diff options
Diffstat (limited to 'contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp')
| -rw-r--r-- | contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp | 701 |
1 files changed, 350 insertions, 351 deletions
diff --git a/contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp b/contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp index 8df7496c6ddd..779dead5d058 100644 --- a/contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp +++ b/contrib/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp @@ -20,11 +20,11 @@ #include "llvm/Support/Path.h" #include "llvm/Support/raw_ostream.h" #include <algorithm> +#include <optional> using namespace clang; -static const enum raw_ostream::Colors noteColor = - raw_ostream::BLACK; +static const enum raw_ostream::Colors noteColor = raw_ostream::CYAN; static const enum raw_ostream::Colors remarkColor = raw_ostream::BLUE; static const enum raw_ostream::Colors fixitColor = @@ -44,7 +44,7 @@ static const enum raw_ostream::Colors savedColor = /// Add highlights to differences in template strings. static void applyTemplateHighlighting(raw_ostream &OS, StringRef Str, bool &Normal, bool Bold) { - while (1) { + while (true) { size_t Pos = Str.find(ToggleHighlight); OS << Str.slice(0, Pos); if (Pos == StringRef::npos) @@ -90,89 +90,108 @@ static int bytesSincePreviousTabOrLineBegin(StringRef SourceLine, size_t i) { /// printableTextForNextCharacter. /// /// \param SourceLine The line of source -/// \param i Pointer to byte index, +/// \param I Pointer to byte index, /// \param TabStop used to expand tabs /// \return pair(printable text, 'true' iff original text was printable) /// static std::pair<SmallString<16>, bool> -printableTextForNextCharacter(StringRef SourceLine, size_t *i, +printableTextForNextCharacter(StringRef SourceLine, size_t *I, unsigned TabStop) { - assert(i && "i must not be null"); - assert(*i<SourceLine.size() && "must point to a valid index"); + assert(I && "I must not be null"); + assert(*I < SourceLine.size() && "must point to a valid index"); - if (SourceLine[*i]=='\t') { + if (SourceLine[*I] == '\t') { assert(0 < TabStop && TabStop <= DiagnosticOptions::MaxTabStop && "Invalid -ftabstop value"); - unsigned col = bytesSincePreviousTabOrLineBegin(SourceLine, *i); - unsigned NumSpaces = TabStop - col%TabStop; + unsigned Col = bytesSincePreviousTabOrLineBegin(SourceLine, *I); + unsigned NumSpaces = TabStop - (Col % TabStop); assert(0 < NumSpaces && NumSpaces <= TabStop && "Invalid computation of space amt"); - ++(*i); + ++(*I); - SmallString<16> expandedTab; - expandedTab.assign(NumSpaces, ' '); - return std::make_pair(expandedTab, true); + SmallString<16> ExpandedTab; + ExpandedTab.assign(NumSpaces, ' '); + return std::make_pair(ExpandedTab, true); } - unsigned char const *begin, *end; - begin = reinterpret_cast<unsigned char const *>(&*(SourceLine.begin() + *i)); - end = begin + (SourceLine.size() - *i); - - if (llvm::isLegalUTF8Sequence(begin, end)) { - llvm::UTF32 c; - llvm::UTF32 *cptr = &c; - unsigned char const *original_begin = begin; - unsigned char const *cp_end = - begin + llvm::getNumBytesForUTF8(SourceLine[*i]); - - llvm::ConversionResult res = llvm::ConvertUTF8toUTF32( - &begin, cp_end, &cptr, cptr + 1, llvm::strictConversion); - (void)res; - assert(llvm::conversionOK == res); - assert(0 < begin-original_begin - && "we must be further along in the string now"); - *i += begin-original_begin; - - if (!llvm::sys::locale::isPrint(c)) { - // If next character is valid UTF-8, but not printable - SmallString<16> expandedCP("<U+>"); - while (c) { - expandedCP.insert(expandedCP.begin()+3, llvm::hexdigit(c%16)); - c/=16; - } - while (expandedCP.size() < 8) - expandedCP.insert(expandedCP.begin()+3, llvm::hexdigit(0)); - return std::make_pair(expandedCP, false); - } - - // If next character is valid UTF-8, and printable - return std::make_pair(SmallString<16>(original_begin, cp_end), true); + const unsigned char *Begin = SourceLine.bytes_begin() + *I; + // Fast path for the common ASCII case. + if (*Begin < 0x80 && llvm::sys::locale::isPrint(*Begin)) { + ++(*I); + return std::make_pair(SmallString<16>(Begin, Begin + 1), true); + } + unsigned CharSize = llvm::getNumBytesForUTF8(*Begin); + const unsigned char *End = Begin + CharSize; + + // Convert it to UTF32 and check if it's printable. + if (End <= SourceLine.bytes_end() && llvm::isLegalUTF8Sequence(Begin, End)) { + llvm::UTF32 C; + llvm::UTF32 *CPtr = &C; + + // Begin and end before conversion. + unsigned char const *OriginalBegin = Begin; + llvm::ConversionResult Res = llvm::ConvertUTF8toUTF32( + &Begin, End, &CPtr, CPtr + 1, llvm::strictConversion); + (void)Res; + assert(Res == llvm::conversionOK); + assert(OriginalBegin < Begin); + assert((Begin - OriginalBegin) == CharSize); + + (*I) += (Begin - OriginalBegin); + + // Valid, multi-byte, printable UTF8 character. + if (llvm::sys::locale::isPrint(C)) + return std::make_pair(SmallString<16>(OriginalBegin, End), true); + + // Valid but not printable. + SmallString<16> Str("<U+>"); + while (C) { + Str.insert(Str.begin() + 3, llvm::hexdigit(C % 16)); + C /= 16; + } + while (Str.size() < 8) + Str.insert(Str.begin() + 3, llvm::hexdigit(0)); + return std::make_pair(Str, false); } - // If next byte is not valid UTF-8 (and therefore not printable) - SmallString<16> expandedByte("<XX>"); - unsigned char byte = SourceLine[*i]; - expandedByte[1] = llvm::hexdigit(byte / 16); - expandedByte[2] = llvm::hexdigit(byte % 16); - ++(*i); - return std::make_pair(expandedByte, false); + // Otherwise, not printable since it's not valid UTF8. + SmallString<16> ExpandedByte("<XX>"); + unsigned char Byte = SourceLine[*I]; + ExpandedByte[1] = llvm::hexdigit(Byte / 16); + ExpandedByte[2] = llvm::hexdigit(Byte % 16); + ++(*I); + return std::make_pair(ExpandedByte, false); } static void expandTabs(std::string &SourceLine, unsigned TabStop) { - size_t i = SourceLine.size(); - while (i>0) { - i--; - if (SourceLine[i]!='\t') + size_t I = SourceLine.size(); + while (I > 0) { + I--; + if (SourceLine[I] != '\t') continue; - size_t tmp_i = i; - std::pair<SmallString<16>,bool> res - = printableTextForNextCharacter(SourceLine, &tmp_i, TabStop); - SourceLine.replace(i, 1, res.first.c_str()); + size_t TmpI = I; + auto [Str, Printable] = + printableTextForNextCharacter(SourceLine, &TmpI, TabStop); + SourceLine.replace(I, 1, Str.c_str()); } } -/// This function takes a raw source line and produces a mapping from the bytes +/// \p BytesOut: +/// A mapping from columns to the byte of the source line that produced the +/// character displaying at that column. This is the inverse of \p ColumnsOut. +/// +/// The last element in the array is the number of bytes in the source string. +/// +/// example: (given a tabstop of 8) +/// +/// "a \t \u3042" -> {0,1,2,-1,-1,-1,-1,-1,3,4,-1,7} +/// +/// (\\u3042 is represented in UTF-8 by three bytes and takes two columns to +/// display) +/// +/// \p ColumnsOut: +/// A mapping from the bytes /// of the printable representation of the line to the columns those printable /// characters will appear at (numbering the first column as 0). /// @@ -194,60 +213,34 @@ static void expandTabs(std::string &SourceLine, unsigned TabStop) { /// /// (\\u3042 is represented in UTF-8 by three bytes and takes two columns to /// display) -static void byteToColumn(StringRef SourceLine, unsigned TabStop, - SmallVectorImpl<int> &out) { - out.clear(); +static void genColumnByteMapping(StringRef SourceLine, unsigned TabStop, + SmallVectorImpl<int> &BytesOut, + SmallVectorImpl<int> &ColumnsOut) { + assert(BytesOut.empty()); + assert(ColumnsOut.empty()); if (SourceLine.empty()) { - out.resize(1u,0); + BytesOut.resize(1u, 0); + ColumnsOut.resize(1u, 0); return; } - out.resize(SourceLine.size()+1, -1); - - int columns = 0; - size_t i = 0; - while (i<SourceLine.size()) { - out[i] = columns; - std::pair<SmallString<16>,bool> res - = printableTextForNextCharacter(SourceLine, &i, TabStop); - columns += llvm::sys::locale::columnWidth(res.first); - } - out.back() = columns; -} - -/// This function takes a raw source line and produces a mapping from columns -/// to the byte of the source line that produced the character displaying at -/// that column. This is the inverse of the mapping produced by byteToColumn() -/// -/// The last element in the array is the number of bytes in the source string -/// -/// example: (given a tabstop of 8) -/// -/// "a \t \u3042" -> {0,1,2,-1,-1,-1,-1,-1,3,4,-1,7} -/// -/// (\\u3042 is represented in UTF-8 by three bytes and takes two columns to -/// display) -static void columnToByte(StringRef SourceLine, unsigned TabStop, - SmallVectorImpl<int> &out) { - out.clear(); - - if (SourceLine.empty()) { - out.resize(1u, 0); - return; + ColumnsOut.resize(SourceLine.size() + 1, -1); + + int Columns = 0; + size_t I = 0; + while (I < SourceLine.size()) { + ColumnsOut[I] = Columns; + BytesOut.resize(Columns + 1, -1); + BytesOut.back() = I; + auto [Str, Printable] = + printableTextForNextCharacter(SourceLine, &I, TabStop); + Columns += llvm::sys::locale::columnWidth(Str); } - int columns = 0; - size_t i = 0; - while (i<SourceLine.size()) { - out.resize(columns+1, -1); - out.back() = i; - std::pair<SmallString<16>,bool> res - = printableTextForNextCharacter(SourceLine, &i, TabStop); - columns += llvm::sys::locale::columnWidth(res.first); - } - out.resize(columns+1, -1); - out.back() = i; + ColumnsOut.back() = Columns; + BytesOut.resize(Columns + 1, -1); + BytesOut.back() = I; } namespace { @@ -255,8 +248,7 @@ struct SourceColumnMap { SourceColumnMap(StringRef SourceLine, unsigned TabStop) : m_SourceLine(SourceLine) { - ::byteToColumn(SourceLine, TabStop, m_byteToColumn); - ::columnToByte(SourceLine, TabStop, m_columnToByte); + genColumnByteMapping(SourceLine, TabStop, m_columnToByte, m_byteToColumn); assert(m_byteToColumn.size()==SourceLine.size()+1); assert(0 < m_byteToColumn.size() && 0 < m_columnToByte.size()); @@ -332,8 +324,7 @@ static void selectInterestingSourceRegion(std::string &SourceLine, return; // No special characters are allowed in CaretLine. - assert(CaretLine.end() == - llvm::find_if(CaretLine, [](char c) { return c < ' ' || '~' < c; })); + assert(llvm::none_of(CaretLine, [](char c) { return c < ' ' || '~' < c; })); // Find the slice that we need to display the full caret line // correctly. @@ -471,9 +462,7 @@ static void selectInterestingSourceRegion(std::string &SourceLine, CaretEnd = map.byteToColumn(SourceEnd) + CaretColumnsOutsideSource; // [CaretStart, CaretEnd) is the slice we want. Update the various - // output lines to show only this slice, with two-space padding - // before the lines so that it looks nicer. - + // output lines to show only this slice. assert(CaretStart!=(unsigned)-1 && CaretEnd!=(unsigned)-1 && SourceStart!=(unsigned)-1 && SourceEnd!=(unsigned)-1); assert(SourceStart <= SourceEnd); @@ -605,21 +594,13 @@ static unsigned findEndOfWord(unsigned Start, StringRef Str, /// Str will be printed. This will be non-zero when part of the first /// line has already been printed. /// \param Bold if the current text should be bold -/// \param Indentation the number of spaces to indent any lines beyond -/// the first line. /// \returns true if word-wrapping was required, or false if the /// string fit on the first line. -static bool printWordWrapped(raw_ostream &OS, StringRef Str, - unsigned Columns, - unsigned Column = 0, - bool Bold = false, - unsigned Indentation = WordWrapIndentation) { +static bool printWordWrapped(raw_ostream &OS, StringRef Str, unsigned Columns, + unsigned Column, bool Bold) { const unsigned Length = std::min(Str.find('\n'), Str.size()); bool TextNormal = true; - // The string used to indent each line. - SmallString<16> IndentStr; - IndentStr.assign(Indentation, ' '); bool Wrapped = false; for (unsigned WordStart = 0, WordEnd; WordStart < Length; WordStart = WordEnd) { @@ -648,10 +629,10 @@ static bool printWordWrapped(raw_ostream &OS, StringRef Str, // This word does not fit on the current line, so wrap to the next // line. OS << '\n'; - OS.write(&IndentStr[0], Indentation); + OS.indent(WordWrapIndentation); applyTemplateHighlighting(OS, Str.substr(WordStart, WordLength), TextNormal, Bold); - Column = Indentation + WordLength; + Column = WordWrapIndentation + WordLength; Wrapped = true; } @@ -754,7 +735,7 @@ void TextDiagnostic::emitFilename(StringRef Filename, const SourceManager &SM) { SmallString<4096> TmpFilename; #endif if (DiagOpts->AbsolutePath) { - auto File = SM.getFileManager().getFile(Filename); + auto File = SM.getFileManager().getOptionalFileRef(Filename); if (File) { // We want to print a simplified absolute path, i. e. without "dots". // @@ -771,7 +752,7 @@ void TextDiagnostic::emitFilename(StringRef Filename, const SourceManager &SM) { // on Windows we can just use llvm::sys::path::remove_dots(), because, // on that system, both aforementioned paths point to the same place. #ifdef _WIN32 - TmpFilename = (*File)->getName(); + TmpFilename = File->getName(); llvm::sys::fs::make_absolute(TmpFilename); llvm::sys::path::native(TmpFilename); llvm::sys::path::remove_dots(TmpFilename, /* remove_dot_dot */ true); @@ -787,7 +768,7 @@ void TextDiagnostic::emitFilename(StringRef Filename, const SourceManager &SM) { /// Print out the file/line/column information and include trace. /// -/// This method handlen the emission of the diagnostic location information. +/// This method handles the emission of the diagnostic location information. /// This includes extracting as much location information as is present for /// the diagnostic and printing it, as well as any include stack or source /// ranges necessary. @@ -796,10 +777,8 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, ArrayRef<CharSourceRange> Ranges) { if (PLoc.isInvalid()) { // At least print the file name if available: - FileID FID = Loc.getFileID(); - if (FID.isValid()) { - const FileEntry *FE = Loc.getFileEntry(); - if (FE && FE->isValid()) { + if (FileID FID = Loc.getFileID(); FID.isValid()) { + if (OptionalFileEntryRef FE = Loc.getFileEntryRef()) { emitFilename(FE->getName(), Loc.getManager()); OS << ": "; } @@ -816,6 +795,7 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, emitFilename(PLoc.getFilename(), Loc.getManager()); switch (DiagOpts->getFormat()) { + case DiagnosticOptions::SARIF: case DiagnosticOptions::Clang: if (DiagOpts->ShowLine) OS << ':' << LineNo; @@ -838,6 +818,7 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, OS << ColNo; } switch (DiagOpts->getFormat()) { + case DiagnosticOptions::SARIF: case DiagnosticOptions::Clang: case DiagnosticOptions::Vi: OS << ':'; break; case DiagnosticOptions::MSVC: @@ -854,31 +835,26 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, if (DiagOpts->ShowSourceRanges && !Ranges.empty()) { FileID CaretFileID = Loc.getExpansionLoc().getFileID(); bool PrintedRange = false; + const SourceManager &SM = Loc.getManager(); - for (ArrayRef<CharSourceRange>::const_iterator RI = Ranges.begin(), - RE = Ranges.end(); - RI != RE; ++RI) { + for (const auto &R : Ranges) { // Ignore invalid ranges. - if (!RI->isValid()) continue; + if (!R.isValid()) + continue; - auto &SM = Loc.getManager(); - SourceLocation B = SM.getExpansionLoc(RI->getBegin()); - CharSourceRange ERange = SM.getExpansionRange(RI->getEnd()); + SourceLocation B = SM.getExpansionLoc(R.getBegin()); + CharSourceRange ERange = SM.getExpansionRange(R.getEnd()); SourceLocation E = ERange.getEnd(); - bool IsTokenRange = ERange.isTokenRange(); - std::pair<FileID, unsigned> BInfo = SM.getDecomposedLoc(B); - std::pair<FileID, unsigned> EInfo = SM.getDecomposedLoc(E); - - // If the start or end of the range is in another file, just discard - // it. - if (BInfo.first != CaretFileID || EInfo.first != CaretFileID) + // If the start or end of the range is in another file, just + // discard it. + if (SM.getFileID(B) != CaretFileID || SM.getFileID(E) != CaretFileID) continue; // Add in the length of the token, so that we cover multi-char // tokens. unsigned TokSize = 0; - if (IsTokenRange) + if (ERange.isTokenRange()) TokSize = Lexer::MeasureTokenLength(E, SM, LangOpts); FullSourceLoc BF(B, SM), EF(E, SM); @@ -896,10 +872,11 @@ void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc, } void TextDiagnostic::emitIncludeLocation(FullSourceLoc Loc, PresumedLoc PLoc) { - if (DiagOpts->ShowLocation && PLoc.isValid()) - OS << "In file included from " << PLoc.getFilename() << ':' - << PLoc.getLine() << ":\n"; - else + if (DiagOpts->ShowLocation && PLoc.isValid()) { + OS << "In file included from "; + emitFilename(PLoc.getFilename(), Loc.getManager()); + OS << ':' << PLoc.getLine() << ":\n"; + } else OS << "In included file:\n"; } @@ -923,15 +900,16 @@ void TextDiagnostic::emitBuildingModuleLocation(FullSourceLoc Loc, } /// Find the suitable set of lines to show to include a set of ranges. -static llvm::Optional<std::pair<unsigned, unsigned>> +static std::optional<std::pair<unsigned, unsigned>> findLinesForRange(const CharSourceRange &R, FileID FID, const SourceManager &SM) { - if (!R.isValid()) return None; + if (!R.isValid()) + return std::nullopt; SourceLocation Begin = R.getBegin(); SourceLocation End = R.getEnd(); if (SM.getFileID(Begin) != FID || SM.getFileID(End) != FID) - return None; + return std::nullopt; return std::make_pair(SM.getExpansionLineNumber(Begin), SM.getExpansionLineNumber(End)); @@ -972,87 +950,43 @@ maybeAddRange(std::pair<unsigned, unsigned> A, std::pair<unsigned, unsigned> B, return A; } -/// Highlight a SourceRange (with ~'s) for any characters on LineNo. -static void highlightRange(const CharSourceRange &R, - unsigned LineNo, FileID FID, - const SourceColumnMap &map, - std::string &CaretLine, - const SourceManager &SM, - const LangOptions &LangOpts) { - if (!R.isValid()) return; - - SourceLocation Begin = R.getBegin(); - SourceLocation End = R.getEnd(); - - unsigned StartLineNo = SM.getExpansionLineNumber(Begin); - if (StartLineNo > LineNo || SM.getFileID(Begin) != FID) - return; // No intersection. - - unsigned EndLineNo = SM.getExpansionLineNumber(End); - if (EndLineNo < LineNo || SM.getFileID(End) != FID) - return; // No intersection. - - // Compute the column number of the start. - unsigned StartColNo = 0; - if (StartLineNo == LineNo) { - StartColNo = SM.getExpansionColumnNumber(Begin); - if (StartColNo) --StartColNo; // Zero base the col #. - } - - // Compute the column number of the end. - unsigned EndColNo = map.getSourceLine().size(); - if (EndLineNo == LineNo) { - EndColNo = SM.getExpansionColumnNumber(End); - if (EndColNo) { - --EndColNo; // Zero base the col #. - - // Add in the length of the token, so that we cover multi-char tokens if - // this is a token range. - if (R.isTokenRange()) - EndColNo += Lexer::MeasureTokenLength(End, SM, LangOpts); - } else { - EndColNo = CaretLine.size(); - } - } - - assert(StartColNo <= EndColNo && "Invalid range!"); - - // Check that a token range does not highlight only whitespace. - if (R.isTokenRange()) { - // Pick the first non-whitespace column. - while (StartColNo < map.getSourceLine().size() && - (map.getSourceLine()[StartColNo] == ' ' || - map.getSourceLine()[StartColNo] == '\t')) - StartColNo = map.startOfNextColumn(StartColNo); - - // Pick the last non-whitespace column. - if (EndColNo > map.getSourceLine().size()) - EndColNo = map.getSourceLine().size(); - while (EndColNo && - (map.getSourceLine()[EndColNo-1] == ' ' || - map.getSourceLine()[EndColNo-1] == '\t')) - EndColNo = map.startOfPreviousColumn(EndColNo); - - // If the start/end passed each other, then we are trying to highlight a - // range that just exists in whitespace. That most likely means we have - // a multi-line highlighting range that covers a blank line. - if (StartColNo > EndColNo) { - assert(StartLineNo != EndLineNo && "trying to highlight whitespace"); - StartColNo = EndColNo; - } - } +struct LineRange { + unsigned LineNo; + unsigned StartCol; + unsigned EndCol; +}; - assert(StartColNo <= map.getSourceLine().size() && "Invalid range!"); - assert(EndColNo <= map.getSourceLine().size() && "Invalid range!"); +/// Highlight \p R (with ~'s) on the current source line. +static void highlightRange(const LineRange &R, const SourceColumnMap &Map, + std::string &CaretLine) { + // Pick the first non-whitespace column. + unsigned StartColNo = R.StartCol; + while (StartColNo < Map.getSourceLine().size() && + (Map.getSourceLine()[StartColNo] == ' ' || + Map.getSourceLine()[StartColNo] == '\t')) + StartColNo = Map.startOfNextColumn(StartColNo); + + // Pick the last non-whitespace column. + unsigned EndColNo = + std::min(static_cast<size_t>(R.EndCol), Map.getSourceLine().size()); + while (EndColNo && (Map.getSourceLine()[EndColNo - 1] == ' ' || + Map.getSourceLine()[EndColNo - 1] == '\t')) + EndColNo = Map.startOfPreviousColumn(EndColNo); + + // If the start/end passed each other, then we are trying to highlight a + // range that just exists in whitespace. That most likely means we have + // a multi-line highlighting range that covers a blank line. + if (StartColNo > EndColNo) + return; // Fill the range with ~'s. - StartColNo = map.byteToContainingColumn(StartColNo); - EndColNo = map.byteToContainingColumn(EndColNo); + StartColNo = Map.byteToContainingColumn(StartColNo); + EndColNo = Map.byteToContainingColumn(EndColNo); assert(StartColNo <= EndColNo && "Invalid range!"); if (CaretLine.size() < EndColNo) - CaretLine.resize(EndColNo,' '); - std::fill(CaretLine.begin()+StartColNo,CaretLine.begin()+EndColNo,'~'); + CaretLine.resize(EndColNo, ' '); + std::fill(CaretLine.begin() + StartColNo, CaretLine.begin() + EndColNo, '~'); } static std::string buildFixItInsertionLine(FileID FID, @@ -1066,51 +1000,51 @@ static std::string buildFixItInsertionLine(FileID FID, return FixItInsertionLine; unsigned PrevHintEndCol = 0; - for (ArrayRef<FixItHint>::iterator I = Hints.begin(), E = Hints.end(); - I != E; ++I) { - if (!I->CodeToInsert.empty()) { - // We have an insertion hint. Determine whether the inserted - // code contains no newlines and is on the same line as the caret. - std::pair<FileID, unsigned> HintLocInfo - = SM.getDecomposedExpansionLoc(I->RemoveRange.getBegin()); - if (FID == HintLocInfo.first && - LineNo == SM.getLineNumber(HintLocInfo.first, HintLocInfo.second) && - StringRef(I->CodeToInsert).find_first_of("\n\r") == StringRef::npos) { - // Insert the new code into the line just below the code - // that the user wrote. - // Note: When modifying this function, be very careful about what is a - // "column" (printed width, platform-dependent) and what is a - // "byte offset" (SourceManager "column"). - unsigned HintByteOffset - = SM.getColumnNumber(HintLocInfo.first, HintLocInfo.second) - 1; - - // The hint must start inside the source or right at the end - assert(HintByteOffset < static_cast<unsigned>(map.bytes())+1); - unsigned HintCol = map.byteToContainingColumn(HintByteOffset); - - // If we inserted a long previous hint, push this one forwards, and add - // an extra space to show that this is not part of the previous - // completion. This is sort of the best we can do when two hints appear - // to overlap. - // - // Note that if this hint is located immediately after the previous - // hint, no space will be added, since the location is more important. - if (HintCol < PrevHintEndCol) - HintCol = PrevHintEndCol + 1; - - // This should NOT use HintByteOffset, because the source might have - // Unicode characters in earlier columns. - unsigned NewFixItLineSize = FixItInsertionLine.size() + - (HintCol - PrevHintEndCol) + I->CodeToInsert.size(); - if (NewFixItLineSize > FixItInsertionLine.size()) - FixItInsertionLine.resize(NewFixItLineSize, ' '); - - std::copy(I->CodeToInsert.begin(), I->CodeToInsert.end(), - FixItInsertionLine.end() - I->CodeToInsert.size()); - - PrevHintEndCol = - HintCol + llvm::sys::locale::columnWidth(I->CodeToInsert); - } + for (const auto &H : Hints) { + if (H.CodeToInsert.empty()) + continue; + + // We have an insertion hint. Determine whether the inserted + // code contains no newlines and is on the same line as the caret. + std::pair<FileID, unsigned> HintLocInfo = + SM.getDecomposedExpansionLoc(H.RemoveRange.getBegin()); + if (FID == HintLocInfo.first && + LineNo == SM.getLineNumber(HintLocInfo.first, HintLocInfo.second) && + StringRef(H.CodeToInsert).find_first_of("\n\r") == StringRef::npos) { + // Insert the new code into the line just below the code + // that the user wrote. + // Note: When modifying this function, be very careful about what is a + // "column" (printed width, platform-dependent) and what is a + // "byte offset" (SourceManager "column"). + unsigned HintByteOffset = + SM.getColumnNumber(HintLocInfo.first, HintLocInfo.second) - 1; + + // The hint must start inside the source or right at the end + assert(HintByteOffset < static_cast<unsigned>(map.bytes()) + 1); + unsigned HintCol = map.byteToContainingColumn(HintByteOffset); + + // If we inserted a long previous hint, push this one forwards, and add + // an extra space to show that this is not part of the previous + // completion. This is sort of the best we can do when two hints appear + // to overlap. + // + // Note that if this hint is located immediately after the previous + // hint, no space will be added, since the location is more important. + if (HintCol < PrevHintEndCol) + HintCol = PrevHintEndCol + 1; + + // This should NOT use HintByteOffset, because the source might have + // Unicode characters in earlier columns. + unsigned NewFixItLineSize = FixItInsertionLine.size() + + (HintCol - PrevHintEndCol) + + H.CodeToInsert.size(); + if (NewFixItLineSize > FixItInsertionLine.size()) + FixItInsertionLine.resize(NewFixItLineSize, ' '); + + std::copy(H.CodeToInsert.begin(), H.CodeToInsert.end(), + FixItInsertionLine.end() - H.CodeToInsert.size()); + + PrevHintEndCol = HintCol + llvm::sys::locale::columnWidth(H.CodeToInsert); } } @@ -1119,6 +1053,65 @@ static std::string buildFixItInsertionLine(FileID FID, return FixItInsertionLine; } +static unsigned getNumDisplayWidth(unsigned N) { + unsigned L = 1u, M = 10u; + while (M <= N && ++L != std::numeric_limits<unsigned>::digits10 + 1) + M *= 10u; + + return L; +} + +/// Filter out invalid ranges, ranges that don't fit into the window of +/// source lines we will print, and ranges from other files. +/// +/// For the remaining ranges, convert them to simple LineRange structs, +/// which only cover one line at a time. +static SmallVector<LineRange> +prepareAndFilterRanges(const SmallVectorImpl<CharSourceRange> &Ranges, + const SourceManager &SM, + const std::pair<unsigned, unsigned> &Lines, FileID FID, + const LangOptions &LangOpts) { + SmallVector<LineRange> LineRanges; + + for (const CharSourceRange &R : Ranges) { + if (R.isInvalid()) + continue; + SourceLocation Begin = R.getBegin(); + SourceLocation End = R.getEnd(); + + unsigned StartLineNo = SM.getExpansionLineNumber(Begin); + if (StartLineNo > Lines.second || SM.getFileID(Begin) != FID) + continue; + + unsigned EndLineNo = SM.getExpansionLineNumber(End); + if (EndLineNo < Lines.first || SM.getFileID(End) != FID) + continue; + + unsigned StartColumn = SM.getExpansionColumnNumber(Begin); + unsigned EndColumn = SM.getExpansionColumnNumber(End); + if (R.isTokenRange()) + EndColumn += Lexer::MeasureTokenLength(End, SM, LangOpts); + + // Only a single line. + if (StartLineNo == EndLineNo) { + LineRanges.push_back({StartLineNo, StartColumn - 1, EndColumn - 1}); + continue; + } + + // Start line. + LineRanges.push_back({StartLineNo, StartColumn - 1, ~0u}); + + // Middle lines. + for (unsigned S = StartLineNo + 1; S != EndLineNo; ++S) + LineRanges.push_back({S, 0, ~0u}); + + // End line. + LineRanges.push_back({EndLineNo, 0, EndColumn - 1}); + } + + return LineRanges; +} + /// Emit a code snippet and caret line. /// /// This routine emits a single line's code snippet and caret line.. @@ -1144,9 +1137,7 @@ void TextDiagnostic::emitSnippetAndCaret( (LastLevel != DiagnosticsEngine::Note || Level == LastLevel)) return; - // Decompose the location into a FID/Offset pair. - std::pair<FileID, unsigned> LocInfo = Loc.getDecomposedLoc(); - FileID FID = LocInfo.first; + FileID FID = Loc.getFileID(); const SourceManager &SM = Loc.getManager(); // Get information about the buffer it points into. @@ -1154,6 +1145,8 @@ void TextDiagnostic::emitSnippetAndCaret( StringRef BufData = Loc.getBufferData(&Invalid); if (Invalid) return; + const char *BufStart = BufData.data(); + const char *BufEnd = BufStart + BufData.size(); unsigned CaretLineNo = Loc.getLineNumber(); unsigned CaretColNo = Loc.getColumnNumber(); @@ -1166,16 +1159,33 @@ void TextDiagnostic::emitSnippetAndCaret( // Find the set of lines to include. const unsigned MaxLines = DiagOpts->SnippetLineLimit; std::pair<unsigned, unsigned> Lines = {CaretLineNo, CaretLineNo}; - for (SmallVectorImpl<CharSourceRange>::iterator I = Ranges.begin(), - E = Ranges.end(); - I != E; ++I) - if (auto OptionalRange = findLinesForRange(*I, FID, SM)) + unsigned DisplayLineNo = Loc.getPresumedLoc().getLine(); + for (const auto &I : Ranges) { + if (auto OptionalRange = findLinesForRange(I, FID, SM)) Lines = maybeAddRange(Lines, *OptionalRange, MaxLines); - for (unsigned LineNo = Lines.first; LineNo != Lines.second + 1; ++LineNo) { - const char *BufStart = BufData.data(); - const char *BufEnd = BufStart + BufData.size(); + DisplayLineNo = + std::min(DisplayLineNo, SM.getPresumedLineNumber(I.getBegin())); + } + // Our line numbers look like: + // " [number] | " + // Where [number] is MaxLineNoDisplayWidth columns + // and the full thing is therefore MaxLineNoDisplayWidth + 4 columns. + unsigned MaxLineNoDisplayWidth = + DiagOpts->ShowLineNumbers + ? std::max(4u, getNumDisplayWidth(DisplayLineNo + MaxLines)) + : 0; + auto indentForLineNumbers = [&] { + if (MaxLineNoDisplayWidth > 0) + OS.indent(MaxLineNoDisplayWidth + 2) << "| "; + }; + + SmallVector<LineRange> LineRanges = + prepareAndFilterRanges(Ranges, SM, Lines, FID, LangOpts); + + for (unsigned LineNo = Lines.first; LineNo != Lines.second + 1; + ++LineNo, ++DisplayLineNo) { // Rewind from the current position to the start of the line. const char *LineStart = BufStart + @@ -1193,34 +1203,28 @@ void TextDiagnostic::emitSnippetAndCaret( if (size_t(LineEnd - LineStart) > MaxLineLengthToPrint) return; - // Trim trailing null-bytes. - StringRef Line(LineStart, LineEnd - LineStart); - while (!Line.empty() && Line.back() == '\0' && - (LineNo != CaretLineNo || Line.size() > CaretColNo)) - Line = Line.drop_back(); - // Copy the line of code into an std::string for ease of manipulation. - std::string SourceLine(Line.begin(), Line.end()); + std::string SourceLine(LineStart, LineEnd); + // Remove trailing null bytes. + while (!SourceLine.empty() && SourceLine.back() == '\0' && + (LineNo != CaretLineNo || SourceLine.size() > CaretColNo)) + SourceLine.pop_back(); // Build the byte to column map. const SourceColumnMap sourceColMap(SourceLine, DiagOpts->TabStop); - // Create a line for the caret that is filled with spaces that is the same - // number of columns as the line of source code. - std::string CaretLine(sourceColMap.columns(), ' '); - + std::string CaretLine; // Highlight all of the characters covered by Ranges with ~ characters. - for (SmallVectorImpl<CharSourceRange>::iterator I = Ranges.begin(), - E = Ranges.end(); - I != E; ++I) - highlightRange(*I, LineNo, FID, sourceColMap, CaretLine, SM, LangOpts); + for (const auto &LR : LineRanges) { + if (LR.LineNo == LineNo) + highlightRange(LR, sourceColMap, CaretLine); + } // Next, insert the caret itself. if (CaretLineNo == LineNo) { - CaretColNo = sourceColMap.byteToContainingColumn(CaretColNo - 1); - if (CaretLine.size() < CaretColNo + 1) - CaretLine.resize(CaretColNo + 1, ' '); - CaretLine[CaretColNo] = '^'; + size_t Col = sourceColMap.byteToContainingColumn(CaretColNo - 1); + CaretLine.resize(std::max(Col + 1, CaretLine.size()), ' '); + CaretLine[Col] = '^'; } std::string FixItInsertionLine = buildFixItInsertionLine( @@ -1237,19 +1241,16 @@ void TextDiagnostic::emitSnippetAndCaret( // to produce easily machine parsable output. Add a space before the // source line and the caret to make it trivial to tell the main diagnostic // line from what the user is intended to see. - if (DiagOpts->ShowSourceRanges) { + if (DiagOpts->ShowSourceRanges && !SourceLine.empty()) { SourceLine = ' ' + SourceLine; CaretLine = ' ' + CaretLine; } - // Finally, remove any blank spaces from the end of CaretLine. - while (!CaretLine.empty() && CaretLine[CaretLine.size() - 1] == ' ') - CaretLine.erase(CaretLine.end() - 1); - // Emit what we have computed. - emitSnippet(SourceLine); + emitSnippet(SourceLine, MaxLineNoDisplayWidth, DisplayLineNo); if (!CaretLine.empty()) { + indentForLineNumbers(); if (DiagOpts->ShowColors) OS.changeColor(caretColor, true); OS << CaretLine << '\n'; @@ -1258,6 +1259,7 @@ void TextDiagnostic::emitSnippetAndCaret( } if (!FixItInsertionLine.empty()) { + indentForLineNumbers(); if (DiagOpts->ShowColors) // Print fixit line in color OS.changeColor(fixitColor, false); @@ -1273,37 +1275,37 @@ void TextDiagnostic::emitSnippetAndCaret( emitParseableFixits(Hints, SM); } -void TextDiagnostic::emitSnippet(StringRef line) { - if (line.empty()) - return; - - size_t i = 0; - - std::string to_print; - bool print_reversed = false; - - while (i<line.size()) { - std::pair<SmallString<16>,bool> res - = printableTextForNextCharacter(line, &i, DiagOpts->TabStop); - bool was_printable = res.second; +void TextDiagnostic::emitSnippet(StringRef SourceLine, + unsigned MaxLineNoDisplayWidth, + unsigned LineNo) { + // Emit line number. + if (MaxLineNoDisplayWidth > 0) { + unsigned LineNoDisplayWidth = getNumDisplayWidth(LineNo); + OS.indent(MaxLineNoDisplayWidth - LineNoDisplayWidth + 1) + << LineNo << " | "; + } - if (DiagOpts->ShowColors && was_printable == print_reversed) { - if (print_reversed) - OS.reverseColor(); - OS << to_print; - to_print.clear(); - if (DiagOpts->ShowColors) - OS.resetColor(); + // Print the source line one character at a time. + bool PrintReversed = false; + size_t I = 0; + while (I < SourceLine.size()) { + auto [Str, WasPrintable] = + printableTextForNextCharacter(SourceLine, &I, DiagOpts->TabStop); + + // Toggle inverted colors on or off for this character. + if (DiagOpts->ShowColors) { + if (WasPrintable == PrintReversed) { + PrintReversed = !PrintReversed; + if (PrintReversed) + OS.reverseColor(); + else + OS.resetColor(); + } } - - print_reversed = !was_printable; - to_print += res.first.str(); + OS << Str; } - if (print_reversed && DiagOpts->ShowColors) - OS.reverseColor(); - OS << to_print; - if (print_reversed && DiagOpts->ShowColors) + if (DiagOpts->ShowColors) OS.resetColor(); OS << '\n'; @@ -1316,24 +1318,21 @@ void TextDiagnostic::emitParseableFixits(ArrayRef<FixItHint> Hints, // We follow FixItRewriter's example in not (yet) handling // fix-its in macros. - for (ArrayRef<FixItHint>::iterator I = Hints.begin(), E = Hints.end(); - I != E; ++I) { - if (I->RemoveRange.isInvalid() || - I->RemoveRange.getBegin().isMacroID() || - I->RemoveRange.getEnd().isMacroID()) + for (const auto &H : Hints) { + if (H.RemoveRange.isInvalid() || H.RemoveRange.getBegin().isMacroID() || + H.RemoveRange.getEnd().isMacroID()) return; } - for (ArrayRef<FixItHint>::iterator I = Hints.begin(), E = Hints.end(); - I != E; ++I) { - SourceLocation BLoc = I->RemoveRange.getBegin(); - SourceLocation ELoc = I->RemoveRange.getEnd(); + for (const auto &H : Hints) { + SourceLocation BLoc = H.RemoveRange.getBegin(); + SourceLocation ELoc = H.RemoveRange.getEnd(); std::pair<FileID, unsigned> BInfo = SM.getDecomposedLoc(BLoc); std::pair<FileID, unsigned> EInfo = SM.getDecomposedLoc(ELoc); // Adjust for token ranges. - if (I->RemoveRange.isTokenRange()) + if (H.RemoveRange.isTokenRange()) EInfo.second += Lexer::MeasureTokenLength(ELoc, SM, LangOpts); // We specifically do not do word-wrapping or tab-expansion here, @@ -1349,7 +1348,7 @@ void TextDiagnostic::emitParseableFixits(ArrayRef<FixItHint> Hints, << '-' << SM.getLineNumber(EInfo.first, EInfo.second) << ':' << SM.getColumnNumber(EInfo.first, EInfo.second) << "}:\""; - OS.write_escaped(I->CodeToInsert); + OS.write_escaped(H.CodeToInsert); OS << "\"\n"; } } |