Coverage Report

Created: 2024-01-17 10:31

/src/llvm-project/clang/lib/Frontend/TextDiagnostic.cpp
Line
Count
Source (jump to first uncovered line)
1
//===--- TextDiagnostic.cpp - Text Diagnostic Pretty-Printing -------------===//
2
//
3
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4
// See https://llvm.org/LICENSE.txt for license information.
5
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6
//
7
//===----------------------------------------------------------------------===//
8
9
#include "clang/Frontend/TextDiagnostic.h"
10
#include "clang/Basic/CharInfo.h"
11
#include "clang/Basic/DiagnosticOptions.h"
12
#include "clang/Basic/FileManager.h"
13
#include "clang/Basic/SourceManager.h"
14
#include "clang/Lex/Lexer.h"
15
#include "llvm/ADT/SmallString.h"
16
#include "llvm/ADT/StringExtras.h"
17
#include "llvm/Support/ConvertUTF.h"
18
#include "llvm/Support/ErrorHandling.h"
19
#include "llvm/Support/Locale.h"
20
#include "llvm/Support/Path.h"
21
#include "llvm/Support/raw_ostream.h"
22
#include <algorithm>
23
#include <optional>
24
25
using namespace clang;
26
27
static const enum raw_ostream::Colors noteColor = raw_ostream::CYAN;
28
static const enum raw_ostream::Colors remarkColor =
29
  raw_ostream::BLUE;
30
static const enum raw_ostream::Colors fixitColor =
31
  raw_ostream::GREEN;
32
static const enum raw_ostream::Colors caretColor =
33
  raw_ostream::GREEN;
34
static const enum raw_ostream::Colors warningColor =
35
  raw_ostream::MAGENTA;
36
static const enum raw_ostream::Colors templateColor =
37
  raw_ostream::CYAN;
38
static const enum raw_ostream::Colors errorColor = raw_ostream::RED;
39
static const enum raw_ostream::Colors fatalColor = raw_ostream::RED;
40
// Used for changing only the bold attribute.
41
static const enum raw_ostream::Colors savedColor =
42
  raw_ostream::SAVEDCOLOR;
43
44
/// Add highlights to differences in template strings.
45
static void applyTemplateHighlighting(raw_ostream &OS, StringRef Str,
46
0
                                      bool &Normal, bool Bold) {
47
0
  while (true) {
48
0
    size_t Pos = Str.find(ToggleHighlight);
49
0
    OS << Str.slice(0, Pos);
50
0
    if (Pos == StringRef::npos)
51
0
      break;
52
53
0
    Str = Str.substr(Pos + 1);
54
0
    if (Normal)
55
0
      OS.changeColor(templateColor, true);
56
0
    else {
57
0
      OS.resetColor();
58
0
      if (Bold)
59
0
        OS.changeColor(savedColor, true);
60
0
    }
61
0
    Normal = !Normal;
62
0
  }
63
0
}
64
65
/// Number of spaces to indent when word-wrapping.
66
const unsigned WordWrapIndentation = 6;
67
68
0
static int bytesSincePreviousTabOrLineBegin(StringRef SourceLine, size_t i) {
69
0
  int bytes = 0;
70
0
  while (0<i) {
71
0
    if (SourceLine[--i]=='\t')
72
0
      break;
73
0
    ++bytes;
74
0
  }
75
0
  return bytes;
76
0
}
77
78
/// returns a printable representation of first item from input range
79
///
80
/// This function returns a printable representation of the next item in a line
81
///  of source. If the next byte begins a valid and printable character, that
82
///  character is returned along with 'true'.
83
///
84
/// Otherwise, if the next byte begins a valid, but unprintable character, a
85
///  printable, escaped representation of the character is returned, along with
86
///  'false'. Otherwise a printable, escaped representation of the next byte
87
///  is returned along with 'false'.
88
///
89
/// \note The index is updated to be used with a subsequent call to
90
///        printableTextForNextCharacter.
91
///
92
/// \param SourceLine The line of source
93
/// \param I Pointer to byte index,
94
/// \param TabStop used to expand tabs
95
/// \return pair(printable text, 'true' iff original text was printable)
96
///
97
static std::pair<SmallString<16>, bool>
98
printableTextForNextCharacter(StringRef SourceLine, size_t *I,
99
0
                              unsigned TabStop) {
100
0
  assert(I && "I must not be null");
101
0
  assert(*I < SourceLine.size() && "must point to a valid index");
102
103
0
  if (SourceLine[*I] == '\t') {
104
0
    assert(0 < TabStop && TabStop <= DiagnosticOptions::MaxTabStop &&
105
0
           "Invalid -ftabstop value");
106
0
    unsigned Col = bytesSincePreviousTabOrLineBegin(SourceLine, *I);
107
0
    unsigned NumSpaces = TabStop - (Col % TabStop);
108
0
    assert(0 < NumSpaces && NumSpaces <= TabStop
109
0
           && "Invalid computation of space amt");
110
0
    ++(*I);
111
112
0
    SmallString<16> ExpandedTab;
113
0
    ExpandedTab.assign(NumSpaces, ' ');
114
0
    return std::make_pair(ExpandedTab, true);
115
0
  }
116
117
0
  const unsigned char *Begin = SourceLine.bytes_begin() + *I;
118
119
  // Fast path for the common ASCII case.
120
0
  if (*Begin < 0x80 && llvm::sys::locale::isPrint(*Begin)) {
121
0
    ++(*I);
122
0
    return std::make_pair(SmallString<16>(Begin, Begin + 1), true);
123
0
  }
124
0
  unsigned CharSize = llvm::getNumBytesForUTF8(*Begin);
125
0
  const unsigned char *End = Begin + CharSize;
126
127
  // Convert it to UTF32 and check if it's printable.
128
0
  if (End <= SourceLine.bytes_end() && llvm::isLegalUTF8Sequence(Begin, End)) {
129
0
    llvm::UTF32 C;
130
0
    llvm::UTF32 *CPtr = &C;
131
132
    // Begin and end before conversion.
133
0
    unsigned char const *OriginalBegin = Begin;
134
0
    llvm::ConversionResult Res = llvm::ConvertUTF8toUTF32(
135
0
        &Begin, End, &CPtr, CPtr + 1, llvm::strictConversion);
136
0
    (void)Res;
137
0
    assert(Res == llvm::conversionOK);
138
0
    assert(OriginalBegin < Begin);
139
0
    assert((Begin - OriginalBegin) == CharSize);
140
141
0
    (*I) += (Begin - OriginalBegin);
142
143
    // Valid, multi-byte, printable UTF8 character.
144
0
    if (llvm::sys::locale::isPrint(C))
145
0
      return std::make_pair(SmallString<16>(OriginalBegin, End), true);
146
147
    // Valid but not printable.
148
0
    SmallString<16> Str("<U+>");
149
0
    while (C) {
150
0
      Str.insert(Str.begin() + 3, llvm::hexdigit(C % 16));
151
0
      C /= 16;
152
0
    }
153
0
    while (Str.size() < 8)
154
0
      Str.insert(Str.begin() + 3, llvm::hexdigit(0));
155
0
    return std::make_pair(Str, false);
156
0
  }
157
158
  // Otherwise, not printable since it's not valid UTF8.
159
0
  SmallString<16> ExpandedByte("<XX>");
160
0
  unsigned char Byte = SourceLine[*I];
161
0
  ExpandedByte[1] = llvm::hexdigit(Byte / 16);
162
0
  ExpandedByte[2] = llvm::hexdigit(Byte % 16);
163
0
  ++(*I);
164
0
  return std::make_pair(ExpandedByte, false);
165
0
}
166
167
0
static void expandTabs(std::string &SourceLine, unsigned TabStop) {
168
0
  size_t I = SourceLine.size();
169
0
  while (I > 0) {
170
0
    I--;
171
0
    if (SourceLine[I] != '\t')
172
0
      continue;
173
0
    size_t TmpI = I;
174
0
    auto [Str, Printable] =
175
0
        printableTextForNextCharacter(SourceLine, &TmpI, TabStop);
176
0
    SourceLine.replace(I, 1, Str.c_str());
177
0
  }
178
0
}
179
180
/// \p BytesOut:
181
///  A mapping from columns to the byte of the source line that produced the
182
///  character displaying at that column. This is the inverse of \p ColumnsOut.
183
///
184
/// The last element in the array is the number of bytes in the source string.
185
///
186
/// example: (given a tabstop of 8)
187
///
188
///    "a \t \u3042" -> {0,1,2,-1,-1,-1,-1,-1,3,4,-1,7}
189
///
190
///  (\\u3042 is represented in UTF-8 by three bytes and takes two columns to
191
///   display)
192
///
193
/// \p ColumnsOut:
194
///  A mapping from the bytes
195
///  of the printable representation of the line to the columns those printable
196
///  characters will appear at (numbering the first column as 0).
197
///
198
/// If a byte 'i' corresponds to multiple columns (e.g. the byte contains a tab
199
///  character) then the array will map that byte to the first column the
200
///  tab appears at and the next value in the map will have been incremented
201
///  more than once.
202
///
203
/// If a byte is the first in a sequence of bytes that together map to a single
204
///  entity in the output, then the array will map that byte to the appropriate
205
///  column while the subsequent bytes will be -1.
206
///
207
/// The last element in the array does not correspond to any byte in the input
208
///  and instead is the number of columns needed to display the source
209
///
210
/// example: (given a tabstop of 8)
211
///
212
///    "a \t \u3042" -> {0,1,2,8,9,-1,-1,11}
213
///
214
///  (\\u3042 is represented in UTF-8 by three bytes and takes two columns to
215
///   display)
216
static void genColumnByteMapping(StringRef SourceLine, unsigned TabStop,
217
                                 SmallVectorImpl<int> &BytesOut,
218
0
                                 SmallVectorImpl<int> &ColumnsOut) {
219
0
  assert(BytesOut.empty());
220
0
  assert(ColumnsOut.empty());
221
222
0
  if (SourceLine.empty()) {
223
0
    BytesOut.resize(1u, 0);
224
0
    ColumnsOut.resize(1u, 0);
225
0
    return;
226
0
  }
227
228
0
  ColumnsOut.resize(SourceLine.size() + 1, -1);
229
230
0
  int Columns = 0;
231
0
  size_t I = 0;
232
0
  while (I < SourceLine.size()) {
233
0
    ColumnsOut[I] = Columns;
234
0
    BytesOut.resize(Columns + 1, -1);
235
0
    BytesOut.back() = I;
236
0
    auto [Str, Printable] =
237
0
        printableTextForNextCharacter(SourceLine, &I, TabStop);
238
0
    Columns += llvm::sys::locale::columnWidth(Str);
239
0
  }
240
241
0
  ColumnsOut.back() = Columns;
242
0
  BytesOut.resize(Columns + 1, -1);
243
0
  BytesOut.back() = I;
244
0
}
245
246
namespace {
247
struct SourceColumnMap {
248
  SourceColumnMap(StringRef SourceLine, unsigned TabStop)
249
0
  : m_SourceLine(SourceLine) {
250
251
0
    genColumnByteMapping(SourceLine, TabStop, m_columnToByte, m_byteToColumn);
252
253
0
    assert(m_byteToColumn.size()==SourceLine.size()+1);
254
0
    assert(0 < m_byteToColumn.size() && 0 < m_columnToByte.size());
255
0
    assert(m_byteToColumn.size()
256
0
           == static_cast<unsigned>(m_columnToByte.back()+1));
257
0
    assert(static_cast<unsigned>(m_byteToColumn.back()+1)
258
0
           == m_columnToByte.size());
259
0
  }
260
0
  int columns() const { return m_byteToColumn.back(); }
261
0
  int bytes() const { return m_columnToByte.back(); }
262
263
  /// Map a byte to the column which it is at the start of, or return -1
264
  /// if it is not at the start of a column (for a UTF-8 trailing byte).
265
0
  int byteToColumn(int n) const {
266
0
    assert(0<=n && n<static_cast<int>(m_byteToColumn.size()));
267
0
    return m_byteToColumn[n];
268
0
  }
269
270
  /// Map a byte to the first column which contains it.
271
0
  int byteToContainingColumn(int N) const {
272
0
    assert(0 <= N && N < static_cast<int>(m_byteToColumn.size()));
273
0
    while (m_byteToColumn[N] == -1)
274
0
      --N;
275
0
    return m_byteToColumn[N];
276
0
  }
277
278
  /// Map a column to the byte which starts the column, or return -1 if
279
  /// the column the second or subsequent column of an expanded tab or similar
280
  /// multi-column entity.
281
0
  int columnToByte(int n) const {
282
0
    assert(0<=n && n<static_cast<int>(m_columnToByte.size()));
283
0
    return m_columnToByte[n];
284
0
  }
285
286
  /// Map from a byte index to the next byte which starts a column.
287
0
  int startOfNextColumn(int N) const {
288
0
    assert(0 <= N && N < static_cast<int>(m_byteToColumn.size() - 1));
289
0
    while (byteToColumn(++N) == -1) {}
290
0
    return N;
291
0
  }
292
293
  /// Map from a byte index to the previous byte which starts a column.
294
0
  int startOfPreviousColumn(int N) const {
295
0
    assert(0 < N && N < static_cast<int>(m_byteToColumn.size()));
296
0
    while (byteToColumn(--N) == -1) {}
297
0
    return N;
298
0
  }
299
300
0
  StringRef getSourceLine() const {
301
0
    return m_SourceLine;
302
0
  }
303
304
private:
305
  const std::string m_SourceLine;
306
  SmallVector<int,200> m_byteToColumn;
307
  SmallVector<int,200> m_columnToByte;
308
};
309
} // end anonymous namespace
310
311
/// When the source code line we want to print is too long for
312
/// the terminal, select the "interesting" region.
313
static void selectInterestingSourceRegion(std::string &SourceLine,
314
                                          std::string &CaretLine,
315
                                          std::string &FixItInsertionLine,
316
                                          unsigned Columns,
317
0
                                          const SourceColumnMap &map) {
318
0
  unsigned CaretColumns = CaretLine.size();
319
0
  unsigned FixItColumns = llvm::sys::locale::columnWidth(FixItInsertionLine);
320
0
  unsigned MaxColumns = std::max(static_cast<unsigned>(map.columns()),
321
0
                                 std::max(CaretColumns, FixItColumns));
322
  // if the number of columns is less than the desired number we're done
323
0
  if (MaxColumns <= Columns)
324
0
    return;
325
326
  // No special characters are allowed in CaretLine.
327
0
  assert(llvm::none_of(CaretLine, [](char c) { return c < ' ' || '~' < c; }));
328
329
  // Find the slice that we need to display the full caret line
330
  // correctly.
331
0
  unsigned CaretStart = 0, CaretEnd = CaretLine.size();
332
0
  for (; CaretStart != CaretEnd; ++CaretStart)
333
0
    if (!isWhitespace(CaretLine[CaretStart]))
334
0
      break;
335
336
0
  for (; CaretEnd != CaretStart; --CaretEnd)
337
0
    if (!isWhitespace(CaretLine[CaretEnd - 1]))
338
0
      break;
339
340
  // caret has already been inserted into CaretLine so the above whitespace
341
  // check is guaranteed to include the caret
342
343
  // If we have a fix-it line, make sure the slice includes all of the
344
  // fix-it information.
345
0
  if (!FixItInsertionLine.empty()) {
346
0
    unsigned FixItStart = 0, FixItEnd = FixItInsertionLine.size();
347
0
    for (; FixItStart != FixItEnd; ++FixItStart)
348
0
      if (!isWhitespace(FixItInsertionLine[FixItStart]))
349
0
        break;
350
351
0
    for (; FixItEnd != FixItStart; --FixItEnd)
352
0
      if (!isWhitespace(FixItInsertionLine[FixItEnd - 1]))
353
0
        break;
354
355
    // We can safely use the byte offset FixItStart as the column offset
356
    // because the characters up until FixItStart are all ASCII whitespace
357
    // characters.
358
0
    unsigned FixItStartCol = FixItStart;
359
0
    unsigned FixItEndCol
360
0
      = llvm::sys::locale::columnWidth(FixItInsertionLine.substr(0, FixItEnd));
361
362
0
    CaretStart = std::min(FixItStartCol, CaretStart);
363
0
    CaretEnd = std::max(FixItEndCol, CaretEnd);
364
0
  }
365
366
  // CaretEnd may have been set at the middle of a character
367
  // If it's not at a character's first column then advance it past the current
368
  //   character.
369
0
  while (static_cast<int>(CaretEnd) < map.columns() &&
370
0
         -1 == map.columnToByte(CaretEnd))
371
0
    ++CaretEnd;
372
373
0
  assert((static_cast<int>(CaretStart) > map.columns() ||
374
0
          -1!=map.columnToByte(CaretStart)) &&
375
0
         "CaretStart must not point to a column in the middle of a source"
376
0
         " line character");
377
0
  assert((static_cast<int>(CaretEnd) > map.columns() ||
378
0
          -1!=map.columnToByte(CaretEnd)) &&
379
0
         "CaretEnd must not point to a column in the middle of a source line"
380
0
         " character");
381
382
  // CaretLine[CaretStart, CaretEnd) contains all of the interesting
383
  // parts of the caret line. While this slice is smaller than the
384
  // number of columns we have, try to grow the slice to encompass
385
  // more context.
386
387
0
  unsigned SourceStart = map.columnToByte(std::min<unsigned>(CaretStart,
388
0
                                                             map.columns()));
389
0
  unsigned SourceEnd = map.columnToByte(std::min<unsigned>(CaretEnd,
390
0
                                                           map.columns()));
391
392
0
  unsigned CaretColumnsOutsideSource = CaretEnd-CaretStart
393
0
    - (map.byteToColumn(SourceEnd)-map.byteToColumn(SourceStart));
394
395
0
  char const *front_ellipse = "  ...";
396
0
  char const *front_space   = "     ";
397
0
  char const *back_ellipse = "...";
398
0
  unsigned ellipses_space = strlen(front_ellipse) + strlen(back_ellipse);
399
400
0
  unsigned TargetColumns = Columns;
401
  // Give us extra room for the ellipses
402
  //  and any of the caret line that extends past the source
403
0
  if (TargetColumns > ellipses_space+CaretColumnsOutsideSource)
404
0
    TargetColumns -= ellipses_space+CaretColumnsOutsideSource;
405
406
0
  while (SourceStart>0 || SourceEnd<SourceLine.size()) {
407
0
    bool ExpandedRegion = false;
408
409
0
    if (SourceStart>0) {
410
0
      unsigned NewStart = map.startOfPreviousColumn(SourceStart);
411
412
      // Skip over any whitespace we see here; we're looking for
413
      // another bit of interesting text.
414
      // FIXME: Detect non-ASCII whitespace characters too.
415
0
      while (NewStart && isWhitespace(SourceLine[NewStart]))
416
0
        NewStart = map.startOfPreviousColumn(NewStart);
417
418
      // Skip over this bit of "interesting" text.
419
0
      while (NewStart) {
420
0
        unsigned Prev = map.startOfPreviousColumn(NewStart);
421
0
        if (isWhitespace(SourceLine[Prev]))
422
0
          break;
423
0
        NewStart = Prev;
424
0
      }
425
426
0
      assert(map.byteToColumn(NewStart) != -1);
427
0
      unsigned NewColumns = map.byteToColumn(SourceEnd) -
428
0
                              map.byteToColumn(NewStart);
429
0
      if (NewColumns <= TargetColumns) {
430
0
        SourceStart = NewStart;
431
0
        ExpandedRegion = true;
432
0
      }
433
0
    }
434
435
0
    if (SourceEnd<SourceLine.size()) {
436
0
      unsigned NewEnd = map.startOfNextColumn(SourceEnd);
437
438
      // Skip over any whitespace we see here; we're looking for
439
      // another bit of interesting text.
440
      // FIXME: Detect non-ASCII whitespace characters too.
441
0
      while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd]))
442
0
        NewEnd = map.startOfNextColumn(NewEnd);
443
444
      // Skip over this bit of "interesting" text.
445
0
      while (NewEnd < SourceLine.size() && isWhitespace(SourceLine[NewEnd]))
446
0
        NewEnd = map.startOfNextColumn(NewEnd);
447
448
0
      assert(map.byteToColumn(NewEnd) != -1);
449
0
      unsigned NewColumns = map.byteToColumn(NewEnd) -
450
0
                              map.byteToColumn(SourceStart);
451
0
      if (NewColumns <= TargetColumns) {
452
0
        SourceEnd = NewEnd;
453
0
        ExpandedRegion = true;
454
0
      }
455
0
    }
456
457
0
    if (!ExpandedRegion)
458
0
      break;
459
0
  }
460
461
0
  CaretStart = map.byteToColumn(SourceStart);
462
0
  CaretEnd = map.byteToColumn(SourceEnd) + CaretColumnsOutsideSource;
463
464
  // [CaretStart, CaretEnd) is the slice we want. Update the various
465
  // output lines to show only this slice.
466
0
  assert(CaretStart!=(unsigned)-1 && CaretEnd!=(unsigned)-1 &&
467
0
         SourceStart!=(unsigned)-1 && SourceEnd!=(unsigned)-1);
468
0
  assert(SourceStart <= SourceEnd);
469
0
  assert(CaretStart <= CaretEnd);
470
471
0
  unsigned BackColumnsRemoved
472
0
    = map.byteToColumn(SourceLine.size())-map.byteToColumn(SourceEnd);
473
0
  unsigned FrontColumnsRemoved = CaretStart;
474
0
  unsigned ColumnsKept = CaretEnd-CaretStart;
475
476
  // We checked up front that the line needed truncation
477
0
  assert(FrontColumnsRemoved+ColumnsKept+BackColumnsRemoved > Columns);
478
479
  // The line needs some truncation, and we'd prefer to keep the front
480
  //  if possible, so remove the back
481
0
  if (BackColumnsRemoved > strlen(back_ellipse))
482
0
    SourceLine.replace(SourceEnd, std::string::npos, back_ellipse);
483
484
  // If that's enough then we're done
485
0
  if (FrontColumnsRemoved+ColumnsKept <= Columns)
486
0
    return;
487
488
  // Otherwise remove the front as well
489
0
  if (FrontColumnsRemoved > strlen(front_ellipse)) {
490
0
    SourceLine.replace(0, SourceStart, front_ellipse);
491
0
    CaretLine.replace(0, CaretStart, front_space);
492
0
    if (!FixItInsertionLine.empty())
493
0
      FixItInsertionLine.replace(0, CaretStart, front_space);
494
0
  }
495
0
}
496
497
/// Skip over whitespace in the string, starting at the given
498
/// index.
499
///
500
/// \returns The index of the first non-whitespace character that is
501
/// greater than or equal to Idx or, if no such character exists,
502
/// returns the end of the string.
503
0
static unsigned skipWhitespace(unsigned Idx, StringRef Str, unsigned Length) {
504
0
  while (Idx < Length && isWhitespace(Str[Idx]))
505
0
    ++Idx;
506
0
  return Idx;
507
0
}
508
509
/// If the given character is the start of some kind of
510
/// balanced punctuation (e.g., quotes or parentheses), return the
511
/// character that will terminate the punctuation.
512
///
513
/// \returns The ending punctuation character, if any, or the NULL
514
/// character if the input character does not start any punctuation.
515
0
static inline char findMatchingPunctuation(char c) {
516
0
  switch (c) {
517
0
  case '\'': return '\'';
518
0
  case '`': return '\'';
519
0
  case '"':  return '"';
520
0
  case '(':  return ')';
521
0
  case '[': return ']';
522
0
  case '{': return '}';
523
0
  default: break;
524
0
  }
525
526
0
  return 0;
527
0
}
528
529
/// Find the end of the word starting at the given offset
530
/// within a string.
531
///
532
/// \returns the index pointing one character past the end of the
533
/// word.
534
static unsigned findEndOfWord(unsigned Start, StringRef Str,
535
                              unsigned Length, unsigned Column,
536
0
                              unsigned Columns) {
537
0
  assert(Start < Str.size() && "Invalid start position!");
538
0
  unsigned End = Start + 1;
539
540
  // If we are already at the end of the string, take that as the word.
541
0
  if (End == Str.size())
542
0
    return End;
543
544
  // Determine if the start of the string is actually opening
545
  // punctuation, e.g., a quote or parentheses.
546
0
  char EndPunct = findMatchingPunctuation(Str[Start]);
547
0
  if (!EndPunct) {
548
    // This is a normal word. Just find the first space character.
549
0
    while (End < Length && !isWhitespace(Str[End]))
550
0
      ++End;
551
0
    return End;
552
0
  }
553
554
  // We have the start of a balanced punctuation sequence (quotes,
555
  // parentheses, etc.). Determine the full sequence is.
556
0
  SmallString<16> PunctuationEndStack;
557
0
  PunctuationEndStack.push_back(EndPunct);
558
0
  while (End < Length && !PunctuationEndStack.empty()) {
559
0
    if (Str[End] == PunctuationEndStack.back())
560
0
      PunctuationEndStack.pop_back();
561
0
    else if (char SubEndPunct = findMatchingPunctuation(Str[End]))
562
0
      PunctuationEndStack.push_back(SubEndPunct);
563
564
0
    ++End;
565
0
  }
566
567
  // Find the first space character after the punctuation ended.
568
0
  while (End < Length && !isWhitespace(Str[End]))
569
0
    ++End;
570
571
0
  unsigned PunctWordLength = End - Start;
572
0
  if (// If the word fits on this line
573
0
      Column + PunctWordLength <= Columns ||
574
      // ... or the word is "short enough" to take up the next line
575
      // without too much ugly white space
576
0
      PunctWordLength < Columns/3)
577
0
    return End; // Take the whole thing as a single "word".
578
579
  // The whole quoted/parenthesized string is too long to print as a
580
  // single "word". Instead, find the "word" that starts just after
581
  // the punctuation and use that end-point instead. This will recurse
582
  // until it finds something small enough to consider a word.
583
0
  return findEndOfWord(Start + 1, Str, Length, Column + 1, Columns);
584
0
}
585
586
/// Print the given string to a stream, word-wrapping it to
587
/// some number of columns in the process.
588
///
589
/// \param OS the stream to which the word-wrapping string will be
590
/// emitted.
591
/// \param Str the string to word-wrap and output.
592
/// \param Columns the number of columns to word-wrap to.
593
/// \param Column the column number at which the first character of \p
594
/// Str will be printed. This will be non-zero when part of the first
595
/// line has already been printed.
596
/// \param Bold if the current text should be bold
597
/// \returns true if word-wrapping was required, or false if the
598
/// string fit on the first line.
599
static bool printWordWrapped(raw_ostream &OS, StringRef Str, unsigned Columns,
600
0
                             unsigned Column, bool Bold) {
601
0
  const unsigned Length = std::min(Str.find('\n'), Str.size());
602
0
  bool TextNormal = true;
603
604
0
  bool Wrapped = false;
605
0
  for (unsigned WordStart = 0, WordEnd; WordStart < Length;
606
0
       WordStart = WordEnd) {
607
    // Find the beginning of the next word.
608
0
    WordStart = skipWhitespace(WordStart, Str, Length);
609
0
    if (WordStart == Length)
610
0
      break;
611
612
    // Find the end of this word.
613
0
    WordEnd = findEndOfWord(WordStart, Str, Length, Column, Columns);
614
615
    // Does this word fit on the current line?
616
0
    unsigned WordLength = WordEnd - WordStart;
617
0
    if (Column + WordLength < Columns) {
618
      // This word fits on the current line; print it there.
619
0
      if (WordStart) {
620
0
        OS << ' ';
621
0
        Column += 1;
622
0
      }
623
0
      applyTemplateHighlighting(OS, Str.substr(WordStart, WordLength),
624
0
                                TextNormal, Bold);
625
0
      Column += WordLength;
626
0
      continue;
627
0
    }
628
629
    // This word does not fit on the current line, so wrap to the next
630
    // line.
631
0
    OS << '\n';
632
0
    OS.indent(WordWrapIndentation);
633
0
    applyTemplateHighlighting(OS, Str.substr(WordStart, WordLength),
634
0
                              TextNormal, Bold);
635
0
    Column = WordWrapIndentation + WordLength;
636
0
    Wrapped = true;
637
0
  }
638
639
  // Append any remaning text from the message with its existing formatting.
640
0
  applyTemplateHighlighting(OS, Str.substr(Length), TextNormal, Bold);
641
642
0
  assert(TextNormal && "Text highlighted at end of diagnostic message.");
643
644
0
  return Wrapped;
645
0
}
646
647
TextDiagnostic::TextDiagnostic(raw_ostream &OS,
648
                               const LangOptions &LangOpts,
649
                               DiagnosticOptions *DiagOpts)
650
0
  : DiagnosticRenderer(LangOpts, DiagOpts), OS(OS) {}
651
652
0
TextDiagnostic::~TextDiagnostic() {}
653
654
void TextDiagnostic::emitDiagnosticMessage(
655
    FullSourceLoc Loc, PresumedLoc PLoc, DiagnosticsEngine::Level Level,
656
    StringRef Message, ArrayRef<clang::CharSourceRange> Ranges,
657
0
    DiagOrStoredDiag D) {
658
0
  uint64_t StartOfLocationInfo = OS.tell();
659
660
  // Emit the location of this particular diagnostic.
661
0
  if (Loc.isValid())
662
0
    emitDiagnosticLoc(Loc, PLoc, Level, Ranges);
663
664
0
  if (DiagOpts->ShowColors)
665
0
    OS.resetColor();
666
667
0
  if (DiagOpts->ShowLevel)
668
0
    printDiagnosticLevel(OS, Level, DiagOpts->ShowColors);
669
0
  printDiagnosticMessage(OS,
670
0
                         /*IsSupplemental*/ Level == DiagnosticsEngine::Note,
671
0
                         Message, OS.tell() - StartOfLocationInfo,
672
0
                         DiagOpts->MessageLength, DiagOpts->ShowColors);
673
0
}
674
675
/*static*/ void
676
TextDiagnostic::printDiagnosticLevel(raw_ostream &OS,
677
                                     DiagnosticsEngine::Level Level,
678
0
                                     bool ShowColors) {
679
0
  if (ShowColors) {
680
    // Print diagnostic category in bold and color
681
0
    switch (Level) {
682
0
    case DiagnosticsEngine::Ignored:
683
0
      llvm_unreachable("Invalid diagnostic type");
684
0
    case DiagnosticsEngine::Note:    OS.changeColor(noteColor, true); break;
685
0
    case DiagnosticsEngine::Remark:  OS.changeColor(remarkColor, true); break;
686
0
    case DiagnosticsEngine::Warning: OS.changeColor(warningColor, true); break;
687
0
    case DiagnosticsEngine::Error:   OS.changeColor(errorColor, true); break;
688
0
    case DiagnosticsEngine::Fatal:   OS.changeColor(fatalColor, true); break;
689
0
    }
690
0
  }
691
692
0
  switch (Level) {
693
0
  case DiagnosticsEngine::Ignored:
694
0
    llvm_unreachable("Invalid diagnostic type");
695
0
  case DiagnosticsEngine::Note:    OS << "note: "; break;
696
0
  case DiagnosticsEngine::Remark:  OS << "remark: "; break;
697
0
  case DiagnosticsEngine::Warning: OS << "warning: "; break;
698
0
  case DiagnosticsEngine::Error:   OS << "error: "; break;
699
0
  case DiagnosticsEngine::Fatal:   OS << "fatal error: "; break;
700
0
  }
701
702
0
  if (ShowColors)
703
0
    OS.resetColor();
704
0
}
705
706
/*static*/
707
void TextDiagnostic::printDiagnosticMessage(raw_ostream &OS,
708
                                            bool IsSupplemental,
709
                                            StringRef Message,
710
                                            unsigned CurrentColumn,
711
0
                                            unsigned Columns, bool ShowColors) {
712
0
  bool Bold = false;
713
0
  if (ShowColors && !IsSupplemental) {
714
    // Print primary diagnostic messages in bold and without color, to visually
715
    // indicate the transition from continuation notes and other output.
716
0
    OS.changeColor(savedColor, true);
717
0
    Bold = true;
718
0
  }
719
720
0
  if (Columns)
721
0
    printWordWrapped(OS, Message, Columns, CurrentColumn, Bold);
722
0
  else {
723
0
    bool Normal = true;
724
0
    applyTemplateHighlighting(OS, Message, Normal, Bold);
725
0
    assert(Normal && "Formatting should have returned to normal");
726
0
  }
727
728
0
  if (ShowColors)
729
0
    OS.resetColor();
730
0
  OS << '\n';
731
0
}
732
733
0
void TextDiagnostic::emitFilename(StringRef Filename, const SourceManager &SM) {
734
#ifdef _WIN32
735
  SmallString<4096> TmpFilename;
736
#endif
737
0
  if (DiagOpts->AbsolutePath) {
738
0
    auto File = SM.getFileManager().getOptionalFileRef(Filename);
739
0
    if (File) {
740
      // We want to print a simplified absolute path, i. e. without "dots".
741
      //
742
      // The hardest part here are the paths like "<part1>/<link>/../<part2>".
743
      // On Unix-like systems, we cannot just collapse "<link>/..", because
744
      // paths are resolved sequentially, and, thereby, the path
745
      // "<part1>/<part2>" may point to a different location. That is why
746
      // we use FileManager::getCanonicalName(), which expands all indirections
747
      // with llvm::sys::fs::real_path() and caches the result.
748
      //
749
      // On the other hand, it would be better to preserve as much of the
750
      // original path as possible, because that helps a user to recognize it.
751
      // real_path() expands all links, which sometimes too much. Luckily,
752
      // on Windows we can just use llvm::sys::path::remove_dots(), because,
753
      // on that system, both aforementioned paths point to the same place.
754
#ifdef _WIN32
755
      TmpFilename = File->getName();
756
      llvm::sys::fs::make_absolute(TmpFilename);
757
      llvm::sys::path::native(TmpFilename);
758
      llvm::sys::path::remove_dots(TmpFilename, /* remove_dot_dot */ true);
759
      Filename = StringRef(TmpFilename.data(), TmpFilename.size());
760
#else
761
0
      Filename = SM.getFileManager().getCanonicalName(*File);
762
0
#endif
763
0
    }
764
0
  }
765
766
0
  OS << Filename;
767
0
}
768
769
/// Print out the file/line/column information and include trace.
770
///
771
/// This method handles the emission of the diagnostic location information.
772
/// This includes extracting as much location information as is present for
773
/// the diagnostic and printing it, as well as any include stack or source
774
/// ranges necessary.
775
void TextDiagnostic::emitDiagnosticLoc(FullSourceLoc Loc, PresumedLoc PLoc,
776
                                       DiagnosticsEngine::Level Level,
777
0
                                       ArrayRef<CharSourceRange> Ranges) {
778
0
  if (PLoc.isInvalid()) {
779
    // At least print the file name if available:
780
0
    if (FileID FID = Loc.getFileID(); FID.isValid()) {
781
0
      if (OptionalFileEntryRef FE = Loc.getFileEntryRef()) {
782
0
        emitFilename(FE->getName(), Loc.getManager());
783
0
        OS << ": ";
784
0
      }
785
0
    }
786
0
    return;
787
0
  }
788
0
  unsigned LineNo = PLoc.getLine();
789
790
0
  if (!DiagOpts->ShowLocation)
791
0
    return;
792
793
0
  if (DiagOpts->ShowColors)
794
0
    OS.changeColor(savedColor, true);
795
796
0
  emitFilename(PLoc.getFilename(), Loc.getManager());
797
0
  switch (DiagOpts->getFormat()) {
798
0
  case DiagnosticOptions::SARIF:
799
0
  case DiagnosticOptions::Clang:
800
0
    if (DiagOpts->ShowLine)
801
0
      OS << ':' << LineNo;
802
0
    break;
803
0
  case DiagnosticOptions::MSVC:  OS << '('  << LineNo; break;
804
0
  case DiagnosticOptions::Vi:    OS << " +" << LineNo; break;
805
0
  }
806
807
0
  if (DiagOpts->ShowColumn)
808
    // Compute the column number.
809
0
    if (unsigned ColNo = PLoc.getColumn()) {
810
0
      if (DiagOpts->getFormat() == DiagnosticOptions::MSVC) {
811
0
        OS << ',';
812
        // Visual Studio 2010 or earlier expects column number to be off by one
813
0
        if (LangOpts.MSCompatibilityVersion &&
814
0
            !LangOpts.isCompatibleWithMSVC(LangOptions::MSVC2012))
815
0
          ColNo--;
816
0
      } else
817
0
        OS << ':';
818
0
      OS << ColNo;
819
0
    }
820
0
  switch (DiagOpts->getFormat()) {
821
0
  case DiagnosticOptions::SARIF:
822
0
  case DiagnosticOptions::Clang:
823
0
  case DiagnosticOptions::Vi:    OS << ':';    break;
824
0
  case DiagnosticOptions::MSVC:
825
    // MSVC2013 and before print 'file(4) : error'. MSVC2015 gets rid of the
826
    // space and prints 'file(4): error'.
827
0
    OS << ')';
828
0
    if (LangOpts.MSCompatibilityVersion &&
829
0
        !LangOpts.isCompatibleWithMSVC(LangOptions::MSVC2015))
830
0
      OS << ' ';
831
0
    OS << ':';
832
0
    break;
833
0
  }
834
835
0
  if (DiagOpts->ShowSourceRanges && !Ranges.empty()) {
836
0
    FileID CaretFileID = Loc.getExpansionLoc().getFileID();
837
0
    bool PrintedRange = false;
838
0
    const SourceManager &SM = Loc.getManager();
839
840
0
    for (const auto &R : Ranges) {
841
      // Ignore invalid ranges.
842
0
      if (!R.isValid())
843
0
        continue;
844
845
0
      SourceLocation B = SM.getExpansionLoc(R.getBegin());
846
0
      CharSourceRange ERange = SM.getExpansionRange(R.getEnd());
847
0
      SourceLocation E = ERange.getEnd();
848
849
      // If the start or end of the range is in another file, just
850
      // discard it.
851
0
      if (SM.getFileID(B) != CaretFileID || SM.getFileID(E) != CaretFileID)
852
0
        continue;
853
854
      // Add in the length of the token, so that we cover multi-char
855
      // tokens.
856
0
      unsigned TokSize = 0;
857
0
      if (ERange.isTokenRange())
858
0
        TokSize = Lexer::MeasureTokenLength(E, SM, LangOpts);
859
860
0
      FullSourceLoc BF(B, SM), EF(E, SM);
861
0
      OS << '{'
862
0
         << BF.getLineNumber() << ':' << BF.getColumnNumber() << '-'
863
0
         << EF.getLineNumber() << ':' << (EF.getColumnNumber() + TokSize)
864
0
         << '}';
865
0
      PrintedRange = true;
866
0
    }
867
868
0
    if (PrintedRange)
869
0
      OS << ':';
870
0
  }
871
0
  OS << ' ';
872
0
}
873
874
0
void TextDiagnostic::emitIncludeLocation(FullSourceLoc Loc, PresumedLoc PLoc) {
875
0
  if (DiagOpts->ShowLocation && PLoc.isValid()) {
876
0
    OS << "In file included from ";
877
0
    emitFilename(PLoc.getFilename(), Loc.getManager());
878
0
    OS << ':' << PLoc.getLine() << ":\n";
879
0
  } else
880
0
    OS << "In included file:\n";
881
0
}
882
883
void TextDiagnostic::emitImportLocation(FullSourceLoc Loc, PresumedLoc PLoc,
884
0
                                        StringRef ModuleName) {
885
0
  if (DiagOpts->ShowLocation && PLoc.isValid())
886
0
    OS << "In module '" << ModuleName << "' imported from "
887
0
       << PLoc.getFilename() << ':' << PLoc.getLine() << ":\n";
888
0
  else
889
0
    OS << "In module '" << ModuleName << "':\n";
890
0
}
891
892
void TextDiagnostic::emitBuildingModuleLocation(FullSourceLoc Loc,
893
                                                PresumedLoc PLoc,
894
0
                                                StringRef ModuleName) {
895
0
  if (DiagOpts->ShowLocation && PLoc.isValid())
896
0
    OS << "While building module '" << ModuleName << "' imported from "
897
0
      << PLoc.getFilename() << ':' << PLoc.getLine() << ":\n";
898
0
  else
899
0
    OS << "While building module '" << ModuleName << "':\n";
900
0
}
901
902
/// Find the suitable set of lines to show to include a set of ranges.
903
static std::optional<std::pair<unsigned, unsigned>>
904
findLinesForRange(const CharSourceRange &R, FileID FID,
905
0
                  const SourceManager &SM) {
906
0
  if (!R.isValid())
907
0
    return std::nullopt;
908
909
0
  SourceLocation Begin = R.getBegin();
910
0
  SourceLocation End = R.getEnd();
911
0
  if (SM.getFileID(Begin) != FID || SM.getFileID(End) != FID)
912
0
    return std::nullopt;
913
914
0
  return std::make_pair(SM.getExpansionLineNumber(Begin),
915
0
                        SM.getExpansionLineNumber(End));
916
0
}
917
918
/// Add as much of range B into range A as possible without exceeding a maximum
919
/// size of MaxRange. Ranges are inclusive.
920
static std::pair<unsigned, unsigned>
921
maybeAddRange(std::pair<unsigned, unsigned> A, std::pair<unsigned, unsigned> B,
922
0
              unsigned MaxRange) {
923
  // If A is already the maximum size, we're done.
924
0
  unsigned Slack = MaxRange - (A.second - A.first + 1);
925
0
  if (Slack == 0)
926
0
    return A;
927
928
  // Easy case: merge succeeds within MaxRange.
929
0
  unsigned Min = std::min(A.first, B.first);
930
0
  unsigned Max = std::max(A.second, B.second);
931
0
  if (Max - Min + 1 <= MaxRange)
932
0
    return {Min, Max};
933
934
  // If we can't reach B from A within MaxRange, there's nothing to do.
935
  // Don't add lines to the range that contain nothing interesting.
936
0
  if ((B.first > A.first && B.first - A.first + 1 > MaxRange) ||
937
0
      (B.second < A.second && A.second - B.second + 1 > MaxRange))
938
0
    return A;
939
940
  // Otherwise, expand A towards B to produce a range of size MaxRange. We
941
  // attempt to expand by the same amount in both directions if B strictly
942
  // contains A.
943
944
  // Expand downwards by up to half the available amount, then upwards as
945
  // much as possible, then downwards as much as possible.
946
0
  A.second = std::min(A.second + (Slack + 1) / 2, Max);
947
0
  Slack = MaxRange - (A.second - A.first + 1);
948
0
  A.first = std::max(Min + Slack, A.first) - Slack;
949
0
  A.second = std::min(A.first + MaxRange - 1, Max);
950
0
  return A;
951
0
}
952
953
struct LineRange {
954
  unsigned LineNo;
955
  unsigned StartCol;
956
  unsigned EndCol;
957
};
958
959
/// Highlight \p R (with ~'s) on the current source line.
960
static void highlightRange(const LineRange &R, const SourceColumnMap &Map,
961
0
                           std::string &CaretLine) {
962
  // Pick the first non-whitespace column.
963
0
  unsigned StartColNo = R.StartCol;
964
0
  while (StartColNo < Map.getSourceLine().size() &&
965
0
         (Map.getSourceLine()[StartColNo] == ' ' ||
966
0
          Map.getSourceLine()[StartColNo] == '\t'))
967
0
    StartColNo = Map.startOfNextColumn(StartColNo);
968
969
  // Pick the last non-whitespace column.
970
0
  unsigned EndColNo =
971
0
      std::min(static_cast<size_t>(R.EndCol), Map.getSourceLine().size());
972
0
  while (EndColNo && (Map.getSourceLine()[EndColNo - 1] == ' ' ||
973
0
                      Map.getSourceLine()[EndColNo - 1] == '\t'))
974
0
    EndColNo = Map.startOfPreviousColumn(EndColNo);
975
976
  // If the start/end passed each other, then we are trying to highlight a
977
  // range that just exists in whitespace. That most likely means we have
978
  // a multi-line highlighting range that covers a blank line.
979
0
  if (StartColNo > EndColNo)
980
0
    return;
981
982
  // Fill the range with ~'s.
983
0
  StartColNo = Map.byteToContainingColumn(StartColNo);
984
0
  EndColNo = Map.byteToContainingColumn(EndColNo);
985
986
0
  assert(StartColNo <= EndColNo && "Invalid range!");
987
0
  if (CaretLine.size() < EndColNo)
988
0
    CaretLine.resize(EndColNo, ' ');
989
0
  std::fill(CaretLine.begin() + StartColNo, CaretLine.begin() + EndColNo, '~');
990
0
}
991
992
static std::string buildFixItInsertionLine(FileID FID,
993
                                           unsigned LineNo,
994
                                           const SourceColumnMap &map,
995
                                           ArrayRef<FixItHint> Hints,
996
                                           const SourceManager &SM,
997
0
                                           const DiagnosticOptions *DiagOpts) {
998
0
  std::string FixItInsertionLine;
999
0
  if (Hints.empty() || !DiagOpts->ShowFixits)
1000
0
    return FixItInsertionLine;
1001
0
  unsigned PrevHintEndCol = 0;
1002
1003
0
  for (const auto &H : Hints) {
1004
0
    if (H.CodeToInsert.empty())
1005
0
      continue;
1006
1007
    // We have an insertion hint. Determine whether the inserted
1008
    // code contains no newlines and is on the same line as the caret.
1009
0
    std::pair<FileID, unsigned> HintLocInfo =
1010
0
        SM.getDecomposedExpansionLoc(H.RemoveRange.getBegin());
1011
0
    if (FID == HintLocInfo.first &&
1012
0
        LineNo == SM.getLineNumber(HintLocInfo.first, HintLocInfo.second) &&
1013
0
        StringRef(H.CodeToInsert).find_first_of("\n\r") == StringRef::npos) {
1014
      // Insert the new code into the line just below the code
1015
      // that the user wrote.
1016
      // Note: When modifying this function, be very careful about what is a
1017
      // "column" (printed width, platform-dependent) and what is a
1018
      // "byte offset" (SourceManager "column").
1019
0
      unsigned HintByteOffset =
1020
0
          SM.getColumnNumber(HintLocInfo.first, HintLocInfo.second) - 1;
1021
1022
      // The hint must start inside the source or right at the end
1023
0
      assert(HintByteOffset < static_cast<unsigned>(map.bytes()) + 1);
1024
0
      unsigned HintCol = map.byteToContainingColumn(HintByteOffset);
1025
1026
      // If we inserted a long previous hint, push this one forwards, and add
1027
      // an extra space to show that this is not part of the previous
1028
      // completion. This is sort of the best we can do when two hints appear
1029
      // to overlap.
1030
      //
1031
      // Note that if this hint is located immediately after the previous
1032
      // hint, no space will be added, since the location is more important.
1033
0
      if (HintCol < PrevHintEndCol)
1034
0
        HintCol = PrevHintEndCol + 1;
1035
1036
      // This should NOT use HintByteOffset, because the source might have
1037
      // Unicode characters in earlier columns.
1038
0
      unsigned NewFixItLineSize = FixItInsertionLine.size() +
1039
0
                                  (HintCol - PrevHintEndCol) +
1040
0
                                  H.CodeToInsert.size();
1041
0
      if (NewFixItLineSize > FixItInsertionLine.size())
1042
0
        FixItInsertionLine.resize(NewFixItLineSize, ' ');
1043
1044
0
      std::copy(H.CodeToInsert.begin(), H.CodeToInsert.end(),
1045
0
                FixItInsertionLine.end() - H.CodeToInsert.size());
1046
1047
0
      PrevHintEndCol = HintCol + llvm::sys::locale::columnWidth(H.CodeToInsert);
1048
0
    }
1049
0
  }
1050
1051
0
  expandTabs(FixItInsertionLine, DiagOpts->TabStop);
1052
1053
0
  return FixItInsertionLine;
1054
0
}
1055
1056
0
static unsigned getNumDisplayWidth(unsigned N) {
1057
0
  unsigned L = 1u, M = 10u;
1058
0
  while (M <= N && ++L != std::numeric_limits<unsigned>::digits10 + 1)
1059
0
    M *= 10u;
1060
1061
0
  return L;
1062
0
}
1063
1064
/// Filter out invalid ranges, ranges that don't fit into the window of
1065
/// source lines we will print, and ranges from other files.
1066
///
1067
/// For the remaining ranges, convert them to simple LineRange structs,
1068
/// which only cover one line at a time.
1069
static SmallVector<LineRange>
1070
prepareAndFilterRanges(const SmallVectorImpl<CharSourceRange> &Ranges,
1071
                       const SourceManager &SM,
1072
                       const std::pair<unsigned, unsigned> &Lines, FileID FID,
1073
0
                       const LangOptions &LangOpts) {
1074
0
  SmallVector<LineRange> LineRanges;
1075
1076
0
  for (const CharSourceRange &R : Ranges) {
1077
0
    if (R.isInvalid())
1078
0
      continue;
1079
0
    SourceLocation Begin = R.getBegin();
1080
0
    SourceLocation End = R.getEnd();
1081
1082
0
    unsigned StartLineNo = SM.getExpansionLineNumber(Begin);
1083
0
    if (StartLineNo > Lines.second || SM.getFileID(Begin) != FID)
1084
0
      continue;
1085
1086
0
    unsigned EndLineNo = SM.getExpansionLineNumber(End);
1087
0
    if (EndLineNo < Lines.first || SM.getFileID(End) != FID)
1088
0
      continue;
1089
1090
0
    unsigned StartColumn = SM.getExpansionColumnNumber(Begin);
1091
0
    unsigned EndColumn = SM.getExpansionColumnNumber(End);
1092
0
    if (R.isTokenRange())
1093
0
      EndColumn += Lexer::MeasureTokenLength(End, SM, LangOpts);
1094
1095
    // Only a single line.
1096
0
    if (StartLineNo == EndLineNo) {
1097
0
      LineRanges.push_back({StartLineNo, StartColumn - 1, EndColumn - 1});
1098
0
      continue;
1099
0
    }
1100
1101
    // Start line.
1102
0
    LineRanges.push_back({StartLineNo, StartColumn - 1, ~0u});
1103
1104
    // Middle lines.
1105
0
    for (unsigned S = StartLineNo + 1; S != EndLineNo; ++S)
1106
0
      LineRanges.push_back({S, 0, ~0u});
1107
1108
    // End line.
1109
0
    LineRanges.push_back({EndLineNo, 0, EndColumn - 1});
1110
0
  }
1111
1112
0
  return LineRanges;
1113
0
}
1114
1115
/// Emit a code snippet and caret line.
1116
///
1117
/// This routine emits a single line's code snippet and caret line..
1118
///
1119
/// \param Loc The location for the caret.
1120
/// \param Ranges The underlined ranges for this code snippet.
1121
/// \param Hints The FixIt hints active for this diagnostic.
1122
void TextDiagnostic::emitSnippetAndCaret(
1123
    FullSourceLoc Loc, DiagnosticsEngine::Level Level,
1124
0
    SmallVectorImpl<CharSourceRange> &Ranges, ArrayRef<FixItHint> Hints) {
1125
0
  assert(Loc.isValid() && "must have a valid source location here");
1126
0
  assert(Loc.isFileID() && "must have a file location here");
1127
1128
  // If caret diagnostics are enabled and we have location, we want to
1129
  // emit the caret.  However, we only do this if the location moved
1130
  // from the last diagnostic, if the last diagnostic was a note that
1131
  // was part of a different warning or error diagnostic, or if the
1132
  // diagnostic has ranges.  We don't want to emit the same caret
1133
  // multiple times if one loc has multiple diagnostics.
1134
0
  if (!DiagOpts->ShowCarets)
1135
0
    return;
1136
0
  if (Loc == LastLoc && Ranges.empty() && Hints.empty() &&
1137
0
      (LastLevel != DiagnosticsEngine::Note || Level == LastLevel))
1138
0
    return;
1139
1140
0
  FileID FID = Loc.getFileID();
1141
0
  const SourceManager &SM = Loc.getManager();
1142
1143
  // Get information about the buffer it points into.
1144
0
  bool Invalid = false;
1145
0
  StringRef BufData = Loc.getBufferData(&Invalid);
1146
0
  if (Invalid)
1147
0
    return;
1148
0
  const char *BufStart = BufData.data();
1149
0
  const char *BufEnd = BufStart + BufData.size();
1150
1151
0
  unsigned CaretLineNo = Loc.getLineNumber();
1152
0
  unsigned CaretColNo = Loc.getColumnNumber();
1153
1154
  // Arbitrarily stop showing snippets when the line is too long.
1155
0
  static const size_t MaxLineLengthToPrint = 4096;
1156
0
  if (CaretColNo > MaxLineLengthToPrint)
1157
0
    return;
1158
1159
  // Find the set of lines to include.
1160
0
  const unsigned MaxLines = DiagOpts->SnippetLineLimit;
1161
0
  std::pair<unsigned, unsigned> Lines = {CaretLineNo, CaretLineNo};
1162
0
  unsigned DisplayLineNo = Loc.getPresumedLoc().getLine();
1163
0
  for (const auto &I : Ranges) {
1164
0
    if (auto OptionalRange = findLinesForRange(I, FID, SM))
1165
0
      Lines = maybeAddRange(Lines, *OptionalRange, MaxLines);
1166
1167
0
    DisplayLineNo =
1168
0
        std::min(DisplayLineNo, SM.getPresumedLineNumber(I.getBegin()));
1169
0
  }
1170
1171
  // Our line numbers look like:
1172
  // " [number] | "
1173
  // Where [number] is MaxLineNoDisplayWidth columns
1174
  // and the full thing is therefore MaxLineNoDisplayWidth + 4 columns.
1175
0
  unsigned MaxLineNoDisplayWidth =
1176
0
      DiagOpts->ShowLineNumbers
1177
0
          ? std::max(4u, getNumDisplayWidth(DisplayLineNo + MaxLines))
1178
0
          : 0;
1179
0
  auto indentForLineNumbers = [&] {
1180
0
    if (MaxLineNoDisplayWidth > 0)
1181
0
      OS.indent(MaxLineNoDisplayWidth + 2) << "| ";
1182
0
  };
1183
1184
0
  SmallVector<LineRange> LineRanges =
1185
0
      prepareAndFilterRanges(Ranges, SM, Lines, FID, LangOpts);
1186
1187
0
  for (unsigned LineNo = Lines.first; LineNo != Lines.second + 1;
1188
0
       ++LineNo, ++DisplayLineNo) {
1189
    // Rewind from the current position to the start of the line.
1190
0
    const char *LineStart =
1191
0
        BufStart +
1192
0
        SM.getDecomposedLoc(SM.translateLineCol(FID, LineNo, 1)).second;
1193
0
    if (LineStart == BufEnd)
1194
0
      break;
1195
1196
    // Compute the line end.
1197
0
    const char *LineEnd = LineStart;
1198
0
    while (*LineEnd != '\n' && *LineEnd != '\r' && LineEnd != BufEnd)
1199
0
      ++LineEnd;
1200
1201
    // Arbitrarily stop showing snippets when the line is too long.
1202
    // FIXME: Don't print any lines in this case.
1203
0
    if (size_t(LineEnd - LineStart) > MaxLineLengthToPrint)
1204
0
      return;
1205
1206
    // Copy the line of code into an std::string for ease of manipulation.
1207
0
    std::string SourceLine(LineStart, LineEnd);
1208
    // Remove trailing null bytes.
1209
0
    while (!SourceLine.empty() && SourceLine.back() == '\0' &&
1210
0
           (LineNo != CaretLineNo || SourceLine.size() > CaretColNo))
1211
0
      SourceLine.pop_back();
1212
1213
    // Build the byte to column map.
1214
0
    const SourceColumnMap sourceColMap(SourceLine, DiagOpts->TabStop);
1215
1216
0
    std::string CaretLine;
1217
    // Highlight all of the characters covered by Ranges with ~ characters.
1218
0
    for (const auto &LR : LineRanges) {
1219
0
      if (LR.LineNo == LineNo)
1220
0
        highlightRange(LR, sourceColMap, CaretLine);
1221
0
    }
1222
1223
    // Next, insert the caret itself.
1224
0
    if (CaretLineNo == LineNo) {
1225
0
      size_t Col = sourceColMap.byteToContainingColumn(CaretColNo - 1);
1226
0
      CaretLine.resize(std::max(Col + 1, CaretLine.size()), ' ');
1227
0
      CaretLine[Col] = '^';
1228
0
    }
1229
1230
0
    std::string FixItInsertionLine = buildFixItInsertionLine(
1231
0
        FID, LineNo, sourceColMap, Hints, SM, DiagOpts.get());
1232
1233
    // If the source line is too long for our terminal, select only the
1234
    // "interesting" source region within that line.
1235
0
    unsigned Columns = DiagOpts->MessageLength;
1236
0
    if (Columns)
1237
0
      selectInterestingSourceRegion(SourceLine, CaretLine, FixItInsertionLine,
1238
0
                                    Columns, sourceColMap);
1239
1240
    // If we are in -fdiagnostics-print-source-range-info mode, we are trying
1241
    // to produce easily machine parsable output.  Add a space before the
1242
    // source line and the caret to make it trivial to tell the main diagnostic
1243
    // line from what the user is intended to see.
1244
0
    if (DiagOpts->ShowSourceRanges && !SourceLine.empty()) {
1245
0
      SourceLine = ' ' + SourceLine;
1246
0
      CaretLine = ' ' + CaretLine;
1247
0
    }
1248
1249
    // Emit what we have computed.
1250
0
    emitSnippet(SourceLine, MaxLineNoDisplayWidth, DisplayLineNo);
1251
1252
0
    if (!CaretLine.empty()) {
1253
0
      indentForLineNumbers();
1254
0
      if (DiagOpts->ShowColors)
1255
0
        OS.changeColor(caretColor, true);
1256
0
      OS << CaretLine << '\n';
1257
0
      if (DiagOpts->ShowColors)
1258
0
        OS.resetColor();
1259
0
    }
1260
1261
0
    if (!FixItInsertionLine.empty()) {
1262
0
      indentForLineNumbers();
1263
0
      if (DiagOpts->ShowColors)
1264
        // Print fixit line in color
1265
0
        OS.changeColor(fixitColor, false);
1266
0
      if (DiagOpts->ShowSourceRanges)
1267
0
        OS << ' ';
1268
0
      OS << FixItInsertionLine << '\n';
1269
0
      if (DiagOpts->ShowColors)
1270
0
        OS.resetColor();
1271
0
    }
1272
0
  }
1273
1274
  // Print out any parseable fixit information requested by the options.
1275
0
  emitParseableFixits(Hints, SM);
1276
0
}
1277
1278
void TextDiagnostic::emitSnippet(StringRef SourceLine,
1279
                                 unsigned MaxLineNoDisplayWidth,
1280
0
                                 unsigned LineNo) {
1281
  // Emit line number.
1282
0
  if (MaxLineNoDisplayWidth > 0) {
1283
0
    unsigned LineNoDisplayWidth = getNumDisplayWidth(LineNo);
1284
0
    OS.indent(MaxLineNoDisplayWidth - LineNoDisplayWidth + 1)
1285
0
        << LineNo << " | ";
1286
0
  }
1287
1288
  // Print the source line one character at a time.
1289
0
  bool PrintReversed = false;
1290
0
  size_t I = 0;
1291
0
  while (I < SourceLine.size()) {
1292
0
    auto [Str, WasPrintable] =
1293
0
        printableTextForNextCharacter(SourceLine, &I, DiagOpts->TabStop);
1294
1295
    // Toggle inverted colors on or off for this character.
1296
0
    if (DiagOpts->ShowColors) {
1297
0
      if (WasPrintable == PrintReversed) {
1298
0
        PrintReversed = !PrintReversed;
1299
0
        if (PrintReversed)
1300
0
          OS.reverseColor();
1301
0
        else
1302
0
          OS.resetColor();
1303
0
      }
1304
0
    }
1305
0
    OS << Str;
1306
0
  }
1307
1308
0
  if (DiagOpts->ShowColors)
1309
0
    OS.resetColor();
1310
1311
0
  OS << '\n';
1312
0
}
1313
1314
void TextDiagnostic::emitParseableFixits(ArrayRef<FixItHint> Hints,
1315
0
                                         const SourceManager &SM) {
1316
0
  if (!DiagOpts->ShowParseableFixits)
1317
0
    return;
1318
1319
  // We follow FixItRewriter's example in not (yet) handling
1320
  // fix-its in macros.
1321
0
  for (const auto &H : Hints) {
1322
0
    if (H.RemoveRange.isInvalid() || H.RemoveRange.getBegin().isMacroID() ||
1323
0
        H.RemoveRange.getEnd().isMacroID())
1324
0
      return;
1325
0
  }
1326
1327
0
  for (const auto &H : Hints) {
1328
0
    SourceLocation BLoc = H.RemoveRange.getBegin();
1329
0
    SourceLocation ELoc = H.RemoveRange.getEnd();
1330
1331
0
    std::pair<FileID, unsigned> BInfo = SM.getDecomposedLoc(BLoc);
1332
0
    std::pair<FileID, unsigned> EInfo = SM.getDecomposedLoc(ELoc);
1333
1334
    // Adjust for token ranges.
1335
0
    if (H.RemoveRange.isTokenRange())
1336
0
      EInfo.second += Lexer::MeasureTokenLength(ELoc, SM, LangOpts);
1337
1338
    // We specifically do not do word-wrapping or tab-expansion here,
1339
    // because this is supposed to be easy to parse.
1340
0
    PresumedLoc PLoc = SM.getPresumedLoc(BLoc);
1341
0
    if (PLoc.isInvalid())
1342
0
      break;
1343
1344
0
    OS << "fix-it:\"";
1345
0
    OS.write_escaped(PLoc.getFilename());
1346
0
    OS << "\":{" << SM.getLineNumber(BInfo.first, BInfo.second)
1347
0
      << ':' << SM.getColumnNumber(BInfo.first, BInfo.second)
1348
0
      << '-' << SM.getLineNumber(EInfo.first, EInfo.second)
1349
0
      << ':' << SM.getColumnNumber(EInfo.first, EInfo.second)
1350
0
      << "}:\"";
1351
0
    OS.write_escaped(H.CodeToInsert);
1352
0
    OS << "\"\n";
1353
0
  }
1354
0
}