diff options
Diffstat (limited to 'clang/lib/Format/Format.cpp')
| -rw-r--r-- | clang/lib/Format/Format.cpp | 805 |
1 files changed, 24 insertions, 781 deletions
diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp index a70a7ef2a3c..9fe22d32c6f 100644 --- a/clang/lib/Format/Format.cpp +++ b/clang/lib/Format/Format.cpp @@ -16,6 +16,9 @@ #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" @@ -782,776 +785,6 @@ std::string configurationAsText(const FormatStyle &Style) { namespace { -class FormatTokenLexer { -public: - 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 *> 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; - } - - const AdditionalKeywords &getKeywords() { return Keywords; } - -private: - void 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 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))); - } - - void 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 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; - 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) { - 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 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 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) { - // 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); - } - - 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) - : 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 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; - } - -protected: - virtual tooling::Replacements - analyze(TokenAnnotator &Annotator, - SmallVectorImpl<AnnotatedLine *> &AnnotatedLines, - FormatTokenLexer &Tokens, tooling::Replacements &Result) = 0; - - void consumeUnwrappedLine(const UnwrappedLine &TheLine) override { - assert(!UnwrappedLines.empty()); - UnwrappedLines.back().push_back(TheLine); - } - - void finishRun() override { - UnwrappedLines.push_back(SmallVector<UnwrappedLine, 16>()); - } - - 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; -}; - class Formatter : public TokenAnalyzer { public: Formatter(const Environment &Env, const FormatStyle &Style, @@ -1974,7 +1207,7 @@ 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) { @@ -2029,13 +1262,11 @@ 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; - +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( @@ -2101,8 +1332,8 @@ tooling::Replacements sortIncludes(const FormatStyle &Style, StringRef Code, } 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; } @@ -2113,7 +1344,19 @@ 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 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; } |

