aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Format/BreakableToken.cpp
blob: 3c9df62f80dca985e4f681b1073f6fed1d7afba6 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
//===--- BreakableToken.cpp - Format C++ code -----------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
///
/// \file
/// \brief 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 const char *const 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) {
  static const char *const KnownPrefixes[] = {
      "///<", "//!<", "///", "//", "//!"};
  StringRef LongestPrefix;
  for (StringRef KnownPrefix : KnownPrefixes) {
    if (Comment.startswith(KnownPrefix)) {
      size_t PrefixLength = KnownPrefix.size();
      while (PrefixLength < Comment.size() && Comment[PrefixLength] == ' ')
        ++PrefixLength;
      if (PrefixLength > LongestPrefix.size())
        LongestPrefix = Comment.substr(0, PrefixLength);
    }
  }
  return LongestPrefix;
}

static BreakableToken::Split getCommentSplit(StringRef Text,
                                             unsigned ContentStartColumn,
                                             unsigned ColumnLimit,
                                             unsigned TabWidth,
                                             encoding::Encoding Encoding) {
  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();) {
    unsigned BytesInChar =
        encoding::getCodePointNumBytes(Text[MaxSplitBytes], Encoding);
    NumChars +=
        encoding::columnWidthWithTabs(Text.substr(MaxSplitBytes, BytesInChar),
                                      ContentStartColumn, TabWidth, Encoding);
    MaxSplitBytes += BytesInChar;
  }

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

  // 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]?\\.");
  if (SpaceOffset != StringRef::npos &&
      kNumberedListRegexp.match(Text.substr(SpaceOffset).ltrim(Blanks)))
    SpaceOffset = Text.find_last_of(Blanks, SpaceOffset);

  if (SpaceOffset == StringRef::npos ||
      // Don't break at leading whitespace.
      Text.find_last_not_of(Blanks, SpaceOffset) == StringRef::npos) {
    // 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 != 0) {
    StringRef BeforeCut = Text.substr(0, SpaceOffset).rtrim(Blanks);
    StringRef AfterCut = Text.substr(SpaceOffset).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() <= Advance)
      break;

    if (IsBlank(Text[0]))
      SpaceOffset = SplitPoint;
    if (Text[0] == '/')
      SlashOffset = SplitPoint;
    if (Advance == 1 && !isAlphanumeric(Text[0]))
      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");
}

unsigned
BreakableToken::getLineLengthAfterCompression(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
  return RemainingTokenColumns + 1 - Split.second;
}

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

unsigned BreakableSingleLineToken::getLineLengthAfterSplit(
    unsigned LineIndex, unsigned TailOffset,
    StringRef::size_type Length) const {
  return StartColumn + Prefix.size() + Postfix.size() +
         encoding::columnWidthWithTabs(Line.substr(TailOffset, Length),
                                       StartColumn + Prefix.size(),
                                       Style.TabWidth, Encoding);
}

BreakableSingleLineToken::BreakableSingleLineToken(
    const FormatToken &Tok, unsigned StartColumn, StringRef Prefix,
    StringRef Postfix, bool InPPDirective, encoding::Encoding Encoding,
    const FormatStyle &Style)
    : BreakableToken(Tok, InPPDirective, Encoding, Style),
      StartColumn(StartColumn), Prefix(Prefix), Postfix(Postfix) {
  assert(Tok.TokenText.startswith(Prefix) && Tok.TokenText.endswith(Postfix));
  Line = Tok.TokenText.substr(
      Prefix.size(), Tok.TokenText.size() - Prefix.size() - Postfix.size());
}

BreakableStringLiteral::BreakableStringLiteral(
    const FormatToken &Tok, unsigned StartColumn, StringRef Prefix,
    StringRef Postfix, bool InPPDirective, encoding::Encoding Encoding,
    const FormatStyle &Style)
    : BreakableSingleLineToken(Tok, StartColumn, Prefix, Postfix, InPPDirective,
                               Encoding, Style) {}

BreakableToken::Split
BreakableStringLiteral::getSplit(unsigned LineIndex, unsigned TailOffset,
                                 unsigned ColumnLimit,
                                 llvm::Regex &CommentPragmasRegex) const {
  return getStringSplit(Line.substr(TailOffset),
                        StartColumn + Prefix.size() + Postfix.size(),
                        ColumnLimit, Style.TabWidth, Encoding);
}

void BreakableStringLiteral::insertBreak(unsigned LineIndex,
                                         unsigned TailOffset, Split Split,
                                         WhitespaceManager &Whitespaces) {
  Whitespaces.replaceWhitespaceInToken(
      Tok, Prefix.size() + TailOffset + Split.first, Split.second, Postfix,
      Prefix, InPPDirective, 1, StartColumn);
}

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,
                           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),
                         getContentStartColumn(LineIndex, TailOffset),
                         ColumnLimit, Style.TabWidth, Encoding);
}

void BreakableComment::compressWhitespace(unsigned LineIndex,
                                          unsigned TailOffset, Split Split,
                                          WhitespaceManager &Whitespaces) {
  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);
}

BreakableToken::Split
BreakableComment::getReflowSplit(StringRef Text, StringRef ReflowPrefix,
                                 unsigned PreviousEndColumn,
                                 unsigned ColumnLimit) const {
  unsigned ReflowStartColumn = PreviousEndColumn + ReflowPrefix.size();
  StringRef TrimmedText = Text.rtrim(Blanks);
  // This is the width of the resulting line in case the full line of Text gets
  // reflown up starting at ReflowStartColumn.
  unsigned FullWidth = ReflowStartColumn + encoding::columnWidthWithTabs(
                                               TrimmedText, ReflowStartColumn,
                                               Style.TabWidth, Encoding);
  // If the full line fits up, we return a reflow split after it,
  // otherwise we compute the largest piece of text that fits after
  // ReflowStartColumn.
  Split ReflowSplit =
      FullWidth <= ColumnLimit
          ? Split(TrimmedText.size(), Text.size() - TrimmedText.size())
          : getCommentSplit(Text, ReflowStartColumn, ColumnLimit,
                            Style.TabWidth, Encoding);

  // We need to be extra careful here, because while it's OK to keep a long line
  // if it can't be broken into smaller pieces (like when the first word of a
  // long line is longer than the column limit), it's not OK to reflow that long
  // word up. So we recompute the size of the previous line after reflowing and
  // only return the reflow split if that's under the line limit.
  if (ReflowSplit.first != StringRef::npos &&
      // Check if the width of the newly reflown line is under the limit.
      PreviousEndColumn + ReflowPrefix.size() +
              encoding::columnWidthWithTabs(Text.substr(0, ReflowSplit.first),
                                            PreviousEndColumn +
                                                ReflowPrefix.size(),
                                            Style.TabWidth, Encoding) <=
          ColumnLimit) {
    return ReflowSplit;
  }
  return Split(StringRef::npos, 0);
}

const FormatToken &BreakableComment::tokenAt(unsigned LineIndex) const {
  return Tokens[LineIndex] ? *Tokens[LineIndex] : Tok;
}

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) {
    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 llvm::Regex kNumberedListRegexp = llvm::Regex("^[1-9][0-9]?\\. ");
  hasSpecialMeaningPrefix = 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
  // non-punctuation.
  return Content.size() >= 2 && !hasSpecialMeaningPrefix &&
         !Content.endswith("\\") &&
         // Note that this is UTF-8 safe, since if isPunctuation(Content[0]) is
         // true, then the first code point must be 1 byte long.
         (!isPunctuation(Content[0]) || !isPunctuation(Content[1]));
}

BreakableBlockComment::BreakableBlockComment(
    const FormatToken &Token, unsigned StartColumn,
    unsigned OriginalStartColumn, bool FirstInLine, bool InPPDirective,
    encoding::Encoding Encoding, const FormatStyle &Style)
    : BreakableComment(Token, StartColumn, InPPDirective, Encoding, Style) {
  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, "\n");

  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(); ++i)
    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("**") &&
      static_cast<unsigned>(ContentColumn[1]) == StartColumn) {
    DecorationColumn = StartColumn;
  }

  Decoration = "* ";
  if (Lines.size() == 1 && !FirstInLine) {
    // 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 = Lines.size(); i < e && !Decoration.empty(); ++i) {
    // If the last line is empty, the closing "*/" will have a star.
    if (i + 1 == e && Content[i].empty())
      break;
    if (!Content[i].empty() && i + 1 != e &&
        Decoration.startswith(Content[i]))
      continue;
    while (!Content[i].startswith(Decoration))
      Decoration = Decoration.substr(0, Decoration.size() - 1);
  }

  LastLineNeedsDecoration = true;
  IndentAtLineBreak = ContentColumn[0] + 1;
  for (size_t i = 1, e = Lines.size(); i < e; ++i) {
    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 (Decoration.empty()) {
        // 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()
                                  : Decoration.size();
    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());

  DEBUG({
    llvm::dbgs() << "IndentAtLineBreak " << IndentAtLineBreak << "\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";
    }
  });
}

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("\\"))
    --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].rtrim("\r\n").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::getLineLengthAfterSplit(
    unsigned LineIndex, unsigned TailOffset,
    StringRef::size_type Length) const {
  unsigned ContentStartColumn = getContentStartColumn(LineIndex, TailOffset);
  unsigned LineLength =
      ContentStartColumn + encoding::columnWidthWithTabs(
                               Content[LineIndex].substr(TailOffset, Length),
                               ContentStartColumn, Style.TabWidth, Encoding);
  // The last line gets a "*/" postfix.
  if (LineIndex + 1 == Lines.size()) {
    LineLength += 2;
    // We never need a decoration when breaking just the trailing "*/" postfix.
    // Note that checking that Length == 0 is not enough, since Length could
    // also be StringRef::npos.
    if (Content[LineIndex].substr(TailOffset, Length).empty()) {
      LineLength -= Decoration.size();
    }
  }
  return LineLength;
}

void BreakableBlockComment::insertBreak(unsigned LineIndex, unsigned TailOffset,
                                        Split Split,
                                        WhitespaceManager &Whitespaces) {
  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.second) {
    // 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());
  Whitespaces.replaceWhitespaceInToken(
      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "", Prefix,
      InPPDirective, /*Newlines=*/1,
      /*Spaces=*/LocalIndentAtLineBreak - Prefix.size());
}

BreakableToken::Split BreakableBlockComment::getSplitBefore(
    unsigned LineIndex,
    unsigned PreviousEndColumn,
    unsigned ColumnLimit,
    llvm::Regex &CommentPragmasRegex) const {
  if (!mayReflow(LineIndex, CommentPragmasRegex))
    return Split(StringRef::npos, 0);
  StringRef TrimmedContent = Content[LineIndex].ltrim(Blanks);
  return getReflowSplit(TrimmedContent, ReflowPrefix, PreviousEndColumn,
                        ColumnLimit);
}

unsigned BreakableBlockComment::getReflownColumn(
    StringRef Content,
    unsigned LineIndex,
    unsigned PreviousEndColumn) const {
    unsigned StartColumn = PreviousEndColumn + ReflowPrefix.size();
    // If this is the last line, it will carry around its '*/' postfix.
    unsigned PostfixLength = (LineIndex + 1 == Lines.size() ? 2 : 0);
    // The line is composed of previous text, reflow prefix, reflown text and
    // postfix.
    unsigned ReflownColumn =
        StartColumn + encoding::columnWidthWithTabs(Content, StartColumn,
                                                    Style.TabWidth, Encoding) +
        PostfixLength;
    return ReflownColumn;
}

unsigned BreakableBlockComment::getLineLengthAfterSplitBefore(
    unsigned LineIndex, unsigned TailOffset,
    unsigned PreviousEndColumn,
    unsigned ColumnLimit,
    Split SplitBefore) const {
  if (SplitBefore.first == StringRef::npos ||
      // Block comment line contents contain the trailing whitespace after the
      // decoration, so the need of left trim. Note that this behavior is
      // consistent with the breaking of block comments where the indentation of
      // a broken line is uniform across all the lines of the block comment.
      SplitBefore.first + SplitBefore.second <
          Content[LineIndex].ltrim().size()) {
    // A piece of line, not the whole, gets reflown.
    return getLineLengthAfterSplit(LineIndex, TailOffset, StringRef::npos);
  } else {
    // The whole line gets reflown, need to check if we need to insert a break
    // for the postfix or not.
    StringRef TrimmedContent = Content[LineIndex].ltrim(Blanks);
    unsigned ReflownColumn =
        getReflownColumn(TrimmedContent, LineIndex, PreviousEndColumn);
    if (ReflownColumn <= ColumnLimit) {
      return ReflownColumn;
    }
    return getLineLengthAfterSplit(LineIndex, TailOffset, StringRef::npos);
  }
}
void BreakableBlockComment::replaceWhitespaceBefore(
    unsigned LineIndex, unsigned PreviousEndColumn, unsigned ColumnLimit,
    Split SplitBefore, WhitespaceManager &Whitespaces) {
  if (LineIndex == 0) return;
  StringRef TrimmedContent = Content[LineIndex].ltrim(Blanks);
  if (SplitBefore.first != StringRef::npos) {
    // 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);
    // Check if we need to also insert a break at the whitespace range.
    // For this we first adapt the reflow split relative to the beginning of the
    // content.
    // Note that we don't need a penalty for this break, since it doesn't change
    // the total number of lines.
    Split BreakSplit = SplitBefore;
    BreakSplit.first += TrimmedContent.data() - Content[LineIndex].data();
    unsigned ReflownColumn =
        getReflownColumn(TrimmedContent, LineIndex, PreviousEndColumn);
    if (ReflownColumn > ColumnLimit) {
      insertBreak(LineIndex, 0, BreakSplit, 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 (!Decoration.empty()) {
      // 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());
}

bool BreakableBlockComment::mayReflow(unsigned LineIndex,
                                      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]) && !Tok.Finalized &&
         !switchesFormatting(tokenAt(LineIndex));
}

unsigned
BreakableBlockComment::getContentStartColumn(unsigned LineIndex,
                                             unsigned TailOffset) const {
  // If we break, we always break at the predefined indent.
  if (TailOffset != 0)
    return IndentAtLineBreak;
  return std::max(0, ContentColumn[LineIndex]);
}

BreakableLineCommentSection::BreakableLineCommentSection(
    const FormatToken &Token, unsigned StartColumn,
    unsigned OriginalStartColumn, bool FirstInLine, 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;
  for (const FormatToken *CurrentTok = &Tok;
       CurrentTok && CurrentTok->is(TT_LineComment);
       CurrentTok = CurrentTok->Next) {
    LastLineTok = LineTok;
    StringRef TokenText(CurrentTok->TokenText);
    assert(TokenText.startswith("//"));
    size_t FirstLineIndex = Lines.size();
    TokenText.split(Lines, "\n");
    Content.resize(Lines.size());
    ContentColumn.resize(Lines.size());
    OriginalContentColumn.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; ++i) {
      // We need to trim the blanks in case this is not the first line in a
      // multiline comment. Then the indent is included in Lines[i].
      StringRef IndentPrefix =
          getLineCommentIndentPrefix(Lines[i].ltrim(Blanks));
      assert(IndentPrefix.startswith("//"));
      OriginalPrefix[i] = Prefix[i] = IndentPrefix;
      if (Lines[i].size() > Prefix[i].size() &&
          isAlphanumeric(Lines[i][Prefix[i].size()])) {
        if (Prefix[i] == "//")
          Prefix[i] = "// ";
        else if (Prefix[i] == "///")
          Prefix[i] = "/// ";
        else if (Prefix[i] == "//!")
          Prefix[i] = "//! ";
        else if (Prefix[i] == "///<")
          Prefix[i] = "///< ";
        else if (Prefix[i] == "//!<")
          Prefix[i] = "//!< ";
      }

      Tokens[i] = LineTok;
      Content[i] = Lines[i].substr(IndentPrefix.size());
      OriginalContentColumn[i] =
          StartColumn +
          encoding::columnWidthWithTabs(OriginalPrefix[i],
                                        StartColumn,
                                        Style.TabWidth,
                                        Encoding);
      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->ContinuesLineCommentSection) {
      // 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;
    }
  }
}

unsigned BreakableLineCommentSection::getLineLengthAfterSplit(
    unsigned LineIndex, unsigned TailOffset,
    StringRef::size_type Length) const {
  unsigned ContentStartColumn =
      (TailOffset == 0 ? ContentColumn[LineIndex]
                       : OriginalContentColumn[LineIndex]);
  return ContentStartColumn + encoding::columnWidthWithTabs(
                                  Content[LineIndex].substr(TailOffset, Length),
                                  ContentStartColumn, Style.TabWidth, Encoding);
}

void BreakableLineCommentSection::insertBreak(unsigned LineIndex,
                                              unsigned TailOffset, Split Split,
                                              WhitespaceManager &Whitespaces) {
  StringRef Text = Content[LineIndex].substr(TailOffset);
  // Compute the offset of the split relative to the beginning of the token
  // text.
  unsigned BreakOffsetInToken =
      Text.data() - tokenAt(LineIndex).TokenText.data() + Split.first;
  unsigned CharsToRemove = Split.second;
  // Compute the size of the new indent, including the size of the new prefix of
  // the newly broken line.
  unsigned IndentAtLineBreak = OriginalContentColumn[LineIndex] +
                               Prefix[LineIndex].size() -
                               OriginalPrefix[LineIndex].size();
  assert(IndentAtLineBreak >= Prefix[LineIndex].size());
  Whitespaces.replaceWhitespaceInToken(
      tokenAt(LineIndex), BreakOffsetInToken, CharsToRemove, "",
      Prefix[LineIndex], InPPDirective, /*Newlines=*/1,
      /*Spaces=*/IndentAtLineBreak - Prefix[LineIndex].size());
}

BreakableComment::Split BreakableLineCommentSection::getSplitBefore(
    unsigned LineIndex, unsigned PreviousEndColumn, unsigned ColumnLimit,
    llvm::Regex &CommentPragmasRegex) const {
  if (!mayReflow(LineIndex, CommentPragmasRegex))
    return Split(StringRef::npos, 0);
  return getReflowSplit(Content[LineIndex], ReflowPrefix, PreviousEndColumn,
                        ColumnLimit);
}

unsigned BreakableLineCommentSection::getLineLengthAfterSplitBefore(
    unsigned LineIndex, unsigned TailOffset,
    unsigned PreviousEndColumn,
    unsigned ColumnLimit,
    Split SplitBefore) const {
  if (SplitBefore.first == StringRef::npos ||
      SplitBefore.first + SplitBefore.second < Content[LineIndex].size()) {
    // A piece of line, not the whole line, gets reflown.
    return getLineLengthAfterSplit(LineIndex, TailOffset, StringRef::npos);
  } else {
    // The whole line gets reflown.
    unsigned StartColumn = PreviousEndColumn + ReflowPrefix.size();
    return StartColumn + encoding::columnWidthWithTabs(Content[LineIndex],
                                                       StartColumn,
                                                       Style.TabWidth,
                                                       Encoding);
  }
}

void BreakableLineCommentSection::replaceWhitespaceBefore(
    unsigned LineIndex, unsigned PreviousEndColumn, unsigned ColumnLimit,
    Split SplitBefore, WhitespaceManager &Whitespaces) {
  // If this is the first line of a token, we need to inform Whitespace Manager
  // about it: either adapt the whitespace range preceding it, or mark it as an
  // untouchable token.
  // This happens for instance here:
  // // line 1 \
  // // line 2
  if (LineIndex > 0 && Tokens[LineIndex] != Tokens[LineIndex - 1]) {
    if (SplitBefore.first != StringRef::npos) {
      // 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);
      // Replace the indent and prefix of the token with the reflow prefix.
      unsigned WhitespaceLength =
          Content[LineIndex].data() - tokenAt(LineIndex).TokenText.data();
      Whitespaces.replaceWhitespaceInToken(*Tokens[LineIndex],
                                           /*Offset=*/0,
                                           /*ReplaceChars=*/WhitespaceLength,
                                           /*PreviousPostfix=*/"",
                                           /*CurrentPrefix=*/ReflowPrefix,
                                           /*InPPDirective=*/false,
                                           /*Newlines=*/0,
                                           /*Spaces=*/0);
    } else {
      // This is the first line for the current token, but no reflow with the
      // previous token is necessary. However, we still may need to adjust the
      // start column. Note that ContentColumn[LineIndex] is the expected
      // content column after a possible update to the prefix, hence the prefix
      // length change is included.
      unsigned LineColumn =
          ContentColumn[LineIndex] -
          (Content[LineIndex].data() - Lines[LineIndex].data()) +
          (OriginalPrefix[LineIndex].size() - Prefix[LineIndex].size());

      // We always want to create a replacement instead of adding an untouchable
      // token, even if LineColumn is the same as the original column of the
      // token. This is because WhitespaceManager doesn't align trailing
      // comments if they are untouchable.
      Whitespaces.replaceWhitespace(*Tokens[LineIndex],
                                    /*Newlines=*/1,
                                    /*Spaces=*/LineColumn,
                                    /*StartOfTokenColumn=*/LineColumn,
                                    /*InPPDirective=*/false);
    }
  }
  if (OriginalPrefix[LineIndex] != Prefix[LineIndex]) {
    // Adjust the prefix if necessary.

    // Take care of the space possibly introduced after a decoration.
    assert(Prefix[LineIndex] == (OriginalPrefix[LineIndex] + " ").str() &&
           "Expecting a line comment prefix to differ from original by at most "
           "a space");
    Whitespaces.replaceWhitespaceInToken(
        tokenAt(LineIndex), OriginalPrefix[LineIndex].size(), 0, "", "",
        /*InPPDirective=*/false, /*Newlines=*/0, /*Spaces=*/1);
  }
  // Add a break after a reflow split has been introduced, if necessary.
  // Note that this break doesn't need to be penalized, since it doesn't change
  // the number of lines.
  if (SplitBefore.first != StringRef::npos &&
      SplitBefore.first + SplitBefore.second < Content[LineIndex].size()) {
    insertBreak(LineIndex, 0, SplitBefore, Whitespaces);
  }
}

void BreakableLineCommentSection::updateNextToken(LineState& State) const {
  if (LastLineTok) {
    State.NextToken = LastLineTok->Next;
  }
}

bool BreakableLineCommentSection::mayReflow(
    unsigned LineIndex, llvm::Regex &CommentPragmasRegex) const {
  // Line comments have the indent as part of the prefix, so we need to
  // recompute the start of the line.
  StringRef IndentContent = Content[LineIndex];
  if (Lines[LineIndex].startswith("//")) {
    IndentContent = Lines[LineIndex].substr(2);
  }
  return LineIndex > 0 && !CommentPragmasRegex.match(IndentContent) &&
         mayReflowContent(Content[LineIndex]) && !Tok.Finalized &&
         !switchesFormatting(tokenAt(LineIndex)) &&
         OriginalPrefix[LineIndex] == OriginalPrefix[LineIndex - 1];
}

unsigned
BreakableLineCommentSection::getContentStartColumn(unsigned LineIndex,
                                                   unsigned TailOffset) const {
  if (TailOffset != 0) {
    return OriginalContentColumn[LineIndex];
  }
  return ContentColumn[LineIndex];
}

} // namespace format
} // namespace clang