RIGHT POINTING INDEX..WHITE DOWN POINTING INDEX 2639..263B ; ID # So [3] WHITE FROWNING FACE..BLACK SMILING FACE 2668 ; ID # So HOT SPRINGS 267F ; ID # So WHEELCHAIR SYMBOL @@ -1415,9 +1452,11 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 26DF..26E1 ; ID # So [3] BLACK TRUCK..RESTRICTED LEFT ENTRY-2 26EA ; ID # So CHURCH 26F1..26F5 ; ID # So [5] UMBRELLA ON GROUND..SAILBOAT -26F7..26FA ; ID # So [4] SKIER..TENT +26F7..26F8 ; ID # So [2] SKIER..ICE SKATE +26FA ; ID # So TENT 26FD..2704 ; ID # So [8] FUEL PUMP..WHITE SCISSORS -2708..270D ; ID # So [6] AIRPLANE..WRITING HAND +2708..2709 ; ID # So [2] AIRPLANE..ENVELOPE +2764 ; ID # So HEAVY BLACK HEART 2E80..2E99 ; ID # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP 2E9B..2EF3 ; ID # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE 2F00..2FD5 ; ID # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE @@ -1458,7 +1497,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 30EF..30F4 ; ID # Lo [6] KATAKANA LETTER WA..KATAKANA LETTER VU 30F7..30FA ; ID # Lo [4] KATAKANA LETTER VA..KATAKANA LETTER VO 30FF ; ID # Lo KATAKANA DIGRAPH KOTO -3105..312D ; ID # Lo [41] BOPOMOFO LETTER B..BOPOMOFO LETTER IH +3105..312E ; ID # Lo [42] BOPOMOFO LETTER B..BOPOMOFO LETTER O WITH DOT ABOVE 3131..318E ; ID # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE 3190..3191 ; ID # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK 3192..3195 ; ID # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK @@ -1478,8 +1517,8 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 3300..33FF ; ID # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF ; ID # Cn [10] <reserved-4DB6>..<reserved-4DBF> -4E00..9FD5 ; ID # Lo [20950] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FD5 -9FD6..9FFF ; ID # Cn [42] <reserved-9FD6>..<reserved-9FFF> +4E00..9FEA ; ID # Lo [20971] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FEA +9FEB..9FFF ; ID # Cn [21] <reserved-9FEB>..<reserved-9FFF> A000..A014 ; ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A016..A48C ; ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; ID # So [55] YI RADICAL QOT..YI RADICAL KE @@ -1518,43 +1557,114 @@ FF40 ; ID # Sk FULLWIDTH GRAVE ACCENT FF41..FF5A ; ID # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z FF5C ; ID # Sm FULLWIDTH VERTICAL LINE FF5E ; ID # Sm FULLWIDTH TILDE +FF66 ; ID # Lo HALFWIDTH KATAKANA LETTER WO +FF71..FF9D ; ID # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +FFA0..FFBE ; ID # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7 ; ID # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF ; ID # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7 ; ID # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC ; ID # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I FFE2 ; ID # Sm FULLWIDTH NOT SIGN FFE3 ; ID # Sk FULLWIDTH MACRON FFE4 ; ID # So FULLWIDTH BROKEN BAR -1B000..1B001 ; ID # Lo [2] KATAKANA LETTER ARCHAIC E..HIRAGANA LETTER ARCHAIC YE +17000..187EC ; ID # Lo [6125] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187EC +18800..18AF2 ; ID # Lo [755] TANGUT COMPONENT-001..TANGUT COMPONENT-755 +1B000..1B11E ; ID # Lo [287] KATAKANA LETTER ARCHAIC E..HENTAIGANA LETTER N-MU-MO-2 +1B170..1B2FB ; ID # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 1F000..1F02B ; ID # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK +1F02C..1F02F ; ID # Cn [4] <reserved-1F02C>..<reserved-1F02F> 1F030..1F093 ; ID # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 +1F094..1F09F ; ID # Cn [12] <reserved-1F094>..<reserved-1F09F> 1F0A0..1F0AE ; ID # So [15] PLAYING CARD BACK..PLAYING CARD KING OF SPADES +1F0AF..1F0B0 ; ID # Cn [2] <reserved-1F0AF>..<reserved-1F0B0> 1F0B1..1F0BF ; ID # So [15] PLAYING CARD ACE OF HEARTS..PLAYING CARD RED JOKER +1F0C0 ; ID # Cn <reserved-1F0C0> 1F0C1..1F0CF ; ID # So [15] PLAYING CARD ACE OF DIAMONDS..PLAYING CARD BLACK JOKER +1F0D0 ; ID # Cn <reserved-1F0D0> 1F0D1..1F0F5 ; ID # So [37] PLAYING CARD ACE OF CLUBS..PLAYING CARD TRUMP-21 +1F0F6..1F0FF ; ID # Cn [10] <reserved-1F0F6>..<reserved-1F0FF> +1F10D..1F10F ; ID # Cn [3] <reserved-1F10D>..<reserved-1F10F> +1F12F ; ID # Cn <reserved-1F12F> +1F16C..1F16F ; ID # Cn [4] <reserved-1F16C>..<reserved-1F16F> +1F1AD..1F1E5 ; ID # Cn [57] <reserved-1F1AD>..<reserved-1F1E5> 1F200..1F202 ; ID # So [3] SQUARE HIRAGANA HOKA..SQUARED KATAKANA SA -1F210..1F23A ; ID # So [43] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-55B6 +1F203..1F20F ; ID # Cn [13] <reserved-1F203>..<reserved-1F20F> +1F210..1F23B ; ID # So [44] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-914D +1F23C..1F23F ; ID # Cn [4] <reserved-1F23C>..<reserved-1F23F> 1F240..1F248 ; ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 +1F249..1F24F ; ID # Cn [7] <reserved-1F249>..<reserved-1F24F> 1F250..1F251 ; ID # So [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT -1F300..1F39B ; ID # So [156] CYCLONE..CONTROL KNOBS +1F252..1F25F ; ID # Cn [14] <reserved-1F252>..<reserved-1F25F> +1F260..1F265 ; ID # So [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI +1F266..1F2FF ; ID # Cn [154] <reserved-1F266>..<reserved-1F2FF> +1F300..1F384 ; ID # So [133] CYCLONE..CHRISTMAS TREE +1F386..1F39B ; ID # So [22] FIREWORKS..CONTROL KNOBS 1F39E..1F3B4 ; ID # So [23] FILM FRAMES..FLOWER PLAYING CARDS 1F3B7..1F3BB ; ID # So [5] SAXOPHONE..VIOLIN -1F3BD..1F3FA ; ID # So [62] RUNNING SHIRT WITH SASH..AMPHORA -1F400..1F49F ; ID # So [160] RAT..HEART DECORATION +1F3BD..1F3C1 ; ID # So [5] RUNNING SHIRT WITH SASH..CHEQUERED FLAG +1F3C5..1F3C6 ; ID # So [2] SPORTS MEDAL..TROPHY +1F3C8..1F3C9 ; ID # So [2] AMERICAN FOOTBALL..RUGBY FOOTBALL +1F3CD..1F3FA ; ID # So [46] RACING MOTORCYCLE..AMPHORA +1F400..1F441 ; ID # So [66] RAT..EYE +1F444..1F445 ; ID # So [2] MOUTH..TONGUE +1F451..1F465 ; ID # So [21] CROWN..BUSTS IN SILHOUETTE +1F46A..1F46D ; ID # So [4] FAMILY..TWO WOMEN HOLDING HANDS +1F46F ; ID # So WOMAN WITH BUNNY EARS +1F479..1F47B ; ID # So [3] JAPANESE OGRE..GHOST +1F47D..1F480 ; ID # So [4] EXTRATERRESTRIAL ALIEN..SKULL +1F484 ; ID # So LIPSTICK +1F488..1F49F ; ID # So [24] BARBER POLE..HEART DECORATION 1F4A1 ; ID # So ELECTRIC LIGHT BULB 1F4A3 ; ID # So BOMB -1F4A5..1F4AE ; ID # So [10] COLLISION SYMBOL..WHITE FLOWER +1F4A5..1F4A9 ; ID # So [5] COLLISION SYMBOL..PILE OF POO +1F4AB..1F4AE ; ID # So [4] DIZZY SYMBOL..WHITE FLOWER 1F4B0 ; ID # So MONEY BAG 1F4B3..1F4FF ; ID # So [77] CREDIT CARD..PRAYER BEADS 1F507..1F516 ; ID # So [16] SPEAKER WITH CANCELLATION STROKE..BOOKMARK 1F525..1F531 ; ID # So [13] FIRE..TRIDENT EMBLEM -1F54A..1F579 ; ID # So [48] DOVE OF PEACE..JOYSTICK -1F57B..1F5A3 ; ID # So [41] LEFT HAND TELEPHONE RECEIVER..BLACK DOWN POINTING BACKHAND INDEX -1F5A5..1F5D3 ; ID # So [47] DESKTOP COMPUTER..SPIRAL CALENDAR PAD +1F54A..1F573 ; ID # So [42] DOVE OF PEACE..HOLE +1F576..1F579 ; ID # So [4] DARK SUNGLASSES..JOYSTICK +1F57B..1F58F ; ID # So [21] LEFT HAND TELEPHONE RECEIVER..TURNED OK HAND SIGN +1F591..1F594 ; ID # So [4] REVERSED RAISED HAND WITH FINGERS SPLAYED..REVERSED VICTORY HAND +1F597..1F5D3 ; ID # So [61] WHITE DOWN POINTING LEFT HAND INDEX..SPIRAL CALENDAR PAD 1F5DC..1F5F3 ; ID # So [24] COMPRESSION..BALLOT BOX WITH BALLOT -1F5FA..1F64F ; ID # So [86] WORLD MAP..PERSON WITH FOLDED HANDS -1F680..1F6D0 ; ID # So [81] ROCKET..PLACE OF WORSHIP +1F5FA..1F644 ; ID # So [75] WORLD MAP..FACE WITH ROLLING EYES +1F648..1F64A ; ID # So [3] SEE-NO-EVIL MONKEY..SPEAK-NO-EVIL MONKEY +1F680..1F6A2 ; ID # So [35] ROCKET..SHIP +1F6A4..1F6B3 ; ID # So [16] SPEEDBOAT..NO BICYCLES +1F6B7..1F6BF ; ID # So [9] NO PEDESTRIANS..SHOWER +1F6C1..1F6CB ; ID # So [11] BATHTUB..COUCH AND LAMP +1F6CD..1F6D4 ; ID # So [8] SHOPPING BAGS..PAGODA +1F6D5..1F6DF ; ID # Cn [11] <reserved-1F6D5>..<reserved-1F6DF> 1F6E0..1F6EC ; ID # So [13] HAMMER AND WRENCH..AIRPLANE ARRIVING -1F6F0..1F6F3 ; ID # So [4] SATELLITE..PASSENGER SHIP -1F910..1F918 ; ID # So [9] ZIPPER-MOUTH FACE..SIGN OF THE HORNS -1F980..1F984 ; ID # So [5] CRAB..UNICORN FACE +1F6ED..1F6EF ; ID # Cn [3] <reserved-1F6ED>..<reserved-1F6EF> +1F6F0..1F6F8 ; ID # So [9] SATELLITE..FLYING SAUCER +1F6F9..1F6FF ; ID # Cn [7] <reserved-1F6F9>..<reserved-1F6FF> +1F774..1F77F ; ID # Cn [12] <reserved-1F774>..<reserved-1F77F> +1F7D5..1F7FF ; ID # Cn [43] <reserved-1F7D5>..<reserved-1F7FF> +1F80C..1F80F ; ID # Cn [4] <reserved-1F80C>..<reserved-1F80F> +1F848..1F84F ; ID # Cn [8] <reserved-1F848>..<reserved-1F84F> +1F85A..1F85F ; ID # Cn [6] <reserved-1F85A>..<reserved-1F85F> +1F888..1F88F ; ID # Cn [8] <reserved-1F888>..<reserved-1F88F> +1F8AE..1F8FF ; ID # Cn [82] <reserved-1F8AE>..<reserved-1F8FF> +1F90C..1F90F ; ID # Cn [4] <reserved-1F90C>..<reserved-1F90F> +1F910..1F917 ; ID # So [8] ZIPPER-MOUTH FACE..HUGGING FACE +1F91D ; ID # So HANDSHAKE +1F920..1F925 ; ID # So [6] FACE WITH COWBOY HAT..LYING FACE +1F927..1F92F ; ID # So [9] SNEEZING FACE..SHOCKED FACE WITH EXPLODING HEAD +1F93A..1F93C ; ID # So [3] FENCER..WRESTLERS +1F93F ; ID # Cn <reserved-1F93F> +1F940..1F94C ; ID # So [13] WILTED FLOWER..CURLING STONE +1F94D..1F94F ; ID # Cn [3] <reserved-1F94D>..<reserved-1F94F> +1F950..1F96B ; ID # So [28] CROISSANT..CANNED FOOD +1F96C..1F97F ; ID # Cn [20] <reserved-1F96C>..<reserved-1F97F> +1F980..1F997 ; ID # So [24] CRAB..CRICKET +1F998..1F9BF ; ID # Cn [40] <reserved-1F998>..<reserved-1F9BF> 1F9C0 ; ID # So CHEESE WEDGE +1F9C1..1F9CF ; ID # Cn [15] <reserved-1F9C1>..<reserved-1F9CF> +1F9D0 ; ID # So FACE WITH MONOCLE +1F9DE..1F9E6 ; ID # So [9] GENIE..SOCKS +1F9E7..1FFFD ; ID # Cn [1559] <reserved-1F9E7>..<reserved-1FFFD> 20000..2A6D6 ; ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 2A6D7..2A6FF ; ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> 2A700..2B734 ; ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 @@ -1562,12 +1672,14 @@ FFE4 ; ID # So FULLWIDTH BROKEN BAR 2B740..2B81D ; ID # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D 2B81E..2B81F ; ID # Cn [2] <reserved-2B81E>..<reserved-2B81F> 2B820..2CEA1 ; ID # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 -2CEA2..2F7FF ; ID # Cn [10590] <reserved-2CEA2>..<reserved-2F7FF> +2CEA2..2CEAF ; ID # Cn [14] <reserved-2CEA2>..<reserved-2CEAF> +2CEB0..2EBE0 ; ID # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2EBE1..2F7FF ; ID # Cn [3103] <reserved-2EBE1>..<reserved-2F7FF> 2F800..2FA1D ; ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D 2FA1E..2FFFD ; ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> 30000..3FFFD ; ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 162973 +# Total code points: 172784 # ================================================ @@ -1623,6 +1735,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0825..0827 ; CM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U 0829..082D ; CM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA 0859..085B ; CM # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; CM # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; CM # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA 093A ; CM # Mn DEVANAGARI VOWEL SIGN OE @@ -1665,6 +1778,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0ACB..0ACC ; CM # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU 0ACD ; CM # Mn GUJARATI SIGN VIRAMA 0AE2..0AE3 ; CM # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; CM # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE 0B01 ; CM # Mn ORIYA SIGN CANDRABINDU 0B02..0B03 ; CM # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA 0B3C ; CM # Mn ORIYA SIGN NUKTA @@ -1706,8 +1820,9 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0CCC..0CCD ; CM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; CM # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK 0CE2..0CE3 ; CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL -0D01 ; CM # Mn MALAYALAM SIGN CANDRABINDU +0D00..0D01 ; CM # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; CM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; CM # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA 0D3E..0D40 ; CM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II 0D41..0D44 ; CM # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR 0D46..0D48 ; CM # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI @@ -1739,6 +1854,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1752..1753 ; CM # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; CM # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 180B..180D ; CM # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; CM # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; CM # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; CM # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U 1923..1926 ; CM # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU @@ -1792,10 +1908,12 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1CED ; CM # Mn VEDIC SIGN TIRYAK 1CF2..1CF3 ; CM # Mc [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA 1CF4 ; CM # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; CM # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; CM # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF5 ; CM # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE -1DFC..1DFF ; CM # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW -200C..200F ; CM # Cf [4] ZERO WIDTH NON-JOINER..RIGHT-TO-LEFT MARK +1DC0..1DF9 ; CM # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; CM # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200C ; CM # Cf ZERO WIDTH NON-JOINER +200E..200F ; CM # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK 202A..202E ; CM # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 2066..206F ; CM # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES 20D0..20DC ; CM # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE @@ -1823,7 +1941,7 @@ A825..A826 ; CM # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN A827 ; CM # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; CM # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; CM # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU -A8C4 ; CM # Mn SAURASHTRA SIGN VIRAMA +A8C4..A8C5 ; CM # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU A8E0..A8F1 ; CM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; CM # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; CM # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R @@ -1896,6 +2014,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11234 ; CM # Mn KHOJKI SIGN ANUSVARA 11235 ; CM # Mc KHOJKI SIGN VIRAMA 11236..11237 ; CM # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; CM # Mn KHOJKI SIGN SUKUN 112DF ; CM # Mn KHUDAWADI SIGN ANUSVARA 112E0..112E2 ; CM # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II 112E3..112EA ; CM # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA @@ -1911,6 +2030,12 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 11362..11363 ; CM # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL 11366..1136C ; CM # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX 11370..11374 ; CM # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11435..11437 ; CM # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; CM # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; CM # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; CM # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; CM # Mc NEWA SIGN VISARGA +11446 ; CM # Mn NEWA SIGN NUKTA 114B0..114B2 ; CM # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II 114B3..114B8 ; CM # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL 114B9 ; CM # Mc TIRHUTA VOWEL SIGN E @@ -1939,6 +2064,36 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 116B0..116B5 ; CM # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU 116B6 ; CM # Mc TAKRI SIGN VIRAMA 116B7 ; CM # Mn TAKRI SIGN NUKTA +11A01..11A06 ; CM # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A07..11A08 ; CM # Mc [2] ZANABAZAR SQUARE VOWEL SIGN AI..ZANABAZAR SQUARE VOWEL SIGN AU +11A09..11A0A ; CM # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; CM # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; CM # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; CM # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; CM # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; CM # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; CM # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; CM # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; CM # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; CM # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; CM # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C2F ; CM # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; CM # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; CM # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; CM # Mc BHAIKSUKI SIGN VISARGA +11C3F ; CM # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; CM # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; CM # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; CM # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; CM # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; CM # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; CM # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; CM # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; CM # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; CM # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; CM # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; CM # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; CM # Mn MASARAM GONDI RA-KARA 16AF0..16AF4 ; CM # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE 16B30..16B36 ; CM # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16F51..16F7E ; CM # Mc [46] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN NG @@ -1959,12 +2114,18 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1DA84 ; CM # Mn SIGNWRITING LOCATION HEAD NECK 1DA9B..1DA9F ; CM # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 1DAA1..1DAAF ; CM # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; CM # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; CM # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; CM # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; CM # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA 1E8D0..1E8D6 ; CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1957 +# Total code points: 2170 # ================================================ @@ -1987,8 +2148,13 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 11175 ; BB # Po MAHAJANI SECTION MARK 111DB ; BB # Po SHARADA SIGN SIDDHAM 115C1 ; BB # Po SIDDHAM SIGN SIDDHAM +11660..1166C ; BB # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT +11A3F ; BB # Po ZANABAZAR SQUARE INITIAL HEAD MARK +11A45 ; BB # Po ZANABAZAR SQUARE INITIAL DOUBLE-LINED HEAD MARK +11A9E..11AA0 ; BB # Po [3] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO HEAD MARK WITH MOON AND SUN +11C70 ; BB # Po MARCHEN HEAD MARK -# Total code points: 23 +# Total code points: 42 # ================================================ @@ -2042,6 +2208,7 @@ A8FC ; BB # Po DEVANAGARI SIGN SIDDHAM 2E3C..2E3E ; BA # Po [3] STENOGRAPHIC FULL STOP..WIGGLY VERTICAL LINE 2E40 ; BA # Pd DOUBLE HYPHEN 2E41 ; BA # Po REVERSED COMMA +2E43..2E49 ; BA # Po [7] DASH WITH LEFT UPTURN..DOUBLE STACKED COMMA 3000 ; BA # Zs IDEOGRAPHIC SPACE A4FE..A4FF ; BA # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D ; BA # Po VAI COMMA @@ -2070,10 +2237,16 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 11238..11239 ; BA # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA 1123B..1123C ; BA # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK 112A9 ; BA # Po MULTANI SECTION MARK +1144B..1144E ; BA # Po [4] NEWA DANDA..NEWA GAP FILLER +1145B ; BA # Po NEWA PLACEHOLDER MARK 115C2..115C3 ; BA # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA 115C9..115D7 ; BA # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES 11641..11642 ; BA # Po [2] MODI DANDA..MODI DOUBLE DANDA 1173C..1173E ; BA # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11A41..11A44 ; BA # Po [4] ZANABAZAR SQUARE MARK TSHEG..ZANABAZAR SQUARE MARK LONG TSHEG +11A9A..11A9C ; BA # Po [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD +11AA1..11AA2 ; BA # Po [2] SOYOMBO TERMINAL MARK-1..SOYOMBO TERMINAL MARK-2 +11C41..11C45 ; BA # Po [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2 12470..12474 ; BA # Po [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON 16A6E..16A6F ; BA # Po [2] MRO DANDA..MRO DOUBLE DANDA 16AF5 ; BA # Po BASSA VAH FULL STOP @@ -2082,7 +2255,7 @@ ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 1BC9F ; BA # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8A ; BA # Po [4] SIGNWRITING COMMA..SIGNWRITING COLON -# Total code points: 206 +# Total code points: 232 # ================================================ @@ -2382,9 +2555,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1F100..1F10C ; AI # No [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1F110..1F12D ; AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD 1F130..1F169 ; AI # So [58] SQUARED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z -1F170..1F19A ; AI # So [43] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VS +1F170..1F1AC ; AI # So [61] NEGATIVE SQUARED LATIN CAPITAL LETTER A..SQUARED VOD -# Total code points: 689 +# Total code points: 707 # ================================================ @@ -3334,4 +3507,59 @@ FF70 ; CJ # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK # Total code points: 26 +# ================================================ + +# Line_Break=E_Base + +261D ; EB # So WHITE UP POINTING INDEX +26F9 ; EB # So PERSON WITH BALL +270A..270D ; EB # So [4] RAISED FIST..WRITING HAND +1F385 ; EB # So FATHER CHRISTMAS +1F3C2..1F3C4 ; EB # So [3] SNOWBOARDER..SURFER +1F3C7 ; EB # So HORSE RACING +1F3CA..1F3CC ; EB # So [3] SWIMMER..GOLFER +1F442..1F443 ; EB # So [2] EAR..NOSE +1F446..1F450 ; EB # So [11] WHITE UP POINTING BACKHAND INDEX..OPEN HANDS SIGN +1F466..1F469 ; EB # So [4] BOY..WOMAN +1F46E ; EB # So POLICE OFFICER +1F470..1F478 ; EB # So [9] BRIDE WITH VEIL..PRINCESS +1F47C ; EB # So BABY ANGEL +1F481..1F483 ; EB # So [3] INFORMATION DESK PERSON..DANCER +1F485..1F487 ; EB # So [3] NAIL POLISH..HAIRCUT +1F4AA ; EB # So FLEXED BICEPS +1F574..1F575 ; EB # So [2] MAN IN BUSINESS SUIT LEVITATING..SLEUTH OR SPY +1F57A ; EB # So MAN DANCING +1F590 ; EB # So RAISED HAND WITH FINGERS SPLAYED +1F595..1F596 ; EB # So [2] REVERSED HAND WITH MIDDLE FINGER EXTENDED..RAISED HAND WITH PART BETWEEN MIDDLE AND RING FINGERS +1F645..1F647 ; EB # So [3] FACE WITH NO GOOD GESTURE..PERSON BOWING DEEPLY +1F64B..1F64F ; EB # So [5] HAPPY PERSON RAISING ONE HAND..PERSON WITH FOLDED HANDS +1F6A3 ; EB # So ROWBOAT +1F6B4..1F6B6 ; EB # So [3] BICYCLIST..PEDESTRIAN +1F6C0 ; EB # So BATH +1F6CC ; EB # So SLEEPING ACCOMMODATION +1F918..1F91C ; EB # So [5] SIGN OF THE HORNS..RIGHT-FACING FIST +1F91E..1F91F ; EB # So [2] HAND WITH INDEX AND MIDDLE FINGERS CROSSED..I LOVE YOU HAND SIGN +1F926 ; EB # So FACE PALM +1F930..1F939 ; EB # So [10] PREGNANT WOMAN..JUGGLING +1F93D..1F93E ; EB # So [2] WATER POLO..HANDBALL +1F9D1..1F9DD ; EB # So [13] ADULT..ELF + +# Total code points: 102 + +# ================================================ + +# Line_Break=E_Modifier + +1F3FB..1F3FF ; EM # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 + +# Total code points: 5 + +# ================================================ + +# Line_Break=ZWJ + +200D ; ZWJ # Cf ZERO WIDTH JOINER + +# Total code points: 1 + # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DNumType.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DNumType.txt index c9423020436..42dfba2bd75 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DNumType.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DNumType.txt @@ -1,10 +1,11 @@ -# DerivedNumericType-8.0.0.txt -# Date: 2015-02-13, 13:47:13 GMT [MD] +# DerivedNumericType-10.0.0.txt +# Date: 2017-02-14, 04:26:10 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -30,7 +31,8 @@ 0B72..0B77 ; Numeric # No [6] ORIYA FRACTION ONE QUARTER..ORIYA FRACTION THREE SIXTEENTHS 0BF0..0BF2 ; Numeric # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND 0C78..0C7E ; Numeric # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR -0D70..0D75 ; Numeric # No [6] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE QUARTERS +0D58..0D5E ; Numeric # No [7] MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH..MALAYALAM FRACTION ONE FIFTH +0D70..0D78 ; Numeric # No [9] MALAYALAM NUMBER TEN..MALAYALAM FRACTION THREE SIXTEENTHS 0F2A..0F33 ; Numeric # No [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO 1372..137C ; Numeric # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND 16EE..16F0 ; Numeric # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL @@ -145,6 +147,7 @@ F9FD ; Numeric # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 111E1..111F4 ; Numeric # No [20] SINHALA ARCHAIC DIGIT ONE..SINHALA ARCHAIC NUMBER ONE THOUSAND 1173A..1173B ; Numeric # No [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY 118EA..118F2 ; Numeric # No [9] WARANG CITI NUMBER TEN..WARANG CITI NUMBER NINETY +11C5A..11C6C ; Numeric # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK 12400..1246E ; Numeric # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 16B5B..16B61 ; Numeric # No [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS 1D360..1D371 ; Numeric # No [18] COUNTING ROD UNIT DIGIT ONE..COUNTING ROD TENS DIGIT NINE @@ -167,7 +170,7 @@ F9FD ; Numeric # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 2626D ; Numeric # Lo CJK UNIFIED IDEOGRAPH-2626D 2F890 ; Numeric # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 836 +# Total code points: 865 # ================================================ @@ -239,15 +242,19 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 11136..1113F ; Decimal # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE 111D0..111D9 ; Decimal # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE 112F0..112F9 ; Decimal # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Decimal # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE 114D0..114D9 ; Decimal # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE 11650..11659 ; Decimal # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE 116C0..116C9 ; Decimal # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Decimal # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Decimal # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11C50..11C59 ; Decimal # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Decimal # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 16A60..16A69 ; Decimal # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE 16B50..16B59 ; Decimal # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE 1D7CE..1D7FF ; Decimal # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE -# Total code points: 550 +# Total code points: 590 # EOF diff --git a/gnu/usr.bin/perl/lib/unicore/extracted/DNumValues.txt b/gnu/usr.bin/perl/lib/unicore/extracted/DNumValues.txt index 4c749b2c236..e8fffb3ba9b 100644 --- a/gnu/usr.bin/perl/lib/unicore/extracted/DNumValues.txt +++ b/gnu/usr.bin/perl/lib/unicore/extracted/DNumValues.txt @@ -1,10 +1,11 @@ -# DerivedNumericValues-8.0.0.txt -# Date: 2015-02-13, 13:47:13 GMT [MD] +# DerivedNumericValues-10.0.0.txt +# Date: 2017-02-14, 04:26:10 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database -# Copyright (c) 1991-2015 Unicode, Inc. -# For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -93,11 +94,14 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 11136 ; 0.0 ; ; 0 # Nd CHAKMA DIGIT ZERO 111D0 ; 0.0 ; ; 0 # Nd SHARADA DIGIT ZERO 112F0 ; 0.0 ; ; 0 # Nd KHUDAWADI DIGIT ZERO +11450 ; 0.0 ; ; 0 # Nd NEWA DIGIT ZERO 114D0 ; 0.0 ; ; 0 # Nd TIRHUTA DIGIT ZERO 11650 ; 0.0 ; ; 0 # Nd MODI DIGIT ZERO 116C0 ; 0.0 ; ; 0 # Nd TAKRI DIGIT ZERO 11730 ; 0.0 ; ; 0 # Nd AHOM DIGIT ZERO 118E0 ; 0.0 ; ; 0 # Nd WARANG CITI DIGIT ZERO +11C50 ; 0.0 ; ; 0 # Nd BHAIKSUKI DIGIT ZERO +11D50 ; 0.0 ; ; 0 # Nd MASARAM GONDI DIGIT ZERO 16A60 ; 0.0 ; ; 0 # Nd MRO DIGIT ZERO 16B50 ; 0.0 ; ; 0 # Nd PAHAWH HMONG DIGIT ZERO 1D7CE ; 0.0 ; ; 0 # Nd MATHEMATICAL BOLD DIGIT ZERO @@ -105,18 +109,44 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1D7E2 ; 0.0 ; ; 0 # Nd MATHEMATICAL SANS-SERIF DIGIT ZERO 1D7EC ; 0.0 ; ; 0 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT ZERO 1D7F6 ; 0.0 ; ; 0 # Nd MATHEMATICAL MONOSPACE DIGIT ZERO +1E950 ; 0.0 ; ; 0 # Nd ADLAM DIGIT ZERO 1F100..1F101 ; 0.0 ; ; 0 # No [2] DIGIT ZERO FULL STOP..DIGIT ZERO COMMA 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO -# Total code points: 71 +# Total code points: 75 + +# ================================================ + +0D58 ; 0.00625 ; ; 1/160 # No MALAYALAM FRACTION ONE ONE-HUNDRED-AND-SIXTIETH + +# Total code points: 1 + +# ================================================ + +0D59 ; 0.025 ; ; 1/40 # No MALAYALAM FRACTION ONE FORTIETH + +# Total code points: 1 + +# ================================================ + +0D5A ; 0.0375 ; ; 3/80 # No MALAYALAM FRACTION THREE EIGHTIETHS + +# Total code points: 1 + +# ================================================ + +0D5B ; 0.05 ; ; 1/20 # No MALAYALAM FRACTION ONE TWENTIETH + +# Total code points: 1 # ================================================ 09F4 ; 0.0625 ; ; 1/16 # No BENGALI CURRENCY NUMERATOR ONE 0B75 ; 0.0625 ; ; 1/16 # No ORIYA FRACTION ONE SIXTEENTH +0D76 ; 0.0625 ; ; 1/16 # No MALAYALAM FRACTION ONE SIXTEENTH A833 ; 0.0625 ; ; 1/16 # No NORTH INDIC FRACTION ONE SIXTEENTH -# Total code points: 3 +# Total code points: 4 # ================================================ @@ -126,9 +156,10 @@ A833 ; 0.0625 ; ; 1/16 # No NORTH INDIC FRACTION ONE SIXTEENTH # ================================================ +0D5C ; 0.1 ; ; 1/10 # No MALAYALAM FRACTION ONE TENTH 2152 ; 0.1 ; ; 1/10 # No VULGAR FRACTION ONE TENTH -# Total code points: 1 +# Total code points: 2 # ================================================ @@ -140,11 +171,12 @@ A833 ; 0.0625 ; ; 1/16 # No NORTH INDIC FRACTION ONE SIXTEENTH 09F5 ; 0.125 ; ; 1/8 # No BENGALI CURRENCY NUMERATOR TWO 0B76 ; 0.125 ; ; 1/8 # No ORIYA FRACTION ONE EIGHTH +0D77 ; 0.125 ; ; 1/8 # No MALAYALAM FRACTION ONE EIGHTH 215B ; 0.125 ; ; 1/8 # No VULGAR FRACTION ONE EIGHTH A834 ; 0.125 ; ; 1/8 # No NORTH INDIC FRACTION ONE EIGHTH 1245F ; 0.125 ; ; 1/8 # Nl CUNEIFORM NUMERIC SIGN ONE EIGHTH ASH -# Total code points: 5 +# Total code points: 6 # ================================================ @@ -154,6 +186,12 @@ A834 ; 0.125 ; ; 1/8 # No NORTH INDIC FRACTION ONE EIGHTH # ================================================ +0D5D ; 0.15 ; ; 3/20 # No MALAYALAM FRACTION THREE TWENTIETHS + +# Total code points: 1 + +# ================================================ + 2159 ; 0.16666667 ; ; 1/6 # No VULGAR FRACTION ONE SIXTH 109F7 ; 0.16666667 ; ; 1/6 # No MEROITIC CURSIVE FRACTION TWO TWELFTHS 12461 ; 0.16666667 ; ; 1/6 # Nl CUNEIFORM NUMERIC SIGN OLD ASSYRIAN ONE SIXTH @@ -164,15 +202,17 @@ A834 ; 0.125 ; ; 1/8 # No NORTH INDIC FRACTION ONE EIGHTH 09F6 ; 0.1875 ; ; 3/16 # No BENGALI CURRENCY NUMERATOR THREE 0B77 ; 0.1875 ; ; 3/16 # No ORIYA FRACTION THREE SIXTEENTHS +0D78 ; 0.1875 ; ; 3/16 # No MALAYALAM FRACTION THREE SIXTEENTHS A835 ; 0.1875 ; ; 3/16 # No NORTH INDIC FRACTION THREE SIXTEENTHS -# Total code points: 3 +# Total code points: 4 # ================================================ +0D5E ; 0.2 ; ; 1/5 # No MALAYALAM FRACTION ONE FIFTH 2155 ; 0.2 ; ; 1/5 # No VULGAR FRACTION ONE FIFTH -# Total code points: 1 +# Total code points: 2 # ================================================ @@ -399,11 +439,15 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 111D1 ; 1.0 ; ; 1 # Nd SHARADA DIGIT ONE 111E1 ; 1.0 ; ; 1 # No SINHALA ARCHAIC DIGIT ONE 112F1 ; 1.0 ; ; 1 # Nd KHUDAWADI DIGIT ONE +11451 ; 1.0 ; ; 1 # Nd NEWA DIGIT ONE 114D1 ; 1.0 ; ; 1 # Nd TIRHUTA DIGIT ONE 11651 ; 1.0 ; ; 1 # Nd MODI DIGIT ONE 116C1 ; 1.0 ; ; 1 # Nd TAKRI DIGIT ONE 11731 ; 1.0 ; ; 1 # Nd AHOM DIGIT ONE 118E1 ; 1.0 ; ; 1 # Nd WARANG CITI DIGIT ONE +11C51 ; 1.0 ; ; 1 # Nd BHAIKSUKI DIGIT ONE +11C5A ; 1.0 ; ; 1 # No BHAIKSUKI NUMBER ONE +11D51 ; 1.0 ; ; 1 # Nd MASARAM GONDI DIGIT ONE 12415 ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE GESH2 1241E ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE GESHU 1242C ; 1.0 ; ; 1 # Nl CUNEIFORM NUMERIC SIGN ONE SHARU @@ -419,10 +463,11 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1D7ED ; 1.0 ; ; 1 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT ONE 1D7F7 ; 1.0 ; ; 1 # Nd MATHEMATICAL MONOSPACE DIGIT ONE 1E8C7 ; 1.0 ; ; 1 # No MENDE KIKAKUI DIGIT ONE +1E951 ; 1.0 ; ; 1 # Nd ADLAM DIGIT ONE 1F102 ; 1.0 ; ; 1 # No DIGIT ONE COMMA 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 117 +# Total code points: 122 # ================================================ @@ -520,11 +565,15 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 111D2 ; 2.0 ; ; 2 # Nd SHARADA DIGIT TWO 111E2 ; 2.0 ; ; 2 # No SINHALA ARCHAIC DIGIT TWO 112F2 ; 2.0 ; ; 2 # Nd KHUDAWADI DIGIT TWO +11452 ; 2.0 ; ; 2 # Nd NEWA DIGIT TWO 114D2 ; 2.0 ; ; 2 # Nd TIRHUTA DIGIT TWO 11652 ; 2.0 ; ; 2 # Nd MODI DIGIT TWO 116C2 ; 2.0 ; ; 2 # Nd TAKRI DIGIT TWO 11732 ; 2.0 ; ; 2 # Nd AHOM DIGIT TWO 118E2 ; 2.0 ; ; 2 # Nd WARANG CITI DIGIT TWO +11C52 ; 2.0 ; ; 2 # Nd BHAIKSUKI DIGIT TWO +11C5B ; 2.0 ; ; 2 # No BHAIKSUKI NUMBER TWO +11D52 ; 2.0 ; ; 2 # Nd MASARAM GONDI DIGIT TWO 12400 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO ASH 12416 ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO GESH2 1241F ; 2.0 ; ; 2 # Nl CUNEIFORM NUMERIC SIGN TWO GESHU @@ -544,10 +593,11 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1D7EE ; 2.0 ; ; 2 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT TWO 1D7F8 ; 2.0 ; ; 2 # Nd MATHEMATICAL MONOSPACE DIGIT TWO 1E8C8 ; 2.0 ; ; 2 # No MENDE KIKAKUI DIGIT TWO +1E952 ; 2.0 ; ; 2 # Nd ADLAM DIGIT TWO 1F103 ; 2.0 ; ; 2 # No DIGIT TWO COMMA 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 117 +# Total code points: 122 # ================================================ @@ -639,11 +689,15 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 111D3 ; 3.0 ; ; 3 # Nd SHARADA DIGIT THREE 111E3 ; 3.0 ; ; 3 # No SINHALA ARCHAIC DIGIT THREE 112F3 ; 3.0 ; ; 3 # Nd KHUDAWADI DIGIT THREE +11453 ; 3.0 ; ; 3 # Nd NEWA DIGIT THREE 114D3 ; 3.0 ; ; 3 # Nd TIRHUTA DIGIT THREE 11653 ; 3.0 ; ; 3 # Nd MODI DIGIT THREE 116C3 ; 3.0 ; ; 3 # Nd TAKRI DIGIT THREE 11733 ; 3.0 ; ; 3 # Nd AHOM DIGIT THREE 118E3 ; 3.0 ; ; 3 # Nd WARANG CITI DIGIT THREE +11C53 ; 3.0 ; ; 3 # Nd BHAIKSUKI DIGIT THREE +11C5C ; 3.0 ; ; 3 # No BHAIKSUKI NUMBER THREE +11D53 ; 3.0 ; ; 3 # Nd MASARAM GONDI DIGIT THREE 12401 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE ASH 12408 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE DISH 12417 ; 3.0 ; ; 3 # Nl CUNEIFORM NUMERIC SIGN THREE GESH2 @@ -664,13 +718,14 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 1D7EF ; 3.0 ; ; 3 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT THREE 1D7F9 ; 3.0 ; ; 3 # Nd MATHEMATICAL MONOSPACE DIGIT THREE 1E8C9 ; 3.0 ; ; 3 # No MENDE KIKAKUI DIGIT THREE +1E953 ; 3.0 ; ; 3 # Nd ADLAM DIGIT THREE 1F104 ; 3.0 ; ; 3 # No DIGIT THREE COMMA 20AFD ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-20AFD 20B19 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-20B19 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 119 +# Total code points: 124 # ================================================ @@ -756,11 +811,15 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 111D4 ; 4.0 ; ; 4 # Nd SHARADA DIGIT FOUR 111E4 ; 4.0 ; ; 4 # No SINHALA ARCHAIC DIGIT FOUR 112F4 ; 4.0 ; ; 4 # Nd KHUDAWADI DIGIT FOUR +11454 ; 4.0 ; ; 4 # Nd NEWA DIGIT FOUR 114D4 ; 4.0 ; ; 4 # Nd TIRHUTA DIGIT FOUR 11654 ; 4.0 ; ; 4 # Nd MODI DIGIT FOUR 116C4 ; 4.0 ; ; 4 # Nd TAKRI DIGIT FOUR 11734 ; 4.0 ; ; 4 # Nd AHOM DIGIT FOUR 118E4 ; 4.0 ; ; 4 # Nd WARANG CITI DIGIT FOUR +11C54 ; 4.0 ; ; 4 # Nd BHAIKSUKI DIGIT FOUR +11C5D ; 4.0 ; ; 4 # No BHAIKSUKI NUMBER FOUR +11D54 ; 4.0 ; ; 4 # Nd MASARAM GONDI DIGIT FOUR 12402 ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR ASH 12409 ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR DISH 1240F ; 4.0 ; ; 4 # Nl CUNEIFORM NUMERIC SIGN FOUR U @@ -782,12 +841,13 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 1D7F0 ; 4.0 ; ; 4 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT FOUR 1D7FA ; 4.0 ; ; 4 # Nd MATHEMATICAL MONOSPACE DIGIT FOUR 1E8CA ; 4.0 ; ; 4 # No MENDE KIKAKUI DIGIT FOUR +1E954 ; 4.0 ; ; 4 # Nd ADLAM DIGIT FOUR 1F105 ; 4.0 ; ; 4 # No DIGIT FOUR COMMA 20064 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-20064 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 111 +# Total code points: 116 # ================================================ @@ -878,11 +938,15 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 111D5 ; 5.0 ; ; 5 # Nd SHARADA DIGIT FIVE 111E5 ; 5.0 ; ; 5 # No SINHALA ARCHAIC DIGIT FIVE 112F5 ; 5.0 ; ; 5 # Nd KHUDAWADI DIGIT FIVE +11455 ; 5.0 ; ; 5 # Nd NEWA DIGIT FIVE 114D5 ; 5.0 ; ; 5 # Nd TIRHUTA DIGIT FIVE 11655 ; 5.0 ; ; 5 # Nd MODI DIGIT FIVE 116C5 ; 5.0 ; ; 5 # Nd TAKRI DIGIT FIVE 11735 ; 5.0 ; ; 5 # Nd AHOM DIGIT FIVE 118E5 ; 5.0 ; ; 5 # Nd WARANG CITI DIGIT FIVE +11C55 ; 5.0 ; ; 5 # Nd BHAIKSUKI DIGIT FIVE +11C5E ; 5.0 ; ; 5 # No BHAIKSUKI NUMBER FIVE +11D55 ; 5.0 ; ; 5 # Nd MASARAM GONDI DIGIT FIVE 12403 ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE ASH 1240A ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE DISH 12410 ; 5.0 ; ; 5 # Nl CUNEIFORM NUMERIC SIGN FIVE U @@ -903,10 +967,11 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1D7F1 ; 5.0 ; ; 5 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT FIVE 1D7FB ; 5.0 ; ; 5 # Nd MATHEMATICAL MONOSPACE DIGIT FIVE 1E8CB ; 5.0 ; ; 5 # No MENDE KIKAKUI DIGIT FIVE +1E955 ; 5.0 ; ; 5 # Nd ADLAM DIGIT FIVE 1F106 ; 5.0 ; ; 5 # No DIGIT FIVE COMMA 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 109 +# Total code points: 114 # ================================================ @@ -988,11 +1053,15 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 111D6 ; 6.0 ; ; 6 # Nd SHARADA DIGIT SIX 111E6 ; 6.0 ; ; 6 # No SINHALA ARCHAIC DIGIT SIX 112F6 ; 6.0 ; ; 6 # Nd KHUDAWADI DIGIT SIX +11456 ; 6.0 ; ; 6 # Nd NEWA DIGIT SIX 114D6 ; 6.0 ; ; 6 # Nd TIRHUTA DIGIT SIX 11656 ; 6.0 ; ; 6 # Nd MODI DIGIT SIX 116C6 ; 6.0 ; ; 6 # Nd TAKRI DIGIT SIX 11736 ; 6.0 ; ; 6 # Nd AHOM DIGIT SIX 118E6 ; 6.0 ; ; 6 # Nd WARANG CITI DIGIT SIX +11C56 ; 6.0 ; ; 6 # Nd BHAIKSUKI DIGIT SIX +11C5F ; 6.0 ; ; 6 # No BHAIKSUKI NUMBER SIX +11D56 ; 6.0 ; ; 6 # Nd MASARAM GONDI DIGIT SIX 12404 ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX ASH 1240B ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX DISH 12411 ; 6.0 ; ; 6 # Nl CUNEIFORM NUMERIC SIGN SIX U @@ -1010,10 +1079,11 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1D7F2 ; 6.0 ; ; 6 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT SIX 1D7FC ; 6.0 ; ; 6 # Nd MATHEMATICAL MONOSPACE DIGIT SIX 1E8CC ; 6.0 ; ; 6 # No MENDE KIKAKUI DIGIT SIX +1E956 ; 6.0 ; ; 6 # Nd ADLAM DIGIT SIX 1F107 ; 6.0 ; ; 6 # No DIGIT SIX COMMA 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 96 +# Total code points: 101 # ================================================ @@ -1093,11 +1163,15 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 111D7 ; 7.0 ; ; 7 # Nd SHARADA DIGIT SEVEN 111E7 ; 7.0 ; ; 7 # No SINHALA ARCHAIC DIGIT SEVEN 112F7 ; 7.0 ; ; 7 # Nd KHUDAWADI DIGIT SEVEN +11457 ; 7.0 ; ; 7 # Nd NEWA DIGIT SEVEN 114D7 ; 7.0 ; ; 7 # Nd TIRHUTA DIGIT SEVEN 11657 ; 7.0 ; ; 7 # Nd MODI DIGIT SEVEN 116C7 ; 7.0 ; ; 7 # Nd TAKRI DIGIT SEVEN 11737 ; 7.0 ; ; 7 # Nd AHOM DIGIT SEVEN 118E7 ; 7.0 ; ; 7 # Nd WARANG CITI DIGIT SEVEN +11C57 ; 7.0 ; ; 7 # Nd BHAIKSUKI DIGIT SEVEN +11C60 ; 7.0 ; ; 7 # No BHAIKSUKI NUMBER SEVEN +11D57 ; 7.0 ; ; 7 # Nd MASARAM GONDI DIGIT SEVEN 12405 ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN ASH 1240C ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN DISH 12412 ; 7.0 ; ; 7 # Nl CUNEIFORM NUMERIC SIGN SEVEN U @@ -1114,10 +1188,11 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1D7F3 ; 7.0 ; ; 7 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT SEVEN 1D7FD ; 7.0 ; ; 7 # Nd MATHEMATICAL MONOSPACE DIGIT SEVEN 1E8CD ; 7.0 ; ; 7 # No MENDE KIKAKUI DIGIT SEVEN +1E957 ; 7.0 ; ; 7 # Nd ADLAM DIGIT SEVEN 1F108 ; 7.0 ; ; 7 # No DIGIT SEVEN COMMA 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 95 +# Total code points: 100 # ================================================ @@ -1195,11 +1270,15 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 111D8 ; 8.0 ; ; 8 # Nd SHARADA DIGIT EIGHT 111E8 ; 8.0 ; ; 8 # No SINHALA ARCHAIC DIGIT EIGHT 112F8 ; 8.0 ; ; 8 # Nd KHUDAWADI DIGIT EIGHT +11458 ; 8.0 ; ; 8 # Nd NEWA DIGIT EIGHT 114D8 ; 8.0 ; ; 8 # Nd TIRHUTA DIGIT EIGHT 11658 ; 8.0 ; ; 8 # Nd MODI DIGIT EIGHT 116C8 ; 8.0 ; ; 8 # Nd TAKRI DIGIT EIGHT 11738 ; 8.0 ; ; 8 # Nd AHOM DIGIT EIGHT 118E8 ; 8.0 ; ; 8 # Nd WARANG CITI DIGIT EIGHT +11C58 ; 8.0 ; ; 8 # Nd BHAIKSUKI DIGIT EIGHT +11C61 ; 8.0 ; ; 8 # No BHAIKSUKI NUMBER EIGHT +11D58 ; 8.0 ; ; 8 # Nd MASARAM GONDI DIGIT EIGHT 12406 ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT ASH 1240D ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT DISH 12413 ; 8.0 ; ; 8 # Nl CUNEIFORM NUMERIC SIGN EIGHT U @@ -1216,9 +1295,10 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1D7F4 ; 8.0 ; ; 8 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT EIGHT 1D7FE ; 8.0 ; ; 8 # Nd MATHEMATICAL MONOSPACE DIGIT EIGHT 1E8CE ; 8.0 ; ; 8 # No MENDE KIKAKUI DIGIT EIGHT +1E958 ; 8.0 ; ; 8 # Nd ADLAM DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA -# Total code points: 91 +# Total code points: 96 # ================================================ @@ -1297,11 +1377,15 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 111D9 ; 9.0 ; ; 9 # Nd SHARADA DIGIT NINE 111E9 ; 9.0 ; ; 9 # No SINHALA ARCHAIC DIGIT NINE 112F9 ; 9.0 ; ; 9 # Nd KHUDAWADI DIGIT NINE +11459 ; 9.0 ; ; 9 # Nd NEWA DIGIT NINE 114D9 ; 9.0 ; ; 9 # Nd TIRHUTA DIGIT NINE 11659 ; 9.0 ; ; 9 # Nd MODI DIGIT NINE 116C9 ; 9.0 ; ; 9 # Nd TAKRI DIGIT NINE 11739 ; 9.0 ; ; 9 # Nd AHOM DIGIT NINE 118E9 ; 9.0 ; ; 9 # Nd WARANG CITI DIGIT NINE +11C59 ; 9.0 ; ; 9 # Nd BHAIKSUKI DIGIT NINE +11C62 ; 9.0 ; ; 9 # No BHAIKSUKI NUMBER NINE +11D59 ; 9.0 ; ; 9 # Nd MASARAM GONDI DIGIT NINE 12407 ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE ASH 1240E ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE DISH 12414 ; 9.0 ; ; 9 # Nl CUNEIFORM NUMERIC SIGN NINE U @@ -1318,10 +1402,11 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1D7F5 ; 9.0 ; ; 9 # Nd MATHEMATICAL SANS-SERIF BOLD DIGIT NINE 1D7FF ; 9.0 ; ; 9 # Nd MATHEMATICAL MONOSPACE DIGIT NINE 1E8CF ; 9.0 ; ; 9 # No MENDE KIKAKUI DIGIT NINE +1E959 ; 9.0 ; ; 9 # Nd ADLAM DIGIT NINE 1F10A ; 9.0 ; ; 9 # No DIGIT NINE COMMA 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 95 +# Total code points: 100 # ================================================ @@ -1372,10 +1457,11 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 111EA ; 10.0 ; ; 10 # No SINHALA ARCHAIC NUMBER TEN 1173A ; 10.0 ; ; 10 # No AHOM NUMBER TEN 118EA ; 10.0 ; ; 10 # No WARANG CITI NUMBER TEN +11C63 ; 10.0 ; ; 10 # No BHAIKSUKI NUMBER TEN 16B5B ; 10.0 ; ; 10 # No PAHAWH HMONG NUMBER TENS 1D369 ; 10.0 ; ; 10 # No COUNTING ROD TENS DIGIT ONE -# Total code points: 53 +# Total code points: 54 # ================================================ @@ -1497,9 +1583,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 111EB ; 20.0 ; ; 20 # No SINHALA ARCHAIC NUMBER TWENTY 1173B ; 20.0 ; ; 20 # No AHOM NUMBER TWENTY 118EB ; 20.0 ; ; 20 # No WARANG CITI NUMBER TWENTY +11C64 ; 20.0 ; ; 20 # No BHAIKSUKI NUMBER TWENTY 1D36A ; 20.0 ; ; 20 # No COUNTING ROD TENS DIGIT TWO -# Total code points: 30 +# Total code points: 31 # ================================================ @@ -1570,10 +1657,11 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 1105D ; 30.0 ; ; 30 # No BRAHMI NUMBER THIRTY 111EC ; 30.0 ; ; 30 # No SINHALA ARCHAIC NUMBER THIRTY 118EC ; 30.0 ; ; 30 # No WARANG CITI NUMBER THIRTY +11C65 ; 30.0 ; ; 30 # No BHAIKSUKI NUMBER THIRTY 1D36B ; 30.0 ; ; 30 # No COUNTING ROD TENS DIGIT THREE 20983 ; 30.0 ; ; 30 # Lo CJK UNIFIED IDEOGRAPH-20983 -# Total code points: 15 +# Total code points: 16 # ================================================ @@ -1642,12 +1730,13 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 1105E ; 40.0 ; ; 40 # No BRAHMI NUMBER FORTY 111ED ; 40.0 ; ; 40 # No SINHALA ARCHAIC NUMBER FORTY 118ED ; 40.0 ; ; 40 # No WARANG CITI NUMBER FORTY +11C66 ; 40.0 ; ; 40 # No BHAIKSUKI NUMBER FORTY 12467 ; 40.0 ; ; 40 # Nl CUNEIFORM NUMERIC SIGN ELAMITE FORTY 1D36C ; 40.0 ; ; 40 # No COUNTING ROD TENS DIGIT FOUR 2098C ; 40.0 ; ; 40 # Lo CJK UNIFIED IDEOGRAPH-2098C 2099C ; 40.0 ; ; 40 # Lo CJK UNIFIED IDEOGRAPH-2099C -# Total code points: 15 +# Total code points: 16 # ================================================ @@ -1726,10 +1815,11 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 1105F ; 50.0 ; ; 50 # No BRAHMI NUMBER FIFTY 111EE ; 50.0 ; ; 50 # No SINHALA ARCHAIC NUMBER FIFTY 118EE ; 50.0 ; ; 50 # No WARANG CITI NUMBER FIFTY +11C67 ; 50.0 ; ; 50 # No BHAIKSUKI NUMBER FIFTY 12468 ; 50.0 ; ; 50 # Nl CUNEIFORM NUMERIC SIGN ELAMITE FIFTY 1D36D ; 50.0 ; ; 50 # No COUNTING ROD TENS DIGIT FIVE -# Total code points: 26 +# Total code points: 27 # ================================================ @@ -1742,9 +1832,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 11060 ; 60.0 ; ; 60 # No BRAHMI NUMBER SIXTY 111EF ; 60.0 ; ; 60 # No SINHALA ARCHAIC NUMBER SIXTY 118EF ; 60.0 ; ; 60 # No WARANG CITI NUMBER SIXTY +11C68 ; 60.0 ; ; 60 # No BHAIKSUKI NUMBER SIXTY 1D36E ; 60.0 ; ; 60 # No COUNTING ROD TENS DIGIT SIX -# Total code points: 10 +# Total code points: 11 # ================================================ @@ -1757,9 +1848,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 11061 ; 70.0 ; ; 70 # No BRAHMI NUMBER SEVENTY 111F0 ; 70.0 ; ; 70 # No SINHALA ARCHAIC NUMBER SEVENTY 118F0 ; 70.0 ; ; 70 # No WARANG CITI NUMBER SEVENTY +11C69 ; 70.0 ; ; 70 # No BHAIKSUKI NUMBER SEVENTY 1D36F ; 70.0 ; ; 70 # No COUNTING ROD TENS DIGIT SEVEN -# Total code points: 10 +# Total code points: 11 # ================================================ @@ -1771,9 +1863,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 11062 ; 80.0 ; ; 80 # No BRAHMI NUMBER EIGHTY 111F1 ; 80.0 ; ; 80 # No SINHALA ARCHAIC NUMBER EIGHTY 118F1 ; 80.0 ; ; 80 # No WARANG CITI NUMBER EIGHTY +11C6A ; 80.0 ; ; 80 # No BHAIKSUKI NUMBER EIGHTY 1D370 ; 80.0 ; ; 80 # No COUNTING ROD TENS DIGIT EIGHT -# Total code points: 9 +# Total code points: 10 # ================================================ @@ -1785,9 +1878,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 11063 ; 90.0 ; ; 90 # No BRAHMI NUMBER NINETY 111F2 ; 90.0 ; ; 90 # No SINHALA ARCHAIC NUMBER NINETY 118F2 ; 90.0 ; ; 90 # No WARANG CITI NUMBER NINETY +11C6B ; 90.0 ; ; 90 # No BHAIKSUKI NUMBER NINETY 1D371 ; 90.0 ; ; 90 # No COUNTING ROD TENS DIGIT NINE -# Total code points: 9 +# Total code points: 10 # ================================================ @@ -1819,9 +1913,10 @@ F9FD ; 10.0 ; ; 10 # Lo CJK COMPATIBILITY IDEOGRAPH-F9FD 10E72 ; 100.0 ; ; 100 # No RUMI NUMBER ONE HUNDRED 11064 ; 100.0 ; ; 100 # No BRAHMI NUMBER ONE HUNDRED 111F3 ; 100.0 ; ; 100 # No SINHALA ARCHAIC NUMBER ONE HUNDRED +11C6C ; 100.0 ; ; 100 # No BHAIKSUKI HUNDREDS UNIT MARK 16B5C ; 100.0 ; ; 100 # No PAHAWH HMONG NUMBER HUNDREDS -# Total code points: 29 +# Total code points: 30 # ================================================ diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Cham.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Cham.pl deleted file mode 100644 index 37b952ade8f..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Cham.pl +++ /dev/null @@ -1,22 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V8 -43520 -43575 -43584 -43598 -43600 -43610 -43612 -43616 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Ethi.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Ethi.pl deleted file mode 100644 index 2edc392913f..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Ethi.pl +++ /dev/null @@ -1,78 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V64 -4608 -4681 -4682 -4686 -4688 -4695 -4696 -4697 -4698 -4702 -4704 -4745 -4746 -4750 -4752 -4785 -4786 -4790 -4792 -4799 -4800 -4801 -4802 -4806 -4808 -4823 -4824 -4881 -4882 -4886 -4888 -4955 -4957 -4989 -4992 -5018 -11648 -11671 -11680 -11687 -11688 -11695 -11696 -11703 -11704 -11711 -11712 -11719 -11720 -11727 -11728 -11735 -11736 -11743 -43777 -43783 -43785 -43791 -43793 -43799 -43808 -43815 -43816 -43823 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hebr.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hebr.pl deleted file mode 100644 index 5bb2a44da9b..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hebr.pl +++ /dev/null @@ -1,32 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V18 -1425 -1480 -1488 -1515 -1520 -1525 -64285 -64311 -64312 -64317 -64318 -64319 -64320 -64322 -64323 -64325 -64326 -64336 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hmng.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hmng.pl deleted file mode 100644 index 0ebf81ead55..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Hmng.pl +++ /dev/null @@ -1,24 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V10 -92928 -92998 -93008 -93018 -93019 -93026 -93027 -93048 -93053 -93072 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khar.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khar.pl deleted file mode 100644 index 73bcc8f8845..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khar.pl +++ /dev/null @@ -1,30 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V16 -68096 -68100 -68101 -68103 -68108 -68116 -68117 -68120 -68121 -68148 -68152 -68155 -68159 -68168 -68176 -68185 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khmr.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khmr.pl deleted file mode 100644 index da7325da20d..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Khmr.pl +++ /dev/null @@ -1,22 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V8 -6016 -6110 -6112 -6122 -6128 -6138 -6624 -6656 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lana.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lana.pl deleted file mode 100644 index 3285c50de0b..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lana.pl +++ /dev/null @@ -1,24 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V10 -6688 -6751 -6752 -6781 -6783 -6794 -6800 -6810 -6816 -6830 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lao.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lao.pl deleted file mode 100644 index d194ec26e09..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Lao.pl +++ /dev/null @@ -1,50 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V36 -3713 -3715 -3716 -3717 -3719 -3721 -3722 -3723 -3725 -3726 -3732 -3736 -3737 -3744 -3745 -3748 -3749 -3750 -3751 -3752 -3754 -3756 -3757 -3770 -3771 -3774 -3776 -3781 -3782 -3783 -3784 -3790 -3792 -3802 -3804 -3808 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Talu.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Talu.pl deleted file mode 100644 index 2f52b88c7b8..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Talu.pl +++ /dev/null @@ -1,22 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V8 -6528 -6572 -6576 -6602 -6608 -6619 -6622 -6624 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Tibt.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Tibt.pl deleted file mode 100644 index 956c74cf317..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Tibt.pl +++ /dev/null @@ -1,28 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V14 -3840 -3912 -3913 -3949 -3953 -3992 -3993 -4029 -4030 -4045 -4046 -4053 -4057 -4059 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Xsux.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Xsux.pl deleted file mode 100644 index 41db27504d2..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Xsux.pl +++ /dev/null @@ -1,22 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V8 -73728 -74650 -74752 -74863 -74864 -74869 -74880 -75076 -END diff --git a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Zzzz.pl b/gnu/usr.bin/perl/lib/unicore/lib/Sc/Zzzz.pl deleted file mode 100644 index a6dd196b6b5..00000000000 --- a/gnu/usr.bin/perl/lib/unicore/lib/Sc/Zzzz.pl +++ /dev/null @@ -1,1235 +0,0 @@ -# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is machine-generated by lib/unicore/mktables from the Unicode -# database, Version 8.0.0. Any changes made here will be lost! - -# !!!!!!! INTERNAL PERL USE ONLY !!!!!!! -# This file is for internal use by core Perl only. The format and even the -# name or existence of this file are subject to change without notice. Don't -# use it directly. Use Unicode::UCD to access the Unicode character data -# base. - - -return <<'END'; -V1221 -888 -890 -896 -900 -907 -908 -909 -910 -930 -931 -1328 -1329 -1367 -1369 -1376 -1377 -1416 -1417 -1419 -1421 -1424 -1425 -1480 -1488 -1515 -1520 -1525 -1536 -1565 -1566 -1806 -1807 -1867 -1869 -1970 -1984 -2043 -2048 -2094 -2096 -2111 -2112 -2140 -2142 -2143 -2208 -2229 -2275 -2436 -2437 -2445 -2447 -2449 -2451 -2473 -2474 -2481 -2482 -2483 -2486 -2490 -2492 -2501 -2503 -2505 -2507 -2511 -2519 -2520 -2524 -2526 -2527 -2532 -2534 -2556 -2561 -2564 -2565 -2571 -2575 -2577 -2579 -2601 -2602 -2609 -2610 -2612 -2613 -2615 -2616 -2618 -2620 -2621 -2622 -2627 -2631 -2633 -2635 -2638 -2641 -2642 -2649 -2653 -2654 -2655 -2662 -2678 -2689 -2692 -2693 -2702 -2703 -2706 -2707 -2729 -2730 -2737 -2738 -2740 -2741 -2746 -2748 -2758 -2759 -2762 -2763 -2766 -2768 -2769 -2784 -2788 -2790 -2802 -2809 -2810 -2817 -2820 -2821 -2829 -2831 -2833 -2835 -2857 -2858 -2865 -2866 -2868 -2869 -2874 -2876 -2885 -2887 -2889 -2891 -2894 -2902 -2904 -2908 -2910 -2911 -2916 -2918 -2936 -2946 -2948 -2949 -2955 -2958 -2961 -2962 -2966 -2969 -2971 -2972 -2973 -2974 -2976 -2979 -2981 -2984 -2987 -2990 -3002 -3006 -3011 -3014 -3017 -3018 -3022 -3024 -3025 -3031 -3032 -3046 -3067 -3072 -3076 -3077 -3085 -3086 -3089 -3090 -3113 -3114 -3130 -3133 -3141 -3142 -3145 -3146 -3150 -3157 -3159 -3160 -3163 -3168 -3172 -3174 -3184 -3192 -3200 -3201 -3204 -3205 -3213 -3214 -3217 -3218 -3241 -3242 -3252 -3253 -3258 -3260 -3269 -3270 -3273 -3274 -3278 -3285 -3287 -3294 -3295 -3296 -3300 -3302 -3312 -3313 -3315 -3329 -3332 -3333 -3341 -3342 -3345 -3346 -3387 -3389 -3397 -3398 -3401 -3402 -3407 -3415 -3416 -3423 -3428 -3430 -3446 -3449 -3456 -3458 -3460 -3461 -3479 -3482 -3506 -3507 -3516 -3517 -3518 -3520 -3527 -3530 -3531 -3535 -3541 -3542 -3543 -3544 -3552 -3558 -3568 -3570 -3573 -3585 -3643 -3647 -3676 -3713 -3715 -3716 -3717 -3719 -3721 -3722 -3723 -3725 -3726 -3732 -3736 -3737 -3744 -3745 -3748 -3749 -3750 -3751 -3752 -3754 -3756 -3757 -3770 -3771 -3774 -3776 -3781 -3782 -3783 -3784 -3790 -3792 -3802 -3804 -3808 -3840 -3912 -3913 -3949 -3953 -3992 -3993 -4029 -4030 -4045 -4046 -4059 -4096 -4294 -4295 -4296 -4301 -4302 -4304 -4681 -4682 -4686 -4688 -4695 -4696 -4697 -4698 -4702 -4704 -4745 -4746 -4750 -4752 -4785 -4786 -4790 -4792 -4799 -4800 -4801 -4802 -4806 -4808 -4823 -4824 -4881 -4882 -4886 -4888 -4955 -4957 -4989 -4992 -5018 -5024 -5110 -5112 -5118 -5120 -5789 -5792 -5881 -5888 -5901 -5902 -5909 -5920 -5943 -5952 -5972 -5984 -5997 -5998 -6001 -6002 -6004 -6016 -6110 -6112 -6122 -6128 -6138 -6144 -6159 -6160 -6170 -6176 -6264 -6272 -6315 -6320 -6390 -6400 -6431 -6432 -6444 -6448 -6460 -6464 -6465 -6468 -6510 -6512 -6517 -6528 -6572 -6576 -6602 -6608 -6619 -6622 -6684 -6686 -6751 -6752 -6781 -6783 -6794 -6800 -6810 -6816 -6830 -6832 -6847 -6912 -6988 -6992 -7037 -7040 -7156 -7164 -7224 -7227 -7242 -7245 -7296 -7360 -7368 -7376 -7415 -7416 -7418 -7424 -7670 -7676 -7958 -7960 -7966 -7968 -8006 -8008 -8014 -8016 -8024 -8025 -8026 -8027 -8028 -8029 -8030 -8031 -8062 -8064 -8117 -8118 -8133 -8134 -8148 -8150 -8156 -8157 -8176 -8178 -8181 -8182 -8191 -8192 -8293 -8294 -8306 -8308 -8335 -8336 -8349 -8352 -8383 -8400 -8433 -8448 -8588 -8592 -9211 -9216 -9255 -9280 -9291 -9312 -11124 -11126 -11158 -11160 -11194 -11197 -11209 -11210 -11218 -11244 -11248 -11264 -11311 -11312 -11359 -11360 -11508 -11513 -11558 -11559 -11560 -11565 -11566 -11568 -11624 -11631 -11633 -11647 -11671 -11680 -11687 -11688 -11695 -11696 -11703 -11704 -11711 -11712 -11719 -11720 -11727 -11728 -11735 -11736 -11743 -11744 -11843 -11904 -11930 -11931 -12020 -12032 -12246 -12272 -12284 -12288 -12352 -12353 -12439 -12441 -12544 -12549 -12590 -12593 -12687 -12688 -12731 -12736 -12772 -12784 -12831 -12832 -13055 -13056 -19894 -19904 -40918 -40960 -42125 -42128 -42183 -42192 -42540 -42560 -42744 -42752 -42926 -42928 -42936 -42999 -43052 -43056 -43066 -43072 -43128 -43136 -43205 -43214 -43226 -43232 -43262 -43264 -43348 -43359 -43389 -43392 -43470 -43471 -43482 -43486 -43519 -43520 -43575 -43584 -43598 -43600 -43610 -43612 -43715 -43739 -43767 -43777 -43783 -43785 -43791 -43793 -43799 -43808 -43815 -43816 -43823 -43824 -43878 -43888 -44014 -44016 -44026 -44032 -55204 -55216 -55239 -55243 -55292 -63744 -64110 -64112 -64218 -64256 -64263 -64275 -64280 -64285 -64311 -64312 -64317 -64318 -64319 -64320 -64322 -64323 -64325 -64326 -64450 -64467 -64832 -64848 -64912 -64914 -64968 -65008 -65022 -65024 -65050 -65056 -65107 -65108 -65127 -65128 -65132 -65136 -65141 -65142 -65277 -65279 -65280 -65281 -65471 -65474 -65480 -65482 -65488 -65490 -65496 -65498 -65501 -65504 -65511 -65512 -65519 -65529 -65534 -65536 -65548 -65549 -65575 -65576 -65595 -65596 -65598 -65599 -65614 -65616 -65630 -65664 -65787 -65792 -65795 -65799 -65844 -65847 -65933 -65936 -65948 -65952 -65953 -66000 -66046 -66176 -66205 -66208 -66257 -66272 -66300 -66304 -66340 -66352 -66379 -66384 -66427 -66432 -66462 -66463 -66500 -66504 -66518 -66560 -66718 -66720 -66730 -66816 -66856 -66864 -66916 -66927 -66928 -67072 -67383 -67392 -67414 -67424 -67432 -67584 -67590 -67592 -67593 -67594 -67638 -67639 -67641 -67644 -67645 -67647 -67670 -67671 -67743 -67751 -67760 -67808 -67827 -67828 -67830 -67835 -67868 -67871 -67898 -67903 -67904 -67968 -68024 -68028 -68048 -68050 -68100 -68101 -68103 -68108 -68116 -68117 -68120 -68121 -68148 -68152 -68155 -68159 -68168 -68176 -68185 -68192 -68256 -68288 -68327 -68331 -68343 -68352 -68406 -68409 -68438 -68440 -68467 -68472 -68498 -68505 -68509 -68521 -68528 -68608 -68681 -68736 -68787 -68800 -68851 -68858 -68864 -69216 -69247 -69632 -69710 -69714 -69744 -69759 -69826 -69840 -69865 -69872 -69882 -69888 -69941 -69942 -69956 -69968 -70007 -70016 -70094 -70096 -70112 -70113 -70133 -70144 -70162 -70163 -70206 -70272 -70279 -70280 -70281 -70282 -70286 -70287 -70302 -70303 -70314 -70320 -70379 -70384 -70394 -70400 -70404 -70405 -70413 -70415 -70417 -70419 -70441 -70442 -70449 -70450 -70452 -70453 -70458 -70460 -70469 -70471 -70473 -70475 -70478 -70480 -70481 -70487 -70488 -70493 -70500 -70502 -70509 -70512 -70517 -70784 -70856 -70864 -70874 -71040 -71094 -71096 -71134 -71168 -71237 -71248 -71258 -71296 -71352 -71360 -71370 -71424 -71450 -71453 -71468 -71472 -71488 -71840 -71923 -71935 -71936 -72384 -72441 -73728 -74650 -74752 -74863 -74864 -74869 -74880 -75076 -77824 -78895 -82944 -83527 -92160 -92729 -92736 -92767 -92768 -92778 -92782 -92784 -92880 -92910 -92912 -92918 -92928 -92998 -93008 -93018 -93019 -93026 -93027 -93048 -93053 -93072 -93952 -94021 -94032 -94079 -94095 -94112 -110592 -110594 -113664 -113771 -113776 -113789 -113792 -113801 -113808 -113818 -113820 -113828 -118784 -119030 -119040 -119079 -119081 -119273 -119296 -119366 -119552 -119639 -119648 -119666 -119808 -119893 -119894 -119965 -119966 -119968 -119970 -119971 -119973 -119975 -119977 -119981 -119982 -119994 -119995 -119996 -119997 -120004 -120005 -120070 -120071 -120075 -120077 -120085 -120086 -120093 -120094 -120122 -120123 -120127 -120128 -120133 -120134 -120135 -120138 -120145 -120146 -120486 -120488 -120780 -120782 -121484 -121499 -121504 -121505 -121520 -124928 -125125 -125127 -125143 -126464 -126468 -126469 -126496 -126497 -126499 -126500 -126501 -126503 -126504 -126505 -126515 -126516 -126520 -126521 -126522 -126523 -126524 -126530 -126531 -126535 -126536 -126537 -126538 -126539 -126540 -126541 -126544 -126545 -126547 -126548 -126549 -126551 -126552 -126553 -126554 -126555 -126556 -126557 -126558 -126559 -126560 -126561 -126563 -126564 -126565 -126567 -126571 -126572 -126579 -126580 -126584 -126585 -126589 -126590 -126591 -126592 -126602 -126603 -126620 -126625 -126628 -126629 -126634 -126635 -126652 -126704 -126706 -126976 -127020 -127024 -127124 -127136 -127151 -127153 -127168 -127169 -127184 -127185 -127222 -127232 -127245 -127248 -127279 -127280 -127340 -127344 -127387 -127462 -127491 -127504 -127547 -127552 -127561 -127568 -127570 -127744 -128378 -128379 -128420 -128421 -128721 -128736 -128749 -128752 -128756 -128768 -128884 -128896 -128981 -129024 -129036 -129040 -129096 -129104 -129114 -129120 -129160 -129168 -129198 -129296 -129305 -129408 -129413 -129472 -129473 -131072 -173783 -173824 -177973 -177984 -178206 -178208 -183970 -194560 -195102 -917505 -917506 -917536 -917632 -917760 -918000 -END diff --git a/gnu/usr.bin/perl/lib/unicore/mktables b/gnu/usr.bin/perl/lib/unicore/mktables index 0e70a782a26..8d535152d89 100644 --- a/gnu/usr.bin/perl/lib/unicore/mktables +++ b/gnu/usr.bin/perl/lib/unicore/mktables @@ -36,6 +36,17 @@ my $debugging_build = $Config{"ccflags"} =~ /-DDEBUGGING/; sub NON_ASCII_PLATFORM { ord("A") != 65 } +# When a new version of Unicode is published, unfortunately the algorithms for +# dealing with various bounds, like \b{gcb}, \b{lb} may have to be updated +# manually. The changes may or may not be backward compatible with older +# releases. The code is in regen/mk_invlist.pl and regexec.c. Make the +# changes, then come back here and set the variable below to what version the +# code is expecting. If a newer version of Unicode is being compiled than +# expected, a warning will be generated. If an older version is being +# compiled, any bounds tests that fail in the generated test file (-maketest +# option) will be marked as TODO. +my $version_of_mk_invlist_bounds = v10.0.0; + ########################################################################## # # mktables -- create the runtime Perl Unicode files (lib/unicore/.../*.pl), @@ -124,7 +135,7 @@ my $map_directory = 'To'; # Where map files go. # each one of the tens of thousands individually. # # In a match table, the value of a range is irrelevant (and hence the type as -# well, which will always be 0), and arbitrarily set to the null string. +# well, which will always be 0), and arbitrarily set to the empty string. # Using the example above, there would be two match tables for those two # entries, one named Upper would contain the 0x41..0x5A range, and the other # named Lower would contain 0x61..0x7A. @@ -352,6 +363,8 @@ my $unicode_reference_url = 'http://www.unicode.org/reports/tr44/'; # # trace ... if main::DEBUG && $to_trace; # +# main::stack_trace() will display what its name implies +# # If there is just one or a few files that you're debugging, you can easily # cause most everything else to be skipped. Change the line # @@ -409,7 +422,7 @@ my $unicode_reference_url = 'http://www.unicode.org/reports/tr44/'; # # A NOTE ON UNIHAN # -# This program can generate tables from the Unihan database. But that db +# This program can generate tables from the Unihan database. But that DB # isn't normally available, so it is marked as optional. Prior to version # 5.2, this database was in a single file, Unihan.txt. In 5.2 the database # was split into 8 different files, all beginning with the letters 'Unihan'. @@ -477,8 +490,8 @@ my $unicode_reference_url = 'http://www.unicode.org/reports/tr44/'; # handled by Unicode::Normalize, nor will it compile when presented a version # that has them. However, you can trivially get it to compile by simply # ignoring those decompositions, by changing the croak to a carp. At the time -# of this writing, the line (in cpan/Unicode-Normalize/Normalize.pm or -# cpan/Unicode-Normalize/mkheader) reads +# of this writing, the line (in dist/Unicode-Normalize/Normalize.pm or +# dist/Unicode-Normalize/mkheader) reads # # croak("Weird Canonical Decomposition of U+$h"); # @@ -617,12 +630,28 @@ our $to_trace = 0; } } +sub stack_trace() { + local $to_trace = 1 if main::DEBUG; + my $line = (caller(0))[2]; + my $i = 1; + + # Accumulate the stack trace + while (1) { + my ($pkg, $file, $caller_line, $caller) = caller $i++; + + last unless defined $caller; + + trace "called from $caller() at line $line"; + $line = $caller_line; + } +} + # This is for a rarely used development feature that allows you to compare two # versions of the Unicode standard without having to deal with changes caused # by the code points introduced in the later version. You probably also want # to use the -annotate option when using this. Run this program on a unicore # containing the starting release you want to compare. Save that output -# structrue. Then, switching to a unicore with the ending release, change the +# structure. Then, switching to a unicore with the ending release, change the # 0 in the $string_compare_versions definition just below to a string # containing a SINGLE dotted Unicode release number (e.g. "2.1") corresponding # to the starting release. This program will then compile, but throw away all @@ -631,7 +660,7 @@ our $to_trace = 0; # common to both releases, and you can see the changes caused just by the # underlying release semantic changes. For versions earlier than 3.2, you # must copy a version of DAge.txt into the directory. -my $string_compare_versions = DEBUG && 0; # e.g., "2.1"; +my $string_compare_versions = DEBUG && ""; # e.g., "2.1"; my $compare_versions = DEBUG && $string_compare_versions && pack "C*", split /\./, $string_compare_versions; @@ -702,7 +731,8 @@ while (@ARGV) { $verbosity = 0; } elsif ($arg eq '-w') { - $write_unchanged_files = 1; # update the files even if havent changed + # update the files even if they haven't changed + $write_unchanged_files = 1; } elsif ($arg eq '-check') { my $this = shift @ARGV; @@ -1110,17 +1140,17 @@ my $MAX_UNICODE_CODEPOINT_STRING = ($v_version ge v2.0.0) my $MAX_UNICODE_CODEPOINT = hex $MAX_UNICODE_CODEPOINT_STRING; my $MAX_UNICODE_CODEPOINTS = $MAX_UNICODE_CODEPOINT + 1; -# We work with above-Unicode code points, up to UV_MAX. But when you get -# that high, above IV_MAX, some operations don't work, and you can easily get -# overflow. Therefore for internal use, we use a much smaller number, -# translating it to UV_MAX only for output. The exact number is immaterial -# (all Unicode code points are treated exactly the same), but the algorithm -# requires it to be at least 2 * $MAX_UNICODE_CODEPOINTS + 1; +# We work with above-Unicode code points, up to IV_MAX, but we may want to use +# sentinels above that number. Therefore for internal use, we use a much +# smaller number, translating it to IV_MAX only for output. The exact number +# is immaterial (all above-Unicode code points are treated exactly the same), +# but the algorithm requires it to be at least +# 2 * $MAX_UNICODE_CODEPOINTS + 1 my $MAX_WORKING_CODEPOINTS= $MAX_UNICODE_CODEPOINT * 8; my $MAX_WORKING_CODEPOINT = $MAX_WORKING_CODEPOINTS - 1; my $MAX_WORKING_CODEPOINT_STRING = sprintf("%X", $MAX_WORKING_CODEPOINT); -my $MAX_PLATFORM_CODEPOINT = ~0; +my $MAX_PLATFORM_CODEPOINT = ~0 >> 1; # Matches legal code point. 4-6 hex numbers, If there are 6, the first # two must be 10; if there are 5, the first must not be a 0. Written this way @@ -1132,7 +1162,7 @@ my $run_on_code_point_re = qr/ (?: 10[0-9A-F]{4} | [1-9A-F][0-9A-F]{4} | [0-9A-F]{4} ) \b/x; my $code_point_re = qr/\b$run_on_code_point_re/; -# This matches the beginning of the line in the Unicode db files that give the +# This matches the beginning of the line in the Unicode DB files that give the # defaults for code points not listed (i.e., missing) in the file. The code # depends on this ending with a semi-colon, so it can assume it is a valid # field when the line is split() by semi-colons @@ -1424,6 +1454,7 @@ my $Assigned; # All assigned characters in this Unicode release my $DI; # Default_Ignorable_Code_Point property my $NChar; # Noncharacter_Code_Point property my $script; +my $scx; # Script_Extensions property # Are there conflicting names because of beginning with 'In_', or 'Is_' my $has_In_conflicts = 0; @@ -1499,7 +1530,7 @@ sub populate_char_info ($) { $viacode[$i] = $perl_charname->value_of($i) || ""; $age[$i] = (defined $age) - ? (($age->value_of($i) =~ / ^ \d \. \d $ /x) + ? (($age->value_of($i) =~ / ^ \d+ \. \d+ $ /x) ? $age->value_of($i) : "") : ""; @@ -2075,7 +2106,7 @@ package Input_file; # 1) call before the first line is read, for pre processing # 2) call to adjust each line of the input before the main handler gets # them. This can be automatically generated, if appropriately simple -# enough, by specifiying a Properties parameter in the constructor. +# enough, by specifying a Properties parameter in the constructor. # 3) call upon EOF before the main handler exits its loop # 4) call at the end, for post processing # @@ -2083,7 +2114,7 @@ package Input_file; # each_line_handler()s. So, if the format of the line is not in the desired # format for the main handler, these are used to do that adjusting. They can # be stacked (by enclosing them in an [ anonymous array ] in the constructor, -# so the $_ output of one is used as the input to the next. The eof handler +# so the $_ output of one is used as the input to the next. The EOF handler # is also stackable, but none of the others are, but could easily be changed # to be so. # @@ -2167,7 +2198,7 @@ sub trace { return main::trace(@_); } # not otherwise be processed, and to not raise a warning about not being # handled. In the constructor call, any value that evaluates to a numeric # 0 or undef means don't skip. Any other value is a string giving the - # reason it is being skippped, and this will appear in generated pod. + # reason it is being skipped, and this will appear in generated pod. # However, an empty string reason will suppress the pod entry. # Internally, calls that evaluate to numeric 0 are changed into undef to # distinguish them from an empty string call. @@ -2180,11 +2211,20 @@ sub trace { return main::trace(@_); } # 'handler' main::set_access('each_line_handler', \%each_line_handler, 'c'); + my %retain_trailing_comments; + # This is used to not discard the comments that end data lines. This + # would be used only for files with non-typical syntax, and most code here + # assumes that comments have been stripped, so special handlers would have + # to be written. It is assumed that the code will use these in + # single-quoted contexts, and so any "'" marks in the comment will be + # prefixed by a backslash. + main::set_access('retain_trailing_comments', \%retain_trailing_comments, 'c'); + my %properties; # Optional ordered list of the properties that occur in each # meaningful line of the input file. If present, an appropriate # each_line_handler() is automatically generated and pushed onto the stack # of such handlers. This is useful when a file contains multiple - # proerties per line, but no other special considerations are necessary. + # properties per line, but no other special considerations are necessary. # The special value "<ignored>" means to discard the corresponding input # field. # Any @missing lines in the file should also match this syntax; no such @@ -2337,6 +2377,7 @@ sub trace { return main::trace(@_); } # Set defaults $handler{$addr} = \&main::process_generic_property_file; + $retain_trailing_comments{$addr} = 0; $non_skip{$addr} = 0; $skip{$addr} = undef; $has_missings_defaults{$addr} = $NO_DEFAULTS; @@ -3002,9 +3043,21 @@ END next; } - # Remove comments and trailing space, and skip this line if the - # result is empty - s/#.*//; + # Unless to keep, remove comments. If to keep, ignore + # comment-only lines + if ($retain_trailing_comments{$addr}) { + next if / ^ \s* \# /x; + + # But escape any single quotes (done in both the comment and + # non-comment portion; this could be a bug someday, but not + # likely) + s/'/\\'/g; + } + else { + s/#.*//; + } + + # Remove trailing space, and skip this line if the result is empty s/\s+$//; next if /^$/; @@ -3501,7 +3554,7 @@ sub trace { return main::trace(@_); } main::set_access('end', \%end, 'r', 's'); my %value; - main::set_access('value', \%value, 'r'); + main::set_access('value', \%value, 'r', 's'); my %type; main::set_access('type', \%type, 'r'); @@ -5272,6 +5325,14 @@ use parent '-norequire', '_Range_List_Base'; return $self->_add_delete('+', @_); } + sub replace_map { + # Replace a range + + my $self = shift; + + return $self->_add_delete('+', @_, Replace => $UNCONDITIONALLY); + } + sub add_duplicate { # Adds entry to a range list which can duplicate an existing entry @@ -5412,6 +5473,15 @@ sub trace { return main::trace(@_); } # used to override calculations. main::set_access('format', \%format, 'r', 'p_s'); + my %has_dependency; + # A boolean that gives whether some other table in this property is + # defined as the complement of this table. This is a crude, but currently + # sufficient, mechanism to make this table not get destroyed before what + # is dependent on it is. Other dependencies could be added, so the name + # was chosen to reflect a more general situation than actually is + # currently the case. + main::set_access('has_dependency', \%has_dependency, 'r', 's'); + sub new { # All arguments are key => value pairs, which you can see below, most # of which match fields documented above. Otherwise: Re_Pod_Entry, @@ -5467,6 +5537,7 @@ sub trace { return main::trace(@_); } $note{$addr} = [ ]; $file_path{$addr} = [ ]; $locked{$addr} = ""; + $has_dependency{$addr} = 0; push @{$description{$addr}}, $description if $description; push @{$note{$addr}}, $note if $note; @@ -6290,6 +6361,22 @@ END } if ($write_as_invlist) { + if ( $previous_end > 0 + && $output_range_counts{$addr}) + { + my $complement_count = $start - $previous_end - 1; + if ($complement_count > 1) { + $OUT[-1] = merge_single_annotation_line( + $OUT[-1], + "#" + . (" " x 17) + . "[" + . main::clarify_code_point_count( + $complement_count) + . "] in complement\n", + $comment_indent); + } + } # Inversion list format has a single number per line, # the starting code point of a range that matches the @@ -7655,6 +7742,7 @@ END # Accessors for the underlying list that should fail if locked. for my $sub (qw( add_duplicate + replace_map )) { no strict "refs"; @@ -7722,6 +7810,12 @@ use parent '-norequire', '_Base_Table'; # version. But manual intervention to decide what the actual behavior # should be may be required should this happen. The introductory comments # have more to say about this. +# +# 4) Definition. This is a string for human consumption that specifies the +# code points that this table matches. This is used only for the generated +# pod file. It may be specified explicitly, or automatically computed. +# Only the first portion of complicated definitions is computed and +# displayed. sub standardize { return main::standardize($_[0]); } sub trace { return main::trace(@_); } @@ -7766,6 +7860,11 @@ sub trace { return main::trace(@_); } # none. main::set_access('complement', \%complement, 'r'); + my %definition; + # Human readable string of the first few ranges of code points matched by + # this table + main::set_access('definition', \%definition, 'r', 's'); + sub new { my $class = shift; @@ -7782,6 +7881,7 @@ sub trace { return main::trace(@_); } my $initialize = delete $args{'Initialize'}; my $matches_all = delete $args{'Matches_All'} || 0; my $format = delete $args{'Format'}; + my $definition = delete $args{'Definition'} // ""; # Rest of parameters passed on. my $range_list = Range_List->new(Initialize => $initialize, @@ -7816,6 +7916,7 @@ sub trace { return main::trace(@_); } $leader{$addr} = $self; $parent{$addr} = $self; $complement{$addr} = 0; + $definition{$addr} = $definition; if (defined $format && $format ne $EMPTY_FORMAT) { Carp::my_carp_bug("'Format' must be '$EMPTY_FORMAT' in a match table instead of '$format'. Using '$EMPTY_FORMAT'"); @@ -7926,13 +8027,23 @@ sub trace { return main::trace(@_); } # complement's if it has one. my $self = shift; - my $complement; - if (($complement = $self->complement) != 0) { - return ~ $complement->_range_list; - } - else { - return $self->SUPER::_range_list; + my $complement = $self->complement; + + # In order to avoid re-complementing on each access, only do the + # complement the first time, and store the result in this table's + # range list to use henceforth. However, this wouldn't work if the + # controlling (complement) table changed after we do this, so lock it. + # Currently, the value of the complement isn't needed until after it + # is fully constructed, so this works. If this were to change, the + # each_range iteration functionality would no longer work on this + # complement. + if ($complement != 0 && $self->SUPER::_range_list->count == 0) { + $self->_set_range_list($self->SUPER::_range_list + + ~ $complement->_range_list); + $complement->lock; } + + return $self->SUPER::_range_list; } sub add_alias { @@ -7970,7 +8081,7 @@ sub trace { return main::trace(@_); } # disambiguate with). if (defined $conflicting_object) { foreach my $alias ($self->aliases) { - if ($alias->name eq $conflicting_name) { + if (standardize($alias->name) eq standardize($conflicting_name)) { # Here, there is an exact match. This results in # ambiguous comments, so disambiguate by changing the @@ -8063,7 +8174,19 @@ sub trace { return main::trace(@_); } # add_alias() # instead for same # property - && ! $other->perl_extension) + && ! $other->perl_extension + + # We allow the sc and scx properties to be marked as + # related. They are in fact related, and this allows + # the pod to show that better. This test isn't valid + # if this is an early Unicode release without the scx + # property (having that also implies the sc property + # exists, so don't have to test for no 'sc') + && ( ! defined $scx + && ! ( ( $self->property == $script + || $self->property == $scx) + && ( $self->property == $script + || $self->property == $scx)))) { Carp::my_carp_bug("set_equivalent_to should have 'Related => 0 for equivalencing two Unicode properties. Assuming $self is not related to $other"); $related = 0; @@ -8134,6 +8257,15 @@ sub trace { return main::trace(@_); } } my $addr = do { no overloading; pack 'J', $self; }; $complement{$addr} = $other; + + # Be sure the other property knows we are depending on them; or the + # other table if it is one in the current property. + if ($self->property != $other->property) { + $other->property->set_has_dependency(1); + } + else { + $other->set_has_dependency(1); + } $self->lock; return; } @@ -8177,6 +8309,235 @@ sub trace { return main::trace(@_); } return; } + sub calculate_table_definition + { + # Returns a human-readable string showing some or all of the code + # points matched by this table. The string will include a + # bracketed-character class for all characters matched in the 00-FF + # range, and the first few ranges matched beyond that. + my $max_ranges = 6; + + my $self = shift; + my $definition = $self->definition || ""; + + # Skip this if already have a definition. + return $definition if $definition; + + my $lows_string = ""; # The string representation of the 0-FF + # characters + my $string_range = ""; # The string rep. of the above FF ranges + my $range_count = 0; # How many ranges in $string_rage + + my @lows_invlist; # The inversion list of the 0-FF code points + my $first_non_control = ord(" "); # Everything below this is a + # control, on ASCII or EBCDIC + my $max_table_code_point = $self->max; + + # On ASCII platforms, the range 80-FF contains no printables. + my $highest_printable = ((main::NON_ASCII_PLATFORM) ? 255 : 126); + + + # Look through the first few ranges matched by this table. + $self->reset_each_range; # Defensive programming + while (defined (my $range = $self->each_range())) { + my $start = $range->start; + my $end = $range->end; + + # Accumulate an inversion list of the 00-FF code points + if ($start < 256 && ($start > 0 || $end < 256)) { + push @lows_invlist, $start; + push @lows_invlist, 1 + (($end < 256) ? $end : 255); + + # Get next range if there are more ranges below 256 + next if $end < 256 && $end < $max_table_code_point; + + # If the range straddles the 255/256 boundary, we split it + # there. We already added above the low portion to the + # inversion list + $start = 256 if $end > 256; + } + + # Here, @lows_invlist contains the code points below 256, and + # there is no other range, or the current one starts at or above + # 256. Generate the [char class] for the 0-255 ones. + while (@lows_invlist) { + + # If this range (necessarily the first one, by the way) starts + # at 0 ... + if ($lows_invlist[0] == 0) { + + # If it ends within the block of controls, that means that + # some controls are in it and some aren't. Since Unicode + # properties pretty much only know about a few of the + # controls, like \n, \t, this means that its one of them + # that isn't in the range. Complement the inversion list + # which will likely cause these to be output using their + # mnemonics, hence being clearer. + if ($lows_invlist[1] < $first_non_control) { + $lows_string .= '^'; + shift @lows_invlist; + push @lows_invlist, 256; + } + elsif ($lows_invlist[1] <= $highest_printable) { + + # Here, it extends into the printables block. Split + # into two ranges so that the controls are separate. + $lows_string .= sprintf "\\x00-\\x%02x", + $first_non_control - 1; + $lows_invlist[0] = $first_non_control; + } + } + + # If the range completely contains the printables, don't + # individually spell out the printables. + if ( $lows_invlist[0] <= $first_non_control + && $lows_invlist[1] > $highest_printable) + { + $lows_string .= sprintf "\\x%02x-\\x%02x", + $lows_invlist[0], $lows_invlist[1] - 1; + shift @lows_invlist; + shift @lows_invlist; + next; + } + + # Here, the range may include some but not all printables. + # Look at each one individually + foreach my $ord (shift @lows_invlist .. shift(@lows_invlist) - 1) { + my $char = chr $ord; + + # If there is already something in the list, an + # alphanumeric char could be the next in sequence. If so, + # we start or extend a range. That is, we could have so + # far something like 'a-c', and the next char is a 'd', so + # we change it to 'a-d'. We use native_to_unicode() + # because a-z on EBCDIC means 26 chars, and excludes the + # gap ones. + if ($lows_string ne "" && $char =~ /[[:alnum:]]/) { + my $prev = substr($lows_string, -1); + if ( $prev !~ /[[:alnum:]]/ + || utf8::native_to_unicode(ord $prev) + 1 + != utf8::native_to_unicode(ord $char)) + { + # Not extending the range + $lows_string .= $char; + } + elsif ( length $lows_string > 1 + && substr($lows_string, -2, 1) eq '-') + { + # We had a sequence like '-c' and the current + # character is 'd'. Extend the range. + substr($lows_string, -1, 1) = $char; + } + else { + # We had something like 'd' and this is 'e'. + # Start a range. + $lows_string .= "-$char"; + } + } + elsif ($char =~ /[[:graph:]]/) { + + # We output a graphic char as-is, preceded by a + # backslash if it is a metacharacter + $lows_string .= '\\' + if $char =~ /[\\\^\$\@\%\|()\[\]\{\}\-\/"']/; + $lows_string .= $char; + } # Otherwise use mnemonic for any that have them + elsif ($char =~ /[\a]/) { + $lows_string .= '\a'; + } + elsif ($char =~ /[\b]/) { + $lows_string .= '\b'; + } + elsif ($char eq "\e") { + $lows_string .= '\e'; + } + elsif ($char eq "\f") { + $lows_string .= '\f'; + } + elsif ($char eq "\cK") { + $lows_string .= '\cK'; + } + elsif ($char eq "\n") { + $lows_string .= '\n'; + } + elsif ($char eq "\r") { + $lows_string .= '\r'; + } + elsif ($char eq "\t") { + $lows_string .= '\t'; + } + else { + + # Here is a non-graphic without a mnemonic. We use \x + # notation. But if the ordinal of this is one above + # the previous, create or extend the range + my $hex_representation = sprintf("%02x", ord $char); + if ( length $lows_string >= 4 + && substr($lows_string, -4, 2) eq '\\x' + && hex(substr($lows_string, -2)) + 1 == ord $char) + { + if ( length $lows_string >= 5 + && substr($lows_string, -5, 1) eq '-' + && ( length $lows_string == 5 + || substr($lows_string, -6, 1) ne '\\')) + { + substr($lows_string, -2) = $hex_representation; + } + else { + $lows_string .= '-\\x' . $hex_representation; + } + } + else { + $lows_string .= '\\x' . $hex_representation; + } + } + } + } + + # Done with assembling the string of all lows. If there are only + # lows in the property, are completely done. + if ($max_table_code_point < 256) { + $self->reset_each_range; + last; + } + + # Otherwise, quit if reached max number of non-lows ranges. If + # there are lows, count them as one unit towards the maximum. + $range_count++; + if ($range_count > (($lows_string eq "") ? $max_ranges : $max_ranges - 1)) { + $string_range .= " ..."; + $self->reset_each_range; + last; + } + + # Otherwise add this range. + $string_range .= ", " if $string_range ne ""; + if ($start == $end) { + $string_range .= sprintf("U+%04X", $start); + } + elsif ($end >= $MAX_WORKING_CODEPOINT) { + $string_range .= sprintf("U+%04X..infinity", $start); + } + else { + $string_range .= sprintf("U+%04X..%04X", + $start, $end); + } + } + + # Done with all the ranges we're going to look at. Assemble the + # definition from the lows + non-lows. + + if ($lows_string ne "" || $string_range ne "") { + if ($lows_string ne "") { + $definition .= "[$lows_string]"; + $definition .= ", " if $string_range; + } + $definition .= $string_range; + } + + return $definition; + } + sub write { my $self = shift; Carp::carp_extra_args(\@_) if main::DEBUG && @_; @@ -8720,6 +9081,15 @@ sub trace { return main::trace(@_) if main::DEBUG && $to_trace } main::set_access('pre_declared_maps', \%pre_declared_maps, 'r', 's'); + my %has_dependency; + # A boolean that gives whether some table somewhere is defined as the + # complement of a table in this property. This is a crude, but currently + # sufficient, mechanism to make this property not get destroyed before + # what is dependent on it is. Other dependencies could be added, so the + # name was chosen to reflect a more general situation than actually is + # currently the case. + main::set_access('has_dependency', \%has_dependency, 'r', 's'); + sub new { # The only required parameter is the positionally first, name. All # other parameters are key => value pairs. See the documentation just @@ -8758,6 +9128,7 @@ sub trace { return main::trace(@_) if main::DEBUG && $to_trace } $has_only_code_point_maps{$addr} = 1; $table_ref{$addr} = { }; $unique_maps{$addr} = { }; + $has_dependency{$addr} = 0; $map{$addr} = Map_Table->new($name, Full_Name => $full_name{$addr}, @@ -9252,6 +9623,7 @@ sub trace { return main::trace(@_) if main::DEBUG && $to_trace } containing_range count default_map + definition delete_range description each_range @@ -9270,6 +9642,7 @@ sub trace { return main::trace(@_) if main::DEBUG && $to_trace } range_count ranges range_size_1 + replace_map reset_each_range set_comment set_default_map @@ -11645,7 +12018,16 @@ END . $CMD_DELIM . $fields[$CHARNAME]; } - elsif ($fields[$CHARNAME] =~ /^CJK/) { + elsif ($fields[$CATEGORY] eq 'Lo') { # Is a letter + + # All the CJK ranges like this have the name given as a + # special case in the next code line. And for the others, we + # hope that Unicode continues to use the correct name in + # future releases, so we don't have to make further special + # cases. + my $name = ($fields[$CHARNAME] =~ /^CJK/) + ? 'CJK UNIFIED IDEOGRAPH' + : uc $fields[$CHARNAME]; # The name for these contains the code point itself, and all # are defined to have the same base name, regardless of what @@ -11657,7 +12039,7 @@ END . '=' . $CP_IN_NAME . $CMD_DELIM - . 'CJK UNIFIED IDEOGRAPH'; + . $name; } elsif ($fields[$CATEGORY] eq 'Co' @@ -13035,9 +13417,9 @@ sub setup_script_extensions { # The Script_Extensions property starts out with a clone of the Script # property. - my $scx = property_ref("Script_Extensions"); - $scx = Property->new("scx", Full_Name => "Script_Extensions") - if ! defined $scx; + $scx = property_ref("Script_Extensions"); + return unless defined $scx; + $scx->_set_format($STRING_WHITE_SPACE_LIST); $scx->initialize($script); $scx->set_default_map($script->default_map); @@ -13273,7 +13655,7 @@ sub filter_all_caps_script_names { my ($range, $script, @remainder) = split /\s*;\s*/, $_, -1; # -1 => retain trailing null fields - my @words = split "_", $script; + my @words = split /[_-]/, $script; for my $word (@words) { $word = ucfirst(lc($word)) if $word ne 'CJK'; @@ -13593,6 +13975,18 @@ numerals. END )); + # Make sure this assumption in perl core code is valid in this Unicode + # release, with known exceptions + foreach my $range (property_ref('Numeric-Type')->table('Decimal')->ranges) { + next if $range->end - $range->start == 9; + next if $range->start == 0x1D7CE; # This whole range was added in 3.1 + next if $range->end == 0x19DA && $v_version eq v5.2.0; + next if $range->end - $range->start < 9 && $v_version le 4.0.0; + Carp::my_carp("Range $range unexpectedly doesn't contain 10" + . " decimal digits. Code in regcomp.c assumes it does," + . " and will have to be fixed. Proceeding anyway."); + } + Property->new('Legacy_Case_Folding', File => "Fold", Directory => $map_directory, @@ -13618,7 +14012,6 @@ END # data is retained in the map table for reference, but the spurious match # tables are deleted. - my $scx = property_ref("Script_Extensions"); if (defined $scx) { foreach my $table ($scx->tables) { next unless $table->name =~ /\s/; # All the new and only the new @@ -13631,6 +14024,21 @@ END } $scx->delete_match_table($table); } + + # Mark the scx table as the parent of the corresponding sc table for + # those which are identical. This causes the pod for the script table + # to refer to the corresponding scx one. + # + # This has to be in a separate loop from above, so as to wait until + # the tables are stabilized before checking for equivalency. + if (defined $pod_directory) { + foreach my $table ($scx->tables) { + my $plain_sc_equiv = $script->table($table->name); + if ($table->matches_identically_to($plain_sc_equiv)) { + $plain_sc_equiv->set_equivalent_to($table, Related => 1); + } + } + } } return; @@ -13780,8 +14188,10 @@ sub handle_compare_versions () { # since the first compare version. my $delta = Range_List->new(); foreach my $table ($age->tables) { + use version; next if $table == $age->table('Unassigned'); - next if $table->name le $string_compare_versions; + next if version->parse($table->name) + le version->parse($string_compare_versions); $delta += $table; } if ($delta->is_empty) { @@ -13804,6 +14214,9 @@ sub handle_compare_versions () { next if $this_block == $no_block || ! ($this_block & $Assigned)->is_empty; $this_block->set_fate($SUPPRESSED, $after_first_version); + foreach my $range ($this_block->ranges) { + $block->replace_map($range->start, $range->end, 'No_Block') + } $no_block += $this_block; } @@ -14050,8 +14463,7 @@ sub compile_perl() { } my $Any = $perl->add_match_table('Any', - Description => "All Unicode code points: [\\x{0000}-\\x{$MAX_UNICODE_CODEPOINT_STRING}]", - ); + Description => "All Unicode code points"); $Any->add_range(0, $MAX_UNICODE_CODEPOINT); $Any->add_alias('Unicode'); @@ -14064,7 +14476,7 @@ sub compile_perl() { ->set_equivalent_to(property_ref('ccc')->table('Above'), Related => 1); - my $ASCII = $perl->add_match_table('ASCII', Description => '[[:ASCII:]]'); + my $ASCII = $perl->add_match_table('ASCII'); if (defined $block) { # This is equivalent to the block if have it. my $Unicode_ASCII = $block->table('Basic_Latin'); if (defined $Unicode_ASCII && ! $Unicode_ASCII->is_empty) { @@ -14124,7 +14536,6 @@ sub compile_perl() { $Lower += $temp & $Assigned; } my $Posix_Lower = $perl->add_match_table("PosixLower", - Description => "[a-z]", Initialize => $Lower & $ASCII, ); @@ -14142,7 +14553,6 @@ sub compile_perl() { $Upper->add_range(0x24B6, 0x24CF); # Circled Latin upper case letters } my $Posix_Upper = $perl->add_match_table("PosixUpper", - Description => "[A-Z]", Initialize => $Upper & $ASCII, ); @@ -14350,7 +14760,6 @@ sub compile_perl() { $Alpha->add_alias('Alphabetic'); } my $Posix_Alpha = $perl->add_match_table("PosixAlpha", - Description => "[A-Za-z]", Initialize => $Alpha & $ASCII, ); $Posix_Upper->set_caseless_equivalent($Posix_Alpha); @@ -14361,13 +14770,13 @@ sub compile_perl() { Initialize => $Alpha + $gc->table('Decimal_Number'), ); $perl->add_match_table("PosixAlnum", - Description => "[A-Za-z0-9]", Initialize => $Alnum & $ASCII, ); my $Word = $perl->add_match_table('Word', Full_Name => 'XPosixWord', Description => '\w, including beyond ASCII;' - . ' = \p{Alnum} + \pM + \p{Pc}', + . ' = \p{Alnum} + \pM + \p{Pc}' + . ' + \p{Join_Control}', Initialize => $Alnum + $gc->table('Mark'), ); my $Pc = $gc->table('Connector_Punctuation'); # 'Pc' Not in release 1 @@ -14387,7 +14796,7 @@ sub compile_perl() { # This is a Perl extension, so the name doesn't begin with Posix. my $PerlWord = $perl->add_match_table('PosixWord', - Description => '\w, restricted to ASCII = [A-Za-z0-9_]', + Description => '\w, restricted to ASCII', Initialize => $Word & $ASCII, ); $PerlWord->add_alias('PerlWord'); @@ -14404,7 +14813,6 @@ sub compile_perl() { ); $Blank->add_alias('HorizSpace'); # Another name for it. $perl->add_match_table("PosixBlank", - Description => "\\t and ' '", Initialize => $Blank & $ASCII, ); @@ -14430,7 +14838,6 @@ sub compile_perl() { $Space->add_alias('Space') if $v_version lt v4.1.0; my $Posix_space = $perl->add_match_table("PosixSpace", - Description => "\\t, \\n, \\cK, \\f, \\r, and ' '. (\\cK is vertical tab)", Initialize => $Space & $ASCII, ); $Posix_space->add_alias('PerlSpace'); # A pre-existing synonym @@ -14439,7 +14846,12 @@ sub compile_perl() { Description => 'Control characters'); $Cntrl->set_equivalent_to($gc->table('Cc'), Related => 1); $perl->add_match_table("PosixCntrl", - Description => "ASCII control characters: NUL, SOH, STX, ETX, EOT, ENQ, ACK, BEL, BS, HT, LF, VT, FF, CR, SO, SI, DLE, DC1, DC2, DC3, DC4, NAK, SYN, ETB, CAN, EOM, SUB, ESC, FS, GS, RS, US, and DEL", + Description => "ASCII control characters", + Definition => "ACK, BEL, BS, CAN, CR, DC1, DC2," + . " DC3, DC4, DEL, DLE, ENQ, EOM," + . " EOT, ESC, ETB, ETX, FF, FS, GS," + . " HT, LF, NAK, NUL, RS, SI, SO," + . " SOH, STX, SUB, SYN, US, VT", Initialize => $Cntrl & $ASCII, ); @@ -14463,8 +14875,6 @@ sub compile_perl() { Initialize => ~ ($Space + $controls), ); $perl->add_match_table("PosixGraph", - Description => - '[-!"#$%&\'()*+,./:;<=>?@[\\\]^_`{|}~0-9A-Za-z]', Initialize => $Graph & $ASCII, ); @@ -14473,8 +14883,6 @@ sub compile_perl() { Initialize => $Blank + $Graph - $gc->table('Control'), ); $perl->add_match_table("PosixPrint", - Description => - '[- 0-9A-Za-z!"#$%&\'()*+,./:;<=>?@[\\\]^_`{|}~]', Initialize => $print & $ASCII, ); @@ -14489,7 +14897,6 @@ sub compile_perl() { Perl_Extension => 1 ); $perl->add_match_table('PosixPunct', Perl_Extension => 1, - Description => '[-!"#$%&\'()*+,./:;<=>?@[\\\]^_`{|}~]', Initialize => $ASCII & $XPosixPunct, ); @@ -14497,7 +14904,6 @@ sub compile_perl() { Description => '[0-9] + all other decimal digits'); $Digit->set_equivalent_to($gc->table('Decimal_Number'), Related => 1); my $PosixDigit = $perl->add_match_table("PosixDigit", - Description => '[0-9]', Initialize => $Digit & $ASCII, ); @@ -14512,7 +14918,6 @@ sub compile_perl() { ord('A') .. ord('F'), ord('a') .. ord('f'), 0xFF10..0xFF19, 0xFF21..0xFF26, 0xFF41..0xFF46]); - $Xdigit->add_description('[0-9A-Fa-f] and corresponding fullwidth versions, like U+FF10: FULLWIDTH DIGIT ZERO'); } # AHex was not present in early releases @@ -14526,7 +14931,6 @@ sub compile_perl() { $PosixXDigit->add_alias('AHex'); $PosixXDigit->add_alias('Ascii_Hex_Digit'); } - $PosixXDigit->add_description('[0-9A-Fa-f]'); my $any_folds = $perl->add_match_table("_Perl_Any_Folds", Description => "Code points that particpate in some fold", @@ -14802,7 +15206,6 @@ sub compile_perl() { + ord("(") + ord(")") + ord("-") - + utf8::unicode_to_native(0xA0) # NBSP ); my @composition = ('Name', 'Unicode_1_Name', '_Perl_Name_Alias'); @@ -14983,6 +15386,9 @@ END . $current_age->name . ' or earlier', ); + foreach my $alias ($current_age->aliases) { + $current_in->add_alias($alias->name); + } $previous_in = $current_in; # Add clarifying material for the corresponding age file. This is @@ -15204,6 +15610,71 @@ END } } + # This property is a modification of the scx property + my $perl_scx = Property->new('_Perl_SCX', + Fate => $INTERNAL_ONLY, + Perl_Extension => 1, + Directory => $map_directory, + Type => $ENUM); + my $source; + + # Use scx if available; otherwise sc; if neither is there (a very old + # Unicode version, just say that everything is 'Common' + if (defined $scx) { + $source = $scx; + $perl_scx->set_default_map('Unknown'); + } + elsif (defined $script) { + $source = $script; + + # Early versions of 'sc', had everything be 'Common' + if (defined $script->table('Unknown')) { + $perl_scx->set_default_map('Unknown'); + } + else { + $perl_scx->set_default_map('Common'); + } + } else { + $perl_scx->add_match_table('Common'); + $perl_scx->add_map(0, $MAX_UNICODE_CODEPOINT, 'Common'); + + $perl_scx->add_match_table('Unknown'); + $perl_scx->set_default_map('Unknown'); + } + + $perl_scx->_set_format($STRING_WHITE_SPACE_LIST); + $perl_scx->set_pre_declared_maps(0); # PropValueAliases doesn't list these + + if (defined $source) { + $perl_scx->initialize($source); + + # UTS 39 says that the scx property should be modified for these + # countries where certain mixed scripts are commonly used. + for my $range ($perl_scx->ranges) { + my $value = $range->value; + my $changed = $value =~ s/ ( \b Han i? \b ) /$1 Hanb Jpan Kore/xi; + $changed |= $value =~ s/ ( \b Hira (gana)? \b ) /$1 Jpan/xi; + $changed |= $value =~ s/ ( \b Kata (kana)? \b ) /$1 Jpan/xi; + $changed |= $value =~ s{ ( \b Katakana_or_Hiragana \b ) } + {$1 Katakana Hiragana Jpan}xi; + $changed |= $value =~ s/ ( \b Hang (ul)? \b ) /$1 Kore/xi; + $changed |= $value =~ s/ ( \b Bopo (mofo)? \b ) /$1 Hanb/xi; + + if ($changed) { + $value = join " ", uniques split " ", $value; + $range->set_value($value) + } + } + + foreach my $table ($source->tables) { + my $scx_table = $perl_scx->add_match_table($table->name, + Full_Name => $table->full_name); + foreach my $alias ($table->aliases) { + $scx_table->add_alias($alias->name); + } + } + } + # Here done with all the basic stuff. Ready to populate the information # about each character if annotating them. if ($annotate) { @@ -15231,7 +15702,7 @@ sub add_perl_synonyms() { # the single-form, \p{name}. These are: # All the binary property Y tables, so that \p{Name=Y} gets \p{Name} and # \p{Is_Name} as synonyms - # \p{Script=Value} gets \p{Value}, \p{Is_Value} as synonyms + # \p{Script_Extensions=Value} gets \p{Value}, \p{Is_Value} as synonyms # \p{General_Category=Value} gets \p{Value}, \p{Is_Value} as synonyms # \p{Block=Value} gets \p{In_Value} as a synonym, and, if there is no # conflict, \p{Value} and \p{Is_Value} as well @@ -15245,8 +15716,14 @@ sub add_perl_synonyms() { property_ref('*'); push @tables, $gc->tables; - # If the version of Unicode includes the Script property, add its tables - push @tables, $script->tables if defined $script; + # If the version of Unicode includes the Script Extensions (preferably), + # or Script property, add its tables + if (defined $scx) { + push @tables, $scx->tables; + } + else { + push @tables, $script->tables if defined $script; + } # The Block tables are kept separate because they are treated differently. # And the earliest versions of Unicode didn't include them, so add only if @@ -15309,7 +15786,7 @@ sub add_perl_synonyms() { if (! defined $pre_existing) { - # No name collision, so ok to add the perl synonym. + # No name collision, so OK to add the perl synonym. my $make_re_pod_entry; my $ok_as_filename; @@ -15404,7 +15881,7 @@ sub add_perl_synonyms() { next; } - # Here, there is a name collision, but it still could be ok if + # Here, there is a name collision, but it still could be OK if # the tables match the identical set of code points, in which # case, we can combine the names. Compare each table's code # point list to see if they are identical. @@ -15905,7 +16382,18 @@ sub make_re_pod_entries($) { $unicode_count = $count; $non_unicode_string = ""; } + my $string_count = clarify_number($unicode_count) . $non_unicode_string; + + my $definition = $input_table->calculate_table_definition; + if ($definition) { + + # Save the definition for later use. + $input_table->set_definition($definition); + + $definition = ": $definition"; + } + my $status = $input_table->status; my $status_info = $input_table->status_info; my $caseless_equivalent = $input_table->caseless_equivalent; @@ -16200,7 +16688,10 @@ sub make_re_pod_entries($) { if ($table_property != $perl && $table->perl_extension) { push @info, '(Perl extension)'; } - push @info, "($string_count)"; + my $definition = $table->definition // ""; + $definition = "" if $entry_for_first_alias; + $definition = ": $definition" if $definition; + push @info, "($string_count$definition)"; # Now, we have both the entry and info so add them to the # list of all the properties. @@ -16243,39 +16734,50 @@ sub make_ucd_table_pod_entries { : $table->parent->property; my $perl_extension = $table->perl_extension; + my $is_perl_extension_match_table_but_not_dollar_perl + = $property != $perl + && $perl_extension + && $property != $table; # Get the more official name for for perl extensions that aren't # stand-alone properties - if ($perl_extension && $property != $table) { - if ($property == $perl ||$property->type == $BINARY) { - $meaning = $table->complete_name; + if ($is_perl_extension_match_table_but_not_dollar_perl) { + if ($property->type == $BINARY) { + $meaning = $property->full_name; } else { - $meaning = $property->full_name . "=$full_name"; + $meaning = $table->parent->complete_name; } } # There are three types of info column. One for the short name, one for # the full name, and one for everything else. They mostly are the same, # so initialize in the same loop. + foreach my $info_ref (\$full_info, \$short_info, \$other_info) { - if ($perl_extension && $property != $table) { + if ($info_ref != \$full_info) { + + # The non-full name columns include the full name + $$info_ref .= $full_name; + } + + + if ($is_perl_extension_match_table_but_not_dollar_perl) { # Add the synonymous name for the non-full name entries; and to # the full-name entry if it adds extra information - if ($info_ref == \$other_info - || ($info_ref == \$short_info - && $standard_short_name ne $standard_full_name) - || standardize($meaning) ne $standard_full_name - ) { - $$info_ref .= "$meaning."; + if ( standardize($meaning) ne $standard_full_name + || $info_ref == \$other_info + || $info_ref == \$short_info) + { + my $parenthesized = $info_ref != \$full_info; + $$info_ref .= " " if $$info_ref && $parenthesized; + $$info_ref .= "(=" if $parenthesized; + $$info_ref .= "$meaning"; + $$info_ref .= ")" if $parenthesized; + $$info_ref .= "."; } } - elsif ($info_ref != \$full_info) { - - # Otherwise, the non-full name columns include the full name - $$info_ref .= $full_name; - } # And the full-name entry includes the short name, if shorter if ($info_ref == \$full_info @@ -16293,8 +16795,23 @@ sub make_ucd_table_pod_entries { } } + my $definition; + my $definition_table; + my $type = $table->property->type; + if ($type == $BINARY || $type == $FORCED_BINARY) { + $definition_table = $table->property->table('Y'); + } + elsif ($table->isa('Match_Table')) { + $definition_table = $table; + } + + $definition = $definition_table->calculate_table_definition + if defined $definition_table + && $definition_table != 0; + # Add any extra annotations to the full name entry foreach my $more_info ($table->description, + $definition, $table->note, $table->status_info) { @@ -16370,7 +16887,7 @@ sub make_ucd_table_pod_entries { Carp::my_carp("Bad news. $property and $ucd_pod{$standard}->{'property'} have unexpected output status and perl-extension combinations. Proceeding anyway."); } - # We modifiy the info column of the one being output to + # We modify the info column of the one being output to # indicate the ambiguity. Set $which to point to that one's # info. my $which; @@ -16432,27 +16949,69 @@ sub pod_alphanumeric_sort { return -1 } - # Determine if the two operands are numeric property values or not. - # A numeric property will look like xyz: 3. But the number - # can begin with an optional minus sign, and may have a - # fraction or rational component, like xyz: 3/2. If either - # isn't numeric, use alphabetic sort. - my ($a_initial, $a_number) = - ($a =~ /^ ( [^:=]+ [:=] \s* ) (-? \d+ (?: [.\/] \d+)? )/ix); - return $a cmp $b unless defined $a_number; - my ($b_initial, $b_number) = - ($b =~ /^ ( [^:=]+ [:=] \s* ) (-? \d+ (?: [.\/] \d+)? )/ix); - return $a cmp $b unless defined $b_number; - - # Here they are both numeric, but use alphabetic sort if the - # initial parts don't match - return $a cmp $b if $a_initial ne $b_initial; + # Determine if the two operands are compound or not, and if so if are + # "numeric" property values or not, like \p{Age: 3.0}. But there are also + # things like \p{Canonical_Combining_Class: CCC133} and \p{Age: V10_0}, + # all of which this considers numeric, and for sorting, looks just at the + # numeric parts. It can also be a rational like \p{Numeric Value=-1/2}. + my $split_re = qr/ + ^ ( [^:=]+ ) # $1 is undef if not a compound form, otherwise is the + # property name + [:=] \s* # The syntax for the compound form + (?: # followed by ... + ( # $2 gets defined if what follows is a "numeric" + # expression, which is ... + ( -? \d+ (?: [.\/] \d+)? # An integer, float, or rational + # number, optionally signed + | [[:alpha:]]{2,} \d+ $ ) # or something like CCC131. Either + # of these go into $3 + | ( V \d+ _ \d+ ) # or a Unicode's Age property version + # number, into $4 + ) + | .* $ # If not "numeric", accept anything so that $1 gets + # defined if it is any compound form + ) /ix; + my ($a_initial, $a_numeric, $a_number, $a_version) = ($a =~ $split_re); + my ($b_initial, $b_numeric, $b_number, $b_version) = ($b =~ $split_re); + + # Sort alphabeticlly on the whole property name if either operand isn't + # compound, or they differ. + return $a cmp $b if ! defined $a_initial + || ! defined $b_initial + || $a_initial ne $b_initial; + + if (! defined $a_numeric) { + + # If neither is numeric, use alpha sort + return $a cmp $b if ! defined $b_numeric; + return 1; # Sort numeric ahead of alpha + } + + # Here $a is numeric + return -1 if ! defined $b_numeric; # Numeric sorts before alpha + + # Here they are both numeric in the same property. + # Convert version numbers into regular numbers + if (defined $a_version) { + ($a_number = $a_version) =~ s/^V//i; + $a_number =~ s/_/./; + } + else { # Otherwise get rid of the, e.g., CCC in CCC9 */ + $a_number =~ s/ ^ [[:alpha:]]+ //x; + } + if (defined $b_version) { + ($b_number = $b_version) =~ s/^V//i; + $b_number =~ s/_/./; + } + else { + $b_number =~ s/ ^ [[:alpha:]]+ //x; + } # Convert rationals to floating for the comparison. $a_number = eval $a_number if $a_number =~ qr{/}; $b_number = eval $b_number if $b_number =~ qr{/}; - return $a_number <=> $b_number; + return $a_number <=> $b_number || $a cmp $b; } sub make_pod () { @@ -16625,7 +17184,7 @@ END push @bad_re_properties, "\n=back\n"; } - # Similiarly, generate a list of files that we don't use, grouped by the + # Similarly, generate a list of files that we don't use, grouped by the # reasons why (Don't output if the reason is empty). First, create a hash # whose keys are the reasons, and whose values are anonymous arrays of all # the files that share that reason. @@ -16678,6 +17237,7 @@ END $ucd_pod = format_pod_line($indent_info_column, 'NAME', ' INFO') . "\n" . $ucd_pod; + my $space_hex = sprintf("%02x", ord " "); local $" = ""; # Everything is ready to assemble. @@ -16738,14 +17298,16 @@ constructs, both single and compound forms. B<Compound forms> consist of two components, separated by an equals sign or a colon. The first component is the property name, and the second component is the particular value of the property to match against, for example, -C<\\p{Script: Greek}> and C<\\p{Script=Greek}> both mean to match characters -whose Script property value is Greek. +C<\\p{Script_Extensions: Greek}> and C<\\p{Script_Extensions=Greek}> both mean +to match characters whose Script_Extensions property value is Greek. +(C<Script_Extensions> is an improved version of the C<Script> property.) B<Single forms>, like C<\\p{Greek}>, are mostly Perl-defined shortcuts for their equivalent compound forms. The table shows these equivalences. (In our -example, C<\\p{Greek}> is a just a shortcut for C<\\p{Script=Greek}>.) -There are also a few Perl-defined single forms that are not shortcuts for a -compound form. One such is C<\\p{Word}>. These are also listed in the table. +example, C<\\p{Greek}> is a just a shortcut for +C<\\p{Script_Extensions=Greek}>). There are also a few Perl-defined single +forms that are not shortcuts for a compound form. One such is C<\\p{Word}>. +These are also listed in the table. In parsing these constructs, Perl always ignores Upper/lower case differences everywhere within the {braces}. Thus C<\\p{Greek}> means the same thing as @@ -16869,8 +17431,16 @@ All single forms are Perl extensions; a few compound forms are as well, and are noted as such. Numbers in (parentheses) indicate the total number of Unicode code points -matched by the property. For emphasis, those properties that match no code -points at all are listed as well in a separate section following the table. +matched by the property. For the entries that give the longest, most +descriptive version of the property, the count is followed by a list of some +of the code points matched by it. The list includes all the matched +characters in the 0-255 range, enclosed in the familiar [brackets] the same as +a regular expression bracketed character class. Following that, the next few +higher matching ranges are also given. To avoid visual ambiguity, the SPACE +character is represented as C<\\x$space_hex>. + +For emphasis, those properties that match no code points at all are listed as +well in a separate section following the table. Most properties match the same code points regardless of whether C<"/i"> case-insensitive matching is specified or not. But a few properties are @@ -16913,34 +17483,20 @@ B<Legend summary:> =over 4 -=item * - -B<*> is a wild-card +=item Z<>B<*> is a wild-card -=item * - -B<(\\d+)> in the info column gives the number of Unicode code points matched +=item B<(\\d+)> in the info column gives the number of Unicode code points matched by this property. -=item * - -B<$DEPRECATED> means this is deprecated. - -=item * - -B<$OBSOLETE> means this is obsolete. - -=item * +=item B<$DEPRECATED> means this is deprecated. -B<$STABILIZED> means this is stabilized. +=item B<$OBSOLETE> means this is obsolete. -=item * +=item B<$STABILIZED> means this is stabilized. -B<$STRICTER> means tighter (stricter) name matching applies. +=item B<$STRICTER> means tighter (stricter) name matching applies. -=item * - -B<$DISCOURAGED> means use of this form is discouraged, and may not be +=item B<$DISCOURAGED> means use of this form is discouraged, and may not be stable. =back @@ -16989,7 +17545,11 @@ an alternative name, if any, plus possibly some annotations. The alternative name is the property's full name, unless that would simply repeat the first column, in which case the second column indicates the property's short name (if different). The annotations are given only in the entry for the full -name. If a property is obsolete, etc, the entry will be flagged with the same +name. The annotations for binary properties include a list of the first few +ranges that the property matches. To avoid any ambiguity, the SPACE character +is represented as C<\\x$space_hex>. + +If a property is obsolete, etc, the entry will be flagged with the same characters used in the table in the L<section above|/Properties accessible through \\p{} and \\P{}>, like B<$DEPRECATED> or B<$STABILIZED>. @@ -17550,7 +18110,7 @@ sub make_UCD () { foreach my $prop_alias ($property->aliases) { my $prop_alias_name = standardize($prop_alias->name); - # If no =value, there's just one combination possibe for this + # If no =value, there's just one combination possible for this if (! $value_name) { # The property may be suppressed, but there may be a proxy @@ -17942,19 +18502,20 @@ sub write_all_tables() { # the children. make_re_pod_entries($table) if defined $pod_directory; - # See if the the table matches identical code points with - # something that has already been output. In that case, - # no need to have two files with the same code points in - # them. We use the table's hash() method to store these - # in buckets, so that it is quite likely that if two - # tables are in the same bucket they will be identical, so - # don't have to compare tables frequently. The tables - # have to have the same status to share a file, so add - # this to the bucket hash. (The reason for this latter is - # that Heavy.pl associates a status with a file.) - # We don't check tables that are inverses of others, as it - # would lead to some coding complications, and checking - # all the regular ones should find everything. + # See if the table matches identical code points with + # something that has already been processed and is ready + # for output. In that case, no need to have two files + # with the same code points in them. We use the table's + # hash() method to store these in buckets, so that it is + # quite likely that if two tables are in the same bucket + # they will be identical, so don't have to compare tables + # frequently. The tables have to have the same status to + # share a file, so add this to the bucket hash. (The + # reason for this latter is that Heavy.pl associates a + # status with a file.) We don't check tables that are + # inverses of others, as it would lead to some coding + # complications, and checking all the regular ones should + # find everything. if ($table->complement == 0) { my $hash = $table->hash . ';' . $table->status; @@ -17963,7 +18524,11 @@ sub write_all_tables() { foreach my $comparison (@{$match_tables_to_write{$hash}}) { - if ($table->matches_identically_to($comparison)) { + # If the table doesn't point back to this one, we + # see if it matches identically + if ( $comparison->leader != $table + && $table->matches_identically_to($comparison)) + { $table->set_equivalent_to($comparison, Related => 0); next TABLE; @@ -18105,7 +18670,7 @@ sub write_all_tables() { # the table. That is, all the property-values given # by this table. By agreement with Unicode::UCD, # if the name and full name are identical, and there - # are no other names, drop the duplcate entry to save + # are no other names, drop the duplicate entry to save # memory. if (@values_list == 2 && $values_list[0] eq $values_list[1]) @@ -18269,14 +18834,14 @@ sub generate_separator($) { sub generate_tests($$$$$) { # This used only for making the test script. It generates test cases that - # are expected to compile successfully in perl. Note that the lhs and - # rhs are assumed to already be as randomized as the caller wants. + # are expected to compile successfully in perl. Note that the LHS and + # RHS are assumed to already be as randomized as the caller wants. my $lhs = shift; # The property: what's to the left of the colon # or equals separator my $rhs = shift; # The property value; what's to the right my $valid_code = shift; # A code point that's known to be in the - # table given by lhs=rhs; undef if table is + # table given by LHS=RHS; undef if table is # empty my $invalid_code = shift; # A code point known to not be in the table; # undef if the table is all code points @@ -18317,13 +18882,13 @@ sub generate_error($$$) { # colon or equals separator my $rhs = shift; # The property value; what's to the right my $already_in_error = shift; # Boolean; if true it's known that the - # unmodified lhs and rhs will cause an error. + # unmodified LHS and RHS will cause an error. # This routine should not force another one # Get the colon or equal my $separator = generate_separator($lhs); # Since this is an error only, don't bother to randomly decide whether to - # put the error on the left or right side; and assume that the rhs is + # put the error on the left or right side; and assume that the RHS is # loosely matched, again for convenience rather than rigor. $rhs = randomize_loose_name($rhs, 'ERROR') unless $already_in_error; @@ -18522,10 +19087,51 @@ sub make_property_test_script() { # or multiple lines. main::write doesn't count the lines. my @output; + push @output, <<'EOF_CODE'; +Error('\p{Script=InGreek}'); # Bug #69018 +Test_GCB("1100 $nobreak 1161"); # Bug #70940 +Expect(0, 0x2028, '\p{Print}', ""); # Bug # 71722 +Expect(0, 0x2029, '\p{Print}', ""); # Bug # 71722 +Expect(1, 0xFF10, '\p{XDigit}', ""); # Bug # 71726 + +# Make sure this gets tested; it was not part of the official test suite at +# the time this was added. Note that this is as it would appear in the +# official suite, and gets modified to check for the perl tailoring by +# Test_WB() +Test_WB("$breakable 0020 $breakable 0020 $breakable 0308 $breakable"); +Test_LB("$nobreak 200B $nobreak 0020 $nobreak 0020 $breakable 2060 $breakable"); +EOF_CODE + # Sort these so get results in same order on different runs of this # program - foreach my $property (sort { $a->name cmp $b->name } property_ref('*')) { - foreach my $table (sort { $a->name cmp $b->name } $property->tables) { + foreach my $property (sort { $a->has_dependency <=> $b->has_dependency + or + lc $a->name cmp lc $b->name + } property_ref('*')) + { + # Non-binary properties should not match \p{}; Test all for that. + if ($property->type != $BINARY) { + my @property_aliases = grep { $_->status ne $INTERNAL_ALIAS } + $property->aliases; + foreach my $property_alias ($property->aliases) { + my $name = standardize($property_alias->name); + + # But some names are ambiguous, meaning a binary property with + # the same name when used in \p{}, and a different + # (non-binary) property in other contexts. + next if grep { $name eq $_ } keys %ambiguous_names; + + push @output, <<"EOF_CODE"; +Error('\\p{$name}'); +Error('\\P{$name}'); +EOF_CODE + } + } + foreach my $table (sort { $a->has_dependency <=> $b->has_dependency + or + lc $a->name cmp lc $b->name + } $property->tables) + { # Find code points that match, and don't match this table. my $valid = $table->get_valid_code_point; @@ -18696,16 +19302,69 @@ sub make_property_test_script() { $property->DESTROY(); } + # Make any test of the boundary (break) properties TODO if the code + # doesn't match the version being compiled + my $TODO_FAILING_BREAKS = ($version_of_mk_invlist_bounds ne $v_version) + ? "\nsub TODO_FAILING_BREAKS { 1 }\n" + : "\nsub TODO_FAILING_BREAKS { 0 }\n"; + + @output= map { + map s/^/ /mgr, + map "$_;\n", + split /;\n/, $_ + } @output; + + # Cause there to be 'if' statements to only execute a portion of this + # long-running test each time, so that we can have a bunch of .t's running + # in parallel + my $chunks = 10 # Number of test files + - 1 # For GCB & SB + - 1 # For WB + - 4; # LB split into this many files + my @output_chunked; + my $chunk_count=0; + my $chunk_size= int(@output / $chunks) + 1; + while (@output) { + $chunk_count++; + my @chunk= splice @output, 0, $chunk_size; + push @output_chunked, + "if (!\$::TESTCHUNK or \$::TESTCHUNK == $chunk_count) {\n", + @chunk, + "}\n"; + } + + $chunk_count++; + push @output_chunked, + "if (!\$::TESTCHUNK or \$::TESTCHUNK == $chunk_count) {\n", + (map {" Test_GCB('$_');\n"} @backslash_X_tests), + (map {" Test_SB('$_');\n"} @SB_tests), + "}\n"; + + + $chunk_size= int(@LB_tests / 4) + 1; + @LB_tests = map {" Test_LB('$_');\n"} @LB_tests; + while (@LB_tests) { + $chunk_count++; + my @chunk= splice @LB_tests, 0, $chunk_size; + push @output_chunked, + "if (!\$::TESTCHUNK or \$::TESTCHUNK == $chunk_count) {\n", + @chunk, + "}\n"; + } + + $chunk_count++; + push @output_chunked, + "if (!\$::TESTCHUNK or \$::TESTCHUNK == $chunk_count) {\n", + (map {" Test_WB('$_');\n"} @WB_tests), + "}\n"; + &write($t_path, 0, # Not utf8; [$HEADER, + $TODO_FAILING_BREAKS, <DATA>, - @output, - (map {"Test_GCB('$_');\n"} @backslash_X_tests), - (map {"Test_LB('$_');\n"} @LB_tests), - (map {"Test_SB('$_');\n"} @SB_tests), - (map {"Test_WB('$_');\n"} @WB_tests), - "Finished();\n" + @output_chunked, + "Finished();\n", ]); return; @@ -18866,6 +19525,14 @@ my @input_file_objects = ( Property => 'Joining_Type', Has_Missings_Defaults => $NOT_IGNORED, ), + Input_file->new("${EXTRACTED}DName.txt", v10.0.0, + Skip => 'This file adds no new information not already' + . ' present in other files', + # And it's unnecessary programmer work to handle this new + # format. Previous Derived files actually had bug fixes + # in them that were useful, but that should not be the + # case here. + ), Input_file->new('Jamo.txt', v2.0.0, Property => 'Jamo_Short_Name', Each_Line_Handler => \&filter_jamo_line, @@ -19077,13 +19744,14 @@ my @input_file_objects = ( # for the release it is. To get it to actually mean # something useful, someone would have to be using an # earlier Unicode release, and copy it into the directory - # for that release and recomplile. So far there has been + # for that release and recompile. So far there has been # no demand to do that, so this hasn't been implemented. Skip => 'Documentation of corrections already ' . 'incorporated into the Unicode data base', ), Input_file->new('StandardizedVariants.html', v3.2.0, - Skip => 'Provides a visual display of the standard ' + Skip => 'Obsoleted as of Unicode 9.0, but previously ' + . 'provided a visual display of the standard ' . 'variant sequences derived from ' . 'F<StandardizedVariants.txt>.', # I don't know why the html came earlier than the @@ -19118,18 +19786,21 @@ my @input_file_objects = ( ), Input_file->new("$AUXILIARY/GCBTest.txt", v4.1.0, Handler => \&process_GCB_test, + retain_trailing_comments => 1, ), Input_file->new("$AUXILIARY/GraphemeBreakTest.html", v4.1.0, Skip => $Validation_Documentation, ), Input_file->new("$AUXILIARY/SBTest.txt", v4.1.0, Handler => \&process_SB_test, + retain_trailing_comments => 1, ), Input_file->new("$AUXILIARY/SentenceBreakTest.html", v4.1.0, Skip => $Validation_Documentation, ), Input_file->new("$AUXILIARY/WBTest.txt", v4.1.0, Handler => \&process_WB_test, + retain_trailing_comments => 1, ), Input_file->new("$AUXILIARY/WordBreakTest.html", v4.1.0, Skip => $Validation_Documentation, @@ -19180,6 +19851,7 @@ my @input_file_objects = ( ), Input_file->new("$AUXILIARY/LBTest.txt", v5.1.0, Handler => \&process_LB_test, + retain_trailing_comments => 1, ), Input_file->new("$AUXILIARY/LineBreakTest.html", v5.1.0, Skip => $Validation_Documentation, @@ -19248,6 +19920,9 @@ my @input_file_objects = ( ), Input_file->new('ScriptExtensions.txt', v6.0.0, Property => 'Script_Extensions', + Early => [ sub {} ], # Doesn't do anything but ensures + # that this isn't skipped for early + # versions Pre_Handler => \&setup_script_extensions, Each_Line_Handler => \&filter_script_extensions_line, Has_Missings_Defaults => (($v_version le v6.0.0) @@ -19293,6 +19968,19 @@ my @input_file_objects = ( Property => 'Indic_Positional_Category', Has_Missings_Defaults => $NOT_IGNORED, ), + Input_file->new('TangutSources.txt', v9.0.0, + Skip => 'Specifies source mappings for Tangut ideographs' + . ' and components. This data file also includes' + . ' informative radical-stroke values that are used' + . ' internally by Unicode', + ), + Input_file->new('VerticalOrientation.txt', v10.0.0, + Property => 'Vertical_Orientation', + Has_Missings_Defaults => $NOT_IGNORED, + ), + Input_file->new('NushuSources.txt', v10.0.0, + Skip => 'Specifies source material for Nushu characters', + ), ); # End of all the preliminaries. @@ -19563,9 +20251,9 @@ if ( $file_list and $make_list ) { print "Updating '$file_list'\n" if $verbosity >= $PROGRESS; foreach my $file (@input_files, @files_actually_output) { - my (undef, $directories, $file) = File::Spec->splitpath($file); - my @directories = File::Spec->splitdir($directories); - $file = join '/', @directories, $file; + my (undef, $directories, $basefile) = File::Spec->splitpath($file); + my @directories = grep length, File::Spec->splitdir($directories); + $file = join '/', @directories, $basefile; } my $ofh; @@ -19625,6 +20313,13 @@ if ($verbosity >= $NORMAL_VERBOSITY && ! $debug_skip) { } print "\nAll done\n" if $verbosity >= $VERBOSE; } + +if ($version_of_mk_invlist_bounds lt $v_version) { + Carp::my_carp("WARNING: \\b{} algorithms (regen/mk_invlist.pl) need" + . " to be checked and possibly updated to Unicode" + . " $string_version"); +} + exit(0); # TRAILING CODE IS USED BY make_property_test_script() @@ -19682,7 +20377,7 @@ sub Expect($$$$) { $Tests++; # A string eval is needed because of the 'no warnings'. - # Assumes no parens in the regular expression + # Assumes no parentheses in the regular expression my $result = eval "$no_warnings my \$RegObj = qr($regex); $string =~ \$RegObj ? 1 : 0"; @@ -19750,7 +20445,10 @@ if (defined &locales_enabled) { } # Eval'd so can run on versions earlier than the property is available in -my $WB_Extend_or_Format_re = eval 'qr/[\p{WB=Extend}\p{WB=Format}]/'; +my $WB_Extend_or_Format_re = eval 'qr/[\p{WB=Extend}\p{WB=Format}\p{WB=ZWJ}]/'; +if (! defined $WB_Extend_or_Format_re) { + $WB_Extend_or_Format_re = eval 'qr/[\p{WB=Extend}\p{WB=Format}]/'; +} sub _test_break($$) { # Test various break property matches. The 2nd parameter gives the @@ -19772,6 +20470,15 @@ sub _test_break($$) { my $break_type = shift; my $line = (caller 1)[2]; # Line number + my $comment = ""; + + if ($template =~ / ( .*? ) \s* \# (.*) /x) { + $template = $1; + $comment = $2; + + # Replace leading spaces with a single one. + $comment =~ s/ ^ \s* / # /x; + } # The line contains characters above the ASCII range, but in Latin1. It # may or may not be in utf8, and if it is, it may or may not know it. So, @@ -19910,12 +20617,24 @@ sub _test_break($$) { my $pattern = "(?$modifier:$break_pattern)"; # Actually do the test + my $matched_text; my $matched = $string =~ qr/$pattern/; - print "not " unless $matched; + if ($matched) { + $matched_text = "matched"; + } + else { + $matched_text = "failed to match"; + print "not "; - # Fancy display of test results - $matched = ($matched) ? "matched" : "failed to match"; - print "ok ", ++$Tests, " - \"$display_string\" $matched /$pattern/$display_upgrade; line $line $display_locale\n"; + if (TODO_FAILING_BREAKS) { + $comment = " # $comment" unless $comment =~ / ^ \s* \# /x; + $comment =~ s/#/# TODO/; + } + } + print "ok ", ++$Tests, " - \"$display_string\" $matched_text /$pattern/$display_upgrade; line $line $display_locale$comment\n"; + + # Only print the comment on the first use of this line + $comment = ""; # Repeat with the first \B{} in the pattern. This makes sure the # code in regexec.c:find_byclass() for \B gets executed @@ -19923,8 +20642,10 @@ sub _test_break($$) { my $B_pattern = "$1$2"; $matched = $string =~ qr/$B_pattern/; print "not " unless $matched; - $matched = ($matched) ? "matched" : "failed to match"; - print "ok ", ++$Tests, " - \"$display_string\" $matched /$B_pattern/$display_upgrade; line $line $display_locale\n"; + $matched_text = ($matched) ? "matched" : "failed to match"; + print "ok ", ++$Tests, " - \"$display_string\" $matched_text /$B_pattern/$display_upgrade; line $line $display_locale"; + print " # TODO" if TODO_FAILING_BREAKS && ! $matched; + print "\n"; } } @@ -19949,7 +20670,9 @@ sub _test_break($$) { } else { $matches[$i] = join("", map { sprintf "\\x{%04X}", ord $_ } split "", $matches[$i]); - print "not ok $Tests - In \"$display_string\" =~ /(\\X)/g, \\X #", + print "not ok $Tests -"; + print " # TODO" if TODO_FAILING_BREAKS; + print " In \"$display_string\" =~ /(\\X)/g, \\X #", $i + 1, " should have matched $should_display[$i]", " but instead matched $matches[$i]", @@ -19963,7 +20686,9 @@ sub _test_break($$) { if (@matches == @should_match) { print "ok $Tests - Nothing was left over; line $line\n"; } else { - print "not ok $Tests - There were ", scalar @should_match, " \\X matches expected, but got ", scalar @matches, " instead; line $line\n"; + print "not ok $Tests - There were ", scalar @should_match, " \\X matches expected, but got ", scalar @matches, " instead; line $line"; + print " # TODO" if TODO_FAILING_BREAKS; + print "\n"; } } @@ -19991,15 +20716,3 @@ sub Finished() { exit($Fails ? -1 : 0); } -Error('\p{Script=InGreek}'); # Bug #69018 -Test_GCB("1100 $nobreak 1161"); # Bug #70940 -Expect(0, 0x2028, '\p{Print}', ""); # Bug # 71722 -Expect(0, 0x2029, '\p{Print}', ""); # Bug # 71722 -Expect(1, 0xFF10, '\p{XDigit}', ""); # Bug # 71726 - -# Make sure this gets tested; it was not part of the official test suite at -# the time this was addded. Note that this is as it would appear in the -# official suite, and gets modified to check for the perl tailoring by -# Test_WB() -Test_WB("$breakable 0020 $breakable 0020 $breakable 0308 $breakable"); -Test_LB("$nobreak 200B $nobreak 0020 $nobreak 0020 $breakable 2060 $breakable"); diff --git a/gnu/usr.bin/perl/lib/unicore/version b/gnu/usr.bin/perl/lib/unicore/version index ae9a76b9249..a13e7b9c87e 100644 --- a/gnu/usr.bin/perl/lib/unicore/version +++ b/gnu/usr.bin/perl/lib/unicore/version @@ -1 +1 @@ -8.0.0 +10.0.0 diff --git a/gnu/usr.bin/perl/lib/utf8.pm b/gnu/usr.bin/perl/lib/utf8.pm index 324cb87c869..9d560955391 100644 --- a/gnu/usr.bin/perl/lib/utf8.pm +++ b/gnu/usr.bin/perl/lib/utf8.pm @@ -2,7 +2,7 @@ package utf8; $utf8::hint_bits = 0x00800000; -our $VERSION = '1.19'; +our $VERSION = '1.21'; sub import { $^H |= $utf8::hint_bits; @@ -109,11 +109,26 @@ you should not say that unless you really want to have UTF-8 source code. Converts in-place the internal representation of the string from an octet sequence in the native encoding (Latin-1 or EBCDIC) to UTF-8. The logical character sequence itself is unchanged. If I<$string> is already -stored as UTF-8, then this is a no-op. Returns the -number of octets necessary to represent the string as UTF-8. Can be -used to make sure that the UTF-8 flag is on, so that C<\w> or C<lc()> -work as Unicode on strings containing non-ASCII characters whose code points -are below 256. +upgraded, then this is a no-op. Returns the +number of octets necessary to represent the string as UTF-8. + +If your code needs to be compatible with versions of perl without +C<use feature 'unicode_strings';>, you can force Unicode semantics on +a given string: + + # force unicode semantics for $string without the + # "unicode_strings" feature + utf8::upgrade($string); + +For example: + + # without explicit or implicit use feature 'unicode_strings' + my $x = "\xDF"; # LATIN SMALL LETTER SHARP S + $x =~ /ss/i; # won't match + my $y = uc($x); # won't convert + utf8::upgrade($x); + $x =~ /ss/i; # matches + my $z = uc($x); # converts to "SS" B<Note that this function does not handle arbitrary encodings>; use L<Encode> instead. @@ -121,14 +136,12 @@ use L<Encode> instead. =item * C<$success = utf8::downgrade($string[, $fail_ok])> (Since Perl v5.8.0) -Converts in-place the internal representation of the string from -UTF-8 to the equivalent octet sequence in the native encoding (Latin-1 -or EBCDIC). The logical character sequence itself is unchanged. If -I<$string> is already stored as native 8 bit, then this is a no-op. Can -be used to -make sure that the UTF-8 flag is off, e.g. when you want to make sure -that the substr() or length() function works with the usually faster -byte algorithm. +Converts in-place the internal representation of the string from UTF-8 to the +equivalent octet sequence in the native encoding (Latin-1 or EBCDIC). The +logical character sequence itself is unchanged. If I<$string> is already +stored as native 8 bit, then this is a no-op. Can be used to make sure that +the UTF-8 flag is off, e.g. when you want to make sure that the substr() or +length() function works with the usually faster byte algorithm. Fails if the original UTF-8 sequence cannot be represented in the native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is @@ -136,6 +149,15 @@ true, returns false. Returns true on success. +If your code expects an octet sequence this can be used to validate +that you've received one: + + # throw an exception if not representable as octets + utf8::downgrade($string) + + # or do your own error handling + utf8::downgrade($string, 1) or die "string must be octets"; + B<Note that this function does not handle arbitrary encodings>; use L<Encode> instead. @@ -143,35 +165,40 @@ use L<Encode> instead. (Since Perl v5.8.0) Converts in-place the character sequence to the corresponding octet -sequence in UTF-8. That is, every (possibly wide) character gets -replaced with a sequence of one or more characters that represent the +sequence in Perl's extended UTF-8. That is, every (possibly wide) character +gets replaced with a sequence of one or more characters that represent the individual UTF-8 bytes of the character. The UTF8 flag is turned off. Returns nothing. - my $a = "\x{100}"; # $a contains one character, with ord 0x100 - utf8::encode($a); # $a contains two characters, with ords (on + my $x = "\x{100}"; # $x contains one character, with ord 0x100 + utf8::encode($x); # $x contains two characters, with ords (on # ASCII platforms) 0xc4 and 0x80. On EBCDIC # 1047, this would instead be 0x8C and 0x41. +Similar to: + + use Encode; + $x = Encode::encode("utf8", $x); + B<Note that this function does not handle arbitrary encodings>; use L<Encode> instead. =item * C<$success = utf8::decode($string)> (Since Perl v5.8.0) -Attempts to convert in-place the octet sequence encoded as UTF-8 to the -corresponding character sequence. That is, it replaces each sequence of -characters in the string whose ords represent a valid UTF-8 byte -sequence, with the corresponding single character. The UTF-8 flag is -turned on only if the source string contains multiple-byte UTF-8 -characters. If I<$string> is invalid as UTF-8, returns false; +Attempts to convert in-place the octet sequence encoded in Perl's extended +UTF-8 to the corresponding character sequence. That is, it replaces each +sequence of characters in the string whose ords represent a valid (extended) +UTF-8 byte sequence, with the corresponding single character. The UTF-8 flag +is turned on only if the source string contains multiple-byte UTF-8 +characters. If I<$string> is invalid as extended UTF-8, returns false; otherwise returns true. - my $a = "\xc4\x80"; # $a contains two characters, with ords + my $x = "\xc4\x80"; # $x contains two characters, with ords # 0xc4 and 0x80 - utf8::decode($a); # On ASCII platforms, $a contains one char, + utf8::decode($x); # On ASCII platforms, $x contains one char, # with ord 0x100. Since these bytes aren't - # legal UTF-EBCDIC, on EBCDIC platforms, $a is + # legal UTF-EBCDIC, on EBCDIC platforms, $x is # unchanged and the function returns FALSE. B<Note that this function does not handle arbitrary encodings>; @@ -208,16 +235,31 @@ platforms, so there is no performance hit in using it there. =item * C<$flag = utf8::is_utf8($string)> (Since Perl 5.8.1) Test whether I<$string> is marked internally as encoded in -UTF-8. Functionally the same as C<Encode::is_utf8()>. +UTF-8. Functionally the same as C<Encode::is_utf8($string)>. + +Typically only necessary for debugging and testing, if you need to +dump the internals of an SV, L<Devel::Peek's|Devel::Peek> Dump() +provides more detail in a compact form. + +If you still think you need this outside of debugging, testing or +dealing with filenames, you should probably read L<perlunitut> and +L<perlunifaq/What is "the UTF8 flag"?>. + +Don't use this flag as a marker to distinguish character and binary +data: that should be decided for each variable when you write your +code. + +To force unicode semantics in code portable to perl 5.8 and 5.10, call +C<utf8::upgrade($string)> unconditionally. =item * C<$flag = utf8::valid($string)> [INTERNAL] Test whether I<$string> is in a consistent state regarding -UTF-8. Will return true if it is well-formed UTF-8 and has the UTF-8 flag +UTF-8. Will return true if it is well-formed Perl extended UTF-8 and has the +UTF-8 flag on B<or> if I<$string> is held as bytes (both these states are 'consistent'). -Main reason for this routine is to allow Perl's test suite to check -that operations have left strings in a consistent state. You most -probably want to use C<utf8::is_utf8()> instead. +The main reason for this routine is to allow Perl's test suite to check +that operations have left strings in a consistent state. =back diff --git a/gnu/usr.bin/perl/lib/utf8.t b/gnu/usr.bin/perl/lib/utf8.t index d90361dbe02..d35110baee0 100644 --- a/gnu/usr.bin/perl/lib/utf8.t +++ b/gnu/usr.bin/perl/lib/utf8.t @@ -40,7 +40,7 @@ no utf8; # Ironic, no? # { - # bug id 20001009.001 + # bug id 20001009.001 (#4409) my ($a, $b); @@ -56,7 +56,7 @@ no utf8; # Ironic, no? { - # bug id 20000730.004 + # bug id 20000730.004 (#3599) my $smiley = "\x{263a}"; @@ -140,6 +140,9 @@ no utf8; # Ironic, no? = join " . ", map {sprintf 'chr (%d)', ord $_} split //, $char; push @char, [$_, $char, $charsubst, $char_as_ord]; } + my $malformed = $::IS_ASCII + ? "\xE1\xA0" + : I8_to_native("\xE6\xA0"); # Now we've done all the UTF8 munching hopefully we're safe my @tests = ( ['check our detection program works', @@ -162,15 +165,15 @@ no utf8; # Ironic, no? # "out of memory" error. We really need the "" [rather than qq() # or q()] to get the best explosion. ["!Feed malformed utf8 into perl.", <<"BANG", - use utf8; %a = ("\xE1\xA0"=>"sterling"); + use utf8; %a = ("$malformed" =>"sterling"); print 'start'; printf '%x,', ord \$_ foreach keys %a; print "end\n"; BANG - qr/^Malformed UTF-8 character \(\d bytes?, need \d, .+\).*start\d+,end$/sm + qr/^Malformed UTF-8 character: .*? \(unexpected non-continuation byte/ ], ); foreach (@tests) { my ($why, $prog, $expect) = @$_; - open P, ">$progfile" or die "Can't open '$progfile': $!"; + open P, ">", $progfile or die "Can't open '$progfile': $!"; binmode(P, ":bytes") if $has_perlio; print P $show, $prog, '; print $b' or die "Print to 'progfile' failed: $!"; diff --git a/gnu/usr.bin/perl/lib/vars.pm b/gnu/usr.bin/perl/lib/vars.pm index 6ca6bb4d2c0..5f6c0598cad 100644 --- a/gnu/usr.bin/perl/lib/vars.pm +++ b/gnu/usr.bin/perl/lib/vars.pm @@ -2,7 +2,7 @@ package vars; use 5.006; -our $VERSION = '1.03'; +our $VERSION = '1.04'; use warnings::register; use strict qw(vars subs); @@ -61,13 +61,14 @@ functionality provided by this pragma has been superseded by C<our> declarations, available in Perl v5.6.0 or later, and use of this pragma is discouraged. See L<perlfunc/our>. -This will predeclare all the variables whose names are -in the list, allowing you to use them under "use strict", and -disabling any typo warnings. +This pragma will predeclare all the variables whose names are +in the list, allowing you to use them under C<use strict>, and +disabling any typo warnings for them. Unlike pragmas that affect the C<$^H> hints variable, the C<use vars> and -C<use subs> declarations are not BLOCK-scoped. They are thus effective -for the entire file in which they appear. You may not rescind such +C<use subs> declarations are not lexically scoped to the block they appear +in: they affect +the entire package in which they appear. It is not possible to rescind these declarations with C<no vars> or C<no subs>. Packages such as the B<AutoLoader> and B<SelfLoader> that delay diff --git a/gnu/usr.bin/perl/lib/warnings.pm b/gnu/usr.bin/perl/lib/warnings.pm index ddb0c35e8dc..43d39259362 100644 --- a/gnu/usr.bin/perl/lib/warnings.pm +++ b/gnu/usr.bin/perl/lib/warnings.pm @@ -5,7 +5,7 @@ package warnings; -our $VERSION = "1.36"; +our $VERSION = "1.42"; # Verify that we're called correctly so that warnings will work. # Can't use Carp, since Carp uses us! @@ -93,153 +93,167 @@ our %Offsets = ( 'locale' => 126, 'missing' => 128, 'redundant' => 130, + + # Warnings Categories added in Perl 5.025 + 'experimental::declared_refs' => 132, + + # Warnings Categories added in Perl 5.027 + 'experimental::alpha_assertions' => 134, + 'experimental::script_run' => 136, + 'shadow' => 138, ); our %Bits = ( - 'all' => "\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x05", # [0..65] - 'ambiguous' => "\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [29] - 'bareword' => "\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [30] - 'closed' => "\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [6] - 'closure' => "\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [1] - 'debugging' => "\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [22] - 'deprecated' => "\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [2] - 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] - 'exec' => "\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] - 'exiting' => "\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] - 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x55\x51\x15\x00", # [51..56,58..62] - 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00", # [58] - 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00", # [59] - 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00", # [52] - 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00", # [55] - 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00", # [60] - 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00", # [61] - 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00", # [53] - 'experimental::signatures' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00", # [56] - 'experimental::smartmatch' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00", # [54] - 'experimental::win32_perlio' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00", # [62] - 'glob' => "\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [4] - 'illegalproto' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00", # [47] - 'imprecision' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00", # [46] - 'inplace' => "\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [23] - 'internal' => "\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [24] - 'io' => "\x00\x54\x55\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00", # [5..11,57] - 'layer' => "\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [8] - 'locale' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00", # [63] - 'malloc' => "\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [25] - 'misc' => "\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [12] - 'missing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01", # [64] - 'newline' => "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [9] - 'non_unicode' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00", # [48] - 'nonchar' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00", # [49] - 'numeric' => "\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [13] - 'once' => "\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [14] - 'overflow' => "\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [15] - 'pack' => "\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [16] - 'parenthesis' => "\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00", # [32] - 'pipe' => "\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [10] - 'portable' => "\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [17] - 'precedence' => "\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00", # [33] - 'printf' => "\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00", # [34] - 'prototype' => "\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00", # [35] - 'qw' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00", # [36] - 'recursion' => "\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [18] - 'redefine' => "\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [19] - 'redundant' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04", # [65] - 'regexp' => "\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [20] - 'reserved' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00", # [37] - 'semicolon' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00", # [38] - 'severe' => "\x00\x00\x00\x00\x00\x54\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [21..25] - 'signal' => "\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [26] - 'substr' => "\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [27] - 'surrogate' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00", # [50] - 'syntax' => "\x00\x00\x00\x00\x00\x00\x00\x55\x55\x15\x00\x40\x00\x00\x00\x00\x00", # [28..38,47] - 'syscalls' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00", # [57] - 'taint' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00", # [39] - 'threads' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00", # [40] - 'uninitialized' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00", # [41] - 'unopened' => "\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [11] - 'unpack' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00", # [42] - 'untie' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00", # [43] - 'utf8' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x15\x00\x00\x00\x00", # [44,48..50] - 'void' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00", # [45] + 'all' => "\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55\x55", # [0..71] + 'ambiguous' => "\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [29] + 'bareword' => "\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [30] + 'closed' => "\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [6] + 'closure' => "\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [1] + 'debugging' => "\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [22] + 'deprecated' => "\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [2] + 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] + 'exec' => "\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] + 'exiting' => "\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] + 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x55\x51\x15\x50\x01", # [51..56,58..62,66..68] + 'experimental::alpha_assertions' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00", # [67] + 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00", # [58] + 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00", # [59] + 'experimental::declared_refs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00", # [66] + 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00", # [52] + 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00", # [55] + 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00", # [60] + 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00", # [61] + 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00", # [53] + 'experimental::script_run' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01", # [68] + 'experimental::signatures' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00", # [56] + 'experimental::smartmatch' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00", # [54] + 'experimental::win32_perlio' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00", # [62] + 'glob' => "\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [4] + 'illegalproto' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00", # [47] + 'imprecision' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00", # [46] + 'inplace' => "\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [23] + 'internal' => "\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [24] + 'io' => "\x00\x54\x55\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00", # [5..11,57] + 'layer' => "\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [8] + 'locale' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00", # [63] + 'malloc' => "\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [25] + 'misc' => "\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [12] + 'missing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00", # [64] + 'newline' => "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [9] + 'non_unicode' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00", # [48] + 'nonchar' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00", # [49] + 'numeric' => "\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [13] + 'once' => "\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [14] + 'overflow' => "\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [15] + 'pack' => "\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [16] + 'parenthesis' => "\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [32] + 'pipe' => "\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [10] + 'portable' => "\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [17] + 'precedence' => "\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [33] + 'printf' => "\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [34] + 'prototype' => "\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [35] + 'qw' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00", # [36] + 'recursion' => "\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [18] + 'redefine' => "\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [19] + 'redundant' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00", # [65] + 'regexp' => "\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [20] + 'reserved' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00", # [37] + 'semicolon' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00", # [38] + 'severe' => "\x00\x00\x00\x00\x00\x54\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [21..25] + 'shadow' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04", # [69] + 'signal' => "\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [26] + 'substr' => "\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [27] + 'surrogate' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00", # [50] + 'syntax' => "\x00\x00\x00\x00\x00\x00\x00\x55\x55\x15\x00\x40\x00\x00\x00\x00\x00\x00", # [28..38,47] + 'syscalls' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00", # [57] + 'taint' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00", # [39] + 'threads' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00", # [40] + 'uninitialized' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00", # [41] + 'unopened' => "\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [11] + 'unpack' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00", # [42] + 'untie' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x40\x00\x00\x00\x00\x00\x00\x00", # [43] + 'utf8' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x15\x00\x00\x00\x00\x00", # [44,48..50] + 'void' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00\x00\x00", # [45] ); our %DeadBits = ( - 'all' => "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\x0a", # [0..65] - 'ambiguous' => "\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [29] - 'bareword' => "\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [30] - 'closed' => "\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [6] - 'closure' => "\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [1] - 'debugging' => "\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [22] - 'deprecated' => "\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [2] - 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] - 'exec' => "\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] - 'exiting' => "\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] - 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\xaa\xa2\x2a\x00", # [51..56,58..62] - 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00", # [58] - 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00", # [59] - 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00", # [52] - 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00", # [55] - 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00", # [60] - 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00", # [61] - 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00", # [53] - 'experimental::signatures' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00", # [56] - 'experimental::smartmatch' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00", # [54] - 'experimental::win32_perlio' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00", # [62] - 'glob' => "\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [4] - 'illegalproto' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00", # [47] - 'imprecision' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00", # [46] - 'inplace' => "\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [23] - 'internal' => "\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [24] - 'io' => "\x00\xa8\xaa\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00", # [5..11,57] - 'layer' => "\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [8] - 'locale' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00", # [63] - 'malloc' => "\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [25] - 'misc' => "\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [12] - 'missing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02", # [64] - 'newline' => "\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [9] - 'non_unicode' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00", # [48] - 'nonchar' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00", # [49] - 'numeric' => "\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [13] - 'once' => "\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [14] - 'overflow' => "\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [15] - 'pack' => "\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [16] - 'parenthesis' => "\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00", # [32] - 'pipe' => "\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [10] - 'portable' => "\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [17] - 'precedence' => "\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00", # [33] - 'printf' => "\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00", # [34] - 'prototype' => "\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00", # [35] - 'qw' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00", # [36] - 'recursion' => "\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [18] - 'redefine' => "\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [19] - 'redundant' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08", # [65] - 'regexp' => "\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [20] - 'reserved' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00", # [37] - 'semicolon' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00", # [38] - 'severe' => "\x00\x00\x00\x00\x00\xa8\x0a\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [21..25] - 'signal' => "\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [26] - 'substr' => "\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [27] - 'surrogate' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00", # [50] - 'syntax' => "\x00\x00\x00\x00\x00\x00\x00\xaa\xaa\x2a\x00\x80\x00\x00\x00\x00\x00", # [28..38,47] - 'syscalls' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00", # [57] - 'taint' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00", # [39] - 'threads' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00", # [40] - 'uninitialized' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00", # [41] - 'unopened' => "\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [11] - 'unpack' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00", # [42] - 'untie' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00", # [43] - 'utf8' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x2a\x00\x00\x00\x00", # [44,48..50] - 'void' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00", # [45] + 'all' => "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa", # [0..71] + 'ambiguous' => "\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [29] + 'bareword' => "\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [30] + 'closed' => "\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [6] + 'closure' => "\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [1] + 'debugging' => "\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [22] + 'deprecated' => "\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [2] + 'digit' => "\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [31] + 'exec' => "\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [7] + 'exiting' => "\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [3] + 'experimental' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\xaa\xa2\x2a\xa0\x02", # [51..56,58..62,66..68] + 'experimental::alpha_assertions' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00", # [67] + 'experimental::bitwise' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00", # [58] + 'experimental::const_attr' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00", # [59] + 'experimental::declared_refs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00", # [66] + 'experimental::lexical_subs' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00", # [52] + 'experimental::postderef' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00", # [55] + 'experimental::re_strict' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00", # [60] + 'experimental::refaliasing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00", # [61] + 'experimental::regex_sets' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00", # [53] + 'experimental::script_run' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02", # [68] + 'experimental::signatures' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00", # [56] + 'experimental::smartmatch' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00", # [54] + 'experimental::win32_perlio' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00", # [62] + 'glob' => "\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [4] + 'illegalproto' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00", # [47] + 'imprecision' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00", # [46] + 'inplace' => "\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [23] + 'internal' => "\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [24] + 'io' => "\x00\xa8\xaa\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00", # [5..11,57] + 'layer' => "\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [8] + 'locale' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00", # [63] + 'malloc' => "\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [25] + 'misc' => "\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [12] + 'missing' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00", # [64] + 'newline' => "\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [9] + 'non_unicode' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00", # [48] + 'nonchar' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00", # [49] + 'numeric' => "\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [13] + 'once' => "\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [14] + 'overflow' => "\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [15] + 'pack' => "\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [16] + 'parenthesis' => "\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [32] + 'pipe' => "\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [10] + 'portable' => "\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [17] + 'precedence' => "\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [33] + 'printf' => "\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [34] + 'prototype' => "\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [35] + 'qw' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00", # [36] + 'recursion' => "\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [18] + 'redefine' => "\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [19] + 'redundant' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00", # [65] + 'regexp' => "\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [20] + 'reserved' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x00", # [37] + 'semicolon' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00", # [38] + 'severe' => "\x00\x00\x00\x00\x00\xa8\x0a\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [21..25] + 'shadow' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08", # [69] + 'signal' => "\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [26] + 'substr' => "\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [27] + 'surrogate' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00", # [50] + 'syntax' => "\x00\x00\x00\x00\x00\x00\x00\xaa\xaa\x2a\x00\x80\x00\x00\x00\x00\x00\x00", # [28..38,47] + 'syscalls' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00", # [57] + 'taint' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00", # [39] + 'threads' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00", # [40] + 'uninitialized' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00", # [41] + 'unopened' => "\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", # [11] + 'unpack' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x00\x00\x00\x00", # [42] + 'untie' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x00\x00\x00\x00\x00\x00\x00", # [43] + 'utf8' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x2a\x00\x00\x00\x00\x00", # [44,48..50] + 'void' => "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00", # [45] ); # These are used by various things, including our own tests -our $NONE = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; -our $DEFAULT = "\x10\x01\x00\x00\x00\x50\x04\x00\x00\x00\x00\x00\x00\x55\x51\x55\x00", # [2,58,59,52,55,60,61,53,56,54,62,4,63,22,23,25] -our $LAST_BIT = 132 ; -our $BYTES = 17 ; - -our $All = "" ; vec($All, $Offsets{'all'}, 2) = 3 ; +our $NONE = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; +our $DEFAULT = "\x10\x01\x00\x00\x00\x50\x04\x00\x00\x00\x00\x00\x00\x55\x51\x55\x50\x01", # [2,4,22,23,25,52..56,58..63,66..68] +our $LAST_BIT = 140 ; +our $BYTES = 18 ; sub Croaker { @@ -249,12 +263,32 @@ sub Croaker Carp::croak(@_); } +sub _expand_bits { + my $bits = shift; + my $want_len = ($LAST_BIT + 7) >> 3; + my $len = length($bits); + if ($len != $want_len) { + if ($bits eq "") { + $bits = "\x00" x $want_len; + } elsif ($len > $want_len) { + substr $bits, $want_len, $len-$want_len, ""; + } else { + my $a = vec($bits, $Offsets{all} >> 1, 2); + $a |= $a << 2; + $a |= $a << 4; + $bits .= chr($a) x ($want_len - $len); + } + } + return $bits; +} + sub _bits { my $mask = shift ; my $catmask ; my $fatal = 0 ; my $no_fatal = 0 ; + $mask = _expand_bits($mask); foreach my $word ( @_ ) { if ($word eq 'FATAL') { $fatal = 1; @@ -267,7 +301,7 @@ sub _bits { elsif ($catmask = $Bits{$word}) { $mask |= $catmask ; $mask |= $DeadBits{$word} if $fatal ; - $mask &= ~($DeadBits{$word}|$All) if $no_fatal ; + $mask = ~(~$mask | $DeadBits{$word}) if $no_fatal ; } else { Croaker("Unknown warnings category '$word'")} @@ -280,7 +314,7 @@ sub bits { # called from B::Deparse.pm push @_, 'all' unless @_ ; - return _bits(undef, @_) ; + return _bits("", @_) ; } sub import @@ -289,16 +323,12 @@ sub import my $mask = ${^WARNING_BITS} // ($^W ? $Bits{all} : $DEFAULT) ; - if (vec($mask, $Offsets{'all'}, 1)) { - $mask |= $Bits{'all'} ; - $mask |= $DeadBits{'all'} if vec($mask, $Offsets{'all'}+1, 1); - } - - # append 'all' when implied (after a lone "FATAL" or "NONFATAL") - push @_, 'all' if @_==1 && ( $_[0] eq 'FATAL' || $_[0] eq 'NONFATAL' ); + # append 'all' when implied (empty import list or after a lone + # "FATAL" or "NONFATAL") + push @_, 'all' + if !@_ || (@_==1 && ($_[0] eq 'FATAL' || $_[0] eq 'NONFATAL')); - # Empty @_ is equivalent to @_ = 'all' ; - ${^WARNING_BITS} = @_ ? _bits($mask, @_) : $mask | $Bits{all} ; + ${^WARNING_BITS} = _bits($mask, @_); } sub unimport @@ -308,20 +338,16 @@ sub unimport my $catmask ; my $mask = ${^WARNING_BITS} // ($^W ? $Bits{all} : $DEFAULT) ; - if (vec($mask, $Offsets{'all'}, 1)) { - $mask |= $Bits{'all'} ; - $mask |= $DeadBits{'all'} if vec($mask, $Offsets{'all'}+1, 1); - } - # append 'all' when implied (empty import list or after a lone "FATAL") push @_, 'all' if !@_ || @_==1 && $_[0] eq 'FATAL'; + $mask = _expand_bits($mask); foreach my $word ( @_ ) { if ($word eq 'FATAL') { next; } elsif ($catmask = $Bits{$word}) { - $mask &= ~($catmask | $DeadBits{$word} | $All); + $mask = ~(~$mask | $catmask | $DeadBits{$word}); } else { Croaker("Unknown warnings category '$word'")} @@ -332,6 +358,7 @@ sub unimport my %builtin_type; @builtin_type{qw(SCALAR ARRAY HASH CODE REF GLOB LVALUE Regexp)} = (); +sub LEVEL () { 8 }; sub MESSAGE () { 4 }; sub FATAL () { 2 }; sub NORMAL () { 1 }; @@ -343,8 +370,18 @@ sub __chk my $isobj = 0 ; my $wanted = shift; my $has_message = $wanted & MESSAGE; - - unless (@_ == 1 || @_ == ($has_message ? 2 : 0)) { + my $has_level = $wanted & LEVEL ; + + if ($has_level) { + if (@_ != ($has_message ? 3 : 2)) { + my $sub = (caller 1)[3]; + my $syntax = $has_message + ? "category, level, 'message'" + : 'category, level'; + Croaker("Usage: $sub($syntax)"); + } + } + elsif (not @_ == 1 || @_ == ($has_message ? 2 : 0)) { my $sub = (caller 1)[3]; my $syntax = $has_message ? "[category,] 'message'" : '[category]'; Croaker("Usage: $sub($syntax)"); @@ -382,6 +419,9 @@ sub __chk } $i -= 2 ; } + elsif ($has_level) { + $i = 2 + shift; + } else { $i = _error_loc(); # see where Carp will allocate the error } @@ -391,22 +431,35 @@ sub __chk my(@callers_bitmask) = (caller($i))[9] ; my $callers_bitmask = @callers_bitmask ? $callers_bitmask[0] // $DEFAULT : 0 ; + length($callers_bitmask) > ($offset >> 3) or $offset = $Offsets{all}; my @results; foreach my $type (FATAL, NORMAL) { next unless $wanted & $type; - push @results, (vec($callers_bitmask, $offset + $type - 1, 1) || - vec($callers_bitmask, $Offsets{'all'} + $type - 1, 1)); + push @results, vec($callers_bitmask, $offset + $type - 1, 1); } # &enabled and &fatal_enabled return $results[0] unless $has_message; # &warnif, and the category is neither enabled as warning nor as fatal - return if $wanted == (NORMAL | FATAL | MESSAGE) + return if ($wanted & (NORMAL | FATAL | MESSAGE)) + == (NORMAL | FATAL | MESSAGE) && !($results[0] || $results[1]); + # If we have an explicit level, bypass Carp. + if ($has_level and @callers_bitmask) { + # logic copied from util.c:mess_sv + my $stuff = " at " . join " line ", (caller $i)[1,2]; + $stuff .= sprintf ", <%s> %s %d", + *${^LAST_FH}{NAME}, + ($/ eq "\n" ? "line" : "chunk"), $. + if $. && ${^LAST_FH}; + die "$message$stuff.\n" if $results[0]; + return warn "$message$stuff.\n"; + } + require Carp; Carp::croak($message) if $results[0]; # will always get here for &warn. will only get here for &warnif if the @@ -429,14 +482,13 @@ sub register_categories for my $name (@names) { if (! defined $Bits{$name}) { - $Bits{$name} = _mkMask($LAST_BIT); - vec($Bits{'all'}, $LAST_BIT, 1) = 1; - $Offsets{$name} = $LAST_BIT ++; - foreach my $k (keys %Bits) { - vec($Bits{$k}, $LAST_BIT, 1) = 0; + $Offsets{$name} = $LAST_BIT; + $Bits{$name} = _mkMask($LAST_BIT++); + $DeadBits{$name} = _mkMask($LAST_BIT++); + if (length($Bits{$name}) > length($Bits{all})) { + $Bits{all} .= "\x55"; + $DeadBits{all} .= "\xaa"; } - $DeadBits{$name} = _mkMask($LAST_BIT); - vec($DeadBits{'all'}, $LAST_BIT++, 1) = 1; } } } @@ -466,9 +518,29 @@ sub warnif return __chk(NORMAL | FATAL | MESSAGE, @_); } +sub enabled_at_level +{ + return __chk(NORMAL | LEVEL, @_); +} + +sub fatal_enabled_at_level +{ + return __chk(FATAL | LEVEL, @_); +} + +sub warn_at_level +{ + return __chk(FATAL | MESSAGE | LEVEL, @_); +} + +sub warnif_at_level +{ + return __chk(NORMAL | FATAL | MESSAGE | LEVEL, @_); +} + # These are not part of any public interface, so we can delete them to save # space. -delete @warnings::{qw(NORMAL FATAL MESSAGE)}; +delete @warnings::{qw(NORMAL FATAL MESSAGE LEVEL)}; 1; __END__ @@ -721,10 +793,14 @@ The current hierarchy is: | +- experimental --+ | | + | +- experimental::alpha_assertions + | | | +- experimental::bitwise | | | +- experimental::const_attr | | + | +- experimental::declared_refs + | | | +- experimental::lexical_subs | | | +- experimental::postderef @@ -735,6 +811,8 @@ The current hierarchy is: | | | +- experimental::regex_sets | | + | +- experimental::script_run + | | | +- experimental::signatures | | | +- experimental::smartmatch @@ -795,6 +873,8 @@ The current hierarchy is: | | | +- malloc | + +- shadow + | +- signal | +- substr @@ -1131,6 +1211,9 @@ warnings::register like this: =head1 FUNCTIONS +Note: The functions with names ending in C<_at_level> were added in Perl +5.28. + =over 4 =item use warnings::register @@ -1160,6 +1243,11 @@ Return TRUE if that warnings category is enabled in the first scope where the object is used. Otherwise returns FALSE. +=item warnings::enabled_at_level($category, $level) + +Like C<warnings::enabled>, but $level specifies the exact call frame, 0 +being the immediate caller. + =item warnings::fatal_enabled() Return TRUE if the warnings category with the same name as the current @@ -1181,6 +1269,11 @@ Return TRUE if that warnings category has been set to FATAL in the first scope where the object is used. Otherwise returns FALSE. +=item warnings::fatal_enabled_at_level($category, $level) + +Like C<warnings::fatal_enabled>, but $level specifies the exact call frame, +0 being the immediate caller. + =item warnings::warn($message) Print C<$message> to STDERR. @@ -1207,6 +1300,10 @@ warnings category. If that warnings category has been set to "FATAL" in the scope where C<$object> is first used then die. Otherwise return. +=item warnings::warn_at_level($category, $level, $message) + +Like C<warnings::warn>, but $level specifies the exact call frame, +0 being the immediate caller. =item warnings::warnif($message) @@ -1229,6 +1326,11 @@ Equivalent to: if (warnings::enabled($object)) { warnings::warn($object, $message) } +=item warnings::warnif_at_level($category, $level, $message) + +Like C<warnings::warnif>, but $level specifies the exact call frame, +0 being the immediate caller. + =item warnings::register_categories(@names) This registers warning categories for the given names and is primarily for |