//===--- BreakableToken.cpp - Format C++ code -----------------------------===//

//

// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.

// See https://llvm.org/LICENSE.txt for license information.

// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception

//

//===----------------------------------------------------------------------===//

///

/// \file

/// Contains implementation of BreakableToken class and classes derived

/// from it.

///

//===----------------------------------------------------------------------===//

#include "BreakableToken.h"

#include "ContinuationIndenter.h"

#include "clang/Basic/CharInfo.h"

#include "clang/Format/Format.h"

#include "llvm/ADT/STLExtras.h"

#include "llvm/Support/Debug.h"

#include <algorithm>

#define DEBUG_TYPE "format-token-breaker"

namespace clang {

namespace format {

static constexpr StringRef Blanks = " \t\v\f\r";

static bool IsBlank(char C) {

  switch (C) {

  case ' ':

  case '\t':

  case '\v':

  case '\f':

  case '\r':

    return true;

  default:

    return false;

  }

}

static StringRef getLineCommentIndentPrefix(StringRef Comment,

                                            const FormatStyle &Style) {

  static constexpr StringRef KnownCStylePrefixes[] = {"///<", "//!<", "///",

                                                      "//!",  "//:",  "//"};

  static constexpr StringRef KnownTextProtoPrefixes[] = {"####", "###", "##",

                                                         "//", "#"};

  ArrayRef<StringRef> KnownPrefixes(KnownCStylePrefixes);

  if (Style.Language == FormatStyle::LK_TextProto)

    KnownPrefixes = KnownTextProtoPrefixes;

  assert(

      llvm::is_sorted(KnownPrefixes, [](StringRef Lhs, StringRef Rhs) noexcept {

        return Lhs.size() > Rhs.size();

      }));

  
for (StringRef KnownPrefix : KnownPrefixes)26.1k
 {

    if (Comment.startswith(KnownPrefix)) {

      const auto PrefixLength =

          Comment.find_first_not_of(' ', KnownPrefix.size());

      return Comment.substr(0, PrefixLength);

    }

  }

  return {};

}

static BreakableToken::Split

getCommentSplit(StringRef Text, unsigned ContentStartColumn,

                unsigned ColumnLimit, unsigned TabWidth,

                encoding::Encoding Encoding, const FormatStyle &Style,

                bool DecorationEndsWithStar = false) {

  LLVM_DEBUG(llvm::dbgs() << "Comment split: \"" << Text

                          << "\", Column limit: " << ColumnLimit

                          << ", Content start: " << ContentStartColumn << "\n");

  if (ColumnLimit <= ContentStartColumn + 1)

    return BreakableToken::Split(StringRef::npos, 0);

  unsigned MaxSplit = ColumnLimit - ContentStartColumn + 1;

  unsigned MaxSplitBytes = 0;

  for (unsigned NumChars = 0;

       NumChars < MaxSplit && 
MaxSplitBytes < Text.size()73.7k
;) {

    unsigned BytesInChar =

        encoding::getCodePointNumBytes(Text[MaxSplitBytes], Encoding);

    NumChars += encoding::columnWidthWithTabs(

        Text.substr(MaxSplitBytes, BytesInChar), ContentStartColumn + NumChars,

        TabWidth, Encoding);

    MaxSplitBytes += BytesInChar;

  }

  // In JavaScript, some @tags can be followed by {, and machinery that parses

  // these comments will fail to understand the comment if followed by a line

  // break. So avoid ever breaking before a {.

  if (Style.isJavaScript()) {

    StringRef::size_type SpaceOffset =

        Text.find_first_of(Blanks, MaxSplitBytes);

    if (SpaceOffset != StringRef::npos && 
SpaceOffset + 1 < Text.size()55
 &&

        
Text[SpaceOffset + 1] == '{'40
) {

      MaxSplitBytes = SpaceOffset + 1;

    }

  }

  StringRef::size_type SpaceOffset = Text.find_last_of(Blanks, MaxSplitBytes);

  static const auto kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\.");

  // Some spaces are unacceptable to break on, rewind past them.

  while (SpaceOffset != StringRef::npos) {

    // If a line-comment ends with `\`, the next line continues the comment,

    // whether or not it starts with `//`. This is confusing and triggers

    // -Wcomment.

    // Avoid introducing multiline comments by not allowing a break right

    // after '\'.

    if (Style.isCpp()) {

      StringRef::size_type LastNonBlank =

          Text.find_last_not_of(Blanks, SpaceOffset);

      if (LastNonBlank != StringRef::npos && 
Text[LastNonBlank] == '\\'2.21k
) {

        SpaceOffset = Text.find_last_of(Blanks, LastNonBlank);

        continue;

      }

    }

    // 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.

    if (kNumberedListRegexp.match(Text.substr(SpaceOffset).ltrim(Blanks))) {

      SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);

      continue;

    }

    // Avoid ever breaking before a @tag or a { in JavaScript.

    if (Style.isJavaScript() && 
SpaceOffset + 1 < Text.size()129
 &&

        
(119
Text[SpaceOffset + 1] == '{'119
 || 
Text[SpaceOffset + 1] == '@'57
)) {

      SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);

      continue;

    }

    break;

  }

  if (SpaceOffset == StringRef::npos ||

      // Don't break at leading whitespace.

      
Text.find_last_not_of(Blanks, SpaceOffset) == StringRef::npos2.30k
) {

    // Make sure that we don't break at leading whitespace that

    // reaches past MaxSplit.

    StringRef::size_type FirstNonWhitespace = Text.find_first_not_of(Blanks);

    if (FirstNonWhitespace == StringRef::npos) {

      // If the comment is only whitespace, we cannot split.

      return BreakableToken::Split(StringRef::npos, 0);

    }

    SpaceOffset = Text.find_first_of(

        Blanks, std::max<unsigned>(MaxSplitBytes, FirstNonWhitespace));

  }

  if (SpaceOffset != StringRef::npos && 
SpaceOffset != 02.97k
) {

    // adaptStartOfLine will break after lines starting with /** if the comment

    // is broken anywhere. Avoid emitting this break twice here.

    // Example: in /** longtextcomesherethatbreaks */ (with ColumnLimit 20) will

    // insert a break after /**, so this code must not insert the same break.

    if (SpaceOffset == 1 && 
Text[SpaceOffset - 1] == '*'5
)

      return BreakableToken::Split(StringRef::npos, 0);

    StringRef BeforeCut = Text.substr(0, SpaceOffset).rtrim(Blanks);

    StringRef AfterCut = Text.substr(SpaceOffset);

    // Don't trim the leading blanks if it would create a */ after the break.

    if (!DecorationEndsWithStar || 
AfterCut.size() <= 110
 || 
AfterCut[1] != '/'10
)

      AfterCut = AfterCut.ltrim(Blanks);

    return BreakableToken::Split(BeforeCut.size(),

                                 AfterCut.begin() - BeforeCut.end());

  }

  return BreakableToken::Split(StringRef::npos, 0);

}

static BreakableToken::Split

getStringSplit(StringRef Text, unsigned UsedColumns, unsigned ColumnLimit,

               unsigned TabWidth, encoding::Encoding Encoding) {

  // FIXME: Reduce unit test case.

  if (Text.empty())

    return BreakableToken::Split(StringRef::npos, 0);

  if (ColumnLimit <= UsedColumns)

    return BreakableToken::Split(StringRef::npos, 0);

  unsigned MaxSplit = ColumnLimit - UsedColumns;

  StringRef::size_type SpaceOffset = 0;

  StringRef::size_type SlashOffset = 0;

  StringRef::size_type WordStartOffset = 0;

  StringRef::size_type SplitPoint = 0;

  for (unsigned Chars = 0;;) {

    unsigned Advance;

    if (Text[0] == '\\') {

      Advance = encoding::getEscapeSequenceLength(Text);

      Chars += Advance;

    } else {

      Advance = encoding::getCodePointNumBytes(Text[0], Encoding);

      Chars += encoding::columnWidthWithTabs(

          Text.substr(0, Advance), UsedColumns + Chars, TabWidth, Encoding);

    }

    if (Chars > MaxSplit || 
Text.size() <= Advance28.3k
)

      break;

    if (IsBlank(Text[0]))

      SpaceOffset = SplitPoint;

    if (Text[0] == '/')

      SlashOffset = SplitPoint;

    if (Advance == 1 && 
!isAlphanumeric(Text[0])28.1k
)

      WordStartOffset = SplitPoint;

    SplitPoint += Advance;

    Text = Text.substr(Advance);

  }

  if (SpaceOffset != 0)

    return BreakableToken::Split(SpaceOffset + 1, 0);

  if (SlashOffset != 0)

    return BreakableToken::Split(SlashOffset + 1, 0);

  if (WordStartOffset != 0)

    return BreakableToken::Split(WordStartOffset + 1, 0);

  if (SplitPoint != 0)

    return BreakableToken::Split(SplitPoint, 0);

  return BreakableToken::Split(StringRef::npos, 0);

}

bool switchesFormatting(const FormatToken &Token) {

  assert((Token.is(TT_BlockComment) || Token.is(TT_LineComment)) &&

         "formatting regions are switched by comment tokens");

  StringRef Content = Token.TokenText.substr(2).ltrim();

  return Content.startswith("clang-format on") ||

         
Content.startswith("clang-format off")31.4k
;

}

unsigned

BreakableToken::getLengthAfterCompression(unsigned RemainingTokenColumns,

                                          Split Split) const {

  // Example: consider the content

  // lala  lala

  // - RemainingTokenColumns is the original number of columns, 10;

  // - Split is (4, 2), denoting the two spaces between the two words;

  //

  // We compute the number of columns when the split is compressed into a single

  // space, like:

  // lala lala

  //

  // FIXME: Correctly measure the length of whitespace in Split.second so it

  // works with tabs.

  return RemainingTokenColumns + 1 - Split.second;

}

unsigned BreakableStringLiteral::getLineCount() const { return 1; }

unsigned BreakableStringLiteral::getRangeLength(unsigned LineIndex,

                                                unsigned Offset,

                                                StringRef::size_type Length,

                                                unsigned StartColumn) const {

  llvm_unreachable("Getting the length of a part of the string literal "

                   "indicates that the code tries to reflow it.");

}

unsigned

BreakableStringLiteral::getRemainingLength(unsigned LineIndex, unsigned Offset,

                                           unsigned StartColumn) const {

  return UnbreakableTailLength + Postfix.size() +

         encoding::columnWidthWithTabs(Line.substr(Offset), StartColumn,

                                       Style.TabWidth, Encoding);

}

unsigned BreakableStringLiteral::getContentStartColumn(unsigned LineIndex,

                                                       bool Break) const {

  return StartColumn + Prefix.size();

}

BreakableStringLiteral::BreakableStringLiteral(

    const FormatToken &Tok, unsigned StartColumn, StringRef Prefix,

    StringRef Postfix, unsigned UnbreakableTailLength, bool InPPDirective,

    encoding::Encoding Encoding, const FormatStyle &Style)

    : BreakableToken(Tok, InPPDirective, Encoding, Style),

      StartColumn(StartColumn), Prefix(Prefix), Postfix(Postfix),

      UnbreakableTailLength(UnbreakableTailLength) {

  assert(Tok.TokenText.startswith(Prefix) && Tok.TokenText.endswith(Postfix));

  Line = Tok.TokenText.substr(

      Prefix.size(), Tok.TokenText.size() - Prefix.size() - Postfix.size());

}

BreakableToken::Split BreakableStringLiteral::getSplit(

    unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,

    unsigned ContentStartColumn, const llvm::Regex &CommentPragmasRegex) const {

  return getStringSplit(Line.substr(TailOffset), ContentStartColumn,

                        ColumnLimit - Postfix.size(), Style.TabWidth, Encoding);

}

void BreakableStringLiteral::insertBreak(unsigned LineIndex,

                                         unsigned TailOffset, Split Split,

                                         unsigned ContentIndent,

                                         WhitespaceManager &Whitespaces) const {

  Whitespaces.replaceWhitespaceInToken(

      Tok, Prefix.size() + TailOffset + Split.first, Split.second, Postfix,

      Prefix, InPPDirective, 1, StartColumn);

}

BreakableStringLiteralUsingOperators::BreakableStringLiteralUsingOperators(

    const FormatToken &Tok, QuoteStyleType QuoteStyle, bool UnindentPlus,

    unsigned StartColumn, unsigned UnbreakableTailLength, bool InPPDirective,

    encoding::Encoding Encoding, const FormatStyle &Style)

    : BreakableStringLiteral(

          Tok, StartColumn, /*Prefix=*/QuoteStyle == SingleQuotes ? 
"'"0

                            : QuoteStyle == AtDoubleQuotes        ? 
"@\""16

                                                                  : 
"\""614
,

          /*Postfix=*/QuoteStyle == SingleQuotes ? 
"'"0
 : "\"",

          UnbreakableTailLength, InPPDirective, Encoding, Style),

      BracesNeeded(Tok.isNot(TT_StringInConcatenation)),

      QuoteStyle(QuoteStyle) {

  // Find the replacement text for inserting braces and quotes and line breaks.

  // We don't create an allocated string concatenated from parts here because it

  // has to outlive the BreakableStringliteral object.  The brace replacements

  // include a quote so that WhitespaceManager can tell it apart from whitespace

  // replacements between the string and surrounding tokens.

  // The option is not implemented in JavaScript.

  bool SignOnNewLine =

      !Style.isJavaScript() &&

      Style.BreakBeforeBinaryOperators != FormatStyle::BOS_None;

  if (Style.isVerilog()) {

    // In Verilog, all strings are quoted by double quotes, joined by commas,

    // and wrapped in braces.  The comma is always before the newline.

    assert(QuoteStyle == DoubleQuotes);

    LeftBraceQuote = Style.Cpp11BracedListStyle ? 
"{\""137
 : 
"{ \""12
;

    RightBraceQuote = Style.Cpp11BracedListStyle ? 
"\"}"137
 : 
"\" }"12
;

    Postfix = "\",";

    Prefix = "\"";

  } else {

    // The plus sign may be on either line.  And also C# and JavaScript have

    // several quoting styles.

    if (QuoteStyle == SingleQuotes) {

      LeftBraceQuote = Style.SpacesInParensOptions.Other ? "( '" : "('";

      RightBraceQuote = Style.SpacesInParensOptions.Other ? "' )" : "')";

      Postfix = SignOnNewLine ? "'" : "' +";

      Prefix = SignOnNewLine ? "+ '" : "'";

    } else {

      if (QuoteStyle == AtDoubleQuotes) {

        LeftBraceQuote = Style.SpacesInParensOptions.Other ? 
"( @"0
 : "(@";

        Prefix = SignOnNewLine ? 
"+ @\""0
 : "@\"";

      } else {

        LeftBraceQuote = Style.SpacesInParensOptions.Other ? 
"( \""0
 : "(\"";

        Prefix = SignOnNewLine ? 
"+ \""311
 : 
"\""154
;

      }

      RightBraceQuote = Style.SpacesInParensOptions.Other ? 
"\" )"0
 : "\")";

      Postfix = SignOnNewLine ? 
"\""311
 : 
"\" +"170
;

    }

  }

  // Following lines are indented by the width of the brace and space if any.

  ContinuationIndent = BracesNeeded ? 
LeftBraceQuote.size() - 142
 : 
0588
;

  // The plus sign may need to be unindented depending on the style.

  // FIXME: Add support for DontAlign.

  if (!Style.isVerilog() && 
SignOnNewLine481
 && 
!BracesNeeded311
 && 
UnindentPlus311
 &&

      
Style.AlignOperands == FormatStyle::OAS_AlignAfterOperator127
) {

    ContinuationIndent -= 2;

  }

}

unsigned BreakableStringLiteralUsingOperators::getRemainingLength(

    unsigned LineIndex, unsigned Offset, unsigned StartColumn) const {

  return UnbreakableTailLength + (BracesNeeded ? 
RightBraceQuote.size()82
 : 
1652
) +

         encoding::columnWidthWithTabs(Line.substr(Offset), StartColumn,

                                       Style.TabWidth, Encoding);

}

unsigned

BreakableStringLiteralUsingOperators::getContentStartColumn(unsigned LineIndex,

                                                            bool Break) const {

  return std::max(

      0,

      static_cast<int>(StartColumn) +

          (Break ? 
ContinuationIndent + static_cast<int>(Prefix.size())104

                 : 
(630
BracesNeeded630
 ? 
static_cast<int>(LeftBraceQuote.size()) - 142

                                 : 
0588
) +

                       (QuoteStyle == AtDoubleQuotes ? 
216
 : 
1614
)));

}

void BreakableStringLiteralUsingOperators::insertBreak(

    unsigned LineIndex, unsigned TailOffset, Split Split,

    unsigned ContentIndent, WhitespaceManager &Whitespaces) const {

  Whitespaces.replaceWhitespaceInToken(

      Tok, /*Offset=*/(QuoteStyle == AtDoubleQuotes ? 
22
 : 
120
) + TailOffset +

               Split.first,

      /*ReplaceChars=*/Split.second, /*PreviousPostfix=*/Postfix,

      /*CurrentPrefix=*/Prefix, InPPDirective, /*NewLines=*/1,

      /*Spaces=*/

      std::max(0, static_cast<int>(StartColumn) + ContinuationIndent));

}

void BreakableStringLiteralUsingOperators::updateAfterBroken(

    WhitespaceManager &Whitespaces) const {

  // Add the braces required for breaking the token if they are needed.

  if (!BracesNeeded)

    return;

  // To add a brace or parenthesis, we replace the quote (or the at sign) with a

  // brace and another quote.  This is because the rest of the program requires

  // one replacement for each source range.  If we replace the empty strings

  // around the string, it may conflict with whitespace replacements between the

  // string and adjacent tokens.

  Whitespaces.replaceWhitespaceInToken(

      Tok, /*Offset=*/0, /*ReplaceChars=*/1, /*PreviousPostfix=*/"",

      /*CurrentPrefix=*/LeftBraceQuote, InPPDirective, /*NewLines=*/0,

      /*Spaces=*/0);

  Whitespaces.replaceWhitespaceInToken(

      Tok, /*Offset=*/Tok.TokenText.size() - 1, /*ReplaceChars=*/1,

      /*PreviousPostfix=*/RightBraceQuote,

      /*CurrentPrefix=*/"", InPPDirective, /*NewLines=*/0, /*Spaces=*/0);

}

BreakableComment::BreakableComment(const FormatToken &Token,

                                   unsigned StartColumn, bool InPPDirective,

                                   encoding::Encoding Encoding,

                                   const FormatStyle &Style)

    : BreakableToken(Token, InPPDirective, Encoding, Style),

      StartColumn(StartColumn) {}

unsigned BreakableComment::getLineCount() const { return Lines.size(); }

BreakableToken::Split

BreakableComment::getSplit(unsigned LineIndex, unsigned TailOffset,

                           unsigned ColumnLimit, unsigned ContentStartColumn,

                           const llvm::Regex &CommentPragmasRegex) const {

  // Don't break lines matching the comment pragmas regex.

  if (CommentPragmasRegex.match(Content[LineIndex]))

    return Split(StringRef::npos, 0);

  return getCommentSplit(Content[LineIndex].substr(TailOffset),

                         ContentStartColumn, ColumnLimit, Style.TabWidth,

                         Encoding, Style);

}

void BreakableComment::compressWhitespace(

    unsigned LineIndex, unsigned TailOffset, Split Split,

    WhitespaceManager &Whitespaces) const {

  StringRef Text = Content[LineIndex].substr(TailOffset);

  // Text is relative to the content line, but Whitespaces operates relative to

  // the start of the corresponding token, so compute the start of the Split

  // that needs to be compressed into a single space relative to the start of

  // its token.

  unsigned BreakOffsetInToken =

      Text.data() - tokenAt(LineIndex).TokenText.data() + Split.first;

  unsigned CharsToRemove = Split.second;

  Whitespaces.replaceWhitespaceInToken(

      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "", "",

      /*InPPDirective=*/false, /*Newlines=*/0, /*Spaces=*/1);

}

const FormatToken &BreakableComment::tokenAt(unsigned LineIndex) const {

  return Tokens[LineIndex] ? 
*Tokens[LineIndex]1.56k
 : 
Tok3.33k
;

}

static bool mayReflowContent(StringRef Content) {

  Content = Content.trim(Blanks);

  // Lines starting with '@' commonly have special meaning.

  // Lines starting with '-', '-#', '+' or '*' are bulleted/numbered lists.

  bool hasSpecialMeaningPrefix = false;

  for (StringRef Prefix :

       {"@", "TODO", "FIXME", "XXX", "-# ", "- ", "+ ", "* "}) {

    if (Content.startswith(Prefix)) {

      hasSpecialMeaningPrefix = true;

      break;

    }

  }

  // 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 const auto kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\. ");

  hasSpecialMeaningPrefix =

      hasSpecialMeaningPrefix || 
kNumberedListRegexp.match(Content)893
;

  // Simple heuristic for what to reflow: content should contain at least two

  // characters and either the first or second character must be

  // non-punctuation.

  return Content.size() >= 2 && 
!hasSpecialMeaningPrefix773
 &&

         
!Content.endswith("\\")741
 &&

         // Note that this is UTF-8 safe, since if isPunctuation(Content[0]) is

         // true, then the first code point must be 1 byte long.

         
(741
!isPunctuation(Content[0])741
 || 
!isPunctuation(Content[1])6
);

}

BreakableBlockComment::BreakableBlockComment(

    const FormatToken &Token, unsigned StartColumn,

    unsigned OriginalStartColumn, bool FirstInLine, bool InPPDirective,

    encoding::Encoding Encoding, const FormatStyle &Style, bool UseCRLF)

    : BreakableComment(Token, StartColumn, InPPDirective, Encoding, Style),

      DelimitersOnNewline(false),

      UnbreakableTailLength(Token.UnbreakableTailLength) {

  assert(Tok.is(TT_BlockComment) &&

         "block comment section must start with a block comment");

  StringRef TokenText(Tok.TokenText);

  assert(TokenText.startswith("/*") && TokenText.endswith("*/"));

  TokenText.substr(2, TokenText.size() - 4)

      .split(Lines, UseCRLF ? 
"\r\n"20
 : 
"\n"4.47k
);

  int IndentDelta = StartColumn - OriginalStartColumn;

  Content.resize(Lines.size());

  Content[0] = Lines[0];

  ContentColumn.resize(Lines.size());

  // Account for the initial '/*'.

  ContentColumn[0] = StartColumn + 2;

  Tokens.resize(Lines.size());

  for (size_t i = 1; i < Lines.size(); 
++i1.66k
)

    adjustWhitespace(i, IndentDelta);

  // Align decorations with the column of the star on the first line,

  // that is one column after the start "/*".

  DecorationColumn = StartColumn + 1;

  // Account for comment decoration patterns like this:

  //

  // /*

  // ** blah blah blah

  // */

  if (Lines.size() >= 2 && 
Content[1].startswith("**")850
 &&

      
static_cast<unsigned>(ContentColumn[1]) == StartColumn12
) {

    DecorationColumn = StartColumn;

  }

  Decoration = "* ";

  if (Lines.size() == 1 && 
!FirstInLine3.64k
) {

    // Comments for which FirstInLine is false can start on arbitrary column,

    // and available horizontal space can be too small to align consecutive

    // lines with the first one.

    // FIXME: We could, probably, align them to current indentation level, but

    // now we just wrap them without stars.

    Decoration = "";

  }

  for (size_t i = 1, e = Content.size(); i < e && 
!Decoration.empty()1.48k
; 
++i959
) {

    const StringRef &Text = Content[i];

    if (i + 1 == e) {

      // If the last line is empty, the closing "*/" will have a star.

      if (Text.empty())

        break;

    } else if (!Text.empty() && 
Decoration.startswith(Text)613
) {

      continue;

    }

    
while (940
!Text.startswith(Decoration))

      Decoration = Decoration.drop_back(1);

  }

  LastLineNeedsDecoration = true;

  IndentAtLineBreak = ContentColumn[0] + 1;

  for (size_t i = 1, e = Lines.size(); i < e; 
++i1.66k
) {

    if (Content[i].empty()) {

      if (i + 1 == e) {

        // Empty last line means that we already have a star as a part of the

        // trailing */. We also need to preserve whitespace, so that */ is

        // correctly indented.

        LastLineNeedsDecoration = false;

        // Align the star in the last '*/' with the stars on the previous lines.

        if (e >= 2 && !Decoration.empty())

          ContentColumn[i] = DecorationColumn;

      } else 
if (28
Decoration.empty()28
) {

        // For all other lines, set the start column to 0 if they're empty, so

        // we do not insert trailing whitespace anywhere.

        ContentColumn[i] = 0;

      }

      continue;

    }

    // The first line already excludes the star.

    // The last line excludes the star if LastLineNeedsDecoration is false.

    // For all other lines, adjust the line to exclude the star and

    // (optionally) the first whitespace.

    unsigned DecorationSize = Decoration.startswith(Content[i])

                                  ? 
Content[i].size()21

                                  : 
Decoration.size()1.09k
;

    if (DecorationSize)

      ContentColumn[i] = DecorationColumn + DecorationSize;

    Content[i] = Content[i].substr(DecorationSize);

    if (!Decoration.startswith(Content[i])) {

      IndentAtLineBreak =

          std::min<int>(IndentAtLineBreak, std::max(0, ContentColumn[i]));

    }

  }

  IndentAtLineBreak = std::max<unsigned>(IndentAtLineBreak, Decoration.size());

  // Detect a multiline jsdoc comment and set DelimitersOnNewline in that case.

  if (Style.isJavaScript() || 
Style.Language == FormatStyle::LK_Java4.30k
) {

    if ((Lines[0] == "*" || 
Lines[0].startswith("* ")120
) && 
Lines.size() > 1156
) {

      // This is a multiline jsdoc comment.

      DelimitersOnNewline = true;

    } else if (Lines[0].startswith("* ") && 
Lines.size() == 154
) {

      // Detect a long single-line comment, like:

      // /** long long long */

      // Below, '2' is the width of '*/'.

      unsigned EndColumn =

          ContentColumn[0] +

          encoding::columnWidthWithTabs(Lines[0], ContentColumn[0],

                                        Style.TabWidth, Encoding) +

          2;

      DelimitersOnNewline = EndColumn > Style.ColumnLimit;

    }

  }

  LLVM_DEBUG({

    llvm::dbgs() << "IndentAtLineBreak " << IndentAtLineBreak << "\n";

    llvm::dbgs() << "DelimitersOnNewline " << DelimitersOnNewline << "\n";

    for (size_t i = 0; i < Lines.size(); ++i) {

      llvm::dbgs() << i << " |" << Content[i] << "| "

                   << "CC=" << ContentColumn[i] << "| "

                   << "IN=" << (Content[i].data() - Lines[i].data()) << "\n";

    }

  });

}

BreakableToken::Split BreakableBlockComment::getSplit(

    unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,

    unsigned ContentStartColumn, const llvm::Regex &CommentPragmasRegex) const {

  // Don't break lines matching the comment pragmas regex.

  if (CommentPragmasRegex.match(Content[LineIndex]))

    return Split(StringRef::npos, 0);

  return getCommentSplit(Content[LineIndex].substr(TailOffset),

                         ContentStartColumn, ColumnLimit, Style.TabWidth,

                         Encoding, Style, Decoration.endswith("*"));

}

void BreakableBlockComment::adjustWhitespace(unsigned LineIndex,

                                             int IndentDelta) {

  // When in a preprocessor directive, the trailing backslash in a block comment

  // is not needed, but can serve a purpose of uniformity with necessary escaped

  // newlines outside the comment. In this case we remove it here before

  // trimming the trailing whitespace. The backslash will be re-added later when

  // inserting a line break.

  size_t EndOfPreviousLine = Lines[LineIndex - 1].size();

  if (InPPDirective && 
Lines[LineIndex - 1].endswith("\\")22
)

    --EndOfPreviousLine;

  // Calculate the end of the non-whitespace text in the previous line.

  EndOfPreviousLine =

      Lines[LineIndex - 1].find_last_not_of(Blanks, EndOfPreviousLine);

  if (EndOfPreviousLine == StringRef::npos)

    EndOfPreviousLine = 0;

  else

    ++EndOfPreviousLine;

  // Calculate the start of the non-whitespace text in the current line.

  size_t StartOfLine = Lines[LineIndex].find_first_not_of(Blanks);

  if (StartOfLine == StringRef::npos)

    StartOfLine = Lines[LineIndex].size();

  StringRef Whitespace = Lines[LineIndex].substr(0, StartOfLine);

  // Adjust Lines to only contain relevant text.

  size_t PreviousContentOffset =

      Content[LineIndex - 1].data() - Lines[LineIndex - 1].data();

  Content[LineIndex - 1] = Lines[LineIndex - 1].substr(

      PreviousContentOffset, EndOfPreviousLine - PreviousContentOffset);

  Content[LineIndex] = Lines[LineIndex].substr(StartOfLine);

  // Adjust the start column uniformly across all lines.

  ContentColumn[LineIndex] =

      encoding::columnWidthWithTabs(Whitespace, 0, Style.TabWidth, Encoding) +

      IndentDelta;

}

unsigned BreakableBlockComment::getRangeLength(unsigned LineIndex,

                                               unsigned Offset,

                                               StringRef::size_type Length,

                                               unsigned StartColumn) const {

  return encoding::columnWidthWithTabs(

      Content[LineIndex].substr(Offset, Length), StartColumn, Style.TabWidth,

      Encoding);

}

unsigned BreakableBlockComment::getRemainingLength(unsigned LineIndex,

                                                   unsigned Offset,

                                                   unsigned StartColumn) const {

  unsigned LineLength =

      UnbreakableTailLength +

      getRangeLength(LineIndex, Offset, StringRef::npos, StartColumn);

  if (LineIndex + 1 == Lines.size()) {

    LineLength += 2;

    // We never need a decoration when breaking just the trailing "*/" postfix.

    bool HasRemainingText = Offset < Content[LineIndex].size();

    if (!HasRemainingText) {

      bool HasDecoration = Lines[LineIndex].ltrim().startswith(Decoration);

      if (HasDecoration)

        LineLength -= Decoration.size();

    }

  }

  return LineLength;

}

unsigned BreakableBlockComment::getContentStartColumn(unsigned LineIndex,

                                                      bool Break) const {

  if (Break)

    return IndentAtLineBreak;

  return std::max(0, ContentColumn[LineIndex]);

}

const llvm::StringSet<>

    BreakableBlockComment::ContentIndentingJavadocAnnotations = {

        "@param", "@return",     "@returns", "@throws",  "@type", "@template",

        "@see",   "@deprecated", "@define",  "@exports", "@mods", "@private",

};

unsigned BreakableBlockComment::getContentIndent(unsigned LineIndex) const {

  if (Style.Language != FormatStyle::LK_Java && 
!Style.isJavaScript()569
)

    return 0;

  // The content at LineIndex 0 of a comment like:

  // /** line 0 */

  // is "* line 0", so we need to skip over the decoration in that case.

  StringRef ContentWithNoDecoration = Content[LineIndex];

  if (LineIndex == 0 && 
ContentWithNoDecoration.startswith("*")35
)

    ContentWithNoDecoration = ContentWithNoDecoration.substr(1).ltrim(Blanks);

  StringRef FirstWord = ContentWithNoDecoration.substr(

      0, ContentWithNoDecoration.find_first_of(Blanks));

  if (ContentIndentingJavadocAnnotations.contains(FirstWord))

    return Style.ContinuationIndentWidth;

  return 0;

}

void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,

                                        Split Split, unsigned ContentIndent,

                                        WhitespaceManager &Whitespaces) const {

  StringRef Text = Content[LineIndex].substr(TailOffset);

  StringRef Prefix = Decoration;

  // We need this to account for the case when we have a decoration "* " for all

  // the lines except for the last one, where the star in "*/" acts as a

  // decoration.

  unsigned LocalIndentAtLineBreak = IndentAtLineBreak;

  if (LineIndex + 1 == Lines.size() &&

      
Text.size() == Split.first + Split.second85
) {

    // For the last line we need to break before "*/", but not to add "* ".

    Prefix = "";

    if (LocalIndentAtLineBreak >= 2)

      LocalIndentAtLineBreak -= 2;

  }

  // The split offset is from the beginning of the line. Convert it to an offset

  // from the beginning of the token text.

  unsigned BreakOffsetInToken =

      Text.data() - tokenAt(LineIndex).TokenText.data() + Split.first;

  unsigned CharsToRemove = Split.second;

  assert(LocalIndentAtLineBreak >= Prefix.size());

  std::string PrefixWithTrailingIndent = std::string(Prefix);

  PrefixWithTrailingIndent.append(ContentIndent, ' ');

  Whitespaces.replaceWhitespaceInToken(

      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "",

      PrefixWithTrailingIndent, InPPDirective, /*Newlines=*/1,

      /*Spaces=*/LocalIndentAtLineBreak + ContentIndent -

          PrefixWithTrailingIndent.size());

}

BreakableToken::Split BreakableBlockComment::getReflowSplit(

    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {

  if (!mayReflow(LineIndex, CommentPragmasRegex))

    return Split(StringRef::npos, 0);

  // If we're reflowing into a line with content indent, only reflow the next

  // line if its starting whitespace matches the content indent.

  size_t Trimmed = Content[LineIndex].find_first_not_of(Blanks);

  if (LineIndex) {

    unsigned PreviousContentIndent = getContentIndent(LineIndex - 1);

    if (PreviousContentIndent && 
Trimmed != StringRef::npos6
 &&

        
Trimmed != PreviousContentIndent6
) {

      return Split(StringRef::npos, 0);

    }

  }

  return Split(0, Trimmed != StringRef::npos ? Trimmed : 
00
);

}

bool BreakableBlockComment::introducesBreakBeforeToken() const {

  // A break is introduced when we want delimiters on newline.

  return DelimitersOnNewline &&

         
Lines[0].substr(1).find_first_not_of(Blanks) != StringRef::npos125
;

}

void BreakableBlockComment::reflow(unsigned LineIndex,

                                   WhitespaceManager &Whitespaces) const {

  StringRef TrimmedContent = Content[LineIndex].ltrim(Blanks);

  // Here we need to reflow.

  assert(Tokens[LineIndex - 1] == Tokens[LineIndex] &&

         "Reflowing whitespace within a token");

  // This is the offset of the end of the last line relative to the start of

  // the token text in the token.

  unsigned WhitespaceOffsetInToken = Content[LineIndex - 1].data() +

                                     Content[LineIndex - 1].size() -

                                     tokenAt(LineIndex).TokenText.data();

  unsigned WhitespaceLength = TrimmedContent.data() -

                              tokenAt(LineIndex).TokenText.data() -

                              WhitespaceOffsetInToken;

  Whitespaces.replaceWhitespaceInToken(

      tokenAt(LineIndex), WhitespaceOffsetInToken,

      /*ReplaceChars=*/WhitespaceLength, /*PreviousPostfix=*/"",

      /*CurrentPrefix=*/ReflowPrefix, InPPDirective, /*Newlines=*/0,

      /*Spaces=*/0);

}

void BreakableBlockComment::adaptStartOfLine(

    unsigned LineIndex, WhitespaceManager &Whitespaces) const {

  if (LineIndex == 0) {

    if (DelimitersOnNewline) {

      // Since we're breaking at index 1 below, the break position and the

      // break length are the same.

      // Note: this works because getCommentSplit is careful never to split at

      // the beginning of a line.

      size_t BreakLength = Lines[0].substr(1).find_first_not_of(Blanks);

      if (BreakLength != StringRef::npos) {

        insertBreak(LineIndex, 0, Split(1, BreakLength), /*ContentIndent=*/0,

                    Whitespaces);

      }

    }

    return;

  }

  // Here no reflow with the previous line will happen.

  // Fix the decoration of the line at LineIndex.

  StringRef Prefix = Decoration;

  if (Content[LineIndex].empty()) {

    if (LineIndex + 1 == Lines.size()) {

      if (!LastLineNeedsDecoration) {

        // If the last line was empty, we don't need a prefix, as the */ will

        // line up with the decoration (if it exists).

        Prefix = "";

      }

    } else 
if (23
!Decoration.empty()23
) {

      // For other empty lines, if we do have a decoration, adapt it to not

      // contain a trailing whitespace.

      Prefix = Prefix.substr(0, 1);

    }

  } else if (ContentColumn[LineIndex] == 1) {

    // This line starts immediately after the decorating *.

    Prefix = Prefix.substr(0, 1);

  }

  // This is the offset of the end of the last line relative to the start of the

  // token text in the token.

  unsigned WhitespaceOffsetInToken = Content[LineIndex - 1].data() +

                                     Content[LineIndex - 1].size() -

                                     tokenAt(LineIndex).TokenText.data();

  unsigned WhitespaceLength = Content[LineIndex].data() -

                              tokenAt(LineIndex).TokenText.data() -

                              WhitespaceOffsetInToken;

  Whitespaces.replaceWhitespaceInToken(

      tokenAt(LineIndex), WhitespaceOffsetInToken, WhitespaceLength, "", Prefix,

      InPPDirective, /*Newlines=*/1, ContentColumn[LineIndex] - Prefix.size());

}

BreakableToken::Split

BreakableBlockComment::getSplitAfterLastLine(unsigned TailOffset) const {

  if (DelimitersOnNewline) {

    // Replace the trailing whitespace of the last line with a newline.

    // In case the last line is empty, the ending '*/' is already on its own

    // line.

    StringRef Line = Content.back().substr(TailOffset);

    StringRef TrimmedLine = Line.rtrim(Blanks);

    if (!TrimmedLine.empty())

      return Split(TrimmedLine.size(), Line.size() - TrimmedLine.size());

  }

  return Split(StringRef::npos, 0);

}

bool BreakableBlockComment::mayReflow(

    unsigned LineIndex, const llvm::Regex &CommentPragmasRegex) const {

  // Content[LineIndex] may exclude the indent after the '*' decoration. In that

  // case, we compute the start of the comment pragma manually.

  StringRef IndentContent = Content[LineIndex];

  if (Lines[LineIndex].ltrim(Blanks).startswith("*"))

    IndentContent = Lines[LineIndex].ltrim(Blanks).substr(1);

  return LineIndex > 0 && !CommentPragmasRegex.match(IndentContent) &&

         
mayReflowContent(Content[LineIndex])249
 && 
!Tok.Finalized101
 &&

         
!switchesFormatting(tokenAt(LineIndex))101
;

}

BreakableLineCommentSection::BreakableLineCommentSection(

    const FormatToken &Token, unsigned StartColumn, bool InPPDirective,

    encoding::Encoding Encoding, const FormatStyle &Style)

    : BreakableComment(Token, StartColumn, InPPDirective, Encoding, Style) {

  assert(Tok.is(TT_LineComment) &&

         "line comment section must start with a line comment");

  FormatToken *LineTok = nullptr;

  const int Minimum = Style.SpacesInLineCommentPrefix.Minimum;

  // How many spaces we changed in the first line of the section, this will be

  // applied in all following lines

  int FirstLineSpaceChange = 0;

  for (const FormatToken *CurrentTok = &Tok;

       CurrentTok && 
CurrentTok->is(TT_LineComment)26.1k
;

       
CurrentTok = CurrentTok->Next9.70k
) {

    LastLineTok = LineTok;

    StringRef TokenText(CurrentTok->TokenText);

    assert((TokenText.startswith("//") || TokenText.startswith("#")) &&

           "unsupported line comment prefix, '//' and '#' are supported");

    size_t FirstLineIndex = Lines.size();

    TokenText.split(Lines, "\n");

    Content.resize(Lines.size());

    ContentColumn.resize(Lines.size());

    PrefixSpaceChange.resize(Lines.size());

    Tokens.resize(Lines.size());

    Prefix.resize(Lines.size());

    OriginalPrefix.resize(Lines.size());

    for (size_t i = FirstLineIndex, e = Lines.size(); i < e; 
++i26.1k
) {

      Lines[i] = Lines[i].ltrim(Blanks);

      StringRef IndentPrefix = getLineCommentIndentPrefix(Lines[i], Style);

      OriginalPrefix[i] = IndentPrefix;

      const int SpacesInPrefix = llvm::count(IndentPrefix, ' ');

      // This lambda also considers multibyte character that is not handled in

      // functions like isPunctuation provided by CharInfo.

      const auto NoSpaceBeforeFirstCommentChar = [&]() {

        assert(Lines[i].size() > IndentPrefix.size());

        const char FirstCommentChar = Lines[i][IndentPrefix.size()];

        const unsigned FirstCharByteSize =

            encoding::getCodePointNumBytes(FirstCommentChar, Encoding);

        if (encoding::columnWidth(

                Lines[i].substr(IndentPrefix.size(), FirstCharByteSize),

                Encoding) != 1) {

          return false;

        }

        // In C-like comments, add a space before #. For example this is useful

        // to preserve the relative indentation when commenting out code with

        // #includes.

        //

        // In languages using # as the comment leader such as proto, don't

        // add a space to support patterns like:

        // #########

        // # section

        // #########

        if (FirstCommentChar == '#' && 
!TokenText.startswith("#")22
)

          return false;

        return FirstCommentChar == '\\' || 
isPunctuation(FirstCommentChar)21.6k
 ||

               
isHorizontalWhitespace(FirstCommentChar)21.0k
;

      };

      // On the first line of the comment section we calculate how many spaces

      // are to be added or removed, all lines after that just get only the

      // change and we will not look at the maximum anymore. Additionally to the

      // actual first line, we calculate that when the non space Prefix changes,

      // e.g. from "///" to "//".

      if (i == 0 || OriginalPrefix[i].rtrim(Blanks) !=

                        OriginalPrefix[i - 1].rtrim(Blanks)) {

        if (SpacesInPrefix < Minimum && 
Lines[i].size() > IndentPrefix.size()4.92k
 &&

            
!NoSpaceBeforeFirstCommentChar()280
) {

          FirstLineSpaceChange = Minimum - SpacesInPrefix;

        } else if (static_cast<unsigned>(SpacesInPrefix) >

                   Style.SpacesInLineCommentPrefix.Maximum) {

          FirstLineSpaceChange =

              Style.SpacesInLineCommentPrefix.Maximum - SpacesInPrefix;

        } else {

          FirstLineSpaceChange = 0;

        }

      }

      if (Lines[i].size() != IndentPrefix.size()) {

        PrefixSpaceChange[i] = FirstLineSpaceChange;

        if (SpacesInPrefix + PrefixSpaceChange[i] < Minimum) {

          PrefixSpaceChange[i] +=

              Minimum - (SpacesInPrefix + PrefixSpaceChange[i]);

        }

        assert(Lines[i].size() > IndentPrefix.size());

        const auto FirstNonSpace = Lines[i][IndentPrefix.size()];

        const bool IsFormatComment = LineTok && 
switchesFormatting(*LineTok)2.09k
;

        const bool LineRequiresLeadingSpace =

            !NoSpaceBeforeFirstCommentChar() ||

            
(581
FirstNonSpace == '}'581
 && 
FirstLineSpaceChange != 048
);

        const bool AllowsSpaceChange =

            !IsFormatComment &&

            
(21.4k
SpacesInPrefix != 021.4k
 || 
LineRequiresLeadingSpace389
);

        if (PrefixSpaceChange[i] > 0 && 
AllowsSpaceChange394
) {

          Prefix[i] = IndentPrefix.str();

          Prefix[i].append(PrefixSpaceChange[i], ' ');

        } else if (PrefixSpaceChange[i] < 0 && 
AllowsSpaceChange136
) {

          Prefix[i] = IndentPrefix

                          .drop_back(std::min<std::size_t>(

                              -PrefixSpaceChange[i], SpacesInPrefix))

                          .str();

        } else {

          Prefix[i] = IndentPrefix.str();

        }

      } else {

        // If the IndentPrefix is the whole line, there is no content and we

        // drop just all space

        Prefix[i] = IndentPrefix.drop_back(SpacesInPrefix).str();

      }

      Tokens[i] = LineTok;

      Content[i] = Lines[i].substr(IndentPrefix.size());

      ContentColumn[i] =

          StartColumn + encoding::columnWidthWithTabs(Prefix[i], StartColumn,

                                                      Style.TabWidth, Encoding);

      // Calculate the end of the non-whitespace text in this line.

      size_t EndOfLine = Content[i].find_last_not_of(Blanks);

      if (EndOfLine == StringRef::npos)

        EndOfLine = Content[i].size();

      else

        ++EndOfLine;

      Content[i] = Content[i].substr(0, EndOfLine);

    }

    LineTok = CurrentTok->Next;

    if (CurrentTok->Next && 
!CurrentTok->Next->ContinuesLineCommentSection18.5k
) {

      // A line comment section needs to broken by a line comment that is

      // preceded by at least two newlines. Note that we put this break here

      // instead of breaking at a previous stage during parsing, since that

      // would split the contents of the enum into two unwrapped lines in this

      // example, which is undesirable:

      // enum A {

      //   a, // comment about a

      //

      //   // comment about b

      //   b

      // };

      //

      // FIXME: Consider putting separate line comment sections as children to

      // the unwrapped line instead.

      break;

    }

  }

}