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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
|
//===--- WhitespaceManager.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 implements WhitespaceManager class.
///
//===----------------------------------------------------------------------===//
#include "WhitespaceManager.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include <algorithm>
namespace clang {
namespace format {
bool WhitespaceManager::Change::IsBeforeInFile::operator()(
const Change &C1, const Change &C2) const {
return SourceMgr.isBeforeInTranslationUnit(
C1.OriginalWhitespaceRange.getBegin(),
C2.OriginalWhitespaceRange.getBegin());
}
WhitespaceManager::Change::Change(const FormatToken &Tok,
bool CreateReplacement,
SourceRange OriginalWhitespaceRange,
int Spaces, unsigned StartOfTokenColumn,
unsigned NewlinesBefore,
StringRef PreviousLinePostfix,
StringRef CurrentLinePrefix, bool IsAligned,
bool ContinuesPPDirective, bool IsInsideToken)
: Tok(&Tok), CreateReplacement(CreateReplacement),
OriginalWhitespaceRange(OriginalWhitespaceRange),
StartOfTokenColumn(StartOfTokenColumn), NewlinesBefore(NewlinesBefore),
PreviousLinePostfix(PreviousLinePostfix),
CurrentLinePrefix(CurrentLinePrefix), IsAligned(IsAligned),
ContinuesPPDirective(ContinuesPPDirective), Spaces(Spaces),
IsInsideToken(IsInsideToken), IsTrailingComment(false), TokenLength(0),
PreviousEndOfTokenColumn(0), EscapedNewlineColumn(0),
StartOfBlockComment(nullptr), IndentationOffset(0), ConditionalsLevel(0) {
}
void WhitespaceManager::replaceWhitespace(FormatToken &Tok, unsigned Newlines,
unsigned Spaces,
unsigned StartOfTokenColumn,
bool IsAligned, bool InPPDirective) {
if (Tok.Finalized)
return;
Tok.setDecision((Newlines > 0) ? FD_Break : FD_Continue);
Changes.push_back(Change(Tok, /*CreateReplacement=*/true, Tok.WhitespaceRange,
Spaces, StartOfTokenColumn, Newlines, "", "",
IsAligned, InPPDirective && !Tok.IsFirst,
/*IsInsideToken=*/false));
}
void WhitespaceManager::addUntouchableToken(const FormatToken &Tok,
bool InPPDirective) {
if (Tok.Finalized)
return;
Changes.push_back(Change(Tok, /*CreateReplacement=*/false,
Tok.WhitespaceRange, /*Spaces=*/0,
Tok.OriginalColumn, Tok.NewlinesBefore, "", "",
/*IsAligned=*/false, InPPDirective && !Tok.IsFirst,
/*IsInsideToken=*/false));
}
llvm::Error
WhitespaceManager::addReplacement(const tooling::Replacement &Replacement) {
return Replaces.add(Replacement);
}
bool WhitespaceManager::inputUsesCRLF(StringRef Text, bool DefaultToCRLF) {
size_t LF = Text.count('\n');
size_t CR = Text.count('\r') * 2;
return LF == CR ? DefaultToCRLF : CR > LF;
}
void WhitespaceManager::replaceWhitespaceInToken(
const FormatToken &Tok, unsigned Offset, unsigned ReplaceChars,
StringRef PreviousPostfix, StringRef CurrentPrefix, bool InPPDirective,
unsigned Newlines, int Spaces) {
if (Tok.Finalized)
return;
SourceLocation Start = Tok.getStartOfNonWhitespace().getLocWithOffset(Offset);
Changes.push_back(
Change(Tok, /*CreateReplacement=*/true,
SourceRange(Start, Start.getLocWithOffset(ReplaceChars)), Spaces,
std::max(0, Spaces), Newlines, PreviousPostfix, CurrentPrefix,
/*IsAligned=*/true, InPPDirective && !Tok.IsFirst,
/*IsInsideToken=*/true));
}
const tooling::Replacements &WhitespaceManager::generateReplacements() {
if (Changes.empty())
return Replaces;
llvm::sort(Changes, Change::IsBeforeInFile(SourceMgr));
calculateLineBreakInformation();
alignConsecutiveMacros();
alignConsecutiveDeclarations();
alignConsecutiveBitFields();
alignConsecutiveAssignments();
alignChainedConditionals();
alignTrailingComments();
alignEscapedNewlines();
alignArrayInitializers();
generateChanges();
return Replaces;
}
void WhitespaceManager::calculateLineBreakInformation() {
Changes[0].PreviousEndOfTokenColumn = 0;
Change *LastOutsideTokenChange = &Changes[0];
for (unsigned i = 1, e = Changes.size(); i != e; ++i) {
SourceLocation OriginalWhitespaceStart =
Changes[i].OriginalWhitespaceRange.getBegin();
SourceLocation PreviousOriginalWhitespaceEnd =
Changes[i - 1].OriginalWhitespaceRange.getEnd();
unsigned OriginalWhitespaceStartOffset =
SourceMgr.getFileOffset(OriginalWhitespaceStart);
unsigned PreviousOriginalWhitespaceEndOffset =
SourceMgr.getFileOffset(PreviousOriginalWhitespaceEnd);
assert(PreviousOriginalWhitespaceEndOffset <=
OriginalWhitespaceStartOffset);
const char *const PreviousOriginalWhitespaceEndData =
SourceMgr.getCharacterData(PreviousOriginalWhitespaceEnd);
StringRef Text(PreviousOriginalWhitespaceEndData,
SourceMgr.getCharacterData(OriginalWhitespaceStart) -
PreviousOriginalWhitespaceEndData);
// Usually consecutive changes would occur in consecutive tokens. This is
// not the case however when analyzing some preprocessor runs of the
// annotated lines. For example, in this code:
//
// #if A // line 1
// int i = 1;
// #else B // line 2
// int i = 2;
// #endif // line 3
//
// one of the runs will produce the sequence of lines marked with line 1, 2
// and 3. So the two consecutive whitespace changes just before '// line 2'
// and before '#endif // line 3' span multiple lines and tokens:
//
// #else B{change X}[// line 2
// int i = 2;
// ]{change Y}#endif // line 3
//
// For this reason, if the text between consecutive changes spans multiple
// newlines, the token length must be adjusted to the end of the original
// line of the token.
auto NewlinePos = Text.find_first_of('\n');
if (NewlinePos == StringRef::npos) {
Changes[i - 1].TokenLength = OriginalWhitespaceStartOffset -
PreviousOriginalWhitespaceEndOffset +
Changes[i].PreviousLinePostfix.size() +
Changes[i - 1].CurrentLinePrefix.size();
} else {
Changes[i - 1].TokenLength =
NewlinePos + Changes[i - 1].CurrentLinePrefix.size();
}
// If there are multiple changes in this token, sum up all the changes until
// the end of the line.
if (Changes[i - 1].IsInsideToken && Changes[i - 1].NewlinesBefore == 0) {
LastOutsideTokenChange->TokenLength +=
Changes[i - 1].TokenLength + Changes[i - 1].Spaces;
} else {
LastOutsideTokenChange = &Changes[i - 1];
}
Changes[i].PreviousEndOfTokenColumn =
Changes[i - 1].StartOfTokenColumn + Changes[i - 1].TokenLength;
Changes[i - 1].IsTrailingComment =
(Changes[i].NewlinesBefore > 0 || Changes[i].Tok->is(tok::eof) ||
(Changes[i].IsInsideToken && Changes[i].Tok->is(tok::comment))) &&
Changes[i - 1].Tok->is(tok::comment) &&
// FIXME: This is a dirty hack. The problem is that
// BreakableLineCommentSection does comment reflow changes and here is
// the aligning of trailing comments. Consider the case where we reflow
// the second line up in this example:
//
// // line 1
// // line 2
//
// That amounts to 2 changes by BreakableLineCommentSection:
// - the first, delimited by (), for the whitespace between the tokens,
// - and second, delimited by [], for the whitespace at the beginning
// of the second token:
//
// // line 1(
// )[// ]line 2
//
// So in the end we have two changes like this:
//
// // line1()[ ]line 2
//
// Note that the OriginalWhitespaceStart of the second change is the
// same as the PreviousOriginalWhitespaceEnd of the first change.
// In this case, the below check ensures that the second change doesn't
// get treated as a trailing comment change here, since this might
// trigger additional whitespace to be wrongly inserted before "line 2"
// by the comment aligner here.
//
// For a proper solution we need a mechanism to say to WhitespaceManager
// that a particular change breaks the current sequence of trailing
// comments.
OriginalWhitespaceStart != PreviousOriginalWhitespaceEnd;
}
// FIXME: The last token is currently not always an eof token; in those
// cases, setting TokenLength of the last token to 0 is wrong.
Changes.back().TokenLength = 0;
Changes.back().IsTrailingComment = Changes.back().Tok->is(tok::comment);
const WhitespaceManager::Change *LastBlockComment = nullptr;
for (auto &Change : Changes) {
// Reset the IsTrailingComment flag for changes inside of trailing comments
// so they don't get realigned later. Comment line breaks however still need
// to be aligned.
if (Change.IsInsideToken && Change.NewlinesBefore == 0)
Change.IsTrailingComment = false;
Change.StartOfBlockComment = nullptr;
Change.IndentationOffset = 0;
if (Change.Tok->is(tok::comment)) {
if (Change.Tok->is(TT_LineComment) || !Change.IsInsideToken) {
LastBlockComment = &Change;
} else if ((Change.StartOfBlockComment = LastBlockComment)) {
Change.IndentationOffset =
Change.StartOfTokenColumn -
Change.StartOfBlockComment->StartOfTokenColumn;
}
} else {
LastBlockComment = nullptr;
}
}
// Compute conditional nesting level
// Level is increased for each conditional, unless this conditional continues
// a chain of conditional, i.e. starts immediately after the colon of another
// conditional.
SmallVector<bool, 16> ScopeStack;
int ConditionalsLevel = 0;
for (auto &Change : Changes) {
for (unsigned i = 0, e = Change.Tok->FakeLParens.size(); i != e; ++i) {
bool isNestedConditional =
Change.Tok->FakeLParens[e - 1 - i] == prec::Conditional &&
!(i == 0 && Change.Tok->Previous &&
Change.Tok->Previous->is(TT_ConditionalExpr) &&
Change.Tok->Previous->is(tok::colon));
if (isNestedConditional)
++ConditionalsLevel;
ScopeStack.push_back(isNestedConditional);
}
Change.ConditionalsLevel = ConditionalsLevel;
for (unsigned i = Change.Tok->FakeRParens; i > 0 && ScopeStack.size(); --i)
if (ScopeStack.pop_back_val())
--ConditionalsLevel;
}
}
// Align a single sequence of tokens, see AlignTokens below.
// Column - The token for which Matches returns true is moved to this column.
// RightJustify - Whether it is the token's right end or left end that gets
// moved to that column.
template <typename F>
static void
AlignTokenSequence(const FormatStyle &Style, unsigned Start, unsigned End,
unsigned Column, bool RightJustify, F &&Matches,
SmallVector<WhitespaceManager::Change, 16> &Changes) {
bool FoundMatchOnLine = false;
int Shift = 0;
// ScopeStack keeps track of the current scope depth. It contains indices of
// the first token on each scope.
// We only run the "Matches" function on tokens from the outer-most scope.
// However, we do need to pay special attention to one class of tokens
// that are not in the outer-most scope, and that is function parameters
// which are split across multiple lines, as illustrated by this example:
// double a(int x);
// int b(int y,
// double z);
// In the above example, we need to take special care to ensure that
// 'double z' is indented along with it's owning function 'b'.
// The same holds for calling a function:
// double a = foo(x);
// int b = bar(foo(y),
// foor(z));
// Similar for broken string literals:
// double x = 3.14;
// auto s = "Hello"
// "World";
// Special handling is required for 'nested' ternary operators.
SmallVector<unsigned, 16> ScopeStack;
for (unsigned i = Start; i != End; ++i) {
if (ScopeStack.size() != 0 &&
Changes[i].indentAndNestingLevel() <
Changes[ScopeStack.back()].indentAndNestingLevel()) {
ScopeStack.pop_back();
}
// Compare current token to previous non-comment token to ensure whether
// it is in a deeper scope or not.
unsigned PreviousNonComment = i - 1;
while (PreviousNonComment > Start &&
Changes[PreviousNonComment].Tok->is(tok::comment)) {
--PreviousNonComment;
}
if (i != Start && Changes[i].indentAndNestingLevel() >
Changes[PreviousNonComment].indentAndNestingLevel()) {
ScopeStack.push_back(i);
}
bool InsideNestedScope = ScopeStack.size() != 0;
bool ContinuedStringLiteral = i > Start &&
Changes[i].Tok->is(tok::string_literal) &&
Changes[i - 1].Tok->is(tok::string_literal);
bool SkipMatchCheck = InsideNestedScope || ContinuedStringLiteral;
if (Changes[i].NewlinesBefore > 0 && !SkipMatchCheck) {
Shift = 0;
FoundMatchOnLine = false;
}
// If this is the first matching token to be aligned, remember by how many
// spaces it has to be shifted, so the rest of the changes on the line are
// shifted by the same amount
if (!FoundMatchOnLine && !SkipMatchCheck && Matches(Changes[i])) {
FoundMatchOnLine = true;
Shift = Column - (RightJustify ? Changes[i].TokenLength : 0) -
Changes[i].StartOfTokenColumn;
Changes[i].Spaces += Shift;
// FIXME: This is a workaround that should be removed when we fix
// http://llvm.org/PR53699. An assertion later below verifies this.
if (Changes[i].NewlinesBefore == 0) {
Changes[i].Spaces =
std::max(Changes[i].Spaces,
static_cast<int>(Changes[i].Tok->SpacesRequiredBefore));
}
}
// This is for function parameters that are split across multiple lines,
// as mentioned in the ScopeStack comment.
if (InsideNestedScope && Changes[i].NewlinesBefore > 0) {
unsigned ScopeStart = ScopeStack.back();
auto ShouldShiftBeAdded = [&] {
// Function declaration
if (Changes[ScopeStart - 1].Tok->is(TT_FunctionDeclarationName))
return true;
// Lambda.
if (Changes[ScopeStart - 1].Tok->is(TT_LambdaLBrace))
return false;
// Continued function declaration
if (ScopeStart > Start + 1 &&
Changes[ScopeStart - 2].Tok->is(TT_FunctionDeclarationName)) {
return true;
}
// Continued function call
if (ScopeStart > Start + 1 &&
Changes[ScopeStart - 2].Tok->is(tok::identifier) &&
Changes[ScopeStart - 1].Tok->is(tok::l_paren) &&
Changes[ScopeStart].Tok->isNot(TT_LambdaLSquare)) {
if (Changes[i].Tok->MatchingParen &&
Changes[i].Tok->MatchingParen->is(TT_LambdaLBrace)) {
return false;
}
if (Changes[ScopeStart].NewlinesBefore > 0)
return false;
if (Changes[i].Tok->is(tok::l_brace) &&
Changes[i].Tok->is(BK_BracedInit)) {
return true;
}
return Style.BinPackArguments;
}
// Ternary operator
if (Changes[i].Tok->is(TT_ConditionalExpr))
return true;
// Period Initializer .XXX = 1.
if (Changes[i].Tok->is(TT_DesignatedInitializerPeriod))
return true;
// Continued ternary operator
if (Changes[i].Tok->Previous &&
Changes[i].Tok->Previous->is(TT_ConditionalExpr)) {
return true;
}
// Continued direct-list-initialization using braced list.
if (ScopeStart > Start + 1 &&
Changes[ScopeStart - 2].Tok->is(tok::identifier) &&
Changes[ScopeStart - 1].Tok->is(tok::l_brace) &&
Changes[i].Tok->is(tok::l_brace) &&
Changes[i].Tok->is(BK_BracedInit)) {
return true;
}
// Continued braced list.
if (ScopeStart > Start + 1 &&
Changes[ScopeStart - 2].Tok->isNot(tok::identifier) &&
Changes[ScopeStart - 1].Tok->is(tok::l_brace) &&
Changes[i].Tok->isNot(tok::r_brace)) {
for (unsigned OuterScopeStart : llvm::reverse(ScopeStack)) {
// Lambda.
if (OuterScopeStart > Start &&
Changes[OuterScopeStart - 1].Tok->is(TT_LambdaLBrace)) {
return false;
}
}
if (Changes[ScopeStart].NewlinesBefore > 0)
return false;
return true;
}
return false;
};
if (ShouldShiftBeAdded())
Changes[i].Spaces += Shift;
}
if (ContinuedStringLiteral)
Changes[i].Spaces += Shift;
// We should not remove required spaces unless we break the line before.
assert(Shift >= 0 || Changes[i].NewlinesBefore > 0 ||
Changes[i].Spaces >=
static_cast<int>(Changes[i].Tok->SpacesRequiredBefore) ||
Changes[i].Tok->is(tok::eof));
Changes[i].StartOfTokenColumn += Shift;
if (i + 1 != Changes.size())
Changes[i + 1].PreviousEndOfTokenColumn += Shift;
// If PointerAlignment is PAS_Right, keep *s or &s next to the token
if (Style.PointerAlignment == FormatStyle::PAS_Right &&
Changes[i].Spaces != 0) {
for (int Previous = i - 1;
Previous >= 0 &&
Changes[Previous].Tok->getType() == TT_PointerOrReference;
--Previous) {
Changes[Previous + 1].Spaces -= Shift;
Changes[Previous].Spaces += Shift;
Changes[Previous].StartOfTokenColumn += Shift;
}
}
}
}
// Walk through a subset of the changes, starting at StartAt, and find
// sequences of matching tokens to align. To do so, keep track of the lines and
// whether or not a matching token was found on a line. If a matching token is
// found, extend the current sequence. If the current line cannot be part of a
// sequence, e.g. because there is an empty line before it or it contains only
// non-matching tokens, finalize the previous sequence.
// The value returned is the token on which we stopped, either because we
// exhausted all items inside Changes, or because we hit a scope level higher
// than our initial scope.
// This function is recursive. Each invocation processes only the scope level
// equal to the initial level, which is the level of Changes[StartAt].
// If we encounter a scope level greater than the initial level, then we call
// ourselves recursively, thereby avoiding the pollution of the current state
// with the alignment requirements of the nested sub-level. This recursive
// behavior is necessary for aligning function prototypes that have one or more
// arguments.
// If this function encounters a scope level less than the initial level,
// it returns the current position.
// There is a non-obvious subtlety in the recursive behavior: Even though we
// defer processing of nested levels to recursive invocations of this
// function, when it comes time to align a sequence of tokens, we run the
// alignment on the entire sequence, including the nested levels.
// When doing so, most of the nested tokens are skipped, because their
// alignment was already handled by the recursive invocations of this function.
// However, the special exception is that we do NOT skip function parameters
// that are split across multiple lines. See the test case in FormatTest.cpp
// that mentions "split function parameter alignment" for an example of this.
// When the parameter RightJustify is true, the operator will be
// right-justified. It is used to align compound assignments like `+=` and `=`.
// When RightJustify and ACS.PadOperators are true, operators in each block to
// be aligned will be padded on the left to the same length before aligning.
template <typename F>
static unsigned AlignTokens(const FormatStyle &Style, F &&Matches,
SmallVector<WhitespaceManager::Change, 16> &Changes,
unsigned StartAt,
const FormatStyle::AlignConsecutiveStyle &ACS = {},
bool RightJustify = false) {
// We arrange each line in 3 parts. The operator to be aligned (the anchor),
// and text to its left and right. In the aligned text the width of each part
// will be the maximum of that over the block that has been aligned. Maximum
// widths of each part so far. When RightJustify is true and ACS.PadOperators
// is false, the part from start of line to the right end of the anchor.
// Otherwise, only the part to the left of the anchor. Including the space
// that exists on its left from the start. Not including the padding added on
// the left to right-justify the anchor.
unsigned WidthLeft = 0;
// The operator to be aligned when RightJustify is true and ACS.PadOperators
// is false. 0 otherwise.
unsigned WidthAnchor = 0;
// Width to the right of the anchor. Plus width of the anchor when
// RightJustify is false.
unsigned WidthRight = 0;
// Line number of the start and the end of the current token sequence.
unsigned StartOfSequence = 0;
unsigned EndOfSequence = 0;
// Measure the scope level (i.e. depth of (), [], {}) of the first token, and
// abort when we hit any token in a higher scope than the starting one.
auto IndentAndNestingLevel = StartAt < Changes.size()
? Changes[StartAt].indentAndNestingLevel()
: std::tuple<unsigned, unsigned, unsigned>();
// Keep track if the first token has a non-zero indent and nesting level.
// This can happen when aligning the contents of "#else" preprocessor blocks,
// which is done separately.
bool HasInitialIndentAndNesting =
StartAt == 0 &&
IndentAndNestingLevel > std::tuple<unsigned, unsigned, unsigned>();
// Keep track of the number of commas before the matching tokens, we will only
// align a sequence of matching tokens if they are preceded by the same number
// of commas.
unsigned CommasBeforeLastMatch = 0;
unsigned CommasBeforeMatch = 0;
// Whether a matching token has been found on the current line.
bool FoundMatchOnLine = false;
// Whether the current line consists purely of comments.
bool LineIsComment = true;
// Aligns a sequence of matching tokens, on the MinColumn column.
//
// Sequences start from the first matching token to align, and end at the
// first token of the first line that doesn't need to be aligned.
//
// We need to adjust the StartOfTokenColumn of each Change that is on a line
// containing any matching token to be aligned and located after such token.
auto AlignCurrentSequence = [&] {
if (StartOfSequence > 0 && StartOfSequence < EndOfSequence) {
AlignTokenSequence(Style, StartOfSequence, EndOfSequence,
WidthLeft + WidthAnchor, RightJustify, Matches,
Changes);
}
WidthLeft = 0;
WidthAnchor = 0;
WidthRight = 0;
StartOfSequence = 0;
EndOfSequence = 0;
};
unsigned i = StartAt;
for (unsigned e = Changes.size(); i != e; ++i) {
if (Changes[i].indentAndNestingLevel() < IndentAndNestingLevel) {
if (!HasInitialIndentAndNesting)
break;
// The contents of preprocessor blocks are aligned separately.
// If the initial preprocessor block is indented or nested (e.g. it's in
// a function), do not align and exit after finishing this scope block.
// Instead, align, and then lower the baseline indent and nesting level
// in order to continue aligning subsequent blocks.
EndOfSequence = i;
AlignCurrentSequence();
IndentAndNestingLevel =
Changes[i].indentAndNestingLevel(); // new baseline
}
if (Changes[i].NewlinesBefore != 0) {
CommasBeforeMatch = 0;
EndOfSequence = i;
// Whether to break the alignment sequence because of an empty line.
bool EmptyLineBreak =
(Changes[i].NewlinesBefore > 1) && !ACS.AcrossEmptyLines;
// Whether to break the alignment sequence because of a line without a
// match.
bool NoMatchBreak =
!FoundMatchOnLine && !(LineIsComment && ACS.AcrossComments);
if (EmptyLineBreak || NoMatchBreak)
AlignCurrentSequence();
// A new line starts, re-initialize line status tracking bools.
// Keep the match state if a string literal is continued on this line.
if (i == 0 || !Changes[i].Tok->is(tok::string_literal) ||
!Changes[i - 1].Tok->is(tok::string_literal)) {
FoundMatchOnLine = false;
}
LineIsComment = true;
}
if (!Changes[i].Tok->is(tok::comment))
LineIsComment = false;
if (Changes[i].Tok->is(tok::comma)) {
++CommasBeforeMatch;
} else if (Changes[i].indentAndNestingLevel() > IndentAndNestingLevel) {
// Call AlignTokens recursively, skipping over this scope block.
unsigned StoppedAt =
AlignTokens(Style, Matches, Changes, i, ACS, RightJustify);
i = StoppedAt - 1;
continue;
}
if (!Matches(Changes[i]))
continue;
// If there is more than one matching token per line, or if the number of
// preceding commas, do not match anymore, end the sequence.
if (FoundMatchOnLine || CommasBeforeMatch != CommasBeforeLastMatch)
AlignCurrentSequence();
CommasBeforeLastMatch = CommasBeforeMatch;
FoundMatchOnLine = true;
if (StartOfSequence == 0)
StartOfSequence = i;
unsigned ChangeWidthLeft = Changes[i].StartOfTokenColumn;
unsigned ChangeWidthAnchor = 0;
unsigned ChangeWidthRight = 0;
if (RightJustify)
if (ACS.PadOperators)
ChangeWidthAnchor = Changes[i].TokenLength;
else
ChangeWidthLeft += Changes[i].TokenLength;
else
ChangeWidthRight = Changes[i].TokenLength;
for (unsigned j = i + 1; j != e && Changes[j].NewlinesBefore == 0; ++j) {
ChangeWidthRight += Changes[j].Spaces;
// Changes are generally 1:1 with the tokens, but a change could also be
// inside of a token, in which case it's counted more than once: once for
// the whitespace surrounding the token (!IsInsideToken) and once for
// each whitespace change within it (IsInsideToken).
// Therefore, changes inside of a token should only count the space.
if (!Changes[j].IsInsideToken)
ChangeWidthRight += Changes[j].TokenLength;
}
// If we are restricted by the maximum column width, end the sequence.
unsigned NewLeft = std::max(ChangeWidthLeft, WidthLeft);
unsigned NewAnchor = std::max(ChangeWidthAnchor, WidthAnchor);
unsigned NewRight = std::max(ChangeWidthRight, WidthRight);
// `ColumnLimit == 0` means there is no column limit.
if (Style.ColumnLimit != 0 &&
Style.ColumnLimit < NewLeft + NewAnchor + NewRight) {
AlignCurrentSequence();
StartOfSequence = i;
WidthLeft = ChangeWidthLeft;
WidthAnchor = ChangeWidthAnchor;
WidthRight = ChangeWidthRight;
} else {
WidthLeft = NewLeft;
WidthAnchor = NewAnchor;
WidthRight = NewRight;
}
}
EndOfSequence = i;
AlignCurrentSequence();
return i;
}
// Aligns a sequence of matching tokens, on the MinColumn column.
//
// Sequences start from the first matching token to align, and end at the
// first token of the first line that doesn't need to be aligned.
//
// We need to adjust the StartOfTokenColumn of each Change that is on a line
// containing any matching token to be aligned and located after such token.
static void AlignMacroSequence(
unsigned &StartOfSequence, unsigned &EndOfSequence, unsigned &MinColumn,
unsigned &MaxColumn, bool &FoundMatchOnLine,
std::function<bool(const WhitespaceManager::Change &C)> AlignMacrosMatches,
SmallVector<WhitespaceManager::Change, 16> &Changes) {
if (StartOfSequence > 0 && StartOfSequence < EndOfSequence) {
FoundMatchOnLine = false;
int Shift = 0;
for (unsigned I = StartOfSequence; I != EndOfSequence; ++I) {
if (Changes[I].NewlinesBefore > 0) {
Shift = 0;
FoundMatchOnLine = false;
}
// If this is the first matching token to be aligned, remember by how many
// spaces it has to be shifted, so the rest of the changes on the line are
// shifted by the same amount
if (!FoundMatchOnLine && AlignMacrosMatches(Changes[I])) {
FoundMatchOnLine = true;
Shift = MinColumn - Changes[I].StartOfTokenColumn;
Changes[I].Spaces += Shift;
}
assert(Shift >= 0);
Changes[I].StartOfTokenColumn += Shift;
if (I + 1 != Changes.size())
Changes[I + 1].PreviousEndOfTokenColumn += Shift;
}
}
MinColumn = 0;
MaxColumn = UINT_MAX;
StartOfSequence = 0;
EndOfSequence = 0;
}
void WhitespaceManager::alignConsecutiveMacros() {
if (!Style.AlignConsecutiveMacros.Enabled)
return;
auto AlignMacrosMatches = [](const Change &C) {
const FormatToken *Current = C.Tok;
unsigned SpacesRequiredBefore = 1;
if (Current->SpacesRequiredBefore == 0 || !Current->Previous)
return false;
Current = Current->Previous;
// If token is a ")", skip over the parameter list, to the
// token that precedes the "("
if (Current->is(tok::r_paren) && Current->MatchingParen) {
Current = Current->MatchingParen->Previous;
SpacesRequiredBefore = 0;
}
if (!Current || !Current->is(tok::identifier))
return false;
if (!Current->Previous || !Current->Previous->is(tok::pp_define))
return false;
// For a macro function, 0 spaces are required between the
// identifier and the lparen that opens the parameter list.
// For a simple macro, 1 space is required between the
// identifier and the first token of the defined value.
return Current->Next->SpacesRequiredBefore == SpacesRequiredBefore;
};
unsigned MinColumn = 0;
unsigned MaxColumn = UINT_MAX;
// Start and end of the token sequence we're processing.
unsigned StartOfSequence = 0;
unsigned EndOfSequence = 0;
// Whether a matching token has been found on the current line.
bool FoundMatchOnLine = false;
// Whether the current line consists only of comments
bool LineIsComment = true;
unsigned I = 0;
for (unsigned E = Changes.size(); I != E; ++I) {
if (Changes[I].NewlinesBefore != 0) {
EndOfSequence = I;
// Whether to break the alignment sequence because of an empty line.
bool EmptyLineBreak = (Changes[I].NewlinesBefore > 1) &&
!Style.AlignConsecutiveMacros.AcrossEmptyLines;
// Whether to break the alignment sequence because of a line without a
// match.
bool NoMatchBreak =
!FoundMatchOnLine &&
!(LineIsComment && Style.AlignConsecutiveMacros.AcrossComments);
if (EmptyLineBreak || NoMatchBreak) {
AlignMacroSequence(StartOfSequence, EndOfSequence, MinColumn, MaxColumn,
FoundMatchOnLine, AlignMacrosMatches, Changes);
}
// A new line starts, re-initialize line status tracking bools.
FoundMatchOnLine = false;
LineIsComment = true;
}
if (!Changes[I].Tok->is(tok::comment))
LineIsComment = false;
if (!AlignMacrosMatches(Changes[I]))
continue;
FoundMatchOnLine = true;
if (StartOfSequence == 0)
StartOfSequence = I;
unsigned ChangeMinColumn = Changes[I].StartOfTokenColumn;
int LineLengthAfter = -Changes[I].Spaces;
for (unsigned j = I; j != E && Changes[j].NewlinesBefore == 0; ++j)
LineLengthAfter += Changes[j].Spaces + Changes[j].TokenLength;
unsigned ChangeMaxColumn = Style.ColumnLimit - LineLengthAfter;
MinColumn = std::max(MinColumn, ChangeMinColumn);
MaxColumn = std::min(MaxColumn, ChangeMaxColumn);
}
EndOfSequence = I;
AlignMacroSequence(StartOfSequence, EndOfSequence, MinColumn, MaxColumn,
FoundMatchOnLine, AlignMacrosMatches, Changes);
}
void WhitespaceManager::alignConsecutiveAssignments() {
if (!Style.AlignConsecutiveAssignments.Enabled)
return;
AlignTokens(
Style,
[&](const Change &C) {
// Do not align on equal signs that are first on a line.
if (C.NewlinesBefore > 0)
return false;
// Do not align on equal signs that are last on a line.
if (&C != &Changes.back() && (&C + 1)->NewlinesBefore > 0)
return false;
// Do not align operator= overloads.
FormatToken *Previous = C.Tok->getPreviousNonComment();
if (Previous && Previous->is(tok::kw_operator))
return false;
return Style.AlignConsecutiveAssignments.AlignCompound
? C.Tok->getPrecedence() == prec::Assignment
: C.Tok->is(tok::equal);
},
Changes, /*StartAt=*/0, Style.AlignConsecutiveAssignments,
/*RightJustify=*/true);
}
void WhitespaceManager::alignConsecutiveBitFields() {
if (!Style.AlignConsecutiveBitFields.Enabled)
return;
AlignTokens(
Style,
[&](Change const &C) {
// Do not align on ':' that is first on a line.
if (C.NewlinesBefore > 0)
return false;
// Do not align on ':' that is last on a line.
if (&C != &Changes.back() && (&C + 1)->NewlinesBefore > 0)
return false;
return C.Tok->is(TT_BitFieldColon);
},
Changes, /*StartAt=*/0, Style.AlignConsecutiveBitFields);
}
void WhitespaceManager::alignConsecutiveDeclarations() {
if (!Style.AlignConsecutiveDeclarations.Enabled)
return;
AlignTokens(
Style,
[](Change const &C) {
if (C.Tok->is(TT_FunctionDeclarationName))
return true;
if (C.Tok->isNot(TT_StartOfName))
return false;
if (C.Tok->Previous &&
C.Tok->Previous->is(TT_StatementAttributeLikeMacro))
return false;
// Check if there is a subsequent name that starts the same declaration.
for (FormatToken *Next = C.Tok->Next; Next; Next = Next->Next) {
if (Next->is(tok::comment))
continue;
if (Next->is(TT_PointerOrReference))
return false;
if (!Next->Tok.getIdentifierInfo())
break;
if (Next->isOneOf(TT_StartOfName, TT_FunctionDeclarationName,
tok::kw_operator)) {
return false;
}
}
return true;
},
Changes, /*StartAt=*/0, Style.AlignConsecutiveDeclarations);
}
void WhitespaceManager::alignChainedConditionals() {
if (Style.BreakBeforeTernaryOperators) {
AlignTokens(
Style,
[](Change const &C) {
// Align question operators and last colon
return C.Tok->is(TT_ConditionalExpr) &&
((C.Tok->is(tok::question) && !C.NewlinesBefore) ||
(C.Tok->is(tok::colon) && C.Tok->Next &&
(C.Tok->Next->FakeLParens.size() == 0 ||
C.Tok->Next->FakeLParens.back() != prec::Conditional)));
},
Changes, /*StartAt=*/0);
} else {
static auto AlignWrappedOperand = [](Change const &C) {
FormatToken *Previous = C.Tok->getPreviousNonComment();
return C.NewlinesBefore && Previous && Previous->is(TT_ConditionalExpr) &&
(Previous->is(tok::colon) &&
(C.Tok->FakeLParens.size() == 0 ||
C.Tok->FakeLParens.back() != prec::Conditional));
};
// Ensure we keep alignment of wrapped operands with non-wrapped operands
// Since we actually align the operators, the wrapped operands need the
// extra offset to be properly aligned.
for (Change &C : Changes)
if (AlignWrappedOperand(C))
C.StartOfTokenColumn -= 2;
AlignTokens(
Style,
[this](Change const &C) {
// Align question operators if next operand is not wrapped, as
// well as wrapped operands after question operator or last
// colon in conditional sequence
return (C.Tok->is(TT_ConditionalExpr) && C.Tok->is(tok::question) &&
&C != &Changes.back() && (&C + 1)->NewlinesBefore == 0 &&
!(&C + 1)->IsTrailingComment) ||
AlignWrappedOperand(C);
},
Changes, /*StartAt=*/0);
}
}
void WhitespaceManager::alignTrailingComments() {
unsigned MinColumn = 0;
unsigned MaxColumn = UINT_MAX;
unsigned StartOfSequence = 0;
bool BreakBeforeNext = false;
unsigned Newlines = 0;
unsigned int NewLineThreshold = 1;
if (Style.AlignTrailingComments.Kind == FormatStyle::TCAS_Always)
NewLineThreshold = Style.AlignTrailingComments.OverEmptyLines + 1;
for (unsigned i = 0, e = Changes.size(); i != e; ++i) {
if (Changes[i].StartOfBlockComment)
continue;
Newlines += Changes[i].NewlinesBefore;
if (!Changes[i].IsTrailingComment)
continue;
if (Style.AlignTrailingComments.Kind == FormatStyle::TCAS_Leave) {
auto OriginalSpaces =
Changes[i].OriginalWhitespaceRange.getEnd().getRawEncoding() -
Changes[i].OriginalWhitespaceRange.getBegin().getRawEncoding() -
Changes[i].Tok->NewlinesBefore;
unsigned RestoredLineLength = Changes[i].StartOfTokenColumn +
Changes[i].TokenLength + OriginalSpaces;
// If leaving comments makes the line exceed the column limit, give up to
// leave the comments.
if (RestoredLineLength >= Style.ColumnLimit && Style.ColumnLimit != 0)
break;
Changes[i].Spaces = OriginalSpaces;
continue;
}
unsigned ChangeMinColumn = Changes[i].StartOfTokenColumn;
unsigned ChangeMaxColumn;
if (Style.ColumnLimit == 0)
ChangeMaxColumn = UINT_MAX;
else if (Style.ColumnLimit >= Changes[i].TokenLength)
ChangeMaxColumn = Style.ColumnLimit - Changes[i].TokenLength;
else
ChangeMaxColumn = ChangeMinColumn;
// If we don't create a replacement for this change, we have to consider
// it to be immovable.
if (!Changes[i].CreateReplacement)
ChangeMaxColumn = ChangeMinColumn;
if (i + 1 != e && Changes[i + 1].ContinuesPPDirective)
ChangeMaxColumn -= 2;
// If this comment follows an } in column 0, it probably documents the
// closing of a namespace and we don't want to align it.
bool FollowsRBraceInColumn0 = i > 0 && Changes[i].NewlinesBefore == 0 &&
Changes[i - 1].Tok->is(tok::r_brace) &&
Changes[i - 1].StartOfTokenColumn == 0;
bool WasAlignedWithStartOfNextLine = false;
if (Changes[i].NewlinesBefore >= 1) { // A comment on its own line.
unsigned CommentColumn = SourceMgr.getSpellingColumnNumber(
Changes[i].OriginalWhitespaceRange.getEnd());
for (unsigned j = i + 1; j != e; ++j) {
if (Changes[j].Tok->is(tok::comment))
continue;
unsigned NextColumn = SourceMgr.getSpellingColumnNumber(
Changes[j].OriginalWhitespaceRange.getEnd());
// The start of the next token was previously aligned with the
// start of this comment.
WasAlignedWithStartOfNextLine =
CommentColumn == NextColumn ||
CommentColumn == NextColumn + Style.IndentWidth;
break;
}
}
if (Style.AlignTrailingComments.Kind == FormatStyle::TCAS_Never ||
FollowsRBraceInColumn0) {
alignTrailingComments(StartOfSequence, i, MinColumn);
MinColumn = ChangeMinColumn;
MaxColumn = ChangeMinColumn;
StartOfSequence = i;
} else if (BreakBeforeNext || Newlines > NewLineThreshold ||
(ChangeMinColumn > MaxColumn || ChangeMaxColumn < MinColumn) ||
// Break the comment sequence if the previous line did not end
// in a trailing comment.
(Changes[i].NewlinesBefore == 1 && i > 0 &&
!Changes[i - 1].IsTrailingComment) ||
WasAlignedWithStartOfNextLine) {
alignTrailingComments(StartOfSequence, i, MinColumn);
MinColumn = ChangeMinColumn;
MaxColumn = ChangeMaxColumn;
StartOfSequence = i;
} else {
MinColumn = std::max(MinColumn, ChangeMinColumn);
MaxColumn = std::min(MaxColumn, ChangeMaxColumn);
}
BreakBeforeNext = (i == 0) || (Changes[i].NewlinesBefore > 1) ||
// Never start a sequence with a comment at the beginning
// of the line.
(Changes[i].NewlinesBefore == 1 && StartOfSequence == i);
Newlines = 0;
}
alignTrailingComments(StartOfSequence, Changes.size(), MinColumn);
}
void WhitespaceManager::alignTrailingComments(unsigned Start, unsigned End,
unsigned Column) {
for (unsigned i = Start; i != End; ++i) {
int Shift = 0;
if (Changes[i].IsTrailingComment)
Shift = Column - Changes[i].StartOfTokenColumn;
if (Changes[i].StartOfBlockComment) {
Shift = Changes[i].IndentationOffset +
Changes[i].StartOfBlockComment->StartOfTokenColumn -
Changes[i].StartOfTokenColumn;
}
if (Shift <= 0)
continue;
Changes[i].Spaces += Shift;
if (i + 1 != Changes.size())
Changes[i + 1].PreviousEndOfTokenColumn += Shift;
Changes[i].StartOfTokenColumn += Shift;
}
}
void WhitespaceManager::alignEscapedNewlines() {
if (Style.AlignEscapedNewlines == FormatStyle::ENAS_DontAlign)
return;
bool AlignLeft = Style.AlignEscapedNewlines == FormatStyle::ENAS_Left;
unsigned MaxEndOfLine = AlignLeft ? 0 : Style.ColumnLimit;
unsigned StartOfMacro = 0;
for (unsigned i = 1, e = Changes.size(); i < e; ++i) {
Change &C = Changes[i];
if (C.NewlinesBefore > 0) {
if (C.ContinuesPPDirective) {
MaxEndOfLine = std::max(C.PreviousEndOfTokenColumn + 2, MaxEndOfLine);
} else {
alignEscapedNewlines(StartOfMacro + 1, i, MaxEndOfLine);
MaxEndOfLine = AlignLeft ? 0 : Style.ColumnLimit;
StartOfMacro = i;
}
}
}
alignEscapedNewlines(StartOfMacro + 1, Changes.size(), MaxEndOfLine);
}
void WhitespaceManager::alignEscapedNewlines(unsigned Start, unsigned End,
unsigned Column) {
for (unsigned i = Start; i < End; ++i) {
Change &C = Changes[i];
if (C.NewlinesBefore > 0) {
assert(C.ContinuesPPDirective);
if (C.PreviousEndOfTokenColumn + 1 > Column)
C.EscapedNewlineColumn = 0;
else
C.EscapedNewlineColumn = Column;
}
}
}
void WhitespaceManager::alignArrayInitializers() {
if (Style.AlignArrayOfStructures == FormatStyle::AIAS_None)
return;
for (unsigned ChangeIndex = 1U, ChangeEnd = Changes.size();
ChangeIndex < ChangeEnd; ++ChangeIndex) {
auto &C = Changes[ChangeIndex];
if (C.Tok->IsArrayInitializer) {
bool FoundComplete = false;
for (unsigned InsideIndex = ChangeIndex + 1; InsideIndex < ChangeEnd;
++InsideIndex) {
if (Changes[InsideIndex].Tok == C.Tok->MatchingParen) {
alignArrayInitializers(ChangeIndex, InsideIndex + 1);
ChangeIndex = InsideIndex + 1;
FoundComplete = true;
break;
}
}
if (!FoundComplete)
ChangeIndex = ChangeEnd;
}
}
}
void WhitespaceManager::alignArrayInitializers(unsigned Start, unsigned End) {
if (Style.AlignArrayOfStructures == FormatStyle::AIAS_Right)
alignArrayInitializersRightJustified(getCells(Start, End));
else if (Style.AlignArrayOfStructures == FormatStyle::AIAS_Left)
alignArrayInitializersLeftJustified(getCells(Start, End));
}
void WhitespaceManager::alignArrayInitializersRightJustified(
CellDescriptions &&CellDescs) {
if (!CellDescs.isRectangular())
return;
auto &Cells = CellDescs.Cells;
// Now go through and fixup the spaces.
auto *CellIter = Cells.begin();
for (auto i = 0U; i < CellDescs.CellCounts[0]; ++i, ++CellIter) {
unsigned NetWidth = 0U;
if (isSplitCell(*CellIter))
NetWidth = getNetWidth(Cells.begin(), CellIter, CellDescs.InitialSpaces);
auto CellWidth = getMaximumCellWidth(CellIter, NetWidth);
if (Changes[CellIter->Index].Tok->is(tok::r_brace)) {
// So in here we want to see if there is a brace that falls
// on a line that was split. If so on that line we make sure that
// the spaces in front of the brace are enough.
const auto *Next = CellIter;
do {
const FormatToken *Previous = Changes[Next->Index].Tok->Previous;
if (Previous && Previous->isNot(TT_LineComment)) {
Changes[Next->Index].Spaces = 0;
Changes[Next->Index].NewlinesBefore = 0;
}
Next = Next->NextColumnElement;
} while (Next);
// Unless the array is empty, we need the position of all the
// immediately adjacent cells
if (CellIter != Cells.begin()) {
auto ThisNetWidth =
getNetWidth(Cells.begin(), CellIter, CellDescs.InitialSpaces);
auto MaxNetWidth = getMaximumNetWidth(
Cells.begin(), CellIter, CellDescs.InitialSpaces,
CellDescs.CellCounts[0], CellDescs.CellCounts.size());
if (ThisNetWidth < MaxNetWidth)
Changes[CellIter->Index].Spaces = (MaxNetWidth - ThisNetWidth);
auto RowCount = 1U;
auto Offset = std::distance(Cells.begin(), CellIter);
for (const auto *Next = CellIter->NextColumnElement; Next != nullptr;
Next = Next->NextColumnElement) {
auto *Start = (Cells.begin() + RowCount * CellDescs.CellCounts[0]);
auto *End = Start + Offset;
ThisNetWidth = getNetWidth(Start, End, CellDescs.InitialSpaces);
if (ThisNetWidth < MaxNetWidth)
Changes[Next->Index].Spaces = (MaxNetWidth - ThisNetWidth);
++RowCount;
}
}
} else {
auto ThisWidth =
calculateCellWidth(CellIter->Index, CellIter->EndIndex, true) +
NetWidth;
if (Changes[CellIter->Index].NewlinesBefore == 0) {
Changes[CellIter->Index].Spaces = (CellWidth - (ThisWidth + NetWidth));
Changes[CellIter->Index].Spaces += (i > 0) ? 1 : 0;
}
alignToStartOfCell(CellIter->Index, CellIter->EndIndex);
for (const auto *Next = CellIter->NextColumnElement; Next != nullptr;
Next = Next->NextColumnElement) {
ThisWidth =
calculateCellWidth(Next->Index, Next->EndIndex, true) + NetWidth;
if (Changes[Next->Index].NewlinesBefore == 0) {
Changes[Next->Index].Spaces = (CellWidth - ThisWidth);
Changes[Next->Index].Spaces += (i > 0) ? 1 : 0;
}
alignToStartOfCell(Next->Index, Next->EndIndex);
}
}
}
}
void WhitespaceManager::alignArrayInitializersLeftJustified(
CellDescriptions &&CellDescs) {
if (!CellDescs.isRectangular())
return;
auto &Cells = CellDescs.Cells;
// Now go through and fixup the spaces.
auto *CellIter = Cells.begin();
// The first cell needs to be against the left brace.
if (Changes[CellIter->Index].NewlinesBefore == 0)
Changes[CellIter->Index].Spaces = 0;
else
Changes[CellIter->Index].Spaces = CellDescs.InitialSpaces;
++CellIter;
for (auto i = 1U; i < CellDescs.CellCounts[0]; i++, ++CellIter) {
auto MaxNetWidth = getMaximumNetWidth(
Cells.begin(), CellIter, CellDescs.InitialSpaces,
CellDescs.CellCounts[0], CellDescs.CellCounts.size());
auto ThisNetWidth =
getNetWidth(Cells.begin(), CellIter, CellDescs.InitialSpaces);
if (Changes[CellIter->Index].NewlinesBefore == 0) {
Changes[CellIter->Index].Spaces =
MaxNetWidth - ThisNetWidth +
(Changes[CellIter->Index].Tok->isNot(tok::r_brace) ? 1 : 0);
}
auto RowCount = 1U;
auto Offset = std::distance(Cells.begin(), CellIter);
for (const auto *Next = CellIter->NextColumnElement; Next != nullptr;
Next = Next->NextColumnElement) {
if (RowCount > CellDescs.CellCounts.size())
break;
auto *Start = (Cells.begin() + RowCount * CellDescs.CellCounts[0]);
auto *End = Start + Offset;
auto ThisNetWidth = getNetWidth(Start, End, CellDescs.InitialSpaces);
if (Changes[Next->Index].NewlinesBefore == 0) {
Changes[Next->Index].Spaces =
MaxNetWidth - ThisNetWidth +
(Changes[Next->Index].Tok->isNot(tok::r_brace) ? 1 : 0);
}
++RowCount;
}
}
}
bool WhitespaceManager::isSplitCell(const CellDescription &Cell) {
if (Cell.HasSplit)
return true;
for (const auto *Next = Cell.NextColumnElement; Next != nullptr;
Next = Next->NextColumnElement) {
if (Next->HasSplit)
return true;
}
return false;
}
WhitespaceManager::CellDescriptions WhitespaceManager::getCells(unsigned Start,
unsigned End) {
unsigned Depth = 0;
unsigned Cell = 0;
SmallVector<unsigned> CellCounts;
unsigned InitialSpaces = 0;
unsigned InitialTokenLength = 0;
unsigned EndSpaces = 0;
SmallVector<CellDescription> Cells;
const FormatToken *MatchingParen = nullptr;
for (unsigned i = Start; i < End; ++i) {
auto &C = Changes[i];
if (C.Tok->is(tok::l_brace))
++Depth;
else if (C.Tok->is(tok::r_brace))
--Depth;
if (Depth == 2) {
if (C.Tok->is(tok::l_brace)) {
Cell = 0;
MatchingParen = C.Tok->MatchingParen;
if (InitialSpaces == 0) {
InitialSpaces = C.Spaces + C.TokenLength;
InitialTokenLength = C.TokenLength;
auto j = i - 1;
for (; Changes[j].NewlinesBefore == 0 && j > Start; --j) {
InitialSpaces += Changes[j].Spaces + Changes[j].TokenLength;
InitialTokenLength += Changes[j].TokenLength;
}
if (C.NewlinesBefore == 0) {
InitialSpaces += Changes[j].Spaces + Changes[j].TokenLength;
InitialTokenLength += Changes[j].TokenLength;
}
}
} else if (C.Tok->is(tok::comma)) {
if (!Cells.empty())
Cells.back().EndIndex = i;
if (C.Tok->getNextNonComment()->isNot(tok::r_brace)) // dangling comma
++Cell;
}
} else if (Depth == 1) {
if (C.Tok == MatchingParen) {
if (!Cells.empty())
Cells.back().EndIndex = i;
Cells.push_back(CellDescription{i, ++Cell, i + 1, false, nullptr});
CellCounts.push_back(C.Tok->Previous->isNot(tok::comma) ? Cell + 1
: Cell);
// Go to the next non-comment and ensure there is a break in front
const auto *NextNonComment = C.Tok->getNextNonComment();
while (NextNonComment->is(tok::comma))
NextNonComment = NextNonComment->getNextNonComment();
auto j = i;
while (Changes[j].Tok != NextNonComment && j < End)
++j;
if (j < End && Changes[j].NewlinesBefore == 0 &&
Changes[j].Tok->isNot(tok::r_brace)) {
Changes[j].NewlinesBefore = 1;
// Account for the added token lengths
Changes[j].Spaces = InitialSpaces - InitialTokenLength;
}
} else if (C.Tok->is(tok::comment)) {
// Trailing comments stay at a space past the last token
C.Spaces = Changes[i - 1].Tok->is(tok::comma) ? 1 : 2;
} else if (C.Tok->is(tok::l_brace)) {
// We need to make sure that the ending braces is aligned to the
// start of our initializer
auto j = i - 1;
for (; j > 0 && !Changes[j].Tok->ArrayInitializerLineStart; --j)
; // Nothing the loop does the work
EndSpaces = Changes[j].Spaces;
}
} else if (Depth == 0 && C.Tok->is(tok::r_brace)) {
C.NewlinesBefore = 1;
C.Spaces = EndSpaces;
}
if (C.Tok->StartsColumn) {
// This gets us past tokens that have been split over multiple
// lines
bool HasSplit = false;
if (Changes[i].NewlinesBefore > 0) {
// So if we split a line previously and the tail line + this token is
// less then the column limit we remove the split here and just put
// the column start at a space past the comma
//
// FIXME This if branch covers the cases where the column is not
// the first column. This leads to weird pathologies like the formatting
// auto foo = Items{
// Section{
// 0, bar(),
// }
// };
// Well if it doesn't lead to that it's indicative that the line
// breaking should be revisited. Unfortunately alot of other options
// interact with this
auto j = i - 1;
if ((j - 1) > Start && Changes[j].Tok->is(tok::comma) &&
Changes[j - 1].NewlinesBefore > 0) {
--j;
auto LineLimit = Changes[j].Spaces + Changes[j].TokenLength;
if (LineLimit < Style.ColumnLimit) {
Changes[i].NewlinesBefore = 0;
Changes[i].Spaces = 1;
}
}
}
while (Changes[i].NewlinesBefore > 0 && Changes[i].Tok == C.Tok) {
Changes[i].Spaces = InitialSpaces;
++i;
HasSplit = true;
}
if (Changes[i].Tok != C.Tok)
--i;
Cells.push_back(CellDescription{i, Cell, i, HasSplit, nullptr});
}
}
return linkCells({Cells, CellCounts, InitialSpaces});
}
unsigned WhitespaceManager::calculateCellWidth(unsigned Start, unsigned End,
bool WithSpaces) const {
unsigned CellWidth = 0;
for (auto i = Start; i < End; i++) {
if (Changes[i].NewlinesBefore > 0)
CellWidth = 0;
CellWidth += Changes[i].TokenLength;
CellWidth += (WithSpaces ? Changes[i].Spaces : 0);
}
return CellWidth;
}
void WhitespaceManager::alignToStartOfCell(unsigned Start, unsigned End) {
if ((End - Start) <= 1)
return;
// If the line is broken anywhere in there make sure everything
// is aligned to the parent
for (auto i = Start + 1; i < End; i++)
if (Changes[i].NewlinesBefore > 0)
Changes[i].Spaces = Changes[Start].Spaces;
}
WhitespaceManager::CellDescriptions
WhitespaceManager::linkCells(CellDescriptions &&CellDesc) {
auto &Cells = CellDesc.Cells;
for (auto *CellIter = Cells.begin(); CellIter != Cells.end(); ++CellIter) {
if (CellIter->NextColumnElement == nullptr &&
((CellIter + 1) != Cells.end())) {
for (auto *NextIter = CellIter + 1; NextIter != Cells.end(); ++NextIter) {
if (NextIter->Cell == CellIter->Cell) {
CellIter->NextColumnElement = &(*NextIter);
break;
}
}
}
}
return std::move(CellDesc);
}
void WhitespaceManager::generateChanges() {
for (unsigned i = 0, e = Changes.size(); i != e; ++i) {
const Change &C = Changes[i];
if (i > 0 && Changes[i - 1].OriginalWhitespaceRange.getBegin() ==
C.OriginalWhitespaceRange.getBegin()) {
// Do not generate two replacements for the same location.
continue;
}
if (C.CreateReplacement) {
std::string ReplacementText = C.PreviousLinePostfix;
if (C.ContinuesPPDirective) {
appendEscapedNewlineText(ReplacementText, C.NewlinesBefore,
C.PreviousEndOfTokenColumn,
C.EscapedNewlineColumn);
} else {
appendNewlineText(ReplacementText, C.NewlinesBefore);
}
// FIXME: This assert should hold if we computed the column correctly.
// assert((int)C.StartOfTokenColumn >= C.Spaces);
appendIndentText(
ReplacementText, C.Tok->IndentLevel, std::max(0, C.Spaces),
std::max((int)C.StartOfTokenColumn, C.Spaces) - std::max(0, C.Spaces),
C.IsAligned);
ReplacementText.append(C.CurrentLinePrefix);
storeReplacement(C.OriginalWhitespaceRange, ReplacementText);
}
}
}
void WhitespaceManager::storeReplacement(SourceRange Range, StringRef Text) {
unsigned WhitespaceLength = SourceMgr.getFileOffset(Range.getEnd()) -
SourceMgr.getFileOffset(Range.getBegin());
// Don't create a replacement, if it does not change anything.
if (StringRef(SourceMgr.getCharacterData(Range.getBegin()),
WhitespaceLength) == Text) {
return;
}
auto Err = Replaces.add(tooling::Replacement(
SourceMgr, CharSourceRange::getCharRange(Range), Text));
// FIXME: better error handling. For now, just print an error message in the
// release version.
if (Err) {
llvm::errs() << llvm::toString(std::move(Err)) << "\n";
assert(false);
}
}
void WhitespaceManager::appendNewlineText(std::string &Text,
unsigned Newlines) {
if (UseCRLF) {
Text.reserve(Text.size() + 2 * Newlines);
for (unsigned i = 0; i < Newlines; ++i)
Text.append("\r\n");
} else {
Text.append(Newlines, '\n');
}
}
void WhitespaceManager::appendEscapedNewlineText(
std::string &Text, unsigned Newlines, unsigned PreviousEndOfTokenColumn,
unsigned EscapedNewlineColumn) {
if (Newlines > 0) {
unsigned Spaces =
std::max<int>(1, EscapedNewlineColumn - PreviousEndOfTokenColumn - 1);
for (unsigned i = 0; i < Newlines; ++i) {
Text.append(Spaces, ' ');
Text.append(UseCRLF ? "\\\r\n" : "\\\n");
Spaces = std::max<int>(0, EscapedNewlineColumn - 1);
}
}
}
void WhitespaceManager::appendIndentText(std::string &Text,
unsigned IndentLevel, unsigned Spaces,
unsigned WhitespaceStartColumn,
bool IsAligned) {
switch (Style.UseTab) {
case FormatStyle::UT_Never:
Text.append(Spaces, ' ');
break;
case FormatStyle::UT_Always: {
if (Style.TabWidth) {
unsigned FirstTabWidth =
Style.TabWidth - WhitespaceStartColumn % Style.TabWidth;
// Insert only spaces when we want to end up before the next tab.
if (Spaces < FirstTabWidth || Spaces == 1) {
Text.append(Spaces, ' ');
break;
}
// Align to the next tab.
Spaces -= FirstTabWidth;
Text.append("\t");
Text.append(Spaces / Style.TabWidth, '\t');
Text.append(Spaces % Style.TabWidth, ' ');
} else if (Spaces == 1) {
Text.append(Spaces, ' ');
}
break;
}
case FormatStyle::UT_ForIndentation:
if (WhitespaceStartColumn == 0) {
unsigned Indentation = IndentLevel * Style.IndentWidth;
Spaces = appendTabIndent(Text, Spaces, Indentation);
}
Text.append(Spaces, ' ');
break;
case FormatStyle::UT_ForContinuationAndIndentation:
if (WhitespaceStartColumn == 0)
Spaces = appendTabIndent(Text, Spaces, Spaces);
Text.append(Spaces, ' ');
break;
case FormatStyle::UT_AlignWithSpaces:
if (WhitespaceStartColumn == 0) {
unsigned Indentation =
IsAligned ? IndentLevel * Style.IndentWidth : Spaces;
Spaces = appendTabIndent(Text, Spaces, Indentation);
}
Text.append(Spaces, ' ');
break;
}
}
unsigned WhitespaceManager::appendTabIndent(std::string &Text, unsigned Spaces,
unsigned Indentation) {
// This happens, e.g. when a line in a block comment is indented less than the
// first one.
if (Indentation > Spaces)
Indentation = Spaces;
if (Style.TabWidth) {
unsigned Tabs = Indentation / Style.TabWidth;
Text.append(Tabs, '\t');
Spaces -= Tabs * Style.TabWidth;
}
return Spaces;
}
} // namespace format
} // namespace clang
|