diff options
| author | 2017-01-14 19:55:43 +0000 | |
|---|---|---|
| committer | 2017-01-14 19:55:43 +0000 | |
| commit | bd3306aecb3a15e8967143b8cdbbccf2b1b19b74 (patch) | |
| tree | 309a8132b44564b9e634c0da6815187ce8eab27c /gnu/llvm/tools/clang/lib/Format | |
| parent | killp -a should not kill the window if only one pane. (diff) | |
| download | wireguard-openbsd-bd3306aecb3a15e8967143b8cdbbccf2b1b19b74.tar.xz wireguard-openbsd-bd3306aecb3a15e8967143b8cdbbccf2b1b19b74.zip | |
Import LLVM 3.9.1 including clang and lld.
Diffstat (limited to 'gnu/llvm/tools/clang/lib/Format')
22 files changed, 2821 insertions, 1082 deletions
diff --git a/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.cpp b/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.cpp new file mode 100644 index 00000000000..5d4df194120 --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.cpp @@ -0,0 +1,150 @@ +//===--- AffectedRangeManager.cpp - Format C++ code -----------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements AffectRangeManager class. +/// +//===----------------------------------------------------------------------===// + +#include "AffectedRangeManager.h" + +#include "FormatToken.h" +#include "TokenAnnotator.h" + +namespace clang { +namespace format { + +bool AffectedRangeManager::computeAffectedLines( + SmallVectorImpl<AnnotatedLine *>::iterator I, + SmallVectorImpl<AnnotatedLine *>::iterator E) { + bool SomeLineAffected = false; + const AnnotatedLine *PreviousLine = nullptr; + while (I != E) { + AnnotatedLine *Line = *I; + Line->LeadingEmptyLinesAffected = affectsLeadingEmptyLines(*Line->First); + + // If a line is part of a preprocessor directive, it needs to be formatted + // if any token within the directive is affected. + if (Line->InPPDirective) { + FormatToken *Last = Line->Last; + SmallVectorImpl<AnnotatedLine *>::iterator PPEnd = I + 1; + while (PPEnd != E && !(*PPEnd)->First->HasUnescapedNewline) { + Last = (*PPEnd)->Last; + ++PPEnd; + } + + if (affectsTokenRange(*Line->First, *Last, + /*IncludeLeadingNewlines=*/false)) { + SomeLineAffected = true; + markAllAsAffected(I, PPEnd); + } + I = PPEnd; + continue; + } + + if (nonPPLineAffected(Line, PreviousLine)) + SomeLineAffected = true; + + PreviousLine = Line; + ++I; + } + return SomeLineAffected; +} + +bool AffectedRangeManager::affectsCharSourceRange( + const CharSourceRange &Range) { + for (SmallVectorImpl<CharSourceRange>::const_iterator I = Ranges.begin(), + E = Ranges.end(); + I != E; ++I) { + if (!SourceMgr.isBeforeInTranslationUnit(Range.getEnd(), I->getBegin()) && + !SourceMgr.isBeforeInTranslationUnit(I->getEnd(), Range.getBegin())) + return true; + } + return false; +} + +bool AffectedRangeManager::affectsTokenRange(const FormatToken &First, + const FormatToken &Last, + bool IncludeLeadingNewlines) { + SourceLocation Start = First.WhitespaceRange.getBegin(); + if (!IncludeLeadingNewlines) + Start = Start.getLocWithOffset(First.LastNewlineOffset); + SourceLocation End = Last.getStartOfNonWhitespace(); + End = End.getLocWithOffset(Last.TokenText.size()); + CharSourceRange Range = CharSourceRange::getCharRange(Start, End); + return affectsCharSourceRange(Range); +} + +bool AffectedRangeManager::affectsLeadingEmptyLines(const FormatToken &Tok) { + CharSourceRange EmptyLineRange = CharSourceRange::getCharRange( + Tok.WhitespaceRange.getBegin(), + Tok.WhitespaceRange.getBegin().getLocWithOffset(Tok.LastNewlineOffset)); + return affectsCharSourceRange(EmptyLineRange); +} + +void AffectedRangeManager::markAllAsAffected( + SmallVectorImpl<AnnotatedLine *>::iterator I, + SmallVectorImpl<AnnotatedLine *>::iterator E) { + while (I != E) { + (*I)->Affected = true; + markAllAsAffected((*I)->Children.begin(), (*I)->Children.end()); + ++I; + } +} + +bool AffectedRangeManager::nonPPLineAffected( + AnnotatedLine *Line, const AnnotatedLine *PreviousLine) { + bool SomeLineAffected = false; + Line->ChildrenAffected = + computeAffectedLines(Line->Children.begin(), Line->Children.end()); + if (Line->ChildrenAffected) + SomeLineAffected = true; + + // Stores whether one of the line's tokens is directly affected. + bool SomeTokenAffected = false; + // Stores whether we need to look at the leading newlines of the next token + // in order to determine whether it was affected. + bool IncludeLeadingNewlines = false; + + // Stores whether the first child line of any of this line's tokens is + // affected. + bool SomeFirstChildAffected = false; + + for (FormatToken *Tok = Line->First; Tok; Tok = Tok->Next) { + // Determine whether 'Tok' was affected. + if (affectsTokenRange(*Tok, *Tok, IncludeLeadingNewlines)) + SomeTokenAffected = true; + + // Determine whether the first child of 'Tok' was affected. + if (!Tok->Children.empty() && Tok->Children.front()->Affected) + SomeFirstChildAffected = true; + + IncludeLeadingNewlines = Tok->Children.empty(); + } + + // Was this line moved, i.e. has it previously been on the same line as an + // affected line? + bool LineMoved = PreviousLine && PreviousLine->Affected && + Line->First->NewlinesBefore == 0; + + bool IsContinuedComment = + Line->First->is(tok::comment) && Line->First->Next == nullptr && + Line->First->NewlinesBefore < 2 && PreviousLine && + PreviousLine->Affected && PreviousLine->Last->is(tok::comment); + + if (SomeTokenAffected || SomeFirstChildAffected || LineMoved || + IsContinuedComment) { + Line->Affected = true; + SomeLineAffected = true; + } + return SomeLineAffected; +} + +} // namespace format +} // namespace clang diff --git a/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.h b/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.h new file mode 100644 index 00000000000..d8d5ee55acd --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/AffectedRangeManager.h @@ -0,0 +1,67 @@ +//===--- AffectedRangeManager.h - Format C++ code ---------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief AffectedRangeManager class manages affected ranges in the code. +/// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CLANG_LIB_FORMAT_AFFECTEDRANGEMANAGER_H +#define LLVM_CLANG_LIB_FORMAT_AFFECTEDRANGEMANAGER_H + +#include "clang/Basic/SourceManager.h" + +namespace clang { +namespace format { + +struct FormatToken; +class AnnotatedLine; + +class AffectedRangeManager { +public: + AffectedRangeManager(const SourceManager &SourceMgr, + const ArrayRef<CharSourceRange> Ranges) + : SourceMgr(SourceMgr), Ranges(Ranges.begin(), Ranges.end()) {} + + // Determines which lines are affected by the SourceRanges given as input. + // Returns \c true if at least one line between I and E or one of their + // children is affected. + bool computeAffectedLines(SmallVectorImpl<AnnotatedLine *>::iterator I, + SmallVectorImpl<AnnotatedLine *>::iterator E); + + // Returns true if 'Range' intersects with one of the input ranges. + bool affectsCharSourceRange(const CharSourceRange &Range); + +private: + // Returns true if the range from 'First' to 'Last' intersects with one of the + // input ranges. + bool affectsTokenRange(const FormatToken &First, const FormatToken &Last, + bool IncludeLeadingNewlines); + + // Returns true if one of the input ranges intersect the leading empty lines + // before 'Tok'. + bool affectsLeadingEmptyLines(const FormatToken &Tok); + + // Marks all lines between I and E as well as all their children as affected. + void markAllAsAffected(SmallVectorImpl<AnnotatedLine *>::iterator I, + SmallVectorImpl<AnnotatedLine *>::iterator E); + + // Determines whether 'Line' is affected by the SourceRanges given as input. + // Returns \c true if line or one if its children is affected. + bool nonPPLineAffected(AnnotatedLine *Line, + const AnnotatedLine *PreviousLine); + + const SourceManager &SourceMgr; + const SmallVector<CharSourceRange, 8> Ranges; +}; + +} // namespace format +} // namespace clang + +#endif // LLVM_CLANG_LIB_FORMAT_AFFECTEDRANGEMANAGER_H diff --git a/gnu/llvm/tools/clang/lib/Format/CMakeLists.txt b/gnu/llvm/tools/clang/lib/Format/CMakeLists.txt index 2ce38343cfe..cb46b9f255d 100644 --- a/gnu/llvm/tools/clang/lib/Format/CMakeLists.txt +++ b/gnu/llvm/tools/clang/lib/Format/CMakeLists.txt @@ -1,10 +1,14 @@ set(LLVM_LINK_COMPONENTS support) add_clang_library(clangFormat + AffectedRangeManager.cpp BreakableToken.cpp ContinuationIndenter.cpp Format.cpp FormatToken.cpp + FormatTokenLexer.cpp + SortJavaScriptImports.cpp + TokenAnalyzer.cpp TokenAnnotator.cpp UnwrappedLineFormatter.cpp UnwrappedLineParser.cpp diff --git a/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.cpp b/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.cpp index b820f53db52..322969e4bb7 100644 --- a/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.cpp +++ b/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.cpp @@ -64,7 +64,7 @@ static bool startsNextParameter(const FormatToken &Current, ContinuationIndenter::ContinuationIndenter(const FormatStyle &Style, const AdditionalKeywords &Keywords, - SourceManager &SourceMgr, + const SourceManager &SourceMgr, WhitespaceManager &Whitespaces, encoding::Encoding Encoding, bool BinPackInconclusiveFunctions) @@ -151,6 +151,7 @@ bool ContinuationIndenter::mustBreak(const LineState &State) { return true; if ((startsNextParameter(Current, Style) || Previous.is(tok::semi) || (Previous.is(TT_TemplateCloser) && Current.is(TT_StartOfName) && + Style.Language == FormatStyle::LK_Cpp && // FIXME: This is a temporary workaround for the case where clang-format // sets BreakBeforeParameter to avoid bin packing and this creates a // completely unnecessary line break after a template type that isn't @@ -249,7 +250,7 @@ bool ContinuationIndenter::mustBreak(const LineState &State) { // If the return type spans multiple lines, wrap before the function name. if ((Current.is(TT_FunctionDeclarationName) || (Current.is(tok::kw_operator) && !Previous.is(tok::coloncolon))) && - State.Stack.back().BreakBeforeParameter) + !Previous.is(tok::kw_template) && State.Stack.back().BreakBeforeParameter) return true; if (startsSegmentOfBuilderTypeCall(Current) && @@ -352,9 +353,20 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, // disallowing any further line breaks if there is no line break after the // opening parenthesis. Don't break if it doesn't conserve columns. if (Style.AlignAfterOpenBracket == FormatStyle::BAS_AlwaysBreak && - Previous.is(tok::l_paren) && State.Column > getNewLineColumn(State) && + Previous.isOneOf(tok::l_paren, TT_TemplateOpener, tok::l_square) && + State.Column > getNewLineColumn(State) && (!Previous.Previous || - !Previous.Previous->isOneOf(tok::kw_for, tok::kw_while, tok::kw_switch))) + !Previous.Previous->isOneOf(tok::kw_for, tok::kw_while, + tok::kw_switch)) && + // Don't do this for simple (no expressions) one-argument function calls + // as that feels like needlessly wasting whitespace, e.g.: + // + // caaaaaaaaaaaall( + // caaaaaaaaaaaall( + // caaaaaaaaaaaall( + // caaaaaaaaaaaaaaaaaaaaaaall(aaaaaaaaaaaaaa, aaaaaaaaa)))); + Current.FakeLParens.size() > 0 && + Current.FakeLParens.back() > prec::Unknown) State.Stack.back().NoLineBreak = true; if (Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign && @@ -400,9 +412,9 @@ void ContinuationIndenter::addTokenOnCurrentLine(LineState &State, bool DryRun, (Previous.isNot(tok::lessless) || Previous.OperatorIndex != 0 || Previous.NextOperator)) || Current.StartsBinaryExpression)) { - // Always indent relative to the RHS of the expression unless this is a - // simple assignment without binary expression on the RHS. Also indent - // relative to unary operators and the colons of constructor initializers. + // Indent relative to the RHS of the expression unless this is a simple + // assignment without binary expression on the RHS. Also indent relative to + // unary operators and the colons of constructor initializers. State.Stack.back().LastSpace = State.Column; } else if (Previous.is(TT_InheritanceColon)) { State.Stack.back().Indent = State.Column; @@ -464,10 +476,13 @@ unsigned ContinuationIndenter::addTokenOnNewLine(LineState &State, // // code // } // - // is common and should be formatted like a free-standing function. - if (Style.Language != FormatStyle::LK_JavaScript || - Current.NestingLevel != 0 || !PreviousNonComment->is(tok::equal) || - !Current.is(Keywords.kw_function)) + // is common and should be formatted like a free-standing function. The same + // goes for wrapping before the lambda return type arrow. + if (!Current.is(TT_LambdaArrow) && + (Style.Language != FormatStyle::LK_JavaScript || + Current.NestingLevel != 0 || !PreviousNonComment || + !PreviousNonComment->is(tok::equal) || + !Current.isOneOf(Keywords.kw_async, Keywords.kw_function))) State.Stack.back().NestedBlockIndent = State.Column; if (NextNonComment->isMemberAccess()) { @@ -529,6 +544,12 @@ unsigned ContinuationIndenter::addTokenOnNewLine(LineState &State, if (!Current.isTrailingComment()) State.Stack.back().LastSpace = State.Column; + if (Current.is(tok::lessless)) + // If we are breaking before a "<<", we always want to indent relative to + // RHS. This is necessary only for "<<", as we special-case it and don't + // always indent relative to the RHS. + State.Stack.back().LastSpace += 3; // 3 -> width of "<< ". + State.StartOfLineLevel = Current.NestingLevel; State.LowestLevelOnLine = Current.NestingLevel; @@ -703,11 +724,15 @@ unsigned ContinuationIndenter::moveStateToNextToken(LineState &State, if (Current.is(TT_ArraySubscriptLSquare) && State.Stack.back().StartOfArraySubscripts == 0) State.Stack.back().StartOfArraySubscripts = State.Column; - if ((Current.is(tok::question) && Style.BreakBeforeTernaryOperators) || - (Current.getPreviousNonComment() && Current.isNot(tok::colon) && - Current.getPreviousNonComment()->is(tok::question) && - !Style.BreakBeforeTernaryOperators)) + if (Style.BreakBeforeTernaryOperators && Current.is(tok::question)) State.Stack.back().QuestionColumn = State.Column; + if (!Style.BreakBeforeTernaryOperators && Current.isNot(tok::colon)) { + const FormatToken *Previous = Current.Previous; + while (Previous && Previous->isTrailingComment()) + Previous = Previous->Previous; + if (Previous && Previous->is(tok::question)) + State.Stack.back().QuestionColumn = State.Column; + } if (!Current.opensScope() && !Current.closesScope()) State.LowestLevelOnLine = std::min(State.LowestLevelOnLine, Current.NestingLevel); @@ -835,7 +860,7 @@ void ContinuationIndenter::moveStatePastFakeLParens(LineState &State, // there is a line-break right after the operator. // Exclude relational operators, as there, it is always more desirable to // have the LHS 'left' of the RHS. - if (Previous && Previous->getPrecedence() > prec::Assignment && + if (Previous && Previous->getPrecedence() != prec::Assignment && Previous->isOneOf(TT_BinaryOperator, TT_ConditionalExpr) && Previous->getPrecedence() != prec::Relational) { bool BreakBeforeOperator = @@ -857,7 +882,8 @@ void ContinuationIndenter::moveStatePastFakeLParens(LineState &State, // ParameterToInnerFunction)); if (*I > prec::Unknown) NewParenState.LastSpace = std::max(NewParenState.LastSpace, State.Column); - if (*I != prec::Conditional && !Current.is(TT_UnaryOperator)) + if (*I != prec::Conditional && !Current.is(TT_UnaryOperator) && + Style.AlignAfterOpenBracket != FormatStyle::BAS_DontAlign) NewParenState.StartOfFunctionCall = State.Column; // Always indent conditional expressions. Never indent expression where @@ -1022,6 +1048,9 @@ void ContinuationIndenter::moveStateToNewBlock(LineState &State) { unsigned ContinuationIndenter::addMultilineToken(const FormatToken &Current, LineState &State) { + if (!Current.IsMultiline) + return 0; + // Break before further function parameters on all levels. for (unsigned i = 0, e = State.Stack.size(); i != e; ++i) State.Stack[i].BreakBeforeParameter = true; @@ -1060,7 +1089,8 @@ unsigned ContinuationIndenter::breakProtrudingToken(const FormatToken &Current, // FIXME: String literal breaking is currently disabled for Java and JS, as // it requires strings to be merged using "+" which we don't support. if (Style.Language == FormatStyle::LK_Java || - Style.Language == FormatStyle::LK_JavaScript) + Style.Language == FormatStyle::LK_JavaScript || + !Style.BreakStringLiterals) return 0; // Don't break string literals inside preprocessor directives (except for @@ -1100,10 +1130,10 @@ unsigned ContinuationIndenter::breakProtrudingToken(const FormatToken &Current, } else { return 0; } - } else if (Current.is(TT_BlockComment) && Current.isTrailingComment()) { - if (!Style.ReflowComments || + } else if (Current.is(TT_BlockComment)) { + if (!Current.isTrailingComment() || !Style.ReflowComments || CommentPragmasRegex.match(Current.TokenText.substr(2))) - return 0; + return addMultilineToken(Current, State); Token.reset(new BreakableBlockComment( Current, State.Line->Level, StartColumn, Current.OriginalColumn, !Current.Previous, State.Line->InPPDirective, Encoding, Style)); diff --git a/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.h b/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.h index 9b9154ed309..21ad653c4fa 100644 --- a/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.h +++ b/gnu/llvm/tools/clang/lib/Format/ContinuationIndenter.h @@ -38,7 +38,8 @@ public: /// column \p FirstIndent. ContinuationIndenter(const FormatStyle &Style, const AdditionalKeywords &Keywords, - SourceManager &SourceMgr, WhitespaceManager &Whitespaces, + const SourceManager &SourceMgr, + WhitespaceManager &Whitespaces, encoding::Encoding Encoding, bool BinPackInconclusiveFunctions); @@ -137,7 +138,7 @@ private: FormatStyle Style; const AdditionalKeywords &Keywords; - SourceManager &SourceMgr; + const SourceManager &SourceMgr; WhitespaceManager &Whitespaces; encoding::Encoding Encoding; bool BinPackInconclusiveFunctions; diff --git a/gnu/llvm/tools/clang/lib/Format/Encoding.h b/gnu/llvm/tools/clang/lib/Format/Encoding.h index 592d7201a8a..148f7fd0e91 100644 --- a/gnu/llvm/tools/clang/lib/Format/Encoding.h +++ b/gnu/llvm/tools/clang/lib/Format/Encoding.h @@ -17,6 +17,7 @@ #define LLVM_CLANG_LIB_FORMAT_ENCODING_H #include "clang/Basic/LLVM.h" +#include "llvm/ADT/StringRef.h" #include "llvm/Support/ConvertUTF.h" #include "llvm/Support/Unicode.h" diff --git a/gnu/llvm/tools/clang/lib/Format/Format.cpp b/gnu/llvm/tools/clang/lib/Format/Format.cpp index 2689368da51..32d6bb855ad 100644 --- a/gnu/llvm/tools/clang/lib/Format/Format.cpp +++ b/gnu/llvm/tools/clang/lib/Format/Format.cpp @@ -14,7 +14,11 @@ //===----------------------------------------------------------------------===// #include "clang/Format/Format.h" +#include "AffectedRangeManager.h" #include "ContinuationIndenter.h" +#include "FormatTokenLexer.h" +#include "SortJavaScriptImports.h" +#include "TokenAnalyzer.h" #include "TokenAnnotator.h" #include "UnwrappedLineFormatter.h" #include "UnwrappedLineParser.h" @@ -22,6 +26,7 @@ #include "clang/Basic/Diagnostic.h" #include "clang/Basic/DiagnosticOptions.h" #include "clang/Basic/SourceManager.h" +#include "clang/Basic/VirtualFileSystem.h" #include "clang/Lex/Lexer.h" #include "llvm/ADT/STLExtras.h" #include "llvm/Support/Allocator.h" @@ -29,6 +34,8 @@ #include "llvm/Support/Path.h" #include "llvm/Support/Regex.h" #include "llvm/Support/YAMLTraits.h" +#include <algorithm> +#include <memory> #include <queue> #include <string> @@ -68,6 +75,16 @@ template <> struct ScalarEnumerationTraits<FormatStyle::UseTabStyle> { IO.enumCase(Value, "Always", FormatStyle::UT_Always); IO.enumCase(Value, "true", FormatStyle::UT_Always); IO.enumCase(Value, "ForIndentation", FormatStyle::UT_ForIndentation); + IO.enumCase(Value, "ForContinuationAndIndentation", + FormatStyle::UT_ForContinuationAndIndentation); + } +}; + +template <> struct ScalarEnumerationTraits<FormatStyle::JavaScriptQuoteStyle> { + static void enumeration(IO &IO, FormatStyle::JavaScriptQuoteStyle &Value) { + IO.enumCase(Value, "Leave", FormatStyle::JSQS_Leave); + IO.enumCase(Value, "Single", FormatStyle::JSQS_Single); + IO.enumCase(Value, "Double", FormatStyle::JSQS_Double); } }; @@ -275,6 +292,9 @@ template <> struct MappingTraits<FormatStyle> { Style.BreakBeforeTernaryOperators); IO.mapOptional("BreakConstructorInitializersBeforeComma", Style.BreakConstructorInitializersBeforeComma); + IO.mapOptional("BreakAfterJavaFieldAnnotations", + Style.BreakAfterJavaFieldAnnotations); + IO.mapOptional("BreakStringLiterals", Style.BreakStringLiterals); IO.mapOptional("ColumnLimit", Style.ColumnLimit); IO.mapOptional("CommentPragmas", Style.CommentPragmas); IO.mapOptional("ConstructorInitializerAllOnOneLineOrOnePerLine", @@ -289,10 +309,13 @@ template <> struct MappingTraits<FormatStyle> { Style.ExperimentalAutoDetectBinPacking); IO.mapOptional("ForEachMacros", Style.ForEachMacros); IO.mapOptional("IncludeCategories", Style.IncludeCategories); + IO.mapOptional("IncludeIsMainRegex", Style.IncludeIsMainRegex); IO.mapOptional("IndentCaseLabels", Style.IndentCaseLabels); IO.mapOptional("IndentWidth", Style.IndentWidth); IO.mapOptional("IndentWrappedFunctionNames", Style.IndentWrappedFunctionNames); + IO.mapOptional("JavaScriptQuotes", Style.JavaScriptQuotes); + IO.mapOptional("JavaScriptWrapImports", Style.JavaScriptWrapImports); IO.mapOptional("KeepEmptyLinesAtTheStartOfBlocks", Style.KeepEmptyLinesAtTheStartOfBlocks); IO.mapOptional("MacroBlockBegin", Style.MacroBlockBegin); @@ -488,8 +511,9 @@ FormatStyle getLLVMStyle() { LLVMStyle.BreakBeforeBraces = FormatStyle::BS_Attach; LLVMStyle.BraceWrapping = {false, false, false, false, false, false, false, false, false, false, false}; - LLVMStyle.BreakConstructorInitializersBeforeComma = false; LLVMStyle.BreakAfterJavaFieldAnnotations = false; + LLVMStyle.BreakConstructorInitializersBeforeComma = false; + LLVMStyle.BreakStringLiterals = true; LLVMStyle.ColumnLimit = 80; LLVMStyle.CommentPragmas = "^ IWYU pragma:"; LLVMStyle.ConstructorInitializerAllOnOneLineOrOnePerLine = false; @@ -504,9 +528,12 @@ FormatStyle getLLVMStyle() { LLVMStyle.IncludeCategories = {{"^\"(llvm|llvm-c|clang|clang-c)/", 2}, {"^(<|\"(gtest|isl|json)/)", 3}, {".*", 1}}; + LLVMStyle.IncludeIsMainRegex = "$"; LLVMStyle.IndentCaseLabels = false; LLVMStyle.IndentWrappedFunctionNames = false; LLVMStyle.IndentWidth = 2; + LLVMStyle.JavaScriptQuotes = FormatStyle::JSQS_Leave; + LLVMStyle.JavaScriptWrapImports = true; LLVMStyle.TabWidth = 8; LLVMStyle.MaxEmptyLinesToKeep = 1; LLVMStyle.KeepEmptyLinesAtTheStartOfBlocks = true; @@ -518,6 +545,7 @@ FormatStyle getLLVMStyle() { LLVMStyle.SpacesBeforeTrailingComments = 1; LLVMStyle.Standard = FormatStyle::LS_Cpp11; LLVMStyle.UseTab = FormatStyle::UT_Never; + LLVMStyle.JavaScriptQuotes = FormatStyle::JSQS_Leave; LLVMStyle.ReflowComments = true; LLVMStyle.SpacesInParentheses = false; LLVMStyle.SpacesInSquareBrackets = false; @@ -555,6 +583,7 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) { GoogleStyle.ConstructorInitializerAllOnOneLineOrOnePerLine = true; GoogleStyle.DerivePointerAlignment = true; GoogleStyle.IncludeCategories = {{"^<.*\\.h>", 1}, {"^<.*", 2}, {".*", 3}}; + GoogleStyle.IncludeIsMainRegex = "([-_](test|unittest))?$"; GoogleStyle.IndentCaseLabels = true; GoogleStyle.KeepEmptyLinesAtTheStartOfBlocks = false; GoogleStyle.ObjCSpaceAfterProperty = false; @@ -583,9 +612,12 @@ FormatStyle getGoogleStyle(FormatStyle::LanguageKind Language) { GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_Inline; GoogleStyle.AlwaysBreakBeforeMultilineStrings = false; GoogleStyle.BreakBeforeTernaryOperators = false; - GoogleStyle.CommentPragmas = "@(export|visibility) {"; + GoogleStyle.CommentPragmas = "@(export|requirecss|return|see|visibility) "; GoogleStyle.MaxEmptyLinesToKeep = 3; + GoogleStyle.NamespaceIndentation = FormatStyle::NI_All; GoogleStyle.SpacesInContainerLiterals = false; + GoogleStyle.JavaScriptQuotes = FormatStyle::JSQS_Single; + GoogleStyle.JavaScriptWrapImports = false; } else if (Language == FormatStyle::LK_Proto) { GoogleStyle.AllowShortFunctionsOnASingleLine = FormatStyle::SFS_None; GoogleStyle.SpacesInContainerLiterals = false; @@ -759,734 +791,35 @@ std::string configurationAsText(const FormatStyle &Style) { namespace { -class FormatTokenLexer { -public: - FormatTokenLexer(SourceManager &SourceMgr, FileID ID, FormatStyle &Style, - encoding::Encoding Encoding) - : FormatTok(nullptr), IsFirstToken(true), GreaterStashed(false), - LessStashed(false), Column(0), TrailingWhitespace(0), - SourceMgr(SourceMgr), ID(ID), Style(Style), - IdentTable(getFormattingLangOpts(Style)), Keywords(IdentTable), - Encoding(Encoding), FirstInLineIndex(0), FormattingDisabled(false), - MacroBlockBeginRegex(Style.MacroBlockBegin), - MacroBlockEndRegex(Style.MacroBlockEnd) { - Lex.reset(new Lexer(ID, SourceMgr.getBuffer(ID), SourceMgr, - getFormattingLangOpts(Style))); - Lex->SetKeepWhitespaceMode(true); - - for (const std::string &ForEachMacro : Style.ForEachMacros) - ForEachMacros.push_back(&IdentTable.get(ForEachMacro)); - std::sort(ForEachMacros.begin(), ForEachMacros.end()); - } - - ArrayRef<FormatToken *> lex() { - assert(Tokens.empty()); - assert(FirstInLineIndex == 0); - do { - Tokens.push_back(getNextToken()); - if (Style.Language == FormatStyle::LK_JavaScript) - tryParseJSRegexLiteral(); - tryMergePreviousTokens(); - if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline) - FirstInLineIndex = Tokens.size() - 1; - } while (Tokens.back()->Tok.isNot(tok::eof)); - return Tokens; - } - - const AdditionalKeywords &getKeywords() { return Keywords; } - -private: - void tryMergePreviousTokens() { - if (tryMerge_TMacro()) - return; - if (tryMergeConflictMarkers()) - return; - if (tryMergeLessLess()) - return; - - if (Style.Language == FormatStyle::LK_JavaScript) { - if (tryMergeTemplateString()) - return; - - static const tok::TokenKind JSIdentity[] = {tok::equalequal, tok::equal}; - static const tok::TokenKind JSNotIdentity[] = {tok::exclaimequal, - tok::equal}; - static const tok::TokenKind JSShiftEqual[] = {tok::greater, tok::greater, - tok::greaterequal}; - static const tok::TokenKind JSRightArrow[] = {tok::equal, tok::greater}; - // FIXME: Investigate what token type gives the correct operator priority. - if (tryMergeTokens(JSIdentity, TT_BinaryOperator)) - return; - if (tryMergeTokens(JSNotIdentity, TT_BinaryOperator)) - return; - if (tryMergeTokens(JSShiftEqual, TT_BinaryOperator)) - return; - if (tryMergeTokens(JSRightArrow, TT_JsFatArrow)) - return; - } - } - - bool tryMergeLessLess() { - // Merge X,less,less,Y into X,lessless,Y unless X or Y is less. - if (Tokens.size() < 3) - return false; - - bool FourthTokenIsLess = false; - if (Tokens.size() > 3) - FourthTokenIsLess = (Tokens.end() - 4)[0]->is(tok::less); - - auto First = Tokens.end() - 3; - if (First[2]->is(tok::less) || First[1]->isNot(tok::less) || - First[0]->isNot(tok::less) || FourthTokenIsLess) - return false; - - // Only merge if there currently is no whitespace between the two "<". - if (First[1]->WhitespaceRange.getBegin() != - First[1]->WhitespaceRange.getEnd()) - return false; - - First[0]->Tok.setKind(tok::lessless); - First[0]->TokenText = "<<"; - First[0]->ColumnWidth += 1; - Tokens.erase(Tokens.end() - 2); - return true; - } - - bool tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, TokenType NewType) { - if (Tokens.size() < Kinds.size()) - return false; - - SmallVectorImpl<FormatToken *>::const_iterator First = - Tokens.end() - Kinds.size(); - if (!First[0]->is(Kinds[0])) - return false; - unsigned AddLength = 0; - for (unsigned i = 1; i < Kinds.size(); ++i) { - if (!First[i]->is(Kinds[i]) || - First[i]->WhitespaceRange.getBegin() != - First[i]->WhitespaceRange.getEnd()) - return false; - AddLength += First[i]->TokenText.size(); - } - Tokens.resize(Tokens.size() - Kinds.size() + 1); - First[0]->TokenText = StringRef(First[0]->TokenText.data(), - First[0]->TokenText.size() + AddLength); - First[0]->ColumnWidth += AddLength; - First[0]->Type = NewType; - return true; - } - - // Returns \c true if \p Tok can only be followed by an operand in JavaScript. - bool precedesOperand(FormatToken *Tok) { - // NB: This is not entirely correct, as an r_paren can introduce an operand - // location in e.g. `if (foo) /bar/.exec(...);`. That is a rare enough - // corner case to not matter in practice, though. - return Tok->isOneOf(tok::period, tok::l_paren, tok::comma, tok::l_brace, - tok::r_brace, tok::l_square, tok::semi, tok::exclaim, - tok::colon, tok::question, tok::tilde) || - Tok->isOneOf(tok::kw_return, tok::kw_do, tok::kw_case, tok::kw_throw, - tok::kw_else, tok::kw_new, tok::kw_delete, tok::kw_void, - tok::kw_typeof, Keywords.kw_instanceof, - Keywords.kw_in) || - Tok->isBinaryOperator(); - } - - bool canPrecedeRegexLiteral(FormatToken *Prev) { - if (!Prev) - return true; - - // Regex literals can only follow after prefix unary operators, not after - // postfix unary operators. If the '++' is followed by a non-operand - // introducing token, the slash here is the operand and not the start of a - // regex. - if (Prev->isOneOf(tok::plusplus, tok::minusminus)) - return (Tokens.size() < 3 || precedesOperand(Tokens[Tokens.size() - 3])); - - // The previous token must introduce an operand location where regex - // literals can occur. - if (!precedesOperand(Prev)) - return false; - - return true; - } - - // Tries to parse a JavaScript Regex literal starting at the current token, - // if that begins with a slash and is in a location where JavaScript allows - // regex literals. Changes the current token to a regex literal and updates - // its text if successful. - void tryParseJSRegexLiteral() { - FormatToken *RegexToken = Tokens.back(); - if (!RegexToken->isOneOf(tok::slash, tok::slashequal)) - return; - - FormatToken *Prev = nullptr; - for (auto I = Tokens.rbegin() + 1, E = Tokens.rend(); I != E; ++I) { - // NB: Because previous pointers are not initialized yet, this cannot use - // Token.getPreviousNonComment. - if ((*I)->isNot(tok::comment)) { - Prev = *I; - break; - } - } - - if (!canPrecedeRegexLiteral(Prev)) - return; - - // 'Manually' lex ahead in the current file buffer. - const char *Offset = Lex->getBufferLocation(); - const char *RegexBegin = Offset - RegexToken->TokenText.size(); - StringRef Buffer = Lex->getBuffer(); - bool InCharacterClass = false; - bool HaveClosingSlash = false; - for (; !HaveClosingSlash && Offset != Buffer.end(); ++Offset) { - // Regular expressions are terminated with a '/', which can only be - // escaped using '\' or a character class between '[' and ']'. - // See http://www.ecma-international.org/ecma-262/5.1/#sec-7.8.5. - switch (*Offset) { - case '\\': - // Skip the escaped character. - ++Offset; - break; - case '[': - InCharacterClass = true; - break; - case ']': - InCharacterClass = false; - break; - case '/': - if (!InCharacterClass) - HaveClosingSlash = true; - break; - } - } - - RegexToken->Type = TT_RegexLiteral; - // Treat regex literals like other string_literals. - RegexToken->Tok.setKind(tok::string_literal); - RegexToken->TokenText = StringRef(RegexBegin, Offset - RegexBegin); - RegexToken->ColumnWidth = RegexToken->TokenText.size(); - - resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset))); - } - - bool tryMergeTemplateString() { - if (Tokens.size() < 2) - return false; - - FormatToken *EndBacktick = Tokens.back(); - // Backticks get lexed as tok::unknown tokens. If a template string contains - // a comment start, it gets lexed as a tok::comment, or tok::unknown if - // unterminated. - if (!EndBacktick->isOneOf(tok::comment, tok::string_literal, - tok::char_constant, tok::unknown)) - return false; - size_t CommentBacktickPos = EndBacktick->TokenText.find('`'); - // Unknown token that's not actually a backtick, or a comment that doesn't - // contain a backtick. - if (CommentBacktickPos == StringRef::npos) - return false; - - unsigned TokenCount = 0; - bool IsMultiline = false; - unsigned EndColumnInFirstLine = - EndBacktick->OriginalColumn + EndBacktick->ColumnWidth; - for (auto I = Tokens.rbegin() + 1, E = Tokens.rend(); I != E; I++) { - ++TokenCount; - if (I[0]->IsMultiline) - IsMultiline = true; - - // If there was a preceding template string, this must be the start of a - // template string, not the end. - if (I[0]->is(TT_TemplateString)) - return false; - - if (I[0]->isNot(tok::unknown) || I[0]->TokenText != "`") { - // Keep track of the rhs offset of the last token to wrap across lines - - // its the rhs offset of the first line of the template string, used to - // determine its width. - if (I[0]->IsMultiline) - EndColumnInFirstLine = I[0]->OriginalColumn + I[0]->ColumnWidth; - // If the token has newlines, the token before it (if it exists) is the - // rhs end of the previous line. - if (I[0]->NewlinesBefore > 0 && (I + 1 != E)) { - EndColumnInFirstLine = I[1]->OriginalColumn + I[1]->ColumnWidth; - IsMultiline = true; - } - continue; - } - - Tokens.resize(Tokens.size() - TokenCount); - Tokens.back()->Type = TT_TemplateString; - const char *EndOffset = - EndBacktick->TokenText.data() + 1 + CommentBacktickPos; - if (CommentBacktickPos != 0) { - // If the backtick was not the first character (e.g. in a comment), - // re-lex after the backtick position. - SourceLocation Loc = EndBacktick->Tok.getLocation(); - resetLexer(SourceMgr.getFileOffset(Loc) + CommentBacktickPos + 1); - } - Tokens.back()->TokenText = - StringRef(Tokens.back()->TokenText.data(), - EndOffset - Tokens.back()->TokenText.data()); - - unsigned EndOriginalColumn = EndBacktick->OriginalColumn; - if (EndOriginalColumn == 0) { - SourceLocation Loc = EndBacktick->Tok.getLocation(); - EndOriginalColumn = SourceMgr.getSpellingColumnNumber(Loc); - } - // If the ` is further down within the token (e.g. in a comment). - EndOriginalColumn += CommentBacktickPos; - - if (IsMultiline) { - // ColumnWidth is from backtick to last token in line. - // LastLineColumnWidth is 0 to backtick. - // x = `some content - // until here`; - Tokens.back()->ColumnWidth = - EndColumnInFirstLine - Tokens.back()->OriginalColumn; - // +1 for the ` itself. - Tokens.back()->LastLineColumnWidth = EndOriginalColumn + 1; - Tokens.back()->IsMultiline = true; - } else { - // Token simply spans from start to end, +1 for the ` itself. - Tokens.back()->ColumnWidth = - EndOriginalColumn - Tokens.back()->OriginalColumn + 1; - } - return true; - } - return false; - } - - bool tryMerge_TMacro() { - if (Tokens.size() < 4) - return false; - FormatToken *Last = Tokens.back(); - if (!Last->is(tok::r_paren)) - return false; - - FormatToken *String = Tokens[Tokens.size() - 2]; - if (!String->is(tok::string_literal) || String->IsMultiline) - return false; - - if (!Tokens[Tokens.size() - 3]->is(tok::l_paren)) - return false; - - FormatToken *Macro = Tokens[Tokens.size() - 4]; - if (Macro->TokenText != "_T") - return false; - - const char *Start = Macro->TokenText.data(); - const char *End = Last->TokenText.data() + Last->TokenText.size(); - String->TokenText = StringRef(Start, End - Start); - String->IsFirst = Macro->IsFirst; - String->LastNewlineOffset = Macro->LastNewlineOffset; - String->WhitespaceRange = Macro->WhitespaceRange; - String->OriginalColumn = Macro->OriginalColumn; - String->ColumnWidth = encoding::columnWidthWithTabs( - String->TokenText, String->OriginalColumn, Style.TabWidth, Encoding); - String->NewlinesBefore = Macro->NewlinesBefore; - String->HasUnescapedNewline = Macro->HasUnescapedNewline; - - Tokens.pop_back(); - Tokens.pop_back(); - Tokens.pop_back(); - Tokens.back() = String; - return true; - } - - bool tryMergeConflictMarkers() { - if (Tokens.back()->NewlinesBefore == 0 && Tokens.back()->isNot(tok::eof)) - return false; - - // Conflict lines look like: - // <marker> <text from the vcs> - // For example: - // >>>>>>> /file/in/file/system at revision 1234 - // - // We merge all tokens in a line that starts with a conflict marker - // into a single token with a special token type that the unwrapped line - // parser will use to correctly rebuild the underlying code. - - FileID ID; - // Get the position of the first token in the line. - unsigned FirstInLineOffset; - std::tie(ID, FirstInLineOffset) = SourceMgr.getDecomposedLoc( - Tokens[FirstInLineIndex]->getStartOfNonWhitespace()); - StringRef Buffer = SourceMgr.getBuffer(ID)->getBuffer(); - // Calculate the offset of the start of the current line. - auto LineOffset = Buffer.rfind('\n', FirstInLineOffset); - if (LineOffset == StringRef::npos) { - LineOffset = 0; - } else { - ++LineOffset; - } - - auto FirstSpace = Buffer.find_first_of(" \n", LineOffset); - StringRef LineStart; - if (FirstSpace == StringRef::npos) { - LineStart = Buffer.substr(LineOffset); - } else { - LineStart = Buffer.substr(LineOffset, FirstSpace - LineOffset); - } - - TokenType Type = TT_Unknown; - if (LineStart == "<<<<<<<" || LineStart == ">>>>") { - Type = TT_ConflictStart; - } else if (LineStart == "|||||||" || LineStart == "=======" || - LineStart == "====") { - Type = TT_ConflictAlternative; - } else if (LineStart == ">>>>>>>" || LineStart == "<<<<") { - Type = TT_ConflictEnd; - } - - if (Type != TT_Unknown) { - FormatToken *Next = Tokens.back(); - - Tokens.resize(FirstInLineIndex + 1); - // We do not need to build a complete token here, as we will skip it - // during parsing anyway (as we must not touch whitespace around conflict - // markers). - Tokens.back()->Type = Type; - Tokens.back()->Tok.setKind(tok::kw___unknown_anytype); - - Tokens.push_back(Next); - return true; - } - - return false; - } - - FormatToken *getStashedToken() { - // Create a synthesized second '>' or '<' token. - Token Tok = FormatTok->Tok; - StringRef TokenText = FormatTok->TokenText; - - unsigned OriginalColumn = FormatTok->OriginalColumn; - FormatTok = new (Allocator.Allocate()) FormatToken; - FormatTok->Tok = Tok; - SourceLocation TokLocation = - FormatTok->Tok.getLocation().getLocWithOffset(Tok.getLength() - 1); - FormatTok->Tok.setLocation(TokLocation); - FormatTok->WhitespaceRange = SourceRange(TokLocation, TokLocation); - FormatTok->TokenText = TokenText; - FormatTok->ColumnWidth = 1; - FormatTok->OriginalColumn = OriginalColumn + 1; - - return FormatTok; - } - - FormatToken *getNextToken() { - if (GreaterStashed) { - GreaterStashed = false; - return getStashedToken(); - } - if (LessStashed) { - LessStashed = false; - return getStashedToken(); - } - - FormatTok = new (Allocator.Allocate()) FormatToken; - readRawToken(*FormatTok); - SourceLocation WhitespaceStart = - FormatTok->Tok.getLocation().getLocWithOffset(-TrailingWhitespace); - FormatTok->IsFirst = IsFirstToken; - IsFirstToken = false; - - // Consume and record whitespace until we find a significant token. - unsigned WhitespaceLength = TrailingWhitespace; - while (FormatTok->Tok.is(tok::unknown)) { - StringRef Text = FormatTok->TokenText; - auto EscapesNewline = [&](int pos) { - // A '\r' here is just part of '\r\n'. Skip it. - if (pos >= 0 && Text[pos] == '\r') - --pos; - // See whether there is an odd number of '\' before this. - unsigned count = 0; - for (; pos >= 0; --pos, ++count) - if (Text[pos] != '\\') - break; - return count & 1; - }; - // FIXME: This miscounts tok:unknown tokens that are not just - // whitespace, e.g. a '`' character. - for (int i = 0, e = Text.size(); i != e; ++i) { - switch (Text[i]) { - case '\n': - ++FormatTok->NewlinesBefore; - FormatTok->HasUnescapedNewline = !EscapesNewline(i - 1); - FormatTok->LastNewlineOffset = WhitespaceLength + i + 1; - Column = 0; - break; - case '\r': - FormatTok->LastNewlineOffset = WhitespaceLength + i + 1; - Column = 0; - break; - case '\f': - case '\v': - Column = 0; - break; - case ' ': - ++Column; - break; - case '\t': - Column += Style.TabWidth - Column % Style.TabWidth; - break; - case '\\': - if (i + 1 == e || (Text[i + 1] != '\r' && Text[i + 1] != '\n')) - FormatTok->Type = TT_ImplicitStringLiteral; - break; - default: - FormatTok->Type = TT_ImplicitStringLiteral; - break; - } - if (FormatTok->Type == TT_ImplicitStringLiteral) - break; - } - - if (FormatTok->is(TT_ImplicitStringLiteral)) - break; - WhitespaceLength += FormatTok->Tok.getLength(); - - readRawToken(*FormatTok); - } - - // In case the token starts with escaped newlines, we want to - // take them into account as whitespace - this pattern is quite frequent - // in macro definitions. - // FIXME: Add a more explicit test. - while (FormatTok->TokenText.size() > 1 && FormatTok->TokenText[0] == '\\' && - FormatTok->TokenText[1] == '\n') { - ++FormatTok->NewlinesBefore; - WhitespaceLength += 2; - FormatTok->LastNewlineOffset = 2; - Column = 0; - FormatTok->TokenText = FormatTok->TokenText.substr(2); - } - - FormatTok->WhitespaceRange = SourceRange( - WhitespaceStart, WhitespaceStart.getLocWithOffset(WhitespaceLength)); - - FormatTok->OriginalColumn = Column; - - TrailingWhitespace = 0; - if (FormatTok->Tok.is(tok::comment)) { - // FIXME: Add the trimmed whitespace to Column. - StringRef UntrimmedText = FormatTok->TokenText; - FormatTok->TokenText = FormatTok->TokenText.rtrim(" \t\v\f"); - TrailingWhitespace = UntrimmedText.size() - FormatTok->TokenText.size(); - } else if (FormatTok->Tok.is(tok::raw_identifier)) { - IdentifierInfo &Info = IdentTable.get(FormatTok->TokenText); - FormatTok->Tok.setIdentifierInfo(&Info); - FormatTok->Tok.setKind(Info.getTokenID()); - if (Style.Language == FormatStyle::LK_Java && - FormatTok->isOneOf(tok::kw_struct, tok::kw_union, tok::kw_delete, - tok::kw_operator)) { - FormatTok->Tok.setKind(tok::identifier); - FormatTok->Tok.setIdentifierInfo(nullptr); - } else if (Style.Language == FormatStyle::LK_JavaScript && - FormatTok->isOneOf(tok::kw_struct, tok::kw_union, - tok::kw_operator)) { - FormatTok->Tok.setKind(tok::identifier); - FormatTok->Tok.setIdentifierInfo(nullptr); - } - } else if (FormatTok->Tok.is(tok::greatergreater)) { - FormatTok->Tok.setKind(tok::greater); - FormatTok->TokenText = FormatTok->TokenText.substr(0, 1); - GreaterStashed = true; - } else if (FormatTok->Tok.is(tok::lessless)) { - FormatTok->Tok.setKind(tok::less); - FormatTok->TokenText = FormatTok->TokenText.substr(0, 1); - LessStashed = true; - } - - // Now FormatTok is the next non-whitespace token. - - StringRef Text = FormatTok->TokenText; - size_t FirstNewlinePos = Text.find('\n'); - if (FirstNewlinePos == StringRef::npos) { - // FIXME: ColumnWidth actually depends on the start column, we need to - // take this into account when the token is moved. - FormatTok->ColumnWidth = - encoding::columnWidthWithTabs(Text, Column, Style.TabWidth, Encoding); - Column += FormatTok->ColumnWidth; - } else { - FormatTok->IsMultiline = true; - // FIXME: ColumnWidth actually depends on the start column, we need to - // take this into account when the token is moved. - FormatTok->ColumnWidth = encoding::columnWidthWithTabs( - Text.substr(0, FirstNewlinePos), Column, Style.TabWidth, Encoding); - - // The last line of the token always starts in column 0. - // Thus, the length can be precomputed even in the presence of tabs. - FormatTok->LastLineColumnWidth = encoding::columnWidthWithTabs( - Text.substr(Text.find_last_of('\n') + 1), 0, Style.TabWidth, - Encoding); - Column = FormatTok->LastLineColumnWidth; - } - - if (Style.Language == FormatStyle::LK_Cpp) { - if (!(Tokens.size() > 0 && Tokens.back()->Tok.getIdentifierInfo() && - Tokens.back()->Tok.getIdentifierInfo()->getPPKeywordID() == - tok::pp_define) && - std::find(ForEachMacros.begin(), ForEachMacros.end(), - FormatTok->Tok.getIdentifierInfo()) != ForEachMacros.end()) { - FormatTok->Type = TT_ForEachMacro; - } else if (FormatTok->is(tok::identifier)) { - if (MacroBlockBeginRegex.match(Text)) { - FormatTok->Type = TT_MacroBlockBegin; - } else if (MacroBlockEndRegex.match(Text)) { - FormatTok->Type = TT_MacroBlockEnd; - } - } - } - - return FormatTok; - } - - FormatToken *FormatTok; - bool IsFirstToken; - bool GreaterStashed, LessStashed; - unsigned Column; - unsigned TrailingWhitespace; - std::unique_ptr<Lexer> Lex; - SourceManager &SourceMgr; - FileID ID; - FormatStyle &Style; - IdentifierTable IdentTable; - AdditionalKeywords Keywords; - encoding::Encoding Encoding; - llvm::SpecificBumpPtrAllocator<FormatToken> Allocator; - // Index (in 'Tokens') of the last token that starts a new line. - unsigned FirstInLineIndex; - SmallVector<FormatToken *, 16> Tokens; - SmallVector<IdentifierInfo *, 8> ForEachMacros; - - bool FormattingDisabled; - - llvm::Regex MacroBlockBeginRegex; - llvm::Regex MacroBlockEndRegex; - - void readRawToken(FormatToken &Tok) { - Lex->LexFromRawLexer(Tok.Tok); - Tok.TokenText = StringRef(SourceMgr.getCharacterData(Tok.Tok.getLocation()), - Tok.Tok.getLength()); - // For formatting, treat unterminated string literals like normal string - // literals. - if (Tok.is(tok::unknown)) { - if (!Tok.TokenText.empty() && Tok.TokenText[0] == '"') { - Tok.Tok.setKind(tok::string_literal); - Tok.IsUnterminatedLiteral = true; - } else if (Style.Language == FormatStyle::LK_JavaScript && - Tok.TokenText == "''") { - Tok.Tok.setKind(tok::char_constant); - } - } - - if (Tok.is(tok::comment) && (Tok.TokenText == "// clang-format on" || - Tok.TokenText == "/* clang-format on */")) { - FormattingDisabled = false; - } - - Tok.Finalized = FormattingDisabled; - - if (Tok.is(tok::comment) && (Tok.TokenText == "// clang-format off" || - Tok.TokenText == "/* clang-format off */")) { - FormattingDisabled = true; - } - } - - void resetLexer(unsigned Offset) { - StringRef Buffer = SourceMgr.getBufferData(ID); - Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), - getFormattingLangOpts(Style), Buffer.begin(), - Buffer.begin() + Offset, Buffer.end())); - Lex->SetKeepWhitespaceMode(true); - TrailingWhitespace = 0; - } -}; - -static StringRef getLanguageName(FormatStyle::LanguageKind Language) { - switch (Language) { - case FormatStyle::LK_Cpp: - return "C++"; - case FormatStyle::LK_Java: - return "Java"; - case FormatStyle::LK_JavaScript: - return "JavaScript"; - case FormatStyle::LK_Proto: - return "Proto"; - default: - return "Unknown"; - } -} - -class Formatter : public UnwrappedLineConsumer { +class Formatter : public TokenAnalyzer { public: - Formatter(const FormatStyle &Style, SourceManager &SourceMgr, FileID ID, - ArrayRef<CharSourceRange> Ranges) - : Style(Style), ID(ID), SourceMgr(SourceMgr), - Whitespaces(SourceMgr, Style, - inputUsesCRLF(SourceMgr.getBufferData(ID))), - Ranges(Ranges.begin(), Ranges.end()), UnwrappedLines(1), - Encoding(encoding::detectEncoding(SourceMgr.getBufferData(ID))) { - DEBUG(llvm::dbgs() << "File encoding: " - << (Encoding == encoding::Encoding_UTF8 ? "UTF8" - : "unknown") - << "\n"); - DEBUG(llvm::dbgs() << "Language: " << getLanguageName(Style.Language) - << "\n"); - } + Formatter(const Environment &Env, const FormatStyle &Style, + bool *IncompleteFormat) + : TokenAnalyzer(Env, Style), IncompleteFormat(IncompleteFormat) {} + + tooling::Replacements + analyze(TokenAnnotator &Annotator, + SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, + FormatTokenLexer &Tokens, tooling::Replacements &Result) override { + deriveLocalStyle(AnnotatedLines); + AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(), + AnnotatedLines.end()); - tooling::Replacements format(bool *IncompleteFormat) { - tooling::Replacements Result; - FormatTokenLexer Tokens(SourceMgr, ID, Style, Encoding); - - UnwrappedLineParser Parser(Style, Tokens.getKeywords(), Tokens.lex(), - *this); - Parser.parse(); - assert(UnwrappedLines.rbegin()->empty()); - for (unsigned Run = 0, RunE = UnwrappedLines.size(); Run + 1 != RunE; - ++Run) { - DEBUG(llvm::dbgs() << "Run " << Run << "...\n"); - SmallVector<AnnotatedLine *, 16> AnnotatedLines; - for (unsigned i = 0, e = UnwrappedLines[Run].size(); i != e; ++i) { - AnnotatedLines.push_back(new AnnotatedLine(UnwrappedLines[Run][i])); - } - tooling::Replacements RunResult = - format(AnnotatedLines, Tokens, IncompleteFormat); - DEBUG({ - llvm::dbgs() << "Replacements for run " << Run << ":\n"; - for (tooling::Replacements::iterator I = RunResult.begin(), - E = RunResult.end(); - I != E; ++I) { - llvm::dbgs() << I->toString() << "\n"; - } - }); - for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) { - delete AnnotatedLines[i]; - } - Result.insert(RunResult.begin(), RunResult.end()); - Whitespaces.reset(); - } - return Result; - } + if (Style.Language == FormatStyle::LK_JavaScript && + Style.JavaScriptQuotes != FormatStyle::JSQS_Leave) + requoteJSStringLiteral(AnnotatedLines, Result); - tooling::Replacements format(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, - FormatTokenLexer &Tokens, - bool *IncompleteFormat) { - TokenAnnotator Annotator(Style, Tokens.getKeywords()); - for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) { - Annotator.annotate(*AnnotatedLines[i]); - } - deriveLocalStyle(AnnotatedLines); for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) { Annotator.calculateFormattingInformation(*AnnotatedLines[i]); } - computeAffectedLines(AnnotatedLines.begin(), AnnotatedLines.end()); Annotator.setCommentLineLevels(AnnotatedLines); - ContinuationIndenter Indenter(Style, Tokens.getKeywords(), SourceMgr, - Whitespaces, Encoding, + + WhitespaceManager Whitespaces( + Env.getSourceManager(), Style, + inputUsesCRLF(Env.getSourceManager().getBufferData(Env.getFileID()))); + ContinuationIndenter Indenter(Style, Tokens.getKeywords(), + Env.getSourceManager(), Whitespaces, Encoding, BinPackInconclusiveFunctions); UnwrappedLineFormatter(&Indenter, &Whitespaces, Style, Tokens.getKeywords(), IncompleteFormat) @@ -1495,137 +828,80 @@ public: } private: - // Determines which lines are affected by the SourceRanges given as input. - // Returns \c true if at least one line between I and E or one of their - // children is affected. - bool computeAffectedLines(SmallVectorImpl<AnnotatedLine *>::iterator I, - SmallVectorImpl<AnnotatedLine *>::iterator E) { - bool SomeLineAffected = false; - const AnnotatedLine *PreviousLine = nullptr; - while (I != E) { - AnnotatedLine *Line = *I; - Line->LeadingEmptyLinesAffected = affectsLeadingEmptyLines(*Line->First); - - // If a line is part of a preprocessor directive, it needs to be formatted - // if any token within the directive is affected. - if (Line->InPPDirective) { - FormatToken *Last = Line->Last; - SmallVectorImpl<AnnotatedLine *>::iterator PPEnd = I + 1; - while (PPEnd != E && !(*PPEnd)->First->HasUnescapedNewline) { - Last = (*PPEnd)->Last; - ++PPEnd; - } - - if (affectsTokenRange(*Line->First, *Last, - /*IncludeLeadingNewlines=*/false)) { - SomeLineAffected = true; - markAllAsAffected(I, PPEnd); - } - I = PPEnd; + // If the last token is a double/single-quoted string literal, generates a + // replacement with a single/double quoted string literal, re-escaping the + // contents in the process. + void requoteJSStringLiteral(SmallVectorImpl<AnnotatedLine *> &Lines, + tooling::Replacements &Result) { + for (AnnotatedLine *Line : Lines) { + requoteJSStringLiteral(Line->Children, Result); + if (!Line->Affected) continue; - } - - if (nonPPLineAffected(Line, PreviousLine)) - SomeLineAffected = true; - - PreviousLine = Line; - ++I; - } - return SomeLineAffected; - } - - // Determines whether 'Line' is affected by the SourceRanges given as input. - // Returns \c true if line or one if its children is affected. - bool nonPPLineAffected(AnnotatedLine *Line, - const AnnotatedLine *PreviousLine) { - bool SomeLineAffected = false; - Line->ChildrenAffected = - computeAffectedLines(Line->Children.begin(), Line->Children.end()); - if (Line->ChildrenAffected) - SomeLineAffected = true; - - // Stores whether one of the line's tokens is directly affected. - bool SomeTokenAffected = false; - // Stores whether we need to look at the leading newlines of the next token - // in order to determine whether it was affected. - bool IncludeLeadingNewlines = false; - - // Stores whether the first child line of any of this line's tokens is - // affected. - bool SomeFirstChildAffected = false; - - for (FormatToken *Tok = Line->First; Tok; Tok = Tok->Next) { - // Determine whether 'Tok' was affected. - if (affectsTokenRange(*Tok, *Tok, IncludeLeadingNewlines)) - SomeTokenAffected = true; - - // Determine whether the first child of 'Tok' was affected. - if (!Tok->Children.empty() && Tok->Children.front()->Affected) - SomeFirstChildAffected = true; - - IncludeLeadingNewlines = Tok->Children.empty(); - } - - // Was this line moved, i.e. has it previously been on the same line as an - // affected line? - bool LineMoved = PreviousLine && PreviousLine->Affected && - Line->First->NewlinesBefore == 0; - - bool IsContinuedComment = - Line->First->is(tok::comment) && Line->First->Next == nullptr && - Line->First->NewlinesBefore < 2 && PreviousLine && - PreviousLine->Affected && PreviousLine->Last->is(tok::comment); - - if (SomeTokenAffected || SomeFirstChildAffected || LineMoved || - IsContinuedComment) { - Line->Affected = true; - SomeLineAffected = true; - } - return SomeLineAffected; - } - - // Marks all lines between I and E as well as all their children as affected. - void markAllAsAffected(SmallVectorImpl<AnnotatedLine *>::iterator I, - SmallVectorImpl<AnnotatedLine *>::iterator E) { - while (I != E) { - (*I)->Affected = true; - markAllAsAffected((*I)->Children.begin(), (*I)->Children.end()); - ++I; - } - } - - // Returns true if the range from 'First' to 'Last' intersects with one of the - // input ranges. - bool affectsTokenRange(const FormatToken &First, const FormatToken &Last, - bool IncludeLeadingNewlines) { - SourceLocation Start = First.WhitespaceRange.getBegin(); - if (!IncludeLeadingNewlines) - Start = Start.getLocWithOffset(First.LastNewlineOffset); - SourceLocation End = Last.getStartOfNonWhitespace(); - End = End.getLocWithOffset(Last.TokenText.size()); - CharSourceRange Range = CharSourceRange::getCharRange(Start, End); - return affectsCharSourceRange(Range); - } + for (FormatToken *FormatTok = Line->First; FormatTok; + FormatTok = FormatTok->Next) { + StringRef Input = FormatTok->TokenText; + if (FormatTok->Finalized || !FormatTok->isStringLiteral() || + // NB: testing for not starting with a double quote to avoid + // breaking + // `template strings`. + (Style.JavaScriptQuotes == FormatStyle::JSQS_Single && + !Input.startswith("\"")) || + (Style.JavaScriptQuotes == FormatStyle::JSQS_Double && + !Input.startswith("\'"))) + continue; - // Returns true if one of the input ranges intersect the leading empty lines - // before 'Tok'. - bool affectsLeadingEmptyLines(const FormatToken &Tok) { - CharSourceRange EmptyLineRange = CharSourceRange::getCharRange( - Tok.WhitespaceRange.getBegin(), - Tok.WhitespaceRange.getBegin().getLocWithOffset(Tok.LastNewlineOffset)); - return affectsCharSourceRange(EmptyLineRange); - } + // Change start and end quote. + bool IsSingle = Style.JavaScriptQuotes == FormatStyle::JSQS_Single; + SourceLocation Start = FormatTok->Tok.getLocation(); + auto Replace = [&](SourceLocation Start, unsigned Length, + StringRef ReplacementText) { + Result.insert(tooling::Replacement(Env.getSourceManager(), Start, + Length, ReplacementText)); + }; + Replace(Start, 1, IsSingle ? "'" : "\""); + Replace(FormatTok->Tok.getEndLoc().getLocWithOffset(-1), 1, + IsSingle ? "'" : "\""); + + // Escape internal quotes. + size_t ColumnWidth = FormatTok->TokenText.size(); + bool Escaped = false; + for (size_t i = 1; i < Input.size() - 1; i++) { + switch (Input[i]) { + case '\\': + if (!Escaped && i + 1 < Input.size() && + ((IsSingle && Input[i + 1] == '"') || + (!IsSingle && Input[i + 1] == '\''))) { + // Remove this \, it's escaping a " or ' that no longer needs + // escaping + ColumnWidth--; + Replace(Start.getLocWithOffset(i), 1, ""); + continue; + } + Escaped = !Escaped; + break; + case '\"': + case '\'': + if (!Escaped && IsSingle == (Input[i] == '\'')) { + // Escape the quote. + Replace(Start.getLocWithOffset(i), 0, "\\"); + ColumnWidth++; + } + Escaped = false; + break; + default: + Escaped = false; + break; + } + } - // Returns true if 'Range' intersects with one of the input ranges. - bool affectsCharSourceRange(const CharSourceRange &Range) { - for (SmallVectorImpl<CharSourceRange>::const_iterator I = Ranges.begin(), - E = Ranges.end(); - I != E; ++I) { - if (!SourceMgr.isBeforeInTranslationUnit(Range.getEnd(), I->getBegin()) && - !SourceMgr.isBeforeInTranslationUnit(I->getEnd(), Range.getBegin())) - return true; + // For formatting, count the number of non-escaped single quotes in them + // and adjust ColumnWidth to take the added escapes into account. + // FIXME(martinprobst): this might conflict with code breaking a long + // string literal (which clang-format doesn't do, yet). For that to + // work, this code would have to modify TokenText directly. + FormatTok->ColumnWidth = ColumnWidth; + } } - return false; } static bool inputUsesCRLF(StringRef Text) { @@ -1634,7 +910,7 @@ private: bool hasCpp03IncompatibleFormat(const SmallVectorImpl<AnnotatedLine *> &Lines) { - for (const AnnotatedLine* Line : Lines) { + for (const AnnotatedLine *Line : Lines) { if (hasCpp03IncompatibleFormat(Line->Children)) return true; for (FormatToken *Tok = Line->First->Next; Tok; Tok = Tok->Next) { @@ -1652,7 +928,7 @@ private: int countVariableAlignments(const SmallVectorImpl<AnnotatedLine *> &Lines) { int AlignmentDiff = 0; - for (const AnnotatedLine* Line : Lines) { + for (const AnnotatedLine *Line : Lines) { AlignmentDiff += countVariableAlignments(Line->Children); for (FormatToken *Tok = Line->First; Tok && Tok->Next; Tok = Tok->Next) { if (!Tok->is(TT_PointerOrReference)) @@ -1699,24 +975,219 @@ private: HasBinPackedFunction || !HasOnePerLineFunction; } - void consumeUnwrappedLine(const UnwrappedLine &TheLine) override { - assert(!UnwrappedLines.empty()); - UnwrappedLines.back().push_back(TheLine); + bool BinPackInconclusiveFunctions; + bool *IncompleteFormat; +}; + +// This class clean up the erroneous/redundant code around the given ranges in +// file. +class Cleaner : public TokenAnalyzer { +public: + Cleaner(const Environment &Env, const FormatStyle &Style) + : TokenAnalyzer(Env, Style), + DeletedTokens(FormatTokenLess(Env.getSourceManager())) {} + + // FIXME: eliminate unused parameters. + tooling::Replacements + analyze(TokenAnnotator &Annotator, + SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, + FormatTokenLexer &Tokens, tooling::Replacements &Result) override { + // FIXME: in the current implementation the granularity of affected range + // is an annotated line. However, this is not sufficient. Furthermore, + // redundant code introduced by replacements does not necessarily + // intercept with ranges of replacements that result in the redundancy. + // To determine if some redundant code is actually introduced by + // replacements(e.g. deletions), we need to come up with a more + // sophisticated way of computing affected ranges. + AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(), + AnnotatedLines.end()); + + checkEmptyNamespace(AnnotatedLines); + + for (auto &Line : AnnotatedLines) { + if (Line->Affected) { + cleanupRight(Line->First, tok::comma, tok::comma); + cleanupRight(Line->First, TT_CtorInitializerColon, tok::comma); + cleanupLeft(Line->First, TT_CtorInitializerComma, tok::l_brace); + cleanupLeft(Line->First, TT_CtorInitializerColon, tok::l_brace); + } + } + + return generateFixes(); } - void finishRun() override { - UnwrappedLines.push_back(SmallVector<UnwrappedLine, 16>()); +private: + bool containsOnlyComments(const AnnotatedLine &Line) { + for (FormatToken *Tok = Line.First; Tok != nullptr; Tok = Tok->Next) { + if (Tok->isNot(tok::comment)) + return false; + } + return true; } - FormatStyle Style; - FileID ID; - SourceManager &SourceMgr; - WhitespaceManager Whitespaces; - SmallVector<CharSourceRange, 8> Ranges; - SmallVector<SmallVector<UnwrappedLine, 16>, 2> UnwrappedLines; + // Iterate through all lines and remove any empty (nested) namespaces. + void checkEmptyNamespace(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines) { + for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) { + auto &Line = *AnnotatedLines[i]; + if (Line.startsWith(tok::kw_namespace) || + Line.startsWith(tok::kw_inline, tok::kw_namespace)) { + checkEmptyNamespace(AnnotatedLines, i, i); + } + } - encoding::Encoding Encoding; - bool BinPackInconclusiveFunctions; + for (auto Line : DeletedLines) { + FormatToken *Tok = AnnotatedLines[Line]->First; + while (Tok) { + deleteToken(Tok); + Tok = Tok->Next; + } + } + } + + // The function checks if the namespace, which starts from \p CurrentLine, and + // its nested namespaces are empty and delete them if they are empty. It also + // sets \p NewLine to the last line checked. + // Returns true if the current namespace is empty. + bool checkEmptyNamespace(SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, + unsigned CurrentLine, unsigned &NewLine) { + unsigned InitLine = CurrentLine, End = AnnotatedLines.size(); + if (Style.BraceWrapping.AfterNamespace) { + // If the left brace is in a new line, we should consume it first so that + // it does not make the namespace non-empty. + // FIXME: error handling if there is no left brace. + if (!AnnotatedLines[++CurrentLine]->startsWith(tok::l_brace)) { + NewLine = CurrentLine; + return false; + } + } else if (!AnnotatedLines[CurrentLine]->endsWith(tok::l_brace)) { + return false; + } + while (++CurrentLine < End) { + if (AnnotatedLines[CurrentLine]->startsWith(tok::r_brace)) + break; + + if (AnnotatedLines[CurrentLine]->startsWith(tok::kw_namespace) || + AnnotatedLines[CurrentLine]->startsWith(tok::kw_inline, + tok::kw_namespace)) { + if (!checkEmptyNamespace(AnnotatedLines, CurrentLine, NewLine)) + return false; + CurrentLine = NewLine; + continue; + } + + if (containsOnlyComments(*AnnotatedLines[CurrentLine])) + continue; + + // If there is anything other than comments or nested namespaces in the + // current namespace, the namespace cannot be empty. + NewLine = CurrentLine; + return false; + } + + NewLine = CurrentLine; + if (CurrentLine >= End) + return false; + + // Check if the empty namespace is actually affected by changed ranges. + if (!AffectedRangeMgr.affectsCharSourceRange(CharSourceRange::getCharRange( + AnnotatedLines[InitLine]->First->Tok.getLocation(), + AnnotatedLines[CurrentLine]->Last->Tok.getEndLoc()))) + return false; + + for (unsigned i = InitLine; i <= CurrentLine; ++i) { + DeletedLines.insert(i); + } + + return true; + } + + // Checks pairs {start, start->next},..., {end->previous, end} and deletes one + // of the token in the pair if the left token has \p LK token kind and the + // right token has \p RK token kind. If \p DeleteLeft is true, the left token + // is deleted on match; otherwise, the right token is deleted. + template <typename LeftKind, typename RightKind> + void cleanupPair(FormatToken *Start, LeftKind LK, RightKind RK, + bool DeleteLeft) { + auto NextNotDeleted = [this](const FormatToken &Tok) -> FormatToken * { + for (auto *Res = Tok.Next; Res; Res = Res->Next) + if (!Res->is(tok::comment) && + DeletedTokens.find(Res) == DeletedTokens.end()) + return Res; + return nullptr; + }; + for (auto *Left = Start; Left;) { + auto *Right = NextNotDeleted(*Left); + if (!Right) + break; + if (Left->is(LK) && Right->is(RK)) { + deleteToken(DeleteLeft ? Left : Right); + // If the right token is deleted, we should keep the left token + // unchanged and pair it with the new right token. + if (!DeleteLeft) + continue; + } + Left = Right; + } + } + + template <typename LeftKind, typename RightKind> + void cleanupLeft(FormatToken *Start, LeftKind LK, RightKind RK) { + cleanupPair(Start, LK, RK, /*DeleteLeft=*/true); + } + + template <typename LeftKind, typename RightKind> + void cleanupRight(FormatToken *Start, LeftKind LK, RightKind RK) { + cleanupPair(Start, LK, RK, /*DeleteLeft=*/false); + } + + // Delete the given token. + inline void deleteToken(FormatToken *Tok) { + if (Tok) + DeletedTokens.insert(Tok); + } + + tooling::Replacements generateFixes() { + tooling::Replacements Fixes; + std::vector<FormatToken *> Tokens; + std::copy(DeletedTokens.begin(), DeletedTokens.end(), + std::back_inserter(Tokens)); + + // Merge multiple continuous token deletions into one big deletion so that + // the number of replacements can be reduced. This makes computing affected + // ranges more efficient when we run reformat on the changed code. + unsigned Idx = 0; + while (Idx < Tokens.size()) { + unsigned St = Idx, End = Idx; + while ((End + 1) < Tokens.size() && + Tokens[End]->Next == Tokens[End + 1]) { + End++; + } + auto SR = CharSourceRange::getCharRange(Tokens[St]->Tok.getLocation(), + Tokens[End]->Tok.getEndLoc()); + Fixes.insert(tooling::Replacement(Env.getSourceManager(), SR, "")); + Idx = End + 1; + } + + return Fixes; + } + + // Class for less-than inequality comparason for the set `RedundantTokens`. + // We store tokens in the order they appear in the translation unit so that + // we do not need to sort them in `generateFixes()`. + struct FormatTokenLess { + FormatTokenLess(const SourceManager &SM) : SM(SM) {} + + bool operator()(const FormatToken *LHS, const FormatToken *RHS) const { + return SM.isBeforeInTranslationUnit(LHS->Tok.getLocation(), + RHS->Tok.getLocation()); + } + const SourceManager &SM; + }; + + // Tokens to be deleted. + std::set<FormatToken *, FormatTokenLess> DeletedTokens; + // The line numbers of lines to be deleted. + std::set<unsigned> DeletedLines; }; struct IncludeDirective { @@ -1742,7 +1213,7 @@ static bool affectsRange(ArrayRef<tooling::Range> Ranges, unsigned Start, // Sorts a block of includes given by 'Includes' alphabetically adding the // necessary replacement to 'Replaces'. 'Includes' must be in strict source // order. -static void sortIncludes(const FormatStyle &Style, +static void sortCppIncludes(const FormatStyle &Style, const SmallVectorImpl<IncludeDirective> &Includes, ArrayRef<tooling::Range> Ranges, StringRef FileName, tooling::Replacements &Replaces, unsigned *Cursor) { @@ -1752,21 +1223,15 @@ static void sortIncludes(const FormatStyle &Style, SmallVector<unsigned, 16> Indices; for (unsigned i = 0, e = Includes.size(); i != e; ++i) Indices.push_back(i); - std::sort(Indices.begin(), Indices.end(), [&](unsigned LHSI, unsigned RHSI) { - return std::tie(Includes[LHSI].Category, Includes[LHSI].Filename) < - std::tie(Includes[RHSI].Category, Includes[RHSI].Filename); - }); + std::stable_sort( + Indices.begin(), Indices.end(), [&](unsigned LHSI, unsigned RHSI) { + return std::tie(Includes[LHSI].Category, Includes[LHSI].Filename) < + std::tie(Includes[RHSI].Category, Includes[RHSI].Filename); + }); // If the #includes are out of order, we generate a single replacement fixing // the entire block. Otherwise, no replacement is generated. - bool OutOfOrder = false; - for (unsigned i = 1, e = Indices.size(); i != e; ++i) { - if (Indices[i] != i) { - OutOfOrder = true; - break; - } - } - if (!OutOfOrder) + if (std::is_sorted(Indices.begin(), Indices.end())) return; std::string result; @@ -1796,17 +1261,73 @@ static void sortIncludes(const FormatStyle &Style, result.size(), result)); } -tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, - ArrayRef<tooling::Range> Ranges, - StringRef FileName, unsigned *Cursor) { - tooling::Replacements Replaces; - if (!Style.SortIncludes) - return Replaces; +namespace { + +// This class manages priorities of #include categories and calculates +// priorities for headers. +class IncludeCategoryManager { +public: + IncludeCategoryManager(const FormatStyle &Style, StringRef FileName) + : Style(Style), FileName(FileName) { + FileStem = llvm::sys::path::stem(FileName); + for (const auto &Category : Style.IncludeCategories) + CategoryRegexs.emplace_back(Category.Regex); + IsMainFile = FileName.endswith(".c") || FileName.endswith(".cc") || + FileName.endswith(".cpp") || FileName.endswith(".c++") || + FileName.endswith(".cxx") || FileName.endswith(".m") || + FileName.endswith(".mm"); + } + + // Returns the priority of the category which \p IncludeName belongs to. + // If \p CheckMainHeader is true and \p IncludeName is a main header, returns + // 0. Otherwise, returns the priority of the matching category or INT_MAX. + int getIncludePriority(StringRef IncludeName, bool CheckMainHeader) { + int Ret = INT_MAX; + for (unsigned i = 0, e = CategoryRegexs.size(); i != e; ++i) + if (CategoryRegexs[i].match(IncludeName)) { + Ret = Style.IncludeCategories[i].Priority; + break; + } + if (CheckMainHeader && IsMainFile && Ret > 0 && isMainHeader(IncludeName)) + Ret = 0; + return Ret; + } + +private: + bool isMainHeader(StringRef IncludeName) const { + if (!IncludeName.startswith("\"")) + return false; + StringRef HeaderStem = + llvm::sys::path::stem(IncludeName.drop_front(1).drop_back(1)); + if (FileStem.startswith(HeaderStem)) { + llvm::Regex MainIncludeRegex( + (HeaderStem + Style.IncludeIsMainRegex).str()); + if (MainIncludeRegex.match(FileStem)) + return true; + } + return false; + } + + const FormatStyle &Style; + bool IsMainFile; + StringRef FileName; + StringRef FileStem; + SmallVector<llvm::Regex, 4> CategoryRegexs; +}; + +const char IncludeRegexPattern[] = + R"(^[\t\ ]*#[\t\ ]*(import|include)[^"<]*(["<][^">]*[">]))"; + +} // anonymous namespace +tooling::Replacements sortCppIncludes(const FormatStyle &Style, StringRef Code, + ArrayRef<tooling::Range> Ranges, + StringRef FileName, + tooling::Replacements &Replaces, + unsigned *Cursor) { unsigned Prev = 0; unsigned SearchFrom = 0; - llvm::Regex IncludeRegex( - R"(^[\t\ ]*#[\t\ ]*(import|include)[^"<]*(["<][^">]*[">]))"); + llvm::Regex IncludeRegex(IncludeRegexPattern); SmallVector<StringRef, 4> Matches; SmallVector<IncludeDirective, 16> IncludesInBlock; @@ -1817,19 +1338,9 @@ tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, // // FIXME: Do some sanity checking, e.g. edit distance of the base name, to fix // cases where the first #include is unlikely to be the main header. - bool IsSource = FileName.endswith(".c") || FileName.endswith(".cc") || - FileName.endswith(".cpp") || FileName.endswith(".c++") || - FileName.endswith(".cxx") || FileName.endswith(".m") || - FileName.endswith(".mm"); - StringRef FileStem = llvm::sys::path::stem(FileName); + IncludeCategoryManager Categories(Style, FileName); bool FirstIncludeBlock = true; bool MainIncludeFound = false; - - // Create pre-compiled regular expressions for the #include categories. - SmallVector<llvm::Regex, 4> CategoryRegexs; - for (const auto &Category : Style.IncludeCategories) - CategoryRegexs.emplace_back(Category.Regex); - bool FormattingOff = false; for (;;) { @@ -1846,26 +1357,15 @@ tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, if (!FormattingOff && !Line.endswith("\\")) { if (IncludeRegex.match(Line, &Matches)) { StringRef IncludeName = Matches[2]; - int Category = INT_MAX; - for (unsigned i = 0, e = CategoryRegexs.size(); i != e; ++i) { - if (CategoryRegexs[i].match(IncludeName)) { - Category = Style.IncludeCategories[i].Priority; - break; - } - } - if (IsSource && !MainIncludeFound && Category > 0 && - FirstIncludeBlock && IncludeName.startswith("\"")) { - StringRef HeaderStem = - llvm::sys::path::stem(IncludeName.drop_front(1).drop_back(1)); - if (FileStem.startswith(HeaderStem)) { - Category = 0; - MainIncludeFound = true; - } - } + int Category = Categories.getIncludePriority( + IncludeName, + /*CheckMainHeader=*/!MainIncludeFound && FirstIncludeBlock); + if (Category == 0) + MainIncludeFound = true; IncludesInBlock.push_back({IncludeName, Line, Prev, Category}); } else if (!IncludesInBlock.empty()) { - sortIncludes(Style, IncludesInBlock, Ranges, FileName, Replaces, - Cursor); + sortCppIncludes(Style, IncludesInBlock, Ranges, FileName, Replaces, + Cursor); IncludesInBlock.clear(); FirstIncludeBlock = false; } @@ -1876,47 +1376,280 @@ tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, SearchFrom = Pos + 1; } if (!IncludesInBlock.empty()) - sortIncludes(Style, IncludesInBlock, Ranges, FileName, Replaces, Cursor); + sortCppIncludes(Style, IncludesInBlock, Ranges, FileName, Replaces, Cursor); return Replaces; } -tooling::Replacements reformat(const FormatStyle &Style, - SourceManager &SourceMgr, FileID ID, - ArrayRef<CharSourceRange> Ranges, +tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, + ArrayRef<tooling::Range> Ranges, + StringRef FileName, unsigned *Cursor) { + tooling::Replacements Replaces; + if (!Style.SortIncludes) + return Replaces; + if (Style.Language == FormatStyle::LanguageKind::LK_JavaScript) + return sortJavaScriptImports(Style, Code, Ranges, FileName); + sortCppIncludes(Style, Code, Ranges, FileName, Replaces, Cursor); + return Replaces; +} + +template <typename T> +static llvm::Expected<tooling::Replacements> +processReplacements(T ProcessFunc, StringRef Code, + const tooling::Replacements &Replaces, + const FormatStyle &Style) { + if (Replaces.empty()) + return tooling::Replacements(); + + auto NewCode = applyAllReplacements(Code, Replaces); + if (!NewCode) + return NewCode.takeError(); + std::vector<tooling::Range> ChangedRanges = + tooling::calculateChangedRanges(Replaces); + StringRef FileName = Replaces.begin()->getFilePath(); + + tooling::Replacements FormatReplaces = + ProcessFunc(Style, *NewCode, ChangedRanges, FileName); + + return mergeReplacements(Replaces, FormatReplaces); +} + +llvm::Expected<tooling::Replacements> +formatReplacements(StringRef Code, const tooling::Replacements &Replaces, + const FormatStyle &Style) { + // We need to use lambda function here since there are two versions of + // `sortIncludes`. + auto SortIncludes = [](const FormatStyle &Style, StringRef Code, + std::vector<tooling::Range> Ranges, + StringRef FileName) -> tooling::Replacements { + return sortIncludes(Style, Code, Ranges, FileName); + }; + auto SortedReplaces = + processReplacements(SortIncludes, Code, Replaces, Style); + if (!SortedReplaces) + return SortedReplaces.takeError(); + + // We need to use lambda function here since there are two versions of + // `reformat`. + auto Reformat = [](const FormatStyle &Style, StringRef Code, + std::vector<tooling::Range> Ranges, + StringRef FileName) -> tooling::Replacements { + return reformat(Style, Code, Ranges, FileName); + }; + return processReplacements(Reformat, Code, *SortedReplaces, Style); +} + +namespace { + +inline bool isHeaderInsertion(const tooling::Replacement &Replace) { + return Replace.getOffset() == UINT_MAX && + llvm::Regex(IncludeRegexPattern).match(Replace.getReplacementText()); +} + +void skipComments(Lexer &Lex, Token &Tok) { + while (Tok.is(tok::comment)) + if (Lex.LexFromRawLexer(Tok)) + return; +} + +// Check if a sequence of tokens is like "#<Name> <raw_identifier>". If it is, +// \p Tok will be the token after this directive; otherwise, it can be any token +// after the given \p Tok (including \p Tok). +bool checkAndConsumeDirectiveWithName(Lexer &Lex, StringRef Name, Token &Tok) { + bool Matched = Tok.is(tok::hash) && !Lex.LexFromRawLexer(Tok) && + Tok.is(tok::raw_identifier) && + Tok.getRawIdentifier() == Name && !Lex.LexFromRawLexer(Tok) && + Tok.is(tok::raw_identifier); + if (Matched) + Lex.LexFromRawLexer(Tok); + return Matched; +} + +unsigned getOffsetAfterHeaderGuardsAndComments(StringRef FileName, + StringRef Code, + const FormatStyle &Style) { + std::unique_ptr<Environment> Env = + Environment::CreateVirtualEnvironment(Code, FileName, /*Ranges=*/{}); + const SourceManager &SourceMgr = Env->getSourceManager(); + Lexer Lex(Env->getFileID(), SourceMgr.getBuffer(Env->getFileID()), SourceMgr, + getFormattingLangOpts(Style)); + Token Tok; + // Get the first token. + Lex.LexFromRawLexer(Tok); + skipComments(Lex, Tok); + unsigned AfterComments = SourceMgr.getFileOffset(Tok.getLocation()); + if (checkAndConsumeDirectiveWithName(Lex, "ifndef", Tok)) { + skipComments(Lex, Tok); + if (checkAndConsumeDirectiveWithName(Lex, "define", Tok)) + return SourceMgr.getFileOffset(Tok.getLocation()); + } + return AfterComments; +} + +// FIXME: we also need to insert a '\n' at the end of the code if we have an +// insertion with offset Code.size(), and there is no '\n' at the end of the +// code. +// FIXME: do not insert headers into conditional #include blocks, e.g. #includes +// surrounded by compile condition "#if...". +// FIXME: insert empty lines between newly created blocks. +tooling::Replacements +fixCppIncludeInsertions(StringRef Code, const tooling::Replacements &Replaces, + const FormatStyle &Style) { + if (Style.Language != FormatStyle::LanguageKind::LK_Cpp) + return Replaces; + + tooling::Replacements HeaderInsertions; + for (const auto &R : Replaces) { + if (isHeaderInsertion(R)) + HeaderInsertions.insert(R); + else if (R.getOffset() == UINT_MAX) + llvm::errs() << "Insertions other than header #include insertion are " + "not supported! " + << R.getReplacementText() << "\n"; + } + if (HeaderInsertions.empty()) + return Replaces; + tooling::Replacements Result; + std::set_difference(Replaces.begin(), Replaces.end(), + HeaderInsertions.begin(), HeaderInsertions.end(), + std::inserter(Result, Result.begin())); + + llvm::Regex IncludeRegex(IncludeRegexPattern); + llvm::Regex DefineRegex(R"(^[\t\ ]*#[\t\ ]*define[\t\ ]*[^\\]*$)"); + SmallVector<StringRef, 4> Matches; + + StringRef FileName = Replaces.begin()->getFilePath(); + IncludeCategoryManager Categories(Style, FileName); + + // Record the offset of the end of the last include in each category. + std::map<int, int> CategoryEndOffsets; + // All possible priorities. + // Add 0 for main header and INT_MAX for headers that are not in any category. + std::set<int> Priorities = {0, INT_MAX}; + for (const auto &Category : Style.IncludeCategories) + Priorities.insert(Category.Priority); + int FirstIncludeOffset = -1; + // All new headers should be inserted after this offset. + unsigned MinInsertOffset = + getOffsetAfterHeaderGuardsAndComments(FileName, Code, Style); + StringRef TrimmedCode = Code.drop_front(MinInsertOffset); + SmallVector<StringRef, 32> Lines; + TrimmedCode.split(Lines, '\n'); + unsigned Offset = MinInsertOffset; + unsigned NextLineOffset; + std::set<StringRef> ExistingIncludes; + for (auto Line : Lines) { + NextLineOffset = std::min(Code.size(), Offset + Line.size() + 1); + if (IncludeRegex.match(Line, &Matches)) { + StringRef IncludeName = Matches[2]; + ExistingIncludes.insert(IncludeName); + int Category = Categories.getIncludePriority( + IncludeName, /*CheckMainHeader=*/FirstIncludeOffset < 0); + CategoryEndOffsets[Category] = NextLineOffset; + if (FirstIncludeOffset < 0) + FirstIncludeOffset = Offset; + } + Offset = NextLineOffset; + } + + // Populate CategoryEndOfssets: + // - Ensure that CategoryEndOffset[Highest] is always populated. + // - If CategoryEndOffset[Priority] isn't set, use the next higher value that + // is set, up to CategoryEndOffset[Highest]. + auto Highest = Priorities.begin(); + if (CategoryEndOffsets.find(*Highest) == CategoryEndOffsets.end()) { + if (FirstIncludeOffset >= 0) + CategoryEndOffsets[*Highest] = FirstIncludeOffset; + else + CategoryEndOffsets[*Highest] = MinInsertOffset; + } + // By this point, CategoryEndOffset[Highest] is always set appropriately: + // - to an appropriate location before/after existing #includes, or + // - to right after the header guard, or + // - to the beginning of the file. + for (auto I = ++Priorities.begin(), E = Priorities.end(); I != E; ++I) + if (CategoryEndOffsets.find(*I) == CategoryEndOffsets.end()) + CategoryEndOffsets[*I] = CategoryEndOffsets[*std::prev(I)]; + + for (const auto &R : HeaderInsertions) { + auto IncludeDirective = R.getReplacementText(); + bool Matched = IncludeRegex.match(IncludeDirective, &Matches); + assert(Matched && "Header insertion replacement must have replacement text " + "'#include ...'"); + (void)Matched; + auto IncludeName = Matches[2]; + if (ExistingIncludes.find(IncludeName) != ExistingIncludes.end()) { + DEBUG(llvm::dbgs() << "Skip adding existing include : " << IncludeName + << "\n"); + continue; + } + int Category = + Categories.getIncludePriority(IncludeName, /*CheckMainHeader=*/true); + Offset = CategoryEndOffsets[Category]; + std::string NewInclude = !IncludeDirective.endswith("\n") + ? (IncludeDirective + "\n").str() + : IncludeDirective.str(); + Result.insert(tooling::Replacement(FileName, Offset, 0, NewInclude)); + } + return Result; +} + +} // anonymous namespace + +llvm::Expected<tooling::Replacements> +cleanupAroundReplacements(StringRef Code, const tooling::Replacements &Replaces, + const FormatStyle &Style) { + // We need to use lambda function here since there are two versions of + // `cleanup`. + auto Cleanup = [](const FormatStyle &Style, StringRef Code, + std::vector<tooling::Range> Ranges, + StringRef FileName) -> tooling::Replacements { + return cleanup(Style, Code, Ranges, FileName); + }; + // Make header insertion replacements insert new headers into correct blocks. + tooling::Replacements NewReplaces = + fixCppIncludeInsertions(Code, Replaces, Style); + return processReplacements(Cleanup, Code, NewReplaces, Style); +} + +tooling::Replacements reformat(const FormatStyle &Style, SourceManager &SM, + FileID ID, ArrayRef<CharSourceRange> Ranges, bool *IncompleteFormat) { FormatStyle Expanded = expandPresets(Style); if (Expanded.DisableFormat) return tooling::Replacements(); - Formatter formatter(Expanded, SourceMgr, ID, Ranges); - return formatter.format(IncompleteFormat); + + Environment Env(SM, ID, Ranges); + Formatter Format(Env, Expanded, IncompleteFormat); + return Format.process(); } tooling::Replacements reformat(const FormatStyle &Style, StringRef Code, ArrayRef<tooling::Range> Ranges, StringRef FileName, bool *IncompleteFormat) { - if (Style.DisableFormat) + FormatStyle Expanded = expandPresets(Style); + if (Expanded.DisableFormat) return tooling::Replacements(); - IntrusiveRefCntPtr<vfs::InMemoryFileSystem> InMemoryFileSystem( - new vfs::InMemoryFileSystem); - FileManager Files(FileSystemOptions(), InMemoryFileSystem); - DiagnosticsEngine Diagnostics( - IntrusiveRefCntPtr<DiagnosticIDs>(new DiagnosticIDs), - new DiagnosticOptions); - SourceManager SourceMgr(Diagnostics, Files); - InMemoryFileSystem->addFile( - FileName, 0, llvm::MemoryBuffer::getMemBuffer( - Code, FileName, /*RequiresNullTerminator=*/false)); - FileID ID = SourceMgr.createFileID(Files.getFile(FileName), SourceLocation(), - clang::SrcMgr::C_User); - SourceLocation StartOfFile = SourceMgr.getLocForStartOfFile(ID); - std::vector<CharSourceRange> CharRanges; - for (const tooling::Range &Range : Ranges) { - SourceLocation Start = StartOfFile.getLocWithOffset(Range.getOffset()); - SourceLocation End = Start.getLocWithOffset(Range.getLength()); - CharRanges.push_back(CharSourceRange::getCharRange(Start, End)); - } - return reformat(Style, SourceMgr, ID, CharRanges, IncompleteFormat); + std::unique_ptr<Environment> Env = + Environment::CreateVirtualEnvironment(Code, FileName, Ranges); + Formatter Format(*Env, Expanded, IncompleteFormat); + return Format.process(); +} + +tooling::Replacements cleanup(const FormatStyle &Style, SourceManager &SM, + FileID ID, ArrayRef<CharSourceRange> Ranges) { + Environment Env(SM, ID, Ranges); + Cleaner Clean(Env, Style); + return Clean.process(); +} + +tooling::Replacements cleanup(const FormatStyle &Style, StringRef Code, + ArrayRef<tooling::Range> Ranges, + StringRef FileName) { + std::unique_ptr<Environment> Env = + Environment::CreateVirtualEnvironment(Code, FileName, Ranges); + Cleaner Clean(*Env, Style); + return Clean.process(); } LangOptions getFormattingLangOpts(const FormatStyle &Style) { @@ -1930,7 +1663,7 @@ LangOptions getFormattingLangOpts(const FormatStyle &Style) { LangOpts.Bool = 1; LangOpts.ObjC1 = 1; LangOpts.ObjC2 = 1; - LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally. + LangOpts.MicrosoftExt = 1; // To get kw___try, kw___finally. LangOpts.DeclSpecKeyword = 1; // To get __declspec. return LangOpts; } @@ -1960,7 +1693,10 @@ static FormatStyle::LanguageKind getLanguageByFileName(StringRef FileName) { } FormatStyle getStyle(StringRef StyleName, StringRef FileName, - StringRef FallbackStyle) { + StringRef FallbackStyle, vfs::FileSystem *FS) { + if (!FS) { + FS = vfs::getRealFileSystem().get(); + } FormatStyle Style = getLLVMStyle(); Style.Language = getLanguageByFileName(FileName); if (!getPredefinedStyle(FallbackStyle, Style.Language, &Style)) { @@ -1991,28 +1727,34 @@ FormatStyle getStyle(StringRef StyleName, StringRef FileName, llvm::sys::fs::make_absolute(Path); for (StringRef Directory = Path; !Directory.empty(); Directory = llvm::sys::path::parent_path(Directory)) { - if (!llvm::sys::fs::is_directory(Directory)) + + auto Status = FS->status(Directory); + if (!Status || + Status->getType() != llvm::sys::fs::file_type::directory_file) { continue; + } + SmallString<128> ConfigFile(Directory); llvm::sys::path::append(ConfigFile, ".clang-format"); DEBUG(llvm::dbgs() << "Trying " << ConfigFile << "...\n"); - bool IsFile = false; - // Ignore errors from is_regular_file: we only need to know if we can read - // the file or not. - llvm::sys::fs::is_regular_file(Twine(ConfigFile), IsFile); + Status = FS->status(ConfigFile.str()); + bool IsFile = + Status && (Status->getType() == llvm::sys::fs::file_type::regular_file); if (!IsFile) { // Try _clang-format too, since dotfiles are not commonly used on Windows. ConfigFile = Directory; llvm::sys::path::append(ConfigFile, "_clang-format"); DEBUG(llvm::dbgs() << "Trying " << ConfigFile << "...\n"); - llvm::sys::fs::is_regular_file(Twine(ConfigFile), IsFile); + Status = FS->status(ConfigFile.str()); + IsFile = Status && + (Status->getType() == llvm::sys::fs::file_type::regular_file); } if (IsFile) { llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> Text = - llvm::MemoryBuffer::getFile(ConfigFile.c_str()); + FS->getBufferForFile(ConfigFile.str()); if (std::error_code EC = Text.getError()) { llvm::errs() << EC.message() << "\n"; break; diff --git a/gnu/llvm/tools/clang/lib/Format/FormatToken.cpp b/gnu/llvm/tools/clang/lib/Format/FormatToken.cpp index d6cd450d892..2ae4ddcfd08 100644 --- a/gnu/llvm/tools/clang/lib/Format/FormatToken.cpp +++ b/gnu/llvm/tools/clang/lib/Format/FormatToken.cpp @@ -53,6 +53,7 @@ bool FormatToken::isSimpleTypeSpecifier() const { case tok::kw_half: case tok::kw_float: case tok::kw_double: + case tok::kw___float128: case tok::kw_wchar_t: case tok::kw_bool: case tok::kw___underlying_type: diff --git a/gnu/llvm/tools/clang/lib/Format/FormatToken.h b/gnu/llvm/tools/clang/lib/Format/FormatToken.h index b683660f350..43b16251362 100644 --- a/gnu/llvm/tools/clang/lib/Format/FormatToken.h +++ b/gnu/llvm/tools/clang/lib/Format/FormatToken.h @@ -54,6 +54,7 @@ namespace format { TYPE(JsComputedPropertyName) \ TYPE(JsFatArrow) \ TYPE(JsTypeColon) \ + TYPE(JsTypeOperator) \ TYPE(JsTypeOptionalQuestion) \ TYPE(LambdaArrow) \ TYPE(LambdaLSquare) \ @@ -144,7 +145,7 @@ struct FormatToken { /// \brief Whether the token text contains newlines (escaped or not). bool IsMultiline = false; - /// \brief Indicates that this is the first token. + /// \brief Indicates that this is the first token of the file. bool IsFirst = false; /// \brief Whether there must be a line break before this token. @@ -296,6 +297,20 @@ struct FormatToken { } template <typename T> bool isNot(T Kind) const { return !is(Kind); } + /// \c true if this token starts a sequence with the given tokens in order, + /// following the ``Next`` pointers, ignoring comments. + template <typename A, typename... Ts> + bool startsSequence(A K1, Ts... Tokens) const { + return startsSequenceInternal(K1, Tokens...); + } + + /// \c true if this token ends a sequence with the given tokens in order, + /// following the ``Previous`` pointers, ignoring comments. + template <typename A, typename... Ts> + bool endsSequence(A K1, Ts... Tokens) const { + return endsSequenceInternal(K1, Tokens...); + } + bool isStringLiteral() const { return tok::isStringLiteral(Tok.getKind()); } bool isObjCAtKeyword(tok::ObjCKeywordKind Kind) const { @@ -428,6 +443,34 @@ private: // Disallow copying. FormatToken(const FormatToken &) = delete; void operator=(const FormatToken &) = delete; + + template <typename A, typename... Ts> + bool startsSequenceInternal(A K1, Ts... Tokens) const { + if (is(tok::comment) && Next) + return Next->startsSequenceInternal(K1, Tokens...); + return is(K1) && Next && Next->startsSequenceInternal(Tokens...); + } + + template <typename A> + bool startsSequenceInternal(A K1) const { + if (is(tok::comment) && Next) + return Next->startsSequenceInternal(K1); + return is(K1); + } + + template <typename A, typename... Ts> + bool endsSequenceInternal(A K1) const { + if (is(tok::comment) && Previous) + return Previous->endsSequenceInternal(K1); + return is(K1); + } + + template <typename A, typename... Ts> + bool endsSequenceInternal(A K1, Ts... Tokens) const { + if (is(tok::comment) && Previous) + return Previous->endsSequenceInternal(K1, Tokens...); + return is(K1) && Previous && Previous->endsSequenceInternal(Tokens...); + } }; class ContinuationIndenter; @@ -528,17 +571,24 @@ struct AdditionalKeywords { kw_final = &IdentTable.get("final"); kw_override = &IdentTable.get("override"); kw_in = &IdentTable.get("in"); + kw_of = &IdentTable.get("of"); kw_CF_ENUM = &IdentTable.get("CF_ENUM"); kw_CF_OPTIONS = &IdentTable.get("CF_OPTIONS"); kw_NS_ENUM = &IdentTable.get("NS_ENUM"); kw_NS_OPTIONS = &IdentTable.get("NS_OPTIONS"); + kw_as = &IdentTable.get("as"); + kw_async = &IdentTable.get("async"); + kw_await = &IdentTable.get("await"); kw_finally = &IdentTable.get("finally"); + kw_from = &IdentTable.get("from"); kw_function = &IdentTable.get("function"); kw_import = &IdentTable.get("import"); kw_is = &IdentTable.get("is"); kw_let = &IdentTable.get("let"); + kw_type = &IdentTable.get("type"); kw_var = &IdentTable.get("var"); + kw_yield = &IdentTable.get("yield"); kw_abstract = &IdentTable.get("abstract"); kw_assert = &IdentTable.get("assert"); @@ -571,6 +621,7 @@ struct AdditionalKeywords { IdentifierInfo *kw_final; IdentifierInfo *kw_override; IdentifierInfo *kw_in; + IdentifierInfo *kw_of; IdentifierInfo *kw_CF_ENUM; IdentifierInfo *kw_CF_OPTIONS; IdentifierInfo *kw_NS_ENUM; @@ -578,12 +629,18 @@ struct AdditionalKeywords { IdentifierInfo *kw___except; // JavaScript keywords. + IdentifierInfo *kw_as; + IdentifierInfo *kw_async; + IdentifierInfo *kw_await; IdentifierInfo *kw_finally; + IdentifierInfo *kw_from; IdentifierInfo *kw_function; IdentifierInfo *kw_import; IdentifierInfo *kw_is; IdentifierInfo *kw_let; + IdentifierInfo *kw_type; IdentifierInfo *kw_var; + IdentifierInfo *kw_yield; // Java keywords. IdentifierInfo *kw_abstract; diff --git a/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.cpp b/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.cpp new file mode 100644 index 00000000000..9778f84732d --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.cpp @@ -0,0 +1,597 @@ +//===--- FormatTokenLexer.cpp - Lex FormatTokens -------------*- C++ ----*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements FormatTokenLexer, which tokenizes a source file +/// into a FormatToken stream suitable for ClangFormat. +/// +//===----------------------------------------------------------------------===// + +#include "FormatTokenLexer.h" +#include "FormatToken.h" +#include "clang/Basic/SourceLocation.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Format/Format.h" +#include "llvm/Support/Regex.h" + +namespace clang { +namespace format { + +FormatTokenLexer::FormatTokenLexer(const SourceManager &SourceMgr, FileID ID, + const FormatStyle &Style, + encoding::Encoding Encoding) + : FormatTok(nullptr), IsFirstToken(true), GreaterStashed(false), + LessStashed(false), Column(0), TrailingWhitespace(0), + SourceMgr(SourceMgr), ID(ID), Style(Style), + IdentTable(getFormattingLangOpts(Style)), Keywords(IdentTable), + Encoding(Encoding), FirstInLineIndex(0), FormattingDisabled(false), + MacroBlockBeginRegex(Style.MacroBlockBegin), + MacroBlockEndRegex(Style.MacroBlockEnd) { + Lex.reset(new Lexer(ID, SourceMgr.getBuffer(ID), SourceMgr, + getFormattingLangOpts(Style))); + Lex->SetKeepWhitespaceMode(true); + + for (const std::string &ForEachMacro : Style.ForEachMacros) + ForEachMacros.push_back(&IdentTable.get(ForEachMacro)); + std::sort(ForEachMacros.begin(), ForEachMacros.end()); +} + +ArrayRef<FormatToken *> FormatTokenLexer::lex() { + assert(Tokens.empty()); + assert(FirstInLineIndex == 0); + do { + Tokens.push_back(getNextToken()); + if (Style.Language == FormatStyle::LK_JavaScript) { + tryParseJSRegexLiteral(); + tryParseTemplateString(); + } + tryMergePreviousTokens(); + if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline) + FirstInLineIndex = Tokens.size() - 1; + } while (Tokens.back()->Tok.isNot(tok::eof)); + return Tokens; +} + +void FormatTokenLexer::tryMergePreviousTokens() { + if (tryMerge_TMacro()) + return; + if (tryMergeConflictMarkers()) + return; + if (tryMergeLessLess()) + return; + + if (Style.Language == FormatStyle::LK_JavaScript) { + static const tok::TokenKind JSIdentity[] = {tok::equalequal, tok::equal}; + static const tok::TokenKind JSNotIdentity[] = {tok::exclaimequal, + tok::equal}; + static const tok::TokenKind JSShiftEqual[] = {tok::greater, tok::greater, + tok::greaterequal}; + static const tok::TokenKind JSRightArrow[] = {tok::equal, tok::greater}; + // FIXME: Investigate what token type gives the correct operator priority. + if (tryMergeTokens(JSIdentity, TT_BinaryOperator)) + return; + if (tryMergeTokens(JSNotIdentity, TT_BinaryOperator)) + return; + if (tryMergeTokens(JSShiftEqual, TT_BinaryOperator)) + return; + if (tryMergeTokens(JSRightArrow, TT_JsFatArrow)) + return; + } +} + +bool FormatTokenLexer::tryMergeLessLess() { + // Merge X,less,less,Y into X,lessless,Y unless X or Y is less. + if (Tokens.size() < 3) + return false; + + bool FourthTokenIsLess = false; + if (Tokens.size() > 3) + FourthTokenIsLess = (Tokens.end() - 4)[0]->is(tok::less); + + auto First = Tokens.end() - 3; + if (First[2]->is(tok::less) || First[1]->isNot(tok::less) || + First[0]->isNot(tok::less) || FourthTokenIsLess) + return false; + + // Only merge if there currently is no whitespace between the two "<". + if (First[1]->WhitespaceRange.getBegin() != + First[1]->WhitespaceRange.getEnd()) + return false; + + First[0]->Tok.setKind(tok::lessless); + First[0]->TokenText = "<<"; + First[0]->ColumnWidth += 1; + Tokens.erase(Tokens.end() - 2); + return true; +} + +bool FormatTokenLexer::tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, + TokenType NewType) { + if (Tokens.size() < Kinds.size()) + return false; + + SmallVectorImpl<FormatToken *>::const_iterator First = + Tokens.end() - Kinds.size(); + if (!First[0]->is(Kinds[0])) + return false; + unsigned AddLength = 0; + for (unsigned i = 1; i < Kinds.size(); ++i) { + if (!First[i]->is(Kinds[i]) || + First[i]->WhitespaceRange.getBegin() != + First[i]->WhitespaceRange.getEnd()) + return false; + AddLength += First[i]->TokenText.size(); + } + Tokens.resize(Tokens.size() - Kinds.size() + 1); + First[0]->TokenText = StringRef(First[0]->TokenText.data(), + First[0]->TokenText.size() + AddLength); + First[0]->ColumnWidth += AddLength; + First[0]->Type = NewType; + return true; +} + +// Returns \c true if \p Tok can only be followed by an operand in JavaScript. +bool FormatTokenLexer::precedesOperand(FormatToken *Tok) { + // NB: This is not entirely correct, as an r_paren can introduce an operand + // location in e.g. `if (foo) /bar/.exec(...);`. That is a rare enough + // corner case to not matter in practice, though. + return Tok->isOneOf(tok::period, tok::l_paren, tok::comma, tok::l_brace, + tok::r_brace, tok::l_square, tok::semi, tok::exclaim, + tok::colon, tok::question, tok::tilde) || + Tok->isOneOf(tok::kw_return, tok::kw_do, tok::kw_case, tok::kw_throw, + tok::kw_else, tok::kw_new, tok::kw_delete, tok::kw_void, + tok::kw_typeof, Keywords.kw_instanceof, Keywords.kw_in) || + Tok->isBinaryOperator(); +} + +bool FormatTokenLexer::canPrecedeRegexLiteral(FormatToken *Prev) { + if (!Prev) + return true; + + // Regex literals can only follow after prefix unary operators, not after + // postfix unary operators. If the '++' is followed by a non-operand + // introducing token, the slash here is the operand and not the start of a + // regex. + if (Prev->isOneOf(tok::plusplus, tok::minusminus)) + return (Tokens.size() < 3 || precedesOperand(Tokens[Tokens.size() - 3])); + + // The previous token must introduce an operand location where regex + // literals can occur. + if (!precedesOperand(Prev)) + return false; + + return true; +} + +// Tries to parse a JavaScript Regex literal starting at the current token, +// if that begins with a slash and is in a location where JavaScript allows +// regex literals. Changes the current token to a regex literal and updates +// its text if successful. +void FormatTokenLexer::tryParseJSRegexLiteral() { + FormatToken *RegexToken = Tokens.back(); + if (!RegexToken->isOneOf(tok::slash, tok::slashequal)) + return; + + FormatToken *Prev = nullptr; + for (auto I = Tokens.rbegin() + 1, E = Tokens.rend(); I != E; ++I) { + // NB: Because previous pointers are not initialized yet, this cannot use + // Token.getPreviousNonComment. + if ((*I)->isNot(tok::comment)) { + Prev = *I; + break; + } + } + + if (!canPrecedeRegexLiteral(Prev)) + return; + + // 'Manually' lex ahead in the current file buffer. + const char *Offset = Lex->getBufferLocation(); + const char *RegexBegin = Offset - RegexToken->TokenText.size(); + StringRef Buffer = Lex->getBuffer(); + bool InCharacterClass = false; + bool HaveClosingSlash = false; + for (; !HaveClosingSlash && Offset != Buffer.end(); ++Offset) { + // Regular expressions are terminated with a '/', which can only be + // escaped using '\' or a character class between '[' and ']'. + // See http://www.ecma-international.org/ecma-262/5.1/#sec-7.8.5. + switch (*Offset) { + case '\\': + // Skip the escaped character. + ++Offset; + break; + case '[': + InCharacterClass = true; + break; + case ']': + InCharacterClass = false; + break; + case '/': + if (!InCharacterClass) + HaveClosingSlash = true; + break; + } + } + + RegexToken->Type = TT_RegexLiteral; + // Treat regex literals like other string_literals. + RegexToken->Tok.setKind(tok::string_literal); + RegexToken->TokenText = StringRef(RegexBegin, Offset - RegexBegin); + RegexToken->ColumnWidth = RegexToken->TokenText.size(); + + resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset))); +} + +void FormatTokenLexer::tryParseTemplateString() { + FormatToken *BacktickToken = Tokens.back(); + if (!BacktickToken->is(tok::unknown) || BacktickToken->TokenText != "`") + return; + + // 'Manually' lex ahead in the current file buffer. + const char *Offset = Lex->getBufferLocation(); + const char *TmplBegin = Offset - BacktickToken->TokenText.size(); // at "`" + for (; Offset != Lex->getBuffer().end() && *Offset != '`'; ++Offset) { + if (*Offset == '\\') + ++Offset; // Skip the escaped character. + } + + StringRef LiteralText(TmplBegin, Offset - TmplBegin + 1); + BacktickToken->Type = TT_TemplateString; + BacktickToken->Tok.setKind(tok::string_literal); + BacktickToken->TokenText = LiteralText; + + // Adjust width for potentially multiline string literals. + size_t FirstBreak = LiteralText.find('\n'); + StringRef FirstLineText = FirstBreak == StringRef::npos + ? LiteralText + : LiteralText.substr(0, FirstBreak); + BacktickToken->ColumnWidth = encoding::columnWidthWithTabs( + FirstLineText, BacktickToken->OriginalColumn, Style.TabWidth, Encoding); + size_t LastBreak = LiteralText.rfind('\n'); + if (LastBreak != StringRef::npos) { + BacktickToken->IsMultiline = true; + unsigned StartColumn = 0; // The template tail spans the entire line. + BacktickToken->LastLineColumnWidth = encoding::columnWidthWithTabs( + LiteralText.substr(LastBreak + 1, LiteralText.size()), StartColumn, + Style.TabWidth, Encoding); + } + + resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset + 1))); +} + +bool FormatTokenLexer::tryMerge_TMacro() { + if (Tokens.size() < 4) + return false; + FormatToken *Last = Tokens.back(); + if (!Last->is(tok::r_paren)) + return false; + + FormatToken *String = Tokens[Tokens.size() - 2]; + if (!String->is(tok::string_literal) || String->IsMultiline) + return false; + + if (!Tokens[Tokens.size() - 3]->is(tok::l_paren)) + return false; + + FormatToken *Macro = Tokens[Tokens.size() - 4]; + if (Macro->TokenText != "_T") + return false; + + const char *Start = Macro->TokenText.data(); + const char *End = Last->TokenText.data() + Last->TokenText.size(); + String->TokenText = StringRef(Start, End - Start); + String->IsFirst = Macro->IsFirst; + String->LastNewlineOffset = Macro->LastNewlineOffset; + String->WhitespaceRange = Macro->WhitespaceRange; + String->OriginalColumn = Macro->OriginalColumn; + String->ColumnWidth = encoding::columnWidthWithTabs( + String->TokenText, String->OriginalColumn, Style.TabWidth, Encoding); + String->NewlinesBefore = Macro->NewlinesBefore; + String->HasUnescapedNewline = Macro->HasUnescapedNewline; + + Tokens.pop_back(); + Tokens.pop_back(); + Tokens.pop_back(); + Tokens.back() = String; + return true; +} + +bool FormatTokenLexer::tryMergeConflictMarkers() { + if (Tokens.back()->NewlinesBefore == 0 && Tokens.back()->isNot(tok::eof)) + return false; + + // Conflict lines look like: + // <marker> <text from the vcs> + // For example: + // >>>>>>> /file/in/file/system at revision 1234 + // + // We merge all tokens in a line that starts with a conflict marker + // into a single token with a special token type that the unwrapped line + // parser will use to correctly rebuild the underlying code. + + FileID ID; + // Get the position of the first token in the line. + unsigned FirstInLineOffset; + std::tie(ID, FirstInLineOffset) = SourceMgr.getDecomposedLoc( + Tokens[FirstInLineIndex]->getStartOfNonWhitespace()); + StringRef Buffer = SourceMgr.getBuffer(ID)->getBuffer(); + // Calculate the offset of the start of the current line. + auto LineOffset = Buffer.rfind('\n', FirstInLineOffset); + if (LineOffset == StringRef::npos) { + LineOffset = 0; + } else { + ++LineOffset; + } + + auto FirstSpace = Buffer.find_first_of(" \n", LineOffset); + StringRef LineStart; + if (FirstSpace == StringRef::npos) { + LineStart = Buffer.substr(LineOffset); + } else { + LineStart = Buffer.substr(LineOffset, FirstSpace - LineOffset); + } + + TokenType Type = TT_Unknown; + if (LineStart == "<<<<<<<" || LineStart == ">>>>") { + Type = TT_ConflictStart; + } else if (LineStart == "|||||||" || LineStart == "=======" || + LineStart == "====") { + Type = TT_ConflictAlternative; + } else if (LineStart == ">>>>>>>" || LineStart == "<<<<") { + Type = TT_ConflictEnd; + } + + if (Type != TT_Unknown) { + FormatToken *Next = Tokens.back(); + + Tokens.resize(FirstInLineIndex + 1); + // We do not need to build a complete token here, as we will skip it + // during parsing anyway (as we must not touch whitespace around conflict + // markers). + Tokens.back()->Type = Type; + Tokens.back()->Tok.setKind(tok::kw___unknown_anytype); + + Tokens.push_back(Next); + return true; + } + + return false; +} + +FormatToken *FormatTokenLexer::getStashedToken() { + // Create a synthesized second '>' or '<' token. + Token Tok = FormatTok->Tok; + StringRef TokenText = FormatTok->TokenText; + + unsigned OriginalColumn = FormatTok->OriginalColumn; + FormatTok = new (Allocator.Allocate()) FormatToken; + FormatTok->Tok = Tok; + SourceLocation TokLocation = + FormatTok->Tok.getLocation().getLocWithOffset(Tok.getLength() - 1); + FormatTok->Tok.setLocation(TokLocation); + FormatTok->WhitespaceRange = SourceRange(TokLocation, TokLocation); + FormatTok->TokenText = TokenText; + FormatTok->ColumnWidth = 1; + FormatTok->OriginalColumn = OriginalColumn + 1; + + return FormatTok; +} + +FormatToken *FormatTokenLexer::getNextToken() { + if (GreaterStashed) { + GreaterStashed = false; + return getStashedToken(); + } + if (LessStashed) { + LessStashed = false; + return getStashedToken(); + } + + FormatTok = new (Allocator.Allocate()) FormatToken; + readRawToken(*FormatTok); + SourceLocation WhitespaceStart = + FormatTok->Tok.getLocation().getLocWithOffset(-TrailingWhitespace); + FormatTok->IsFirst = IsFirstToken; + IsFirstToken = false; + + // Consume and record whitespace until we find a significant token. + unsigned WhitespaceLength = TrailingWhitespace; + while (FormatTok->Tok.is(tok::unknown)) { + StringRef Text = FormatTok->TokenText; + auto EscapesNewline = [&](int pos) { + // A '\r' here is just part of '\r\n'. Skip it. + if (pos >= 0 && Text[pos] == '\r') + --pos; + // See whether there is an odd number of '\' before this. + unsigned count = 0; + for (; pos >= 0; --pos, ++count) + if (Text[pos] != '\\') + break; + return count & 1; + }; + // FIXME: This miscounts tok:unknown tokens that are not just + // whitespace, e.g. a '`' character. + for (int i = 0, e = Text.size(); i != e; ++i) { + switch (Text[i]) { + case '\n': + ++FormatTok->NewlinesBefore; + FormatTok->HasUnescapedNewline = !EscapesNewline(i - 1); + FormatTok->LastNewlineOffset = WhitespaceLength + i + 1; + Column = 0; + break; + case '\r': + FormatTok->LastNewlineOffset = WhitespaceLength + i + 1; + Column = 0; + break; + case '\f': + case '\v': + Column = 0; + break; + case ' ': + ++Column; + break; + case '\t': + Column += Style.TabWidth - Column % Style.TabWidth; + break; + case '\\': + if (i + 1 == e || (Text[i + 1] != '\r' && Text[i + 1] != '\n')) + FormatTok->Type = TT_ImplicitStringLiteral; + break; + default: + FormatTok->Type = TT_ImplicitStringLiteral; + break; + } + if (FormatTok->Type == TT_ImplicitStringLiteral) + break; + } + + if (FormatTok->is(TT_ImplicitStringLiteral)) + break; + WhitespaceLength += FormatTok->Tok.getLength(); + + readRawToken(*FormatTok); + } + + // In case the token starts with escaped newlines, we want to + // take them into account as whitespace - this pattern is quite frequent + // in macro definitions. + // FIXME: Add a more explicit test. + while (FormatTok->TokenText.size() > 1 && FormatTok->TokenText[0] == '\\' && + FormatTok->TokenText[1] == '\n') { + ++FormatTok->NewlinesBefore; + WhitespaceLength += 2; + FormatTok->LastNewlineOffset = 2; + Column = 0; + FormatTok->TokenText = FormatTok->TokenText.substr(2); + } + + FormatTok->WhitespaceRange = SourceRange( + WhitespaceStart, WhitespaceStart.getLocWithOffset(WhitespaceLength)); + + FormatTok->OriginalColumn = Column; + + TrailingWhitespace = 0; + if (FormatTok->Tok.is(tok::comment)) { + // FIXME: Add the trimmed whitespace to Column. + StringRef UntrimmedText = FormatTok->TokenText; + FormatTok->TokenText = FormatTok->TokenText.rtrim(" \t\v\f"); + TrailingWhitespace = UntrimmedText.size() - FormatTok->TokenText.size(); + } else if (FormatTok->Tok.is(tok::raw_identifier)) { + IdentifierInfo &Info = IdentTable.get(FormatTok->TokenText); + FormatTok->Tok.setIdentifierInfo(&Info); + FormatTok->Tok.setKind(Info.getTokenID()); + if (Style.Language == FormatStyle::LK_Java && + FormatTok->isOneOf(tok::kw_struct, tok::kw_union, tok::kw_delete, + tok::kw_operator)) { + FormatTok->Tok.setKind(tok::identifier); + FormatTok->Tok.setIdentifierInfo(nullptr); + } else if (Style.Language == FormatStyle::LK_JavaScript && + FormatTok->isOneOf(tok::kw_struct, tok::kw_union, + tok::kw_operator)) { + FormatTok->Tok.setKind(tok::identifier); + FormatTok->Tok.setIdentifierInfo(nullptr); + } + } else if (FormatTok->Tok.is(tok::greatergreater)) { + FormatTok->Tok.setKind(tok::greater); + FormatTok->TokenText = FormatTok->TokenText.substr(0, 1); + GreaterStashed = true; + } else if (FormatTok->Tok.is(tok::lessless)) { + FormatTok->Tok.setKind(tok::less); + FormatTok->TokenText = FormatTok->TokenText.substr(0, 1); + LessStashed = true; + } + + // Now FormatTok is the next non-whitespace token. + + StringRef Text = FormatTok->TokenText; + size_t FirstNewlinePos = Text.find('\n'); + if (FirstNewlinePos == StringRef::npos) { + // FIXME: ColumnWidth actually depends on the start column, we need to + // take this into account when the token is moved. + FormatTok->ColumnWidth = + encoding::columnWidthWithTabs(Text, Column, Style.TabWidth, Encoding); + Column += FormatTok->ColumnWidth; + } else { + FormatTok->IsMultiline = true; + // FIXME: ColumnWidth actually depends on the start column, we need to + // take this into account when the token is moved. + FormatTok->ColumnWidth = encoding::columnWidthWithTabs( + Text.substr(0, FirstNewlinePos), Column, Style.TabWidth, Encoding); + + // The last line of the token always starts in column 0. + // Thus, the length can be precomputed even in the presence of tabs. + FormatTok->LastLineColumnWidth = encoding::columnWidthWithTabs( + Text.substr(Text.find_last_of('\n') + 1), 0, Style.TabWidth, Encoding); + Column = FormatTok->LastLineColumnWidth; + } + + if (Style.Language == FormatStyle::LK_Cpp) { + if (!(Tokens.size() > 0 && Tokens.back()->Tok.getIdentifierInfo() && + Tokens.back()->Tok.getIdentifierInfo()->getPPKeywordID() == + tok::pp_define) && + std::find(ForEachMacros.begin(), ForEachMacros.end(), + FormatTok->Tok.getIdentifierInfo()) != ForEachMacros.end()) { + FormatTok->Type = TT_ForEachMacro; + } else if (FormatTok->is(tok::identifier)) { + if (MacroBlockBeginRegex.match(Text)) { + FormatTok->Type = TT_MacroBlockBegin; + } else if (MacroBlockEndRegex.match(Text)) { + FormatTok->Type = TT_MacroBlockEnd; + } + } + } + + return FormatTok; +} + +void FormatTokenLexer::readRawToken(FormatToken &Tok) { + Lex->LexFromRawLexer(Tok.Tok); + Tok.TokenText = StringRef(SourceMgr.getCharacterData(Tok.Tok.getLocation()), + Tok.Tok.getLength()); + // For formatting, treat unterminated string literals like normal string + // literals. + if (Tok.is(tok::unknown)) { + if (!Tok.TokenText.empty() && Tok.TokenText[0] == '"') { + Tok.Tok.setKind(tok::string_literal); + Tok.IsUnterminatedLiteral = true; + } else if (Style.Language == FormatStyle::LK_JavaScript && + Tok.TokenText == "''") { + Tok.Tok.setKind(tok::string_literal); + } + } + + if (Style.Language == FormatStyle::LK_JavaScript && + Tok.is(tok::char_constant)) { + Tok.Tok.setKind(tok::string_literal); + } + + if (Tok.is(tok::comment) && (Tok.TokenText == "// clang-format on" || + Tok.TokenText == "/* clang-format on */")) { + FormattingDisabled = false; + } + + Tok.Finalized = FormattingDisabled; + + if (Tok.is(tok::comment) && (Tok.TokenText == "// clang-format off" || + Tok.TokenText == "/* clang-format off */")) { + FormattingDisabled = true; + } +} + +void FormatTokenLexer::resetLexer(unsigned Offset) { + StringRef Buffer = SourceMgr.getBufferData(ID); + Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), + getFormattingLangOpts(Style), Buffer.begin(), + Buffer.begin() + Offset, Buffer.end())); + Lex->SetKeepWhitespaceMode(true); + TrailingWhitespace = 0; +} + +} // namespace format +} // namespace clang diff --git a/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.h b/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.h new file mode 100644 index 00000000000..fa8c8882574 --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/FormatTokenLexer.h @@ -0,0 +1,97 @@ +//===--- FormatTokenLexer.h - Format C++ code ----------------*- C++ ----*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file contains FormatTokenLexer, which tokenizes a source file +/// into a token stream suitable for ClangFormat. +/// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H +#define LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H + +#include "Encoding.h" +#include "FormatToken.h" +#include "clang/Basic/SourceLocation.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Format/Format.h" +#include "llvm/Support/Regex.h" + +namespace clang { +namespace format { + +class FormatTokenLexer { +public: + FormatTokenLexer(const SourceManager &SourceMgr, FileID ID, + const FormatStyle &Style, encoding::Encoding Encoding); + + ArrayRef<FormatToken *> lex(); + + const AdditionalKeywords &getKeywords() { return Keywords; } + +private: + void tryMergePreviousTokens(); + + bool tryMergeLessLess(); + + bool tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, TokenType NewType); + + // Returns \c true if \p Tok can only be followed by an operand in JavaScript. + bool precedesOperand(FormatToken *Tok); + + bool canPrecedeRegexLiteral(FormatToken *Prev); + + // Tries to parse a JavaScript Regex literal starting at the current token, + // if that begins with a slash and is in a location where JavaScript allows + // regex literals. Changes the current token to a regex literal and updates + // its text if successful. + void tryParseJSRegexLiteral(); + + void tryParseTemplateString(); + + bool tryMerge_TMacro(); + + bool tryMergeConflictMarkers(); + + FormatToken *getStashedToken(); + + FormatToken *getNextToken(); + + FormatToken *FormatTok; + bool IsFirstToken; + bool GreaterStashed, LessStashed; + unsigned Column; + unsigned TrailingWhitespace; + std::unique_ptr<Lexer> Lex; + const SourceManager &SourceMgr; + FileID ID; + const FormatStyle &Style; + IdentifierTable IdentTable; + AdditionalKeywords Keywords; + encoding::Encoding Encoding; + llvm::SpecificBumpPtrAllocator<FormatToken> Allocator; + // Index (in 'Tokens') of the last token that starts a new line. + unsigned FirstInLineIndex; + SmallVector<FormatToken *, 16> Tokens; + SmallVector<IdentifierInfo *, 8> ForEachMacros; + + bool FormattingDisabled; + + llvm::Regex MacroBlockBeginRegex; + llvm::Regex MacroBlockEndRegex; + + void readRawToken(FormatToken &Tok); + + void resetLexer(unsigned Offset); +}; + +} // namespace format +} // namespace clang + +#endif diff --git a/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.cpp b/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.cpp new file mode 100644 index 00000000000..32d5d756a3f --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.cpp @@ -0,0 +1,442 @@ +//===--- SortJavaScriptImports.h - Sort ES6 Imports -------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements a sort operation for JavaScript ES6 imports. +/// +//===----------------------------------------------------------------------===// + +#include "SortJavaScriptImports.h" +#include "SortJavaScriptImports.h" +#include "TokenAnalyzer.h" +#include "TokenAnnotator.h" +#include "clang/Basic/Diagnostic.h" +#include "clang/Basic/DiagnosticOptions.h" +#include "clang/Basic/LLVM.h" +#include "clang/Basic/SourceLocation.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Format/Format.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/Support/Debug.h" +#include <algorithm> +#include <string> + +#define DEBUG_TYPE "format-formatter" + +namespace clang { +namespace format { + +class FormatTokenLexer; + +using clang::format::FormatStyle; + +// An imported symbol in a JavaScript ES6 import/export, possibly aliased. +struct JsImportedSymbol { + StringRef Symbol; + StringRef Alias; + SourceRange Range; + + bool operator==(const JsImportedSymbol &RHS) const { + // Ignore Range for comparison, it is only used to stitch code together, + // but imports at different code locations are still conceptually the same. + return Symbol == RHS.Symbol && Alias == RHS.Alias; + } +}; + +// An ES6 module reference. +// +// ES6 implements a module system, where individual modules (~= source files) +// can reference other modules, either importing symbols from them, or exporting +// symbols from them: +// import {foo} from 'foo'; +// export {foo}; +// export {bar} from 'bar'; +// +// `export`s with URLs are syntactic sugar for an import of the symbol from the +// URL, followed by an export of the symbol, allowing this code to treat both +// statements more or less identically, with the exception being that `export`s +// are sorted last. +// +// imports and exports support individual symbols, but also a wildcard syntax: +// import * as prefix from 'foo'; +// export * from 'bar'; +// +// This struct represents both exports and imports to build up the information +// required for sorting module references. +struct JsModuleReference { + bool IsExport = false; + // Module references are sorted into these categories, in order. + enum ReferenceCategory { + SIDE_EFFECT, // "import 'something';" + ABSOLUTE, // from 'something' + RELATIVE_PARENT, // from '../*' + RELATIVE, // from './*' + }; + ReferenceCategory Category = ReferenceCategory::SIDE_EFFECT; + // The URL imported, e.g. `import .. from 'url';`. Empty for `export {a, b};`. + StringRef URL; + // Prefix from "import * as prefix". Empty for symbol imports and `export *`. + // Implies an empty names list. + StringRef Prefix; + // Symbols from `import {SymbolA, SymbolB, ...} from ...;`. + SmallVector<JsImportedSymbol, 1> Symbols; + // Textual position of the import/export, including preceding and trailing + // comments. + SourceRange Range; +}; + +bool operator<(const JsModuleReference &LHS, const JsModuleReference &RHS) { + if (LHS.IsExport != RHS.IsExport) + return LHS.IsExport < RHS.IsExport; + if (LHS.Category != RHS.Category) + return LHS.Category < RHS.Category; + if (LHS.Category == JsModuleReference::ReferenceCategory::SIDE_EFFECT) + // Side effect imports might be ordering sensitive. Consider them equal so + // that they maintain their relative order in the stable sort below. + // This retains transitivity because LHS.Category == RHS.Category here. + return false; + // Empty URLs sort *last* (for export {...};). + if (LHS.URL.empty() != RHS.URL.empty()) + return LHS.URL.empty() < RHS.URL.empty(); + if (int Res = LHS.URL.compare_lower(RHS.URL)) + return Res < 0; + // '*' imports (with prefix) sort before {a, b, ...} imports. + if (LHS.Prefix.empty() != RHS.Prefix.empty()) + return LHS.Prefix.empty() < RHS.Prefix.empty(); + if (LHS.Prefix != RHS.Prefix) + return LHS.Prefix > RHS.Prefix; + return false; +} + +// JavaScriptImportSorter sorts JavaScript ES6 imports and exports. It is +// implemented as a TokenAnalyzer because ES6 imports have substantial syntactic +// structure, making it messy to sort them using regular expressions. +class JavaScriptImportSorter : public TokenAnalyzer { +public: + JavaScriptImportSorter(const Environment &Env, const FormatStyle &Style) + : TokenAnalyzer(Env, Style), + FileContents(Env.getSourceManager().getBufferData(Env.getFileID())) {} + + tooling::Replacements + analyze(TokenAnnotator &Annotator, + SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, + FormatTokenLexer &Tokens, tooling::Replacements &Result) override { + AffectedRangeMgr.computeAffectedLines(AnnotatedLines.begin(), + AnnotatedLines.end()); + + const AdditionalKeywords &Keywords = Tokens.getKeywords(); + SmallVector<JsModuleReference, 16> References; + AnnotatedLine *FirstNonImportLine; + std::tie(References, FirstNonImportLine) = + parseModuleReferences(Keywords, AnnotatedLines); + + if (References.empty()) + return Result; + + SmallVector<unsigned, 16> Indices; + for (unsigned i = 0, e = References.size(); i != e; ++i) + Indices.push_back(i); + std::stable_sort(Indices.begin(), Indices.end(), + [&](unsigned LHSI, unsigned RHSI) { + return References[LHSI] < References[RHSI]; + }); + bool ReferencesInOrder = std::is_sorted(Indices.begin(), Indices.end()); + + std::string ReferencesText; + bool SymbolsInOrder = true; + for (unsigned i = 0, e = Indices.size(); i != e; ++i) { + JsModuleReference Reference = References[Indices[i]]; + if (appendReference(ReferencesText, Reference)) + SymbolsInOrder = false; + if (i + 1 < e) { + // Insert breaks between imports and exports. + ReferencesText += "\n"; + // Separate imports groups with two line breaks, but keep all exports + // in a single group. + if (!Reference.IsExport && + (Reference.IsExport != References[Indices[i + 1]].IsExport || + Reference.Category != References[Indices[i + 1]].Category)) + ReferencesText += "\n"; + } + } + + if (ReferencesInOrder && SymbolsInOrder) + return Result; + + SourceRange InsertionPoint = References[0].Range; + InsertionPoint.setEnd(References[References.size() - 1].Range.getEnd()); + + // The loop above might collapse previously existing line breaks between + // import blocks, and thus shrink the file. SortIncludes must not shrink + // overall source length as there is currently no re-calculation of ranges + // after applying source sorting. + // This loop just backfills trailing spaces after the imports, which are + // harmless and will be stripped by the subsequent formatting pass. + // FIXME: A better long term fix is to re-calculate Ranges after sorting. + unsigned PreviousSize = getSourceText(InsertionPoint).size(); + while (ReferencesText.size() < PreviousSize) { + ReferencesText += " "; + } + + // Separate references from the main code body of the file. + if (FirstNonImportLine && FirstNonImportLine->First->NewlinesBefore < 2) + ReferencesText += "\n"; + + DEBUG(llvm::dbgs() << "Replacing imports:\n" + << getSourceText(InsertionPoint) << "\nwith:\n" + << ReferencesText << "\n"); + Result.insert(tooling::Replacement( + Env.getSourceManager(), CharSourceRange::getCharRange(InsertionPoint), + ReferencesText)); + + return Result; + } + +private: + FormatToken *Current; + FormatToken *LineEnd; + + FormatToken invalidToken; + + StringRef FileContents; + + void skipComments() { Current = skipComments(Current); } + + FormatToken *skipComments(FormatToken *Tok) { + while (Tok && Tok->is(tok::comment)) + Tok = Tok->Next; + return Tok; + } + + void nextToken() { + Current = Current->Next; + skipComments(); + if (!Current || Current == LineEnd->Next) { + // Set the current token to an invalid token, so that further parsing on + // this line fails. + invalidToken.Tok.setKind(tok::unknown); + Current = &invalidToken; + } + } + + StringRef getSourceText(SourceRange Range) { + return getSourceText(Range.getBegin(), Range.getEnd()); + } + + StringRef getSourceText(SourceLocation Begin, SourceLocation End) { + const SourceManager &SM = Env.getSourceManager(); + return FileContents.substr(SM.getFileOffset(Begin), + SM.getFileOffset(End) - SM.getFileOffset(Begin)); + } + + // Appends ``Reference`` to ``Buffer``, returning true if text within the + // ``Reference`` changed (e.g. symbol order). + bool appendReference(std::string &Buffer, JsModuleReference &Reference) { + // Sort the individual symbols within the import. + // E.g. `import {b, a} from 'x';` -> `import {a, b} from 'x';` + SmallVector<JsImportedSymbol, 1> Symbols = Reference.Symbols; + std::stable_sort( + Symbols.begin(), Symbols.end(), + [&](const JsImportedSymbol &LHS, const JsImportedSymbol &RHS) { + return LHS.Symbol.compare_lower(RHS.Symbol) < 0; + }); + if (Symbols == Reference.Symbols) { + // No change in symbol order. + StringRef ReferenceStmt = getSourceText(Reference.Range); + Buffer += ReferenceStmt; + return false; + } + // Stitch together the module reference start... + SourceLocation SymbolsStart = Reference.Symbols.front().Range.getBegin(); + SourceLocation SymbolsEnd = Reference.Symbols.back().Range.getEnd(); + Buffer += getSourceText(Reference.Range.getBegin(), SymbolsStart); + // ... then the references in order ... + for (auto I = Symbols.begin(), E = Symbols.end(); I != E; ++I) { + if (I != Symbols.begin()) + Buffer += ","; + Buffer += getSourceText(I->Range); + } + // ... followed by the module reference end. + Buffer += getSourceText(SymbolsEnd, Reference.Range.getEnd()); + return true; + } + + // Parses module references in the given lines. Returns the module references, + // and a pointer to the first "main code" line if that is adjacent to the + // affected lines of module references, nullptr otherwise. + std::pair<SmallVector<JsModuleReference, 16>, AnnotatedLine*> + parseModuleReferences(const AdditionalKeywords &Keywords, + SmallVectorImpl<AnnotatedLine *> &AnnotatedLines) { + SmallVector<JsModuleReference, 16> References; + SourceLocation Start; + bool FoundLines = false; + AnnotatedLine *FirstNonImportLine = nullptr; + for (auto Line : AnnotatedLines) { + if (!Line->Affected) { + // Only sort the first contiguous block of affected lines. + if (FoundLines) + break; + else + continue; + } + Current = Line->First; + LineEnd = Line->Last; + skipComments(); + if (Start.isInvalid() || References.empty()) + // After the first file level comment, consider line comments to be part + // of the import that immediately follows them by using the previously + // set Start. + Start = Line->First->Tok.getLocation(); + if (!Current) + continue; // Only comments on this line. + FoundLines = true; + JsModuleReference Reference; + Reference.Range.setBegin(Start); + if (!parseModuleReference(Keywords, Reference)) { + FirstNonImportLine = Line; + break; + } + Reference.Range.setEnd(LineEnd->Tok.getEndLoc()); + DEBUG({ + llvm::dbgs() << "JsModuleReference: {" + << "is_export: " << Reference.IsExport + << ", cat: " << Reference.Category + << ", url: " << Reference.URL + << ", prefix: " << Reference.Prefix; + for (size_t i = 0; i < Reference.Symbols.size(); ++i) + llvm::dbgs() << ", " << Reference.Symbols[i].Symbol << " as " + << Reference.Symbols[i].Alias; + llvm::dbgs() << ", text: " << getSourceText(Reference.Range); + llvm::dbgs() << "}\n"; + }); + References.push_back(Reference); + Start = SourceLocation(); + } + return std::make_pair(References, FirstNonImportLine); + } + + // Parses a JavaScript/ECMAScript 6 module reference. + // See http://www.ecma-international.org/ecma-262/6.0/#sec-scripts-and-modules + // for grammar EBNF (production ModuleItem). + bool parseModuleReference(const AdditionalKeywords &Keywords, + JsModuleReference &Reference) { + if (!Current || !Current->isOneOf(Keywords.kw_import, tok::kw_export)) + return false; + Reference.IsExport = Current->is(tok::kw_export); + + nextToken(); + if (Current->isStringLiteral() && !Reference.IsExport) { + // "import 'side-effect';" + Reference.Category = JsModuleReference::ReferenceCategory::SIDE_EFFECT; + Reference.URL = + Current->TokenText.substr(1, Current->TokenText.size() - 2); + return true; + } + + if (!parseModuleBindings(Keywords, Reference)) + return false; + nextToken(); + + if (Current->is(Keywords.kw_from)) { + // imports have a 'from' clause, exports might not. + nextToken(); + if (!Current->isStringLiteral()) + return false; + // URL = TokenText without the quotes. + Reference.URL = + Current->TokenText.substr(1, Current->TokenText.size() - 2); + if (Reference.URL.startswith("..")) + Reference.Category = + JsModuleReference::ReferenceCategory::RELATIVE_PARENT; + else if (Reference.URL.startswith(".")) + Reference.Category = JsModuleReference::ReferenceCategory::RELATIVE; + else + Reference.Category = JsModuleReference::ReferenceCategory::ABSOLUTE; + } else { + // w/o URL groups with "empty". + Reference.Category = JsModuleReference::ReferenceCategory::RELATIVE; + } + return true; + } + + bool parseModuleBindings(const AdditionalKeywords &Keywords, + JsModuleReference &Reference) { + if (parseStarBinding(Keywords, Reference)) + return true; + return parseNamedBindings(Keywords, Reference); + } + + bool parseStarBinding(const AdditionalKeywords &Keywords, + JsModuleReference &Reference) { + // * as prefix from '...'; + if (Current->isNot(tok::star)) + return false; + nextToken(); + if (Current->isNot(Keywords.kw_as)) + return false; + nextToken(); + if (Current->isNot(tok::identifier)) + return false; + Reference.Prefix = Current->TokenText; + return true; + } + + bool parseNamedBindings(const AdditionalKeywords &Keywords, + JsModuleReference &Reference) { + if (Current->isNot(tok::l_brace)) + return false; + + // {sym as alias, sym2 as ...} from '...'; + nextToken(); + while (true) { + if (Current->is(tok::r_brace)) + return true; + if (Current->isNot(tok::identifier)) + return false; + + JsImportedSymbol Symbol; + Symbol.Symbol = Current->TokenText; + // Make sure to include any preceding comments. + Symbol.Range.setBegin( + Current->getPreviousNonComment()->Next->WhitespaceRange.getBegin()); + nextToken(); + + if (Current->is(Keywords.kw_as)) { + nextToken(); + if (Current->isNot(tok::identifier)) + return false; + Symbol.Alias = Current->TokenText; + nextToken(); + } + Symbol.Range.setEnd(Current->Tok.getLocation()); + Reference.Symbols.push_back(Symbol); + + if (Current->is(tok::r_brace)) + return true; + if (Current->isNot(tok::comma)) + return false; + nextToken(); + } + } +}; + +tooling::Replacements sortJavaScriptImports(const FormatStyle &Style, + StringRef Code, + ArrayRef<tooling::Range> Ranges, + StringRef FileName) { + // FIXME: Cursor support. + std::unique_ptr<Environment> Env = + Environment::CreateVirtualEnvironment(Code, FileName, Ranges); + JavaScriptImportSorter Sorter(*Env, Style); + return Sorter.process(); +} + +} // end namespace format +} // end namespace clang diff --git a/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.h b/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.h new file mode 100644 index 00000000000..f22a051008f --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/SortJavaScriptImports.h @@ -0,0 +1,36 @@ +//===--- SortJavaScriptImports.h - Sort ES6 Imports -------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements a sorter for JavaScript ES6 imports. +/// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CLANG_LIB_FORMAT_SORTJAVASCRIPTIMPORTS_H +#define LLVM_CLANG_LIB_FORMAT_SORTJAVASCRIPTIMPORTS_H + +#include "clang/Basic/LLVM.h" +#include "clang/Format/Format.h" +#include "llvm/ADT/ArrayRef.h" +#include "llvm/ADT/StringRef.h" + +namespace clang { +namespace format { + +// Sort JavaScript ES6 imports/exports in ``Code``. The generated replacements +// only monotonically increase the length of the given code. +tooling::Replacements sortJavaScriptImports(const FormatStyle &Style, + StringRef Code, + ArrayRef<tooling::Range> Ranges, + StringRef FileName); + +} // end namespace format +} // end namespace clang + +#endif diff --git a/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.cpp b/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.cpp new file mode 100644 index 00000000000..89ac35f3e84 --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.cpp @@ -0,0 +1,138 @@ +//===--- TokenAnalyzer.cpp - Analyze Token Streams --------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file implements an abstract TokenAnalyzer and associated helper +/// classes. TokenAnalyzer can be extended to generate replacements based on +/// an annotated and pre-processed token stream. +/// +//===----------------------------------------------------------------------===// + +#include "TokenAnalyzer.h" +#include "AffectedRangeManager.h" +#include "Encoding.h" +#include "FormatToken.h" +#include "FormatTokenLexer.h" +#include "TokenAnnotator.h" +#include "UnwrappedLineParser.h" +#include "clang/Basic/Diagnostic.h" +#include "clang/Basic/DiagnosticOptions.h" +#include "clang/Basic/FileManager.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Format/Format.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/Support/Debug.h" + +#define DEBUG_TYPE "format-formatter" + +namespace clang { +namespace format { + +// This sets up an virtual file system with file \p FileName containing \p +// Code. +std::unique_ptr<Environment> +Environment::CreateVirtualEnvironment(StringRef Code, StringRef FileName, + ArrayRef<tooling::Range> Ranges) { + // This is referenced by `FileMgr` and will be released by `FileMgr` when it + // is deleted. + IntrusiveRefCntPtr<vfs::InMemoryFileSystem> InMemoryFileSystem( + new vfs::InMemoryFileSystem); + // This is passed to `SM` as reference, so the pointer has to be referenced + // in `Environment` so that `FileMgr` can out-live this function scope. + std::unique_ptr<FileManager> FileMgr( + new FileManager(FileSystemOptions(), InMemoryFileSystem)); + // This is passed to `SM` as reference, so the pointer has to be referenced + // by `Environment` due to the same reason above. + std::unique_ptr<DiagnosticsEngine> Diagnostics(new DiagnosticsEngine( + IntrusiveRefCntPtr<DiagnosticIDs>(new DiagnosticIDs), + new DiagnosticOptions)); + // This will be stored as reference, so the pointer has to be stored in + // due to the same reason above. + std::unique_ptr<SourceManager> VirtualSM( + new SourceManager(*Diagnostics, *FileMgr)); + InMemoryFileSystem->addFile( + FileName, 0, llvm::MemoryBuffer::getMemBuffer( + Code, FileName, /*RequiresNullTerminator=*/false)); + FileID ID = VirtualSM->createFileID(FileMgr->getFile(FileName), + SourceLocation(), clang::SrcMgr::C_User); + assert(ID.isValid()); + SourceLocation StartOfFile = VirtualSM->getLocForStartOfFile(ID); + std::vector<CharSourceRange> CharRanges; + for (const tooling::Range &Range : Ranges) { + SourceLocation Start = StartOfFile.getLocWithOffset(Range.getOffset()); + SourceLocation End = Start.getLocWithOffset(Range.getLength()); + CharRanges.push_back(CharSourceRange::getCharRange(Start, End)); + } + return llvm::make_unique<Environment>(ID, std::move(FileMgr), + std::move(VirtualSM), + std::move(Diagnostics), CharRanges); +} + +TokenAnalyzer::TokenAnalyzer(const Environment &Env, const FormatStyle &Style) + : Style(Style), Env(Env), + AffectedRangeMgr(Env.getSourceManager(), Env.getCharRanges()), + UnwrappedLines(1), + Encoding(encoding::detectEncoding( + Env.getSourceManager().getBufferData(Env.getFileID()))) { + DEBUG( + llvm::dbgs() << "File encoding: " + << (Encoding == encoding::Encoding_UTF8 ? "UTF8" : "unknown") + << "\n"); + DEBUG(llvm::dbgs() << "Language: " << getLanguageName(Style.Language) + << "\n"); +} + +tooling::Replacements TokenAnalyzer::process() { + tooling::Replacements Result; + FormatTokenLexer Tokens(Env.getSourceManager(), Env.getFileID(), Style, + Encoding); + + UnwrappedLineParser Parser(Style, Tokens.getKeywords(), Tokens.lex(), *this); + Parser.parse(); + assert(UnwrappedLines.rbegin()->empty()); + for (unsigned Run = 0, RunE = UnwrappedLines.size(); Run + 1 != RunE; ++Run) { + DEBUG(llvm::dbgs() << "Run " << Run << "...\n"); + SmallVector<AnnotatedLine *, 16> AnnotatedLines; + + TokenAnnotator Annotator(Style, Tokens.getKeywords()); + for (unsigned i = 0, e = UnwrappedLines[Run].size(); i != e; ++i) { + AnnotatedLines.push_back(new AnnotatedLine(UnwrappedLines[Run][i])); + Annotator.annotate(*AnnotatedLines.back()); + } + + tooling::Replacements RunResult = + analyze(Annotator, AnnotatedLines, Tokens, Result); + + DEBUG({ + llvm::dbgs() << "Replacements for run " << Run << ":\n"; + for (tooling::Replacements::iterator I = RunResult.begin(), + E = RunResult.end(); + I != E; ++I) { + llvm::dbgs() << I->toString() << "\n"; + } + }); + for (unsigned i = 0, e = AnnotatedLines.size(); i != e; ++i) { + delete AnnotatedLines[i]; + } + Result.insert(RunResult.begin(), RunResult.end()); + } + return Result; +} + +void TokenAnalyzer::consumeUnwrappedLine(const UnwrappedLine &TheLine) { + assert(!UnwrappedLines.empty()); + UnwrappedLines.back().push_back(TheLine); +} + +void TokenAnalyzer::finishRun() { + UnwrappedLines.push_back(SmallVector<UnwrappedLine, 16>()); +} + +} // end namespace format +} // end namespace clang diff --git a/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.h b/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.h new file mode 100644 index 00000000000..c1aa9c594fc --- /dev/null +++ b/gnu/llvm/tools/clang/lib/Format/TokenAnalyzer.h @@ -0,0 +1,108 @@ +//===--- TokenAnalyzer.h - Analyze Token Streams ----------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// \brief This file declares an abstract TokenAnalyzer, and associated helper +/// classes. TokenAnalyzer can be extended to generate replacements based on +/// an annotated and pre-processed token stream. +/// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CLANG_LIB_FORMAT_TOKENANALYZER_H +#define LLVM_CLANG_LIB_FORMAT_TOKENANALYZER_H + +#include "AffectedRangeManager.h" +#include "Encoding.h" +#include "FormatToken.h" +#include "FormatTokenLexer.h" +#include "TokenAnnotator.h" +#include "UnwrappedLineParser.h" +#include "clang/Basic/Diagnostic.h" +#include "clang/Basic/DiagnosticOptions.h" +#include "clang/Basic/FileManager.h" +#include "clang/Basic/SourceManager.h" +#include "clang/Format/Format.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/Support/Debug.h" + +#define DEBUG_TYPE "format-formatter" + +namespace clang { +namespace format { + +class Environment { +public: + Environment(SourceManager &SM, FileID ID, ArrayRef<CharSourceRange> Ranges) + : ID(ID), CharRanges(Ranges.begin(), Ranges.end()), SM(SM) {} + + Environment(FileID ID, std::unique_ptr<FileManager> FileMgr, + std::unique_ptr<SourceManager> VirtualSM, + std::unique_ptr<DiagnosticsEngine> Diagnostics, + const std::vector<CharSourceRange> &CharRanges) + : ID(ID), CharRanges(CharRanges.begin(), CharRanges.end()), + SM(*VirtualSM), FileMgr(std::move(FileMgr)), + VirtualSM(std::move(VirtualSM)), Diagnostics(std::move(Diagnostics)) {} + + // This sets up an virtual file system with file \p FileName containing \p + // Code. + static std::unique_ptr<Environment> + CreateVirtualEnvironment(StringRef Code, StringRef FileName, + ArrayRef<tooling::Range> Ranges); + + FileID getFileID() const { return ID; } + + StringRef getFileName() const { return FileName; } + + ArrayRef<CharSourceRange> getCharRanges() const { return CharRanges; } + + const SourceManager &getSourceManager() const { return SM; } + +private: + FileID ID; + StringRef FileName; + SmallVector<CharSourceRange, 8> CharRanges; + SourceManager &SM; + + // The order of these fields are important - they should be in the same order + // as they are created in `CreateVirtualEnvironment` so that they can be + // deleted in the reverse order as they are created. + std::unique_ptr<FileManager> FileMgr; + std::unique_ptr<SourceManager> VirtualSM; + std::unique_ptr<DiagnosticsEngine> Diagnostics; +}; + +class TokenAnalyzer : public UnwrappedLineConsumer { +public: + TokenAnalyzer(const Environment &Env, const FormatStyle &Style); + + tooling::Replacements process(); + +protected: + virtual tooling::Replacements + analyze(TokenAnnotator &Annotator, + SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, + FormatTokenLexer &Tokens, tooling::Replacements &Result) = 0; + + void consumeUnwrappedLine(const UnwrappedLine &TheLine) override; + + void finishRun() override; + + FormatStyle Style; + // Stores Style, FileID and SourceManager etc. + const Environment &Env; + // AffectedRangeMgr stores ranges to be fixed. + AffectedRangeManager AffectedRangeMgr; + SmallVector<SmallVector<UnwrappedLine, 16>, 2> UnwrappedLines; + encoding::Encoding Encoding; +}; + +} // end namespace format +} // end namespace clang + +#endif diff --git a/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.cpp b/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.cpp index 8fbb43b7996..4a90522e6e3 100644 --- a/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.cpp +++ b/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.cpp @@ -42,11 +42,24 @@ public: private: bool parseAngle() { - if (!CurrentToken) + if (!CurrentToken || !CurrentToken->Previous) + return false; + if (NonTemplateLess.count(CurrentToken->Previous)) return false; + + const FormatToken& Previous = *CurrentToken->Previous; + if (Previous.Previous) { + if (Previous.Previous->Tok.isLiteral()) + return false; + if (Previous.Previous->is(tok::r_paren) && Contexts.size() > 1 && + (!Previous.Previous->MatchingParen || + !Previous.Previous->MatchingParen->is(TT_OverloadedOperatorLParen))) + return false; + } + FormatToken *Left = CurrentToken->Previous; Left->ParentBracket = Contexts.back().ContextKind; - ScopedContextCreator ContextCreator(*this, tok::less, 10); + ScopedContextCreator ContextCreator(*this, tok::less, 12); // If this angle is in the context of an expression, we need to be more // hesitant to detect it as opening template parameters. @@ -121,6 +134,10 @@ private: if (Left->is(TT_OverloadedOperatorLParen)) { Contexts.back().IsExpression = false; + } else if (Style.Language == FormatStyle::LK_JavaScript && + Line.startsWith(Keywords.kw_type, tok::identifier)) { + // type X = (...); + Contexts.back().IsExpression = false; } else if (Left->Previous && (Left->Previous->isOneOf(tok::kw_static_assert, tok::kw_decltype, tok::kw_if, tok::kw_while, tok::l_paren, @@ -128,6 +145,16 @@ private: Left->Previous->is(TT_BinaryOperator))) { // static_assert, if and while usually contain expressions. Contexts.back().IsExpression = true; + } else if (Style.Language == FormatStyle::LK_JavaScript && Left->Previous && + (Left->Previous->is(Keywords.kw_function) || + (Left->Previous->endsSequence(tok::identifier, + Keywords.kw_function)))) { + // function(...) or function f(...) + Contexts.back().IsExpression = false; + } else if (Style.Language == FormatStyle::LK_JavaScript && Left->Previous && + Left->Previous->is(TT_JsTypeColon)) { + // let x: (SomeType); + Contexts.back().IsExpression = false; } else if (Left->Previous && Left->Previous->is(tok::r_square) && Left->Previous->MatchingParen && Left->Previous->MatchingParen->is(TT_LambdaLSquare)) { @@ -159,8 +186,8 @@ private: Left->Type = TT_ObjCMethodExpr; } - bool MightBeFunctionType = CurrentToken->isOneOf(tok::star, tok::amp) && - !Contexts[Contexts.size() - 2].IsExpression; + bool MightBeFunctionType = !Contexts[Contexts.size() - 2].IsExpression; + bool ProbablyFunctionType = CurrentToken->isOneOf(tok::star, tok::amp); bool HasMultipleLines = false; bool HasMultipleParametersOnALine = false; bool MightBeObjCForRangeLoop = @@ -187,14 +214,15 @@ private: if (CurrentToken->Previous->is(TT_PointerOrReference) && CurrentToken->Previous->Previous->isOneOf(tok::l_paren, tok::coloncolon)) - MightBeFunctionType = true; + ProbablyFunctionType = true; + if (CurrentToken->is(tok::comma)) + MightBeFunctionType = false; if (CurrentToken->Previous->is(TT_BinaryOperator)) Contexts.back().IsExpression = true; if (CurrentToken->is(tok::r_paren)) { - if (MightBeFunctionType && CurrentToken->Next && + if (MightBeFunctionType && ProbablyFunctionType && CurrentToken->Next && (CurrentToken->Next->is(tok::l_paren) || - (CurrentToken->Next->is(tok::l_square) && - Line.MustBeDeclaration))) + (CurrentToken->Next->is(tok::l_square) && Line.MustBeDeclaration))) Left->Type = TT_FunctionTypeLParen; Left->MatchingParen = CurrentToken; CurrentToken->MatchingParen = Left; @@ -299,9 +327,9 @@ private: Left->Type = TT_JsComputedPropertyName; } else if (Style.Language == FormatStyle::LK_Proto || (Parent && - Parent->isOneOf(TT_BinaryOperator, tok::at, tok::comma, - tok::l_paren, tok::l_square, tok::question, - tok::colon, tok::kw_return, + Parent->isOneOf(TT_BinaryOperator, TT_TemplateCloser, tok::at, + tok::comma, tok::l_paren, tok::l_square, + tok::question, tok::colon, tok::kw_return, // Should only be relevant to JavaScript: tok::kw_default))) { Left->Type = TT_ArrayInitializerLSquare; @@ -396,7 +424,8 @@ private: (!Contexts.back().ColonIsDictLiteral || Style.Language != FormatStyle::LK_Cpp)) || Style.Language == FormatStyle::LK_Proto) && - Previous->Tok.getIdentifierInfo()) + (Previous->Tok.getIdentifierInfo() || + Previous->is(tok::string_literal))) Previous->Type = TT_SelectorName; if (CurrentToken->is(tok::colon) || Style.Language == FormatStyle::LK_JavaScript) @@ -410,7 +439,7 @@ private: } void updateParameterCount(FormatToken *Left, FormatToken *Current) { - if (Current->is(tok::l_brace) && !Current->is(TT_DictLiteral)) + if (Current->is(tok::l_brace) && Current->BlockKind == BK_Block) ++Left->BlockParameterCount; if (Current->is(tok::comma)) { ++Left->ParameterCount; @@ -491,7 +520,7 @@ private: Tok->Type = TT_BitFieldColon; } else if (Contexts.size() == 1 && !Line.First->isOneOf(tok::kw_enum, tok::kw_case)) { - if (Tok->Previous->is(tok::r_paren)) + if (Tok->Previous->isOneOf(tok::r_paren, tok::kw_noexcept)) Tok->Type = TT_CtorInitializerColon; else Tok->Type = TT_InheritanceColon; @@ -504,6 +533,14 @@ private: Tok->Type = TT_InlineASMColon; } break; + case tok::pipe: + case tok::amp: + // | and & in declarations/type expressions represent union and + // intersection types, respectively. + if (Style.Language == FormatStyle::LK_JavaScript && + !Contexts.back().IsExpression) + Tok->Type = TT_JsTypeOperator; + break; case tok::kw_if: case tok::kw_while: if (CurrentToken && CurrentToken->is(tok::l_paren)) { @@ -513,6 +550,9 @@ private: } break; case tok::kw_for: + if (Style.Language == FormatStyle::LK_JavaScript && Tok->Previous && + Tok->Previous->is(tok::period)) + break; Contexts.back().ColonIsForRangeExpr = true; next(); if (!parseParens()) @@ -550,11 +590,7 @@ private: return false; break; case tok::less: - if (!NonTemplateLess.count(Tok) && - (!Tok->Previous || - (!Tok->Previous->Tok.isLiteral() && - !(Tok->Previous->is(tok::r_paren) && Contexts.size() > 1))) && - parseAngle()) { + if (parseAngle()) { Tok->Type = TT_TemplateOpener; } else { Tok->Type = TT_BinaryOperator; @@ -603,7 +639,7 @@ private: } // Declarations cannot be conditional expressions, this can only be part // of a type declaration. - if (Line.MustBeDeclaration && + if (Line.MustBeDeclaration && !Contexts.back().IsExpression && Style.Language == FormatStyle::LK_JavaScript) break; parseConditional(); @@ -666,10 +702,24 @@ private: } LineType parsePreprocessorDirective() { + bool IsFirstToken = CurrentToken->IsFirst; LineType Type = LT_PreprocessorDirective; next(); if (!CurrentToken) return Type; + + if (Style.Language == FormatStyle::LK_JavaScript && IsFirstToken) { + // JavaScript files can contain shebang lines of the form: + // #!/usr/bin/env node + // Treat these like C++ #include directives. + while (CurrentToken) { + // Tokens cannot be comments here. + CurrentToken->Type = TT_ImplicitStringLiteral; + next(); + } + return LT_ImportStatement; + } + if (CurrentToken->Tok.is(tok::numeric_constant)) { CurrentToken->SpacesRequiredBefore = 1; return Type; @@ -745,11 +795,29 @@ public: bool KeywordVirtualFound = false; bool ImportStatement = false; + + // import {...} from '...'; + if (Style.Language == FormatStyle::LK_JavaScript && + CurrentToken->is(Keywords.kw_import)) + ImportStatement = true; + while (CurrentToken) { if (CurrentToken->is(tok::kw_virtual)) KeywordVirtualFound = true; - if (isImportStatement(*CurrentToken)) - ImportStatement = true; + if (Style.Language == FormatStyle::LK_JavaScript) { + // export {...} from '...'; + // An export followed by "from 'some string';" is a re-export from + // another module identified by a URI and is treated as a + // LT_ImportStatement (i.e. prevent wraps on it for long URIs). + // Just "export {...};" or "export class ..." should not be treated as + // an import in this sense. + if (Line.First->is(tok::kw_export) && + CurrentToken->is(Keywords.kw_from) && CurrentToken->Next && + CurrentToken->Next->isStringLiteral()) + ImportStatement = true; + if (isClosureImportStatement(*CurrentToken)) + ImportStatement = true; + } if (!consumeToken()) return LT_Invalid; } @@ -769,15 +837,15 @@ public: } private: - bool isImportStatement(const FormatToken &Tok) { + bool isClosureImportStatement(const FormatToken &Tok) { // FIXME: Closure-library specific stuff should not be hard-coded but be // configurable. - return Style.Language == FormatStyle::LK_JavaScript && - Tok.TokenText == "goog" && Tok.Next && Tok.Next->is(tok::period) && + return Tok.TokenText == "goog" && Tok.Next && Tok.Next->is(tok::period) && Tok.Next->Next && (Tok.Next->Next->TokenText == "module" || Tok.Next->Next->TokenText == "provide" || Tok.Next->Next->TokenText == "require" || - Tok.Next->Next->TokenText == "setTestOnly") && + Tok.Next->Next->TokenText == "setTestOnly" || + Tok.Next->Next->TokenText == "forwardDeclare") && Tok.Next->Next->Next && Tok.Next->Next->Next->is(tok::l_paren); } @@ -853,6 +921,9 @@ private: void modifyContext(const FormatToken &Current) { if (Current.getPrecedence() == prec::Assignment && !Line.First->isOneOf(tok::kw_template, tok::kw_using, tok::kw_return) && + // Type aliases use `type X = ...;` in TypeScript. + !(Style.Language == FormatStyle::LK_JavaScript && + Line.startsWith(Keywords.kw_type, tok::identifier)) && (!Current.Previous || Current.Previous->isNot(tok::kw_operator))) { Contexts.back().IsExpression = true; if (!Line.startsWith(TT_UnaryOperator)) { @@ -882,17 +953,17 @@ private: Contexts.back().IsExpression = false; } else if (Current.is(TT_LambdaArrow) || Current.is(Keywords.kw_assert)) { Contexts.back().IsExpression = Style.Language == FormatStyle::LK_Java; + } else if (Current.Previous && + Current.Previous->is(TT_CtorInitializerColon)) { + Contexts.back().IsExpression = true; + Contexts.back().InCtorInitializer = true; } else if (Current.isOneOf(tok::r_paren, tok::greater, tok::comma)) { for (FormatToken *Previous = Current.Previous; Previous && Previous->isOneOf(tok::star, tok::amp); Previous = Previous->Previous) Previous->Type = TT_PointerOrReference; - if (Line.MustBeDeclaration) - Contexts.back().IsExpression = Contexts.front().InCtorInitializer; - } else if (Current.Previous && - Current.Previous->is(TT_CtorInitializerColon)) { - Contexts.back().IsExpression = true; - Contexts.back().InCtorInitializer = true; + if (Line.MustBeDeclaration && !Contexts.front().InCtorInitializer) + Contexts.back().IsExpression = false; } else if (Current.is(tok::kw_new)) { Contexts.back().CanBeExpression = false; } else if (Current.isOneOf(tok::semi, tok::exclaim)) { @@ -938,7 +1009,7 @@ private: Current.Type = TT_UnaryOperator; } else if (Current.is(tok::question)) { if (Style.Language == FormatStyle::LK_JavaScript && - Line.MustBeDeclaration) { + Line.MustBeDeclaration && !Contexts.back().IsExpression) { // In JavaScript, `interface X { foo?(): bar; }` is an optional method // on the interface, not a ternary expression. Current.Type = TT_JsTypeOptionalQuestion; @@ -964,7 +1035,8 @@ private: Current.Type = TT_CastRParen; if (Current.MatchingParen && Current.Next && !Current.Next->isBinaryOperator() && - !Current.Next->isOneOf(tok::semi, tok::colon, tok::l_brace)) + !Current.Next->isOneOf(tok::semi, tok::colon, tok::l_brace, + tok::period, tok::arrow, tok::coloncolon)) if (FormatToken *BeforeParen = Current.MatchingParen->Previous) if (BeforeParen->is(tok::identifier) && BeforeParen->TokenText == BeforeParen->TokenText.upper() && @@ -1035,6 +1107,9 @@ private: if (Tok.Previous->isOneOf(TT_LeadingJavaAnnotation, Keywords.kw_instanceof)) return false; + if (Style.Language == FormatStyle::LK_JavaScript && + Tok.Previous->is(Keywords.kw_in)) + return false; // Skip "const" as it does not have an influence on whether this is a name. FormatToken *PreviousNotConst = Tok.Previous; @@ -1078,7 +1153,7 @@ private: FormatToken *LeftOfParens = Tok.MatchingParen->getPreviousNonComment(); if (LeftOfParens) { - // If there is an opening parenthesis left of the current parentheses, + // If there is a closing parenthesis left of the current parentheses, // look past it as these might be chained casts. if (LeftOfParens->is(tok::r_paren)) { if (!LeftOfParens->MatchingParen || @@ -1097,7 +1172,7 @@ private: // Certain other tokens right before the parentheses are also signals that // this cannot be a cast. if (LeftOfParens->isOneOf(tok::at, tok::r_square, TT_OverloadedOperator, - TT_TemplateCloser)) + TT_TemplateCloser, tok::ellipsis)) return false; } @@ -1131,9 +1206,9 @@ private: if (!LeftOfParens) return false; - // If the following token is an identifier, this is a cast. All cases where - // this can be something else are handled above. - if (Tok.Next->is(tok::identifier)) + // If the following token is an identifier or 'this', this is a cast. All + // cases where this can be something else are handled above. + if (Tok.Next->isOneOf(tok::identifier, tok::kw_this)) return true; if (!Tok.Next->Next) @@ -1390,11 +1465,15 @@ private: Style.Language == FormatStyle::LK_JavaScript) && Current->is(Keywords.kw_instanceof)) return prec::Relational; + if (Style.Language == FormatStyle::LK_JavaScript && + Current->is(Keywords.kw_in)) + return prec::Relational; if (Current->is(TT_BinaryOperator) || Current->is(tok::comma)) return Current->getPrecedence(); if (Current->isOneOf(tok::period, tok::arrow)) return PrecedenceArrowAndPeriod; - if (Style.Language == FormatStyle::LK_Java && + if ((Style.Language == FormatStyle::LK_Java || + Style.Language == FormatStyle::LK_JavaScript) && Current->isOneOf(Keywords.kw_extends, Keywords.kw_implements, Keywords.kw_throws)) return 0; @@ -1508,7 +1587,8 @@ void TokenAnnotator::annotate(AnnotatedLine &Line) { // This function heuristically determines whether 'Current' starts the name of a // function declaration. -static bool isFunctionDeclarationName(const FormatToken &Current) { +static bool isFunctionDeclarationName(const FormatToken &Current, + const AnnotatedLine &Line) { auto skipOperatorName = [](const FormatToken* Next) -> const FormatToken* { for (; Next; Next = Next->Next) { if (Next->is(TT_OverloadedOperatorLParen)) @@ -1528,6 +1608,7 @@ static bool isFunctionDeclarationName(const FormatToken &Current) { return nullptr; }; + // Find parentheses of parameter list. const FormatToken *Next = Current.Next; if (Current.is(tok::kw_operator)) { if (Current.Previous && Current.Previous->is(tok::coloncolon)) @@ -1557,14 +1638,22 @@ static bool isFunctionDeclarationName(const FormatToken &Current) { } } - if (!Next || !Next->is(tok::l_paren)) + // Check whether parameter list can be long to a function declaration. + if (!Next || !Next->is(tok::l_paren) || !Next->MatchingParen) return false; + // If the lines ends with "{", this is likely an function definition. + if (Line.Last->is(tok::l_brace)) + return true; if (Next->Next == Next->MatchingParen) + return true; // Empty parentheses. + // If there is an &/&& after the r_paren, this is likely a function. + if (Next->MatchingParen->Next && + Next->MatchingParen->Next->is(TT_PointerOrReference)) return true; for (const FormatToken *Tok = Next->Next; Tok && Tok != Next->MatchingParen; Tok = Tok->Next) { if (Tok->is(tok::kw_const) || Tok->isSimpleTypeSpecifier() || - Tok->isOneOf(TT_PointerOrReference, TT_StartOfName)) + Tok->isOneOf(TT_PointerOrReference, TT_StartOfName, tok::ellipsis)) return true; if (Tok->isOneOf(tok::l_brace, tok::string_literal, TT_ObjCMethodExpr) || Tok->Tok.isLiteral()) @@ -1610,7 +1699,7 @@ void TokenAnnotator::calculateFormattingInformation(AnnotatedLine &Line) { FormatToken *Current = Line.First->Next; bool InFunctionDecl = Line.MightBeFunctionDecl; while (Current) { - if (isFunctionDeclarationName(*Current)) + if (isFunctionDeclarationName(*Current, Line)) Current->Type = TT_FunctionDeclarationName; if (Current->is(TT_LineComment)) { if (Current->Previous->BlockKind == BK_BracedInit && @@ -1736,7 +1825,7 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line, if (Style.Language == FormatStyle::LK_Proto) return 1; if (Left.is(tok::r_square)) - return 25; + return 200; // Slightly prefer formatting local lambda definitions like functions. if (Right.is(TT_LambdaLSquare) && Left.is(tok::equal)) return 35; @@ -1768,6 +1857,8 @@ unsigned TokenAnnotator::splitPenalty(const AnnotatedLine &Line, return 500; if (Left.isOneOf(tok::kw_class, tok::kw_struct)) return 5000; + if (Left.is(tok::comment)) + return 1000; if (Left.isOneOf(TT_RangeBasedForLoopColon, TT_InheritanceColon)) return 2; @@ -1910,15 +2001,14 @@ bool TokenAnnotator::spaceRequiredBetween(const AnnotatedLine &Line, if (Left.is(tok::less) || Right.isOneOf(tok::greater, tok::less)) return false; if (Right.is(tok::ellipsis)) - return Left.Tok.isLiteral(); + return Left.Tok.isLiteral() || (Left.is(tok::identifier) && Left.Previous && + Left.Previous->is(tok::kw_case)); if (Left.is(tok::l_square) && Right.is(tok::amp)) return false; if (Right.is(TT_PointerOrReference)) - return (Left.is(tok::r_paren) && Left.MatchingParen && - (Left.MatchingParen->is(TT_OverloadedOperatorLParen) || - (Left.MatchingParen->Previous && - Left.MatchingParen->Previous->is(TT_FunctionDeclarationName)))) || - (Left.Tok.isLiteral() || + return (Left.is(tok::r_paren) && Line.MightBeFunctionDecl) || + (Left.Tok.isLiteral() || (Left.is(tok::kw_const) && Left.Previous && + Left.Previous->is(tok::r_paren)) || (!Left.isOneOf(TT_PointerOrReference, tok::l_paren) && (Style.PointerAlignment != FormatStyle::PAS_Left || Line.IsMultiVariableDeclStmt))); @@ -2021,8 +2111,14 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line, Left.isOneOf(Keywords.kw_returns, Keywords.kw_option)) return true; } else if (Style.Language == FormatStyle::LK_JavaScript) { - if (Left.isOneOf(Keywords.kw_let, Keywords.kw_var, TT_JsFatArrow, - Keywords.kw_in)) + if (Left.is(TT_JsFatArrow)) + return true; + if (Right.is(tok::star) && + Left.isOneOf(Keywords.kw_function, Keywords.kw_yield)) + return false; + if (Left.isOneOf(Keywords.kw_let, Keywords.kw_var, Keywords.kw_in, + Keywords.kw_of, tok::kw_const) && + (!Left.Previous || !Left.Previous->is(tok::period))) return true; if (Left.is(tok::kw_default) && Left.Previous && Left.Previous->is(tok::kw_export)) @@ -2031,6 +2127,8 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line, return true; if (Right.isOneOf(TT_JsTypeColon, TT_JsTypeOptionalQuestion)) return false; + if (Left.is(TT_JsTypeOperator) || Right.is(TT_JsTypeOperator)) + return false; if ((Left.is(tok::l_brace) || Right.is(tok::r_brace)) && Line.First->isOneOf(Keywords.kw_import, tok::kw_export)) return false; @@ -2043,6 +2141,11 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line, // locations that should have whitespace following are identified by the // above set of follower tokens. return false; + // Postfix non-null assertion operator, as in `foo!.bar()`. + if (Right.is(tok::exclaim) && (Left.isOneOf(tok::identifier, tok::r_paren, + tok::r_square, tok::r_brace) || + Left.Tok.isLiteral())) + return false; } else if (Style.Language == FormatStyle::LK_Java) { if (Left.is(tok::r_square) && Right.is(tok::l_brace)) return true; @@ -2111,10 +2214,11 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line, if (!Style.SpaceBeforeAssignmentOperators && Right.getPrecedence() == prec::Assignment) return false; - if (Right.is(tok::coloncolon) && Left.isNot(tok::l_brace)) + if (Right.is(tok::coloncolon) && !Left.isOneOf(tok::l_brace, tok::comment)) return (Left.is(TT_TemplateOpener) && Style.Standard == FormatStyle::LS_Cpp03) || - !(Left.isOneOf(tok::identifier, tok::l_paren, tok::r_paren) || + !(Left.isOneOf(tok::identifier, tok::l_paren, tok::r_paren, + tok::l_square) || Left.isOneOf(TT_TemplateCloser, TT_TemplateOpener)); if ((Left.is(TT_TemplateOpener)) != (Right.is(TT_TemplateCloser))) return Style.SpacesInAngles; @@ -2152,8 +2256,8 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line, if (Style.Language == FormatStyle::LK_JavaScript) { // FIXME: This might apply to other languages and token kinds. - if (Right.is(tok::char_constant) && Left.is(tok::plus) && Left.Previous && - Left.Previous->is(tok::char_constant)) + if (Right.is(tok::string_literal) && Left.is(tok::plus) && Left.Previous && + Left.Previous->is(tok::string_literal)) return true; if (Left.is(TT_DictLiteral) && Left.is(tok::l_brace) && Line.Level == 0 && Left.Previous && Left.Previous->is(tok::equal) && @@ -2239,9 +2343,6 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line, return (Line.startsWith(tok::kw_enum) && Style.BraceWrapping.AfterEnum) || (Line.startsWith(tok::kw_class) && Style.BraceWrapping.AfterClass) || (Line.startsWith(tok::kw_struct) && Style.BraceWrapping.AfterStruct); - if (Style.Language == FormatStyle::LK_Proto && Left.isNot(tok::l_brace) && - Right.is(TT_SelectorName)) - return true; if (Left.is(TT_ObjCBlockLBrace) && !Style.AllowShortBlocksOnASingleLine) return true; @@ -2268,12 +2369,20 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line, Keywords.kw_implements)) return true; } else if (Style.Language == FormatStyle::LK_JavaScript) { + if (Left.is(tok::kw_return)) + return false; // Otherwise a semicolon is inserted. if (Left.is(TT_JsFatArrow) && Right.is(tok::l_brace)) return false; if (Left.is(TT_JsTypeColon)) return true; if (Right.NestingLevel == 0 && Right.is(Keywords.kw_is)) return false; + if (Left.is(Keywords.kw_in)) + return Style.BreakBeforeBinaryOperators == FormatStyle::BOS_None; + if (Right.is(Keywords.kw_in)) + return Style.BreakBeforeBinaryOperators != FormatStyle::BOS_None; + if (Right.is(Keywords.kw_as)) + return false; // must not break before as in 'x as type' casts } if (Left.is(tok::at)) @@ -2390,7 +2499,7 @@ bool TokenAnnotator::canBreakBefore(const AnnotatedLine &Line, Left.getPrecedence() == prec::Assignment)) return true; return Left.isOneOf(tok::comma, tok::coloncolon, tok::semi, tok::l_brace, - tok::kw_class, tok::kw_struct) || + tok::kw_class, tok::kw_struct, tok::comment) || Right.isMemberAccess() || Right.isOneOf(TT_TrailingReturnArrow, TT_LambdaArrow, tok::lessless, tok::colon, tok::l_square, tok::at) || diff --git a/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.h b/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.h index 5329f1f3f2f..baa68ded974 100644 --- a/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.h +++ b/gnu/llvm/tools/clang/lib/Format/TokenAnnotator.h @@ -83,7 +83,15 @@ public: /// \c true if this line starts with the given tokens in order, ignoring /// comments. template <typename... Ts> bool startsWith(Ts... Tokens) const { - return startsWith(First, Tokens...); + return First && First->startsSequence(Tokens...); + } + + /// \c true if this line ends with the given tokens in reversed order, + /// ignoring comments. + /// For example, given tokens [T1, T2, T3, ...], the function returns true if + /// this line is like "... T3 T2 T1". + template <typename... Ts> bool endsWith(Ts... Tokens) const { + return Last && Last->endsSequence(Tokens...); } /// \c true if this line looks like a function definition instead of a @@ -122,18 +130,6 @@ private: // Disallow copying. AnnotatedLine(const AnnotatedLine &) = delete; void operator=(const AnnotatedLine &) = delete; - - template <typename A, typename... Ts> - bool startsWith(FormatToken *Tok, A K1) const { - while (Tok && Tok->is(tok::comment)) - Tok = Tok->Next; - return Tok && Tok->is(K1); - } - - template <typename A, typename... Ts> - bool startsWith(FormatToken *Tok, A K1, Ts... Tokens) const { - return startsWith(Tok, K1) && startsWith(Tok->Next, Tokens...); - } }; /// \brief Determines extra information about the tokens comprising an diff --git a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineFormatter.cpp b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineFormatter.cpp index f6505690796..35035ea8afb 100644 --- a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineFormatter.cpp +++ b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineFormatter.cpp @@ -847,7 +847,9 @@ UnwrappedLineFormatter::format(const SmallVectorImpl<AnnotatedLine *> &Lines, unsigned ColumnLimit = getColumnLimit(TheLine.InPPDirective, NextLine); bool FitsIntoOneLine = TheLine.Last->TotalLength + Indent <= ColumnLimit || - TheLine.Type == LT_ImportStatement; + (TheLine.Type == LT_ImportStatement && + (Style.Language != FormatStyle::LK_JavaScript || + !Style.JavaScriptWrapImports)); if (Style.ColumnLimit == 0) NoColumnLimitLineFormatter(Indenter, Whitespaces, Style, this) @@ -863,7 +865,9 @@ UnwrappedLineFormatter::format(const SmallVectorImpl<AnnotatedLine *> &Lines, // If no token in the current line is affected, we still need to format // affected children. if (TheLine.ChildrenAffected) - format(TheLine.Children, DryRun); + for (const FormatToken *Tok = TheLine.First; Tok; Tok = Tok->Next) + if (!Tok->Children.empty()) + format(Tok->Children, DryRun); // Adapt following lines on the current indent level to the same level // unless the current \c AnnotatedLine is not at the beginning of a line. diff --git a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.cpp b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.cpp index 7b8f6e65241..2fe72987bc7 100644 --- a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.cpp +++ b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.cpp @@ -363,6 +363,8 @@ void UnwrappedLineParser::calculateBraceTypes(bool ExpectClassBody) { // // We exclude + and - as they can be ObjC visibility modifiers. ProbablyBracedList = + (Style.Language == FormatStyle::LK_JavaScript && + NextTok->isOneOf(Keywords.kw_of, Keywords.kw_in)) || NextTok->isOneOf(tok::comma, tok::period, tok::colon, tok::r_paren, tok::r_square, tok::l_brace, tok::l_square, tok::l_paren, tok::ellipsis) || @@ -428,6 +430,9 @@ void UnwrappedLineParser::parseBlock(bool MustBeDeclaration, bool AddLevel, ++Line->Level; parseLevel(/*HasOpeningBrace=*/true); + if (eof()) + return; + if (MacroBlock ? !FormatTok->is(TT_MacroBlockEnd) : !FormatTok->is(tok::r_brace)) { Line->Level = InitialLevel; @@ -658,6 +663,85 @@ static bool tokenCanStartNewLine(const clang::Token &Tok) { Tok.isNot(tok::kw_noexcept); } +static bool mustBeJSIdent(const AdditionalKeywords &Keywords, + const FormatToken *FormatTok) { + // FIXME: This returns true for C/C++ keywords like 'struct'. + return FormatTok->is(tok::identifier) && + (FormatTok->Tok.getIdentifierInfo() == nullptr || + !FormatTok->isOneOf(Keywords.kw_in, Keywords.kw_of, Keywords.kw_as, + Keywords.kw_async, Keywords.kw_await, + Keywords.kw_yield, Keywords.kw_finally, + Keywords.kw_function, Keywords.kw_import, + Keywords.kw_is, Keywords.kw_let, Keywords.kw_var, + Keywords.kw_abstract, Keywords.kw_extends, + Keywords.kw_implements, Keywords.kw_instanceof, + Keywords.kw_interface, Keywords.kw_throws)); +} + +static bool mustBeJSIdentOrValue(const AdditionalKeywords &Keywords, + const FormatToken *FormatTok) { + return FormatTok->Tok.isLiteral() || mustBeJSIdent(Keywords, FormatTok); +} + +// isJSDeclOrStmt returns true if |FormatTok| starts a declaration or statement +// when encountered after a value (see mustBeJSIdentOrValue). +static bool isJSDeclOrStmt(const AdditionalKeywords &Keywords, + const FormatToken *FormatTok) { + return FormatTok->isOneOf( + tok::kw_return, Keywords.kw_yield, + // conditionals + tok::kw_if, tok::kw_else, + // loops + tok::kw_for, tok::kw_while, tok::kw_do, tok::kw_continue, tok::kw_break, + // switch/case + tok::kw_switch, tok::kw_case, + // exceptions + tok::kw_throw, tok::kw_try, tok::kw_catch, Keywords.kw_finally, + // declaration + tok::kw_const, tok::kw_class, Keywords.kw_var, Keywords.kw_let, + Keywords.kw_async, Keywords.kw_function, + // import/export + Keywords.kw_import, tok::kw_export); +} + +// readTokenWithJavaScriptASI reads the next token and terminates the current +// line if JavaScript Automatic Semicolon Insertion must +// happen between the current token and the next token. +// +// This method is conservative - it cannot cover all edge cases of JavaScript, +// but only aims to correctly handle certain well known cases. It *must not* +// return true in speculative cases. +void UnwrappedLineParser::readTokenWithJavaScriptASI() { + FormatToken *Previous = FormatTok; + readToken(); + FormatToken *Next = FormatTok; + + bool IsOnSameLine = + CommentsBeforeNextToken.empty() + ? Next->NewlinesBefore == 0 + : CommentsBeforeNextToken.front()->NewlinesBefore == 0; + if (IsOnSameLine) + return; + + bool PreviousMustBeValue = mustBeJSIdentOrValue(Keywords, Previous); + if (PreviousMustBeValue && Line && Line->Tokens.size() > 1) { + // If the token before the previous one is an '@', the previous token is an + // annotation and can precede another identifier/value. + const FormatToken *PrePrevious = std::prev(Line->Tokens.end(), 2)->Tok; + if (PrePrevious->is(tok::at)) + return; + } + if (Next->is(tok::exclaim) && PreviousMustBeValue) + addUnwrappedLine(); + bool NextMustBeValue = mustBeJSIdentOrValue(Keywords, Next); + if (NextMustBeValue && (PreviousMustBeValue || + Previous->isOneOf(tok::r_square, tok::r_paren, + tok::plusplus, tok::minusminus))) + addUnwrappedLine(); + if (PreviousMustBeValue && isJSDeclOrStmt(Keywords, Next)) + addUnwrappedLine(); +} + void UnwrappedLineParser::parseStructuralElement() { assert(!FormatTok->is(tok::l_brace)); if (Style.Language == FormatStyle::LK_TableGen && @@ -798,10 +882,23 @@ void UnwrappedLineParser::parseStructuralElement() { /*MunchSemi=*/false); return; } - if (Style.Language == FormatStyle::LK_JavaScript && - FormatTok->is(Keywords.kw_import)) { - parseJavaScriptEs6ImportExport(); - return; + if (FormatTok->is(Keywords.kw_import)) { + if (Style.Language == FormatStyle::LK_JavaScript) { + parseJavaScriptEs6ImportExport(); + return; + } + if (Style.Language == FormatStyle::LK_Proto) { + nextToken(); + if (FormatTok->is(tok::kw_public)) + nextToken(); + if (!FormatTok->is(tok::string_literal)) + return; + nextToken(); + if (FormatTok->is(tok::semi)) + nextToken(); + addUnwrappedLine(); + return; + } } if (FormatTok->isOneOf(Keywords.kw_signals, Keywords.kw_qsignals, Keywords.kw_slots, Keywords.kw_qslots)) { @@ -818,6 +915,7 @@ void UnwrappedLineParser::parseStructuralElement() { break; } do { + const FormatToken *Previous = getPreviousToken(); switch (FormatTok->Tok.getKind()) { case tok::at: nextToken(); @@ -825,6 +923,12 @@ void UnwrappedLineParser::parseStructuralElement() { parseBracedList(); break; case tok::kw_enum: + // Ignore if this is part of "template <enum ...". + if (Previous && Previous->is(tok::less)) { + nextToken(); + break; + } + // parseEnum falls through and does not yet add an unwrapped line as an // enum definition can start a structural element. if (!parseEnum()) @@ -922,18 +1026,35 @@ void UnwrappedLineParser::parseStructuralElement() { // Parse function literal unless 'function' is the first token in a line // in which case this should be treated as a free-standing function. if (Style.Language == FormatStyle::LK_JavaScript && - FormatTok->is(Keywords.kw_function) && Line->Tokens.size() > 0) { + (FormatTok->is(Keywords.kw_function) || + FormatTok->startsSequence(Keywords.kw_async, + Keywords.kw_function)) && + Line->Tokens.size() > 0) { tryToParseJSFunction(); break; } if ((Style.Language == FormatStyle::LK_JavaScript || Style.Language == FormatStyle::LK_Java) && FormatTok->is(Keywords.kw_interface)) { + if (Style.Language == FormatStyle::LK_JavaScript) { + // In JavaScript/TypeScript, "interface" can be used as a standalone + // identifier, e.g. in `var interface = 1;`. If "interface" is + // followed by another identifier, it is very like to be an actual + // interface declaration. + unsigned StoredPosition = Tokens->getPosition(); + FormatToken *Next = Tokens->getNextToken(); + FormatTok = Tokens->setPosition(StoredPosition); + if (Next && !mustBeJSIdent(Keywords, Next)) { + nextToken(); + break; + } + } parseRecord(); addUnwrappedLine(); return; } + // See if the following token should start a new unwrapped line. StringRef Text = FormatTok->TokenText; nextToken(); if (Line->Tokens.size() == 1 && @@ -941,6 +1062,7 @@ void UnwrappedLineParser::parseStructuralElement() { // not labels. Style.Language != FormatStyle::LK_JavaScript) { if (FormatTok->Tok.is(tok::colon) && !Line->MustBeDeclaration) { + Line->Tokens.begin()->Tok->MustBreakBefore = true; parseLabel(); return; } @@ -1093,8 +1215,17 @@ bool UnwrappedLineParser::tryToParseLambdaIntroducer() { } void UnwrappedLineParser::tryToParseJSFunction() { + assert(FormatTok->is(Keywords.kw_function) || + FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function)); + if (FormatTok->is(Keywords.kw_async)) + nextToken(); + // Consume "function". nextToken(); + // Consume * (generator function). + if (FormatTok->is(tok::star)) + nextToken(); + // Consume function name. if (FormatTok->is(tok::identifier)) nextToken(); @@ -1139,7 +1270,8 @@ bool UnwrappedLineParser::parseBracedList(bool ContinueOnSemicolons) { // replace this by using parseAssigmentExpression() inside. do { if (Style.Language == FormatStyle::LK_JavaScript) { - if (FormatTok->is(Keywords.kw_function)) { + if (FormatTok->is(Keywords.kw_function) || + FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function)) { tryToParseJSFunction(); continue; } @@ -1237,7 +1369,8 @@ void UnwrappedLineParser::parseParens() { break; case tok::identifier: if (Style.Language == FormatStyle::LK_JavaScript && - FormatTok->is(Keywords.kw_function)) + (FormatTok->is(Keywords.kw_function) || + FormatTok->startsSequence(Keywords.kw_async, Keywords.kw_function))) tryToParseJSFunction(); else nextToken(); @@ -1315,6 +1448,8 @@ void UnwrappedLineParser::parseIfThenElse() { addUnwrappedLine(); ++Line->Level; parseStructuralElement(); + if (FormatTok->is(tok::eof)) + addUnwrappedLine(); --Line->Level; } } else if (NeedsUnwrappedLine) { @@ -1503,6 +1638,10 @@ void UnwrappedLineParser::parseLabel() { addUnwrappedLine(); } Line->Level = OldLineLevel; + if (FormatTok->isNot(tok::l_brace)) { + parseStructuralElement(); + addUnwrappedLine(); + } } void UnwrappedLineParser::parseCaseLabel() { @@ -1550,7 +1689,8 @@ bool UnwrappedLineParser::parseEnum() { // In TypeScript, "enum" can also be used as property name, e.g. in interface // declarations. An "enum" keyword followed by a colon would be a syntax // error and thus assume it is just an identifier. - if (Style.Language == FormatStyle::LK_JavaScript && FormatTok->is(tok::colon)) + if (Style.Language == FormatStyle::LK_JavaScript && + FormatTok->isOneOf(tok::colon, tok::question)) return false; // Eat up enum class ... @@ -1795,28 +1935,31 @@ void UnwrappedLineParser::parseObjCProtocol() { } void UnwrappedLineParser::parseJavaScriptEs6ImportExport() { - assert(FormatTok->isOneOf(Keywords.kw_import, tok::kw_export)); + bool IsImport = FormatTok->is(Keywords.kw_import); + assert(IsImport || FormatTok->is(tok::kw_export)); nextToken(); // Consume the "default" in "export default class/function". if (FormatTok->is(tok::kw_default)) nextToken(); - // Consume "function" and "default function", so that these get parsed as - // free-standing JS functions, i.e. do not require a trailing semicolon. + // Consume "async function", "function" and "default function", so that these + // get parsed as free-standing JS functions, i.e. do not require a trailing + // semicolon. + if (FormatTok->is(Keywords.kw_async)) + nextToken(); if (FormatTok->is(Keywords.kw_function)) { nextToken(); return; } - // Consume the "abstract" in "export abstract class". - if (FormatTok->is(Keywords.kw_abstract)) - nextToken(); - - if (FormatTok->isOneOf(tok::kw_const, tok::kw_class, tok::kw_enum, - Keywords.kw_interface, Keywords.kw_let, - Keywords.kw_var)) - return; // Fall through to parsing the corresponding structure. + // For imports, `export *`, `export {...}`, consume the rest of the line up + // to the terminating `;`. For everything else, just return and continue + // parsing the structural element, i.e. the declaration or expression for + // `export default`. + if (!IsImport && !FormatTok->isOneOf(tok::l_brace, tok::star) && + !FormatTok->isStringLiteral()) + return; while (!eof() && FormatTok->isNot(tok::semi)) { if (FormatTok->is(tok::l_brace)) { @@ -1895,7 +2038,10 @@ void UnwrappedLineParser::nextToken() { return; flushComments(isOnNewLine(*FormatTok)); pushToken(FormatTok); - readToken(); + if (Style.Language != FormatStyle::LK_JavaScript) + readToken(); + else + readTokenWithJavaScriptASI(); } const FormatToken *UnwrappedLineParser::getPreviousToken() { diff --git a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.h b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.h index 6d40ab4f312..9c78d33632c 100644 --- a/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.h +++ b/gnu/llvm/tools/clang/lib/Format/UnwrappedLineParser.h @@ -81,6 +81,7 @@ private: void parsePPElse(); void parsePPEndIf(); void parsePPUnknown(); + void readTokenWithJavaScriptASI(); void parseStructuralElement(); bool tryToParseBracedList(); bool parseBracedList(bool ContinueOnSemicolons = false); diff --git a/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.cpp b/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.cpp index d6e6ed2c2ba..9cdba9df10a 100644 --- a/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.cpp +++ b/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.cpp @@ -372,16 +372,20 @@ void WhitespaceManager::alignTrailingComments() { unsigned CommentColumn = SourceMgr.getSpellingColumnNumber( Changes[i].OriginalWhitespaceRange.getEnd()); for (unsigned j = i + 1; j != e; ++j) { - if (Changes[j].Kind != tok::comment) { // Skip over comments. - unsigned NextColumn = SourceMgr.getSpellingColumnNumber( - Changes[j].OriginalWhitespaceRange.getEnd()); - // The start of the next token was previously aligned with the - // start of this comment. - WasAlignedWithStartOfNextLine = - CommentColumn == NextColumn || - CommentColumn == NextColumn + Style.IndentWidth; - break; - } + if (Changes[j].Kind == tok::comment || + Changes[j].Kind == tok::unknown) + // Skip over comments and unknown tokens. "unknown tokens are used for + // the continuation of multiline comments. + continue; + + unsigned NextColumn = SourceMgr.getSpellingColumnNumber( + Changes[j].OriginalWhitespaceRange.getEnd()); + // The start of the next token was previously aligned with the + // start of this comment. + WasAlignedWithStartOfNextLine = + CommentColumn == NextColumn || + CommentColumn == NextColumn + Style.IndentWidth; + break; } } if (!Style.AlignTrailingComments || FollowsRBraceInColumn0) { @@ -554,6 +558,14 @@ void WhitespaceManager::appendIndentText(std::string &Text, } Text.append(Spaces, ' '); break; + case FormatStyle::UT_ForContinuationAndIndentation: + if (WhitespaceStartColumn == 0) { + unsigned Tabs = Spaces / Style.TabWidth; + Text.append(Tabs, '\t'); + Spaces -= Tabs * Style.TabWidth; + } + Text.append(Spaces, ' '); + break; } } diff --git a/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.h b/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.h index 9ca9db6f748..3562347a0e6 100644 --- a/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.h +++ b/gnu/llvm/tools/clang/lib/Format/WhitespaceManager.h @@ -37,7 +37,7 @@ namespace format { /// There may be multiple calls to \c breakToken for a given token. class WhitespaceManager { public: - WhitespaceManager(SourceManager &SourceMgr, const FormatStyle &Style, + WhitespaceManager(const SourceManager &SourceMgr, const FormatStyle &Style, bool UseCRLF) : SourceMgr(SourceMgr), Style(Style), UseCRLF(UseCRLF) {} @@ -203,7 +203,7 @@ private: unsigned Spaces, unsigned WhitespaceStartColumn); SmallVector<Change, 16> Changes; - SourceManager &SourceMgr; + const SourceManager &SourceMgr; tooling::Replacements Replaces; const FormatStyle &Style; bool UseCRLF; |
