forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathUnwrappedLineParser.cpp
3618 lines (3304 loc) · 113 KB
/
UnwrappedLineParser.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
//===--- UnwrappedLineParser.cpp - Format C++ code ------------------------===//
//
// 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 file contains the implementation of the UnwrappedLineParser,
/// which turns a stream of tokens into UnwrappedLines.
///
//===----------------------------------------------------------------------===//
#include "UnwrappedLineParser.h"
#include "FormatToken.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#define DEBUG_TYPE "format-parser"
namespace clang {
namespace format {
class FormatTokenSource {
public:
virtual ~FormatTokenSource() {}
// Returns the next token in the token stream.
virtual FormatToken *getNextToken() = 0;
// Returns the token preceding the token returned by the last call to
// getNextToken() in the token stream, or nullptr if no such token exists.
virtual FormatToken *getPreviousToken() = 0;
// Returns the token that would be returned by the next call to
// getNextToken().
virtual FormatToken *peekNextToken() = 0;
// Returns whether we are at the end of the file.
// This can be different from whether getNextToken() returned an eof token
// when the FormatTokenSource is a view on a part of the token stream.
virtual bool isEOF() = 0;
// Gets the current position in the token stream, to be used by setPosition().
virtual unsigned getPosition() = 0;
// Resets the token stream to the state it was in when getPosition() returned
// Position, and return the token at that position in the stream.
virtual FormatToken *setPosition(unsigned Position) = 0;
};
namespace {
class ScopedDeclarationState {
public:
ScopedDeclarationState(UnwrappedLine &Line, llvm::BitVector &Stack,
bool MustBeDeclaration)
: Line(Line), Stack(Stack) {
Line.MustBeDeclaration = MustBeDeclaration;
Stack.push_back(MustBeDeclaration);
}
~ScopedDeclarationState() {
Stack.pop_back();
if (!Stack.empty())
Line.MustBeDeclaration = Stack.back();
else
Line.MustBeDeclaration = true;
}
private:
UnwrappedLine &Line;
llvm::BitVector &Stack;
};
static bool isLineComment(const FormatToken &FormatTok) {
return FormatTok.is(tok::comment) && !FormatTok.TokenText.startswith("/*");
}
// Checks if \p FormatTok is a line comment that continues the line comment
// \p Previous. The original column of \p MinColumnToken is used to determine
// whether \p FormatTok is indented enough to the right to continue \p Previous.
static bool continuesLineComment(const FormatToken &FormatTok,
const FormatToken *Previous,
const FormatToken *MinColumnToken) {
if (!Previous || !MinColumnToken)
return false;
unsigned MinContinueColumn =
MinColumnToken->OriginalColumn + (isLineComment(*MinColumnToken) ? 0 : 1);
return isLineComment(FormatTok) && FormatTok.NewlinesBefore == 1 &&
isLineComment(*Previous) &&
FormatTok.OriginalColumn >= MinContinueColumn;
}
class ScopedMacroState : public FormatTokenSource {
public:
ScopedMacroState(UnwrappedLine &Line, FormatTokenSource *&TokenSource,
FormatToken *&ResetToken)
: Line(Line), TokenSource(TokenSource), ResetToken(ResetToken),
PreviousLineLevel(Line.Level), PreviousTokenSource(TokenSource),
Token(nullptr), PreviousToken(nullptr) {
FakeEOF.Tok.startToken();
FakeEOF.Tok.setKind(tok::eof);
TokenSource = this;
Line.Level = 0;
Line.InPPDirective = true;
}
~ScopedMacroState() override {
TokenSource = PreviousTokenSource;
ResetToken = Token;
Line.InPPDirective = false;
Line.Level = PreviousLineLevel;
}
FormatToken *getNextToken() override {
// The \c UnwrappedLineParser guards against this by never calling
// \c getNextToken() after it has encountered the first eof token.
assert(!eof());
PreviousToken = Token;
Token = PreviousTokenSource->getNextToken();
if (eof())
return &FakeEOF;
return Token;
}
FormatToken *getPreviousToken() override {
return PreviousTokenSource->getPreviousToken();
}
FormatToken *peekNextToken() override {
if (eof())
return &FakeEOF;
return PreviousTokenSource->peekNextToken();
}
bool isEOF() override { return PreviousTokenSource->isEOF(); }
unsigned getPosition() override { return PreviousTokenSource->getPosition(); }
FormatToken *setPosition(unsigned Position) override {
PreviousToken = nullptr;
Token = PreviousTokenSource->setPosition(Position);
return Token;
}
private:
bool eof() {
return Token && Token->HasUnescapedNewline &&
!continuesLineComment(*Token, PreviousToken,
/*MinColumnToken=*/PreviousToken);
}
FormatToken FakeEOF;
UnwrappedLine &Line;
FormatTokenSource *&TokenSource;
FormatToken *&ResetToken;
unsigned PreviousLineLevel;
FormatTokenSource *PreviousTokenSource;
FormatToken *Token;
FormatToken *PreviousToken;
};
} // end anonymous namespace
class ScopedLineState {
public:
ScopedLineState(UnwrappedLineParser &Parser,
bool SwitchToPreprocessorLines = false)
: Parser(Parser), OriginalLines(Parser.CurrentLines) {
if (SwitchToPreprocessorLines)
Parser.CurrentLines = &Parser.PreprocessorDirectives;
else if (!Parser.Line->Tokens.empty())
Parser.CurrentLines = &Parser.Line->Tokens.back().Children;
PreBlockLine = std::move(Parser.Line);
Parser.Line = std::make_unique<UnwrappedLine>();
Parser.Line->Level = PreBlockLine->Level;
Parser.Line->InPPDirective = PreBlockLine->InPPDirective;
}
~ScopedLineState() {
if (!Parser.Line->Tokens.empty())
Parser.addUnwrappedLine();
assert(Parser.Line->Tokens.empty());
Parser.Line = std::move(PreBlockLine);
if (Parser.CurrentLines == &Parser.PreprocessorDirectives)
Parser.MustBreakBeforeNextToken = true;
Parser.CurrentLines = OriginalLines;
}
private:
UnwrappedLineParser &Parser;
std::unique_ptr<UnwrappedLine> PreBlockLine;
SmallVectorImpl<UnwrappedLine> *OriginalLines;
};
class CompoundStatementIndenter {
public:
CompoundStatementIndenter(UnwrappedLineParser *Parser,
const FormatStyle &Style, unsigned &LineLevel)
: CompoundStatementIndenter(Parser, LineLevel,
Style.BraceWrapping.AfterControlStatement,
Style.BraceWrapping.IndentBraces) {}
CompoundStatementIndenter(UnwrappedLineParser *Parser, unsigned &LineLevel,
bool WrapBrace, bool IndentBrace)
: LineLevel(LineLevel), OldLineLevel(LineLevel) {
if (WrapBrace)
Parser->addUnwrappedLine();
if (IndentBrace)
++LineLevel;
}
~CompoundStatementIndenter() { LineLevel = OldLineLevel; }
private:
unsigned &LineLevel;
unsigned OldLineLevel;
};
namespace {
class IndexedTokenSource : public FormatTokenSource {
public:
IndexedTokenSource(ArrayRef<FormatToken *> Tokens)
: Tokens(Tokens), Position(-1) {}
FormatToken *getNextToken() override {
if (Position >= 0 && Tokens[Position]->is(tok::eof)) {
LLVM_DEBUG({
llvm::dbgs() << "Next ";
dbgToken(Position);
});
return Tokens[Position];
}
++Position;
LLVM_DEBUG({
llvm::dbgs() << "Next ";
dbgToken(Position);
});
return Tokens[Position];
}
FormatToken *getPreviousToken() override {
return Position > 0 ? Tokens[Position - 1] : nullptr;
}
FormatToken *peekNextToken() override {
int Next = Position + 1;
LLVM_DEBUG({
llvm::dbgs() << "Peeking ";
dbgToken(Next);
});
return Tokens[Next];
}
bool isEOF() override { return Tokens[Position]->is(tok::eof); }
unsigned getPosition() override {
LLVM_DEBUG(llvm::dbgs() << "Getting Position: " << Position << "\n");
assert(Position >= 0);
return Position;
}
FormatToken *setPosition(unsigned P) override {
LLVM_DEBUG(llvm::dbgs() << "Setting Position: " << P << "\n");
Position = P;
return Tokens[Position];
}
void reset() { Position = -1; }
private:
void dbgToken(int Position, llvm::StringRef Indent = "") {
FormatToken *Tok = Tokens[Position];
llvm::dbgs() << Indent << "[" << Position
<< "] Token: " << Tok->Tok.getName() << " / " << Tok->TokenText
<< ", Macro: " << !!Tok->MacroCtx << "\n";
}
ArrayRef<FormatToken *> Tokens;
int Position;
};
} // end anonymous namespace
UnwrappedLineParser::UnwrappedLineParser(const FormatStyle &Style,
const AdditionalKeywords &Keywords,
unsigned FirstStartColumn,
ArrayRef<FormatToken *> Tokens,
UnwrappedLineConsumer &Callback)
: Line(new UnwrappedLine), MustBreakBeforeNextToken(false),
CurrentLines(&Lines), Style(Style), Keywords(Keywords),
CommentPragmasRegex(Style.CommentPragmas), Tokens(nullptr),
Callback(Callback), AllTokens(Tokens), PPBranchLevel(-1),
IncludeGuard(Style.IndentPPDirectives == FormatStyle::PPDIS_None
? IG_Rejected
: IG_Inited),
IncludeGuardToken(nullptr), FirstStartColumn(FirstStartColumn) {}
void UnwrappedLineParser::reset() {
PPBranchLevel = -1;
IncludeGuard = Style.IndentPPDirectives == FormatStyle::PPDIS_None
? IG_Rejected
: IG_Inited;
IncludeGuardToken = nullptr;
Line.reset(new UnwrappedLine);
CommentsBeforeNextToken.clear();
FormatTok = nullptr;
MustBreakBeforeNextToken = false;
PreprocessorDirectives.clear();
CurrentLines = &Lines;
DeclarationScopeStack.clear();
NestedTooDeep.clear();
PPStack.clear();
Line->FirstStartColumn = FirstStartColumn;
}
void UnwrappedLineParser::parse() {
IndexedTokenSource TokenSource(AllTokens);
Line->FirstStartColumn = FirstStartColumn;
do {
LLVM_DEBUG(llvm::dbgs() << "----\n");
reset();
Tokens = &TokenSource;
TokenSource.reset();
readToken();
parseFile();
// If we found an include guard then all preprocessor directives (other than
// the guard) are over-indented by one.
if (IncludeGuard == IG_Found)
for (auto &Line : Lines)
if (Line.InPPDirective && Line.Level > 0)
--Line.Level;
// Create line with eof token.
pushToken(FormatTok);
addUnwrappedLine();
for (const UnwrappedLine &Line : Lines)
Callback.consumeUnwrappedLine(Line);
Callback.finishRun();
Lines.clear();
while (!PPLevelBranchIndex.empty() &&
PPLevelBranchIndex.back() + 1 >= PPLevelBranchCount.back()) {
PPLevelBranchIndex.resize(PPLevelBranchIndex.size() - 1);
PPLevelBranchCount.resize(PPLevelBranchCount.size() - 1);
}
if (!PPLevelBranchIndex.empty()) {
++PPLevelBranchIndex.back();
assert(PPLevelBranchIndex.size() == PPLevelBranchCount.size());
assert(PPLevelBranchIndex.back() <= PPLevelBranchCount.back());
}
} while (!PPLevelBranchIndex.empty());
}
void UnwrappedLineParser::parseFile() {
// The top-level context in a file always has declarations, except for pre-
// processor directives and JavaScript files.
bool MustBeDeclaration = !Line->InPPDirective && !Style.isJavaScript();
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
MustBeDeclaration);
if (Style.Language == FormatStyle::LK_TextProto)
parseBracedList();
else
parseLevel(/*HasOpeningBrace=*/false);
// Make sure to format the remaining tokens.
//
// LK_TextProto is special since its top-level is parsed as the body of a
// braced list, which does not necessarily have natural line separators such
// as a semicolon. Comments after the last entry that have been determined to
// not belong to that line, as in:
// key: value
// // endfile comment
// do not have a chance to be put on a line of their own until this point.
// Here we add this newline before end-of-file comments.
if (Style.Language == FormatStyle::LK_TextProto &&
!CommentsBeforeNextToken.empty())
addUnwrappedLine();
flushComments(true);
addUnwrappedLine();
}
void UnwrappedLineParser::parseCSharpGenericTypeConstraint() {
do {
switch (FormatTok->Tok.getKind()) {
case tok::l_brace:
return;
default:
if (FormatTok->is(Keywords.kw_where)) {
addUnwrappedLine();
nextToken();
parseCSharpGenericTypeConstraint();
break;
}
nextToken();
break;
}
} while (!eof());
}
void UnwrappedLineParser::parseCSharpAttribute() {
int UnpairedSquareBrackets = 1;
do {
switch (FormatTok->Tok.getKind()) {
case tok::r_square:
nextToken();
--UnpairedSquareBrackets;
if (UnpairedSquareBrackets == 0) {
addUnwrappedLine();
return;
}
break;
case tok::l_square:
++UnpairedSquareBrackets;
nextToken();
break;
default:
nextToken();
break;
}
} while (!eof());
}
bool UnwrappedLineParser::precededByCommentOrPPDirective() const {
if (!Lines.empty() && Lines.back().InPPDirective)
return true;
const FormatToken *Previous = Tokens->getPreviousToken();
return Previous && Previous->is(tok::comment) &&
(Previous->IsMultiline || Previous->NewlinesBefore > 0);
}
// Returns true if a simple block, or false otherwise. (A simple block has a
// single statement.)
bool UnwrappedLineParser::parseLevel(bool HasOpeningBrace, IfStmtKind *IfKind) {
const bool IsPrecededByCommentOrPPDirective =
!Style.RemoveBracesLLVM || precededByCommentOrPPDirective();
unsigned StatementCount = 0;
bool SwitchLabelEncountered = false;
do {
tok::TokenKind kind = FormatTok->Tok.getKind();
if (FormatTok->getType() == TT_MacroBlockBegin)
kind = tok::l_brace;
else if (FormatTok->getType() == TT_MacroBlockEnd)
kind = tok::r_brace;
switch (kind) {
case tok::comment:
nextToken();
addUnwrappedLine();
break;
case tok::l_brace:
// FIXME: Add parameter whether this can happen - if this happens, we must
// be in a non-declaration context.
if (!FormatTok->is(TT_MacroBlockBegin) && tryToParseBracedList())
continue;
parseBlock();
++StatementCount;
assert(StatementCount > 0 && "StatementCount overflow!");
addUnwrappedLine();
break;
case tok::r_brace:
if (HasOpeningBrace) {
if (!Style.RemoveBracesLLVM)
return false;
if (FormatTok->isNot(tok::r_brace) || StatementCount != 1 ||
IsPrecededByCommentOrPPDirective ||
precededByCommentOrPPDirective())
return false;
const FormatToken *Next = Tokens->peekNextToken();
return Next->isNot(tok::comment) || Next->NewlinesBefore > 0;
}
nextToken();
addUnwrappedLine();
break;
case tok::kw_default: {
unsigned StoredPosition = Tokens->getPosition();
FormatToken *Next;
do {
Next = Tokens->getNextToken();
assert(Next);
} while (Next->is(tok::comment));
FormatTok = Tokens->setPosition(StoredPosition);
if (Next->isNot(tok::colon)) {
// default not followed by ':' is not a case label; treat it like
// an identifier.
parseStructuralElement();
break;
}
// Else, if it is 'default:', fall through to the case handling.
LLVM_FALLTHROUGH;
}
case tok::kw_case:
if (Style.isJavaScript() && Line->MustBeDeclaration) {
// A 'case: string' style field declaration.
parseStructuralElement();
break;
}
if (!SwitchLabelEncountered &&
(Style.IndentCaseLabels || (Line->InPPDirective && Line->Level == 1)))
++Line->Level;
SwitchLabelEncountered = true;
parseStructuralElement();
break;
case tok::l_square:
if (Style.isCSharp()) {
nextToken();
parseCSharpAttribute();
break;
}
LLVM_FALLTHROUGH;
default:
parseStructuralElement(IfKind, !HasOpeningBrace);
++StatementCount;
assert(StatementCount > 0 && "StatementCount overflow!");
break;
}
} while (!eof());
return false;
}
void UnwrappedLineParser::calculateBraceTypes(bool ExpectClassBody) {
// We'll parse forward through the tokens until we hit
// a closing brace or eof - note that getNextToken() will
// parse macros, so this will magically work inside macro
// definitions, too.
unsigned StoredPosition = Tokens->getPosition();
FormatToken *Tok = FormatTok;
const FormatToken *PrevTok = Tok->Previous;
// Keep a stack of positions of lbrace tokens. We will
// update information about whether an lbrace starts a
// braced init list or a different block during the loop.
SmallVector<FormatToken *, 8> LBraceStack;
assert(Tok->Tok.is(tok::l_brace));
do {
// Get next non-comment token.
FormatToken *NextTok;
unsigned ReadTokens = 0;
do {
NextTok = Tokens->getNextToken();
++ReadTokens;
} while (NextTok->is(tok::comment));
switch (Tok->Tok.getKind()) {
case tok::l_brace:
if (Style.isJavaScript() && PrevTok) {
if (PrevTok->isOneOf(tok::colon, tok::less))
// A ':' indicates this code is in a type, or a braced list
// following a label in an object literal ({a: {b: 1}}).
// A '<' could be an object used in a comparison, but that is nonsense
// code (can never return true), so more likely it is a generic type
// argument (`X<{a: string; b: number}>`).
// The code below could be confused by semicolons between the
// individual members in a type member list, which would normally
// trigger BK_Block. In both cases, this must be parsed as an inline
// braced init.
Tok->setBlockKind(BK_BracedInit);
else if (PrevTok->is(tok::r_paren))
// `) { }` can only occur in function or method declarations in JS.
Tok->setBlockKind(BK_Block);
} else {
Tok->setBlockKind(BK_Unknown);
}
LBraceStack.push_back(Tok);
break;
case tok::r_brace:
if (LBraceStack.empty())
break;
if (LBraceStack.back()->is(BK_Unknown)) {
bool ProbablyBracedList = false;
if (Style.Language == FormatStyle::LK_Proto) {
ProbablyBracedList = NextTok->isOneOf(tok::comma, tok::r_square);
} else {
// Skip NextTok over preprocessor lines, otherwise we may not
// properly diagnose the block as a braced intializer
// if the comma separator appears after the pp directive.
while (NextTok->is(tok::hash)) {
ScopedMacroState MacroState(*Line, Tokens, NextTok);
do {
NextTok = Tokens->getNextToken();
++ReadTokens;
} while (NextTok->isNot(tok::eof));
}
// Using OriginalColumn to distinguish between ObjC methods and
// binary operators is a bit hacky.
bool NextIsObjCMethod = NextTok->isOneOf(tok::plus, tok::minus) &&
NextTok->OriginalColumn == 0;
// If there is a comma, semicolon or right paren after the closing
// brace, we assume this is a braced initializer list. Note that
// regardless how we mark inner braces here, we will overwrite the
// BlockKind later if we parse a braced list (where all blocks
// inside are by default braced lists), or when we explicitly detect
// blocks (for example while parsing lambdas).
// FIXME: Some of these do not apply to JS, e.g. "} {" can never be a
// braced list in JS.
ProbablyBracedList =
(Style.isJavaScript() &&
NextTok->isOneOf(Keywords.kw_of, Keywords.kw_in,
Keywords.kw_as)) ||
(Style.isCpp() && NextTok->is(tok::l_paren)) ||
NextTok->isOneOf(tok::comma, tok::period, tok::colon,
tok::r_paren, tok::r_square, tok::l_brace,
tok::ellipsis) ||
(NextTok->is(tok::identifier) &&
!PrevTok->isOneOf(tok::semi, tok::r_brace, tok::l_brace)) ||
(NextTok->is(tok::semi) &&
(!ExpectClassBody || LBraceStack.size() != 1)) ||
(NextTok->isBinaryOperator() && !NextIsObjCMethod);
if (!Style.isCSharp() && NextTok->is(tok::l_square)) {
// We can have an array subscript after a braced init
// list, but C++11 attributes are expected after blocks.
NextTok = Tokens->getNextToken();
++ReadTokens;
ProbablyBracedList = NextTok->isNot(tok::l_square);
}
}
if (ProbablyBracedList) {
Tok->setBlockKind(BK_BracedInit);
LBraceStack.back()->setBlockKind(BK_BracedInit);
} else {
Tok->setBlockKind(BK_Block);
LBraceStack.back()->setBlockKind(BK_Block);
}
}
LBraceStack.pop_back();
break;
case tok::identifier:
if (!Tok->is(TT_StatementMacro))
break;
LLVM_FALLTHROUGH;
case tok::at:
case tok::semi:
case tok::kw_if:
case tok::kw_while:
case tok::kw_for:
case tok::kw_switch:
case tok::kw_try:
case tok::kw___try:
if (!LBraceStack.empty() && LBraceStack.back()->is(BK_Unknown))
LBraceStack.back()->setBlockKind(BK_Block);
break;
default:
break;
}
PrevTok = Tok;
Tok = NextTok;
} while (Tok->Tok.isNot(tok::eof) && !LBraceStack.empty());
// Assume other blocks for all unclosed opening braces.
for (FormatToken *LBrace : LBraceStack)
if (LBrace->is(BK_Unknown))
LBrace->setBlockKind(BK_Block);
FormatTok = Tokens->setPosition(StoredPosition);
}
template <class T>
static inline void hash_combine(std::size_t &seed, const T &v) {
std::hash<T> hasher;
seed ^= hasher(v) + 0x9e3779b9 + (seed << 6) + (seed >> 2);
}
size_t UnwrappedLineParser::computePPHash() const {
size_t h = 0;
for (const auto &i : PPStack) {
hash_combine(h, size_t(i.Kind));
hash_combine(h, i.Line);
}
return h;
}
UnwrappedLineParser::IfStmtKind
UnwrappedLineParser::parseBlock(bool MustBeDeclaration, unsigned AddLevels,
bool MunchSemi,
bool UnindentWhitesmithsBraces) {
assert(FormatTok->isOneOf(tok::l_brace, TT_MacroBlockBegin) &&
"'{' or macro block token expected");
FormatToken *Tok = FormatTok;
const bool MacroBlock = FormatTok->is(TT_MacroBlockBegin);
FormatTok->setBlockKind(BK_Block);
// For Whitesmiths mode, jump to the next level prior to skipping over the
// braces.
if (AddLevels > 0 && Style.BreakBeforeBraces == FormatStyle::BS_Whitesmiths)
++Line->Level;
size_t PPStartHash = computePPHash();
unsigned InitialLevel = Line->Level;
nextToken(/*LevelDifference=*/AddLevels);
if (MacroBlock && FormatTok->is(tok::l_paren))
parseParens();
size_t NbPreprocessorDirectives =
CurrentLines == &Lines ? PreprocessorDirectives.size() : 0;
addUnwrappedLine();
size_t OpeningLineIndex =
CurrentLines->empty()
? (UnwrappedLine::kInvalidIndex)
: (CurrentLines->size() - 1 - NbPreprocessorDirectives);
// Whitesmiths is weird here. The brace needs to be indented for the namespace
// block, but the block itself may not be indented depending on the style
// settings. This allows the format to back up one level in those cases.
if (UnindentWhitesmithsBraces)
--Line->Level;
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
MustBeDeclaration);
if (AddLevels > 0u && Style.BreakBeforeBraces != FormatStyle::BS_Whitesmiths)
Line->Level += AddLevels;
IfStmtKind IfKind = IfStmtKind::NotIf;
const bool SimpleBlock = parseLevel(/*HasOpeningBrace=*/true, &IfKind);
if (eof())
return IfKind;
if (MacroBlock ? !FormatTok->is(TT_MacroBlockEnd)
: !FormatTok->is(tok::r_brace)) {
Line->Level = InitialLevel;
FormatTok->setBlockKind(BK_Block);
return IfKind;
}
if (SimpleBlock && Tok->is(tok::l_brace)) {
assert(FormatTok->is(tok::r_brace));
const FormatToken *Previous = Tokens->getPreviousToken();
assert(Previous);
if (Previous->isNot(tok::r_brace) || Previous->Optional) {
Tok->MatchingParen = FormatTok;
FormatTok->MatchingParen = Tok;
}
}
size_t PPEndHash = computePPHash();
// Munch the closing brace.
nextToken(/*LevelDifference=*/-AddLevels);
if (MacroBlock && FormatTok->is(tok::l_paren))
parseParens();
if (FormatTok->is(tok::arrow)) {
// Following the } we can find a trailing return type arrow
// as part of an implicit conversion constraint.
nextToken();
parseStructuralElement();
}
if (MunchSemi && FormatTok->Tok.is(tok::semi))
nextToken();
Line->Level = InitialLevel;
if (PPStartHash == PPEndHash) {
Line->MatchingOpeningBlockLineIndex = OpeningLineIndex;
if (OpeningLineIndex != UnwrappedLine::kInvalidIndex) {
// Update the opening line to add the forward reference as well
(*CurrentLines)[OpeningLineIndex].MatchingClosingBlockLineIndex =
CurrentLines->size() - 1;
}
}
return IfKind;
}
static bool isGoogScope(const UnwrappedLine &Line) {
// FIXME: Closure-library specific stuff should not be hard-coded but be
// configurable.
if (Line.Tokens.size() < 4)
return false;
auto I = Line.Tokens.begin();
if (I->Tok->TokenText != "goog")
return false;
++I;
if (I->Tok->isNot(tok::period))
return false;
++I;
if (I->Tok->TokenText != "scope")
return false;
++I;
return I->Tok->is(tok::l_paren);
}
static bool isIIFE(const UnwrappedLine &Line,
const AdditionalKeywords &Keywords) {
// Look for the start of an immediately invoked anonymous function.
// https://en.wikipedia.org/wiki/Immediately-invoked_function_expression
// This is commonly done in JavaScript to create a new, anonymous scope.
// Example: (function() { ... })()
if (Line.Tokens.size() < 3)
return false;
auto I = Line.Tokens.begin();
if (I->Tok->isNot(tok::l_paren))
return false;
++I;
if (I->Tok->isNot(Keywords.kw_function))
return false;
++I;
return I->Tok->is(tok::l_paren);
}
static bool ShouldBreakBeforeBrace(const FormatStyle &Style,
const FormatToken &InitialToken) {
if (InitialToken.isOneOf(tok::kw_namespace, TT_NamespaceMacro))
return Style.BraceWrapping.AfterNamespace;
if (InitialToken.is(tok::kw_class))
return Style.BraceWrapping.AfterClass;
if (InitialToken.is(tok::kw_union))
return Style.BraceWrapping.AfterUnion;
if (InitialToken.is(tok::kw_struct))
return Style.BraceWrapping.AfterStruct;
if (InitialToken.is(tok::kw_enum))
return Style.BraceWrapping.AfterEnum;
return false;
}
void UnwrappedLineParser::parseChildBlock() {
FormatTok->setBlockKind(BK_Block);
nextToken();
{
bool SkipIndent = (Style.isJavaScript() &&
(isGoogScope(*Line) || isIIFE(*Line, Keywords)));
ScopedLineState LineState(*this);
ScopedDeclarationState DeclarationState(*Line, DeclarationScopeStack,
/*MustBeDeclaration=*/false);
Line->Level += SkipIndent ? 0 : 1;
parseLevel(/*HasOpeningBrace=*/true);
flushComments(isOnNewLine(*FormatTok));
Line->Level -= SkipIndent ? 0 : 1;
}
nextToken();
}
void UnwrappedLineParser::parsePPDirective() {
assert(FormatTok->Tok.is(tok::hash) && "'#' expected");
ScopedMacroState MacroState(*Line, Tokens, FormatTok);
nextToken();
if (!FormatTok->Tok.getIdentifierInfo()) {
parsePPUnknown();
return;
}
switch (FormatTok->Tok.getIdentifierInfo()->getPPKeywordID()) {
case tok::pp_define:
parsePPDefine();
return;
case tok::pp_if:
parsePPIf(/*IfDef=*/false);
break;
case tok::pp_ifdef:
case tok::pp_ifndef:
parsePPIf(/*IfDef=*/true);
break;
case tok::pp_else:
parsePPElse();
break;
case tok::pp_elifdef:
case tok::pp_elifndef:
case tok::pp_elif:
parsePPElIf();
break;
case tok::pp_endif:
parsePPEndIf();
break;
default:
parsePPUnknown();
break;
}
}
void UnwrappedLineParser::conditionalCompilationCondition(bool Unreachable) {
size_t Line = CurrentLines->size();
if (CurrentLines == &PreprocessorDirectives)
Line += Lines.size();
if (Unreachable ||
(!PPStack.empty() && PPStack.back().Kind == PP_Unreachable))
PPStack.push_back({PP_Unreachable, Line});
else
PPStack.push_back({PP_Conditional, Line});
}
void UnwrappedLineParser::conditionalCompilationStart(bool Unreachable) {
++PPBranchLevel;
assert(PPBranchLevel >= 0 && PPBranchLevel <= (int)PPLevelBranchIndex.size());
if (PPBranchLevel == (int)PPLevelBranchIndex.size()) {
PPLevelBranchIndex.push_back(0);
PPLevelBranchCount.push_back(0);
}
PPChainBranchIndex.push(0);
bool Skip = PPLevelBranchIndex[PPBranchLevel] > 0;
conditionalCompilationCondition(Unreachable || Skip);
}
void UnwrappedLineParser::conditionalCompilationAlternative() {
if (!PPStack.empty())
PPStack.pop_back();
assert(PPBranchLevel < (int)PPLevelBranchIndex.size());
if (!PPChainBranchIndex.empty())
++PPChainBranchIndex.top();
conditionalCompilationCondition(
PPBranchLevel >= 0 && !PPChainBranchIndex.empty() &&
PPLevelBranchIndex[PPBranchLevel] != PPChainBranchIndex.top());
}
void UnwrappedLineParser::conditionalCompilationEnd() {
assert(PPBranchLevel < (int)PPLevelBranchIndex.size());
if (PPBranchLevel >= 0 && !PPChainBranchIndex.empty()) {
if (PPChainBranchIndex.top() + 1 > PPLevelBranchCount[PPBranchLevel])
PPLevelBranchCount[PPBranchLevel] = PPChainBranchIndex.top() + 1;
}
// Guard against #endif's without #if.
if (PPBranchLevel > -1)
--PPBranchLevel;
if (!PPChainBranchIndex.empty())
PPChainBranchIndex.pop();
if (!PPStack.empty())
PPStack.pop_back();
}
void UnwrappedLineParser::parsePPIf(bool IfDef) {
bool IfNDef = FormatTok->is(tok::pp_ifndef);
nextToken();
bool Unreachable = false;
if (!IfDef && (FormatTok->is(tok::kw_false) || FormatTok->TokenText == "0"))
Unreachable = true;
if (IfDef && !IfNDef && FormatTok->TokenText == "SWIG")
Unreachable = true;
conditionalCompilationStart(Unreachable);
FormatToken *IfCondition = FormatTok;
// If there's a #ifndef on the first line, and the only lines before it are
// comments, it could be an include guard.
bool MaybeIncludeGuard = IfNDef;
if (IncludeGuard == IG_Inited && MaybeIncludeGuard)
for (auto &Line : Lines) {
if (!Line.Tokens.front().Tok->is(tok::comment)) {
MaybeIncludeGuard = false;
IncludeGuard = IG_Rejected;
break;
}
}
--PPBranchLevel;
parsePPUnknown();
++PPBranchLevel;
if (IncludeGuard == IG_Inited && MaybeIncludeGuard) {
IncludeGuard = IG_IfNdefed;
IncludeGuardToken = IfCondition;
}
}
void UnwrappedLineParser::parsePPElse() {
// If a potential include guard has an #else, it's not an include guard.
if (IncludeGuard == IG_Defined && PPBranchLevel == 0)
IncludeGuard = IG_Rejected;
conditionalCompilationAlternative();
if (PPBranchLevel > -1)
--PPBranchLevel;
parsePPUnknown();
++PPBranchLevel;
}
void UnwrappedLineParser::parsePPElIf() { parsePPElse(); }
void UnwrappedLineParser::parsePPEndIf() {
conditionalCompilationEnd();
parsePPUnknown();
// If the #endif of a potential include guard is the last thing in the file,
// then we found an include guard.
if (IncludeGuard == IG_Defined && PPBranchLevel == -1 && Tokens->isEOF() &&
Style.IndentPPDirectives != FormatStyle::PPDIS_None)
IncludeGuard = IG_Found;
}
void UnwrappedLineParser::parsePPDefine() {
nextToken();
if (!FormatTok->Tok.getIdentifierInfo()) {
IncludeGuard = IG_Rejected;
IncludeGuardToken = nullptr;
parsePPUnknown();
return;
}
if (IncludeGuard == IG_IfNdefed &&
IncludeGuardToken->TokenText == FormatTok->TokenText) {
IncludeGuard = IG_Defined;