forked from flang-compiler/flang-driver
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathPreprocessor.cpp
1396 lines (1220 loc) · 50.5 KB
/
Preprocessor.cpp
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
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
//===- Preprocessor.cpp - C Language Family Preprocessor Implementation ---===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements the Preprocessor interface.
//
//===----------------------------------------------------------------------===//
//
// Options to support:
// -H - Print the name of each header file used.
// -d[DNI] - Dump various things.
// -fworking-directory - #line's with preprocessor's working dir.
// -fpreprocessed
// -dependency-file,-M,-MM,-MF,-MG,-MP,-MT,-MQ,-MD,-MMD
// -W*
// -w
//
// Messages to emit:
// "Multiple include guards may be useful for:\n"
//
//===----------------------------------------------------------------------===//
#include "clang/Lex/Preprocessor.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/FileSystemStatCache.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/LLVM.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/Module.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Lex/CodeCompletionHandler.h"
#include "clang/Lex/ExternalPreprocessorSource.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Lex/Lexer.h"
#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/MacroArgs.h"
#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/ModuleLoader.h"
#include "clang/Lex/Pragma.h"
#include "clang/Lex/PreprocessingRecord.h"
#include "clang/Lex/PreprocessorLexer.h"
#include "clang/Lex/PreprocessorOptions.h"
#include "clang/Lex/ScratchBuffer.h"
#include "clang/Lex/Token.h"
#include "clang/Lex/TokenLexer.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/Capacity.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cassert>
#include <memory>
#include <string>
#include <utility>
#include <vector>
using namespace clang;
LLVM_INSTANTIATE_REGISTRY(PragmaHandlerRegistry)
ExternalPreprocessorSource::~ExternalPreprocessorSource() = default;
Preprocessor::Preprocessor(std::shared_ptr<PreprocessorOptions> PPOpts,
DiagnosticsEngine &diags, LangOptions &opts,
SourceManager &SM, HeaderSearch &Headers,
ModuleLoader &TheModuleLoader,
IdentifierInfoLookup *IILookup, bool OwnsHeaders,
TranslationUnitKind TUKind)
: PPOpts(std::move(PPOpts)), Diags(&diags), LangOpts(opts),
FileMgr(Headers.getFileMgr()), SourceMgr(SM),
ScratchBuf(new ScratchBuffer(SourceMgr)), HeaderInfo(Headers),
TheModuleLoader(TheModuleLoader), ExternalSource(nullptr),
// As the language options may have not been loaded yet (when
// deserializing an ASTUnit), adding keywords to the identifier table is
// deferred to Preprocessor::Initialize().
Identifiers(IILookup), PragmaHandlers(new PragmaNamespace(StringRef())),
TUKind(TUKind), SkipMainFilePreamble(0, true),
CurSubmoduleState(&NullSubmoduleState) {
OwnsHeaderSearch = OwnsHeaders;
// Default to discarding comments.
KeepComments = false;
KeepMacroComments = false;
SuppressIncludeNotFoundError = false;
// Macro expansion is enabled.
DisableMacroExpansion = false;
MacroExpansionInDirectivesOverride = false;
InMacroArgs = false;
ArgMacro = nullptr;
InMacroArgPreExpansion = false;
NumCachedTokenLexers = 0;
PragmasEnabled = true;
ParsingIfOrElifDirective = false;
PreprocessedOutput = false;
// We haven't read anything from the external source.
ReadMacrosFromExternalSource = false;
// "Poison" __VA_ARGS__, __VA_OPT__ which can only appear in the expansion of
// a macro. They get unpoisoned where it is allowed.
(Ident__VA_ARGS__ = getIdentifierInfo("__VA_ARGS__"))->setIsPoisoned();
SetPoisonReason(Ident__VA_ARGS__,diag::ext_pp_bad_vaargs_use);
if (getLangOpts().CPlusPlus2a) {
(Ident__VA_OPT__ = getIdentifierInfo("__VA_OPT__"))->setIsPoisoned();
SetPoisonReason(Ident__VA_OPT__,diag::ext_pp_bad_vaopt_use);
} else {
Ident__VA_OPT__ = nullptr;
}
// Initialize the pragma handlers.
RegisterBuiltinPragmas();
// Initialize builtin macros like __LINE__ and friends.
RegisterBuiltinMacros();
if(LangOpts.Borland) {
Ident__exception_info = getIdentifierInfo("_exception_info");
Ident___exception_info = getIdentifierInfo("__exception_info");
Ident_GetExceptionInfo = getIdentifierInfo("GetExceptionInformation");
Ident__exception_code = getIdentifierInfo("_exception_code");
Ident___exception_code = getIdentifierInfo("__exception_code");
Ident_GetExceptionCode = getIdentifierInfo("GetExceptionCode");
Ident__abnormal_termination = getIdentifierInfo("_abnormal_termination");
Ident___abnormal_termination = getIdentifierInfo("__abnormal_termination");
Ident_AbnormalTermination = getIdentifierInfo("AbnormalTermination");
} else {
Ident__exception_info = Ident__exception_code = nullptr;
Ident__abnormal_termination = Ident___exception_info = nullptr;
Ident___exception_code = Ident___abnormal_termination = nullptr;
Ident_GetExceptionInfo = Ident_GetExceptionCode = nullptr;
Ident_AbnormalTermination = nullptr;
}
// If using a PCH where a #pragma hdrstop is expected, start skipping tokens.
if (usingPCHWithPragmaHdrStop())
SkippingUntilPragmaHdrStop = true;
// If using a PCH with a through header, start skipping tokens.
if (!this->PPOpts->PCHThroughHeader.empty() &&
!this->PPOpts->ImplicitPCHInclude.empty())
SkippingUntilPCHThroughHeader = true;
if (this->PPOpts->GeneratePreamble)
PreambleConditionalStack.startRecording();
}
Preprocessor::~Preprocessor() {
assert(BacktrackPositions.empty() && "EnableBacktrack/Backtrack imbalance!");
IncludeMacroStack.clear();
// Destroy any macro definitions.
while (MacroInfoChain *I = MIChainHead) {
MIChainHead = I->Next;
I->~MacroInfoChain();
}
// Free any cached macro expanders.
// This populates MacroArgCache, so all TokenLexers need to be destroyed
// before the code below that frees up the MacroArgCache list.
std::fill(TokenLexerCache, TokenLexerCache + NumCachedTokenLexers, nullptr);
CurTokenLexer.reset();
// Free any cached MacroArgs.
for (MacroArgs *ArgList = MacroArgCache; ArgList;)
ArgList = ArgList->deallocate();
// Delete the header search info, if we own it.
if (OwnsHeaderSearch)
delete &HeaderInfo;
}
void Preprocessor::Initialize(const TargetInfo &Target,
const TargetInfo *AuxTarget) {
assert((!this->Target || this->Target == &Target) &&
"Invalid override of target information");
this->Target = &Target;
assert((!this->AuxTarget || this->AuxTarget == AuxTarget) &&
"Invalid override of aux target information.");
this->AuxTarget = AuxTarget;
// Initialize information about built-ins.
BuiltinInfo.InitializeTarget(Target, AuxTarget);
HeaderInfo.setTarget(Target);
// Populate the identifier table with info about keywords for the current language.
Identifiers.AddKeywords(LangOpts);
}
void Preprocessor::InitializeForModelFile() {
NumEnteredSourceFiles = 0;
// Reset pragmas
PragmaHandlersBackup = std::move(PragmaHandlers);
PragmaHandlers = llvm::make_unique<PragmaNamespace>(StringRef());
RegisterBuiltinPragmas();
// Reset PredefinesFileID
PredefinesFileID = FileID();
}
void Preprocessor::FinalizeForModelFile() {
NumEnteredSourceFiles = 1;
PragmaHandlers = std::move(PragmaHandlersBackup);
}
void Preprocessor::DumpToken(const Token &Tok, bool DumpFlags) const {
llvm::errs() << tok::getTokenName(Tok.getKind()) << " '"
<< getSpelling(Tok) << "'";
if (!DumpFlags) return;
llvm::errs() << "\t";
if (Tok.isAtStartOfLine())
llvm::errs() << " [StartOfLine]";
if (Tok.hasLeadingSpace())
llvm::errs() << " [LeadingSpace]";
if (Tok.isExpandDisabled())
llvm::errs() << " [ExpandDisabled]";
if (Tok.needsCleaning()) {
const char *Start = SourceMgr.getCharacterData(Tok.getLocation());
llvm::errs() << " [UnClean='" << StringRef(Start, Tok.getLength())
<< "']";
}
llvm::errs() << "\tLoc=<";
DumpLocation(Tok.getLocation());
llvm::errs() << ">";
}
void Preprocessor::DumpLocation(SourceLocation Loc) const {
Loc.print(llvm::errs(), SourceMgr);
}
void Preprocessor::DumpMacro(const MacroInfo &MI) const {
llvm::errs() << "MACRO: ";
for (unsigned i = 0, e = MI.getNumTokens(); i != e; ++i) {
DumpToken(MI.getReplacementToken(i));
llvm::errs() << " ";
}
llvm::errs() << "\n";
}
void Preprocessor::PrintStats() {
llvm::errs() << "\n*** Preprocessor Stats:\n";
llvm::errs() << NumDirectives << " directives found:\n";
llvm::errs() << " " << NumDefined << " #define.\n";
llvm::errs() << " " << NumUndefined << " #undef.\n";
llvm::errs() << " #include/#include_next/#import:\n";
llvm::errs() << " " << NumEnteredSourceFiles << " source files entered.\n";
llvm::errs() << " " << MaxIncludeStackDepth << " max include stack depth\n";
llvm::errs() << " " << NumIf << " #if/#ifndef/#ifdef.\n";
llvm::errs() << " " << NumElse << " #else/#elif.\n";
llvm::errs() << " " << NumEndif << " #endif.\n";
llvm::errs() << " " << NumPragma << " #pragma.\n";
llvm::errs() << NumSkipped << " #if/#ifndef#ifdef regions skipped\n";
llvm::errs() << NumMacroExpanded << "/" << NumFnMacroExpanded << "/"
<< NumBuiltinMacroExpanded << " obj/fn/builtin macros expanded, "
<< NumFastMacroExpanded << " on the fast path.\n";
llvm::errs() << (NumFastTokenPaste+NumTokenPaste)
<< " token paste (##) operations performed, "
<< NumFastTokenPaste << " on the fast path.\n";
llvm::errs() << "\nPreprocessor Memory: " << getTotalMemory() << "B total";
llvm::errs() << "\n BumpPtr: " << BP.getTotalMemory();
llvm::errs() << "\n Macro Expanded Tokens: "
<< llvm::capacity_in_bytes(MacroExpandedTokens);
llvm::errs() << "\n Predefines Buffer: " << Predefines.capacity();
// FIXME: List information for all submodules.
llvm::errs() << "\n Macros: "
<< llvm::capacity_in_bytes(CurSubmoduleState->Macros);
llvm::errs() << "\n #pragma push_macro Info: "
<< llvm::capacity_in_bytes(PragmaPushMacroInfo);
llvm::errs() << "\n Poison Reasons: "
<< llvm::capacity_in_bytes(PoisonReasons);
llvm::errs() << "\n Comment Handlers: "
<< llvm::capacity_in_bytes(CommentHandlers) << "\n";
}
Preprocessor::macro_iterator
Preprocessor::macro_begin(bool IncludeExternalMacros) const {
if (IncludeExternalMacros && ExternalSource &&
!ReadMacrosFromExternalSource) {
ReadMacrosFromExternalSource = true;
ExternalSource->ReadDefinedMacros();
}
// Make sure we cover all macros in visible modules.
for (const ModuleMacro &Macro : ModuleMacros)
CurSubmoduleState->Macros.insert(std::make_pair(Macro.II, MacroState()));
return CurSubmoduleState->Macros.begin();
}
size_t Preprocessor::getTotalMemory() const {
return BP.getTotalMemory()
+ llvm::capacity_in_bytes(MacroExpandedTokens)
+ Predefines.capacity() /* Predefines buffer. */
// FIXME: Include sizes from all submodules, and include MacroInfo sizes,
// and ModuleMacros.
+ llvm::capacity_in_bytes(CurSubmoduleState->Macros)
+ llvm::capacity_in_bytes(PragmaPushMacroInfo)
+ llvm::capacity_in_bytes(PoisonReasons)
+ llvm::capacity_in_bytes(CommentHandlers);
}
Preprocessor::macro_iterator
Preprocessor::macro_end(bool IncludeExternalMacros) const {
if (IncludeExternalMacros && ExternalSource &&
!ReadMacrosFromExternalSource) {
ReadMacrosFromExternalSource = true;
ExternalSource->ReadDefinedMacros();
}
return CurSubmoduleState->Macros.end();
}
/// Compares macro tokens with a specified token value sequence.
static bool MacroDefinitionEquals(const MacroInfo *MI,
ArrayRef<TokenValue> Tokens) {
return Tokens.size() == MI->getNumTokens() &&
std::equal(Tokens.begin(), Tokens.end(), MI->tokens_begin());
}
StringRef Preprocessor::getLastMacroWithSpelling(
SourceLocation Loc,
ArrayRef<TokenValue> Tokens) const {
SourceLocation BestLocation;
StringRef BestSpelling;
for (Preprocessor::macro_iterator I = macro_begin(), E = macro_end();
I != E; ++I) {
const MacroDirective::DefInfo
Def = I->second.findDirectiveAtLoc(Loc, SourceMgr);
if (!Def || !Def.getMacroInfo())
continue;
if (!Def.getMacroInfo()->isObjectLike())
continue;
if (!MacroDefinitionEquals(Def.getMacroInfo(), Tokens))
continue;
SourceLocation Location = Def.getLocation();
// Choose the macro defined latest.
if (BestLocation.isInvalid() ||
(Location.isValid() &&
SourceMgr.isBeforeInTranslationUnit(BestLocation, Location))) {
BestLocation = Location;
BestSpelling = I->first->getName();
}
}
return BestSpelling;
}
void Preprocessor::recomputeCurLexerKind() {
if (CurLexer)
CurLexerKind = CLK_Lexer;
else if (CurTokenLexer)
CurLexerKind = CLK_TokenLexer;
else
CurLexerKind = CLK_CachingLexer;
}
bool Preprocessor::SetCodeCompletionPoint(const FileEntry *File,
unsigned CompleteLine,
unsigned CompleteColumn) {
assert(File);
assert(CompleteLine && CompleteColumn && "Starts from 1:1");
assert(!CodeCompletionFile && "Already set");
using llvm::MemoryBuffer;
// Load the actual file's contents.
bool Invalid = false;
const MemoryBuffer *Buffer = SourceMgr.getMemoryBufferForFile(File, &Invalid);
if (Invalid)
return true;
// Find the byte position of the truncation point.
const char *Position = Buffer->getBufferStart();
for (unsigned Line = 1; Line < CompleteLine; ++Line) {
for (; *Position; ++Position) {
if (*Position != '\r' && *Position != '\n')
continue;
// Eat \r\n or \n\r as a single line.
if ((Position[1] == '\r' || Position[1] == '\n') &&
Position[0] != Position[1])
++Position;
++Position;
break;
}
}
Position += CompleteColumn - 1;
// If pointing inside the preamble, adjust the position at the beginning of
// the file after the preamble.
if (SkipMainFilePreamble.first &&
SourceMgr.getFileEntryForID(SourceMgr.getMainFileID()) == File) {
if (Position - Buffer->getBufferStart() < SkipMainFilePreamble.first)
Position = Buffer->getBufferStart() + SkipMainFilePreamble.first;
}
if (Position > Buffer->getBufferEnd())
Position = Buffer->getBufferEnd();
CodeCompletionFile = File;
CodeCompletionOffset = Position - Buffer->getBufferStart();
auto NewBuffer = llvm::WritableMemoryBuffer::getNewUninitMemBuffer(
Buffer->getBufferSize() + 1, Buffer->getBufferIdentifier());
char *NewBuf = NewBuffer->getBufferStart();
char *NewPos = std::copy(Buffer->getBufferStart(), Position, NewBuf);
*NewPos = '\0';
std::copy(Position, Buffer->getBufferEnd(), NewPos+1);
SourceMgr.overrideFileContents(File, std::move(NewBuffer));
return false;
}
void Preprocessor::CodeCompleteIncludedFile(llvm::StringRef Dir,
bool IsAngled) {
if (CodeComplete)
CodeComplete->CodeCompleteIncludedFile(Dir, IsAngled);
setCodeCompletionReached();
}
void Preprocessor::CodeCompleteNaturalLanguage() {
if (CodeComplete)
CodeComplete->CodeCompleteNaturalLanguage();
setCodeCompletionReached();
}
/// getSpelling - This method is used to get the spelling of a token into a
/// SmallVector. Note that the returned StringRef may not point to the
/// supplied buffer if a copy can be avoided.
StringRef Preprocessor::getSpelling(const Token &Tok,
SmallVectorImpl<char> &Buffer,
bool *Invalid) const {
// NOTE: this has to be checked *before* testing for an IdentifierInfo.
if (Tok.isNot(tok::raw_identifier) && !Tok.hasUCN()) {
// Try the fast path.
if (const IdentifierInfo *II = Tok.getIdentifierInfo())
return II->getName();
}
// Resize the buffer if we need to copy into it.
if (Tok.needsCleaning())
Buffer.resize(Tok.getLength());
const char *Ptr = Buffer.data();
unsigned Len = getSpelling(Tok, Ptr, Invalid);
return StringRef(Ptr, Len);
}
/// CreateString - Plop the specified string into a scratch buffer and return a
/// location for it. If specified, the source location provides a source
/// location for the token.
void Preprocessor::CreateString(StringRef Str, Token &Tok,
SourceLocation ExpansionLocStart,
SourceLocation ExpansionLocEnd) {
Tok.setLength(Str.size());
const char *DestPtr;
SourceLocation Loc = ScratchBuf->getToken(Str.data(), Str.size(), DestPtr);
if (ExpansionLocStart.isValid())
Loc = SourceMgr.createExpansionLoc(Loc, ExpansionLocStart,
ExpansionLocEnd, Str.size());
Tok.setLocation(Loc);
// If this is a raw identifier or a literal token, set the pointer data.
if (Tok.is(tok::raw_identifier))
Tok.setRawIdentifierData(DestPtr);
else if (Tok.isLiteral())
Tok.setLiteralData(DestPtr);
}
SourceLocation Preprocessor::SplitToken(SourceLocation Loc, unsigned Length) {
auto &SM = getSourceManager();
SourceLocation SpellingLoc = SM.getSpellingLoc(Loc);
std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(SpellingLoc);
bool Invalid = false;
StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
if (Invalid)
return SourceLocation();
// FIXME: We could consider re-using spelling for tokens we see repeatedly.
const char *DestPtr;
SourceLocation Spelling =
ScratchBuf->getToken(Buffer.data() + LocInfo.second, Length, DestPtr);
return SM.createTokenSplitLoc(Spelling, Loc, Loc.getLocWithOffset(Length));
}
Module *Preprocessor::getCurrentModule() {
if (!getLangOpts().isCompilingModule())
return nullptr;
return getHeaderSearchInfo().lookupModule(getLangOpts().CurrentModule);
}
//===----------------------------------------------------------------------===//
// Preprocessor Initialization Methods
//===----------------------------------------------------------------------===//
/// EnterMainSourceFile - Enter the specified FileID as the main source file,
/// which implicitly adds the builtin defines etc.
void Preprocessor::EnterMainSourceFile() {
// We do not allow the preprocessor to reenter the main file. Doing so will
// cause FileID's to accumulate information from both runs (e.g. #line
// information) and predefined macros aren't guaranteed to be set properly.
assert(NumEnteredSourceFiles == 0 && "Cannot reenter the main file!");
FileID MainFileID = SourceMgr.getMainFileID();
// If MainFileID is loaded it means we loaded an AST file, no need to enter
// a main file.
if (!SourceMgr.isLoadedFileID(MainFileID)) {
// Enter the main file source buffer.
EnterSourceFile(MainFileID, nullptr, SourceLocation());
// If we've been asked to skip bytes in the main file (e.g., as part of a
// precompiled preamble), do so now.
if (SkipMainFilePreamble.first > 0)
CurLexer->SetByteOffset(SkipMainFilePreamble.first,
SkipMainFilePreamble.second);
// Tell the header info that the main file was entered. If the file is later
// #imported, it won't be re-entered.
if (const FileEntry *FE = SourceMgr.getFileEntryForID(MainFileID))
HeaderInfo.IncrementIncludeCount(FE);
}
// Preprocess Predefines to populate the initial preprocessor state.
std::unique_ptr<llvm::MemoryBuffer> SB =
llvm::MemoryBuffer::getMemBufferCopy(Predefines, "<built-in>");
assert(SB && "Cannot create predefined source buffer");
FileID FID = SourceMgr.createFileID(std::move(SB));
assert(FID.isValid() && "Could not create FileID for predefines?");
setPredefinesFileID(FID);
// Start parsing the predefines.
EnterSourceFile(FID, nullptr, SourceLocation());
if (!PPOpts->PCHThroughHeader.empty()) {
// Lookup and save the FileID for the through header. If it isn't found
// in the search path, it's a fatal error.
const DirectoryLookup *CurDir;
const FileEntry *File = LookupFile(
SourceLocation(), PPOpts->PCHThroughHeader,
/*isAngled=*/false, /*FromDir=*/nullptr, /*FromFile=*/nullptr, CurDir,
/*SearchPath=*/nullptr, /*RelativePath=*/nullptr,
/*SuggestedModule=*/nullptr, /*IsMapped=*/nullptr,
/*IsFrameworkFound=*/nullptr);
if (!File) {
Diag(SourceLocation(), diag::err_pp_through_header_not_found)
<< PPOpts->PCHThroughHeader;
return;
}
setPCHThroughHeaderFileID(
SourceMgr.createFileID(File, SourceLocation(), SrcMgr::C_User));
}
// Skip tokens from the Predefines and if needed the main file.
if ((usingPCHWithThroughHeader() && SkippingUntilPCHThroughHeader) ||
(usingPCHWithPragmaHdrStop() && SkippingUntilPragmaHdrStop))
SkipTokensWhileUsingPCH();
}
void Preprocessor::setPCHThroughHeaderFileID(FileID FID) {
assert(PCHThroughHeaderFileID.isInvalid() &&
"PCHThroughHeaderFileID already set!");
PCHThroughHeaderFileID = FID;
}
bool Preprocessor::isPCHThroughHeader(const FileEntry *FE) {
assert(PCHThroughHeaderFileID.isValid() &&
"Invalid PCH through header FileID");
return FE == SourceMgr.getFileEntryForID(PCHThroughHeaderFileID);
}
bool Preprocessor::creatingPCHWithThroughHeader() {
return TUKind == TU_Prefix && !PPOpts->PCHThroughHeader.empty() &&
PCHThroughHeaderFileID.isValid();
}
bool Preprocessor::usingPCHWithThroughHeader() {
return TUKind != TU_Prefix && !PPOpts->PCHThroughHeader.empty() &&
PCHThroughHeaderFileID.isValid();
}
bool Preprocessor::creatingPCHWithPragmaHdrStop() {
return TUKind == TU_Prefix && PPOpts->PCHWithHdrStop;
}
bool Preprocessor::usingPCHWithPragmaHdrStop() {
return TUKind != TU_Prefix && PPOpts->PCHWithHdrStop;
}
/// Skip tokens until after the #include of the through header or
/// until after a #pragma hdrstop is seen. Tokens in the predefines file
/// and the main file may be skipped. If the end of the predefines file
/// is reached, skipping continues into the main file. If the end of the
/// main file is reached, it's a fatal error.
void Preprocessor::SkipTokensWhileUsingPCH() {
bool ReachedMainFileEOF = false;
bool UsingPCHThroughHeader = SkippingUntilPCHThroughHeader;
bool UsingPragmaHdrStop = SkippingUntilPragmaHdrStop;
Token Tok;
while (true) {
bool InPredefines =
(CurLexer && CurLexer->getFileID() == getPredefinesFileID());
switch (CurLexerKind) {
case CLK_Lexer:
CurLexer->Lex(Tok);
break;
case CLK_TokenLexer:
CurTokenLexer->Lex(Tok);
break;
case CLK_CachingLexer:
CachingLex(Tok);
break;
case CLK_LexAfterModuleImport:
LexAfterModuleImport(Tok);
break;
}
if (Tok.is(tok::eof) && !InPredefines) {
ReachedMainFileEOF = true;
break;
}
if (UsingPCHThroughHeader && !SkippingUntilPCHThroughHeader)
break;
if (UsingPragmaHdrStop && !SkippingUntilPragmaHdrStop)
break;
}
if (ReachedMainFileEOF) {
if (UsingPCHThroughHeader)
Diag(SourceLocation(), diag::err_pp_through_header_not_seen)
<< PPOpts->PCHThroughHeader << 1;
else if (!PPOpts->PCHWithHdrStopCreate)
Diag(SourceLocation(), diag::err_pp_pragma_hdrstop_not_seen);
}
}
void Preprocessor::replayPreambleConditionalStack() {
// Restore the conditional stack from the preamble, if there is one.
if (PreambleConditionalStack.isReplaying()) {
assert(CurPPLexer &&
"CurPPLexer is null when calling replayPreambleConditionalStack.");
CurPPLexer->setConditionalLevels(PreambleConditionalStack.getStack());
PreambleConditionalStack.doneReplaying();
if (PreambleConditionalStack.reachedEOFWhileSkipping())
SkipExcludedConditionalBlock(
PreambleConditionalStack.SkipInfo->HashTokenLoc,
PreambleConditionalStack.SkipInfo->IfTokenLoc,
PreambleConditionalStack.SkipInfo->FoundNonSkipPortion,
PreambleConditionalStack.SkipInfo->FoundElse,
PreambleConditionalStack.SkipInfo->ElseLoc);
}
}
void Preprocessor::EndSourceFile() {
// Notify the client that we reached the end of the source file.
if (Callbacks)
Callbacks->EndOfMainFile();
}
//===----------------------------------------------------------------------===//
// Lexer Event Handling.
//===----------------------------------------------------------------------===//
/// LookUpIdentifierInfo - Given a tok::raw_identifier token, look up the
/// identifier information for the token and install it into the token,
/// updating the token kind accordingly.
IdentifierInfo *Preprocessor::LookUpIdentifierInfo(Token &Identifier) const {
assert(!Identifier.getRawIdentifier().empty() && "No raw identifier data!");
// Look up this token, see if it is a macro, or if it is a language keyword.
IdentifierInfo *II;
if (!Identifier.needsCleaning() && !Identifier.hasUCN()) {
// No cleaning needed, just use the characters from the lexed buffer.
II = getIdentifierInfo(Identifier.getRawIdentifier());
} else {
// Cleaning needed, alloca a buffer, clean into it, then use the buffer.
SmallString<64> IdentifierBuffer;
StringRef CleanedStr = getSpelling(Identifier, IdentifierBuffer);
if (Identifier.hasUCN()) {
SmallString<64> UCNIdentifierBuffer;
expandUCNs(UCNIdentifierBuffer, CleanedStr);
II = getIdentifierInfo(UCNIdentifierBuffer);
} else {
II = getIdentifierInfo(CleanedStr);
}
}
// Update the token info (identifier info and appropriate token kind).
Identifier.setIdentifierInfo(II);
if (getLangOpts().MSVCCompat && II->isCPlusPlusOperatorKeyword() &&
getSourceManager().isInSystemHeader(Identifier.getLocation()))
Identifier.setKind(tok::identifier);
else
Identifier.setKind(II->getTokenID());
return II;
}
void Preprocessor::SetPoisonReason(IdentifierInfo *II, unsigned DiagID) {
PoisonReasons[II] = DiagID;
}
void Preprocessor::PoisonSEHIdentifiers(bool Poison) {
assert(Ident__exception_code && Ident__exception_info);
assert(Ident___exception_code && Ident___exception_info);
Ident__exception_code->setIsPoisoned(Poison);
Ident___exception_code->setIsPoisoned(Poison);
Ident_GetExceptionCode->setIsPoisoned(Poison);
Ident__exception_info->setIsPoisoned(Poison);
Ident___exception_info->setIsPoisoned(Poison);
Ident_GetExceptionInfo->setIsPoisoned(Poison);
Ident__abnormal_termination->setIsPoisoned(Poison);
Ident___abnormal_termination->setIsPoisoned(Poison);
Ident_AbnormalTermination->setIsPoisoned(Poison);
}
void Preprocessor::HandlePoisonedIdentifier(Token & Identifier) {
assert(Identifier.getIdentifierInfo() &&
"Can't handle identifiers without identifier info!");
llvm::DenseMap<IdentifierInfo*,unsigned>::const_iterator it =
PoisonReasons.find(Identifier.getIdentifierInfo());
if(it == PoisonReasons.end())
Diag(Identifier, diag::err_pp_used_poisoned_id);
else
Diag(Identifier,it->second) << Identifier.getIdentifierInfo();
}
/// Returns a diagnostic message kind for reporting a future keyword as
/// appropriate for the identifier and specified language.
static diag::kind getFutureCompatDiagKind(const IdentifierInfo &II,
const LangOptions &LangOpts) {
assert(II.isFutureCompatKeyword() && "diagnostic should not be needed");
if (LangOpts.CPlusPlus)
return llvm::StringSwitch<diag::kind>(II.getName())
#define CXX11_KEYWORD(NAME, FLAGS) \
.Case(#NAME, diag::warn_cxx11_keyword)
#define CXX2A_KEYWORD(NAME, FLAGS) \
.Case(#NAME, diag::warn_cxx2a_keyword)
#include "clang/Basic/TokenKinds.def"
;
llvm_unreachable(
"Keyword not known to come from a newer Standard or proposed Standard");
}
void Preprocessor::updateOutOfDateIdentifier(IdentifierInfo &II) const {
assert(II.isOutOfDate() && "not out of date");
getExternalSource()->updateOutOfDateIdentifier(II);
}
/// HandleIdentifier - This callback is invoked when the lexer reads an
/// identifier. This callback looks up the identifier in the map and/or
/// potentially macro expands it or turns it into a named token (like 'for').
///
/// Note that callers of this method are guarded by checking the
/// IdentifierInfo's 'isHandleIdentifierCase' bit. If this method changes, the
/// IdentifierInfo methods that compute these properties will need to change to
/// match.
bool Preprocessor::HandleIdentifier(Token &Identifier) {
assert(Identifier.getIdentifierInfo() &&
"Can't handle identifiers without identifier info!");
IdentifierInfo &II = *Identifier.getIdentifierInfo();
// If the information about this identifier is out of date, update it from
// the external source.
// We have to treat __VA_ARGS__ in a special way, since it gets
// serialized with isPoisoned = true, but our preprocessor may have
// unpoisoned it if we're defining a C99 macro.
if (II.isOutOfDate()) {
bool CurrentIsPoisoned = false;
const bool IsSpecialVariadicMacro =
&II == Ident__VA_ARGS__ || &II == Ident__VA_OPT__;
if (IsSpecialVariadicMacro)
CurrentIsPoisoned = II.isPoisoned();
updateOutOfDateIdentifier(II);
Identifier.setKind(II.getTokenID());
if (IsSpecialVariadicMacro)
II.setIsPoisoned(CurrentIsPoisoned);
}
// If this identifier was poisoned, and if it was not produced from a macro
// expansion, emit an error.
if (II.isPoisoned() && CurPPLexer) {
HandlePoisonedIdentifier(Identifier);
}
// If this is a macro to be expanded, do it.
if (MacroDefinition MD = getMacroDefinition(&II)) {
auto *MI = MD.getMacroInfo();
assert(MI && "macro definition with no macro info?");
if (!DisableMacroExpansion) {
if (!Identifier.isExpandDisabled() && MI->isEnabled()) {
// C99 6.10.3p10: If the preprocessing token immediately after the
// macro name isn't a '(', this macro should not be expanded.
if (!MI->isFunctionLike() || isNextPPTokenLParen())
return HandleMacroExpandedIdentifier(Identifier, MD);
} else {
// C99 6.10.3.4p2 says that a disabled macro may never again be
// expanded, even if it's in a context where it could be expanded in the
// future.
Identifier.setFlag(Token::DisableExpand);
if (MI->isObjectLike() || isNextPPTokenLParen())
Diag(Identifier, diag::pp_disabled_macro_expansion);
}
}
}
// If this identifier is a keyword in a newer Standard or proposed Standard,
// produce a warning. Don't warn if we're not considering macro expansion,
// since this identifier might be the name of a macro.
// FIXME: This warning is disabled in cases where it shouldn't be, like
// "#define constexpr constexpr", "int constexpr;"
if (II.isFutureCompatKeyword() && !DisableMacroExpansion) {
Diag(Identifier, getFutureCompatDiagKind(II, getLangOpts()))
<< II.getName();
// Don't diagnose this keyword again in this translation unit.
II.setIsFutureCompatKeyword(false);
}
// If this is an extension token, diagnose its use.
// We avoid diagnosing tokens that originate from macro definitions.
// FIXME: This warning is disabled in cases where it shouldn't be,
// like "#define TY typeof", "TY(1) x".
if (II.isExtensionToken() && !DisableMacroExpansion)
Diag(Identifier, diag::ext_token_used);
// If this is the 'import' contextual keyword following an '@', note
// that the next token indicates a module name.
//
// Note that we do not treat 'import' as a contextual
// keyword when we're in a caching lexer, because caching lexers only get
// used in contexts where import declarations are disallowed.
//
// Likewise if this is the C++ Modules TS import keyword.
if (((LastTokenWasAt && II.isModulesImport()) ||
Identifier.is(tok::kw_import)) &&
!InMacroArgs && !DisableMacroExpansion &&
(getLangOpts().Modules || getLangOpts().DebuggerSupport) &&
CurLexerKind != CLK_CachingLexer) {
ModuleImportLoc = Identifier.getLocation();
ModuleImportPath.clear();
ModuleImportExpectsIdentifier = true;
CurLexerKind = CLK_LexAfterModuleImport;
}
return true;
}
void Preprocessor::Lex(Token &Result) {
++LexLevel;
// We loop here until a lex function returns a token; this avoids recursion.
bool ReturnedToken;
do {
switch (CurLexerKind) {
case CLK_Lexer:
ReturnedToken = CurLexer->Lex(Result);
break;
case CLK_TokenLexer:
ReturnedToken = CurTokenLexer->Lex(Result);
break;
case CLK_CachingLexer:
CachingLex(Result);
ReturnedToken = true;
break;
case CLK_LexAfterModuleImport:
ReturnedToken = LexAfterModuleImport(Result);
break;
}
} while (!ReturnedToken);
if (Result.is(tok::code_completion) && Result.getIdentifierInfo()) {
// Remember the identifier before code completion token.
setCodeCompletionIdentifierInfo(Result.getIdentifierInfo());
setCodeCompletionTokenRange(Result.getLocation(), Result.getEndLoc());
// Set IdenfitierInfo to null to avoid confusing code that handles both
// identifiers and completion tokens.
Result.setIdentifierInfo(nullptr);
}
// Update ImportSeqState to track our position within a C++20 import-seq
// if this token is being produced as a result of phase 4 of translation.
if (getLangOpts().CPlusPlusModules && LexLevel == 1 &&
!Result.getFlag(Token::IsReinjected)) {
switch (Result.getKind()) {
case tok::l_paren: case tok::l_square: case tok::l_brace:
ImportSeqState.handleOpenBracket();
break;
case tok::r_paren: case tok::r_square:
ImportSeqState.handleCloseBracket();
break;
case tok::r_brace:
ImportSeqState.handleCloseBrace();
break;
case tok::semi:
ImportSeqState.handleSemi();
break;
case tok::header_name:
case tok::annot_header_unit:
ImportSeqState.handleHeaderName();
break;
case tok::kw_export:
ImportSeqState.handleExport();
break;
case tok::identifier:
if (Result.getIdentifierInfo()->isModulesImport()) {
ImportSeqState.handleImport();
if (ImportSeqState.afterImportSeq()) {
ModuleImportLoc = Result.getLocation();
ModuleImportPath.clear();
ModuleImportExpectsIdentifier = true;
CurLexerKind = CLK_LexAfterModuleImport;
}
break;
}
LLVM_FALLTHROUGH;
default:
ImportSeqState.handleMisc();
break;
}
}
LastTokenWasAt = Result.is(tok::at);
--LexLevel;
if (OnToken && LexLevel == 0 && !Result.getFlag(Token::IsReinjected))
OnToken(Result);
}
/// Lex a header-name token (including one formed from header-name-tokens if
/// \p AllowConcatenation is \c true).
///
/// \param FilenameTok Filled in with the next token. On success, this will
/// be either a header_name token. On failure, it will be whatever other
/// token was found instead.
/// \param AllowMacroExpansion If \c true, allow the header name to be formed
/// by macro expansion (concatenating tokens as necessary if the first
/// token is a '<').
/// \return \c true if we reached EOD or EOF while looking for a > token in
/// a concatenated header name and diagnosed it. \c false otherwise.
bool Preprocessor::LexHeaderName(Token &FilenameTok, bool AllowMacroExpansion) {
// Lex using header-name tokenization rules if tokens are being lexed from
// a file. Just grab a token normally if we're in a macro expansion.
if (CurPPLexer)
CurPPLexer->LexIncludeFilename(FilenameTok);
else
Lex(FilenameTok);
// This could be a <foo/bar.h> file coming from a macro expansion. In this
// case, glue the tokens together into an angle_string_literal token.
SmallString<128> FilenameBuffer;
if (FilenameTok.is(tok::less) && AllowMacroExpansion) {
bool StartOfLine = FilenameTok.isAtStartOfLine();
bool LeadingSpace = FilenameTok.hasLeadingSpace();
bool LeadingEmptyMacro = FilenameTok.hasLeadingEmptyMacro();
SourceLocation Start = FilenameTok.getLocation();
SourceLocation End;
FilenameBuffer.push_back('<');
// Consume tokens until we find a '>'.
// FIXME: A header-name could be formed starting or ending with an
// alternative token. It's not clear whether that's ill-formed in all
// cases.
while (FilenameTok.isNot(tok::greater)) {
Lex(FilenameTok);
if (FilenameTok.isOneOf(tok::eod, tok::eof)) {
Diag(FilenameTok.getLocation(), diag::err_expected) << tok::greater;
Diag(Start, diag::note_matching) << tok::less;
return true;
}