From cc66bca775eeb81ef24456338bcd97e2e780c236 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 11 Dec 2018 20:00:49 +0900 Subject: kconfig: fix ambiguous grammar in terms of new lines This commit decreases 8 shift/reduce conflicts. A certain amount of grammatical ambiguity comes from how to reduce excessive T_EOL tokens. Let's take a look at the example code below: 1 config A 2 bool "a" 3 4 depends on B 5 6 config B 7 def_bool y The line 3 is melt into "config_option_list", but the line 5 can be either a part of "config_option_list" or "common_stmt" by itself. Currently, the lexer converts '\n' to T_EOL verbatim. In Kconfig, a new line works as a statement terminator, but new lines in empty lines are not critical since empty lines (or lines that contain only whitespaces/comments) are just no-op. If the lexer simply discards no-op lines, the parser will not be bothered by excessive T_EOL tokens. Of course, this means we are shifting the complexity from the parser to the lexer, but it is much easier than tackling on shift/reduce conflicts. I introduced the second stage lexer to tweak the behavior. Discard T_EOL if the previous token is T_EOL or T_HELPTEXT. Two T_EOL tokens in a row is meaningless. T_HELPTEXT is a special token that is reduced without T_EOL. Signed-off-by: Masahiro Yamada --- scripts/kconfig/zconf.l | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'scripts/kconfig/zconf.l') diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l index b7bc164fdf00..847ba4248092 100644 --- a/scripts/kconfig/zconf.l +++ b/scripts/kconfig/zconf.l @@ -16,6 +16,8 @@ #include "lkc.h" +#define YY_DECL static int yylex1(void) + #define START_STRSIZE 16 static struct { @@ -23,6 +25,7 @@ static struct { int lineno; } current_pos; +static int prev_token = T_EOL; static char *text; static int text_size, text_asize; @@ -268,6 +271,24 @@ n [A-Za-z0-9_-] } %% + +/* second stage lexer */ +int yylex(void) +{ + int token; + +repeat: + token = yylex1(); + + /* Do not pass unneeded T_EOL to the parser. */ + if ((prev_token == T_EOL || prev_token == T_HELPTEXT) && token == T_EOL) + goto repeat; + + prev_token = token; + + return token; +} + static char *expand_token(const char *in, size_t n) { char *out; -- cgit v1.2.3-59-g8ed1b