diff options
Diffstat (limited to 'lib/Format/BreakableToken.cpp')
| -rw-r--r-- | lib/Format/BreakableToken.cpp | 76 |
1 files changed, 54 insertions, 22 deletions
diff --git a/lib/Format/BreakableToken.cpp b/lib/Format/BreakableToken.cpp index 4735ab3564f0..cc68f70100e3 100644 --- a/lib/Format/BreakableToken.cpp +++ b/lib/Format/BreakableToken.cpp @@ -8,7 +8,7 @@ //===----------------------------------------------------------------------===// /// /// \file -/// \brief Contains implementation of BreakableToken class and classes derived +/// Contains implementation of BreakableToken class and classes derived /// from it. /// //===----------------------------------------------------------------------===// @@ -44,7 +44,8 @@ static StringRef getLineCommentIndentPrefix(StringRef Comment, const FormatStyle &Style) { static const char *const KnownCStylePrefixes[] = {"///<", "//!<", "///", "//", "//!"}; - static const char *const KnownTextProtoPrefixes[] = {"//", "#"}; + static const char *const KnownTextProtoPrefixes[] = {"//", "#", "##", "###", + "####"}; ArrayRef<const char *> KnownPrefixes(KnownCStylePrefixes); if (Style.Language == FormatStyle::LK_TextProto) KnownPrefixes = KnownTextProtoPrefixes; @@ -67,8 +68,9 @@ static BreakableToken::Split getCommentSplit(StringRef Text, unsigned ColumnLimit, unsigned TabWidth, encoding::Encoding Encoding) { - DEBUG(llvm::dbgs() << "Comment split: \"" << Text << ", " << ColumnLimit - << "\", Content start: " << ContentStartColumn << "\n"); + LLVM_DEBUG(llvm::dbgs() << "Comment split: \"" << Text << ", " << ColumnLimit + << "\", Content start: " << ContentStartColumn + << "\n"); if (ColumnLimit <= ContentStartColumn + 1) return BreakableToken::Split(StringRef::npos, 0); @@ -89,9 +91,9 @@ static BreakableToken::Split getCommentSplit(StringRef Text, // Do not split before a number followed by a dot: this would be interpreted // as a numbered list, which would prevent re-flowing in subsequent passes. - static llvm::Regex kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\."); + static auto *const kNumberedListRegexp = new llvm::Regex("^[1-9][0-9]?\\."); if (SpaceOffset != StringRef::npos && - kNumberedListRegexp.match(Text.substr(SpaceOffset).ltrim(Blanks))) + kNumberedListRegexp->match(Text.substr(SpaceOffset).ltrim(Blanks))) SpaceOffset = Text.find_last_of(Blanks, SpaceOffset); if (SpaceOffset == StringRef::npos || @@ -214,11 +216,11 @@ unsigned BreakableStringLiteral::getContentStartColumn(unsigned LineIndex, BreakableStringLiteral::BreakableStringLiteral( const FormatToken &Tok, unsigned StartColumn, StringRef Prefix, - StringRef Postfix, bool InPPDirective, encoding::Encoding Encoding, - const FormatStyle &Style) + StringRef Postfix, unsigned UnbreakableTailLength, bool InPPDirective, + encoding::Encoding Encoding, const FormatStyle &Style) : BreakableToken(Tok, InPPDirective, Encoding, Style), StartColumn(StartColumn), Prefix(Prefix), Postfix(Postfix), - UnbreakableTailLength(Tok.UnbreakableTailLength) { + UnbreakableTailLength(UnbreakableTailLength) { assert(Tok.TokenText.startswith(Prefix) && Tok.TokenText.endswith(Postfix)); Line = Tok.TokenText.substr( Prefix.size(), Tok.TokenText.size() - Prefix.size() - Postfix.size()); @@ -284,10 +286,9 @@ static bool mayReflowContent(StringRef Content) { Content = Content.trim(Blanks); // Lines starting with '@' commonly have special meaning. // Lines starting with '-', '-#', '+' or '*' are bulleted/numbered lists. - static const SmallVector<StringRef, 8> kSpecialMeaningPrefixes = { - "@", "TODO", "FIXME", "XXX", "-# ", "- ", "+ ", "* "}; bool hasSpecialMeaningPrefix = false; - for (StringRef Prefix : kSpecialMeaningPrefixes) { + for (StringRef Prefix : + {"@", "TODO", "FIXME", "XXX", "-# ", "- ", "+ ", "* "}) { if (Content.startswith(Prefix)) { hasSpecialMeaningPrefix = true; break; @@ -297,9 +298,9 @@ static bool mayReflowContent(StringRef Content) { // Numbered lists may also start with a number followed by '.' // To avoid issues if a line starts with a number which is actually the end // of a previous line, we only consider numbers with up to 2 digits. - static llvm::Regex kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\. "); + static auto *const kNumberedListRegexp = new llvm::Regex("^[1-9][0-9]?\\. "); hasSpecialMeaningPrefix = - hasSpecialMeaningPrefix || kNumberedListRegexp.match(Content); + hasSpecialMeaningPrefix || kNumberedListRegexp->match(Content); // Simple heuristic for what to reflow: content should contain at least two // characters and either the first or second character must be @@ -425,7 +426,7 @@ BreakableBlockComment::BreakableBlockComment( } } - DEBUG({ + LLVM_DEBUG({ llvm::dbgs() << "IndentAtLineBreak " << IndentAtLineBreak << "\n"; llvm::dbgs() << "DelimitersOnNewline " << DelimitersOnNewline << "\n"; for (size_t i = 0; i < Lines.size(); ++i) { @@ -788,16 +789,47 @@ BreakableComment::Split BreakableLineCommentSection::getReflowSplit( void BreakableLineCommentSection::reflow(unsigned LineIndex, WhitespaceManager &Whitespaces) const { - // Reflow happens between tokens. Replace the whitespace between the - // tokens by the empty string. - Whitespaces.replaceWhitespace( - *Tokens[LineIndex], /*Newlines=*/0, /*Spaces=*/0, - /*StartOfTokenColumn=*/StartColumn, /*InPPDirective=*/false); + if (LineIndex > 0 && Tokens[LineIndex] != Tokens[LineIndex - 1]) { + // Reflow happens between tokens. Replace the whitespace between the + // tokens by the empty string. + Whitespaces.replaceWhitespace( + *Tokens[LineIndex], /*Newlines=*/0, /*Spaces=*/0, + /*StartOfTokenColumn=*/StartColumn, /*InPPDirective=*/false); + } else if (LineIndex > 0) { + // In case we're reflowing after the '\' in: + // + // // line comment \ + // // line 2 + // + // the reflow happens inside the single comment token (it is a single line + // comment with an unescaped newline). + // Replace the whitespace between the '\' and '//' with the empty string. + // + // Offset points to after the '\' relative to start of the token. + unsigned Offset = Lines[LineIndex - 1].data() + + Lines[LineIndex - 1].size() - + tokenAt(LineIndex - 1).TokenText.data(); + // WhitespaceLength is the number of chars between the '\' and the '//' on + // the next line. + unsigned WhitespaceLength = + Lines[LineIndex].data() - tokenAt(LineIndex).TokenText.data() - Offset; + Whitespaces.replaceWhitespaceInToken(*Tokens[LineIndex], + Offset, + /*ReplaceChars=*/WhitespaceLength, + /*PreviousPostfix=*/"", + /*CurrentPrefix=*/"", + /*InPPDirective=*/false, + /*Newlines=*/0, + /*Spaces=*/0); + + } // Replace the indent and prefix of the token with the reflow prefix. + unsigned Offset = + Lines[LineIndex].data() - tokenAt(LineIndex).TokenText.data(); unsigned WhitespaceLength = - Content[LineIndex].data() - tokenAt(LineIndex).TokenText.data(); + Content[LineIndex].data() - Lines[LineIndex].data(); Whitespaces.replaceWhitespaceInToken(*Tokens[LineIndex], - /*Offset=*/0, + Offset, /*ReplaceChars=*/WhitespaceLength, /*PreviousPostfix=*/"", /*CurrentPrefix=*/ReflowPrefix, |