aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clang16/lib/Lex/LiteralSupport.cpp
blob: 421a8533604300cbee0fc01138f04c13b1cde258 (plain) (blame)
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
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
//===--- LiteralSupport.cpp - Code to parse and process literals ----------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the NumericLiteralParser, CharLiteralParser, and
// StringLiteralParser interfaces.
//
//===----------------------------------------------------------------------===//

#include "clang/Lex/LiteralSupport.h"
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Lex/LexDiagnostic.h"
#include "clang/Lex/Lexer.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Lex/Token.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/Unicode.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <cstring>
#include <string>

using namespace clang;

static unsigned getCharWidth(tok::TokenKind kind, const TargetInfo &Target) {
  switch (kind) {
  default: llvm_unreachable("Unknown token type!");
  case tok::char_constant:
  case tok::string_literal:
  case tok::utf8_char_constant:
  case tok::utf8_string_literal:
    return Target.getCharWidth();
  case tok::wide_char_constant:
  case tok::wide_string_literal:
    return Target.getWCharWidth();
  case tok::utf16_char_constant:
  case tok::utf16_string_literal:
    return Target.getChar16Width();
  case tok::utf32_char_constant:
  case tok::utf32_string_literal:
    return Target.getChar32Width();
  }
}

static CharSourceRange MakeCharSourceRange(const LangOptions &Features,
                                           FullSourceLoc TokLoc,
                                           const char *TokBegin,
                                           const char *TokRangeBegin,
                                           const char *TokRangeEnd) {
  SourceLocation Begin =
    Lexer::AdvanceToTokenCharacter(TokLoc, TokRangeBegin - TokBegin,
                                   TokLoc.getManager(), Features);
  SourceLocation End =
    Lexer::AdvanceToTokenCharacter(Begin, TokRangeEnd - TokRangeBegin,
                                   TokLoc.getManager(), Features);
  return CharSourceRange::getCharRange(Begin, End);
}

/// Produce a diagnostic highlighting some portion of a literal.
///
/// Emits the diagnostic \p DiagID, highlighting the range of characters from
/// \p TokRangeBegin (inclusive) to \p TokRangeEnd (exclusive), which must be
/// a substring of a spelling buffer for the token beginning at \p TokBegin.
static DiagnosticBuilder Diag(DiagnosticsEngine *Diags,
                              const LangOptions &Features, FullSourceLoc TokLoc,
                              const char *TokBegin, const char *TokRangeBegin,
                              const char *TokRangeEnd, unsigned DiagID) {
  SourceLocation Begin =
    Lexer::AdvanceToTokenCharacter(TokLoc, TokRangeBegin - TokBegin,
                                   TokLoc.getManager(), Features);
  return Diags->Report(Begin, DiagID) <<
    MakeCharSourceRange(Features, TokLoc, TokBegin, TokRangeBegin, TokRangeEnd);
}

/// ProcessCharEscape - Parse a standard C escape sequence, which can occur in
/// either a character or a string literal.
static unsigned ProcessCharEscape(const char *ThisTokBegin,
                                  const char *&ThisTokBuf,
                                  const char *ThisTokEnd, bool &HadError,
                                  FullSourceLoc Loc, unsigned CharWidth,
                                  DiagnosticsEngine *Diags,
                                  const LangOptions &Features) {
  const char *EscapeBegin = ThisTokBuf;
  bool Delimited = false;
  bool EndDelimiterFound = false;

  // Skip the '\' char.
  ++ThisTokBuf;

  // We know that this character can't be off the end of the buffer, because
  // that would have been \", which would not have been the end of string.
  unsigned ResultChar = *ThisTokBuf++;
  switch (ResultChar) {
  // These map to themselves.
  case '\\': case '\'': case '"': case '?': break;

    // These have fixed mappings.
  case 'a':
    // TODO: K&R: the meaning of '\\a' is different in traditional C
    ResultChar = 7;
    break;
  case 'b':
    ResultChar = 8;
    break;
  case 'e':
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::ext_nonstandard_escape) << "e";
    ResultChar = 27;
    break;
  case 'E':
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::ext_nonstandard_escape) << "E";
    ResultChar = 27;
    break;
  case 'f':
    ResultChar = 12;
    break;
  case 'n':
    ResultChar = 10;
    break;
  case 'r':
    ResultChar = 13;
    break;
  case 't':
    ResultChar = 9;
    break;
  case 'v':
    ResultChar = 11;
    break;
  case 'x': { // Hex escape.
    ResultChar = 0;
    if (ThisTokBuf != ThisTokEnd && *ThisTokBuf == '{') {
      Delimited = true;
      ThisTokBuf++;
      if (*ThisTokBuf == '}') {
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_delimited_escape_empty);
        return ResultChar;
      }
    } else if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
      if (Diags)
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_hex_escape_no_digits) << "x";
      return ResultChar;
    }

    // Hex escapes are a maximal series of hex digits.
    bool Overflow = false;
    for (; ThisTokBuf != ThisTokEnd; ++ThisTokBuf) {
      if (Delimited && *ThisTokBuf == '}') {
        ThisTokBuf++;
        EndDelimiterFound = true;
        break;
      }
      int CharVal = llvm::hexDigitValue(*ThisTokBuf);
      if (CharVal == -1) {
        // Non delimited hex escape sequences stop at the first non-hex digit.
        if (!Delimited)
          break;
        HadError = true;
        if (Diags)
          Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
               diag::err_delimited_escape_invalid)
              << StringRef(ThisTokBuf, 1);
        continue;
      }
      // About to shift out a digit?
      if (ResultChar & 0xF0000000)
        Overflow = true;
      ResultChar <<= 4;
      ResultChar |= CharVal;
    }
    // See if any bits will be truncated when evaluated as a character.
    if (CharWidth != 32 && (ResultChar >> CharWidth) != 0) {
      Overflow = true;
      ResultChar &= ~0U >> (32-CharWidth);
    }

    // Check for overflow.
    if (!HadError && Overflow) { // Too many digits to fit in
      HadError = true;
      if (Diags)
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_escape_too_large)
            << 0;
    }
    break;
  }
  case '0': case '1': case '2': case '3':
  case '4': case '5': case '6': case '7': {
    // Octal escapes.
    --ThisTokBuf;
    ResultChar = 0;

    // Octal escapes are a series of octal digits with maximum length 3.
    // "\0123" is a two digit sequence equal to "\012" "3".
    unsigned NumDigits = 0;
    do {
      ResultChar <<= 3;
      ResultChar |= *ThisTokBuf++ - '0';
      ++NumDigits;
    } while (ThisTokBuf != ThisTokEnd && NumDigits < 3 &&
             ThisTokBuf[0] >= '0' && ThisTokBuf[0] <= '7');

    // Check for overflow.  Reject '\777', but not L'\777'.
    if (CharWidth != 32 && (ResultChar >> CharWidth) != 0) {
      if (Diags)
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_escape_too_large) << 1;
      ResultChar &= ~0U >> (32-CharWidth);
    }
    break;
  }
  case 'o': {
    bool Overflow = false;
    if (ThisTokBuf == ThisTokEnd || *ThisTokBuf != '{') {
      HadError = true;
      if (Diags)
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_delimited_escape_missing_brace)
            << "o";

      break;
    }
    ResultChar = 0;
    Delimited = true;
    ++ThisTokBuf;
    if (*ThisTokBuf == '}') {
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::err_delimited_escape_empty);
      return ResultChar;
    }

    while (ThisTokBuf != ThisTokEnd) {
      if (*ThisTokBuf == '}') {
        EndDelimiterFound = true;
        ThisTokBuf++;
        break;
      }
      if (*ThisTokBuf < '0' || *ThisTokBuf > '7') {
        HadError = true;
        if (Diags)
          Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
               diag::err_delimited_escape_invalid)
              << StringRef(ThisTokBuf, 1);
        ThisTokBuf++;
        continue;
      }
      if (ResultChar & 0x020000000)
        Overflow = true;

      ResultChar <<= 3;
      ResultChar |= *ThisTokBuf++ - '0';
    }
    // Check for overflow.  Reject '\777', but not L'\777'.
    if (!HadError &&
        (Overflow || (CharWidth != 32 && (ResultChar >> CharWidth) != 0))) {
      HadError = true;
      if (Diags)
        Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
             diag::err_escape_too_large)
            << 1;
      ResultChar &= ~0U >> (32 - CharWidth);
    }
    break;
  }
    // Otherwise, these are not valid escapes.
  case '(': case '{': case '[': case '%':
    // GCC accepts these as extensions.  We warn about them as such though.
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::ext_nonstandard_escape)
        << std::string(1, ResultChar);
    break;
  default:
    if (!Diags)
      break;

    if (isPrintable(ResultChar))
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::ext_unknown_escape)
        << std::string(1, ResultChar);
    else
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::ext_unknown_escape)
        << "x" + llvm::utohexstr(ResultChar);
    break;
  }

  if (Delimited && Diags) {
    if (!EndDelimiterFound)
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           diag::err_expected)
          << tok::r_brace;
    else if (!HadError) {
      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
           Features.CPlusPlus2b ? diag::warn_cxx2b_delimited_escape_sequence
                                : diag::ext_delimited_escape_sequence)
          << /*delimited*/ 0 << (Features.CPlusPlus ? 1 : 0);
    }
  }

  return ResultChar;
}

static void appendCodePoint(unsigned Codepoint,
                            llvm::SmallVectorImpl<char> &Str) {
  char ResultBuf[4];
  char *ResultPtr = ResultBuf;
  if (llvm::ConvertCodePointToUTF8(Codepoint, ResultPtr))
    Str.append(ResultBuf, ResultPtr);
}

void clang::expandUCNs(SmallVectorImpl<char> &Buf, StringRef Input) {
  for (StringRef::iterator I = Input.begin(), E = Input.end(); I != E; ++I) {
    if (*I != '\\') {
      Buf.push_back(*I);
      continue;
    }

    ++I;
    char Kind = *I;
    ++I;

    assert(Kind == 'u' || Kind == 'U' || Kind == 'N');
    uint32_t CodePoint = 0;

    if (Kind == 'u' && *I == '{') {
      for (++I; *I != '}'; ++I) {
        unsigned Value = llvm::hexDigitValue(*I);
        assert(Value != -1U);
        CodePoint <<= 4;
        CodePoint += Value;
      }
      appendCodePoint(CodePoint, Buf);
      continue;
    }

    if (Kind == 'N') {
      assert(*I == '{');
      ++I;
      auto Delim = std::find(I, Input.end(), '}');
      assert(Delim != Input.end());
      std::optional<llvm::sys::unicode::LooseMatchingResult> Res =
          llvm::sys::unicode::nameToCodepointLooseMatching(
              StringRef(I, std::distance(I, Delim)));
      assert(Res);
      CodePoint = Res->CodePoint;
      assert(CodePoint != 0xFFFFFFFF);
      appendCodePoint(CodePoint, Buf);
      I = Delim;
      continue;
    }

    unsigned NumHexDigits;
    if (Kind == 'u')
      NumHexDigits = 4;
    else
      NumHexDigits = 8;

    assert(I + NumHexDigits <= E);

    for (; NumHexDigits != 0; ++I, --NumHexDigits) {
      unsigned Value = llvm::hexDigitValue(*I);
      assert(Value != -1U);

      CodePoint <<= 4;
      CodePoint += Value;
    }

    appendCodePoint(CodePoint, Buf);
    --I;
  }
}

static bool ProcessNumericUCNEscape(const char *ThisTokBegin,
                                    const char *&ThisTokBuf,
                                    const char *ThisTokEnd, uint32_t &UcnVal,
                                    unsigned short &UcnLen, bool &Delimited,
                                    FullSourceLoc Loc, DiagnosticsEngine *Diags,
                                    const LangOptions &Features,
                                    bool in_char_string_literal = false) {
  const char *UcnBegin = ThisTokBuf;
  bool HasError = false;
  bool EndDelimiterFound = false;

  // Skip the '\u' char's.
  ThisTokBuf += 2;
  Delimited = false;
  if (UcnBegin[1] == 'u' && in_char_string_literal &&
      ThisTokBuf != ThisTokEnd && *ThisTokBuf == '{') {
    Delimited = true;
    ThisTokBuf++;
  } else if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           diag::err_hex_escape_no_digits)
          << StringRef(&ThisTokBuf[-1], 1);
    return false;
  }
  UcnLen = (ThisTokBuf[-1] == 'u' ? 4 : 8);

  bool Overflow = false;
  unsigned short Count = 0;
  for (; ThisTokBuf != ThisTokEnd && (Delimited || Count != UcnLen);
       ++ThisTokBuf) {
    if (Delimited && *ThisTokBuf == '}') {
      ++ThisTokBuf;
      EndDelimiterFound = true;
      break;
    }
    int CharVal = llvm::hexDigitValue(*ThisTokBuf);
    if (CharVal == -1) {
      HasError = true;
      if (!Delimited)
        break;
      if (Diags) {
        Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
             diag::err_delimited_escape_invalid)
            << StringRef(ThisTokBuf, 1);
      }
      Count++;
      continue;
    }
    if (UcnVal & 0xF0000000) {
      Overflow = true;
      continue;
    }
    UcnVal <<= 4;
    UcnVal |= CharVal;
    Count++;
  }

  if (Overflow) {
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           diag::err_escape_too_large)
          << 0;
    return false;
  }

  if (Delimited && !EndDelimiterFound) {
    if (Diags) {
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           diag::err_expected)
          << tok::r_brace;
    }
    return false;
  }

  // If we didn't consume the proper number of digits, there is a problem.
  if (Count == 0 || (!Delimited && Count != UcnLen)) {
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           Delimited ? diag::err_delimited_escape_empty
                     : diag::err_ucn_escape_incomplete);
    return false;
  }
  return !HasError;
}

static void DiagnoseInvalidUnicodeCharacterName(
    DiagnosticsEngine *Diags, const LangOptions &Features, FullSourceLoc Loc,
    const char *TokBegin, const char *TokRangeBegin, const char *TokRangeEnd,
    llvm::StringRef Name) {

  Diag(Diags, Features, Loc, TokBegin, TokRangeBegin, TokRangeEnd,
       diag::err_invalid_ucn_name)
      << Name;

  namespace u = llvm::sys::unicode;

  std::optional<u::LooseMatchingResult> Res =
      u::nameToCodepointLooseMatching(Name);
  if (Res) {
    Diag(Diags, Features, Loc, TokBegin, TokRangeBegin, TokRangeEnd,
         diag::note_invalid_ucn_name_loose_matching)
        << FixItHint::CreateReplacement(
               MakeCharSourceRange(Features, Loc, TokBegin, TokRangeBegin,
                                   TokRangeEnd),
               Res->Name);
    return;
  }

  unsigned Distance = 0;
  SmallVector<u::MatchForCodepointName> Matches =
      u::nearestMatchesForCodepointName(Name, 5);
  assert(!Matches.empty() && "No unicode characters found");

  for (const auto &Match : Matches) {
    if (Distance == 0)
      Distance = Match.Distance;
    if (std::max(Distance, Match.Distance) -
            std::min(Distance, Match.Distance) >
        3)
      break;
    Distance = Match.Distance;

    std::string Str;
    llvm::UTF32 V = Match.Value;
    bool Converted =
        llvm::convertUTF32ToUTF8String(llvm::ArrayRef<llvm::UTF32>(&V, 1), Str);
    (void)Converted;
    assert(Converted && "Found a match wich is not a unicode character");

    Diag(Diags, Features, Loc, TokBegin, TokRangeBegin, TokRangeEnd,
         diag::note_invalid_ucn_name_candidate)
        << Match.Name << llvm::utohexstr(Match.Value)
        << Str // FIXME: Fix the rendering of non printable characters
        << FixItHint::CreateReplacement(
               MakeCharSourceRange(Features, Loc, TokBegin, TokRangeBegin,
                                   TokRangeEnd),
               Match.Name);
  }
}

static bool ProcessNamedUCNEscape(const char *ThisTokBegin,
                                  const char *&ThisTokBuf,
                                  const char *ThisTokEnd, uint32_t &UcnVal,
                                  unsigned short &UcnLen, FullSourceLoc Loc,
                                  DiagnosticsEngine *Diags,
                                  const LangOptions &Features) {
  const char *UcnBegin = ThisTokBuf;
  assert(UcnBegin[0] == '\\' && UcnBegin[1] == 'N');
  ThisTokBuf += 2;
  if (ThisTokBuf == ThisTokEnd || *ThisTokBuf != '{') {
    if (Diags) {
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           diag::err_delimited_escape_missing_brace)
          << StringRef(&ThisTokBuf[-1], 1);
    }
    return false;
  }
  ThisTokBuf++;
  const char *ClosingBrace = std::find_if(ThisTokBuf, ThisTokEnd, [](char C) {
    return C == '}' || isVerticalWhitespace(C);
  });
  bool Incomplete = ClosingBrace == ThisTokEnd;
  bool Empty = ClosingBrace == ThisTokBuf;
  if (Incomplete || Empty) {
    if (Diags) {
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           Incomplete ? diag::err_ucn_escape_incomplete
                      : diag::err_delimited_escape_empty)
          << StringRef(&UcnBegin[1], 1);
    }
    ThisTokBuf = ClosingBrace == ThisTokEnd ? ClosingBrace : ClosingBrace + 1;
    return false;
  }
  StringRef Name(ThisTokBuf, ClosingBrace - ThisTokBuf);
  ThisTokBuf = ClosingBrace + 1;
  std::optional<char32_t> Res = llvm::sys::unicode::nameToCodepointStrict(Name);
  if (!Res) {
    if (Diags)
      DiagnoseInvalidUnicodeCharacterName(Diags, Features, Loc, ThisTokBegin,
                                          &UcnBegin[3], ClosingBrace, Name);
    return false;
  }
  UcnVal = *Res;
  UcnLen = UcnVal > 0xFFFF ? 8 : 4;
  return true;
}

/// ProcessUCNEscape - Read the Universal Character Name, check constraints and
/// return the UTF32.
static bool ProcessUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf,
                             const char *ThisTokEnd, uint32_t &UcnVal,
                             unsigned short &UcnLen, FullSourceLoc Loc,
                             DiagnosticsEngine *Diags,
                             const LangOptions &Features,
                             bool in_char_string_literal = false) {

  bool HasError;
  const char *UcnBegin = ThisTokBuf;
  bool IsDelimitedEscapeSequence = false;
  bool IsNamedEscapeSequence = false;
  if (ThisTokBuf[1] == 'N') {
    IsNamedEscapeSequence = true;
    HasError = !ProcessNamedUCNEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd,
                                      UcnVal, UcnLen, Loc, Diags, Features);
  } else {
    HasError =
        !ProcessNumericUCNEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd, UcnVal,
                                 UcnLen, IsDelimitedEscapeSequence, Loc, Diags,
                                 Features, in_char_string_literal);
  }
  if (HasError)
    return false;

  // Check UCN constraints (C99 6.4.3p2) [C++11 lex.charset p2]
  if ((0xD800 <= UcnVal && UcnVal <= 0xDFFF) || // surrogate codepoints
      UcnVal > 0x10FFFF) {                      // maximum legal UTF32 value
    if (Diags)
      Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
           diag::err_ucn_escape_invalid);
    return false;
  }

  // C++11 allows UCNs that refer to control characters and basic source
  // characters inside character and string literals
  if (UcnVal < 0xa0 &&
      (UcnVal != 0x24 && UcnVal != 0x40 && UcnVal != 0x60)) {  // $, @, `
    bool IsError = (!Features.CPlusPlus11 || !in_char_string_literal);
    if (Diags) {
      char BasicSCSChar = UcnVal;
      if (UcnVal >= 0x20 && UcnVal < 0x7f)
        Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
             IsError ? diag::err_ucn_escape_basic_scs :
                       diag::warn_cxx98_compat_literal_ucn_escape_basic_scs)
            << StringRef(&BasicSCSChar, 1);
      else
        Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
             IsError ? diag::err_ucn_control_character :
                       diag::warn_cxx98_compat_literal_ucn_control_character);
    }
    if (IsError)
      return false;
  }

  if (!Features.CPlusPlus && !Features.C99 && Diags)
    Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
         diag::warn_ucn_not_valid_in_c89_literal);

  if ((IsDelimitedEscapeSequence || IsNamedEscapeSequence) && Diags)
    Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
         Features.CPlusPlus2b ? diag::warn_cxx2b_delimited_escape_sequence
                              : diag::ext_delimited_escape_sequence)
        << (IsNamedEscapeSequence ? 1 : 0) << (Features.CPlusPlus ? 1 : 0);

  return true;
}

/// MeasureUCNEscape - Determine the number of bytes within the resulting string
/// which this UCN will occupy.
static int MeasureUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf,
                            const char *ThisTokEnd, unsigned CharByteWidth,
                            const LangOptions &Features, bool &HadError) {
  // UTF-32: 4 bytes per escape.
  if (CharByteWidth == 4)
    return 4;

  uint32_t UcnVal = 0;
  unsigned short UcnLen = 0;
  FullSourceLoc Loc;

  if (!ProcessUCNEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd, UcnVal,
                        UcnLen, Loc, nullptr, Features, true)) {
    HadError = true;
    return 0;
  }

  // UTF-16: 2 bytes for BMP, 4 bytes otherwise.
  if (CharByteWidth == 2)
    return UcnVal <= 0xFFFF ? 2 : 4;

  // UTF-8.
  if (UcnVal < 0x80)
    return 1;
  if (UcnVal < 0x800)
    return 2;
  if (UcnVal < 0x10000)
    return 3;
  return 4;
}

/// EncodeUCNEscape - Read the Universal Character Name, check constraints and
/// convert the UTF32 to UTF8 or UTF16. This is a subroutine of
/// StringLiteralParser. When we decide to implement UCN's for identifiers,
/// we will likely rework our support for UCN's.
static void EncodeUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf,
                            const char *ThisTokEnd,
                            char *&ResultBuf, bool &HadError,
                            FullSourceLoc Loc, unsigned CharByteWidth,
                            DiagnosticsEngine *Diags,
                            const LangOptions &Features) {
  typedef uint32_t UTF32;
  UTF32 UcnVal = 0;
  unsigned short UcnLen = 0;
  if (!ProcessUCNEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd, UcnVal, UcnLen,
                        Loc, Diags, Features, true)) {
    HadError = true;
    return;
  }

  assert((CharByteWidth == 1 || CharByteWidth == 2 || CharByteWidth == 4) &&
         "only character widths of 1, 2, or 4 bytes supported");

  (void)UcnLen;
  assert((UcnLen== 4 || UcnLen== 8) && "only ucn length of 4 or 8 supported");

  if (CharByteWidth == 4) {
    // FIXME: Make the type of the result buffer correct instead of
    // using reinterpret_cast.
    llvm::UTF32 *ResultPtr = reinterpret_cast<llvm::UTF32*>(ResultBuf);
    *ResultPtr = UcnVal;
    ResultBuf += 4;
    return;
  }

  if (CharByteWidth == 2) {
    // FIXME: Make the type of the result buffer correct instead of
    // using reinterpret_cast.
    llvm::UTF16 *ResultPtr = reinterpret_cast<llvm::UTF16*>(ResultBuf);

    if (UcnVal <= (UTF32)0xFFFF) {
      *ResultPtr = UcnVal;
      ResultBuf += 2;
      return;
    }

    // Convert to UTF16.
    UcnVal -= 0x10000;
    *ResultPtr     = 0xD800 + (UcnVal >> 10);
    *(ResultPtr+1) = 0xDC00 + (UcnVal & 0x3FF);
    ResultBuf += 4;
    return;
  }

  assert(CharByteWidth == 1 && "UTF-8 encoding is only for 1 byte characters");

  // Now that we've parsed/checked the UCN, we convert from UTF32->UTF8.
  // The conversion below was inspired by:
  //   http://www.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.c
  // First, we determine how many bytes the result will require.
  typedef uint8_t UTF8;

  unsigned short bytesToWrite = 0;
  if (UcnVal < (UTF32)0x80)
    bytesToWrite = 1;
  else if (UcnVal < (UTF32)0x800)
    bytesToWrite = 2;
  else if (UcnVal < (UTF32)0x10000)
    bytesToWrite = 3;
  else
    bytesToWrite = 4;

  const unsigned byteMask = 0xBF;
  const unsigned byteMark = 0x80;

  // Once the bits are split out into bytes of UTF8, this is a mask OR-ed
  // into the first byte, depending on how many bytes follow.
  static const UTF8 firstByteMark[5] = {
    0x00, 0x00, 0xC0, 0xE0, 0xF0
  };
  // Finally, we write the bytes into ResultBuf.
  ResultBuf += bytesToWrite;
  switch (bytesToWrite) { // note: everything falls through.
  case 4:
    *--ResultBuf = (UTF8)((UcnVal | byteMark) & byteMask); UcnVal >>= 6;
    [[fallthrough]];
  case 3:
    *--ResultBuf = (UTF8)((UcnVal | byteMark) & byteMask); UcnVal >>= 6;
    [[fallthrough]];
  case 2:
    *--ResultBuf = (UTF8)((UcnVal | byteMark) & byteMask); UcnVal >>= 6;
    [[fallthrough]];
  case 1:
    *--ResultBuf = (UTF8) (UcnVal | firstByteMark[bytesToWrite]);
  }
  // Update the buffer.
  ResultBuf += bytesToWrite;
}

///       integer-constant: [C99 6.4.4.1]
///         decimal-constant integer-suffix
///         octal-constant integer-suffix
///         hexadecimal-constant integer-suffix
///         binary-literal integer-suffix [GNU, C++1y]
///       user-defined-integer-literal: [C++11 lex.ext]
///         decimal-literal ud-suffix
///         octal-literal ud-suffix
///         hexadecimal-literal ud-suffix
///         binary-literal ud-suffix [GNU, C++1y]
///       decimal-constant:
///         nonzero-digit
///         decimal-constant digit
///       octal-constant:
///         0
///         octal-constant octal-digit
///       hexadecimal-constant:
///         hexadecimal-prefix hexadecimal-digit
///         hexadecimal-constant hexadecimal-digit
///       hexadecimal-prefix: one of
///         0x 0X
///       binary-literal:
///         0b binary-digit
///         0B binary-digit
///         binary-literal binary-digit
///       integer-suffix:
///         unsigned-suffix [long-suffix]
///         unsigned-suffix [long-long-suffix]
///         long-suffix [unsigned-suffix]
///         long-long-suffix [unsigned-sufix]
///       nonzero-digit:
///         1 2 3 4 5 6 7 8 9
///       octal-digit:
///         0 1 2 3 4 5 6 7
///       hexadecimal-digit:
///         0 1 2 3 4 5 6 7 8 9
///         a b c d e f
///         A B C D E F
///       binary-digit:
///         0
///         1
///       unsigned-suffix: one of
///         u U
///       long-suffix: one of
///         l L
///       long-long-suffix: one of
///         ll LL
///
///       floating-constant: [C99 6.4.4.2]
///         TODO: add rules...
///
NumericLiteralParser::NumericLiteralParser(StringRef TokSpelling,
                                           SourceLocation TokLoc,
                                           const SourceManager &SM,
                                           const LangOptions &LangOpts,
                                           const TargetInfo &Target,
                                           DiagnosticsEngine &Diags)
    : SM(SM), LangOpts(LangOpts), Diags(Diags),
      ThisTokBegin(TokSpelling.begin()), ThisTokEnd(TokSpelling.end()) {

  s = DigitsBegin = ThisTokBegin;
  saw_exponent = false;
  saw_period = false;
  saw_ud_suffix = false;
  saw_fixed_point_suffix = false;
  isLong = false;
  isUnsigned = false;
  isLongLong = false;
  isSizeT = false;
  isHalf = false;
  isFloat = false;
  isImaginary = false;
  isFloat16 = false;
  isFloat128 = false;
  MicrosoftInteger = 0;
  isFract = false;
  isAccum = false;
  hadError = false;
  isBitInt = false;

  // This routine assumes that the range begin/end matches the regex for integer
  // and FP constants (specifically, the 'pp-number' regex), and assumes that
  // the byte at "*end" is both valid and not part of the regex.  Because of
  // this, it doesn't have to check for 'overscan' in various places.
  if (isPreprocessingNumberBody(*ThisTokEnd)) {
    Diags.Report(TokLoc, diag::err_lexing_numeric);
    hadError = true;
    return;
  }

  if (*s == '0') { // parse radix
    ParseNumberStartingWithZero(TokLoc);
    if (hadError)
      return;
  } else { // the first digit is non-zero
    radix = 10;
    s = SkipDigits(s);
    if (s == ThisTokEnd) {
      // Done.
    } else {
      ParseDecimalOrOctalCommon(TokLoc);
      if (hadError)
        return;
    }
  }

  SuffixBegin = s;
  checkSeparator(TokLoc, s, CSK_AfterDigits);

  // Initial scan to lookahead for fixed point suffix.
  if (LangOpts.FixedPoint) {
    for (const char *c = s; c != ThisTokEnd; ++c) {
      if (*c == 'r' || *c == 'k' || *c == 'R' || *c == 'K') {
        saw_fixed_point_suffix = true;
        break;
      }
    }
  }

  // Parse the suffix.  At this point we can classify whether we have an FP or
  // integer constant.
  bool isFixedPointConstant = isFixedPointLiteral();
  bool isFPConstant = isFloatingLiteral();
  bool HasSize = false;

  // Loop over all of the characters of the suffix.  If we see something bad,
  // we break out of the loop.
  for (; s != ThisTokEnd; ++s) {
    switch (*s) {
    case 'R':
    case 'r':
      if (!LangOpts.FixedPoint)
        break;
      if (isFract || isAccum) break;
      if (!(saw_period || saw_exponent)) break;
      isFract = true;
      continue;
    case 'K':
    case 'k':
      if (!LangOpts.FixedPoint)
        break;
      if (isFract || isAccum) break;
      if (!(saw_period || saw_exponent)) break;
      isAccum = true;
      continue;
    case 'h':      // FP Suffix for "half".
    case 'H':
      // OpenCL Extension v1.2 s9.5 - h or H suffix for half type.
      if (!(LangOpts.Half || LangOpts.FixedPoint))
        break;
      if (isIntegerLiteral()) break;  // Error for integer constant.
      if (HasSize)
        break;
      HasSize = true;
      isHalf = true;
      continue;  // Success.
    case 'f':      // FP Suffix for "float"
    case 'F':
      if (!isFPConstant) break;  // Error for integer constant.
      if (HasSize)
        break;
      HasSize = true;

      // CUDA host and device may have different _Float16 support, therefore
      // allows f16 literals to avoid false alarm.
      // When we compile for OpenMP target offloading on NVPTX, f16 suffix
      // should also be supported.
      // ToDo: more precise check for CUDA.
      // TODO: AMDGPU might also support it in the future.
      if ((Target.hasFloat16Type() || LangOpts.CUDA ||
           (LangOpts.OpenMPIsDevice && Target.getTriple().isNVPTX())) &&
          s + 2 < ThisTokEnd && s[1] == '1' && s[2] == '6') {
        s += 2; // success, eat up 2 characters.
        isFloat16 = true;
        continue;
      }

      isFloat = true;
      continue;  // Success.
    case 'q':    // FP Suffix for "__float128"
    case 'Q':
      if (!isFPConstant) break;  // Error for integer constant.
      if (HasSize)
        break;
      HasSize = true;
      isFloat128 = true;
      continue;  // Success.
    case 'u':
    case 'U':
      if (isFPConstant) break;  // Error for floating constant.
      if (isUnsigned) break;    // Cannot be repeated.
      isUnsigned = true;
      continue;  // Success.
    case 'l':
    case 'L':
      if (HasSize)
        break;
      HasSize = true;

      // Check for long long.  The L's need to be adjacent and the same case.
      if (s[1] == s[0]) {
        assert(s + 1 < ThisTokEnd && "didn't maximally munch?");
        if (isFPConstant) break;        // long long invalid for floats.
        isLongLong = true;
        ++s;  // Eat both of them.
      } else {
        isLong = true;
      }
      continue; // Success.
    case 'z':
    case 'Z':
      if (isFPConstant)
        break; // Invalid for floats.
      if (HasSize)
        break;
      HasSize = true;
      isSizeT = true;
      continue;
    case 'i':
    case 'I':
      if (LangOpts.MicrosoftExt && !isFPConstant) {
        // Allow i8, i16, i32, and i64. First, look ahead and check if
        // suffixes are Microsoft integers and not the imaginary unit.
        uint8_t Bits = 0;
        size_t ToSkip = 0;
        switch (s[1]) {
        case '8': // i8 suffix
          Bits = 8;
          ToSkip = 2;
          break;
        case '1':
          if (s[2] == '6') { // i16 suffix
            Bits = 16;
            ToSkip = 3;
          }
          break;
        case '3':
          if (s[2] == '2') { // i32 suffix
            Bits = 32;
            ToSkip = 3;
          }
          break;
        case '6':
          if (s[2] == '4') { // i64 suffix
            Bits = 64;
            ToSkip = 3;
          }
          break;
        default:
          break;
        }
        if (Bits) {
          if (HasSize)
            break;
          HasSize = true;
          MicrosoftInteger = Bits;
          s += ToSkip;
          assert(s <= ThisTokEnd && "didn't maximally munch?");
          break;
        }
      }
      [[fallthrough]];
    case 'j':
    case 'J':
      if (isImaginary) break;   // Cannot be repeated.
      isImaginary = true;
      continue;  // Success.
    case 'w':
    case 'W':
      if (isFPConstant)
        break; // Invalid for floats.
      if (HasSize)
        break; // Invalid if we already have a size for the literal.

      // wb and WB are allowed, but a mixture of cases like Wb or wB is not. We
      // explicitly do not support the suffix in C++ as an extension because a
      // library-based UDL that resolves to a library type may be more
      // appropriate there.
      if (!LangOpts.CPlusPlus && ((s[0] == 'w' && s[1] == 'b') ||
          (s[0] == 'W' && s[1] == 'B'))) {
        isBitInt = true;
        HasSize = true;
        ++s; // Skip both characters (2nd char skipped on continue).
        continue; // Success.
      }
    }
    // If we reached here, there was an error or a ud-suffix.
    break;
  }

  // "i", "if", and "il" are user-defined suffixes in C++1y.
  if (s != ThisTokEnd || isImaginary) {
    // FIXME: Don't bother expanding UCNs if !tok.hasUCN().
    expandUCNs(UDSuffixBuf, StringRef(SuffixBegin, ThisTokEnd - SuffixBegin));
    if (isValidUDSuffix(LangOpts, UDSuffixBuf)) {
      if (!isImaginary) {
        // Any suffix pieces we might have parsed are actually part of the
        // ud-suffix.
        isLong = false;
        isUnsigned = false;
        isLongLong = false;
        isSizeT = false;
        isFloat = false;
        isFloat16 = false;
        isHalf = false;
        isImaginary = false;
        isBitInt = false;
        MicrosoftInteger = 0;
        saw_fixed_point_suffix = false;
        isFract = false;
        isAccum = false;
      }

      saw_ud_suffix = true;
      return;
    }

    if (s != ThisTokEnd) {
      // Report an error if there are any.
      Diags.Report(Lexer::AdvanceToTokenCharacter(
                       TokLoc, SuffixBegin - ThisTokBegin, SM, LangOpts),
                   diag::err_invalid_suffix_constant)
          << StringRef(SuffixBegin, ThisTokEnd - SuffixBegin)
          << (isFixedPointConstant ? 2 : isFPConstant);
      hadError = true;
    }
  }

  if (!hadError && saw_fixed_point_suffix) {
    assert(isFract || isAccum);
  }
}

/// ParseDecimalOrOctalCommon - This method is called for decimal or octal
/// numbers. It issues an error for illegal digits, and handles floating point
/// parsing. If it detects a floating point number, the radix is set to 10.
void NumericLiteralParser::ParseDecimalOrOctalCommon(SourceLocation TokLoc){
  assert((radix == 8 || radix == 10) && "Unexpected radix");

  // If we have a hex digit other than 'e' (which denotes a FP exponent) then
  // the code is using an incorrect base.
  if (isHexDigit(*s) && *s != 'e' && *s != 'E' &&
      !isValidUDSuffix(LangOpts, StringRef(s, ThisTokEnd - s))) {
    Diags.Report(
        Lexer::AdvanceToTokenCharacter(TokLoc, s - ThisTokBegin, SM, LangOpts),
        diag::err_invalid_digit)
        << StringRef(s, 1) << (radix == 8 ? 1 : 0);
    hadError = true;
    return;
  }

  if (*s == '.') {
    checkSeparator(TokLoc, s, CSK_AfterDigits);
    s++;
    radix = 10;
    saw_period = true;
    checkSeparator(TokLoc, s, CSK_BeforeDigits);
    s = SkipDigits(s); // Skip suffix.
  }
  if (*s == 'e' || *s == 'E') { // exponent
    checkSeparator(TokLoc, s, CSK_AfterDigits);
    const char *Exponent = s;
    s++;
    radix = 10;
    saw_exponent = true;
    if (s != ThisTokEnd && (*s == '+' || *s == '-'))  s++; // sign
    const char *first_non_digit = SkipDigits(s);
    if (containsDigits(s, first_non_digit)) {
      checkSeparator(TokLoc, s, CSK_BeforeDigits);
      s = first_non_digit;
    } else {
      if (!hadError) {
        Diags.Report(Lexer::AdvanceToTokenCharacter(
                         TokLoc, Exponent - ThisTokBegin, SM, LangOpts),
                     diag::err_exponent_has_no_digits);
        hadError = true;
      }
      return;
    }
  }
}

/// Determine whether a suffix is a valid ud-suffix. We avoid treating reserved
/// suffixes as ud-suffixes, because the diagnostic experience is better if we
/// treat it as an invalid suffix.
bool NumericLiteralParser::isValidUDSuffix(const LangOptions &LangOpts,
                                           StringRef Suffix) {
  if (!LangOpts.CPlusPlus11 || Suffix.empty())
    return false;

  // By C++11 [lex.ext]p10, ud-suffixes starting with an '_' are always valid.
  if (Suffix[0] == '_')
    return true;

  // In C++11, there are no library suffixes.
  if (!LangOpts.CPlusPlus14)
    return false;

  // In C++14, "s", "h", "min", "ms", "us", and "ns" are used in the library.
  // Per tweaked N3660, "il", "i", and "if" are also used in the library.
  // In C++2a "d" and "y" are used in the library.
  return llvm::StringSwitch<bool>(Suffix)
      .Cases("h", "min", "s", true)
      .Cases("ms", "us", "ns", true)
      .Cases("il", "i", "if", true)
      .Cases("d", "y", LangOpts.CPlusPlus20)
      .Default(false);
}

void NumericLiteralParser::checkSeparator(SourceLocation TokLoc,
                                          const char *Pos,
                                          CheckSeparatorKind IsAfterDigits) {
  if (IsAfterDigits == CSK_AfterDigits) {
    if (Pos == ThisTokBegin)
      return;
    --Pos;
  } else if (Pos == ThisTokEnd)
    return;

  if (isDigitSeparator(*Pos)) {
    Diags.Report(Lexer::AdvanceToTokenCharacter(TokLoc, Pos - ThisTokBegin, SM,
                                                LangOpts),
                 diag::err_digit_separator_not_between_digits)
        << IsAfterDigits;
    hadError = true;
  }
}

/// ParseNumberStartingWithZero - This method is called when the first character
/// of the number is found to be a zero.  This means it is either an octal
/// number (like '04') or a hex number ('0x123a') a binary number ('0b1010') or
/// a floating point number (01239.123e4).  Eat the prefix, determining the
/// radix etc.
void NumericLiteralParser::ParseNumberStartingWithZero(SourceLocation TokLoc) {
  assert(s[0] == '0' && "Invalid method call");
  s++;

  int c1 = s[0];

  // Handle a hex number like 0x1234.
  if ((c1 == 'x' || c1 == 'X') && (isHexDigit(s[1]) || s[1] == '.')) {
    s++;
    assert(s < ThisTokEnd && "didn't maximally munch?");
    radix = 16;
    DigitsBegin = s;
    s = SkipHexDigits(s);
    bool HasSignificandDigits = containsDigits(DigitsBegin, s);
    if (s == ThisTokEnd) {
      // Done.
    } else if (*s == '.') {
      s++;
      saw_period = true;
      const char *floatDigitsBegin = s;
      s = SkipHexDigits(s);
      if (containsDigits(floatDigitsBegin, s))
        HasSignificandDigits = true;
      if (HasSignificandDigits)
        checkSeparator(TokLoc, floatDigitsBegin, CSK_BeforeDigits);
    }

    if (!HasSignificandDigits) {
      Diags.Report(Lexer::AdvanceToTokenCharacter(TokLoc, s - ThisTokBegin, SM,
                                                  LangOpts),
                   diag::err_hex_constant_requires)
          << LangOpts.CPlusPlus << 1;
      hadError = true;
      return;
    }

    // A binary exponent can appear with or with a '.'. If dotted, the
    // binary exponent is required.
    if (*s == 'p' || *s == 'P') {
      checkSeparator(TokLoc, s, CSK_AfterDigits);
      const char *Exponent = s;
      s++;
      saw_exponent = true;
      if (s != ThisTokEnd && (*s == '+' || *s == '-'))  s++; // sign
      const char *first_non_digit = SkipDigits(s);
      if (!containsDigits(s, first_non_digit)) {
        if (!hadError) {
          Diags.Report(Lexer::AdvanceToTokenCharacter(
                           TokLoc, Exponent - ThisTokBegin, SM, LangOpts),
                       diag::err_exponent_has_no_digits);
          hadError = true;
        }
        return;
      }
      checkSeparator(TokLoc, s, CSK_BeforeDigits);
      s = first_non_digit;

      if (!LangOpts.HexFloats)
        Diags.Report(TokLoc, LangOpts.CPlusPlus
                                 ? diag::ext_hex_literal_invalid
                                 : diag::ext_hex_constant_invalid);
      else if (LangOpts.CPlusPlus17)
        Diags.Report(TokLoc, diag::warn_cxx17_hex_literal);
    } else if (saw_period) {
      Diags.Report(Lexer::AdvanceToTokenCharacter(TokLoc, s - ThisTokBegin, SM,
                                                  LangOpts),
                   diag::err_hex_constant_requires)
          << LangOpts.CPlusPlus << 0;
      hadError = true;
    }
    return;
  }

  // Handle simple binary numbers 0b01010
  if ((c1 == 'b' || c1 == 'B') && (s[1] == '0' || s[1] == '1')) {
    // 0b101010 is a C++1y / GCC extension.
    Diags.Report(TokLoc, LangOpts.CPlusPlus14
                             ? diag::warn_cxx11_compat_binary_literal
                         : LangOpts.CPlusPlus ? diag::ext_binary_literal_cxx14
                                              : diag::ext_binary_literal);
    ++s;
    assert(s < ThisTokEnd && "didn't maximally munch?");
    radix = 2;
    DigitsBegin = s;
    s = SkipBinaryDigits(s);
    if (s == ThisTokEnd) {
      // Done.
    } else if (isHexDigit(*s) &&
               !isValidUDSuffix(LangOpts, StringRef(s, ThisTokEnd - s))) {
      Diags.Report(Lexer::AdvanceToTokenCharacter(TokLoc, s - ThisTokBegin, SM,
                                                  LangOpts),
                   diag::err_invalid_digit)
          << StringRef(s, 1) << 2;
      hadError = true;
    }
    // Other suffixes will be diagnosed by the caller.
    return;
  }

  // For now, the radix is set to 8. If we discover that we have a
  // floating point constant, the radix will change to 10. Octal floating
  // point constants are not permitted (only decimal and hexadecimal).
  radix = 8;
  const char *PossibleNewDigitStart = s;
  s = SkipOctalDigits(s);
  // When the value is 0 followed by a suffix (like 0wb), we want to leave 0
  // as the start of the digits. So if skipping octal digits does not skip
  // anything, we leave the digit start where it was.
  if (s != PossibleNewDigitStart)
    DigitsBegin = PossibleNewDigitStart;

  if (s == ThisTokEnd)
    return; // Done, simple octal number like 01234

  // If we have some other non-octal digit that *is* a decimal digit, see if
  // this is part of a floating point number like 094.123 or 09e1.
  if (isDigit(*s)) {
    const char *EndDecimal = SkipDigits(s);
    if (EndDecimal[0] == '.' || EndDecimal[0] == 'e' || EndDecimal[0] == 'E') {
      s = EndDecimal;
      radix = 10;
    }
  }

  ParseDecimalOrOctalCommon(TokLoc);
}

static bool alwaysFitsInto64Bits(unsigned Radix, unsigned NumDigits) {
  switch (Radix) {
  case 2:
    return NumDigits <= 64;
  case 8:
    return NumDigits <= 64 / 3; // Digits are groups of 3 bits.
  case 10:
    return NumDigits <= 19; // floor(log10(2^64))
  case 16:
    return NumDigits <= 64 / 4; // Digits are groups of 4 bits.
  default:
    llvm_unreachable("impossible Radix");
  }
}

/// GetIntegerValue - Convert this numeric literal value to an APInt that
/// matches Val's input width.  If there is an overflow, set Val to the low bits
/// of the result and return true.  Otherwise, return false.
bool NumericLiteralParser::GetIntegerValue(llvm::APInt &Val) {
  // Fast path: Compute a conservative bound on the maximum number of
  // bits per digit in this radix. If we can't possibly overflow a
  // uint64 based on that bound then do the simple conversion to
  // integer. This avoids the expensive overflow checking below, and
  // handles the common cases that matter (small decimal integers and
  // hex/octal values which don't overflow).
  const unsigned NumDigits = SuffixBegin - DigitsBegin;
  if (alwaysFitsInto64Bits(radix, NumDigits)) {
    uint64_t N = 0;
    for (const char *Ptr = DigitsBegin; Ptr != SuffixBegin; ++Ptr)
      if (!isDigitSeparator(*Ptr))
        N = N * radix + llvm::hexDigitValue(*Ptr);

    // This will truncate the value to Val's input width. Simply check
    // for overflow by comparing.
    Val = N;
    return Val.getZExtValue() != N;
  }

  Val = 0;
  const char *Ptr = DigitsBegin;

  llvm::APInt RadixVal(Val.getBitWidth(), radix);
  llvm::APInt CharVal(Val.getBitWidth(), 0);
  llvm::APInt OldVal = Val;

  bool OverflowOccurred = false;
  while (Ptr < SuffixBegin) {
    if (isDigitSeparator(*Ptr)) {
      ++Ptr;
      continue;
    }

    unsigned C = llvm::hexDigitValue(*Ptr++);

    // If this letter is out of bound for this radix, reject it.
    assert(C < radix && "NumericLiteralParser ctor should have rejected this");

    CharVal = C;

    // Add the digit to the value in the appropriate radix.  If adding in digits
    // made the value smaller, then this overflowed.
    OldVal = Val;

    // Multiply by radix, did overflow occur on the multiply?
    Val *= RadixVal;
    OverflowOccurred |= Val.udiv(RadixVal) != OldVal;

    // Add value, did overflow occur on the value?
    //   (a + b) ult b  <=> overflow
    Val += CharVal;
    OverflowOccurred |= Val.ult(CharVal);
  }
  return OverflowOccurred;
}

llvm::APFloat::opStatus
NumericLiteralParser::GetFloatValue(llvm::APFloat &Result) {
  using llvm::APFloat;

  unsigned n = std::min(SuffixBegin - ThisTokBegin, ThisTokEnd - ThisTokBegin);

  llvm::SmallString<16> Buffer;
  StringRef Str(ThisTokBegin, n);
  if (Str.contains('\'')) {
    Buffer.reserve(n);
    std::remove_copy_if(Str.begin(), Str.end(), std::back_inserter(Buffer),
                        &isDigitSeparator);
    Str = Buffer;
  }

  auto StatusOrErr =
      Result.convertFromString(Str, APFloat::rmNearestTiesToEven);
  assert(StatusOrErr && "Invalid floating point representation");
  return !errorToBool(StatusOrErr.takeError()) ? *StatusOrErr
                                               : APFloat::opInvalidOp;
}

static inline bool IsExponentPart(char c) {
  return c == 'p' || c == 'P' || c == 'e' || c == 'E';
}

bool NumericLiteralParser::GetFixedPointValue(llvm::APInt &StoreVal, unsigned Scale) {
  assert(radix == 16 || radix == 10);

  // Find how many digits are needed to store the whole literal.
  unsigned NumDigits = SuffixBegin - DigitsBegin;
  if (saw_period) --NumDigits;

  // Initial scan of the exponent if it exists
  bool ExpOverflowOccurred = false;
  bool NegativeExponent = false;
  const char *ExponentBegin;
  uint64_t Exponent = 0;
  int64_t BaseShift = 0;
  if (saw_exponent) {
    const char *Ptr = DigitsBegin;

    while (!IsExponentPart(*Ptr)) ++Ptr;
    ExponentBegin = Ptr;
    ++Ptr;
    NegativeExponent = *Ptr == '-';
    if (NegativeExponent) ++Ptr;

    unsigned NumExpDigits = SuffixBegin - Ptr;
    if (alwaysFitsInto64Bits(radix, NumExpDigits)) {
      llvm::StringRef ExpStr(Ptr, NumExpDigits);
      llvm::APInt ExpInt(/*numBits=*/64, ExpStr, /*radix=*/10);
      Exponent = ExpInt.getZExtValue();
    } else {
      ExpOverflowOccurred = true;
    }

    if (NegativeExponent) BaseShift -= Exponent;
    else BaseShift += Exponent;
  }

  // Number of bits needed for decimal literal is
  //   ceil(NumDigits * log2(10))       Integral part
  // + Scale                            Fractional part
  // + ceil(Exponent * log2(10))        Exponent
  // --------------------------------------------------
  //   ceil((NumDigits + Exponent) * log2(10)) + Scale
  //
  // But for simplicity in handling integers, we can round up log2(10) to 4,
  // making:
  // 4 * (NumDigits + Exponent) + Scale
  //
  // Number of digits needed for hexadecimal literal is
  //   4 * NumDigits                    Integral part
  // + Scale                            Fractional part
  // + Exponent                         Exponent
  // --------------------------------------------------
  //   (4 * NumDigits) + Scale + Exponent
  uint64_t NumBitsNeeded;
  if (radix == 10)
    NumBitsNeeded = 4 * (NumDigits + Exponent) + Scale;
  else
    NumBitsNeeded = 4 * NumDigits + Exponent + Scale;

  if (NumBitsNeeded > std::numeric_limits<unsigned>::max())
    ExpOverflowOccurred = true;
  llvm::APInt Val(static_cast<unsigned>(NumBitsNeeded), 0, /*isSigned=*/false);

  bool FoundDecimal = false;

  int64_t FractBaseShift = 0;
  const char *End = saw_exponent ? ExponentBegin : SuffixBegin;
  for (const char *Ptr = DigitsBegin; Ptr < End; ++Ptr) {
    if (*Ptr == '.') {
      FoundDecimal = true;
      continue;
    }

    // Normal reading of an integer
    unsigned C = llvm::hexDigitValue(*Ptr);
    assert(C < radix && "NumericLiteralParser ctor should have rejected this");

    Val *= radix;
    Val += C;

    if (FoundDecimal)
      // Keep track of how much we will need to adjust this value by from the
      // number of digits past the radix point.
      --FractBaseShift;
  }

  // For a radix of 16, we will be multiplying by 2 instead of 16.
  if (radix == 16) FractBaseShift *= 4;
  BaseShift += FractBaseShift;

  Val <<= Scale;

  uint64_t Base = (radix == 16) ? 2 : 10;
  if (BaseShift > 0) {
    for (int64_t i = 0; i < BaseShift; ++i) {
      Val *= Base;
    }
  } else if (BaseShift < 0) {
    for (int64_t i = BaseShift; i < 0 && !Val.isZero(); ++i)
      Val = Val.udiv(Base);
  }

  bool IntOverflowOccurred = false;
  auto MaxVal = llvm::APInt::getMaxValue(StoreVal.getBitWidth());
  if (Val.getBitWidth() > StoreVal.getBitWidth()) {
    IntOverflowOccurred |= Val.ugt(MaxVal.zext(Val.getBitWidth()));
    StoreVal = Val.trunc(StoreVal.getBitWidth());
  } else if (Val.getBitWidth() < StoreVal.getBitWidth()) {
    IntOverflowOccurred |= Val.zext(MaxVal.getBitWidth()).ugt(MaxVal);
    StoreVal = Val.zext(StoreVal.getBitWidth());
  } else {
    StoreVal = Val;
  }

  return IntOverflowOccurred || ExpOverflowOccurred;
}

/// \verbatim
///       user-defined-character-literal: [C++11 lex.ext]
///         character-literal ud-suffix
///       ud-suffix:
///         identifier
///       character-literal: [C++11 lex.ccon]
///         ' c-char-sequence '
///         u' c-char-sequence '
///         U' c-char-sequence '
///         L' c-char-sequence '
///         u8' c-char-sequence ' [C++1z lex.ccon]
///       c-char-sequence:
///         c-char
///         c-char-sequence c-char
///       c-char:
///         any member of the source character set except the single-quote ',
///           backslash \, or new-line character
///         escape-sequence
///         universal-character-name
///       escape-sequence:
///         simple-escape-sequence
///         octal-escape-sequence
///         hexadecimal-escape-sequence
///       simple-escape-sequence:
///         one of \' \" \? \\ \a \b \f \n \r \t \v
///       octal-escape-sequence:
///         \ octal-digit
///         \ octal-digit octal-digit
///         \ octal-digit octal-digit octal-digit
///       hexadecimal-escape-sequence:
///         \x hexadecimal-digit
///         hexadecimal-escape-sequence hexadecimal-digit
///       universal-character-name: [C++11 lex.charset]
///         \u hex-quad
///         \U hex-quad hex-quad
///       hex-quad:
///         hex-digit hex-digit hex-digit hex-digit
/// \endverbatim
///
CharLiteralParser::CharLiteralParser(const char *begin, const char *end,
                                     SourceLocation Loc, Preprocessor &PP,
                                     tok::TokenKind kind) {
  // At this point we know that the character matches the regex "(L|u|U)?'.*'".
  HadError = false;

  Kind = kind;

  const char *TokBegin = begin;

  // Skip over wide character determinant.
  if (Kind != tok::char_constant)
    ++begin;
  if (Kind == tok::utf8_char_constant)
    ++begin;

  // Skip over the entry quote.
  if (begin[0] != '\'') {
    PP.Diag(Loc, diag::err_lexing_char);
    HadError = true;
    return;
  }

  ++begin;

  // Remove an optional ud-suffix.
  if (end[-1] != '\'') {
    const char *UDSuffixEnd = end;
    do {
      --end;
    } while (end[-1] != '\'');
    // FIXME: Don't bother with this if !tok.hasUCN().
    expandUCNs(UDSuffixBuf, StringRef(end, UDSuffixEnd - end));
    UDSuffixOffset = end - TokBegin;
  }

  // Trim the ending quote.
  assert(end != begin && "Invalid token lexed");
  --end;

  // FIXME: The "Value" is an uint64_t so we can handle char literals of
  // up to 64-bits.
  // FIXME: This extensively assumes that 'char' is 8-bits.
  assert(PP.getTargetInfo().getCharWidth() == 8 &&
         "Assumes char is 8 bits");
  assert(PP.getTargetInfo().getIntWidth() <= 64 &&
         (PP.getTargetInfo().getIntWidth() & 7) == 0 &&
         "Assumes sizeof(int) on target is <= 64 and a multiple of char");
  assert(PP.getTargetInfo().getWCharWidth() <= 64 &&
         "Assumes sizeof(wchar) on target is <= 64");

  SmallVector<uint32_t, 4> codepoint_buffer;
  codepoint_buffer.resize(end - begin);
  uint32_t *buffer_begin = &codepoint_buffer.front();
  uint32_t *buffer_end = buffer_begin + codepoint_buffer.size();

  // Unicode escapes representing characters that cannot be correctly
  // represented in a single code unit are disallowed in character literals
  // by this implementation.
  uint32_t largest_character_for_kind;
  if (tok::wide_char_constant == Kind) {
    largest_character_for_kind =
        0xFFFFFFFFu >> (32-PP.getTargetInfo().getWCharWidth());
  } else if (tok::utf8_char_constant == Kind) {
    largest_character_for_kind = 0x7F;
  } else if (tok::utf16_char_constant == Kind) {
    largest_character_for_kind = 0xFFFF;
  } else if (tok::utf32_char_constant == Kind) {
    largest_character_for_kind = 0x10FFFF;
  } else {
    largest_character_for_kind = 0x7Fu;
  }

  while (begin != end) {
    // Is this a span of non-escape characters?
    if (begin[0] != '\\') {
      char const *start = begin;
      do {
        ++begin;
      } while (begin != end && *begin != '\\');

      char const *tmp_in_start = start;
      uint32_t *tmp_out_start = buffer_begin;
      llvm::ConversionResult res =
          llvm::ConvertUTF8toUTF32(reinterpret_cast<llvm::UTF8 const **>(&start),
                             reinterpret_cast<llvm::UTF8 const *>(begin),
                             &buffer_begin, buffer_end, llvm::strictConversion);
      if (res != llvm::conversionOK) {
        // If we see bad encoding for unprefixed character literals, warn and
        // simply copy the byte values, for compatibility with gcc and
        // older versions of clang.
        bool NoErrorOnBadEncoding = isOrdinary();
        unsigned Msg = diag::err_bad_character_encoding;
        if (NoErrorOnBadEncoding)
          Msg = diag::warn_bad_character_encoding;
        PP.Diag(Loc, Msg);
        if (NoErrorOnBadEncoding) {
          start = tmp_in_start;
          buffer_begin = tmp_out_start;
          for (; start != begin; ++start, ++buffer_begin)
            *buffer_begin = static_cast<uint8_t>(*start);
        } else {
          HadError = true;
        }
      } else {
        for (; tmp_out_start < buffer_begin; ++tmp_out_start) {
          if (*tmp_out_start > largest_character_for_kind) {
            HadError = true;
            PP.Diag(Loc, diag::err_character_too_large);
          }
        }
      }

      continue;
    }
    // Is this a Universal Character Name escape?
    if (begin[1] == 'u' || begin[1] == 'U' || begin[1] == 'N') {
      unsigned short UcnLen = 0;
      if (!ProcessUCNEscape(TokBegin, begin, end, *buffer_begin, UcnLen,
                            FullSourceLoc(Loc, PP.getSourceManager()),
                            &PP.getDiagnostics(), PP.getLangOpts(), true)) {
        HadError = true;
      } else if (*buffer_begin > largest_character_for_kind) {
        HadError = true;
        PP.Diag(Loc, diag::err_character_too_large);
      }

      ++buffer_begin;
      continue;
    }
    unsigned CharWidth = getCharWidth(Kind, PP.getTargetInfo());
    uint64_t result =
      ProcessCharEscape(TokBegin, begin, end, HadError,
                        FullSourceLoc(Loc,PP.getSourceManager()),
                        CharWidth, &PP.getDiagnostics(), PP.getLangOpts());
    *buffer_begin++ = result;
  }

  unsigned NumCharsSoFar = buffer_begin - &codepoint_buffer.front();

  if (NumCharsSoFar > 1) {
    if (isOrdinary() && NumCharsSoFar == 4)
      PP.Diag(Loc, diag::warn_four_char_character_literal);
    else if (isOrdinary())
      PP.Diag(Loc, diag::warn_multichar_character_literal);
    else {
      PP.Diag(Loc, diag::err_multichar_character_literal) << (isWide() ? 0 : 1);
      HadError = true;
    }
    IsMultiChar = true;
  } else {
    IsMultiChar = false;
  }

  llvm::APInt LitVal(PP.getTargetInfo().getIntWidth(), 0);

  // Narrow character literals act as though their value is concatenated
  // in this implementation, but warn on overflow.
  bool multi_char_too_long = false;
  if (isOrdinary() && isMultiChar()) {
    LitVal = 0;
    for (size_t i = 0; i < NumCharsSoFar; ++i) {
      // check for enough leading zeros to shift into
      multi_char_too_long |= (LitVal.countLeadingZeros() < 8);
      LitVal <<= 8;
      LitVal = LitVal + (codepoint_buffer[i] & 0xFF);
    }
  } else if (NumCharsSoFar > 0) {
    // otherwise just take the last character
    LitVal = buffer_begin[-1];
  }

  if (!HadError && multi_char_too_long) {
    PP.Diag(Loc, diag::warn_char_constant_too_large);
  }

  // Transfer the value from APInt to uint64_t
  Value = LitVal.getZExtValue();

  // If this is a single narrow character, sign extend it (e.g. '\xFF' is "-1")
  // if 'char' is signed for this target (C99 6.4.4.4p10).  Note that multiple
  // character constants are not sign extended in the this implementation:
  // '\xFF\xFF' = 65536 and '\x0\xFF' = 255, which matches GCC.
  if (isOrdinary() && NumCharsSoFar == 1 && (Value & 128) &&
      PP.getLangOpts().CharIsSigned)
    Value = (signed char)Value;
}

/// \verbatim
///       string-literal: [C++0x lex.string]
///         encoding-prefix " [s-char-sequence] "
///         encoding-prefix R raw-string
///       encoding-prefix:
///         u8
///         u
///         U
///         L
///       s-char-sequence:
///         s-char
///         s-char-sequence s-char
///       s-char:
///         any member of the source character set except the double-quote ",
///           backslash \, or new-line character
///         escape-sequence
///         universal-character-name
///       raw-string:
///         " d-char-sequence ( r-char-sequence ) d-char-sequence "
///       r-char-sequence:
///         r-char
///         r-char-sequence r-char
///       r-char:
///         any member of the source character set, except a right parenthesis )
///           followed by the initial d-char-sequence (which may be empty)
///           followed by a double quote ".
///       d-char-sequence:
///         d-char
///         d-char-sequence d-char
///       d-char:
///         any member of the basic source character set except:
///           space, the left parenthesis (, the right parenthesis ),
///           the backslash \, and the control characters representing horizontal
///           tab, vertical tab, form feed, and newline.
///       escape-sequence: [C++0x lex.ccon]
///         simple-escape-sequence
///         octal-escape-sequence
///         hexadecimal-escape-sequence
///       simple-escape-sequence:
///         one of \' \" \? \\ \a \b \f \n \r \t \v
///       octal-escape-sequence:
///         \ octal-digit
///         \ octal-digit octal-digit
///         \ octal-digit octal-digit octal-digit
///       hexadecimal-escape-sequence:
///         \x hexadecimal-digit
///         hexadecimal-escape-sequence hexadecimal-digit
///       universal-character-name:
///         \u hex-quad
///         \U hex-quad hex-quad
///       hex-quad:
///         hex-digit hex-digit hex-digit hex-digit
/// \endverbatim
///
StringLiteralParser::
StringLiteralParser(ArrayRef<Token> StringToks,
                    Preprocessor &PP)
  : SM(PP.getSourceManager()), Features(PP.getLangOpts()),
    Target(PP.getTargetInfo()), Diags(&PP.getDiagnostics()),
    MaxTokenLength(0), SizeBound(0), CharByteWidth(0), Kind(tok::unknown),
    ResultPtr(ResultBuf.data()), hadError(false), Pascal(false) {
  init(StringToks);
}

void StringLiteralParser::init(ArrayRef<Token> StringToks){
  // The literal token may have come from an invalid source location (e.g. due
  // to a PCH error), in which case the token length will be 0.
  if (StringToks.empty() || StringToks[0].getLength() < 2)
    return DiagnoseLexingError(SourceLocation());

  // Scan all of the string portions, remember the max individual token length,
  // computing a bound on the concatenated string length, and see whether any
  // piece is a wide-string.  If any of the string portions is a wide-string
  // literal, the result is a wide-string literal [C99 6.4.5p4].
  assert(!StringToks.empty() && "expected at least one token");
  MaxTokenLength = StringToks[0].getLength();
  assert(StringToks[0].getLength() >= 2 && "literal token is invalid!");
  SizeBound = StringToks[0].getLength()-2;  // -2 for "".
  Kind = StringToks[0].getKind();

  hadError = false;

  // Implement Translation Phase #6: concatenation of string literals
  /// (C99 5.1.1.2p1).  The common case is only one string fragment.
  for (unsigned i = 1; i != StringToks.size(); ++i) {
    if (StringToks[i].getLength() < 2)
      return DiagnoseLexingError(StringToks[i].getLocation());

    // The string could be shorter than this if it needs cleaning, but this is a
    // reasonable bound, which is all we need.
    assert(StringToks[i].getLength() >= 2 && "literal token is invalid!");
    SizeBound += StringToks[i].getLength()-2;  // -2 for "".

    // Remember maximum string piece length.
    if (StringToks[i].getLength() > MaxTokenLength)
      MaxTokenLength = StringToks[i].getLength();

    // Remember if we see any wide or utf-8/16/32 strings.
    // Also check for illegal concatenations.
    if (StringToks[i].isNot(Kind) && StringToks[i].isNot(tok::string_literal)) {
      if (isOrdinary()) {
        Kind = StringToks[i].getKind();
      } else {
        if (Diags)
          Diags->Report(StringToks[i].getLocation(),
                        diag::err_unsupported_string_concat);
        hadError = true;
      }
    }
  }

  // Include space for the null terminator.
  ++SizeBound;

  // TODO: K&R warning: "traditional C rejects string constant concatenation"

  // Get the width in bytes of char/wchar_t/char16_t/char32_t
  CharByteWidth = getCharWidth(Kind, Target);
  assert((CharByteWidth & 7) == 0 && "Assumes character size is byte multiple");
  CharByteWidth /= 8;

  // The output buffer size needs to be large enough to hold wide characters.
  // This is a worst-case assumption which basically corresponds to L"" "long".
  SizeBound *= CharByteWidth;

  // Size the temporary buffer to hold the result string data.
  ResultBuf.resize(SizeBound);

  // Likewise, but for each string piece.
  SmallString<512> TokenBuf;
  TokenBuf.resize(MaxTokenLength);

  // Loop over all the strings, getting their spelling, and expanding them to
  // wide strings as appropriate.
  ResultPtr = &ResultBuf[0];   // Next byte to fill in.

  Pascal = false;

  SourceLocation UDSuffixTokLoc;

  for (unsigned i = 0, e = StringToks.size(); i != e; ++i) {
    const char *ThisTokBuf = &TokenBuf[0];
    // Get the spelling of the token, which eliminates trigraphs, etc.  We know
    // that ThisTokBuf points to a buffer that is big enough for the whole token
    // and 'spelled' tokens can only shrink.
    bool StringInvalid = false;
    unsigned ThisTokLen =
      Lexer::getSpelling(StringToks[i], ThisTokBuf, SM, Features,
                         &StringInvalid);
    if (StringInvalid)
      return DiagnoseLexingError(StringToks[i].getLocation());

    const char *ThisTokBegin = ThisTokBuf;
    const char *ThisTokEnd = ThisTokBuf+ThisTokLen;

    // Remove an optional ud-suffix.
    if (ThisTokEnd[-1] != '"') {
      const char *UDSuffixEnd = ThisTokEnd;
      do {
        --ThisTokEnd;
      } while (ThisTokEnd[-1] != '"');

      StringRef UDSuffix(ThisTokEnd, UDSuffixEnd - ThisTokEnd);

      if (UDSuffixBuf.empty()) {
        if (StringToks[i].hasUCN())
          expandUCNs(UDSuffixBuf, UDSuffix);
        else
          UDSuffixBuf.assign(UDSuffix);
        UDSuffixToken = i;
        UDSuffixOffset = ThisTokEnd - ThisTokBuf;
        UDSuffixTokLoc = StringToks[i].getLocation();
      } else {
        SmallString<32> ExpandedUDSuffix;
        if (StringToks[i].hasUCN()) {
          expandUCNs(ExpandedUDSuffix, UDSuffix);
          UDSuffix = ExpandedUDSuffix;
        }

        // C++11 [lex.ext]p8: At the end of phase 6, if a string literal is the
        // result of a concatenation involving at least one user-defined-string-
        // literal, all the participating user-defined-string-literals shall
        // have the same ud-suffix.
        if (UDSuffixBuf != UDSuffix) {
          if (Diags) {
            SourceLocation TokLoc = StringToks[i].getLocation();
            Diags->Report(TokLoc, diag::err_string_concat_mixed_suffix)
              << UDSuffixBuf << UDSuffix
              << SourceRange(UDSuffixTokLoc, UDSuffixTokLoc)
              << SourceRange(TokLoc, TokLoc);
          }
          hadError = true;
        }
      }
    }

    // Strip the end quote.
    --ThisTokEnd;

    // TODO: Input character set mapping support.

    // Skip marker for wide or unicode strings.
    if (ThisTokBuf[0] == 'L' || ThisTokBuf[0] == 'u' || ThisTokBuf[0] == 'U') {
      ++ThisTokBuf;
      // Skip 8 of u8 marker for utf8 strings.
      if (ThisTokBuf[0] == '8')
        ++ThisTokBuf;
    }

    // Check for raw string
    if (ThisTokBuf[0] == 'R') {
      if (ThisTokBuf[1] != '"') {
        // The file may have come from PCH and then changed after loading the
        // PCH; Fail gracefully.
        return DiagnoseLexingError(StringToks[i].getLocation());
      }
      ThisTokBuf += 2; // skip R"

      // C++11 [lex.string]p2: A `d-char-sequence` shall consist of at most 16
      // characters.
      constexpr unsigned MaxRawStrDelimLen = 16;

      const char *Prefix = ThisTokBuf;
      while (static_cast<unsigned>(ThisTokBuf - Prefix) < MaxRawStrDelimLen &&
             ThisTokBuf[0] != '(')
        ++ThisTokBuf;
      if (ThisTokBuf[0] != '(')
        return DiagnoseLexingError(StringToks[i].getLocation());
      ++ThisTokBuf; // skip '('

      // Remove same number of characters from the end
      ThisTokEnd -= ThisTokBuf - Prefix;
      if (ThisTokEnd < ThisTokBuf)
        return DiagnoseLexingError(StringToks[i].getLocation());

      // C++14 [lex.string]p4: A source-file new-line in a raw string literal
      // results in a new-line in the resulting execution string-literal.
      StringRef RemainingTokenSpan(ThisTokBuf, ThisTokEnd - ThisTokBuf);
      while (!RemainingTokenSpan.empty()) {
        // Split the string literal on \r\n boundaries.
        size_t CRLFPos = RemainingTokenSpan.find("\r\n");
        StringRef BeforeCRLF = RemainingTokenSpan.substr(0, CRLFPos);
        StringRef AfterCRLF = RemainingTokenSpan.substr(CRLFPos);

        // Copy everything before the \r\n sequence into the string literal.
        if (CopyStringFragment(StringToks[i], ThisTokBegin, BeforeCRLF))
          hadError = true;

        // Point into the \n inside the \r\n sequence and operate on the
        // remaining portion of the literal.
        RemainingTokenSpan = AfterCRLF.substr(1);
      }
    } else {
      if (ThisTokBuf[0] != '"') {
        // The file may have come from PCH and then changed after loading the
        // PCH; Fail gracefully.
        return DiagnoseLexingError(StringToks[i].getLocation());
      }
      ++ThisTokBuf; // skip "

      // Check if this is a pascal string
      if (Features.PascalStrings && ThisTokBuf + 1 != ThisTokEnd &&
          ThisTokBuf[0] == '\\' && ThisTokBuf[1] == 'p') {

        // If the \p sequence is found in the first token, we have a pascal string
        // Otherwise, if we already have a pascal string, ignore the first \p
        if (i == 0) {
          ++ThisTokBuf;
          Pascal = true;
        } else if (Pascal)
          ThisTokBuf += 2;
      }

      while (ThisTokBuf != ThisTokEnd) {
        // Is this a span of non-escape characters?
        if (ThisTokBuf[0] != '\\') {
          const char *InStart = ThisTokBuf;
          do {
            ++ThisTokBuf;
          } while (ThisTokBuf != ThisTokEnd && ThisTokBuf[0] != '\\');

          // Copy the character span over.
          if (CopyStringFragment(StringToks[i], ThisTokBegin,
                                 StringRef(InStart, ThisTokBuf - InStart)))
            hadError = true;
          continue;
        }
        // Is this a Universal Character Name escape?
        if (ThisTokBuf[1] == 'u' || ThisTokBuf[1] == 'U' ||
            ThisTokBuf[1] == 'N') {
          EncodeUCNEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd,
                          ResultPtr, hadError,
                          FullSourceLoc(StringToks[i].getLocation(), SM),
                          CharByteWidth, Diags, Features);
          continue;
        }
        // Otherwise, this is a non-UCN escape character.  Process it.
        unsigned ResultChar =
          ProcessCharEscape(ThisTokBegin, ThisTokBuf, ThisTokEnd, hadError,
                            FullSourceLoc(StringToks[i].getLocation(), SM),
                            CharByteWidth*8, Diags, Features);

        if (CharByteWidth == 4) {
          // FIXME: Make the type of the result buffer correct instead of
          // using reinterpret_cast.
          llvm::UTF32 *ResultWidePtr = reinterpret_cast<llvm::UTF32*>(ResultPtr);
          *ResultWidePtr = ResultChar;
          ResultPtr += 4;
        } else if (CharByteWidth == 2) {
          // FIXME: Make the type of the result buffer correct instead of
          // using reinterpret_cast.
          llvm::UTF16 *ResultWidePtr = reinterpret_cast<llvm::UTF16*>(ResultPtr);
          *ResultWidePtr = ResultChar & 0xFFFF;
          ResultPtr += 2;
        } else {
          assert(CharByteWidth == 1 && "Unexpected char width");
          *ResultPtr++ = ResultChar & 0xFF;
        }
      }
    }
  }

  if (Pascal) {
    if (CharByteWidth == 4) {
      // FIXME: Make the type of the result buffer correct instead of
      // using reinterpret_cast.
      llvm::UTF32 *ResultWidePtr = reinterpret_cast<llvm::UTF32*>(ResultBuf.data());
      ResultWidePtr[0] = GetNumStringChars() - 1;
    } else if (CharByteWidth == 2) {
      // FIXME: Make the type of the result buffer correct instead of
      // using reinterpret_cast.
      llvm::UTF16 *ResultWidePtr = reinterpret_cast<llvm::UTF16*>(ResultBuf.data());
      ResultWidePtr[0] = GetNumStringChars() - 1;
    } else {
      assert(CharByteWidth == 1 && "Unexpected char width");
      ResultBuf[0] = GetNumStringChars() - 1;
    }

    // Verify that pascal strings aren't too large.
    if (GetStringLength() > 256) {
      if (Diags)
        Diags->Report(StringToks.front().getLocation(),
                      diag::err_pascal_string_too_long)
          << SourceRange(StringToks.front().getLocation(),
                         StringToks.back().getLocation());
      hadError = true;
      return;
    }
  } else if (Diags) {
    // Complain if this string literal has too many characters.
    unsigned MaxChars = Features.CPlusPlus? 65536 : Features.C99 ? 4095 : 509;

    if (GetNumStringChars() > MaxChars)
      Diags->Report(StringToks.front().getLocation(),
                    diag::ext_string_too_long)
        << GetNumStringChars() << MaxChars
        << (Features.CPlusPlus ? 2 : Features.C99 ? 1 : 0)
        << SourceRange(StringToks.front().getLocation(),
                       StringToks.back().getLocation());
  }
}

static const char *resyncUTF8(const char *Err, const char *End) {
  if (Err == End)
    return End;
  End = Err + std::min<unsigned>(llvm::getNumBytesForUTF8(*Err), End-Err);
  while (++Err != End && (*Err & 0xC0) == 0x80)
    ;
  return Err;
}

/// This function copies from Fragment, which is a sequence of bytes
/// within Tok's contents (which begin at TokBegin) into ResultPtr.
/// Performs widening for multi-byte characters.
bool StringLiteralParser::CopyStringFragment(const Token &Tok,
                                             const char *TokBegin,
                                             StringRef Fragment) {
  const llvm::UTF8 *ErrorPtrTmp;
  if (ConvertUTF8toWide(CharByteWidth, Fragment, ResultPtr, ErrorPtrTmp))
    return false;

  // If we see bad encoding for unprefixed string literals, warn and
  // simply copy the byte values, for compatibility with gcc and older
  // versions of clang.
  bool NoErrorOnBadEncoding = isOrdinary();
  if (NoErrorOnBadEncoding) {
    memcpy(ResultPtr, Fragment.data(), Fragment.size());
    ResultPtr += Fragment.size();
  }

  if (Diags) {
    const char *ErrorPtr = reinterpret_cast<const char *>(ErrorPtrTmp);

    FullSourceLoc SourceLoc(Tok.getLocation(), SM);
    const DiagnosticBuilder &Builder =
      Diag(Diags, Features, SourceLoc, TokBegin,
           ErrorPtr, resyncUTF8(ErrorPtr, Fragment.end()),
           NoErrorOnBadEncoding ? diag::warn_bad_string_encoding
                                : diag::err_bad_string_encoding);

    const char *NextStart = resyncUTF8(ErrorPtr, Fragment.end());
    StringRef NextFragment(NextStart, Fragment.end()-NextStart);

    // Decode into a dummy buffer.
    SmallString<512> Dummy;
    Dummy.reserve(Fragment.size() * CharByteWidth);
    char *Ptr = Dummy.data();

    while (!ConvertUTF8toWide(CharByteWidth, NextFragment, Ptr, ErrorPtrTmp)) {
      const char *ErrorPtr = reinterpret_cast<const char *>(ErrorPtrTmp);
      NextStart = resyncUTF8(ErrorPtr, Fragment.end());
      Builder << MakeCharSourceRange(Features, SourceLoc, TokBegin,
                                     ErrorPtr, NextStart);
      NextFragment = StringRef(NextStart, Fragment.end()-NextStart);
    }
  }
  return !NoErrorOnBadEncoding;
}

void StringLiteralParser::DiagnoseLexingError(SourceLocation Loc) {
  hadError = true;
  if (Diags)
    Diags->Report(Loc, diag::err_lexing_string);
}

/// getOffsetOfStringByte - This function returns the offset of the
/// specified byte of the string data represented by Token.  This handles
/// advancing over escape sequences in the string.
unsigned StringLiteralParser::getOffsetOfStringByte(const Token &Tok,
                                                    unsigned ByteNo) const {
  // Get the spelling of the token.
  SmallString<32> SpellingBuffer;
  SpellingBuffer.resize(Tok.getLength());

  bool StringInvalid = false;
  const char *SpellingPtr = &SpellingBuffer[0];
  unsigned TokLen = Lexer::getSpelling(Tok, SpellingPtr, SM, Features,
                                       &StringInvalid);
  if (StringInvalid)
    return 0;

  const char *SpellingStart = SpellingPtr;
  const char *SpellingEnd = SpellingPtr+TokLen;

  // Handle UTF-8 strings just like narrow strings.
  if (SpellingPtr[0] == 'u' && SpellingPtr[1] == '8')
    SpellingPtr += 2;

  assert(SpellingPtr[0] != 'L' && SpellingPtr[0] != 'u' &&
         SpellingPtr[0] != 'U' && "Doesn't handle wide or utf strings yet");

  // For raw string literals, this is easy.
  if (SpellingPtr[0] == 'R') {
    assert(SpellingPtr[1] == '"' && "Should be a raw string literal!");
    // Skip 'R"'.
    SpellingPtr += 2;
    while (*SpellingPtr != '(') {
      ++SpellingPtr;
      assert(SpellingPtr < SpellingEnd && "Missing ( for raw string literal");
    }
    // Skip '('.
    ++SpellingPtr;
    return SpellingPtr - SpellingStart + ByteNo;
  }

  // Skip over the leading quote
  assert(SpellingPtr[0] == '"' && "Should be a string literal!");
  ++SpellingPtr;

  // Skip over bytes until we find the offset we're looking for.
  while (ByteNo) {
    assert(SpellingPtr < SpellingEnd && "Didn't find byte offset!");

    // Step over non-escapes simply.
    if (*SpellingPtr != '\\') {
      ++SpellingPtr;
      --ByteNo;
      continue;
    }

    // Otherwise, this is an escape character.  Advance over it.
    bool HadError = false;
    if (SpellingPtr[1] == 'u' || SpellingPtr[1] == 'U' ||
        SpellingPtr[1] == 'N') {
      const char *EscapePtr = SpellingPtr;
      unsigned Len = MeasureUCNEscape(SpellingStart, SpellingPtr, SpellingEnd,
                                      1, Features, HadError);
      if (Len > ByteNo) {
        // ByteNo is somewhere within the escape sequence.
        SpellingPtr = EscapePtr;
        break;
      }
      ByteNo -= Len;
    } else {
      ProcessCharEscape(SpellingStart, SpellingPtr, SpellingEnd, HadError,
                        FullSourceLoc(Tok.getLocation(), SM),
                        CharByteWidth*8, Diags, Features);
      --ByteNo;
    }
    assert(!HadError && "This method isn't valid on erroneous strings");
  }

  return SpellingPtr-SpellingStart;
}

/// Determine whether a suffix is a valid ud-suffix. We avoid treating reserved
/// suffixes as ud-suffixes, because the diagnostic experience is better if we
/// treat it as an invalid suffix.
bool StringLiteralParser::isValidUDSuffix(const LangOptions &LangOpts,
                                          StringRef Suffix) {
  return NumericLiteralParser::isValidUDSuffix(LangOpts, Suffix) ||
         Suffix == "sv";
}