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
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
|
//===--- Lexer.cpp - C Language Family Lexer ------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the Lexer and Token interfaces.
//
//===----------------------------------------------------------------------===//
//
// TODO: GCC Diagnostics emitted by the lexer:
// PEDWARN: (form feed|vertical tab) in preprocessing directive
//
// Universal characters, unicode, char mapping:
// WARNING: `%.*s' is not in NFKC
// WARNING: `%.*s' is not in NFC
//
// Other:
// TODO: Options to support:
// -fexec-charset,-fwide-exec-charset
//
//===----------------------------------------------------------------------===//
#include "clang/Lex/Lexer.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Basic/SourceManager.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/MemoryBuffer.h"
#include <cctype>
using namespace clang;
static void InitCharacterInfo();
//===----------------------------------------------------------------------===//
// Token Class Implementation
//===----------------------------------------------------------------------===//
/// isObjCAtKeyword - Return true if we have an ObjC keyword identifier.
bool Token::isObjCAtKeyword(tok::ObjCKeywordKind objcKey) const {
if (IdentifierInfo *II = getIdentifierInfo())
return II->getObjCKeywordID() == objcKey;
return false;
}
/// getObjCKeywordID - Return the ObjC keyword kind.
tok::ObjCKeywordKind Token::getObjCKeywordID() const {
IdentifierInfo *specId = getIdentifierInfo();
return specId ? specId->getObjCKeywordID() : tok::objc_not_keyword;
}
//===----------------------------------------------------------------------===//
// Lexer Class Implementation
//===----------------------------------------------------------------------===//
void Lexer::InitLexer(const char *BufStart, const char *BufPtr,
const char *BufEnd) {
InitCharacterInfo();
BufferStart = BufStart;
BufferPtr = BufPtr;
BufferEnd = BufEnd;
assert(BufEnd[0] == 0 &&
"We assume that the input buffer has a null character at the end"
" to simplify lexing!");
Is_PragmaLexer = false;
IsInConflictMarker = false;
// Start of the file is a start of line.
IsAtStartOfLine = true;
// We are not after parsing a #.
ParsingPreprocessorDirective = false;
// We are not after parsing #include.
ParsingFilename = false;
// We are not in raw mode. Raw mode disables diagnostics and interpretation
// of tokens (e.g. identifiers, thus disabling macro expansion). It is used
// to quickly lex the tokens of the buffer, e.g. when handling a "#if 0" block
// or otherwise skipping over tokens.
LexingRawMode = false;
// Default to not keeping comments.
ExtendedTokenMode = 0;
}
/// Lexer constructor - Create a new lexer object for the specified buffer
/// with the specified preprocessor managing the lexing process. This lexer
/// assumes that the associated file buffer and Preprocessor objects will
/// outlive it, so it doesn't take ownership of either of them.
Lexer::Lexer(FileID FID, const llvm::MemoryBuffer *InputFile, Preprocessor &PP)
: PreprocessorLexer(&PP, FID),
FileLoc(PP.getSourceManager().getLocForStartOfFile(FID)),
Features(PP.getLangOptions()) {
InitLexer(InputFile->getBufferStart(), InputFile->getBufferStart(),
InputFile->getBufferEnd());
// Default to keeping comments if the preprocessor wants them.
SetCommentRetentionState(PP.getCommentRetentionState());
}
/// Lexer constructor - Create a new raw lexer object. This object is only
/// suitable for calls to 'LexRawToken'. This lexer assumes that the text
/// range will outlive it, so it doesn't take ownership of it.
Lexer::Lexer(SourceLocation fileloc, const LangOptions &features,
const char *BufStart, const char *BufPtr, const char *BufEnd)
: FileLoc(fileloc), Features(features) {
InitLexer(BufStart, BufPtr, BufEnd);
// We *are* in raw mode.
LexingRawMode = true;
}
/// Lexer constructor - Create a new raw lexer object. This object is only
/// suitable for calls to 'LexRawToken'. This lexer assumes that the text
/// range will outlive it, so it doesn't take ownership of it.
Lexer::Lexer(FileID FID, const llvm::MemoryBuffer *FromFile,
const SourceManager &SM, const LangOptions &features)
: FileLoc(SM.getLocForStartOfFile(FID)), Features(features) {
InitLexer(FromFile->getBufferStart(), FromFile->getBufferStart(),
FromFile->getBufferEnd());
// We *are* in raw mode.
LexingRawMode = true;
}
/// Create_PragmaLexer: Lexer constructor - Create a new lexer object for
/// _Pragma expansion. This has a variety of magic semantics that this method
/// sets up. It returns a new'd Lexer that must be delete'd when done.
///
/// On entrance to this routine, TokStartLoc is a macro location which has a
/// spelling loc that indicates the bytes to be lexed for the token and an
/// instantiation location that indicates where all lexed tokens should be
/// "expanded from".
///
/// FIXME: It would really be nice to make _Pragma just be a wrapper around a
/// normal lexer that remaps tokens as they fly by. This would require making
/// Preprocessor::Lex virtual. Given that, we could just dump in a magic lexer
/// interface that could handle this stuff. This would pull GetMappedTokenLoc
/// out of the critical path of the lexer!
///
Lexer *Lexer::Create_PragmaLexer(SourceLocation SpellingLoc,
SourceLocation InstantiationLocStart,
SourceLocation InstantiationLocEnd,
unsigned TokLen, Preprocessor &PP) {
SourceManager &SM = PP.getSourceManager();
// Create the lexer as if we were going to lex the file normally.
FileID SpellingFID = SM.getFileID(SpellingLoc);
const llvm::MemoryBuffer *InputFile = SM.getBuffer(SpellingFID);
Lexer *L = new Lexer(SpellingFID, InputFile, PP);
// Now that the lexer is created, change the start/end locations so that we
// just lex the subsection of the file that we want. This is lexing from a
// scratch buffer.
const char *StrData = SM.getCharacterData(SpellingLoc);
L->BufferPtr = StrData;
L->BufferEnd = StrData+TokLen;
assert(L->BufferEnd[0] == 0 && "Buffer is not nul terminated!");
// Set the SourceLocation with the remapping information. This ensures that
// GetMappedTokenLoc will remap the tokens as they are lexed.
L->FileLoc = SM.createInstantiationLoc(SM.getLocForStartOfFile(SpellingFID),
InstantiationLocStart,
InstantiationLocEnd, TokLen);
// Ensure that the lexer thinks it is inside a directive, so that end \n will
// return an EOM token.
L->ParsingPreprocessorDirective = true;
// This lexer really is for _Pragma.
L->Is_PragmaLexer = true;
return L;
}
/// Stringify - Convert the specified string into a C string, with surrounding
/// ""'s, and with escaped \ and " characters.
std::string Lexer::Stringify(const std::string &Str, bool Charify) {
std::string Result = Str;
char Quote = Charify ? '\'' : '"';
for (unsigned i = 0, e = Result.size(); i != e; ++i) {
if (Result[i] == '\\' || Result[i] == Quote) {
Result.insert(Result.begin()+i, '\\');
++i; ++e;
}
}
return Result;
}
/// Stringify - Convert the specified string into a C string by escaping '\'
/// and " characters. This does not add surrounding ""'s to the string.
void Lexer::Stringify(llvm::SmallVectorImpl<char> &Str) {
for (unsigned i = 0, e = Str.size(); i != e; ++i) {
if (Str[i] == '\\' || Str[i] == '"') {
Str.insert(Str.begin()+i, '\\');
++i; ++e;
}
}
}
static bool isWhitespace(unsigned char c);
/// MeasureTokenLength - Relex the token at the specified location and return
/// its length in bytes in the input file. If the token needs cleaning (e.g.
/// includes a trigraph or an escaped newline) then this count includes bytes
/// that are part of that.
unsigned Lexer::MeasureTokenLength(SourceLocation Loc,
const SourceManager &SM,
const LangOptions &LangOpts) {
// TODO: this could be special cased for common tokens like identifiers, ')',
// etc to make this faster, if it mattered. Just look at StrData[0] to handle
// all obviously single-char tokens. This could use
// Lexer::isObviouslySimpleCharacter for example to handle identifiers or
// something.
// If this comes from a macro expansion, we really do want the macro name, not
// the token this macro expanded to.
Loc = SM.getInstantiationLoc(Loc);
std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Loc);
bool Invalid = false;
llvm::StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
if (Invalid)
return 0;
const char *StrData = Buffer.data()+LocInfo.second;
if (isWhitespace(StrData[0]))
return 0;
// Create a lexer starting at the beginning of this token.
Lexer TheLexer(Loc, LangOpts, Buffer.begin(), StrData, Buffer.end());
TheLexer.SetCommentRetentionState(true);
Token TheTok;
TheLexer.LexFromRawLexer(TheTok);
return TheTok.getLength();
}
//===----------------------------------------------------------------------===//
// Character information.
//===----------------------------------------------------------------------===//
enum {
CHAR_HORZ_WS = 0x01, // ' ', '\t', '\f', '\v'. Note, no '\0'
CHAR_VERT_WS = 0x02, // '\r', '\n'
CHAR_LETTER = 0x04, // a-z,A-Z
CHAR_NUMBER = 0x08, // 0-9
CHAR_UNDER = 0x10, // _
CHAR_PERIOD = 0x20 // .
};
// Statically initialize CharInfo table based on ASCII character set
// Reference: FreeBSD 7.2 /usr/share/misc/ascii
static const unsigned char CharInfo[256] =
{
// 0 NUL 1 SOH 2 STX 3 ETX
// 4 EOT 5 ENQ 6 ACK 7 BEL
0 , 0 , 0 , 0 ,
0 , 0 , 0 , 0 ,
// 8 BS 9 HT 10 NL 11 VT
//12 NP 13 CR 14 SO 15 SI
0 , CHAR_HORZ_WS, CHAR_VERT_WS, CHAR_HORZ_WS,
CHAR_HORZ_WS, CHAR_VERT_WS, 0 , 0 ,
//16 DLE 17 DC1 18 DC2 19 DC3
//20 DC4 21 NAK 22 SYN 23 ETB
0 , 0 , 0 , 0 ,
0 , 0 , 0 , 0 ,
//24 CAN 25 EM 26 SUB 27 ESC
//28 FS 29 GS 30 RS 31 US
0 , 0 , 0 , 0 ,
0 , 0 , 0 , 0 ,
//32 SP 33 ! 34 " 35 #
//36 $ 37 % 38 & 39 '
CHAR_HORZ_WS, 0 , 0 , 0 ,
0 , 0 , 0 , 0 ,
//40 ( 41 ) 42 * 43 +
//44 , 45 - 46 . 47 /
0 , 0 , 0 , 0 ,
0 , 0 , CHAR_PERIOD , 0 ,
//48 0 49 1 50 2 51 3
//52 4 53 5 54 6 55 7
CHAR_NUMBER , CHAR_NUMBER , CHAR_NUMBER , CHAR_NUMBER ,
CHAR_NUMBER , CHAR_NUMBER , CHAR_NUMBER , CHAR_NUMBER ,
//56 8 57 9 58 : 59 ;
//60 < 61 = 62 > 63 ?
CHAR_NUMBER , CHAR_NUMBER , 0 , 0 ,
0 , 0 , 0 , 0 ,
//64 @ 65 A 66 B 67 C
//68 D 69 E 70 F 71 G
0 , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//72 H 73 I 74 J 75 K
//76 L 77 M 78 N 79 O
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//80 P 81 Q 82 R 83 S
//84 T 85 U 86 V 87 W
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//88 X 89 Y 90 Z 91 [
//92 \ 93 ] 94 ^ 95 _
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , 0 ,
0 , 0 , 0 , CHAR_UNDER ,
//96 ` 97 a 98 b 99 c
//100 d 101 e 102 f 103 g
0 , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//104 h 105 i 106 j 107 k
//108 l 109 m 110 n 111 o
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//112 p 113 q 114 r 115 s
//116 t 117 u 118 v 119 w
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , CHAR_LETTER ,
//120 x 121 y 122 z 123 {
//124 | 125 } 126 ~ 127 DEL
CHAR_LETTER , CHAR_LETTER , CHAR_LETTER , 0 ,
0 , 0 , 0 , 0
};
static void InitCharacterInfo() {
static bool isInited = false;
if (isInited) return;
// check the statically-initialized CharInfo table
assert(CHAR_HORZ_WS == CharInfo[(int)' ']);
assert(CHAR_HORZ_WS == CharInfo[(int)'\t']);
assert(CHAR_HORZ_WS == CharInfo[(int)'\f']);
assert(CHAR_HORZ_WS == CharInfo[(int)'\v']);
assert(CHAR_VERT_WS == CharInfo[(int)'\n']);
assert(CHAR_VERT_WS == CharInfo[(int)'\r']);
assert(CHAR_UNDER == CharInfo[(int)'_']);
assert(CHAR_PERIOD == CharInfo[(int)'.']);
for (unsigned i = 'a'; i <= 'z'; ++i) {
assert(CHAR_LETTER == CharInfo[i]);
assert(CHAR_LETTER == CharInfo[i+'A'-'a']);
}
for (unsigned i = '0'; i <= '9'; ++i)
assert(CHAR_NUMBER == CharInfo[i]);
isInited = true;
}
/// isIdentifierBody - Return true if this is the body character of an
/// identifier, which is [a-zA-Z0-9_].
static inline bool isIdentifierBody(unsigned char c) {
return (CharInfo[c] & (CHAR_LETTER|CHAR_NUMBER|CHAR_UNDER)) ? true : false;
}
/// isHorizontalWhitespace - Return true if this character is horizontal
/// whitespace: ' ', '\t', '\f', '\v'. Note that this returns false for '\0'.
static inline bool isHorizontalWhitespace(unsigned char c) {
return (CharInfo[c] & CHAR_HORZ_WS) ? true : false;
}
/// isWhitespace - Return true if this character is horizontal or vertical
/// whitespace: ' ', '\t', '\f', '\v', '\n', '\r'. Note that this returns false
/// for '\0'.
static inline bool isWhitespace(unsigned char c) {
return (CharInfo[c] & (CHAR_HORZ_WS|CHAR_VERT_WS)) ? true : false;
}
/// isNumberBody - Return true if this is the body character of an
/// preprocessing number, which is [a-zA-Z0-9_.].
static inline bool isNumberBody(unsigned char c) {
return (CharInfo[c] & (CHAR_LETTER|CHAR_NUMBER|CHAR_UNDER|CHAR_PERIOD)) ?
true : false;
}
//===----------------------------------------------------------------------===//
// Diagnostics forwarding code.
//===----------------------------------------------------------------------===//
/// GetMappedTokenLoc - If lexing out of a 'mapped buffer', where we pretend the
/// lexer buffer was all instantiated at a single point, perform the mapping.
/// This is currently only used for _Pragma implementation, so it is the slow
/// path of the hot getSourceLocation method. Do not allow it to be inlined.
static DISABLE_INLINE SourceLocation GetMappedTokenLoc(Preprocessor &PP,
SourceLocation FileLoc,
unsigned CharNo,
unsigned TokLen);
static SourceLocation GetMappedTokenLoc(Preprocessor &PP,
SourceLocation FileLoc,
unsigned CharNo, unsigned TokLen) {
assert(FileLoc.isMacroID() && "Must be an instantiation");
// Otherwise, we're lexing "mapped tokens". This is used for things like
// _Pragma handling. Combine the instantiation location of FileLoc with the
// spelling location.
SourceManager &SM = PP.getSourceManager();
// Create a new SLoc which is expanded from Instantiation(FileLoc) but whose
// characters come from spelling(FileLoc)+Offset.
SourceLocation SpellingLoc = SM.getSpellingLoc(FileLoc);
SpellingLoc = SpellingLoc.getFileLocWithOffset(CharNo);
// Figure out the expansion loc range, which is the range covered by the
// original _Pragma(...) sequence.
std::pair<SourceLocation,SourceLocation> II =
SM.getImmediateInstantiationRange(FileLoc);
return SM.createInstantiationLoc(SpellingLoc, II.first, II.second, TokLen);
}
/// getSourceLocation - Return a source location identifier for the specified
/// offset in the current file.
SourceLocation Lexer::getSourceLocation(const char *Loc,
unsigned TokLen) const {
assert(Loc >= BufferStart && Loc <= BufferEnd &&
"Location out of range for this buffer!");
// In the normal case, we're just lexing from a simple file buffer, return
// the file id from FileLoc with the offset specified.
unsigned CharNo = Loc-BufferStart;
if (FileLoc.isFileID())
return FileLoc.getFileLocWithOffset(CharNo);
// Otherwise, this is the _Pragma lexer case, which pretends that all of the
// tokens are lexed from where the _Pragma was defined.
assert(PP && "This doesn't work on raw lexers");
return GetMappedTokenLoc(*PP, FileLoc, CharNo, TokLen);
}
/// Diag - Forwarding function for diagnostics. This translate a source
/// position in the current buffer into a SourceLocation object for rendering.
DiagnosticBuilder Lexer::Diag(const char *Loc, unsigned DiagID) const {
return PP->Diag(getSourceLocation(Loc), DiagID);
}
//===----------------------------------------------------------------------===//
// Trigraph and Escaped Newline Handling Code.
//===----------------------------------------------------------------------===//
/// GetTrigraphCharForLetter - Given a character that occurs after a ?? pair,
/// return the decoded trigraph letter it corresponds to, or '\0' if nothing.
static char GetTrigraphCharForLetter(char Letter) {
switch (Letter) {
default: return 0;
case '=': return '#';
case ')': return ']';
case '(': return '[';
case '!': return '|';
case '\'': return '^';
case '>': return '}';
case '/': return '\\';
case '<': return '{';
case '-': return '~';
}
}
/// DecodeTrigraphChar - If the specified character is a legal trigraph when
/// prefixed with ??, emit a trigraph warning. If trigraphs are enabled,
/// return the result character. Finally, emit a warning about trigraph use
/// whether trigraphs are enabled or not.
static char DecodeTrigraphChar(const char *CP, Lexer *L) {
char Res = GetTrigraphCharForLetter(*CP);
if (!Res || !L) return Res;
if (!L->getFeatures().Trigraphs) {
if (!L->isLexingRawMode())
L->Diag(CP-2, diag::trigraph_ignored);
return 0;
}
if (!L->isLexingRawMode())
L->Diag(CP-2, diag::trigraph_converted) << std::string()+Res;
return Res;
}
/// getEscapedNewLineSize - Return the size of the specified escaped newline,
/// or 0 if it is not an escaped newline. P[-1] is known to be a "\" or a
/// trigraph equivalent on entry to this function.
unsigned Lexer::getEscapedNewLineSize(const char *Ptr) {
unsigned Size = 0;
while (isWhitespace(Ptr[Size])) {
++Size;
if (Ptr[Size-1] != '\n' && Ptr[Size-1] != '\r')
continue;
// If this is a \r\n or \n\r, skip the other half.
if ((Ptr[Size] == '\r' || Ptr[Size] == '\n') &&
Ptr[Size-1] != Ptr[Size])
++Size;
return Size;
}
// Not an escaped newline, must be a \t or something else.
return 0;
}
/// SkipEscapedNewLines - If P points to an escaped newline (or a series of
/// them), skip over them and return the first non-escaped-newline found,
/// otherwise return P.
const char *Lexer::SkipEscapedNewLines(const char *P) {
while (1) {
const char *AfterEscape;
if (*P == '\\') {
AfterEscape = P+1;
} else if (*P == '?') {
// If not a trigraph for escape, bail out.
if (P[1] != '?' || P[2] != '/')
return P;
AfterEscape = P+3;
} else {
return P;
}
unsigned NewLineSize = Lexer::getEscapedNewLineSize(AfterEscape);
if (NewLineSize == 0) return P;
P = AfterEscape+NewLineSize;
}
}
/// getCharAndSizeSlow - Peek a single 'character' from the specified buffer,
/// get its size, and return it. This is tricky in several cases:
/// 1. If currently at the start of a trigraph, we warn about the trigraph,
/// then either return the trigraph (skipping 3 chars) or the '?',
/// depending on whether trigraphs are enabled or not.
/// 2. If this is an escaped newline (potentially with whitespace between
/// the backslash and newline), implicitly skip the newline and return
/// the char after it.
/// 3. If this is a UCN, return it. FIXME: C++ UCN's?
///
/// This handles the slow/uncommon case of the getCharAndSize method. Here we
/// know that we can accumulate into Size, and that we have already incremented
/// Ptr by Size bytes.
///
/// NOTE: When this method is updated, getCharAndSizeSlowNoWarn (below) should
/// be updated to match.
///
char Lexer::getCharAndSizeSlow(const char *Ptr, unsigned &Size,
Token *Tok) {
// If we have a slash, look for an escaped newline.
if (Ptr[0] == '\\') {
++Size;
++Ptr;
Slash:
// Common case, backslash-char where the char is not whitespace.
if (!isWhitespace(Ptr[0])) return '\\';
// See if we have optional whitespace characters between the slash and
// newline.
if (unsigned EscapedNewLineSize = getEscapedNewLineSize(Ptr)) {
// Remember that this token needs to be cleaned.
if (Tok) Tok->setFlag(Token::NeedsCleaning);
// Warn if there was whitespace between the backslash and newline.
if (Ptr[0] != '\n' && Ptr[0] != '\r' && Tok && !isLexingRawMode())
Diag(Ptr, diag::backslash_newline_space);
// Found backslash<whitespace><newline>. Parse the char after it.
Size += EscapedNewLineSize;
Ptr += EscapedNewLineSize;
// Use slow version to accumulate a correct size field.
return getCharAndSizeSlow(Ptr, Size, Tok);
}
// Otherwise, this is not an escaped newline, just return the slash.
return '\\';
}
// If this is a trigraph, process it.
if (Ptr[0] == '?' && Ptr[1] == '?') {
// If this is actually a legal trigraph (not something like "??x"), emit
// a trigraph warning. If so, and if trigraphs are enabled, return it.
if (char C = DecodeTrigraphChar(Ptr+2, Tok ? this : 0)) {
// Remember that this token needs to be cleaned.
if (Tok) Tok->setFlag(Token::NeedsCleaning);
Ptr += 3;
Size += 3;
if (C == '\\') goto Slash;
return C;
}
}
// If this is neither, return a single character.
++Size;
return *Ptr;
}
/// getCharAndSizeSlowNoWarn - Handle the slow/uncommon case of the
/// getCharAndSizeNoWarn method. Here we know that we can accumulate into Size,
/// and that we have already incremented Ptr by Size bytes.
///
/// NOTE: When this method is updated, getCharAndSizeSlow (above) should
/// be updated to match.
char Lexer::getCharAndSizeSlowNoWarn(const char *Ptr, unsigned &Size,
const LangOptions &Features) {
// If we have a slash, look for an escaped newline.
if (Ptr[0] == '\\') {
++Size;
++Ptr;
Slash:
// Common case, backslash-char where the char is not whitespace.
if (!isWhitespace(Ptr[0])) return '\\';
// See if we have optional whitespace characters followed by a newline.
if (unsigned EscapedNewLineSize = getEscapedNewLineSize(Ptr)) {
// Found backslash<whitespace><newline>. Parse the char after it.
Size += EscapedNewLineSize;
Ptr += EscapedNewLineSize;
// Use slow version to accumulate a correct size field.
return getCharAndSizeSlowNoWarn(Ptr, Size, Features);
}
// Otherwise, this is not an escaped newline, just return the slash.
return '\\';
}
// If this is a trigraph, process it.
if (Features.Trigraphs && Ptr[0] == '?' && Ptr[1] == '?') {
// If this is actually a legal trigraph (not something like "??x"), return
// it.
if (char C = GetTrigraphCharForLetter(Ptr[2])) {
Ptr += 3;
Size += 3;
if (C == '\\') goto Slash;
return C;
}
}
// If this is neither, return a single character.
++Size;
return *Ptr;
}
//===----------------------------------------------------------------------===//
// Helper methods for lexing.
//===----------------------------------------------------------------------===//
void Lexer::LexIdentifier(Token &Result, const char *CurPtr) {
// Match [_A-Za-z0-9]*, we have already matched [_A-Za-z$]
unsigned Size;
unsigned char C = *CurPtr++;
while (isIdentifierBody(C))
C = *CurPtr++;
--CurPtr; // Back up over the skipped character.
// Fast path, no $,\,? in identifier found. '\' might be an escaped newline
// or UCN, and ? might be a trigraph for '\', an escaped newline or UCN.
// FIXME: UCNs.
//
// TODO: Could merge these checks into a CharInfo flag to make the comparison
// cheaper
if (C != '\\' && C != '?' && (C != '$' || !Features.DollarIdents)) {
FinishIdentifier:
const char *IdStart = BufferPtr;
FormTokenWithChars(Result, CurPtr, tok::identifier);
// If we are in raw mode, return this identifier raw. There is no need to
// look up identifier information or attempt to macro expand it.
if (LexingRawMode) return;
// Fill in Result.IdentifierInfo, looking up the identifier in the
// identifier table.
IdentifierInfo *II = PP->LookUpIdentifierInfo(Result, IdStart);
// Change the kind of this identifier to the appropriate token kind, e.g.
// turning "for" into a keyword.
Result.setKind(II->getTokenID());
// Finally, now that we know we have an identifier, pass this off to the
// preprocessor, which may macro expand it or something.
if (II->isHandleIdentifierCase())
PP->HandleIdentifier(Result);
return;
}
// Otherwise, $,\,? in identifier found. Enter slower path.
C = getCharAndSize(CurPtr, Size);
while (1) {
if (C == '$') {
// If we hit a $ and they are not supported in identifiers, we are done.
if (!Features.DollarIdents) goto FinishIdentifier;
// Otherwise, emit a diagnostic and continue.
if (!isLexingRawMode())
Diag(CurPtr, diag::ext_dollar_in_identifier);
CurPtr = ConsumeChar(CurPtr, Size, Result);
C = getCharAndSize(CurPtr, Size);
continue;
} else if (!isIdentifierBody(C)) { // FIXME: UCNs.
// Found end of identifier.
goto FinishIdentifier;
}
// Otherwise, this character is good, consume it.
CurPtr = ConsumeChar(CurPtr, Size, Result);
C = getCharAndSize(CurPtr, Size);
while (isIdentifierBody(C)) { // FIXME: UCNs.
CurPtr = ConsumeChar(CurPtr, Size, Result);
C = getCharAndSize(CurPtr, Size);
}
}
}
/// LexNumericConstant - Lex the remainder of a integer or floating point
/// constant. From[-1] is the first character lexed. Return the end of the
/// constant.
void Lexer::LexNumericConstant(Token &Result, const char *CurPtr) {
unsigned Size;
char C = getCharAndSize(CurPtr, Size);
char PrevCh = 0;
while (isNumberBody(C)) { // FIXME: UCNs?
CurPtr = ConsumeChar(CurPtr, Size, Result);
PrevCh = C;
C = getCharAndSize(CurPtr, Size);
}
// If we fell out, check for a sign, due to 1e+12. If we have one, continue.
if ((C == '-' || C == '+') && (PrevCh == 'E' || PrevCh == 'e'))
return LexNumericConstant(Result, ConsumeChar(CurPtr, Size, Result));
// If we have a hex FP constant, continue.
if ((C == '-' || C == '+') && (PrevCh == 'P' || PrevCh == 'p') &&
(!PP || !PP->getLangOptions().CPlusPlus0x))
return LexNumericConstant(Result, ConsumeChar(CurPtr, Size, Result));
// Update the location of token as well as BufferPtr.
const char *TokStart = BufferPtr;
FormTokenWithChars(Result, CurPtr, tok::numeric_constant);
Result.setLiteralData(TokStart);
}
/// LexStringLiteral - Lex the remainder of a string literal, after having lexed
/// either " or L".
void Lexer::LexStringLiteral(Token &Result, const char *CurPtr, bool Wide) {
const char *NulCharacter = 0; // Does this string contain the \0 character?
char C = getAndAdvanceChar(CurPtr, Result);
while (C != '"') {
// Skip escaped characters.
if (C == '\\') {
// Skip the escaped character.
C = getAndAdvanceChar(CurPtr, Result);
} else if (C == '\n' || C == '\r' || // Newline.
(C == 0 && CurPtr-1 == BufferEnd)) { // End of file.
if (!isLexingRawMode() && !Features.AsmPreprocessor)
Diag(BufferPtr, diag::err_unterminated_string);
FormTokenWithChars(Result, CurPtr-1, tok::unknown);
return;
} else if (C == 0) {
NulCharacter = CurPtr-1;
}
C = getAndAdvanceChar(CurPtr, Result);
}
// If a nul character existed in the string, warn about it.
if (NulCharacter && !isLexingRawMode())
Diag(NulCharacter, diag::null_in_string);
// Update the location of the token as well as the BufferPtr instance var.
const char *TokStart = BufferPtr;
FormTokenWithChars(Result, CurPtr,
Wide ? tok::wide_string_literal : tok::string_literal);
Result.setLiteralData(TokStart);
}
/// LexAngledStringLiteral - Lex the remainder of an angled string literal,
/// after having lexed the '<' character. This is used for #include filenames.
void Lexer::LexAngledStringLiteral(Token &Result, const char *CurPtr) {
const char *NulCharacter = 0; // Does this string contain the \0 character?
const char *AfterLessPos = CurPtr;
char C = getAndAdvanceChar(CurPtr, Result);
while (C != '>') {
// Skip escaped characters.
if (C == '\\') {
// Skip the escaped character.
C = getAndAdvanceChar(CurPtr, Result);
} else if (C == '\n' || C == '\r' || // Newline.
(C == 0 && CurPtr-1 == BufferEnd)) { // End of file.
// If the filename is unterminated, then it must just be a lone <
// character. Return this as such.
FormTokenWithChars(Result, AfterLessPos, tok::less);
return;
} else if (C == 0) {
NulCharacter = CurPtr-1;
}
C = getAndAdvanceChar(CurPtr, Result);
}
// If a nul character existed in the string, warn about it.
if (NulCharacter && !isLexingRawMode())
Diag(NulCharacter, diag::null_in_string);
// Update the location of token as well as BufferPtr.
const char *TokStart = BufferPtr;
FormTokenWithChars(Result, CurPtr, tok::angle_string_literal);
Result.setLiteralData(TokStart);
}
/// LexCharConstant - Lex the remainder of a character constant, after having
/// lexed either ' or L'.
void Lexer::LexCharConstant(Token &Result, const char *CurPtr) {
const char *NulCharacter = 0; // Does this character contain the \0 character?
// Handle the common case of 'x' and '\y' efficiently.
char C = getAndAdvanceChar(CurPtr, Result);
if (C == '\'') {
if (!isLexingRawMode() && !Features.AsmPreprocessor)
Diag(BufferPtr, diag::err_empty_character);
FormTokenWithChars(Result, CurPtr, tok::unknown);
return;
} else if (C == '\\') {
// Skip the escaped character.
// FIXME: UCN's.
C = getAndAdvanceChar(CurPtr, Result);
}
if (C && C != '\n' && C != '\r' && CurPtr[0] == '\'') {
++CurPtr;
} else {
// Fall back on generic code for embedded nulls, newlines, wide chars.
do {
// Skip escaped characters.
if (C == '\\') {
// Skip the escaped character.
C = getAndAdvanceChar(CurPtr, Result);
} else if (C == '\n' || C == '\r' || // Newline.
(C == 0 && CurPtr-1 == BufferEnd)) { // End of file.
if (!isLexingRawMode() && !Features.AsmPreprocessor)
Diag(BufferPtr, diag::err_unterminated_char);
FormTokenWithChars(Result, CurPtr-1, tok::unknown);
return;
} else if (C == 0) {
NulCharacter = CurPtr-1;
}
C = getAndAdvanceChar(CurPtr, Result);
} while (C != '\'');
}
if (NulCharacter && !isLexingRawMode())
Diag(NulCharacter, diag::null_in_char);
// Update the location of token as well as BufferPtr.
const char *TokStart = BufferPtr;
FormTokenWithChars(Result, CurPtr, tok::char_constant);
Result.setLiteralData(TokStart);
}
/// SkipWhitespace - Efficiently skip over a series of whitespace characters.
/// Update BufferPtr to point to the next non-whitespace character and return.
///
/// This method forms a token and returns true if KeepWhitespaceMode is enabled.
///
bool Lexer::SkipWhitespace(Token &Result, const char *CurPtr) {
// Whitespace - Skip it, then return the token after the whitespace.
unsigned char Char = *CurPtr; // Skip consequtive spaces efficiently.
while (1) {
// Skip horizontal whitespace very aggressively.
while (isHorizontalWhitespace(Char))
Char = *++CurPtr;
// Otherwise if we have something other than whitespace, we're done.
if (Char != '\n' && Char != '\r')
break;
if (ParsingPreprocessorDirective) {
// End of preprocessor directive line, let LexTokenInternal handle this.
BufferPtr = CurPtr;
return false;
}
// ok, but handle newline.
// The returned token is at the start of the line.
Result.setFlag(Token::StartOfLine);
// No leading whitespace seen so far.
Result.clearFlag(Token::LeadingSpace);
Char = *++CurPtr;
}
// If this isn't immediately after a newline, there is leading space.
char PrevChar = CurPtr[-1];
if (PrevChar != '\n' && PrevChar != '\r')
Result.setFlag(Token::LeadingSpace);
// If the client wants us to return whitespace, return it now.
if (isKeepWhitespaceMode()) {
FormTokenWithChars(Result, CurPtr, tok::unknown);
return true;
}
BufferPtr = CurPtr;
return false;
}
// SkipBCPLComment - We have just read the // characters from input. Skip until
// we find the newline character thats terminate the comment. Then update
/// BufferPtr and return.
///
/// If we're in KeepCommentMode or any CommentHandler has inserted
/// some tokens, this will store the first token and return true.
bool Lexer::SkipBCPLComment(Token &Result, const char *CurPtr) {
// If BCPL comments aren't explicitly enabled for this language, emit an
// extension warning.
if (!Features.BCPLComment && !isLexingRawMode()) {
Diag(BufferPtr, diag::ext_bcpl_comment);
// Mark them enabled so we only emit one warning for this translation
// unit.
Features.BCPLComment = true;
}
// Scan over the body of the comment. The common case, when scanning, is that
// the comment contains normal ascii characters with nothing interesting in
// them. As such, optimize for this case with the inner loop.
char C;
do {
C = *CurPtr;
// FIXME: Speedup BCPL comment lexing. Just scan for a \n or \r character.
// If we find a \n character, scan backwards, checking to see if it's an
// escaped newline, like we do for block comments.
// Skip over characters in the fast loop.
while (C != 0 && // Potentially EOF.
C != '\\' && // Potentially escaped newline.
C != '?' && // Potentially trigraph.
C != '\n' && C != '\r') // Newline or DOS-style newline.
C = *++CurPtr;
// If this is a newline, we're done.
if (C == '\n' || C == '\r')
break; // Found the newline? Break out!
// Otherwise, this is a hard case. Fall back on getAndAdvanceChar to
// properly decode the character. Read it in raw mode to avoid emitting
// diagnostics about things like trigraphs. If we see an escaped newline,
// we'll handle it below.
const char *OldPtr = CurPtr;
bool OldRawMode = isLexingRawMode();
LexingRawMode = true;
C = getAndAdvanceChar(CurPtr, Result);
LexingRawMode = OldRawMode;
// If the char that we finally got was a \n, then we must have had something
// like \<newline><newline>. We don't want to have consumed the second
// newline, we want CurPtr, to end up pointing to it down below.
if (C == '\n' || C == '\r') {
--CurPtr;
C = 'x'; // doesn't matter what this is.
}
// If we read multiple characters, and one of those characters was a \r or
// \n, then we had an escaped newline within the comment. Emit diagnostic
// unless the next line is also a // comment.
if (CurPtr != OldPtr+1 && C != '/' && CurPtr[0] != '/') {
for (; OldPtr != CurPtr; ++OldPtr)
if (OldPtr[0] == '\n' || OldPtr[0] == '\r') {
// Okay, we found a // comment that ends in a newline, if the next
// line is also a // comment, but has spaces, don't emit a diagnostic.
if (isspace(C)) {
const char *ForwardPtr = CurPtr;
while (isspace(*ForwardPtr)) // Skip whitespace.
++ForwardPtr;
if (ForwardPtr[0] == '/' && ForwardPtr[1] == '/')
break;
}
if (!isLexingRawMode())
Diag(OldPtr-1, diag::ext_multi_line_bcpl_comment);
break;
}
}
if (CurPtr == BufferEnd+1) { --CurPtr; break; }
} while (C != '\n' && C != '\r');
// Found but did not consume the newline. Notify comment handlers about the
// comment unless we're in a #if 0 block.
if (PP && !isLexingRawMode() &&
PP->HandleComment(Result, SourceRange(getSourceLocation(BufferPtr),
getSourceLocation(CurPtr)))) {
BufferPtr = CurPtr;
return true; // A token has to be returned.
}
// If we are returning comments as tokens, return this comment as a token.
if (inKeepCommentMode())
return SaveBCPLComment(Result, CurPtr);
// If we are inside a preprocessor directive and we see the end of line,
// return immediately, so that the lexer can return this as an EOM token.
if (ParsingPreprocessorDirective || CurPtr == BufferEnd) {
BufferPtr = CurPtr;
return false;
}
// Otherwise, eat the \n character. We don't care if this is a \n\r or
// \r\n sequence. This is an efficiency hack (because we know the \n can't
// contribute to another token), it isn't needed for correctness. Note that
// this is ok even in KeepWhitespaceMode, because we would have returned the
/// comment above in that mode.
++CurPtr;
// The next returned token is at the start of the line.
Result.setFlag(Token::StartOfLine);
// No leading whitespace seen so far.
Result.clearFlag(Token::LeadingSpace);
BufferPtr = CurPtr;
return false;
}
/// SaveBCPLComment - If in save-comment mode, package up this BCPL comment in
/// an appropriate way and return it.
bool Lexer::SaveBCPLComment(Token &Result, const char *CurPtr) {
// If we're not in a preprocessor directive, just return the // comment
// directly.
FormTokenWithChars(Result, CurPtr, tok::comment);
if (!ParsingPreprocessorDirective)
return true;
// If this BCPL-style comment is in a macro definition, transmogrify it into
// a C-style block comment.
bool Invalid = false;
std::string Spelling = PP->getSpelling(Result, &Invalid);
if (Invalid)
return true;
assert(Spelling[0] == '/' && Spelling[1] == '/' && "Not bcpl comment?");
Spelling[1] = '*'; // Change prefix to "/*".
Spelling += "*/"; // add suffix.
Result.setKind(tok::comment);
PP->CreateString(&Spelling[0], Spelling.size(), Result,
Result.getLocation());
return true;
}
/// isBlockCommentEndOfEscapedNewLine - Return true if the specified newline
/// character (either \n or \r) is part of an escaped newline sequence. Issue a
/// diagnostic if so. We know that the newline is inside of a block comment.
static bool isEndOfBlockCommentWithEscapedNewLine(const char *CurPtr,
Lexer *L) {
assert(CurPtr[0] == '\n' || CurPtr[0] == '\r');
// Back up off the newline.
--CurPtr;
// If this is a two-character newline sequence, skip the other character.
if (CurPtr[0] == '\n' || CurPtr[0] == '\r') {
// \n\n or \r\r -> not escaped newline.
if (CurPtr[0] == CurPtr[1])
return false;
// \n\r or \r\n -> skip the newline.
--CurPtr;
}
// If we have horizontal whitespace, skip over it. We allow whitespace
// between the slash and newline.
bool HasSpace = false;
while (isHorizontalWhitespace(*CurPtr) || *CurPtr == 0) {
--CurPtr;
HasSpace = true;
}
// If we have a slash, we know this is an escaped newline.
if (*CurPtr == '\\') {
if (CurPtr[-1] != '*') return false;
} else {
// It isn't a slash, is it the ?? / trigraph?
if (CurPtr[0] != '/' || CurPtr[-1] != '?' || CurPtr[-2] != '?' ||
CurPtr[-3] != '*')
return false;
// This is the trigraph ending the comment. Emit a stern warning!
CurPtr -= 2;
// If no trigraphs are enabled, warn that we ignored this trigraph and
// ignore this * character.
if (!L->getFeatures().Trigraphs) {
if (!L->isLexingRawMode())
L->Diag(CurPtr, diag::trigraph_ignored_block_comment);
return false;
}
if (!L->isLexingRawMode())
L->Diag(CurPtr, diag::trigraph_ends_block_comment);
}
// Warn about having an escaped newline between the */ characters.
if (!L->isLexingRawMode())
L->Diag(CurPtr, diag::escaped_newline_block_comment_end);
// If there was space between the backslash and newline, warn about it.
if (HasSpace && !L->isLexingRawMode())
L->Diag(CurPtr, diag::backslash_newline_space);
return true;
}
#ifdef __SSE2__
#include <emmintrin.h>
#elif __ALTIVEC__
#include <altivec.h>
#undef bool
#endif
/// SkipBlockComment - We have just read the /* characters from input. Read
/// until we find the */ characters that terminate the comment. Note that we
/// don't bother decoding trigraphs or escaped newlines in block comments,
/// because they cannot cause the comment to end. The only thing that can
/// happen is the comment could end with an escaped newline between the */ end
/// of comment.
///
/// If we're in KeepCommentMode or any CommentHandler has inserted
/// some tokens, this will store the first token and return true.
bool Lexer::SkipBlockComment(Token &Result, const char *CurPtr) {
// Scan one character past where we should, looking for a '/' character. Once
// we find it, check to see if it was preceeded by a *. This common
// optimization helps people who like to put a lot of * characters in their
// comments.
// The first character we get with newlines and trigraphs skipped to handle
// the degenerate /*/ case below correctly if the * has an escaped newline
// after it.
unsigned CharSize;
unsigned char C = getCharAndSize(CurPtr, CharSize);
CurPtr += CharSize;
if (C == 0 && CurPtr == BufferEnd+1) {
if (!isLexingRawMode())
Diag(BufferPtr, diag::err_unterminated_block_comment);
--CurPtr;
// KeepWhitespaceMode should return this broken comment as a token. Since
// it isn't a well formed comment, just return it as an 'unknown' token.
if (isKeepWhitespaceMode()) {
FormTokenWithChars(Result, CurPtr, tok::unknown);
return true;
}
BufferPtr = CurPtr;
return false;
}
// Check to see if the first character after the '/*' is another /. If so,
// then this slash does not end the block comment, it is part of it.
if (C == '/')
C = *CurPtr++;
while (1) {
// Skip over all non-interesting characters until we find end of buffer or a
// (probably ending) '/' character.
if (CurPtr + 24 < BufferEnd) {
// While not aligned to a 16-byte boundary.
while (C != '/' && ((intptr_t)CurPtr & 0x0F) != 0)
C = *CurPtr++;
if (C == '/') goto FoundSlash;
#ifdef __SSE2__
__m128i Slashes = _mm_set_epi8('/', '/', '/', '/', '/', '/', '/', '/',
'/', '/', '/', '/', '/', '/', '/', '/');
while (CurPtr+16 <= BufferEnd &&
_mm_movemask_epi8(_mm_cmpeq_epi8(*(__m128i*)CurPtr, Slashes)) == 0)
CurPtr += 16;
#elif __ALTIVEC__
__vector unsigned char Slashes = {
'/', '/', '/', '/', '/', '/', '/', '/',
'/', '/', '/', '/', '/', '/', '/', '/'
};
while (CurPtr+16 <= BufferEnd &&
!vec_any_eq(*(vector unsigned char*)CurPtr, Slashes))
CurPtr += 16;
#else
// Scan for '/' quickly. Many block comments are very large.
while (CurPtr[0] != '/' &&
CurPtr[1] != '/' &&
CurPtr[2] != '/' &&
CurPtr[3] != '/' &&
CurPtr+4 < BufferEnd) {
CurPtr += 4;
}
#endif
// It has to be one of the bytes scanned, increment to it and read one.
C = *CurPtr++;
}
// Loop to scan the remainder.
while (C != '/' && C != '\0')
C = *CurPtr++;
FoundSlash:
if (C == '/') {
if (CurPtr[-2] == '*') // We found the final */. We're done!
break;
if ((CurPtr[-2] == '\n' || CurPtr[-2] == '\r')) {
if (isEndOfBlockCommentWithEscapedNewLine(CurPtr-2, this)) {
// We found the final */, though it had an escaped newline between the
// * and /. We're done!
break;
}
}
if (CurPtr[0] == '*' && CurPtr[1] != '/') {
// If this is a /* inside of the comment, emit a warning. Don't do this
// if this is a /*/, which will end the comment. This misses cases with
// embedded escaped newlines, but oh well.
if (!isLexingRawMode())
Diag(CurPtr-1, diag::warn_nested_block_comment);
}
} else if (C == 0 && CurPtr == BufferEnd+1) {
if (!isLexingRawMode())
Diag(BufferPtr, diag::err_unterminated_block_comment);
// Note: the user probably forgot a */. We could continue immediately
// after the /*, but this would involve lexing a lot of what really is the
// comment, which surely would confuse the parser.
--CurPtr;
// KeepWhitespaceMode should return this broken comment as a token. Since
// it isn't a well formed comment, just return it as an 'unknown' token.
if (isKeepWhitespaceMode()) {
FormTokenWithChars(Result, CurPtr, tok::unknown);
return true;
}
BufferPtr = CurPtr;
return false;
}
C = *CurPtr++;
}
// Notify comment handlers about the comment unless we're in a #if 0 block.
if (PP && !isLexingRawMode() &&
PP->HandleComment(Result, SourceRange(getSourceLocation(BufferPtr),
getSourceLocation(CurPtr)))) {
BufferPtr = CurPtr;
return true; // A token has to be returned.
}
// If we are returning comments as tokens, return this comment as a token.
if (inKeepCommentMode()) {
FormTokenWithChars(Result, CurPtr, tok::comment);
return true;
}
// It is common for the tokens immediately after a /**/ comment to be
// whitespace. Instead of going through the big switch, handle it
// efficiently now. This is safe even in KeepWhitespaceMode because we would
// have already returned above with the comment as a token.
if (isHorizontalWhitespace(*CurPtr)) {
Result.setFlag(Token::LeadingSpace);
SkipWhitespace(Result, CurPtr+1);
return false;
}
// Otherwise, just return so that the next character will be lexed as a token.
BufferPtr = CurPtr;
Result.setFlag(Token::LeadingSpace);
return false;
}
//===----------------------------------------------------------------------===//
// Primary Lexing Entry Points
//===----------------------------------------------------------------------===//
/// ReadToEndOfLine - Read the rest of the current preprocessor line as an
/// uninterpreted string. This switches the lexer out of directive mode.
std::string Lexer::ReadToEndOfLine() {
assert(ParsingPreprocessorDirective && ParsingFilename == false &&
"Must be in a preprocessing directive!");
std::string Result;
Token Tmp;
// CurPtr - Cache BufferPtr in an automatic variable.
const char *CurPtr = BufferPtr;
while (1) {
char Char = getAndAdvanceChar(CurPtr, Tmp);
switch (Char) {
default:
Result += Char;
break;
case 0: // Null.
// Found end of file?
if (CurPtr-1 != BufferEnd) {
// Nope, normal character, continue.
Result += Char;
break;
}
// FALL THROUGH.
case '\r':
case '\n':
// Okay, we found the end of the line. First, back up past the \0, \r, \n.
assert(CurPtr[-1] == Char && "Trigraphs for newline?");
BufferPtr = CurPtr-1;
// Next, lex the character, which should handle the EOM transition.
Lex(Tmp);
assert(Tmp.is(tok::eom) && "Unexpected token!");
// Finally, we're done, return the string we found.
return Result;
}
}
}
/// LexEndOfFile - CurPtr points to the end of this file. Handle this
/// condition, reporting diagnostics and handling other edge cases as required.
/// This returns true if Result contains a token, false if PP.Lex should be
/// called again.
bool Lexer::LexEndOfFile(Token &Result, const char *CurPtr) {
// If we hit the end of the file while parsing a preprocessor directive,
// end the preprocessor directive first. The next token returned will
// then be the end of file.
if (ParsingPreprocessorDirective) {
// Done parsing the "line".
ParsingPreprocessorDirective = false;
// Update the location of token as well as BufferPtr.
FormTokenWithChars(Result, CurPtr, tok::eom);
// Restore comment saving mode, in case it was disabled for directive.
SetCommentRetentionState(PP->getCommentRetentionState());
return true; // Have a token.
}
// If we are in raw mode, return this event as an EOF token. Let the caller
// that put us in raw mode handle the event.
if (isLexingRawMode()) {
Result.startToken();
BufferPtr = BufferEnd;
FormTokenWithChars(Result, BufferEnd, tok::eof);
return true;
}
// Otherwise, check if we are code-completing, then issue diagnostics for
// unterminated #if and missing newline.
if (PP && PP->isCodeCompletionFile(FileLoc)) {
// We're at the end of the file, but we've been asked to consider the
// end of the file to be a code-completion token. Return the
// code-completion token.
Result.startToken();
FormTokenWithChars(Result, CurPtr, tok::code_completion);
// Only do the eof -> code_completion translation once.
PP->SetCodeCompletionPoint(0, 0, 0);
return true;
}
// If we are in a #if directive, emit an error.
while (!ConditionalStack.empty()) {
PP->Diag(ConditionalStack.back().IfLoc,
diag::err_pp_unterminated_conditional);
ConditionalStack.pop_back();
}
// C99 5.1.1.2p2: If the file is non-empty and didn't end in a newline, issue
// a pedwarn.
if (CurPtr != BufferStart && (CurPtr[-1] != '\n' && CurPtr[-1] != '\r'))
Diag(BufferEnd, diag::ext_no_newline_eof)
<< FixItHint::CreateInsertion(getSourceLocation(BufferEnd), "\n");
BufferPtr = CurPtr;
// Finally, let the preprocessor handle this.
return PP->HandleEndOfFile(Result);
}
/// isNextPPTokenLParen - Return 1 if the next unexpanded token lexed from
/// the specified lexer will return a tok::l_paren token, 0 if it is something
/// else and 2 if there are no more tokens in the buffer controlled by the
/// lexer.
unsigned Lexer::isNextPPTokenLParen() {
assert(!LexingRawMode && "How can we expand a macro from a skipping buffer?");
// Switch to 'skipping' mode. This will ensure that we can lex a token
// without emitting diagnostics, disables macro expansion, and will cause EOF
// to return an EOF token instead of popping the include stack.
LexingRawMode = true;
// Save state that can be changed while lexing so that we can restore it.
const char *TmpBufferPtr = BufferPtr;
bool inPPDirectiveMode = ParsingPreprocessorDirective;
Token Tok;
Tok.startToken();
LexTokenInternal(Tok);
// Restore state that may have changed.
BufferPtr = TmpBufferPtr;
ParsingPreprocessorDirective = inPPDirectiveMode;
// Restore the lexer back to non-skipping mode.
LexingRawMode = false;
if (Tok.is(tok::eof))
return 2;
return Tok.is(tok::l_paren);
}
/// FindConflictEnd - Find the end of a version control conflict marker.
static const char *FindConflictEnd(const char *CurPtr, const char *BufferEnd) {
llvm::StringRef RestOfBuffer(CurPtr+7, BufferEnd-CurPtr-7);
size_t Pos = RestOfBuffer.find(">>>>>>>");
while (Pos != llvm::StringRef::npos) {
// Must occur at start of line.
if (RestOfBuffer[Pos-1] != '\r' &&
RestOfBuffer[Pos-1] != '\n') {
RestOfBuffer = RestOfBuffer.substr(Pos+7);
continue;
}
return RestOfBuffer.data()+Pos;
}
return 0;
}
/// IsStartOfConflictMarker - If the specified pointer is the start of a version
/// control conflict marker like '<<<<<<<', recognize it as such, emit an error
/// and recover nicely. This returns true if it is a conflict marker and false
/// if not.
bool Lexer::IsStartOfConflictMarker(const char *CurPtr) {
// Only a conflict marker if it starts at the beginning of a line.
if (CurPtr != BufferStart &&
CurPtr[-1] != '\n' && CurPtr[-1] != '\r')
return false;
// Check to see if we have <<<<<<<.
if (BufferEnd-CurPtr < 8 ||
llvm::StringRef(CurPtr, 7) != "<<<<<<<")
return false;
// If we have a situation where we don't care about conflict markers, ignore
// it.
if (IsInConflictMarker || isLexingRawMode())
return false;
// Check to see if there is a >>>>>>> somewhere in the buffer at the start of
// a line to terminate this conflict marker.
if (FindConflictEnd(CurPtr+7, BufferEnd)) {
// We found a match. We are really in a conflict marker.
// Diagnose this, and ignore to the end of line.
Diag(CurPtr, diag::err_conflict_marker);
IsInConflictMarker = true;
// Skip ahead to the end of line. We know this exists because the
// end-of-conflict marker starts with \r or \n.
while (*CurPtr != '\r' && *CurPtr != '\n') {
assert(CurPtr != BufferEnd && "Didn't find end of line");
++CurPtr;
}
BufferPtr = CurPtr;
return true;
}
// No end of conflict marker found.
return false;
}
/// HandleEndOfConflictMarker - If this is a '=======' or '|||||||' or '>>>>>>>'
/// marker, then it is the end of a conflict marker. Handle it by ignoring up
/// until the end of the line. This returns true if it is a conflict marker and
/// false if not.
bool Lexer::HandleEndOfConflictMarker(const char *CurPtr) {
// Only a conflict marker if it starts at the beginning of a line.
if (CurPtr != BufferStart &&
CurPtr[-1] != '\n' && CurPtr[-1] != '\r')
return false;
// If we have a situation where we don't care about conflict markers, ignore
// it.
if (!IsInConflictMarker || isLexingRawMode())
return false;
// Check to see if we have the marker (7 characters in a row).
for (unsigned i = 1; i != 7; ++i)
if (CurPtr[i] != CurPtr[0])
return false;
// If we do have it, search for the end of the conflict marker. This could
// fail if it got skipped with a '#if 0' or something. Note that CurPtr might
// be the end of conflict marker.
if (const char *End = FindConflictEnd(CurPtr, BufferEnd)) {
CurPtr = End;
// Skip ahead to the end of line.
while (CurPtr != BufferEnd && *CurPtr != '\r' && *CurPtr != '\n')
++CurPtr;
BufferPtr = CurPtr;
// No longer in the conflict marker.
IsInConflictMarker = false;
return true;
}
return false;
}
/// LexTokenInternal - This implements a simple C family lexer. It is an
/// extremely performance critical piece of code. This assumes that the buffer
/// has a null character at the end of the file. This returns a preprocessing
/// token, not a normal token, as such, it is an internal interface. It assumes
/// that the Flags of result have been cleared before calling this.
void Lexer::LexTokenInternal(Token &Result) {
LexNextToken:
// New token, can't need cleaning yet.
Result.clearFlag(Token::NeedsCleaning);
Result.setIdentifierInfo(0);
// CurPtr - Cache BufferPtr in an automatic variable.
const char *CurPtr = BufferPtr;
// Small amounts of horizontal whitespace is very common between tokens.
if ((*CurPtr == ' ') || (*CurPtr == '\t')) {
++CurPtr;
while ((*CurPtr == ' ') || (*CurPtr == '\t'))
++CurPtr;
// If we are keeping whitespace and other tokens, just return what we just
// skipped. The next lexer invocation will return the token after the
// whitespace.
if (isKeepWhitespaceMode()) {
FormTokenWithChars(Result, CurPtr, tok::unknown);
return;
}
BufferPtr = CurPtr;
Result.setFlag(Token::LeadingSpace);
}
unsigned SizeTmp, SizeTmp2; // Temporaries for use in cases below.
// Read a character, advancing over it.
char Char = getAndAdvanceChar(CurPtr, Result);
tok::TokenKind Kind;
switch (Char) {
case 0: // Null.
// Found end of file?
if (CurPtr-1 == BufferEnd) {
// Read the PP instance variable into an automatic variable, because
// LexEndOfFile will often delete 'this'.
Preprocessor *PPCache = PP;
if (LexEndOfFile(Result, CurPtr-1)) // Retreat back into the file.
return; // Got a token to return.
assert(PPCache && "Raw buffer::LexEndOfFile should return a token");
return PPCache->Lex(Result);
}
if (!isLexingRawMode())
Diag(CurPtr-1, diag::null_in_file);
Result.setFlag(Token::LeadingSpace);
if (SkipWhitespace(Result, CurPtr))
return; // KeepWhitespaceMode
goto LexNextToken; // GCC isn't tail call eliminating.
case 26: // DOS & CP/M EOF: "^Z".
// If we're in Microsoft extensions mode, treat this as end of file.
if (Features.Microsoft) {
// Read the PP instance variable into an automatic variable, because
// LexEndOfFile will often delete 'this'.
Preprocessor *PPCache = PP;
if (LexEndOfFile(Result, CurPtr-1)) // Retreat back into the file.
return; // Got a token to return.
assert(PPCache && "Raw buffer::LexEndOfFile should return a token");
return PPCache->Lex(Result);
}
// If Microsoft extensions are disabled, this is just random garbage.
Kind = tok::unknown;
break;
case '\n':
case '\r':
// If we are inside a preprocessor directive and we see the end of line,
// we know we are done with the directive, so return an EOM token.
if (ParsingPreprocessorDirective) {
// Done parsing the "line".
ParsingPreprocessorDirective = false;
// Restore comment saving mode, in case it was disabled for directive.
SetCommentRetentionState(PP->getCommentRetentionState());
// Since we consumed a newline, we are back at the start of a line.
IsAtStartOfLine = true;
Kind = tok::eom;
break;
}
// The returned token is at the start of the line.
Result.setFlag(Token::StartOfLine);
// No leading whitespace seen so far.
Result.clearFlag(Token::LeadingSpace);
if (SkipWhitespace(Result, CurPtr))
return; // KeepWhitespaceMode
goto LexNextToken; // GCC isn't tail call eliminating.
case ' ':
case '\t':
case '\f':
case '\v':
SkipHorizontalWhitespace:
Result.setFlag(Token::LeadingSpace);
if (SkipWhitespace(Result, CurPtr))
return; // KeepWhitespaceMode
SkipIgnoredUnits:
CurPtr = BufferPtr;
// If the next token is obviously a // or /* */ comment, skip it efficiently
// too (without going through the big switch stmt).
if (CurPtr[0] == '/' && CurPtr[1] == '/' && !inKeepCommentMode() &&
Features.BCPLComment) {
if (SkipBCPLComment(Result, CurPtr+2))
return; // There is a token to return.
goto SkipIgnoredUnits;
} else if (CurPtr[0] == '/' && CurPtr[1] == '*' && !inKeepCommentMode()) {
if (SkipBlockComment(Result, CurPtr+2))
return; // There is a token to return.
goto SkipIgnoredUnits;
} else if (isHorizontalWhitespace(*CurPtr)) {
goto SkipHorizontalWhitespace;
}
goto LexNextToken; // GCC isn't tail call eliminating.
// C99 6.4.4.1: Integer Constants.
// C99 6.4.4.2: Floating Constants.
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexNumericConstant(Result, CurPtr);
case 'L': // Identifier (Loony) or wide literal (L'x' or L"xyz").
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
Char = getCharAndSize(CurPtr, SizeTmp);
// Wide string literal.
if (Char == '"')
return LexStringLiteral(Result, ConsumeChar(CurPtr, SizeTmp, Result),
true);
// Wide character constant.
if (Char == '\'')
return LexCharConstant(Result, ConsumeChar(CurPtr, SizeTmp, Result));
// FALL THROUGH, treating L like the start of an identifier.
// C99 6.4.2: Identifiers.
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G':
case 'H': case 'I': case 'J': case 'K': /*'L'*/case 'M': case 'N':
case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U':
case 'V': case 'W': case 'X': case 'Y': case 'Z':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g':
case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n':
case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u':
case 'v': case 'w': case 'x': case 'y': case 'z':
case '_':
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexIdentifier(Result, CurPtr);
case '$': // $ in identifiers.
if (Features.DollarIdents) {
if (!isLexingRawMode())
Diag(CurPtr-1, diag::ext_dollar_in_identifier);
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexIdentifier(Result, CurPtr);
}
Kind = tok::unknown;
break;
// C99 6.4.4: Character Constants.
case '\'':
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexCharConstant(Result, CurPtr);
// C99 6.4.5: String Literals.
case '"':
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexStringLiteral(Result, CurPtr, false);
// C99 6.4.6: Punctuators.
case '?':
Kind = tok::question;
break;
case '[':
Kind = tok::l_square;
break;
case ']':
Kind = tok::r_square;
break;
case '(':
Kind = tok::l_paren;
break;
case ')':
Kind = tok::r_paren;
break;
case '{':
Kind = tok::l_brace;
break;
case '}':
Kind = tok::r_brace;
break;
case '.':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char >= '0' && Char <= '9') {
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
return LexNumericConstant(Result, ConsumeChar(CurPtr, SizeTmp, Result));
} else if (Features.CPlusPlus && Char == '*') {
Kind = tok::periodstar;
CurPtr += SizeTmp;
} else if (Char == '.' &&
getCharAndSize(CurPtr+SizeTmp, SizeTmp2) == '.') {
Kind = tok::ellipsis;
CurPtr = ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result);
} else {
Kind = tok::period;
}
break;
case '&':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '&') {
Kind = tok::ampamp;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Char == '=') {
Kind = tok::ampequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::amp;
}
break;
case '*':
if (getCharAndSize(CurPtr, SizeTmp) == '=') {
Kind = tok::starequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::star;
}
break;
case '+':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '+') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::plusplus;
} else if (Char == '=') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::plusequal;
} else {
Kind = tok::plus;
}
break;
case '-':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '-') { // --
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::minusminus;
} else if (Char == '>' && Features.CPlusPlus &&
getCharAndSize(CurPtr+SizeTmp, SizeTmp2) == '*') { // C++ ->*
CurPtr = ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result);
Kind = tok::arrowstar;
} else if (Char == '>') { // ->
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::arrow;
} else if (Char == '=') { // -=
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::minusequal;
} else {
Kind = tok::minus;
}
break;
case '~':
Kind = tok::tilde;
break;
case '!':
if (getCharAndSize(CurPtr, SizeTmp) == '=') {
Kind = tok::exclaimequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::exclaim;
}
break;
case '/':
// 6.4.9: Comments
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '/') { // BCPL comment.
// Even if BCPL comments are disabled (e.g. in C89 mode), we generally
// want to lex this as a comment. There is one problem with this though,
// that in one particular corner case, this can change the behavior of the
// resultant program. For example, In "foo //**/ bar", C89 would lex
// this as "foo / bar" and langauges with BCPL comments would lex it as
// "foo". Check to see if the character after the second slash is a '*'.
// If so, we will lex that as a "/" instead of the start of a comment.
if (Features.BCPLComment ||
getCharAndSize(CurPtr+SizeTmp, SizeTmp2) != '*') {
if (SkipBCPLComment(Result, ConsumeChar(CurPtr, SizeTmp, Result)))
return; // There is a token to return.
// It is common for the tokens immediately after a // comment to be
// whitespace (indentation for the next line). Instead of going through
// the big switch, handle it efficiently now.
goto SkipIgnoredUnits;
}
}
if (Char == '*') { // /**/ comment.
if (SkipBlockComment(Result, ConsumeChar(CurPtr, SizeTmp, Result)))
return; // There is a token to return.
goto LexNextToken; // GCC isn't tail call eliminating.
}
if (Char == '=') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::slashequal;
} else {
Kind = tok::slash;
}
break;
case '%':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '=') {
Kind = tok::percentequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Features.Digraphs && Char == '>') {
Kind = tok::r_brace; // '%>' -> '}'
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Features.Digraphs && Char == ':') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '%' && getCharAndSize(CurPtr+SizeTmp, SizeTmp2) == ':') {
Kind = tok::hashhash; // '%:%:' -> '##'
CurPtr = ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result);
} else if (Char == '@' && Features.Microsoft) { // %:@ -> #@ -> Charize
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
if (!isLexingRawMode())
Diag(BufferPtr, diag::charize_microsoft_ext);
Kind = tok::hashat;
} else { // '%:' -> '#'
// We parsed a # character. If this occurs at the start of the line,
// it's actually the start of a preprocessing directive. Callback to
// the preprocessor to handle it.
// FIXME: -fpreprocessed mode??
if (Result.isAtStartOfLine() && !LexingRawMode && !Is_PragmaLexer) {
FormTokenWithChars(Result, CurPtr, tok::hash);
PP->HandleDirective(Result);
// As an optimization, if the preprocessor didn't switch lexers, tail
// recurse.
if (PP->isCurrentLexer(this)) {
// Start a new token. If this is a #include or something, the PP may
// want us starting at the beginning of the line again. If so, set
// the StartOfLine flag and clear LeadingSpace.
if (IsAtStartOfLine) {
Result.setFlag(Token::StartOfLine);
Result.clearFlag(Token::LeadingSpace);
IsAtStartOfLine = false;
}
goto LexNextToken; // GCC isn't tail call eliminating.
}
return PP->Lex(Result);
}
Kind = tok::hash;
}
} else {
Kind = tok::percent;
}
break;
case '<':
Char = getCharAndSize(CurPtr, SizeTmp);
if (ParsingFilename) {
return LexAngledStringLiteral(Result, CurPtr);
} else if (Char == '<') {
char After = getCharAndSize(CurPtr+SizeTmp, SizeTmp2);
if (After == '=') {
Kind = tok::lesslessequal;
CurPtr = ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result);
} else if (After == '<' && IsStartOfConflictMarker(CurPtr-1)) {
// If this is actually a '<<<<<<<' version control conflict marker,
// recognize it as such and recover nicely.
goto LexNextToken;
} else {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::lessless;
}
} else if (Char == '=') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::lessequal;
} else if (Features.Digraphs && Char == ':') { // '<:' -> '['
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::l_square;
} else if (Features.Digraphs && Char == '%') { // '<%' -> '{'
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::l_brace;
} else {
Kind = tok::less;
}
break;
case '>':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '=') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::greaterequal;
} else if (Char == '>') {
char After = getCharAndSize(CurPtr+SizeTmp, SizeTmp2);
if (After == '=') {
CurPtr = ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
SizeTmp2, Result);
Kind = tok::greatergreaterequal;
} else if (After == '>' && HandleEndOfConflictMarker(CurPtr-1)) {
// If this is '>>>>>>>' and we're in a conflict marker, ignore it.
goto LexNextToken;
} else {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::greatergreater;
}
} else {
Kind = tok::greater;
}
break;
case '^':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '=') {
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
Kind = tok::caretequal;
} else {
Kind = tok::caret;
}
break;
case '|':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '=') {
Kind = tok::pipeequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Char == '|') {
// If this is '|||||||' and we're in a conflict marker, ignore it.
if (CurPtr[1] == '|' && HandleEndOfConflictMarker(CurPtr-1))
goto LexNextToken;
Kind = tok::pipepipe;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::pipe;
}
break;
case ':':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Features.Digraphs && Char == '>') {
Kind = tok::r_square; // ':>' -> ']'
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Features.CPlusPlus && Char == ':') {
Kind = tok::coloncolon;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::colon;
}
break;
case ';':
Kind = tok::semi;
break;
case '=':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '=') {
// If this is '=======' and we're in a conflict marker, ignore it.
if (CurPtr[1] == '=' && HandleEndOfConflictMarker(CurPtr-1))
goto LexNextToken;
Kind = tok::equalequal;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
Kind = tok::equal;
}
break;
case ',':
Kind = tok::comma;
break;
case '#':
Char = getCharAndSize(CurPtr, SizeTmp);
if (Char == '#') {
Kind = tok::hashhash;
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else if (Char == '@' && Features.Microsoft) { // #@ -> Charize
Kind = tok::hashat;
if (!isLexingRawMode())
Diag(BufferPtr, diag::charize_microsoft_ext);
CurPtr = ConsumeChar(CurPtr, SizeTmp, Result);
} else {
// We parsed a # character. If this occurs at the start of the line,
// it's actually the start of a preprocessing directive. Callback to
// the preprocessor to handle it.
// FIXME: -fpreprocessed mode??
if (Result.isAtStartOfLine() && !LexingRawMode && !Is_PragmaLexer) {
FormTokenWithChars(Result, CurPtr, tok::hash);
PP->HandleDirective(Result);
// As an optimization, if the preprocessor didn't switch lexers, tail
// recurse.
if (PP->isCurrentLexer(this)) {
// Start a new token. If this is a #include or something, the PP may
// want us starting at the beginning of the line again. If so, set
// the StartOfLine flag and clear LeadingSpace.
if (IsAtStartOfLine) {
Result.setFlag(Token::StartOfLine);
Result.clearFlag(Token::LeadingSpace);
IsAtStartOfLine = false;
}
goto LexNextToken; // GCC isn't tail call eliminating.
}
return PP->Lex(Result);
}
Kind = tok::hash;
}
break;
case '@':
// Objective C support.
if (CurPtr[-1] == '@' && Features.ObjC1)
Kind = tok::at;
else
Kind = tok::unknown;
break;
case '\\':
// FIXME: UCN's.
// FALL THROUGH.
default:
Kind = tok::unknown;
break;
}
// Notify MIOpt that we read a non-whitespace/non-comment token.
MIOpt.ReadToken();
// Update the location of token as well as BufferPtr.
FormTokenWithChars(Result, CurPtr, Kind);
}
|