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
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
|
//===--- PPDirectives.cpp - Directive Handling for Preprocessor -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements # directive processing for the Preprocessor.
//
//===----------------------------------------------------------------------===//
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/MacroInfo.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/SourceManager.h"
#include "llvm/ADT/APInt.h"
using namespace clang;
//===----------------------------------------------------------------------===//
// Utility Methods for Preprocessor Directive Handling.
//===----------------------------------------------------------------------===//
MacroInfo *Preprocessor::AllocateMacroInfo(SourceLocation L) {
MacroInfo *MI;
if (!MICache.empty()) {
MI = MICache.back();
MICache.pop_back();
} else
MI = (MacroInfo*) BP.Allocate<MacroInfo>();
new (MI) MacroInfo(L);
return MI;
}
/// ReleaseMacroInfo - Release the specified MacroInfo. This memory will
/// be reused for allocating new MacroInfo objects.
void Preprocessor::ReleaseMacroInfo(MacroInfo* MI) {
MICache.push_back(MI);
MI->FreeArgumentList(BP);
}
/// DiscardUntilEndOfDirective - Read and discard all tokens remaining on the
/// current line until the tok::eom token is found.
void Preprocessor::DiscardUntilEndOfDirective() {
Token Tmp;
do {
LexUnexpandedToken(Tmp);
} while (Tmp.isNot(tok::eom));
}
/// ReadMacroName - Lex and validate a macro name, which occurs after a
/// #define or #undef. This sets the token kind to eom and discards the rest
/// of the macro line if the macro name is invalid. isDefineUndef is 1 if
/// this is due to a a #define, 2 if #undef directive, 0 if it is something
/// else (e.g. #ifdef).
void Preprocessor::ReadMacroName(Token &MacroNameTok, char isDefineUndef) {
// Read the token, don't allow macro expansion on it.
LexUnexpandedToken(MacroNameTok);
// Missing macro name?
if (MacroNameTok.is(tok::eom)) {
Diag(MacroNameTok, diag::err_pp_missing_macro_name);
return;
}
IdentifierInfo *II = MacroNameTok.getIdentifierInfo();
if (II == 0) {
bool Invalid = false;
std::string Spelling = getSpelling(MacroNameTok, &Invalid);
if (Invalid)
return;
const IdentifierInfo &Info = Identifiers.get(Spelling);
if (Info.isCPlusPlusOperatorKeyword())
// C++ 2.5p2: Alternative tokens behave the same as its primary token
// except for their spellings.
Diag(MacroNameTok, diag::err_pp_operator_used_as_macro_name) << Spelling;
else
Diag(MacroNameTok, diag::err_pp_macro_not_identifier);
// Fall through on error.
} else if (isDefineUndef && II->getPPKeywordID() == tok::pp_defined) {
// Error if defining "defined": C99 6.10.8.4.
Diag(MacroNameTok, diag::err_defined_macro_name);
} else if (isDefineUndef && II->hasMacroDefinition() &&
getMacroInfo(II)->isBuiltinMacro()) {
// Error if defining "__LINE__" and other builtins: C99 6.10.8.4.
if (isDefineUndef == 1)
Diag(MacroNameTok, diag::pp_redef_builtin_macro);
else
Diag(MacroNameTok, diag::pp_undef_builtin_macro);
} else {
// Okay, we got a good identifier node. Return it.
return;
}
// Invalid macro name, read and discard the rest of the line. Then set the
// token kind to tok::eom.
MacroNameTok.setKind(tok::eom);
return DiscardUntilEndOfDirective();
}
/// CheckEndOfDirective - Ensure that the next token is a tok::eom token. If
/// not, emit a diagnostic and consume up until the eom. If EnableMacros is
/// true, then we consider macros that expand to zero tokens as being ok.
void Preprocessor::CheckEndOfDirective(const char *DirType, bool EnableMacros) {
Token Tmp;
// Lex unexpanded tokens for most directives: macros might expand to zero
// tokens, causing us to miss diagnosing invalid lines. Some directives (like
// #line) allow empty macros.
if (EnableMacros)
Lex(Tmp);
else
LexUnexpandedToken(Tmp);
// There should be no tokens after the directive, but we allow them as an
// extension.
while (Tmp.is(tok::comment)) // Skip comments in -C mode.
LexUnexpandedToken(Tmp);
if (Tmp.isNot(tok::eom)) {
// Add a fixit in GNU/C99/C++ mode. Don't offer a fixit for strict-C89,
// because it is more trouble than it is worth to insert /**/ and check that
// there is no /**/ in the range also.
FixItHint Hint;
if (Features.GNUMode || Features.C99 || Features.CPlusPlus)
Hint = FixItHint::CreateInsertion(Tmp.getLocation(),"//");
Diag(Tmp, diag::ext_pp_extra_tokens_at_eol) << DirType << Hint;
DiscardUntilEndOfDirective();
}
}
/// SkipExcludedConditionalBlock - We just read a #if or related directive and
/// decided that the subsequent tokens are in the #if'd out portion of the
/// file. Lex the rest of the file, until we see an #endif. If
/// FoundNonSkipPortion is true, then we have already emitted code for part of
/// this #if directive, so #else/#elif blocks should never be entered. If ElseOk
/// is true, then #else directives are ok, if not, then we have already seen one
/// so a #else directive is a duplicate. When this returns, the caller can lex
/// the first valid token.
void Preprocessor::SkipExcludedConditionalBlock(SourceLocation IfTokenLoc,
bool FoundNonSkipPortion,
bool FoundElse) {
++NumSkipped;
assert(CurTokenLexer == 0 && CurPPLexer && "Lexing a macro, not a file?");
CurPPLexer->pushConditionalLevel(IfTokenLoc, /*isSkipping*/false,
FoundNonSkipPortion, FoundElse);
if (CurPTHLexer) {
PTHSkipExcludedConditionalBlock();
return;
}
// Enter raw mode to disable identifier lookup (and thus macro expansion),
// disabling warnings, etc.
CurPPLexer->LexingRawMode = true;
Token Tok;
while (1) {
CurLexer->Lex(Tok);
// If this is the end of the buffer, we have an error.
if (Tok.is(tok::eof)) {
// Emit errors for each unterminated conditional on the stack, including
// the current one.
while (!CurPPLexer->ConditionalStack.empty()) {
Diag(CurPPLexer->ConditionalStack.back().IfLoc,
diag::err_pp_unterminated_conditional);
CurPPLexer->ConditionalStack.pop_back();
}
// Just return and let the caller lex after this #include.
break;
}
// If this token is not a preprocessor directive, just skip it.
if (Tok.isNot(tok::hash) || !Tok.isAtStartOfLine())
continue;
// We just parsed a # character at the start of a line, so we're in
// directive mode. Tell the lexer this so any newlines we see will be
// converted into an EOM token (this terminates the macro).
CurPPLexer->ParsingPreprocessorDirective = true;
if (CurLexer) CurLexer->SetCommentRetentionState(false);
// Read the next token, the directive flavor.
LexUnexpandedToken(Tok);
// If this isn't an identifier directive (e.g. is "# 1\n" or "#\n", or
// something bogus), skip it.
if (Tok.isNot(tok::identifier)) {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepComments);
continue;
}
// If the first letter isn't i or e, it isn't intesting to us. We know that
// this is safe in the face of spelling differences, because there is no way
// to spell an i/e in a strange way that is another letter. Skipping this
// allows us to avoid looking up the identifier info for #define/#undef and
// other common directives.
bool Invalid = false;
const char *RawCharData = SourceMgr.getCharacterData(Tok.getLocation(),
&Invalid);
if (Invalid)
return;
char FirstChar = RawCharData[0];
if (FirstChar >= 'a' && FirstChar <= 'z' &&
FirstChar != 'i' && FirstChar != 'e') {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepComments);
continue;
}
// Get the identifier name without trigraphs or embedded newlines. Note
// that we can't use Tok.getIdentifierInfo() because its lookup is disabled
// when skipping.
char DirectiveBuf[20];
llvm::StringRef Directive;
if (!Tok.needsCleaning() && Tok.getLength() < 20) {
Directive = llvm::StringRef(RawCharData, Tok.getLength());
} else {
std::string DirectiveStr = getSpelling(Tok);
unsigned IdLen = DirectiveStr.size();
if (IdLen >= 20) {
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepComments);
continue;
}
memcpy(DirectiveBuf, &DirectiveStr[0], IdLen);
Directive = llvm::StringRef(DirectiveBuf, IdLen);
}
if (Directive.startswith("if")) {
llvm::StringRef Sub = Directive.substr(2);
if (Sub.empty() || // "if"
Sub == "def" || // "ifdef"
Sub == "ndef") { // "ifndef"
// We know the entire #if/#ifdef/#ifndef block will be skipped, don't
// bother parsing the condition.
DiscardUntilEndOfDirective();
CurPPLexer->pushConditionalLevel(Tok.getLocation(), /*wasskipping*/true,
/*foundnonskip*/false,
/*fnddelse*/false);
}
} else if (Directive[0] == 'e') {
llvm::StringRef Sub = Directive.substr(1);
if (Sub == "ndif") { // "endif"
CheckEndOfDirective("endif");
PPConditionalInfo CondInfo;
CondInfo.WasSkipping = true; // Silence bogus warning.
bool InCond = CurPPLexer->popConditionalLevel(CondInfo);
InCond = InCond; // Silence warning in no-asserts mode.
assert(!InCond && "Can't be skipping if not in a conditional!");
// If we popped the outermost skipping block, we're done skipping!
if (!CondInfo.WasSkipping)
break;
} else if (Sub == "lse") { // "else".
// #else directive in a skipping conditional. If not in some other
// skipping conditional, and if #else hasn't already been seen, enter it
// as a non-skipping conditional.
DiscardUntilEndOfDirective(); // C99 6.10p4.
PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();
// If this is a #else with a #else before it, report the error.
if (CondInfo.FoundElse) Diag(Tok, diag::pp_err_else_after_else);
// Note that we've seen a #else in this conditional.
CondInfo.FoundElse = true;
// If the conditional is at the top level, and the #if block wasn't
// entered, enter the #else block now.
if (!CondInfo.WasSkipping && !CondInfo.FoundNonSkip) {
CondInfo.FoundNonSkip = true;
break;
}
} else if (Sub == "lif") { // "elif".
PPConditionalInfo &CondInfo = CurPPLexer->peekConditionalLevel();
bool ShouldEnter;
// If this is in a skipping block or if we're already handled this #if
// block, don't bother parsing the condition.
if (CondInfo.WasSkipping || CondInfo.FoundNonSkip) {
DiscardUntilEndOfDirective();
ShouldEnter = false;
} else {
// Restore the value of LexingRawMode so that identifiers are
// looked up, etc, inside the #elif expression.
assert(CurPPLexer->LexingRawMode && "We have to be skipping here!");
CurPPLexer->LexingRawMode = false;
IdentifierInfo *IfNDefMacro = 0;
ShouldEnter = EvaluateDirectiveExpression(IfNDefMacro);
CurPPLexer->LexingRawMode = true;
}
// If this is a #elif with a #else before it, report the error.
if (CondInfo.FoundElse) Diag(Tok, diag::pp_err_elif_after_else);
// If this condition is true, enter it!
if (ShouldEnter) {
CondInfo.FoundNonSkip = true;
break;
}
}
}
CurPPLexer->ParsingPreprocessorDirective = false;
// Restore comment saving mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepComments);
}
// Finally, if we are out of the conditional (saw an #endif or ran off the end
// of the file, just stop skipping and return to lexing whatever came after
// the #if block.
CurPPLexer->LexingRawMode = false;
}
void Preprocessor::PTHSkipExcludedConditionalBlock() {
while (1) {
assert(CurPTHLexer);
assert(CurPTHLexer->LexingRawMode == false);
// Skip to the next '#else', '#elif', or #endif.
if (CurPTHLexer->SkipBlock()) {
// We have reached an #endif. Both the '#' and 'endif' tokens
// have been consumed by the PTHLexer. Just pop off the condition level.
PPConditionalInfo CondInfo;
bool InCond = CurPTHLexer->popConditionalLevel(CondInfo);
InCond = InCond; // Silence warning in no-asserts mode.
assert(!InCond && "Can't be skipping if not in a conditional!");
break;
}
// We have reached a '#else' or '#elif'. Lex the next token to get
// the directive flavor.
Token Tok;
LexUnexpandedToken(Tok);
// We can actually look up the IdentifierInfo here since we aren't in
// raw mode.
tok::PPKeywordKind K = Tok.getIdentifierInfo()->getPPKeywordID();
if (K == tok::pp_else) {
// #else: Enter the else condition. We aren't in a nested condition
// since we skip those. We're always in the one matching the last
// blocked we skipped.
PPConditionalInfo &CondInfo = CurPTHLexer->peekConditionalLevel();
// Note that we've seen a #else in this conditional.
CondInfo.FoundElse = true;
// If the #if block wasn't entered then enter the #else block now.
if (!CondInfo.FoundNonSkip) {
CondInfo.FoundNonSkip = true;
// Scan until the eom token.
CurPTHLexer->ParsingPreprocessorDirective = true;
DiscardUntilEndOfDirective();
CurPTHLexer->ParsingPreprocessorDirective = false;
break;
}
// Otherwise skip this block.
continue;
}
assert(K == tok::pp_elif);
PPConditionalInfo &CondInfo = CurPTHLexer->peekConditionalLevel();
// If this is a #elif with a #else before it, report the error.
if (CondInfo.FoundElse)
Diag(Tok, diag::pp_err_elif_after_else);
// If this is in a skipping block or if we're already handled this #if
// block, don't bother parsing the condition. We just skip this block.
if (CondInfo.FoundNonSkip)
continue;
// Evaluate the condition of the #elif.
IdentifierInfo *IfNDefMacro = 0;
CurPTHLexer->ParsingPreprocessorDirective = true;
bool ShouldEnter = EvaluateDirectiveExpression(IfNDefMacro);
CurPTHLexer->ParsingPreprocessorDirective = false;
// If this condition is true, enter it!
if (ShouldEnter) {
CondInfo.FoundNonSkip = true;
break;
}
// Otherwise, skip this block and go to the next one.
continue;
}
}
/// LookupFile - Given a "foo" or <foo> reference, look up the indicated file,
/// return null on failure. isAngled indicates whether the file reference is
/// for system #include's or not (i.e. using <> instead of "").
const FileEntry *Preprocessor::LookupFile(llvm::StringRef Filename,
bool isAngled,
const DirectoryLookup *FromDir,
const DirectoryLookup *&CurDir) {
// If the header lookup mechanism may be relative to the current file, pass in
// info about where the current file is.
const FileEntry *CurFileEnt = 0;
if (!FromDir) {
FileID FID = getCurrentFileLexer()->getFileID();
CurFileEnt = SourceMgr.getFileEntryForID(FID);
// If there is no file entry associated with this file, it must be the
// predefines buffer. Any other file is not lexed with a normal lexer, so
// it won't be scanned for preprocessor directives. If we have the
// predefines buffer, resolve #include references (which come from the
// -include command line argument) as if they came from the main file, this
// affects file lookup etc.
if (CurFileEnt == 0) {
FID = SourceMgr.getMainFileID();
CurFileEnt = SourceMgr.getFileEntryForID(FID);
}
}
// Do a standard file entry lookup.
CurDir = CurDirLookup;
const FileEntry *FE =
HeaderInfo.LookupFile(Filename, isAngled, FromDir, CurDir, CurFileEnt);
if (FE) return FE;
// Otherwise, see if this is a subframework header. If so, this is relative
// to one of the headers on the #include stack. Walk the list of the current
// headers on the #include stack and pass them to HeaderInfo.
if (IsFileLexer()) {
if ((CurFileEnt = SourceMgr.getFileEntryForID(CurPPLexer->getFileID())))
if ((FE = HeaderInfo.LookupSubframeworkHeader(Filename, CurFileEnt)))
return FE;
}
for (unsigned i = 0, e = IncludeMacroStack.size(); i != e; ++i) {
IncludeStackInfo &ISEntry = IncludeMacroStack[e-i-1];
if (IsFileLexer(ISEntry)) {
if ((CurFileEnt =
SourceMgr.getFileEntryForID(ISEntry.ThePPLexer->getFileID())))
if ((FE = HeaderInfo.LookupSubframeworkHeader(Filename, CurFileEnt)))
return FE;
}
}
// Otherwise, we really couldn't find the file.
return 0;
}
//===----------------------------------------------------------------------===//
// Preprocessor Directive Handling.
//===----------------------------------------------------------------------===//
/// HandleDirective - This callback is invoked when the lexer sees a # token
/// at the start of a line. This consumes the directive, modifies the
/// lexer/preprocessor state, and advances the lexer(s) so that the next token
/// read is the correct one.
void Preprocessor::HandleDirective(Token &Result) {
// FIXME: Traditional: # with whitespace before it not recognized by K&R?
// We just parsed a # character at the start of a line, so we're in directive
// mode. Tell the lexer this so any newlines we see will be converted into an
// EOM token (which terminates the directive).
CurPPLexer->ParsingPreprocessorDirective = true;
++NumDirectives;
// We are about to read a token. For the multiple-include optimization FA to
// work, we have to remember if we had read any tokens *before* this
// pp-directive.
bool ReadAnyTokensBeforeDirective =CurPPLexer->MIOpt.getHasReadAnyTokensVal();
// Save the '#' token in case we need to return it later.
Token SavedHash = Result;
// Read the next token, the directive flavor. This isn't expanded due to
// C99 6.10.3p8.
LexUnexpandedToken(Result);
// C99 6.10.3p11: Is this preprocessor directive in macro invocation? e.g.:
// #define A(x) #x
// A(abc
// #warning blah
// def)
// If so, the user is relying on non-portable behavior, emit a diagnostic.
if (InMacroArgs)
Diag(Result, diag::ext_embedded_directive);
TryAgain:
switch (Result.getKind()) {
case tok::eom:
return; // null directive.
case tok::comment:
// Handle stuff like "# /*foo*/ define X" in -E -C mode.
LexUnexpandedToken(Result);
goto TryAgain;
case tok::numeric_constant: // # 7 GNU line marker directive.
if (getLangOptions().AsmPreprocessor)
break; // # 4 is not a preprocessor directive in .S files.
return HandleDigitDirective(Result);
default:
IdentifierInfo *II = Result.getIdentifierInfo();
if (II == 0) break; // Not an identifier.
// Ask what the preprocessor keyword ID is.
switch (II->getPPKeywordID()) {
default: break;
// C99 6.10.1 - Conditional Inclusion.
case tok::pp_if:
return HandleIfDirective(Result, ReadAnyTokensBeforeDirective);
case tok::pp_ifdef:
return HandleIfdefDirective(Result, false, true/*not valid for miopt*/);
case tok::pp_ifndef:
return HandleIfdefDirective(Result, true, ReadAnyTokensBeforeDirective);
case tok::pp_elif:
return HandleElifDirective(Result);
case tok::pp_else:
return HandleElseDirective(Result);
case tok::pp_endif:
return HandleEndifDirective(Result);
// C99 6.10.2 - Source File Inclusion.
case tok::pp_include:
return HandleIncludeDirective(Result); // Handle #include.
case tok::pp___include_macros:
return HandleIncludeMacrosDirective(Result); // Handle -imacros.
// C99 6.10.3 - Macro Replacement.
case tok::pp_define:
return HandleDefineDirective(Result);
case tok::pp_undef:
return HandleUndefDirective(Result);
// C99 6.10.4 - Line Control.
case tok::pp_line:
return HandleLineDirective(Result);
// C99 6.10.5 - Error Directive.
case tok::pp_error:
return HandleUserDiagnosticDirective(Result, false);
// C99 6.10.6 - Pragma Directive.
case tok::pp_pragma:
return HandlePragmaDirective();
// GNU Extensions.
case tok::pp_import:
return HandleImportDirective(Result);
case tok::pp_include_next:
return HandleIncludeNextDirective(Result);
case tok::pp_warning:
Diag(Result, diag::ext_pp_warning_directive);
return HandleUserDiagnosticDirective(Result, true);
case tok::pp_ident:
return HandleIdentSCCSDirective(Result);
case tok::pp_sccs:
return HandleIdentSCCSDirective(Result);
case tok::pp_assert:
//isExtension = true; // FIXME: implement #assert
break;
case tok::pp_unassert:
//isExtension = true; // FIXME: implement #unassert
break;
}
break;
}
// If this is a .S file, treat unknown # directives as non-preprocessor
// directives. This is important because # may be a comment or introduce
// various pseudo-ops. Just return the # token and push back the following
// token to be lexed next time.
if (getLangOptions().AsmPreprocessor) {
Token *Toks = new Token[2];
// Return the # and the token after it.
Toks[0] = SavedHash;
Toks[1] = Result;
// Enter this token stream so that we re-lex the tokens. Make sure to
// enable macro expansion, in case the token after the # is an identifier
// that is expanded.
EnterTokenStream(Toks, 2, false, true);
return;
}
// If we reached here, the preprocessing token is not valid!
Diag(Result, diag::err_pp_invalid_directive);
// Read the rest of the PP line.
DiscardUntilEndOfDirective();
// Okay, we're done parsing the directive.
}
/// GetLineValue - Convert a numeric token into an unsigned value, emitting
/// Diagnostic DiagID if it is invalid, and returning the value in Val.
static bool GetLineValue(Token &DigitTok, unsigned &Val,
unsigned DiagID, Preprocessor &PP) {
if (DigitTok.isNot(tok::numeric_constant)) {
PP.Diag(DigitTok, DiagID);
if (DigitTok.isNot(tok::eom))
PP.DiscardUntilEndOfDirective();
return true;
}
llvm::SmallString<64> IntegerBuffer;
IntegerBuffer.resize(DigitTok.getLength());
const char *DigitTokBegin = &IntegerBuffer[0];
bool Invalid = false;
unsigned ActualLength = PP.getSpelling(DigitTok, DigitTokBegin, &Invalid);
if (Invalid)
return true;
// Verify that we have a simple digit-sequence, and compute the value. This
// is always a simple digit string computed in decimal, so we do this manually
// here.
Val = 0;
for (unsigned i = 0; i != ActualLength; ++i) {
if (!isdigit(DigitTokBegin[i])) {
PP.Diag(PP.AdvanceToTokenCharacter(DigitTok.getLocation(), i),
diag::err_pp_line_digit_sequence);
PP.DiscardUntilEndOfDirective();
return true;
}
unsigned NextVal = Val*10+(DigitTokBegin[i]-'0');
if (NextVal < Val) { // overflow.
PP.Diag(DigitTok, DiagID);
PP.DiscardUntilEndOfDirective();
return true;
}
Val = NextVal;
}
// Reject 0, this is needed both by #line numbers and flags.
if (Val == 0) {
PP.Diag(DigitTok, DiagID);
PP.DiscardUntilEndOfDirective();
return true;
}
if (DigitTokBegin[0] == '0')
PP.Diag(DigitTok.getLocation(), diag::warn_pp_line_decimal);
return false;
}
/// HandleLineDirective - Handle #line directive: C99 6.10.4. The two
/// acceptable forms are:
/// # line digit-sequence
/// # line digit-sequence "s-char-sequence"
void Preprocessor::HandleLineDirective(Token &Tok) {
// Read the line # and string argument. Per C99 6.10.4p5, these tokens are
// expanded.
Token DigitTok;
Lex(DigitTok);
// Validate the number and convert it to an unsigned.
unsigned LineNo;
if (GetLineValue(DigitTok, LineNo, diag::err_pp_line_requires_integer,*this))
return;
// Enforce C99 6.10.4p3: "The digit sequence shall not specify ... a
// number greater than 2147483647". C90 requires that the line # be <= 32767.
unsigned LineLimit = Features.C99 ? 2147483648U : 32768U;
if (LineNo >= LineLimit)
Diag(DigitTok, diag::ext_pp_line_too_big) << LineLimit;
int FilenameID = -1;
Token StrTok;
Lex(StrTok);
// If the StrTok is "eom", then it wasn't present. Otherwise, it must be a
// string followed by eom.
if (StrTok.is(tok::eom))
; // ok
else if (StrTok.isNot(tok::string_literal)) {
Diag(StrTok, diag::err_pp_line_invalid_filename);
DiscardUntilEndOfDirective();
return;
} else {
// Parse and validate the string, converting it into a unique ID.
StringLiteralParser Literal(&StrTok, 1, *this);
assert(!Literal.AnyWide && "Didn't allow wide strings in");
if (Literal.hadError)
return DiscardUntilEndOfDirective();
if (Literal.Pascal) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
return DiscardUntilEndOfDirective();
}
FilenameID = SourceMgr.getLineTableFilenameID(Literal.GetString(),
Literal.GetStringLength());
// Verify that there is nothing after the string, other than EOM. Because
// of C99 6.10.4p5, macros that expand to empty tokens are ok.
CheckEndOfDirective("line", true);
}
SourceMgr.AddLineNote(DigitTok.getLocation(), LineNo, FilenameID);
if (Callbacks)
Callbacks->FileChanged(DigitTok.getLocation(), PPCallbacks::RenameFile,
SrcMgr::C_User);
}
/// ReadLineMarkerFlags - Parse and validate any flags at the end of a GNU line
/// marker directive.
static bool ReadLineMarkerFlags(bool &IsFileEntry, bool &IsFileExit,
bool &IsSystemHeader, bool &IsExternCHeader,
Preprocessor &PP) {
unsigned FlagVal;
Token FlagTok;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eom)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag, PP))
return true;
if (FlagVal == 1) {
IsFileEntry = true;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eom)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag,PP))
return true;
} else if (FlagVal == 2) {
IsFileExit = true;
SourceManager &SM = PP.getSourceManager();
// If we are leaving the current presumed file, check to make sure the
// presumed include stack isn't empty!
FileID CurFileID =
SM.getDecomposedInstantiationLoc(FlagTok.getLocation()).first;
PresumedLoc PLoc = SM.getPresumedLoc(FlagTok.getLocation());
// If there is no include loc (main file) or if the include loc is in a
// different physical file, then we aren't in a "1" line marker flag region.
SourceLocation IncLoc = PLoc.getIncludeLoc();
if (IncLoc.isInvalid() ||
SM.getDecomposedInstantiationLoc(IncLoc).first != CurFileID) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_pop);
PP.DiscardUntilEndOfDirective();
return true;
}
PP.Lex(FlagTok);
if (FlagTok.is(tok::eom)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag,PP))
return true;
}
// We must have 3 if there are still flags.
if (FlagVal != 3) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
IsSystemHeader = true;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eom)) return false;
if (GetLineValue(FlagTok, FlagVal, diag::err_pp_linemarker_invalid_flag, PP))
return true;
// We must have 4 if there is yet another flag.
if (FlagVal != 4) {
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
IsExternCHeader = true;
PP.Lex(FlagTok);
if (FlagTok.is(tok::eom)) return false;
// There are no more valid flags here.
PP.Diag(FlagTok, diag::err_pp_linemarker_invalid_flag);
PP.DiscardUntilEndOfDirective();
return true;
}
/// HandleDigitDirective - Handle a GNU line marker directive, whose syntax is
/// one of the following forms:
///
/// # 42
/// # 42 "file" ('1' | '2')?
/// # 42 "file" ('1' | '2')? '3' '4'?
///
void Preprocessor::HandleDigitDirective(Token &DigitTok) {
// Validate the number and convert it to an unsigned. GNU does not have a
// line # limit other than it fit in 32-bits.
unsigned LineNo;
if (GetLineValue(DigitTok, LineNo, diag::err_pp_linemarker_requires_integer,
*this))
return;
Token StrTok;
Lex(StrTok);
bool IsFileEntry = false, IsFileExit = false;
bool IsSystemHeader = false, IsExternCHeader = false;
int FilenameID = -1;
// If the StrTok is "eom", then it wasn't present. Otherwise, it must be a
// string followed by eom.
if (StrTok.is(tok::eom))
; // ok
else if (StrTok.isNot(tok::string_literal)) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
return DiscardUntilEndOfDirective();
} else {
// Parse and validate the string, converting it into a unique ID.
StringLiteralParser Literal(&StrTok, 1, *this);
assert(!Literal.AnyWide && "Didn't allow wide strings in");
if (Literal.hadError)
return DiscardUntilEndOfDirective();
if (Literal.Pascal) {
Diag(StrTok, diag::err_pp_linemarker_invalid_filename);
return DiscardUntilEndOfDirective();
}
FilenameID = SourceMgr.getLineTableFilenameID(Literal.GetString(),
Literal.GetStringLength());
// If a filename was present, read any flags that are present.
if (ReadLineMarkerFlags(IsFileEntry, IsFileExit,
IsSystemHeader, IsExternCHeader, *this))
return;
}
// Create a line note with this information.
SourceMgr.AddLineNote(DigitTok.getLocation(), LineNo, FilenameID,
IsFileEntry, IsFileExit,
IsSystemHeader, IsExternCHeader);
// If the preprocessor has callbacks installed, notify them of the #line
// change. This is used so that the line marker comes out in -E mode for
// example.
if (Callbacks) {
PPCallbacks::FileChangeReason Reason = PPCallbacks::RenameFile;
if (IsFileEntry)
Reason = PPCallbacks::EnterFile;
else if (IsFileExit)
Reason = PPCallbacks::ExitFile;
SrcMgr::CharacteristicKind FileKind = SrcMgr::C_User;
if (IsExternCHeader)
FileKind = SrcMgr::C_ExternCSystem;
else if (IsSystemHeader)
FileKind = SrcMgr::C_System;
Callbacks->FileChanged(DigitTok.getLocation(), Reason, FileKind);
}
}
/// HandleUserDiagnosticDirective - Handle a #warning or #error directive.
///
void Preprocessor::HandleUserDiagnosticDirective(Token &Tok,
bool isWarning) {
// PTH doesn't emit #warning or #error directives.
if (CurPTHLexer)
return CurPTHLexer->DiscardToEndOfLine();
// Read the rest of the line raw. We do this because we don't want macros
// to be expanded and we don't require that the tokens be valid preprocessing
// tokens. For example, this is allowed: "#warning ` 'foo". GCC does
// collapse multiple consequtive white space between tokens, but this isn't
// specified by the standard.
std::string Message = CurLexer->ReadToEndOfLine();
if (isWarning)
Diag(Tok, diag::pp_hash_warning) << Message;
else
Diag(Tok, diag::err_pp_hash_error) << Message;
}
/// HandleIdentSCCSDirective - Handle a #ident/#sccs directive.
///
void Preprocessor::HandleIdentSCCSDirective(Token &Tok) {
// Yes, this directive is an extension.
Diag(Tok, diag::ext_pp_ident_directive);
// Read the string argument.
Token StrTok;
Lex(StrTok);
// If the token kind isn't a string, it's a malformed directive.
if (StrTok.isNot(tok::string_literal) &&
StrTok.isNot(tok::wide_string_literal)) {
Diag(StrTok, diag::err_pp_malformed_ident);
if (StrTok.isNot(tok::eom))
DiscardUntilEndOfDirective();
return;
}
// Verify that there is nothing after the string, other than EOM.
CheckEndOfDirective("ident");
if (Callbacks) {
bool Invalid = false;
std::string Str = getSpelling(StrTok, &Invalid);
if (!Invalid)
Callbacks->Ident(Tok.getLocation(), Str);
}
}
//===----------------------------------------------------------------------===//
// Preprocessor Include Directive Handling.
//===----------------------------------------------------------------------===//
/// GetIncludeFilenameSpelling - Turn the specified lexer token into a fully
/// checked and spelled filename, e.g. as an operand of #include. This returns
/// true if the input filename was in <>'s or false if it were in ""'s. The
/// caller is expected to provide a buffer that is large enough to hold the
/// spelling of the filename, but is also expected to handle the case when
/// this method decides to use a different buffer.
bool Preprocessor::GetIncludeFilenameSpelling(SourceLocation Loc,
llvm::StringRef &Buffer) {
// Get the text form of the filename.
assert(!Buffer.empty() && "Can't have tokens with empty spellings!");
// Make sure the filename is <x> or "x".
bool isAngled;
if (Buffer[0] == '<') {
if (Buffer.back() != '>') {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = llvm::StringRef();
return true;
}
isAngled = true;
} else if (Buffer[0] == '"') {
if (Buffer.back() != '"') {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = llvm::StringRef();
return true;
}
isAngled = false;
} else {
Diag(Loc, diag::err_pp_expects_filename);
Buffer = llvm::StringRef();
return true;
}
// Diagnose #include "" as invalid.
if (Buffer.size() <= 2) {
Diag(Loc, diag::err_pp_empty_filename);
Buffer = llvm::StringRef();
return true;
}
// Skip the brackets.
Buffer = Buffer.substr(1, Buffer.size()-2);
return isAngled;
}
/// ConcatenateIncludeName - Handle cases where the #include name is expanded
/// from a macro as multiple tokens, which need to be glued together. This
/// occurs for code like:
/// #define FOO <a/b.h>
/// #include FOO
/// because in this case, "<a/b.h>" is returned as 7 tokens, not one.
///
/// This code concatenates and consumes tokens up to the '>' token. It returns
/// false if the > was found, otherwise it returns true if it finds and consumes
/// the EOM marker.
bool Preprocessor::ConcatenateIncludeName(
llvm::SmallString<128> &FilenameBuffer) {
Token CurTok;
Lex(CurTok);
while (CurTok.isNot(tok::eom)) {
// Append the spelling of this token to the buffer. If there was a space
// before it, add it now.
if (CurTok.hasLeadingSpace())
FilenameBuffer.push_back(' ');
// Get the spelling of the token, directly into FilenameBuffer if possible.
unsigned PreAppendSize = FilenameBuffer.size();
FilenameBuffer.resize(PreAppendSize+CurTok.getLength());
const char *BufPtr = &FilenameBuffer[PreAppendSize];
unsigned ActualLen = getSpelling(CurTok, BufPtr);
// If the token was spelled somewhere else, copy it into FilenameBuffer.
if (BufPtr != &FilenameBuffer[PreAppendSize])
memcpy(&FilenameBuffer[PreAppendSize], BufPtr, ActualLen);
// Resize FilenameBuffer to the correct size.
if (CurTok.getLength() != ActualLen)
FilenameBuffer.resize(PreAppendSize+ActualLen);
// If we found the '>' marker, return success.
if (CurTok.is(tok::greater))
return false;
Lex(CurTok);
}
// If we hit the eom marker, emit an error and return true so that the caller
// knows the EOM has been read.
Diag(CurTok.getLocation(), diag::err_pp_expects_filename);
return true;
}
/// HandleIncludeDirective - The "#include" tokens have just been read, read the
/// file to be included from the lexer, then include it! This is a common
/// routine with functionality shared between #include, #include_next and
/// #import. LookupFrom is set when this is a #include_next directive, it
/// specifies the file to start searching from.
void Preprocessor::HandleIncludeDirective(Token &IncludeTok,
const DirectoryLookup *LookupFrom,
bool isImport) {
Token FilenameTok;
CurPPLexer->LexIncludeFilename(FilenameTok);
// Reserve a buffer to get the spelling.
llvm::SmallString<128> FilenameBuffer;
llvm::StringRef Filename;
switch (FilenameTok.getKind()) {
case tok::eom:
// If the token kind is EOM, the error has already been diagnosed.
return;
case tok::angle_string_literal:
case tok::string_literal:
Filename = getSpelling(FilenameTok, FilenameBuffer);
break;
case tok::less:
// This could be a <foo/bar.h> file coming from a macro expansion. In this
// case, glue the tokens together into FilenameBuffer and interpret those.
FilenameBuffer.push_back('<');
if (ConcatenateIncludeName(FilenameBuffer))
return; // Found <eom> but no ">"? Diagnostic already emitted.
Filename = FilenameBuffer.str();
break;
default:
Diag(FilenameTok.getLocation(), diag::err_pp_expects_filename);
DiscardUntilEndOfDirective();
return;
}
bool isAngled =
GetIncludeFilenameSpelling(FilenameTok.getLocation(), Filename);
// If GetIncludeFilenameSpelling set the start ptr to null, there was an
// error.
if (Filename.empty()) {
DiscardUntilEndOfDirective();
return;
}
// Verify that there is nothing after the filename, other than EOM. Note that
// we allow macros that expand to nothing after the filename, because this
// falls into the category of "#include pp-tokens new-line" specified in
// C99 6.10.2p4.
CheckEndOfDirective(IncludeTok.getIdentifierInfo()->getNameStart(), true);
// Check that we don't have infinite #include recursion.
if (IncludeMacroStack.size() == MaxAllowedIncludeStackDepth-1) {
Diag(FilenameTok, diag::err_pp_include_too_deep);
return;
}
// Search include directories.
const DirectoryLookup *CurDir;
const FileEntry *File = LookupFile(Filename, isAngled, LookupFrom, CurDir);
if (File == 0) {
Diag(FilenameTok, diag::err_pp_file_not_found) << Filename;
return;
}
// Ask HeaderInfo if we should enter this #include file. If not, #including
// this file will have no effect.
if (!HeaderInfo.ShouldEnterIncludeFile(File, isImport))
return;
// The #included file will be considered to be a system header if either it is
// in a system include directory, or if the #includer is a system include
// header.
SrcMgr::CharacteristicKind FileCharacter =
std::max(HeaderInfo.getFileDirFlavor(File),
SourceMgr.getFileCharacteristic(FilenameTok.getLocation()));
// Look up the file, create a File ID for it.
FileID FID = SourceMgr.createFileID(File, FilenameTok.getLocation(),
FileCharacter);
if (FID.isInvalid()) {
Diag(FilenameTok, diag::err_pp_file_not_found) << Filename;
return;
}
// Finally, if all is good, enter the new file!
std::string ErrorStr;
if (EnterSourceFile(FID, CurDir, ErrorStr))
Diag(FilenameTok, diag::err_pp_error_opening_file)
<< std::string(SourceMgr.getFileEntryForID(FID)->getName()) << ErrorStr;
}
/// HandleIncludeNextDirective - Implements #include_next.
///
void Preprocessor::HandleIncludeNextDirective(Token &IncludeNextTok) {
Diag(IncludeNextTok, diag::ext_pp_include_next_directive);
// #include_next is like #include, except that we start searching after
// the current found directory. If we can't do this, issue a
// diagnostic.
const DirectoryLookup *Lookup = CurDirLookup;
if (isInPrimaryFile()) {
Lookup = 0;
Diag(IncludeNextTok, diag::pp_include_next_in_primary);
} else if (Lookup == 0) {
Diag(IncludeNextTok, diag::pp_include_next_absolute_path);
} else {
// Start looking up in the next directory.
++Lookup;
}
return HandleIncludeDirective(IncludeNextTok, Lookup);
}
/// HandleImportDirective - Implements #import.
///
void Preprocessor::HandleImportDirective(Token &ImportTok) {
if (!Features.ObjC1) // #import is standard for ObjC.
Diag(ImportTok, diag::ext_pp_import_directive);
return HandleIncludeDirective(ImportTok, 0, true);
}
/// HandleIncludeMacrosDirective - The -imacros command line option turns into a
/// pseudo directive in the predefines buffer. This handles it by sucking all
/// tokens through the preprocessor and discarding them (only keeping the side
/// effects on the preprocessor).
void Preprocessor::HandleIncludeMacrosDirective(Token &IncludeMacrosTok) {
// This directive should only occur in the predefines buffer. If not, emit an
// error and reject it.
SourceLocation Loc = IncludeMacrosTok.getLocation();
if (strcmp(SourceMgr.getBufferName(Loc), "<built-in>") != 0) {
Diag(IncludeMacrosTok.getLocation(),
diag::pp_include_macros_out_of_predefines);
DiscardUntilEndOfDirective();
return;
}
// Treat this as a normal #include for checking purposes. If this is
// successful, it will push a new lexer onto the include stack.
HandleIncludeDirective(IncludeMacrosTok, 0, false);
Token TmpTok;
do {
Lex(TmpTok);
assert(TmpTok.isNot(tok::eof) && "Didn't find end of -imacros!");
} while (TmpTok.isNot(tok::hashhash));
}
//===----------------------------------------------------------------------===//
// Preprocessor Macro Directive Handling.
//===----------------------------------------------------------------------===//
/// ReadMacroDefinitionArgList - The ( starting an argument list of a macro
/// definition has just been read. Lex the rest of the arguments and the
/// closing ), updating MI with what we learn. Return true if an error occurs
/// parsing the arg list.
bool Preprocessor::ReadMacroDefinitionArgList(MacroInfo *MI) {
llvm::SmallVector<IdentifierInfo*, 32> Arguments;
Token Tok;
while (1) {
LexUnexpandedToken(Tok);
switch (Tok.getKind()) {
case tok::r_paren:
// Found the end of the argument list.
if (Arguments.empty()) // #define FOO()
return false;
// Otherwise we have #define FOO(A,)
Diag(Tok, diag::err_pp_expected_ident_in_arg_list);
return true;
case tok::ellipsis: // #define X(... -> C99 varargs
// Warn if use of C99 feature in non-C99 mode.
if (!Features.C99) Diag(Tok, diag::ext_variadic_macro);
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
if (Tok.isNot(tok::r_paren)) {
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
}
// Add the __VA_ARGS__ identifier as an argument.
Arguments.push_back(Ident__VA_ARGS__);
MI->setIsC99Varargs();
MI->setArgumentList(&Arguments[0], Arguments.size(), BP);
return false;
case tok::eom: // #define X(
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
default:
// Handle keywords and identifiers here to accept things like
// #define Foo(for) for.
IdentifierInfo *II = Tok.getIdentifierInfo();
if (II == 0) {
// #define X(1
Diag(Tok, diag::err_pp_invalid_tok_in_arg_list);
return true;
}
// If this is already used as an argument, it is used multiple times (e.g.
// #define X(A,A.
if (std::find(Arguments.begin(), Arguments.end(), II) !=
Arguments.end()) { // C99 6.10.3p6
Diag(Tok, diag::err_pp_duplicate_name_in_arg_list) << II;
return true;
}
// Add the argument to the macro info.
Arguments.push_back(II);
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
switch (Tok.getKind()) {
default: // #define X(A B
Diag(Tok, diag::err_pp_expected_comma_in_arg_list);
return true;
case tok::r_paren: // #define X(A)
MI->setArgumentList(&Arguments[0], Arguments.size(), BP);
return false;
case tok::comma: // #define X(A,
break;
case tok::ellipsis: // #define X(A... -> GCC extension
// Diagnose extension.
Diag(Tok, diag::ext_named_variadic_macro);
// Lex the token after the identifier.
LexUnexpandedToken(Tok);
if (Tok.isNot(tok::r_paren)) {
Diag(Tok, diag::err_pp_missing_rparen_in_macro_def);
return true;
}
MI->setIsGNUVarargs();
MI->setArgumentList(&Arguments[0], Arguments.size(), BP);
return false;
}
}
}
}
/// HandleDefineDirective - Implements #define. This consumes the entire macro
/// line then lets the caller lex the next real token.
void Preprocessor::HandleDefineDirective(Token &DefineTok) {
++NumDefined;
Token MacroNameTok;
ReadMacroName(MacroNameTok, 1);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eom))
return;
Token LastTok = MacroNameTok;
// If we are supposed to keep comments in #defines, reenable comment saving
// mode.
if (CurLexer) CurLexer->SetCommentRetentionState(KeepMacroComments);
// Create the new macro.
MacroInfo *MI = AllocateMacroInfo(MacroNameTok.getLocation());
Token Tok;
LexUnexpandedToken(Tok);
// If this is a function-like macro definition, parse the argument list,
// marking each of the identifiers as being used as macro arguments. Also,
// check other constraints on the first token of the macro body.
if (Tok.is(tok::eom)) {
// If there is no body to this macro, we have no special handling here.
} else if (Tok.hasLeadingSpace()) {
// This is a normal token with leading space. Clear the leading space
// marker on the first token to get proper expansion.
Tok.clearFlag(Token::LeadingSpace);
} else if (Tok.is(tok::l_paren)) {
// This is a function-like macro definition. Read the argument list.
MI->setIsFunctionLike();
if (ReadMacroDefinitionArgList(MI)) {
// Forget about MI.
ReleaseMacroInfo(MI);
// Throw away the rest of the line.
if (CurPPLexer->ParsingPreprocessorDirective)
DiscardUntilEndOfDirective();
return;
}
// If this is a definition of a variadic C99 function-like macro, not using
// the GNU named varargs extension, enabled __VA_ARGS__.
// "Poison" __VA_ARGS__, which can only appear in the expansion of a macro.
// This gets unpoisoned where it is allowed.
assert(Ident__VA_ARGS__->isPoisoned() && "__VA_ARGS__ should be poisoned!");
if (MI->isC99Varargs())
Ident__VA_ARGS__->setIsPoisoned(false);
// Read the first token after the arg list for down below.
LexUnexpandedToken(Tok);
} else if (Features.C99) {
// C99 requires whitespace between the macro definition and the body. Emit
// a diagnostic for something like "#define X+".
Diag(Tok, diag::ext_c99_whitespace_required_after_macro_name);
} else {
// C90 6.8 TC1 says: "In the definition of an object-like macro, if the
// first character of a replacement list is not a character required by
// subclause 5.2.1, then there shall be white-space separation between the
// identifier and the replacement list.". 5.2.1 lists this set:
// "A-Za-z0-9!"#%&'()*+,_./:;<=>?[\]^_{|}~" as well as whitespace, which
// is irrelevant here.
bool isInvalid = false;
if (Tok.is(tok::at)) // @ is not in the list above.
isInvalid = true;
else if (Tok.is(tok::unknown)) {
// If we have an unknown token, it is something strange like "`". Since
// all of valid characters would have lexed into a single character
// token of some sort, we know this is not a valid case.
isInvalid = true;
}
if (isInvalid)
Diag(Tok, diag::ext_missing_whitespace_after_macro_name);
else
Diag(Tok, diag::warn_missing_whitespace_after_macro_name);
}
if (!Tok.is(tok::eom))
LastTok = Tok;
// Read the rest of the macro body.
if (MI->isObjectLike()) {
// Object-like macros are very simple, just read their body.
while (Tok.isNot(tok::eom)) {
LastTok = Tok;
MI->AddTokenToBody(Tok);
// Get the next token of the macro.
LexUnexpandedToken(Tok);
}
} else {
// Otherwise, read the body of a function-like macro. While we are at it,
// check C99 6.10.3.2p1: ensure that # operators are followed by macro
// parameters in function-like macro expansions.
while (Tok.isNot(tok::eom)) {
LastTok = Tok;
if (Tok.isNot(tok::hash)) {
MI->AddTokenToBody(Tok);
// Get the next token of the macro.
LexUnexpandedToken(Tok);
continue;
}
// Get the next token of the macro.
LexUnexpandedToken(Tok);
// Check for a valid macro arg identifier.
if (Tok.getIdentifierInfo() == 0 ||
MI->getArgumentNum(Tok.getIdentifierInfo()) == -1) {
// If this is assembler-with-cpp mode, we accept random gibberish after
// the '#' because '#' is often a comment character. However, change
// the kind of the token to tok::unknown so that the preprocessor isn't
// confused.
if (getLangOptions().AsmPreprocessor && Tok.isNot(tok::eom)) {
LastTok.setKind(tok::unknown);
} else {
Diag(Tok, diag::err_pp_stringize_not_parameter);
ReleaseMacroInfo(MI);
// Disable __VA_ARGS__ again.
Ident__VA_ARGS__->setIsPoisoned(true);
return;
}
}
// Things look ok, add the '#' and param name tokens to the macro.
MI->AddTokenToBody(LastTok);
MI->AddTokenToBody(Tok);
LastTok = Tok;
// Get the next token of the macro.
LexUnexpandedToken(Tok);
}
}
// Disable __VA_ARGS__ again.
Ident__VA_ARGS__->setIsPoisoned(true);
// Check that there is no paste (##) operator at the begining or end of the
// replacement list.
unsigned NumTokens = MI->getNumTokens();
if (NumTokens != 0) {
if (MI->getReplacementToken(0).is(tok::hashhash)) {
Diag(MI->getReplacementToken(0), diag::err_paste_at_start);
ReleaseMacroInfo(MI);
return;
}
if (MI->getReplacementToken(NumTokens-1).is(tok::hashhash)) {
Diag(MI->getReplacementToken(NumTokens-1), diag::err_paste_at_end);
ReleaseMacroInfo(MI);
return;
}
}
// If this is the primary source file, remember that this macro hasn't been
// used yet.
if (isInPrimaryFile())
MI->setIsUsed(false);
MI->setDefinitionEndLoc(LastTok.getLocation());
// Finally, if this identifier already had a macro defined for it, verify that
// the macro bodies are identical and free the old definition.
if (MacroInfo *OtherMI = getMacroInfo(MacroNameTok.getIdentifierInfo())) {
// It is very common for system headers to have tons of macro redefinitions
// and for warnings to be disabled in system headers. If this is the case,
// then don't bother calling MacroInfo::isIdenticalTo.
if (!getDiagnostics().getSuppressSystemWarnings() ||
!SourceMgr.isInSystemHeader(DefineTok.getLocation())) {
if (!OtherMI->isUsed())
Diag(OtherMI->getDefinitionLoc(), diag::pp_macro_not_used);
// Macros must be identical. This means all tokes and whitespace
// separation must be the same. C99 6.10.3.2.
if (!MI->isIdenticalTo(*OtherMI, *this)) {
Diag(MI->getDefinitionLoc(), diag::ext_pp_macro_redef)
<< MacroNameTok.getIdentifierInfo();
Diag(OtherMI->getDefinitionLoc(), diag::note_previous_definition);
}
}
ReleaseMacroInfo(OtherMI);
}
setMacroInfo(MacroNameTok.getIdentifierInfo(), MI);
// If the callbacks want to know, tell them about the macro definition.
if (Callbacks)
Callbacks->MacroDefined(MacroNameTok.getIdentifierInfo(), MI);
}
/// HandleUndefDirective - Implements #undef.
///
void Preprocessor::HandleUndefDirective(Token &UndefTok) {
++NumUndefined;
Token MacroNameTok;
ReadMacroName(MacroNameTok, 2);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eom))
return;
// Check to see if this is the last token on the #undef line.
CheckEndOfDirective("undef");
// Okay, we finally have a valid identifier to undef.
MacroInfo *MI = getMacroInfo(MacroNameTok.getIdentifierInfo());
// If the macro is not defined, this is a noop undef, just return.
if (MI == 0) return;
if (!MI->isUsed())
Diag(MI->getDefinitionLoc(), diag::pp_macro_not_used);
// If the callbacks want to know, tell them about the macro #undef.
if (Callbacks)
Callbacks->MacroUndefined(MacroNameTok.getIdentifierInfo(), MI);
// Free macro definition.
ReleaseMacroInfo(MI);
setMacroInfo(MacroNameTok.getIdentifierInfo(), 0);
}
//===----------------------------------------------------------------------===//
// Preprocessor Conditional Directive Handling.
//===----------------------------------------------------------------------===//
/// HandleIfdefDirective - Implements the #ifdef/#ifndef directive. isIfndef is
/// true when this is a #ifndef directive. ReadAnyTokensBeforeDirective is true
/// if any tokens have been returned or pp-directives activated before this
/// #ifndef has been lexed.
///
void Preprocessor::HandleIfdefDirective(Token &Result, bool isIfndef,
bool ReadAnyTokensBeforeDirective) {
++NumIf;
Token DirectiveTok = Result;
Token MacroNameTok;
ReadMacroName(MacroNameTok);
// Error reading macro name? If so, diagnostic already issued.
if (MacroNameTok.is(tok::eom)) {
// Skip code until we get to #endif. This helps with recovery by not
// emitting an error when the #endif is reached.
SkipExcludedConditionalBlock(DirectiveTok.getLocation(),
/*Foundnonskip*/false, /*FoundElse*/false);
return;
}
// Check to see if this is the last token on the #if[n]def line.
CheckEndOfDirective(isIfndef ? "ifndef" : "ifdef");
IdentifierInfo *MII = MacroNameTok.getIdentifierInfo();
MacroInfo *MI = getMacroInfo(MII);
if (CurPPLexer->getConditionalStackDepth() == 0) {
// If the start of a top-level #ifdef and if the macro is not defined,
// inform MIOpt that this might be the start of a proper include guard.
// Otherwise it is some other form of unknown conditional which we can't
// handle.
if (!ReadAnyTokensBeforeDirective && MI == 0) {
assert(isIfndef && "#ifdef shouldn't reach here");
CurPPLexer->MIOpt.EnterTopLevelIFNDEF(MII);
} else
CurPPLexer->MIOpt.EnterTopLevelConditional();
}
// If there is a macro, process it.
if (MI) // Mark it used.
MI->setIsUsed(true);
// Should we include the stuff contained by this directive?
if (!MI == isIfndef) {
// Yes, remember that we are inside a conditional, then lex the next token.
CurPPLexer->pushConditionalLevel(DirectiveTok.getLocation(),
/*wasskip*/false, /*foundnonskip*/true,
/*foundelse*/false);
} else {
// No, skip the contents of this block and return the first token after it.
SkipExcludedConditionalBlock(DirectiveTok.getLocation(),
/*Foundnonskip*/false,
/*FoundElse*/false);
}
}
/// HandleIfDirective - Implements the #if directive.
///
void Preprocessor::HandleIfDirective(Token &IfToken,
bool ReadAnyTokensBeforeDirective) {
++NumIf;
// Parse and evaluation the conditional expression.
IdentifierInfo *IfNDefMacro = 0;
bool ConditionalTrue = EvaluateDirectiveExpression(IfNDefMacro);
// If this condition is equivalent to #ifndef X, and if this is the first
// directive seen, handle it for the multiple-include optimization.
if (CurPPLexer->getConditionalStackDepth() == 0) {
if (!ReadAnyTokensBeforeDirective && IfNDefMacro && ConditionalTrue)
CurPPLexer->MIOpt.EnterTopLevelIFNDEF(IfNDefMacro);
else
CurPPLexer->MIOpt.EnterTopLevelConditional();
}
// Should we include the stuff contained by this directive?
if (ConditionalTrue) {
// Yes, remember that we are inside a conditional, then lex the next token.
CurPPLexer->pushConditionalLevel(IfToken.getLocation(), /*wasskip*/false,
/*foundnonskip*/true, /*foundelse*/false);
} else {
// No, skip the contents of this block and return the first token after it.
SkipExcludedConditionalBlock(IfToken.getLocation(), /*Foundnonskip*/false,
/*FoundElse*/false);
}
}
/// HandleEndifDirective - Implements the #endif directive.
///
void Preprocessor::HandleEndifDirective(Token &EndifToken) {
++NumEndif;
// Check that this is the whole directive.
CheckEndOfDirective("endif");
PPConditionalInfo CondInfo;
if (CurPPLexer->popConditionalLevel(CondInfo)) {
// No conditionals on the stack: this is an #endif without an #if.
Diag(EndifToken, diag::err_pp_endif_without_if);
return;
}
// If this the end of a top-level #endif, inform MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.ExitTopLevelConditional();
assert(!CondInfo.WasSkipping && !CurPPLexer->LexingRawMode &&
"This code should only be reachable in the non-skipping case!");
}
void Preprocessor::HandleElseDirective(Token &Result) {
++NumElse;
// #else directive in a non-skipping conditional... start skipping.
CheckEndOfDirective("else");
PPConditionalInfo CI;
if (CurPPLexer->popConditionalLevel(CI)) {
Diag(Result, diag::pp_err_else_without_if);
return;
}
// If this is a top-level #else, inform the MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.EnterTopLevelConditional();
// If this is a #else with a #else before it, report the error.
if (CI.FoundElse) Diag(Result, diag::pp_err_else_after_else);
// Finally, skip the rest of the contents of this block and return the first
// token after it.
return SkipExcludedConditionalBlock(CI.IfLoc, /*Foundnonskip*/true,
/*FoundElse*/true);
}
void Preprocessor::HandleElifDirective(Token &ElifToken) {
++NumElse;
// #elif directive in a non-skipping conditional... start skipping.
// We don't care what the condition is, because we will always skip it (since
// the block immediately before it was included).
DiscardUntilEndOfDirective();
PPConditionalInfo CI;
if (CurPPLexer->popConditionalLevel(CI)) {
Diag(ElifToken, diag::pp_err_elif_without_if);
return;
}
// If this is a top-level #elif, inform the MIOpt.
if (CurPPLexer->getConditionalStackDepth() == 0)
CurPPLexer->MIOpt.EnterTopLevelConditional();
// If this is a #elif with a #else before it, report the error.
if (CI.FoundElse) Diag(ElifToken, diag::pp_err_elif_after_else);
// Finally, skip the rest of the contents of this block and return the first
// token after it.
return SkipExcludedConditionalBlock(CI.IfLoc, /*Foundnonskip*/true,
/*FoundElse*/CI.FoundElse);
}
|