aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clang14/lib/Lex/DependencyDirectivesSourceMinimizer.cpp
blob: f597c56837fb481828c6aabbaabb8ab62c1d2610 (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
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
//===- DependencyDirectivesSourceMinimizer.cpp -  -------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This is the implementation for minimizing header and source files to the
/// minimum necessary preprocessor directives for evaluating includes. It
/// reduces the source down to #define, #include, #import, @import, and any
/// conditional preprocessor logic that contains one of those.
///
//===----------------------------------------------------------------------===//

#include "clang/Lex/DependencyDirectivesSourceMinimizer.h"
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Lex/LexDiagnostic.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/MemoryBuffer.h"

using namespace llvm;
using namespace clang;
using namespace clang::minimize_source_to_dependency_directives;

namespace {

struct Minimizer {
  /// Minimized output.
  SmallVectorImpl<char> &Out;
  /// The known tokens encountered during the minimization.
  SmallVectorImpl<Token> &Tokens;

  Minimizer(SmallVectorImpl<char> &Out, SmallVectorImpl<Token> &Tokens,
            StringRef Input, DiagnosticsEngine *Diags,
            SourceLocation InputSourceLoc)
      : Out(Out), Tokens(Tokens), Input(Input), Diags(Diags),
        InputSourceLoc(InputSourceLoc) {}

  /// Lex the provided source and emit the minimized output.
  ///
  /// \returns True on error.
  bool minimize();

private:
  struct IdInfo {
    const char *Last;
    StringRef Name;
  };

  /// Lex an identifier.
  ///
  /// \pre First points at a valid identifier head.
  LLVM_NODISCARD IdInfo lexIdentifier(const char *First, const char *const End);
  LLVM_NODISCARD bool isNextIdentifier(StringRef Id, const char *&First,
                                       const char *const End);
  LLVM_NODISCARD bool minimizeImpl(const char *First, const char *const End);
  LLVM_NODISCARD bool lexPPLine(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexAt(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexModule(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexDefine(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexPragma(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexEndif(const char *&First, const char *const End);
  LLVM_NODISCARD bool lexDefault(TokenKind Kind, StringRef Directive,
                                 const char *&First, const char *const End);
  Token &makeToken(TokenKind K) {
    Tokens.emplace_back(K, Out.size());
    return Tokens.back();
  }
  void popToken() {
    Out.resize(Tokens.back().Offset);
    Tokens.pop_back();
  }
  TokenKind top() const { return Tokens.empty() ? pp_none : Tokens.back().K; }

  Minimizer &put(char Byte) {
    Out.push_back(Byte);
    return *this;
  }
  Minimizer &append(StringRef S) { return append(S.begin(), S.end()); }
  Minimizer &append(const char *First, const char *Last) {
    Out.append(First, Last);
    return *this;
  }

  void printToNewline(const char *&First, const char *const End);
  void printAdjacentModuleNameParts(const char *&First, const char *const End);
  LLVM_NODISCARD bool printAtImportBody(const char *&First,
                                        const char *const End);
  void printDirectiveBody(const char *&First, const char *const End);
  void printAdjacentMacroArgs(const char *&First, const char *const End);
  LLVM_NODISCARD bool printMacroArgs(const char *&First, const char *const End);

  /// Reports a diagnostic if the diagnostic engine is provided. Always returns
  /// true at the end.
  bool reportError(const char *CurPtr, unsigned Err);

  StringMap<char> SplitIds;
  StringRef Input;
  DiagnosticsEngine *Diags;
  SourceLocation InputSourceLoc;
};

} // end anonymous namespace

bool Minimizer::reportError(const char *CurPtr, unsigned Err) {
  if (!Diags)
    return true;
  assert(CurPtr >= Input.data() && "invalid buffer ptr");
  Diags->Report(InputSourceLoc.getLocWithOffset(CurPtr - Input.data()), Err);
  return true;
}

static void skipOverSpaces(const char *&First, const char *const End) {
  while (First != End && isHorizontalWhitespace(*First))
    ++First;
}

LLVM_NODISCARD static bool isRawStringLiteral(const char *First,
                                              const char *Current) {
  assert(First <= Current);

  // Check if we can even back up.
  if (*Current != '"' || First == Current)
    return false;

  // Check for an "R".
  --Current;
  if (*Current != 'R')
    return false;
  if (First == Current || !isAsciiIdentifierContinue(*--Current))
    return true;

  // Check for a prefix of "u", "U", or "L".
  if (*Current == 'u' || *Current == 'U' || *Current == 'L')
    return First == Current || !isAsciiIdentifierContinue(*--Current);

  // Check for a prefix of "u8".
  if (*Current != '8' || First == Current || *Current-- != 'u')
    return false;
  return First == Current || !isAsciiIdentifierContinue(*--Current);
}

static void skipRawString(const char *&First, const char *const End) {
  assert(First[0] == '"');
  assert(First[-1] == 'R');

  const char *Last = ++First;
  while (Last != End && *Last != '(')
    ++Last;
  if (Last == End) {
    First = Last; // Hit the end... just give up.
    return;
  }

  StringRef Terminator(First, Last - First);
  for (;;) {
    // Move First to just past the next ")".
    First = Last;
    while (First != End && *First != ')')
      ++First;
    if (First == End)
      return;
    ++First;

    // Look ahead for the terminator sequence.
    Last = First;
    while (Last != End && size_t(Last - First) < Terminator.size() &&
           Terminator[Last - First] == *Last)
      ++Last;

    // Check if we hit it (or the end of the file).
    if (Last == End) {
      First = Last;
      return;
    }
    if (size_t(Last - First) < Terminator.size())
      continue;
    if (*Last != '"')
      continue;
    First = Last + 1;
    return;
  }
}

// Returns the length of EOL, either 0 (no end-of-line), 1 (\n) or 2 (\r\n)
static unsigned isEOL(const char *First, const char *const End) {
  if (First == End)
    return 0;
  if (End - First > 1 && isVerticalWhitespace(First[0]) &&
      isVerticalWhitespace(First[1]) && First[0] != First[1])
    return 2;
  return !!isVerticalWhitespace(First[0]);
}

static void skipString(const char *&First, const char *const End) {
  assert(*First == '\'' || *First == '"' || *First == '<');
  const char Terminator = *First == '<' ? '>' : *First;
  for (++First; First != End && *First != Terminator; ++First) {
    // String and character literals don't extend past the end of the line.
    if (isVerticalWhitespace(*First))
      return;
    if (*First != '\\')
      continue;
    // Skip past backslash to the next character. This ensures that the
    // character right after it is skipped as well, which matters if it's
    // the terminator.
    if (++First == End)
      return;
    if (!isWhitespace(*First))
      continue;
    // Whitespace after the backslash might indicate a line continuation.
    const char *FirstAfterBackslashPastSpace = First;
    skipOverSpaces(FirstAfterBackslashPastSpace, End);
    if (unsigned NLSize = isEOL(FirstAfterBackslashPastSpace, End)) {
      // Advance the character pointer to the next line for the next
      // iteration.
      First = FirstAfterBackslashPastSpace + NLSize - 1;
    }
  }
  if (First != End)
    ++First; // Finish off the string.
}

// Returns the length of the skipped newline
static unsigned skipNewline(const char *&First, const char *End) {
  if (First == End)
    return 0;
  assert(isVerticalWhitespace(*First));
  unsigned Len = isEOL(First, End);
  assert(Len && "expected newline");
  First += Len;
  return Len;
}

static bool wasLineContinuation(const char *First, unsigned EOLLen) {
  return *(First - (int)EOLLen - 1) == '\\';
}

static void skipToNewlineRaw(const char *&First, const char *const End) {
  for (;;) {
    if (First == End)
      return;

    unsigned Len = isEOL(First, End);
    if (Len)
      return;

    do {
      if (++First == End)
        return;
      Len = isEOL(First, End);
    } while (!Len);

    if (First[-1] != '\\')
      return;

    First += Len;
    // Keep skipping lines...
  }
}

static const char *findLastNonSpace(const char *First, const char *Last) {
  assert(First <= Last);
  while (First != Last && isHorizontalWhitespace(Last[-1]))
    --Last;
  return Last;
}

static const char *findFirstTrailingSpace(const char *First,
                                          const char *Last) {
  const char *LastNonSpace = findLastNonSpace(First, Last);
  if (Last == LastNonSpace)
    return Last;
  assert(isHorizontalWhitespace(LastNonSpace[0]));
  return LastNonSpace + 1;
}

static void skipLineComment(const char *&First, const char *const End) {
  assert(First[0] == '/' && First[1] == '/');
  First += 2;
  skipToNewlineRaw(First, End);
}

static void skipBlockComment(const char *&First, const char *const End) {
  assert(First[0] == '/' && First[1] == '*');
  if (End - First < 4) {
    First = End;
    return;
  }
  for (First += 3; First != End; ++First)
    if (First[-1] == '*' && First[0] == '/') {
      ++First;
      return;
    }
}

/// \returns True if the current single quotation mark character is a C++ 14
/// digit separator.
static bool isQuoteCppDigitSeparator(const char *const Start,
                                     const char *const Cur,
                                     const char *const End) {
  assert(*Cur == '\'' && "expected quotation character");
  // skipLine called in places where we don't expect a valid number
  // body before `start` on the same line, so always return false at the start.
  if (Start == Cur)
    return false;
  // The previous character must be a valid PP number character.
  // Make sure that the L, u, U, u8 prefixes don't get marked as a
  // separator though.
  char Prev = *(Cur - 1);
  if (Prev == 'L' || Prev == 'U' || Prev == 'u')
    return false;
  if (Prev == '8' && (Cur - 1 != Start) && *(Cur - 2) == 'u')
    return false;
  if (!isPreprocessingNumberBody(Prev))
    return false;
  // The next character should be a valid identifier body character.
  return (Cur + 1) < End && isAsciiIdentifierContinue(*(Cur + 1));
}

static void skipLine(const char *&First, const char *const End) {
  for (;;) {
    assert(First <= End);
    if (First == End)
      return;

    if (isVerticalWhitespace(*First)) {
      skipNewline(First, End);
      return;
    }
    const char *Start = First;
    while (First != End && !isVerticalWhitespace(*First)) {
      // Iterate over strings correctly to avoid comments and newlines.
      if (*First == '"' ||
          (*First == '\'' && !isQuoteCppDigitSeparator(Start, First, End))) {
        if (isRawStringLiteral(Start, First))
          skipRawString(First, End);
        else
          skipString(First, End);
        continue;
      }

      // Iterate over comments correctly.
      if (*First != '/' || End - First < 2) {
        ++First;
        continue;
      }

      if (First[1] == '/') {
        // "//...".
        skipLineComment(First, End);
        continue;
      }

      if (First[1] != '*') {
        ++First;
        continue;
      }

      // "/*...*/".
      skipBlockComment(First, End);
    }
    if (First == End)
      return;

    // Skip over the newline.
    unsigned Len = skipNewline(First, End);
    if (!wasLineContinuation(First, Len)) // Continue past line-continuations.
      break;
  }
}

static void skipDirective(StringRef Name, const char *&First,
                          const char *const End) {
  if (llvm::StringSwitch<bool>(Name)
          .Case("warning", true)
          .Case("error", true)
          .Default(false))
    // Do not process quotes or comments.
    skipToNewlineRaw(First, End);
  else
    skipLine(First, End);
}

void Minimizer::printToNewline(const char *&First, const char *const End) {
  while (First != End && !isVerticalWhitespace(*First)) {
    const char *Last = First;
    do {
      // Iterate over strings correctly to avoid comments and newlines.
      if (*Last == '"' || *Last == '\'' ||
          (*Last == '<' && top() == pp_include)) {
        if (LLVM_UNLIKELY(isRawStringLiteral(First, Last)))
          skipRawString(Last, End);
        else
          skipString(Last, End);
        continue;
      }
      if (*Last != '/' || End - Last < 2) {
        ++Last;
        continue; // Gather the rest up to print verbatim.
      }

      if (Last[1] != '/' && Last[1] != '*') {
        ++Last;
        continue;
      }

      // Deal with "//..." and "/*...*/".
      append(First, findFirstTrailingSpace(First, Last));
      First = Last;

      if (Last[1] == '/') {
        skipLineComment(First, End);
        return;
      }

      put(' ');
      skipBlockComment(First, End);
      skipOverSpaces(First, End);
      Last = First;
    } while (Last != End && !isVerticalWhitespace(*Last));

    // Print out the string.
    const char *LastBeforeTrailingSpace = findLastNonSpace(First, Last);
    if (Last == End || LastBeforeTrailingSpace == First ||
        LastBeforeTrailingSpace[-1] != '\\') {
      append(First, LastBeforeTrailingSpace);
      First = Last;
      skipNewline(First, End);
      return;
    }

    // Print up to the backslash, backing up over spaces. Preserve at least one
    // space, as the space matters when tokens are separated by a line
    // continuation.
    append(First, findFirstTrailingSpace(
                      First, LastBeforeTrailingSpace - 1));

    First = Last;
    skipNewline(First, End);
    skipOverSpaces(First, End);
  }
}

static void skipWhitespace(const char *&First, const char *const End) {
  for (;;) {
    assert(First <= End);
    skipOverSpaces(First, End);

    if (End - First < 2)
      return;

    if (First[0] == '\\' && isVerticalWhitespace(First[1])) {
      skipNewline(++First, End);
      continue;
    }

    // Check for a non-comment character.
    if (First[0] != '/')
      return;

    // "// ...".
    if (First[1] == '/') {
      skipLineComment(First, End);
      return;
    }

    // Cannot be a comment.
    if (First[1] != '*')
      return;

    // "/*...*/".
    skipBlockComment(First, End);
  }
}

void Minimizer::printAdjacentModuleNameParts(const char *&First,
                                             const char *const End) {
  // Skip over parts of the body.
  const char *Last = First;
  do
    ++Last;
  while (Last != End && (isAsciiIdentifierContinue(*Last) || *Last == '.'));
  append(First, Last);
  First = Last;
}

bool Minimizer::printAtImportBody(const char *&First, const char *const End) {
  for (;;) {
    skipWhitespace(First, End);
    if (First == End)
      return true;

    if (isVerticalWhitespace(*First)) {
      skipNewline(First, End);
      continue;
    }

    // Found a semicolon.
    if (*First == ';') {
      put(*First++).put('\n');
      return false;
    }

    // Don't handle macro expansions inside @import for now.
    if (!isAsciiIdentifierContinue(*First) && *First != '.')
      return true;

    printAdjacentModuleNameParts(First, End);
  }
}

void Minimizer::printDirectiveBody(const char *&First, const char *const End) {
  skipWhitespace(First, End); // Skip initial whitespace.
  printToNewline(First, End);
  while (Out.back() == ' ')
    Out.pop_back();
  put('\n');
}

LLVM_NODISCARD static const char *lexRawIdentifier(const char *First,
                                                   const char *const End) {
  assert(isAsciiIdentifierContinue(*First) && "invalid identifer");
  const char *Last = First + 1;
  while (Last != End && isAsciiIdentifierContinue(*Last))
    ++Last;
  return Last;
}

LLVM_NODISCARD static const char *
getIdentifierContinuation(const char *First, const char *const End) {
  if (End - First < 3 || First[0] != '\\' || !isVerticalWhitespace(First[1]))
    return nullptr;

  ++First;
  skipNewline(First, End);
  if (First == End)
    return nullptr;
  return isAsciiIdentifierContinue(First[0]) ? First : nullptr;
}

Minimizer::IdInfo Minimizer::lexIdentifier(const char *First,
                                           const char *const End) {
  const char *Last = lexRawIdentifier(First, End);
  const char *Next = getIdentifierContinuation(Last, End);
  if (LLVM_LIKELY(!Next))
    return IdInfo{Last, StringRef(First, Last - First)};

  // Slow path, where identifiers are split over lines.
  SmallVector<char, 64> Id(First, Last);
  while (Next) {
    Last = lexRawIdentifier(Next, End);
    Id.append(Next, Last);
    Next = getIdentifierContinuation(Last, End);
  }
  return IdInfo{
      Last,
      SplitIds.try_emplace(StringRef(Id.begin(), Id.size()), 0).first->first()};
}

void Minimizer::printAdjacentMacroArgs(const char *&First,
                                       const char *const End) {
  // Skip over parts of the body.
  const char *Last = First;
  do
    ++Last;
  while (Last != End &&
         (isAsciiIdentifierContinue(*Last) || *Last == '.' || *Last == ','));
  append(First, Last);
  First = Last;
}

bool Minimizer::printMacroArgs(const char *&First, const char *const End) {
  assert(*First == '(');
  put(*First++);
  for (;;) {
    skipWhitespace(First, End);
    if (First == End)
      return true;

    if (*First == ')') {
      put(*First++);
      return false;
    }

    // This is intentionally fairly liberal.
    if (!(isAsciiIdentifierContinue(*First) || *First == '.' || *First == ','))
      return true;

    printAdjacentMacroArgs(First, End);
  }
}

/// Looks for an identifier starting from Last.
///
/// Updates "First" to just past the next identifier, if any.  Returns true iff
/// the identifier matches "Id".
bool Minimizer::isNextIdentifier(StringRef Id, const char *&First,
                                 const char *const End) {
  skipWhitespace(First, End);
  if (First == End || !isAsciiIdentifierStart(*First))
    return false;

  IdInfo FoundId = lexIdentifier(First, End);
  First = FoundId.Last;
  return FoundId.Name == Id;
}

bool Minimizer::lexAt(const char *&First, const char *const End) {
  // Handle "@import".
  const char *ImportLoc = First++;
  if (!isNextIdentifier("import", First, End)) {
    skipLine(First, End);
    return false;
  }
  makeToken(decl_at_import);
  append("@import ");
  if (printAtImportBody(First, End))
    return reportError(
        ImportLoc, diag::err_dep_source_minimizer_missing_sema_after_at_import);
  skipWhitespace(First, End);
  if (First == End)
    return false;
  if (!isVerticalWhitespace(*First))
    return reportError(
        ImportLoc, diag::err_dep_source_minimizer_unexpected_tokens_at_import);
  skipNewline(First, End);
  return false;
}

bool Minimizer::lexModule(const char *&First, const char *const End) {
  IdInfo Id = lexIdentifier(First, End);
  First = Id.Last;
  bool Export = false;
  if (Id.Name == "export") {
    Export = true;
    skipWhitespace(First, End);
    if (!isAsciiIdentifierContinue(*First)) {
      skipLine(First, End);
      return false;
    }
    Id = lexIdentifier(First, End);
    First = Id.Last;
  }

  if (Id.Name != "module" && Id.Name != "import") {
    skipLine(First, End);
    return false;
  }

  skipWhitespace(First, End);

  // Ignore this as a module directive if the next character can't be part of
  // an import.

  switch (*First) {
  case ':':
  case '<':
  case '"':
    break;
  default:
    if (!isAsciiIdentifierContinue(*First)) {
      skipLine(First, End);
      return false;
    }
  }

  if (Export) {
    makeToken(cxx_export_decl);
    append("export ");
  }

  if (Id.Name == "module")
    makeToken(cxx_module_decl);
  else
    makeToken(cxx_import_decl);
  append(Id.Name);
  append(" ");
  printToNewline(First, End);
  append("\n");
  return false;
}

bool Minimizer::lexDefine(const char *&First, const char *const End) {
  makeToken(pp_define);
  append("#define ");
  skipWhitespace(First, End);

  if (!isAsciiIdentifierStart(*First))
    return reportError(First, diag::err_pp_macro_not_identifier);

  IdInfo Id = lexIdentifier(First, End);
  const char *Last = Id.Last;
  append(Id.Name);
  if (Last == End)
    return false;
  if (*Last == '(') {
    size_t Size = Out.size();
    if (printMacroArgs(Last, End)) {
      // Be robust to bad macro arguments, since they can show up in disabled
      // code.
      Out.resize(Size);
      append("(/* invalid */\n");
      skipLine(Last, End);
      return false;
    }
  }
  skipWhitespace(Last, End);
  if (Last == End)
    return false;
  if (!isVerticalWhitespace(*Last))
    put(' ');
  printDirectiveBody(Last, End);
  First = Last;
  return false;
}

bool Minimizer::lexPragma(const char *&First, const char *const End) {
  // #pragma.
  skipWhitespace(First, End);
  if (First == End || !isAsciiIdentifierStart(*First))
    return false;

  IdInfo FoundId = lexIdentifier(First, End);
  First = FoundId.Last;
  if (FoundId.Name == "once") {
    // #pragma once
    skipLine(First, End);
    makeToken(pp_pragma_once);
    append("#pragma once\n");
    return false;
  }
  if (FoundId.Name == "push_macro") {
    // #pragma push_macro
    makeToken(pp_pragma_push_macro);
    append("#pragma push_macro");
    printDirectiveBody(First, End);
    return false;
  }
  if (FoundId.Name == "pop_macro") {
    // #pragma pop_macro
    makeToken(pp_pragma_pop_macro);
    append("#pragma pop_macro");
    printDirectiveBody(First, End);
    return false;
  }
  if (FoundId.Name == "include_alias") {
    // #pragma include_alias
    makeToken(pp_pragma_include_alias);
    append("#pragma include_alias");
    printDirectiveBody(First, End);
    return false;
  }

  if (FoundId.Name != "clang") {
    skipLine(First, End);
    return false;
  }

  // #pragma clang.
  if (!isNextIdentifier("module", First, End)) {
    skipLine(First, End);
    return false;
  }

  // #pragma clang module.
  if (!isNextIdentifier("import", First, End)) {
    skipLine(First, End);
    return false;
  }

  // #pragma clang module import.
  makeToken(pp_pragma_import);
  append("#pragma clang module import ");
  printDirectiveBody(First, End);
  return false;
}

bool Minimizer::lexEndif(const char *&First, const char *const End) {
  // Strip out "#else" if it's empty.
  if (top() == pp_else)
    popToken();

  // If "#ifdef" is empty, strip it and skip the "#endif".
  //
  // FIXME: Once/if Clang starts disallowing __has_include in macro expansions,
  // we can skip empty `#if` and `#elif` blocks as well after scanning for a
  // literal __has_include in the condition.  Even without that rule we could
  // drop the tokens if we scan for identifiers in the condition and find none.
  if (top() == pp_ifdef || top() == pp_ifndef) {
    popToken();
    skipLine(First, End);
    return false;
  }

  return lexDefault(pp_endif, "endif", First, End);
}

bool Minimizer::lexDefault(TokenKind Kind, StringRef Directive,
                           const char *&First, const char *const End) {
  makeToken(Kind);
  put('#').append(Directive).put(' ');
  printDirectiveBody(First, End);
  return false;
}

static bool isStartOfRelevantLine(char First) {
  switch (First) {
  case '#':
  case '@':
  case 'i':
  case 'e':
  case 'm':
    return true;
  }
  return false;
}

bool Minimizer::lexPPLine(const char *&First, const char *const End) {
  assert(First != End);

  skipWhitespace(First, End);
  assert(First <= End);
  if (First == End)
    return false;

  if (!isStartOfRelevantLine(*First)) {
    skipLine(First, End);
    assert(First <= End);
    return false;
  }

  // Handle "@import".
  if (*First == '@')
    return lexAt(First, End);

  if (*First == 'i' || *First == 'e' || *First == 'm')
    return lexModule(First, End);

  // Handle preprocessing directives.
  ++First; // Skip over '#'.
  skipWhitespace(First, End);

  if (First == End)
    return reportError(First, diag::err_pp_expected_eol);

  if (!isAsciiIdentifierStart(*First)) {
    skipLine(First, End);
    return false;
  }

  // Figure out the token.
  IdInfo Id = lexIdentifier(First, End);
  First = Id.Last;

  if (Id.Name == "pragma")
    return lexPragma(First, End);

  auto Kind = llvm::StringSwitch<TokenKind>(Id.Name)
                  .Case("include", pp_include)
                  .Case("__include_macros", pp___include_macros)
                  .Case("define", pp_define)
                  .Case("undef", pp_undef)
                  .Case("import", pp_import)
                  .Case("include_next", pp_include_next)
                  .Case("if", pp_if)
                  .Case("ifdef", pp_ifdef)
                  .Case("ifndef", pp_ifndef)
                  .Case("elif", pp_elif)
                  .Case("elifdef", pp_elifdef)
                  .Case("elifndef", pp_elifndef)
                  .Case("else", pp_else)
                  .Case("endif", pp_endif)
                  .Default(pp_none);
  if (Kind == pp_none) {
    skipDirective(Id.Name, First, End);
    return false;
  }

  if (Kind == pp_endif)
    return lexEndif(First, End);

  if (Kind == pp_define)
    return lexDefine(First, End);

  // Everything else.
  return lexDefault(Kind, Id.Name, First, End);
}

static void skipUTF8ByteOrderMark(const char *&First, const char *const End) {
  if ((End - First) >= 3 && First[0] == '\xef' && First[1] == '\xbb' &&
      First[2] == '\xbf')
    First += 3;
}

bool Minimizer::minimizeImpl(const char *First, const char *const End) {
  skipUTF8ByteOrderMark(First, End);
  while (First != End)
    if (lexPPLine(First, End))
      return true;
  return false;
}

bool Minimizer::minimize() {
  bool Error = minimizeImpl(Input.begin(), Input.end());

  if (!Error) {
    // Add a trailing newline and an EOF on success.
    if (!Out.empty() && Out.back() != '\n')
      Out.push_back('\n');
    makeToken(pp_eof);
  }

  // Null-terminate the output. This way the memory buffer that's passed to
  // Clang will not have to worry about the terminating '\0'.
  Out.push_back(0);
  Out.pop_back();
  return Error;
}

bool clang::minimize_source_to_dependency_directives::computeSkippedRanges(
    ArrayRef<Token> Input, llvm::SmallVectorImpl<SkippedRange> &Range) {
  struct Directive {
    enum DirectiveKind {
      If,  // if/ifdef/ifndef
      Else // elif/elifdef/elifndef, else
    };
    int Offset;
    DirectiveKind Kind;
  };
  llvm::SmallVector<Directive, 32> Offsets;
  for (const Token &T : Input) {
    switch (T.K) {
    case pp_if:
    case pp_ifdef:
    case pp_ifndef:
      Offsets.push_back({T.Offset, Directive::If});
      break;

    case pp_elif:
    case pp_elifdef:
    case pp_elifndef:
    case pp_else: {
      if (Offsets.empty())
        return true;
      int PreviousOffset = Offsets.back().Offset;
      Range.push_back({PreviousOffset, T.Offset - PreviousOffset});
      Offsets.push_back({T.Offset, Directive::Else});
      break;
    }

    case pp_endif: {
      if (Offsets.empty())
        return true;
      int PreviousOffset = Offsets.back().Offset;
      Range.push_back({PreviousOffset, T.Offset - PreviousOffset});
      do {
        Directive::DirectiveKind Kind = Offsets.pop_back_val().Kind;
        if (Kind == Directive::If)
          break;
      } while (!Offsets.empty());
      break;
    }
    default:
      break;
    }
  }
  return false;
}

bool clang::minimizeSourceToDependencyDirectives(
    StringRef Input, SmallVectorImpl<char> &Output,
    SmallVectorImpl<Token> &Tokens, DiagnosticsEngine *Diags,
    SourceLocation InputSourceLoc) {
  Output.clear();
  Tokens.clear();
  return Minimizer(Output, Tokens, Input, Diags, InputSourceLoc).minimize();
}