aboutsummaryrefslogtreecommitdiffstats
path: root/lib/AST/RawCommentList.cpp
blob: df53b7fa10047ad64a309a9552ce58ca3fd3541f (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
//===--- RawCommentList.cpp - Processing raw comments -----------*- C++ -*-===//
//
// 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
//
//===----------------------------------------------------------------------===//

#include "clang/AST/RawCommentList.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/Comment.h"
#include "clang/AST/CommentBriefParser.h"
#include "clang/AST/CommentCommandTraits.h"
#include "clang/AST/CommentLexer.h"
#include "clang/AST/CommentParser.h"
#include "clang/AST/CommentSema.h"
#include "clang/Basic/CharInfo.h"
#include "llvm/ADT/STLExtras.h"

using namespace clang;

namespace {
/// Get comment kind and bool describing if it is a trailing comment.
std::pair<RawComment::CommentKind, bool> getCommentKind(StringRef Comment,
                                                        bool ParseAllComments) {
  const size_t MinCommentLength = ParseAllComments ? 2 : 3;
  if ((Comment.size() < MinCommentLength) || Comment[0] != '/')
    return std::make_pair(RawComment::RCK_Invalid, false);

  RawComment::CommentKind K;
  if (Comment[1] == '/') {
    if (Comment.size() < 3)
      return std::make_pair(RawComment::RCK_OrdinaryBCPL, false);

    if (Comment[2] == '/')
      K = RawComment::RCK_BCPLSlash;
    else if (Comment[2] == '!')
      K = RawComment::RCK_BCPLExcl;
    else
      return std::make_pair(RawComment::RCK_OrdinaryBCPL, false);
  } else {
    assert(Comment.size() >= 4);

    // Comment lexer does not understand escapes in comment markers, so pretend
    // that this is not a comment.
    if (Comment[1] != '*' ||
        Comment[Comment.size() - 2] != '*' ||
        Comment[Comment.size() - 1] != '/')
      return std::make_pair(RawComment::RCK_Invalid, false);

    if (Comment[2] == '*')
      K = RawComment::RCK_JavaDoc;
    else if (Comment[2] == '!')
      K = RawComment::RCK_Qt;
    else
      return std::make_pair(RawComment::RCK_OrdinaryC, false);
  }
  const bool TrailingComment = (Comment.size() > 3) && (Comment[3] == '<');
  return std::make_pair(K, TrailingComment);
}

bool mergedCommentIsTrailingComment(StringRef Comment) {
  return (Comment.size() > 3) && (Comment[3] == '<');
}

/// Returns true if R1 and R2 both have valid locations that start on the same
/// column.
bool commentsStartOnSameColumn(const SourceManager &SM, const RawComment &R1,
                               const RawComment &R2) {
  SourceLocation L1 = R1.getBeginLoc();
  SourceLocation L2 = R2.getBeginLoc();
  bool Invalid = false;
  unsigned C1 = SM.getPresumedColumnNumber(L1, &Invalid);
  if (!Invalid) {
    unsigned C2 = SM.getPresumedColumnNumber(L2, &Invalid);
    return !Invalid && (C1 == C2);
  }
  return false;
}
} // unnamed namespace

/// Determines whether there is only whitespace in `Buffer` between `P`
/// and the previous line.
/// \param Buffer The buffer to search in.
/// \param P The offset from the beginning of `Buffer` to start from.
/// \return true if all of the characters in `Buffer` ranging from the closest
/// line-ending character before `P` (or the beginning of `Buffer`) to `P - 1`
/// are whitespace.
static bool onlyWhitespaceOnLineBefore(const char *Buffer, unsigned P) {
  // Search backwards until we see linefeed or carriage return.
  for (unsigned I = P; I != 0; --I) {
    char C = Buffer[I - 1];
    if (isVerticalWhitespace(C))
      return true;
    if (!isHorizontalWhitespace(C))
      return false;
  }
  // We hit the beginning of the buffer.
  return true;
}

/// Returns whether `K` is an ordinary comment kind.
static bool isOrdinaryKind(RawComment::CommentKind K) {
  return (K == RawComment::RCK_OrdinaryBCPL) ||
         (K == RawComment::RCK_OrdinaryC);
}

RawComment::RawComment(const SourceManager &SourceMgr, SourceRange SR,
                       const CommentOptions &CommentOpts, bool Merged) :
    Range(SR), RawTextValid(false), BriefTextValid(false),
    IsAttached(false), IsTrailingComment(false),
    IsAlmostTrailingComment(false) {
  // Extract raw comment text, if possible.
  if (SR.getBegin() == SR.getEnd() || getRawText(SourceMgr).empty()) {
    Kind = RCK_Invalid;
    return;
  }

  // Guess comment kind.
  std::pair<CommentKind, bool> K =
      getCommentKind(RawText, CommentOpts.ParseAllComments);

  // Guess whether an ordinary comment is trailing.
  if (CommentOpts.ParseAllComments && isOrdinaryKind(K.first)) {
    FileID BeginFileID;
    unsigned BeginOffset;
    std::tie(BeginFileID, BeginOffset) =
        SourceMgr.getDecomposedLoc(Range.getBegin());
    if (BeginOffset != 0) {
      bool Invalid = false;
      const char *Buffer =
          SourceMgr.getBufferData(BeginFileID, &Invalid).data();
      IsTrailingComment |=
          (!Invalid && !onlyWhitespaceOnLineBefore(Buffer, BeginOffset));
    }
  }

  if (!Merged) {
    Kind = K.first;
    IsTrailingComment |= K.second;

    IsAlmostTrailingComment = RawText.startswith("//<") ||
                                 RawText.startswith("/*<");
  } else {
    Kind = RCK_Merged;
    IsTrailingComment =
        IsTrailingComment || mergedCommentIsTrailingComment(RawText);
  }
}

StringRef RawComment::getRawTextSlow(const SourceManager &SourceMgr) const {
  FileID BeginFileID;
  FileID EndFileID;
  unsigned BeginOffset;
  unsigned EndOffset;

  std::tie(BeginFileID, BeginOffset) =
      SourceMgr.getDecomposedLoc(Range.getBegin());
  std::tie(EndFileID, EndOffset) = SourceMgr.getDecomposedLoc(Range.getEnd());

  const unsigned Length = EndOffset - BeginOffset;
  if (Length < 2)
    return StringRef();

  // The comment can't begin in one file and end in another.
  assert(BeginFileID == EndFileID);

  bool Invalid = false;
  const char *BufferStart = SourceMgr.getBufferData(BeginFileID,
                                                    &Invalid).data();
  if (Invalid)
    return StringRef();

  return StringRef(BufferStart + BeginOffset, Length);
}

const char *RawComment::extractBriefText(const ASTContext &Context) const {
  // Lazily initialize RawText using the accessor before using it.
  (void)getRawText(Context.getSourceManager());

  // Since we will be copying the resulting text, all allocations made during
  // parsing are garbage after resulting string is formed.  Thus we can use
  // a separate allocator for all temporary stuff.
  llvm::BumpPtrAllocator Allocator;

  comments::Lexer L(Allocator, Context.getDiagnostics(),
                    Context.getCommentCommandTraits(),
                    Range.getBegin(),
                    RawText.begin(), RawText.end());
  comments::BriefParser P(L, Context.getCommentCommandTraits());

  const std::string Result = P.Parse();
  const unsigned BriefTextLength = Result.size();
  char *BriefTextPtr = new (Context) char[BriefTextLength + 1];
  memcpy(BriefTextPtr, Result.c_str(), BriefTextLength + 1);
  BriefText = BriefTextPtr;
  BriefTextValid = true;

  return BriefTextPtr;
}

comments::FullComment *RawComment::parse(const ASTContext &Context,
                                         const Preprocessor *PP,
                                         const Decl *D) const {
  // Lazily initialize RawText using the accessor before using it.
  (void)getRawText(Context.getSourceManager());

  comments::Lexer L(Context.getAllocator(), Context.getDiagnostics(),
                    Context.getCommentCommandTraits(),
                    getSourceRange().getBegin(),
                    RawText.begin(), RawText.end());
  comments::Sema S(Context.getAllocator(), Context.getSourceManager(),
                   Context.getDiagnostics(),
                   Context.getCommentCommandTraits(),
                   PP);
  S.setDecl(D);
  comments::Parser P(L, S, Context.getAllocator(), Context.getSourceManager(),
                     Context.getDiagnostics(),
                     Context.getCommentCommandTraits());

  return P.parseFullComment();
}

static bool onlyWhitespaceBetween(SourceManager &SM,
                                  SourceLocation Loc1, SourceLocation Loc2,
                                  unsigned MaxNewlinesAllowed) {
  std::pair<FileID, unsigned> Loc1Info = SM.getDecomposedLoc(Loc1);
  std::pair<FileID, unsigned> Loc2Info = SM.getDecomposedLoc(Loc2);

  // Question does not make sense if locations are in different files.
  if (Loc1Info.first != Loc2Info.first)
    return false;

  bool Invalid = false;
  const char *Buffer = SM.getBufferData(Loc1Info.first, &Invalid).data();
  if (Invalid)
    return false;

  unsigned NumNewlines = 0;
  assert(Loc1Info.second <= Loc2Info.second && "Loc1 after Loc2!");
  // Look for non-whitespace characters and remember any newlines seen.
  for (unsigned I = Loc1Info.second; I != Loc2Info.second; ++I) {
    switch (Buffer[I]) {
    default:
      return false;
    case ' ':
    case '\t':
    case '\f':
    case '\v':
      break;
    case '\r':
    case '\n':
      ++NumNewlines;

      // Check if we have found more than the maximum allowed number of
      // newlines.
      if (NumNewlines > MaxNewlinesAllowed)
        return false;

      // Collapse \r\n and \n\r into a single newline.
      if (I + 1 != Loc2Info.second &&
          (Buffer[I + 1] == '\n' || Buffer[I + 1] == '\r') &&
          Buffer[I] != Buffer[I + 1])
        ++I;
      break;
    }
  }

  return true;
}

void RawCommentList::addComment(const RawComment &RC,
                                const CommentOptions &CommentOpts,
                                llvm::BumpPtrAllocator &Allocator) {
  if (RC.isInvalid())
    return;

  // Check if the comments are not in source order.
  while (!Comments.empty() &&
         !SourceMgr.isBeforeInTranslationUnit(Comments.back()->getBeginLoc(),
                                              RC.getBeginLoc())) {
    // If they are, just pop a few last comments that don't fit.
    // This happens if an \#include directive contains comments.
    Comments.pop_back();
  }

  // Ordinary comments are not interesting for us.
  if (RC.isOrdinary() && !CommentOpts.ParseAllComments)
    return;

  // If this is the first Doxygen comment, save it (because there isn't
  // anything to merge it with).
  if (Comments.empty()) {
    Comments.push_back(new (Allocator) RawComment(RC));
    return;
  }

  const RawComment &C1 = *Comments.back();
  const RawComment &C2 = RC;

  // Merge comments only if there is only whitespace between them.
  // Can't merge trailing and non-trailing comments unless the second is
  // non-trailing ordinary in the same column, as in the case:
  //   int x; // documents x
  //          // more text
  // versus:
  //   int x; // documents x
  //   int y; // documents y
  // or:
  //   int x; // documents x
  //   // documents y
  //   int y;
  // Merge comments if they are on same or consecutive lines.
  if ((C1.isTrailingComment() == C2.isTrailingComment() ||
       (C1.isTrailingComment() && !C2.isTrailingComment() &&
        isOrdinaryKind(C2.getKind()) &&
        commentsStartOnSameColumn(SourceMgr, C1, C2))) &&
      onlyWhitespaceBetween(SourceMgr, C1.getEndLoc(), C2.getBeginLoc(),
                            /*MaxNewlinesAllowed=*/1)) {
    SourceRange MergedRange(C1.getBeginLoc(), C2.getEndLoc());
    *Comments.back() = RawComment(SourceMgr, MergedRange, CommentOpts, true);
  } else {
    Comments.push_back(new (Allocator) RawComment(RC));
  }
}

void RawCommentList::addDeserializedComments(ArrayRef<RawComment *> DeserializedComments) {
  std::vector<RawComment *> MergedComments;
  MergedComments.reserve(Comments.size() + DeserializedComments.size());

  std::merge(Comments.begin(), Comments.end(),
             DeserializedComments.begin(), DeserializedComments.end(),
             std::back_inserter(MergedComments),
             BeforeThanCompare<RawComment>(SourceMgr));
  std::swap(Comments, MergedComments);
}

std::string RawComment::getFormattedText(const SourceManager &SourceMgr,
                                         DiagnosticsEngine &Diags) const {
  llvm::StringRef CommentText = getRawText(SourceMgr);
  if (CommentText.empty())
    return "";

  llvm::BumpPtrAllocator Allocator;
  // We do not parse any commands, so CommentOptions are ignored by
  // comments::Lexer. Therefore, we just use default-constructed options.
  CommentOptions DefOpts;
  comments::CommandTraits EmptyTraits(Allocator, DefOpts);
  comments::Lexer L(Allocator, Diags, EmptyTraits, getSourceRange().getBegin(),
                    CommentText.begin(), CommentText.end(),
                    /*ParseCommands=*/false);

  std::string Result;
  // A column number of the first non-whitespace token in the comment text.
  // We skip whitespace up to this column, but keep the whitespace after this
  // column. IndentColumn is calculated when lexing the first line and reused
  // for the rest of lines.
  unsigned IndentColumn = 0;

  // Processes one line of the comment and adds it to the result.
  // Handles skipping the indent at the start of the line.
  // Returns false when eof is reached and true otherwise.
  auto LexLine = [&](bool IsFirstLine) -> bool {
    comments::Token Tok;
    // Lex the first token on the line. We handle it separately, because we to
    // fix up its indentation.
    L.lex(Tok);
    if (Tok.is(comments::tok::eof))
      return false;
    if (Tok.is(comments::tok::newline)) {
      Result += "\n";
      return true;
    }
    llvm::StringRef TokText = L.getSpelling(Tok, SourceMgr);
    bool LocInvalid = false;
    unsigned TokColumn =
        SourceMgr.getSpellingColumnNumber(Tok.getLocation(), &LocInvalid);
    assert(!LocInvalid && "getFormattedText for invalid location");

    // Amount of leading whitespace in TokText.
    size_t WhitespaceLen = TokText.find_first_not_of(" \t");
    if (WhitespaceLen == StringRef::npos)
      WhitespaceLen = TokText.size();
    // Remember the amount of whitespace we skipped in the first line to remove
    // indent up to that column in the following lines.
    if (IsFirstLine)
      IndentColumn = TokColumn + WhitespaceLen;

    // Amount of leading whitespace we actually want to skip.
    // For the first line we skip all the whitespace.
    // For the rest of the lines, we skip whitespace up to IndentColumn.
    unsigned SkipLen =
        IsFirstLine
            ? WhitespaceLen
            : std::min<size_t>(
                  WhitespaceLen,
                  std::max<int>(static_cast<int>(IndentColumn) - TokColumn, 0));
    llvm::StringRef Trimmed = TokText.drop_front(SkipLen);
    Result += Trimmed;
    // Lex all tokens in the rest of the line.
    for (L.lex(Tok); Tok.isNot(comments::tok::eof); L.lex(Tok)) {
      if (Tok.is(comments::tok::newline)) {
        Result += "\n";
        return true;
      }
      Result += L.getSpelling(Tok, SourceMgr);
    }
    // We've reached the end of file token.
    return false;
  };

  auto DropTrailingNewLines = [](std::string &Str) {
    while (Str.back() == '\n')
      Str.pop_back();
  };

  // Process first line separately to remember indent for the following lines.
  if (!LexLine(/*IsFirstLine=*/true)) {
    DropTrailingNewLines(Result);
    return Result;
  }
  // Process the rest of the lines.
  while (LexLine(/*IsFirstLine=*/false))
    ;
  DropTrailingNewLines(Result);
  return Result;
}