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
|
/*
* iconv library implemented with Win32 API.
*
* This file is placed in the public domain.
*
* Maintainer: Yukihiro Nakadaira <yukihiro.nakadaira@gmail.com>
*
* If $WINICONV_LIBICONV_DLL environment variable was defined, win_iconv
* loads the specified DLL dynamically and uses it. If loading the DLL
* or iconv_open() failed, falls back to internal conversion.
* $WINICONV_LIBICONV_DLL is a comma separated list. The first loadable
* DLL is used. The specified DLL should have iconv_open(),
* iconv_close() and iconv() functions. Or these functions can be
* libiconv_open(), libiconv_close() and libiconv().
*
* Win32 API does not support strict encoding conversion for some
* codepage. And MLang function drop or replace invalid bytes and does
* not return useful error status as iconv. This implementation cannot
* be used for encoding validation purpose.
*/
/* for WC_NO_BEST_FIT_CHARS */
#ifndef WINVER
# define WINVER 0x0500
#endif
#define STRICT
#include <windows.h>
#include <errno.h>
#include <string.h>
#include <stdlib.h>
#if 0
# define MAKE_EXE
# define MAKE_DLL
# define USE_LIBICONV_DLL
#endif
#if !defined(DEFAULT_LIBICONV_DLL)
# define DEFAULT_LIBICONV_DLL ""
#endif
#define MB_CHAR_MAX 16
#define UNICODE_MODE_BOM_DONE 1
#define UNICODE_MODE_SWAPPED 2
#define FLAG_USE_BOM_ENDIAN 1
#define FLAG_TRANSLIT 2 /* //TRANSLIT */
#define FLAG_IGNORE 4 /* //IGNORE (not implemented) */
#define return_error(code) \
do { \
errno = code; \
return -1; \
} while (0)
#define xstrlcpy(dst, src, size) \
do { \
strncpy(dst, src, size); \
dst[size - 1] = 0; \
} while (0)
#define xstrlcpyn(dst, src, srclen, size) \
xstrlcpy(dst, src, xmin((srclen) + 1, size))
#define xmin(a, b) ((a) < (b) ? (a) : (b))
#define xmax(a, b) ((a) > (b) ? (a) : (b))
#define STATIC_STRLEN(arr) (sizeof(arr) - 1)
typedef unsigned char uchar;
typedef unsigned short ushort;
typedef unsigned int uint;
typedef void* iconv_t;
iconv_t iconv_open(const char *tocode, const char *fromcode);
int iconv_close(iconv_t cd);
size_t iconv(iconv_t cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft);
/* libiconv interface for vim */
#if defined(MAKE_DLL)
int
iconvctl (iconv_t cd, int request, void* argument)
{
/* not supported */
return 0;
}
#endif
typedef struct compat_t compat_t;
typedef struct csconv_t csconv_t;
typedef struct rec_iconv_t rec_iconv_t;
typedef iconv_t (*f_iconv_open)(const char *tocode, const char *fromcode);
typedef int (*f_iconv_close)(iconv_t cd);
typedef size_t (*f_iconv)(iconv_t cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft);
typedef int* (*f_errno)(void);
typedef int (*f_mbtowc)(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
typedef int (*f_wctomb)(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
typedef int (*f_mblen)(csconv_t *cv, const uchar *buf, int bufsize);
typedef int (*f_flush)(csconv_t *cv, uchar *buf, int bufsize);
#define COMPAT_IN 1
#define COMPAT_OUT 2
/* unicode mapping for compatibility with other conversion table. */
struct compat_t {
uint in;
uint out;
uint flag;
};
struct csconv_t {
int codepage;
int flags;
f_mbtowc mbtowc;
f_wctomb wctomb;
f_mblen mblen;
f_flush flush;
DWORD mode;
compat_t *compat;
};
struct rec_iconv_t {
iconv_t cd;
f_iconv_close iconv_close;
f_iconv iconv;
f_errno _errno;
csconv_t from;
csconv_t to;
#if defined(USE_LIBICONV_DLL)
HMODULE hlibiconv;
#endif
};
static int win_iconv_open(rec_iconv_t *cd, const char *tocode, const char *fromcode);
static int win_iconv_close(iconv_t cd);
static size_t win_iconv(iconv_t cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft);
static int load_mlang();
static csconv_t make_csconv(const char *name);
static int name_to_codepage(const char *name);
static uint utf16_to_ucs4(const ushort *wbuf);
static void ucs4_to_utf16(uint wc, ushort *wbuf, int *wbufsize);
static int is_unicode(int codepage);
static int mbtowc_flags(int codepage);
static int must_use_null_useddefaultchar(int codepage);
static void check_utf_bom(rec_iconv_t *cd, ushort *wbuf, int *wbufsize);
static char *strrstr(const char *str, const char *token);
#if defined(USE_LIBICONV_DLL)
static int libiconv_iconv_open(rec_iconv_t *cd, const char *tocode, const char *fromcode);
static PVOID MyImageDirectoryEntryToData(LPVOID Base, BOOLEAN MappedAsImage, USHORT DirectoryEntry, PULONG Size);
static HMODULE find_imported_module_by_funcname(HMODULE hModule, const char *funcname);
static HMODULE hwiniconv;
static HMODULE hlastdll; /* keep dll loaded for efficiency (unnecessary?) */
#endif
static int sbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize);
static int dbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize);
static int mbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize);
static int utf8_mblen(csconv_t *cv, const uchar *buf, int bufsize);
static int eucjp_mblen(csconv_t *cv, const uchar *buf, int bufsize);
static int kernel_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
static int kernel_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
static int mlang_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
static int mlang_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
static int utf16_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
static int utf16_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
static int utf32_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
static int utf32_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
static int iso2022jp_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize);
static int iso2022jp_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize);
static int iso2022jp_flush(csconv_t *cv, uchar *buf, int bufsize);
static struct {
int codepage;
const char *name;
} codepage_alias[] = {
{65001, "CP65001"},
{65001, "UTF8"},
{65001, "UTF-8"},
{1200, "CP1200"},
{1200, "UTF16LE"},
{1200, "UTF-16LE"},
{1200, "UCS2LE"},
{1200, "UCS-2LE"},
{1201, "CP1201"},
{1201, "UTF16BE"},
{1201, "UTF-16BE"},
{1201, "UCS2BE"},
{1201, "UCS-2BE"},
{1201, "unicodeFFFE"},
{12000, "CP12000"},
{12000, "UTF32LE"},
{12000, "UTF-32LE"},
{12000, "UCS4LE"},
{12000, "UCS-4LE"},
{12001, "CP12001"},
{12001, "UTF32BE"},
{12001, "UTF-32BE"},
{12001, "UCS4BE"},
{12001, "UCS-4BE"},
#ifndef GLIB_COMPILATION
/*
* Default is big endian.
* See rfc2781 4.3 Interpreting text labelled as UTF-16.
*/
{1201, "UTF16"},
{1201, "UTF-16"},
{12001, "UTF32"},
{12001, "UTF-32"},
{12001, "UCS-4"},
{12001, "UCS4"},
#else
/* Default is little endian, because the platform is */
{1200, "UTF16"},
{1200, "UTF-16"},
{1200, "UCS2"},
{1200, "UCS-2"},
{12000, "UTF32"},
{12000, "UTF-32"},
{12000, "UCS4"},
{12000, "UCS-4"},
#endif
/* copy from libiconv `iconv -l` */
/* !IsValidCodePage(367) */
{20127, "ANSI_X3.4-1968"},
{20127, "ANSI_X3.4-1986"},
{20127, "ASCII"},
{20127, "CP367"},
{20127, "IBM367"},
{20127, "ISO-IR-6"},
{20127, "ISO646-US"},
{20127, "ISO_646.IRV:1991"},
{20127, "US"},
{20127, "US-ASCII"},
{20127, "CSASCII"},
/* !IsValidCodePage(819) */
{1252, "CP819"},
{1252, "IBM819"},
{28591, "ISO-8859-1"},
{28591, "ISO-IR-100"},
{28591, "ISO8859-1"},
{28591, "ISO_8859-1"},
{28591, "ISO_8859-1:1987"},
{28591, "L1"},
{28591, "LATIN1"},
{28591, "CSISOLATIN1"},
{1250, "CP1250"},
{1250, "MS-EE"},
{1250, "WINDOWS-1250"},
{1251, "CP1251"},
{1251, "MS-CYRL"},
{1251, "WINDOWS-1251"},
{1252, "CP1252"},
{1252, "MS-ANSI"},
{1252, "WINDOWS-1252"},
{1253, "CP1253"},
{1253, "MS-GREEK"},
{1253, "WINDOWS-1253"},
{1254, "CP1254"},
{1254, "MS-TURK"},
{1254, "WINDOWS-1254"},
{1255, "CP1255"},
{1255, "MS-HEBR"},
{1255, "WINDOWS-1255"},
{1256, "CP1256"},
{1256, "MS-ARAB"},
{1256, "WINDOWS-1256"},
{1257, "CP1257"},
{1257, "WINBALTRIM"},
{1257, "WINDOWS-1257"},
{1258, "CP1258"},
{1258, "WINDOWS-1258"},
{850, "850"},
{850, "CP850"},
{850, "IBM850"},
{850, "CSPC850MULTILINGUAL"},
/* !IsValidCodePage(862) */
{862, "862"},
{862, "CP862"},
{862, "IBM862"},
{862, "CSPC862LATINHEBREW"},
{866, "866"},
{866, "CP866"},
{866, "IBM866"},
{866, "CSIBM866"},
/* !IsValidCodePage(154) */
{154, "CP154"},
{154, "CYRILLIC-ASIAN"},
{154, "PT154"},
{154, "PTCP154"},
{154, "CSPTCP154"},
/* !IsValidCodePage(1133) */
{1133, "CP1133"},
{1133, "IBM-CP1133"},
{874, "CP874"},
{874, "WINDOWS-874"},
/* !IsValidCodePage(51932) */
{51932, "CP51932"},
{51932, "MS51932"},
{51932, "WINDOWS-51932"},
{51932, "EUC-JP"},
{932, "CP932"},
{932, "MS932"},
{932, "SHIFFT_JIS"},
{932, "SHIFFT_JIS-MS"},
{932, "SJIS"},
{932, "SJIS-MS"},
{932, "SJIS-OPEN"},
{932, "SJIS-WIN"},
{932, "WINDOWS-31J"},
{932, "WINDOWS-932"},
{932, "CSWINDOWS31J"},
{50221, "CP50221"},
{50221, "ISO-2022-JP"},
{50221, "ISO-2022-JP-MS"},
{50221, "ISO2022-JP"},
{50221, "ISO2022-JP-MS"},
{50221, "MS50221"},
{50221, "WINDOWS-50221"},
{936, "CP936"},
{936, "GBK"},
{936, "MS936"},
{936, "WINDOWS-936"},
{950, "CP950"},
{950, "BIG5"},
{949, "CP949"},
{949, "UHC"},
{949, "EUC-KR"},
{1361, "CP1361"},
{1361, "JOHAB"},
{437, "437"},
{437, "CP437"},
{437, "IBM437"},
{437, "CSPC8CODEPAGE437"},
{737, "CP737"},
{775, "CP775"},
{775, "IBM775"},
{775, "CSPC775BALTIC"},
{852, "852"},
{852, "CP852"},
{852, "IBM852"},
{852, "CSPCP852"},
/* !IsValidCodePage(853) */
{853, "CP853"},
{855, "855"},
{855, "CP855"},
{855, "IBM855"},
{855, "CSIBM855"},
{857, "857"},
{857, "CP857"},
{857, "IBM857"},
{857, "CSIBM857"},
/* !IsValidCodePage(858) */
{858, "CP858"},
{860, "860"},
{860, "CP860"},
{860, "IBM860"},
{860, "CSIBM860"},
{861, "861"},
{861, "CP-IS"},
{861, "CP861"},
{861, "IBM861"},
{861, "CSIBM861"},
{863, "863"},
{863, "CP863"},
{863, "IBM863"},
{863, "CSIBM863"},
{864, "CP864"},
{864, "IBM864"},
{864, "CSIBM864"},
{865, "865"},
{865, "CP865"},
{865, "IBM865"},
{865, "CSIBM865"},
{869, "869"},
{869, "CP-GR"},
{869, "CP869"},
{869, "IBM869"},
{869, "CSIBM869"},
/* !IsValidCodePage(1152) */
{1125, "CP1125"},
/*
* Code Page Identifiers
* http://msdn2.microsoft.com/en-us/library/ms776446.aspx
*/
{37, "IBM037"}, /* IBM EBCDIC US-Canada */
{437, "IBM437"}, /* OEM United States */
{500, "IBM500"}, /* IBM EBCDIC International */
{708, "ASMO-708"}, /* Arabic (ASMO 708) */
/* 709 Arabic (ASMO-449+, BCON V4) */
/* 710 Arabic - Transparent Arabic */
{720, "DOS-720"}, /* Arabic (Transparent ASMO); Arabic (DOS) */
{737, "ibm737"}, /* OEM Greek (formerly 437G); Greek (DOS) */
{775, "ibm775"}, /* OEM Baltic; Baltic (DOS) */
{850, "ibm850"}, /* OEM Multilingual Latin 1; Western European (DOS) */
{852, "ibm852"}, /* OEM Latin 2; Central European (DOS) */
{855, "IBM855"}, /* OEM Cyrillic (primarily Russian) */
{857, "ibm857"}, /* OEM Turkish; Turkish (DOS) */
{858, "IBM00858"}, /* OEM Multilingual Latin 1 + Euro symbol */
{860, "IBM860"}, /* OEM Portuguese; Portuguese (DOS) */
{861, "ibm861"}, /* OEM Icelandic; Icelandic (DOS) */
{862, "DOS-862"}, /* OEM Hebrew; Hebrew (DOS) */
{863, "IBM863"}, /* OEM French Canadian; French Canadian (DOS) */
{864, "IBM864"}, /* OEM Arabic; Arabic (864) */
{865, "IBM865"}, /* OEM Nordic; Nordic (DOS) */
{866, "cp866"}, /* OEM Russian; Cyrillic (DOS) */
{869, "ibm869"}, /* OEM Modern Greek; Greek, Modern (DOS) */
{870, "IBM870"}, /* IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2 */
{874, "windows-874"}, /* ANSI/OEM Thai (same as 28605, ISO 8859-15); Thai (Windows) */
{875, "cp875"}, /* IBM EBCDIC Greek Modern */
{932, "shift_jis"}, /* ANSI/OEM Japanese; Japanese (Shift-JIS) */
{932, "shift-jis"}, /* alternative name for it */
{936, "gb2312"}, /* ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312) */
{949, "ks_c_5601-1987"}, /* ANSI/OEM Korean (Unified Hangul Code) */
{950, "big5"}, /* ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5) */
{1026, "IBM1026"}, /* IBM EBCDIC Turkish (Latin 5) */
{1047, "IBM01047"}, /* IBM EBCDIC Latin 1/Open System */
{1140, "IBM01140"}, /* IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro) */
{1141, "IBM01141"}, /* IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro) */
{1142, "IBM01142"}, /* IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro) */
{1143, "IBM01143"}, /* IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro) */
{1144, "IBM01144"}, /* IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro) */
{1145, "IBM01145"}, /* IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro) */
{1146, "IBM01146"}, /* IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro) */
{1147, "IBM01147"}, /* IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro) */
{1148, "IBM01148"}, /* IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro) */
{1149, "IBM01149"}, /* IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro) */
{1250, "windows-1250"}, /* ANSI Central European; Central European (Windows) */
{1251, "windows-1251"}, /* ANSI Cyrillic; Cyrillic (Windows) */
{1252, "windows-1252"}, /* ANSI Latin 1; Western European (Windows) */
{1253, "windows-1253"}, /* ANSI Greek; Greek (Windows) */
{1254, "windows-1254"}, /* ANSI Turkish; Turkish (Windows) */
{1255, "windows-1255"}, /* ANSI Hebrew; Hebrew (Windows) */
{1256, "windows-1256"}, /* ANSI Arabic; Arabic (Windows) */
{1257, "windows-1257"}, /* ANSI Baltic; Baltic (Windows) */
{1258, "windows-1258"}, /* ANSI/OEM Vietnamese; Vietnamese (Windows) */
{1361, "Johab"}, /* Korean (Johab) */
{10000, "macintosh"}, /* MAC Roman; Western European (Mac) */
{10001, "x-mac-japanese"}, /* Japanese (Mac) */
{10002, "x-mac-chinesetrad"}, /* MAC Traditional Chinese (Big5); Chinese Traditional (Mac) */
{10003, "x-mac-korean"}, /* Korean (Mac) */
{10004, "x-mac-arabic"}, /* Arabic (Mac) */
{10005, "x-mac-hebrew"}, /* Hebrew (Mac) */
{10006, "x-mac-greek"}, /* Greek (Mac) */
{10007, "x-mac-cyrillic"}, /* Cyrillic (Mac) */
{10008, "x-mac-chinesesimp"}, /* MAC Simplified Chinese (GB 2312); Chinese Simplified (Mac) */
{10010, "x-mac-romanian"}, /* Romanian (Mac) */
{10017, "x-mac-ukrainian"}, /* Ukrainian (Mac) */
{10021, "x-mac-thai"}, /* Thai (Mac) */
{10029, "x-mac-ce"}, /* MAC Latin 2; Central European (Mac) */
{10079, "x-mac-icelandic"}, /* Icelandic (Mac) */
{10081, "x-mac-turkish"}, /* Turkish (Mac) */
{10082, "x-mac-croatian"}, /* Croatian (Mac) */
{20000, "x-Chinese_CNS"}, /* CNS Taiwan; Chinese Traditional (CNS) */
{20001, "x-cp20001"}, /* TCA Taiwan */
{20002, "x_Chinese-Eten"}, /* Eten Taiwan; Chinese Traditional (Eten) */
{20003, "x-cp20003"}, /* IBM5550 Taiwan */
{20004, "x-cp20004"}, /* TeleText Taiwan */
{20005, "x-cp20005"}, /* Wang Taiwan */
{20105, "x-IA5"}, /* IA5 (IRV International Alphabet No. 5, 7-bit); Western European (IA5) */
{20106, "x-IA5-German"}, /* IA5 German (7-bit) */
{20107, "x-IA5-Swedish"}, /* IA5 Swedish (7-bit) */
{20108, "x-IA5-Norwegian"}, /* IA5 Norwegian (7-bit) */
{20127, "us-ascii"}, /* US-ASCII (7-bit) */
{20261, "x-cp20261"}, /* T.61 */
{20269, "x-cp20269"}, /* ISO 6937 Non-Spacing Accent */
{20273, "IBM273"}, /* IBM EBCDIC Germany */
{20277, "IBM277"}, /* IBM EBCDIC Denmark-Norway */
{20278, "IBM278"}, /* IBM EBCDIC Finland-Sweden */
{20280, "IBM280"}, /* IBM EBCDIC Italy */
{20284, "IBM284"}, /* IBM EBCDIC Latin America-Spain */
{20285, "IBM285"}, /* IBM EBCDIC United Kingdom */
{20290, "IBM290"}, /* IBM EBCDIC Japanese Katakana Extended */
{20297, "IBM297"}, /* IBM EBCDIC France */
{20420, "IBM420"}, /* IBM EBCDIC Arabic */
{20423, "IBM423"}, /* IBM EBCDIC Greek */
{20424, "IBM424"}, /* IBM EBCDIC Hebrew */
{20833, "x-EBCDIC-KoreanExtended"}, /* IBM EBCDIC Korean Extended */
{20838, "IBM-Thai"}, /* IBM EBCDIC Thai */
{20866, "koi8-r"}, /* Russian (KOI8-R); Cyrillic (KOI8-R) */
{20871, "IBM871"}, /* IBM EBCDIC Icelandic */
{20880, "IBM880"}, /* IBM EBCDIC Cyrillic Russian */
{20905, "IBM905"}, /* IBM EBCDIC Turkish */
{20924, "IBM00924"}, /* IBM EBCDIC Latin 1/Open System (1047 + Euro symbol) */
{20932, "EUC-JP"}, /* Japanese (JIS 0208-1990 and 0121-1990) */
{20936, "x-cp20936"}, /* Simplified Chinese (GB2312); Chinese Simplified (GB2312-80) */
{20949, "x-cp20949"}, /* Korean Wansung */
{21025, "cp1025"}, /* IBM EBCDIC Cyrillic Serbian-Bulgarian */
/* 21027 (deprecated) */
{21866, "koi8-u"}, /* Ukrainian (KOI8-U); Cyrillic (KOI8-U) */
{28591, "iso-8859-1"}, /* ISO 8859-1 Latin 1; Western European (ISO) */
{28591, "iso8859-1"}, /* ISO 8859-1 Latin 1; Western European (ISO) */
{28592, "iso-8859-2"}, /* ISO 8859-2 Central European; Central European (ISO) */
{28592, "iso8859-2"}, /* ISO 8859-2 Central European; Central European (ISO) */
{28593, "iso-8859-3"}, /* ISO 8859-3 Latin 3 */
{28593, "iso8859-3"}, /* ISO 8859-3 Latin 3 */
{28594, "iso-8859-4"}, /* ISO 8859-4 Baltic */
{28594, "iso8859-4"}, /* ISO 8859-4 Baltic */
{28595, "iso-8859-5"}, /* ISO 8859-5 Cyrillic */
{28595, "iso8859-5"}, /* ISO 8859-5 Cyrillic */
{28596, "iso-8859-6"}, /* ISO 8859-6 Arabic */
{28596, "iso8859-6"}, /* ISO 8859-6 Arabic */
{28597, "iso-8859-7"}, /* ISO 8859-7 Greek */
{28597, "iso8859-7"}, /* ISO 8859-7 Greek */
{28598, "iso-8859-8"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Visual) */
{28598, "iso8859-8"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Visual) */
{28599, "iso-8859-9"}, /* ISO 8859-9 Turkish */
{28599, "iso8859-9"}, /* ISO 8859-9 Turkish */
{28603, "iso-8859-13"}, /* ISO 8859-13 Estonian */
{28603, "iso8859-13"}, /* ISO 8859-13 Estonian */
{28605, "iso-8859-15"}, /* ISO 8859-15 Latin 9 */
{28605, "iso8859-15"}, /* ISO 8859-15 Latin 9 */
{29001, "x-Europa"}, /* Europa 3 */
{38598, "iso-8859-8-i"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Logical) */
{38598, "iso8859-8-i"}, /* ISO 8859-8 Hebrew; Hebrew (ISO-Logical) */
{50220, "iso-2022-jp"}, /* ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS) */
{50221, "csISO2022JP"}, /* ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana) */
{50222, "iso-2022-jp"}, /* ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI) */
{50225, "iso-2022-kr"}, /* ISO 2022 Korean */
{50225, "iso2022-kr"}, /* ISO 2022 Korean */
{50227, "x-cp50227"}, /* ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022) */
/* 50229 ISO 2022 Traditional Chinese */
/* 50930 EBCDIC Japanese (Katakana) Extended */
/* 50931 EBCDIC US-Canada and Japanese */
/* 50933 EBCDIC Korean Extended and Korean */
/* 50935 EBCDIC Simplified Chinese Extended and Simplified Chinese */
/* 50936 EBCDIC Simplified Chinese */
/* 50937 EBCDIC US-Canada and Traditional Chinese */
/* 50939 EBCDIC Japanese (Latin) Extended and Japanese */
{51932, "euc-jp"}, /* EUC Japanese */
{51936, "EUC-CN"}, /* EUC Simplified Chinese; Chinese Simplified (EUC) */
{51949, "euc-kr"}, /* EUC Korean */
/* 51950 EUC Traditional Chinese */
{52936, "hz-gb-2312"}, /* HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ) */
{54936, "GB18030"}, /* Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030) */
{57002, "x-iscii-de"}, /* ISCII Devanagari */
{57003, "x-iscii-be"}, /* ISCII Bengali */
{57004, "x-iscii-ta"}, /* ISCII Tamil */
{57005, "x-iscii-te"}, /* ISCII Telugu */
{57006, "x-iscii-as"}, /* ISCII Assamese */
{57007, "x-iscii-or"}, /* ISCII Oriya */
{57008, "x-iscii-ka"}, /* ISCII Kannada */
{57009, "x-iscii-ma"}, /* ISCII Malayalam */
{57010, "x-iscii-gu"}, /* ISCII Gujarati */
{57011, "x-iscii-pa"}, /* ISCII Punjabi */
{0, NULL}
};
/*
* SJIS SHIFTJIS table CP932 table
* ---- --------------------------- --------------------------------
* 5C U+00A5 YEN SIGN U+005C REVERSE SOLIDUS
* 7E U+203E OVERLINE U+007E TILDE
* 815C U+2014 EM DASH U+2015 HORIZONTAL BAR
* 815F U+005C REVERSE SOLIDUS U+FF3C FULLWIDTH REVERSE SOLIDUS
* 8160 U+301C WAVE DASH U+FF5E FULLWIDTH TILDE
* 8161 U+2016 DOUBLE VERTICAL LINE U+2225 PARALLEL TO
* 817C U+2212 MINUS SIGN U+FF0D FULLWIDTH HYPHEN-MINUS
* 8191 U+00A2 CENT SIGN U+FFE0 FULLWIDTH CENT SIGN
* 8192 U+00A3 POUND SIGN U+FFE1 FULLWIDTH POUND SIGN
* 81CA U+00AC NOT SIGN U+FFE2 FULLWIDTH NOT SIGN
*
* EUC-JP and ISO-2022-JP should be compatible with CP932.
*
* Kernel and MLang have different Unicode mapping table. Make sure
* which API is used.
*/
static compat_t cp932_compat[] = {
{0x00A5, 0x005C, COMPAT_OUT},
{0x203E, 0x007E, COMPAT_OUT},
{0x2014, 0x2015, COMPAT_OUT},
{0x301C, 0xFF5E, COMPAT_OUT},
{0x2016, 0x2225, COMPAT_OUT},
{0x2212, 0xFF0D, COMPAT_OUT},
{0x00A2, 0xFFE0, COMPAT_OUT},
{0x00A3, 0xFFE1, COMPAT_OUT},
{0x00AC, 0xFFE2, COMPAT_OUT},
{0, 0, 0}
};
static compat_t cp20932_compat[] = {
{0x00A5, 0x005C, COMPAT_OUT},
{0x203E, 0x007E, COMPAT_OUT},
{0x2014, 0x2015, COMPAT_OUT},
{0xFF5E, 0x301C, COMPAT_OUT|COMPAT_IN},
{0x2225, 0x2016, COMPAT_OUT|COMPAT_IN},
{0xFF0D, 0x2212, COMPAT_OUT|COMPAT_IN},
{0xFFE0, 0x00A2, COMPAT_OUT|COMPAT_IN},
{0xFFE1, 0x00A3, COMPAT_OUT|COMPAT_IN},
{0xFFE2, 0x00AC, COMPAT_OUT|COMPAT_IN},
{0, 0, 0}
};
static compat_t *cp51932_compat = cp932_compat;
/* cp20932_compat for kernel. cp932_compat for mlang. */
static compat_t *cp5022x_compat = cp932_compat;
typedef HRESULT (WINAPI *CONVERTINETSTRING)(
LPDWORD lpdwMode,
DWORD dwSrcEncoding,
DWORD dwDstEncoding,
LPCSTR lpSrcStr,
LPINT lpnSrcSize,
LPBYTE lpDstStr,
LPINT lpnDstSize
);
typedef HRESULT (WINAPI *CONVERTINETMULTIBYTETOUNICODE)(
LPDWORD lpdwMode,
DWORD dwSrcEncoding,
LPCSTR lpSrcStr,
LPINT lpnMultiCharCount,
LPWSTR lpDstStr,
LPINT lpnWideCharCount
);
typedef HRESULT (WINAPI *CONVERTINETUNICODETOMULTIBYTE)(
LPDWORD lpdwMode,
DWORD dwEncoding,
LPCWSTR lpSrcStr,
LPINT lpnWideCharCount,
LPSTR lpDstStr,
LPINT lpnMultiCharCount
);
typedef HRESULT (WINAPI *ISCONVERTINETSTRINGAVAILABLE)(
DWORD dwSrcEncoding,
DWORD dwDstEncoding
);
typedef HRESULT (WINAPI *LCIDTORFC1766A)(
LCID Locale,
LPSTR pszRfc1766,
int nChar
);
typedef HRESULT (WINAPI *LCIDTORFC1766W)(
LCID Locale,
LPWSTR pszRfc1766,
int nChar
);
typedef HRESULT (WINAPI *RFC1766TOLCIDA)(
LCID *pLocale,
LPSTR pszRfc1766
);
typedef HRESULT (WINAPI *RFC1766TOLCIDW)(
LCID *pLocale,
LPWSTR pszRfc1766
);
static CONVERTINETSTRING ConvertINetString;
static CONVERTINETMULTIBYTETOUNICODE ConvertINetMultiByteToUnicode;
static CONVERTINETUNICODETOMULTIBYTE ConvertINetUnicodeToMultiByte;
static ISCONVERTINETSTRINGAVAILABLE IsConvertINetStringAvailable;
static LCIDTORFC1766A LcidToRfc1766A;
static RFC1766TOLCIDA Rfc1766ToLcidA;
static int
load_mlang()
{
HMODULE h = NULL;
char mlang_dll[MAX_PATH + 100];
int n;
if (ConvertINetString != NULL)
return TRUE;
n = GetSystemDirectory(mlang_dll, MAX_PATH);
if (n > 0 && n < MAX_PATH)
{
if (mlang_dll[n-1] != '\\' &&
mlang_dll[n-1] != '/')
strcat(mlang_dll, "\\");
strcat(mlang_dll, "mlang.dll");
h = LoadLibrary(mlang_dll);
}
if (!h)
return FALSE;
ConvertINetString = (CONVERTINETSTRING)GetProcAddress(h, "ConvertINetString");
ConvertINetMultiByteToUnicode = (CONVERTINETMULTIBYTETOUNICODE)GetProcAddress(h, "ConvertINetMultiByteToUnicode");
ConvertINetUnicodeToMultiByte = (CONVERTINETUNICODETOMULTIBYTE)GetProcAddress(h, "ConvertINetUnicodeToMultiByte");
IsConvertINetStringAvailable = (ISCONVERTINETSTRINGAVAILABLE)GetProcAddress(h, "IsConvertINetStringAvailable");
LcidToRfc1766A = (LCIDTORFC1766A)GetProcAddress(h, "LcidToRfc1766A");
Rfc1766ToLcidA = (RFC1766TOLCIDA)GetProcAddress(h, "Rfc1766ToLcidA");
return TRUE;
}
iconv_t
iconv_open(const char *tocode, const char *fromcode)
{
rec_iconv_t *cd;
cd = (rec_iconv_t *)calloc(1, sizeof(rec_iconv_t));
if (cd == NULL)
{
errno = ENOMEM;
return (iconv_t)(-1);
}
#if defined(USE_LIBICONV_DLL)
if (libiconv_iconv_open(cd, tocode, fromcode))
return (iconv_t)cd;
#endif
if (win_iconv_open(cd, tocode, fromcode))
return (iconv_t)cd;
free(cd);
errno = EINVAL;
return (iconv_t)(-1);
}
int
iconv_close(iconv_t _cd)
{
rec_iconv_t *cd = (rec_iconv_t *)_cd;
int r = cd->iconv_close(cd->cd);
int e = *(cd->_errno());
#if defined(USE_LIBICONV_DLL)
if (cd->hlibiconv != NULL)
FreeLibrary(cd->hlibiconv);
#endif
free(cd);
errno = e;
return r;
}
size_t
iconv(iconv_t _cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft)
{
rec_iconv_t *cd = (rec_iconv_t *)_cd;
size_t r = cd->iconv(cd->cd, inbuf, inbytesleft, outbuf, outbytesleft);
errno = *(cd->_errno());
return r;
}
static int
win_iconv_open(rec_iconv_t *cd, const char *tocode, const char *fromcode)
{
cd->from = make_csconv(fromcode);
cd->to = make_csconv(tocode);
if (cd->from.codepage == -1 || cd->to.codepage == -1)
return FALSE;
cd->iconv_close = win_iconv_close;
cd->iconv = win_iconv;
cd->_errno = _errno;
cd->cd = (iconv_t)cd;
return TRUE;
}
static int
win_iconv_close(iconv_t cd)
{
return 0;
}
static size_t
win_iconv(iconv_t _cd, const char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft)
{
rec_iconv_t *cd = (rec_iconv_t *)_cd;
ushort wbuf[MB_CHAR_MAX]; /* enough room for one character */
int insize;
int outsize;
int wsize;
DWORD mode;
uint wc;
compat_t *cp;
int i;
if (inbuf == NULL || *inbuf == NULL)
{
if (outbuf != NULL && *outbuf != NULL && cd->to.flush != NULL)
{
outsize = cd->to.flush(&cd->to, (uchar *)*outbuf, *outbytesleft);
if (outsize == -1)
return (size_t)(-1);
*outbuf += outsize;
*outbytesleft -= outsize;
}
if (is_unicode(cd->from.codepage) && (cd->from.mode & UNICODE_MODE_SWAPPED))
cd->from.codepage ^= 1;
cd->from.mode = 0;
cd->to.mode = 0;
return 0;
}
while (*inbytesleft != 0)
{
mode = cd->from.mode;
wsize = MB_CHAR_MAX;
insize = cd->from.mbtowc(&cd->from, (const uchar *)*inbuf, *inbytesleft, wbuf, &wsize);
if (insize == -1)
return (size_t)(-1);
if (is_unicode(cd->from.codepage) && !(cd->from.mode & UNICODE_MODE_BOM_DONE))
{
check_utf_bom(cd, wbuf, &wsize);
cd->from.mode |= UNICODE_MODE_BOM_DONE;
}
if (wsize == 0)
{
*inbuf += insize;
*inbytesleft -= insize;
continue;
}
if (cd->from.compat != NULL)
{
wc = utf16_to_ucs4(wbuf);
cp = cd->from.compat;
for (i = 0; cp[i].in != 0; ++i)
{
if ((cp[i].flag & COMPAT_IN) && cp[i].out == wc)
{
ucs4_to_utf16(cp[i].in, wbuf, &wsize);
break;
}
}
}
if (cd->to.compat != NULL)
{
wc = utf16_to_ucs4(wbuf);
cp = cd->to.compat;
for (i = 0; cp[i].in != 0; ++i)
{
if ((cp[i].flag & COMPAT_OUT) && cp[i].in == wc)
{
ucs4_to_utf16(cp[i].out, wbuf, &wsize);
break;
}
}
}
outsize = cd->to.wctomb(&cd->to, wbuf, wsize, (uchar *)*outbuf, *outbytesleft);
if (outsize == -1)
{
cd->from.mode = mode;
return (size_t)(-1);
}
*inbuf += insize;
*outbuf += outsize;
*inbytesleft -= insize;
*outbytesleft -= outsize;
}
return 0;
}
static csconv_t
make_csconv(const char *_name)
{
CPINFOEX cpinfoex;
csconv_t cv;
int use_compat = TRUE;
int flag = 0;
char name[128];
char *p;
xstrlcpy(name, _name, sizeof(name));
/* check for option "enc_name//opt1//opt2" */
while ((p = strrstr(name, "//")) != NULL)
{
if (_stricmp(p + 2, "nocompat") == 0)
use_compat = FALSE;
else if (_stricmp(p + 2, "translit") == 0)
flag |= FLAG_TRANSLIT;
else if (_stricmp(p + 2, "ignore") == 0)
flag |= FLAG_IGNORE;
*p = 0;
}
cv.mode = 0;
cv.flags = flag;
cv.mblen = NULL;
cv.flush = NULL;
cv.compat = NULL;
cv.codepage = name_to_codepage(name);
if (cv.codepage == 1200 || cv.codepage == 1201)
{
cv.mbtowc = utf16_mbtowc;
cv.wctomb = utf16_wctomb;
if (_stricmp(name, "UTF-16") == 0 ||
_stricmp(name, "UTF16") == 0 ||
_stricmp(name, "UCS-2") == 0 ||
_stricmp(name, "UCS2") == 0)
cv.flags |= FLAG_USE_BOM_ENDIAN;
}
else if (cv.codepage == 12000 || cv.codepage == 12001)
{
cv.mbtowc = utf32_mbtowc;
cv.wctomb = utf32_wctomb;
if (_stricmp(name, "UTF-32") == 0 ||
_stricmp(name, "UTF32") == 0 ||
_stricmp(name, "UCS-4") == 0 ||
_stricmp(name, "UCS4") == 0)
cv.flags |= FLAG_USE_BOM_ENDIAN;
}
else if (cv.codepage == 65001)
{
cv.mbtowc = kernel_mbtowc;
cv.wctomb = kernel_wctomb;
cv.mblen = utf8_mblen;
}
else if ((cv.codepage == 50220 || cv.codepage == 50221 || cv.codepage == 50222) && load_mlang())
{
cv.mbtowc = iso2022jp_mbtowc;
cv.wctomb = iso2022jp_wctomb;
cv.flush = iso2022jp_flush;
}
else if (cv.codepage == 51932 && load_mlang())
{
cv.mbtowc = mlang_mbtowc;
cv.wctomb = mlang_wctomb;
cv.mblen = eucjp_mblen;
}
else if (IsValidCodePage(cv.codepage)
&& GetCPInfoEx(cv.codepage, 0, &cpinfoex) != 0)
{
cv.mbtowc = kernel_mbtowc;
cv.wctomb = kernel_wctomb;
if (cpinfoex.MaxCharSize == 1)
cv.mblen = sbcs_mblen;
else if (cpinfoex.MaxCharSize == 2)
cv.mblen = dbcs_mblen;
else
cv.mblen = mbcs_mblen;
}
else
{
/* not supported */
cv.codepage = -1;
}
if (use_compat)
{
switch (cv.codepage)
{
case 932: cv.compat = cp932_compat; break;
case 20932: cv.compat = cp20932_compat; break;
case 51932: cv.compat = cp51932_compat; break;
case 50220: case 50221: case 50222: cv.compat = cp5022x_compat; break;
}
}
return cv;
}
static int
name_to_codepage(const char *name)
{
int i;
if (*name == '\0' ||
strcmp(name, "char") == 0)
return GetACP();
else if (strcmp(name, "wchar_t") == 0)
return 1200;
else if (_strnicmp(name, "cp", 2) == 0)
return atoi(name + 2); /* CP123 */
else if ('0' <= name[0] && name[0] <= '9')
return atoi(name); /* 123 */
else if (_strnicmp(name, "xx", 2) == 0)
return atoi(name + 2); /* XX123 for debug */
for (i = 0; codepage_alias[i].name != NULL; ++i)
if (_stricmp(name, codepage_alias[i].name) == 0)
return codepage_alias[i].codepage;
return -1;
}
/*
* http://www.faqs.org/rfcs/rfc2781.html
*/
static uint
utf16_to_ucs4(const ushort *wbuf)
{
uint wc = wbuf[0];
if (0xD800 <= wbuf[0] && wbuf[0] <= 0xDBFF)
wc = ((wbuf[0] & 0x3FF) << 10) + (wbuf[1] & 0x3FF) + 0x10000;
return wc;
}
static void
ucs4_to_utf16(uint wc, ushort *wbuf, int *wbufsize)
{
if (wc < 0x10000)
{
wbuf[0] = wc;
*wbufsize = 1;
}
else
{
wc -= 0x10000;
wbuf[0] = 0xD800 | ((wc >> 10) & 0x3FF);
wbuf[1] = 0xDC00 | (wc & 0x3FF);
*wbufsize = 2;
}
}
static int
is_unicode(int codepage)
{
return (codepage == 1200 || codepage == 1201 ||
codepage == 12000 || codepage == 12001 ||
codepage == 65000 || codepage == 65001);
}
/*
* Check if codepage is one of those for which the dwFlags parameter
* to MultiByteToWideChar() must be zero. Return zero or
* MB_ERR_INVALID_CHARS. The docs in Platform SDK for for Windows
* Server 2003 R2 claims that also codepage 65001 is one of these, but
* that doesn't seem to be the case. The MSDN docs for MSVS2008 leave
* out 65001 (UTF-8), and that indeed seems to be the case on XP, it
* works fine to pass MB_ERR_INVALID_CHARS in dwFlags when converting
* from UTF-8.
*/
static int
mbtowc_flags(int codepage)
{
return (codepage == 50220 || codepage == 50221 ||
codepage == 50222 || codepage == 50225 ||
codepage == 50227 || codepage == 50229 ||
codepage == 52936 || codepage == 54936 ||
(codepage >= 57002 && codepage <= 57011) ||
codepage == 65000 || codepage == 42) ? 0 : MB_ERR_INVALID_CHARS;
}
/*
* Check if codepage is one those for which the lpUsedDefaultChar
* parameter to WideCharToMultiByte() must be NULL. The docs in
* Platform SDK for for Windows Server 2003 R2 claims that this is the
* list below, while the MSDN docs for MSVS2008 claim that it is only
* for 65000 (UTF-7) and 65001 (UTF-8). This time the earlier Platform
* SDK seems to be correct, at least for XP.
*/
static int
must_use_null_useddefaultchar(int codepage)
{
return (codepage == 65000 || codepage == 65001 ||
codepage == 50220 || codepage == 50221 ||
codepage == 50222 || codepage == 50225 ||
codepage == 50227 || codepage == 50229 ||
codepage == 52936 || codepage == 54936 ||
(codepage >= 57002 && codepage <= 57011) ||
codepage == 42);
}
static void
check_utf_bom(rec_iconv_t *cd, ushort *wbuf, int *wbufsize)
{
/* If we have a BOM, trust it, despite what the caller said */
if (wbuf[0] == 0xFFFE && (cd->from.flags & FLAG_USE_BOM_ENDIAN))
{
/* swap endian: 1200 <-> 1201 or 12000 <-> 12001 */
cd->from.codepage ^= 1;
cd->from.mode |= UNICODE_MODE_SWAPPED;
wbuf[0] = 0xFEFF;
}
/*
* Remove BOM.
* Don't do this if "to" is Unicode,
* except if "to" is UTF-8.
*/
if (wbuf[0] == 0xFEFF && (!is_unicode(cd->to.codepage) || cd->to.codepage == 65001))
*wbufsize = 0;
}
static char *
strrstr(const char *str, const char *token)
{
int len = strlen(token);
const char *p = str + strlen(str);
while (str <= --p)
if (p[0] == token[0] && strncmp(p, token, len) == 0)
return (char *)p;
return NULL;
}
#if defined(USE_LIBICONV_DLL)
static int
libiconv_iconv_open(rec_iconv_t *cd, const char *fromcode, const char *tocode)
{
HMODULE hlibiconv = NULL;
HMODULE hmsvcrt = NULL;
char dllname[_MAX_PATH];
const char *p;
const char *e;
f_iconv_open _iconv_open;
/*
* always try to load dll, so that we can switch dll in runtime.
*/
/* XXX: getenv() can't get variable set by SetEnvironmentVariable() */
p = getenv("WINICONV_LIBICONV_DLL");
if (p == NULL)
p = DEFAULT_LIBICONV_DLL;
/* parse comma separated value */
for ( ; *p != 0; p = (*e == ',') ? e + 1 : e)
{
e = strchr(p, ',');
if (p == e)
continue;
else if (e == NULL)
e = p + strlen(p);
xstrlcpyn(dllname, p, e - p, sizeof(dllname));
hlibiconv = LoadLibrary(dllname);
if (hlibiconv != NULL)
{
if (hlibiconv == hwiniconv)
{
FreeLibrary(hlibiconv);
hlibiconv = NULL;
continue;
}
break;
}
}
if (hlastdll != NULL)
{
/* decrement reference count */
FreeLibrary(hlastdll);
hlastdll = NULL;
}
if (hlibiconv == NULL)
goto failed;
hmsvcrt = find_imported_module_by_funcname(hlibiconv, "_errno");
if (hmsvcrt == NULL)
goto failed;
_iconv_open = (f_iconv_open)GetProcAddress(hlibiconv, "libiconv_open");
if (_iconv_open == NULL)
_iconv_open = (f_iconv_open)GetProcAddress(hlibiconv, "iconv_open");
cd->iconv_close = (f_iconv_close)GetProcAddress(hlibiconv, "libiconv_close");
if (cd->iconv_close == NULL)
cd->iconv_close = (f_iconv_close)GetProcAddress(hlibiconv, "iconv_close");
cd->iconv = (f_iconv)GetProcAddress(hlibiconv, "libiconv");
if (cd->iconv == NULL)
cd->iconv = (f_iconv)GetProcAddress(hlibiconv, "iconv");
cd->_errno = (f_errno)GetProcAddress(hmsvcrt, "_errno");
if (_iconv_open == NULL || cd->iconv_close == NULL
|| cd->iconv == NULL || cd->_errno == NULL)
goto failed;
/* increment reference count */
hlastdll = LoadLibrary(dllname);
cd->cd = _iconv_open(tocode, fromcode);
if (cd->cd == (iconv_t)(-1))
goto failed;
cd->hlibiconv = hlibiconv;
return TRUE;
failed:
if (hlibiconv != NULL)
FreeLibrary(hlibiconv);
/* do not free hmsvcrt which is obtained by GetModuleHandle() */
return FALSE;
}
/*
* Reference:
* http://forums.belution.com/ja/vc/000/234/78s.shtml
* http://nienie.com/~masapico/api_ImageDirectoryEntryToData.html
*
* The formal way is
* imagehlp.h or dbghelp.h
* imagehlp.lib or dbghelp.lib
* ImageDirectoryEntryToData()
*/
#define TO_DOS_HEADER(base) ((PIMAGE_DOS_HEADER)(base))
#define TO_NT_HEADERS(base) ((PIMAGE_NT_HEADERS)((LPBYTE)(base) + TO_DOS_HEADER(base)->e_lfanew))
static PVOID
MyImageDirectoryEntryToData(LPVOID Base, BOOLEAN MappedAsImage, USHORT DirectoryEntry, PULONG Size)
{
/* TODO: MappedAsImage? */
PIMAGE_DATA_DIRECTORY p;
p = TO_NT_HEADERS(Base)->OptionalHeader.DataDirectory + DirectoryEntry;
if (p->VirtualAddress == 0) {
*Size = 0;
return NULL;
}
*Size = p->Size;
return (PVOID)((LPBYTE)Base + p->VirtualAddress);
}
static HMODULE
find_imported_module_by_funcname(HMODULE hModule, const char *funcname)
{
DWORD Base;
ULONG Size;
PIMAGE_IMPORT_DESCRIPTOR Imp;
PIMAGE_THUNK_DATA Name; /* Import Name Table */
PIMAGE_IMPORT_BY_NAME ImpName;
Base = (DWORD)hModule;
Imp = MyImageDirectoryEntryToData(
(LPVOID)Base,
TRUE,
IMAGE_DIRECTORY_ENTRY_IMPORT,
&Size);
if (Imp == NULL)
return NULL;
for ( ; Imp->OriginalFirstThunk != 0; ++Imp)
{
Name = (PIMAGE_THUNK_DATA)(Base + Imp->OriginalFirstThunk);
for ( ; Name->u1.Ordinal != 0; ++Name)
{
if (!IMAGE_SNAP_BY_ORDINAL(Name->u1.Ordinal))
{
ImpName = (PIMAGE_IMPORT_BY_NAME)
(Base + (DWORD)Name->u1.AddressOfData);
if (strcmp((char *)ImpName->Name, funcname) == 0)
return GetModuleHandle((char *)(Base + Imp->Name));
}
}
}
return NULL;
}
#endif
static int
sbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize)
{
return 1;
}
static int
dbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize)
{
int len = IsDBCSLeadByteEx(cv->codepage, buf[0]) ? 2 : 1;
if (bufsize < len)
return_error(EINVAL);
return len;
}
static int
mbcs_mblen(csconv_t *cv, const uchar *buf, int bufsize)
{
int len = 0;
if (cv->codepage == 54936) {
if (buf[0] <= 0x7F) len = 1;
else if (buf[0] >= 0x81 && buf[0] <= 0xFE &&
bufsize >= 2 &&
((buf[1] >= 0x40 && buf[1] <= 0x7E) ||
(buf[1] >= 0x80 && buf[1] <= 0xFE))) len = 2;
else if (buf[0] >= 0x81 && buf[0] <= 0xFE &&
bufsize >= 4 &&
buf[1] >= 0x30 && buf[1] <= 0x39) len = 4;
else
return_error(EINVAL);
return len;
}
else
return_error(EINVAL);
}
static int
utf8_mblen(csconv_t *cv, const uchar *buf, int bufsize)
{
int len = 0;
if (buf[0] < 0x80) len = 1;
else if ((buf[0] & 0xE0) == 0xC0) len = 2;
else if ((buf[0] & 0xF0) == 0xE0) len = 3;
else if ((buf[0] & 0xF8) == 0xF0) len = 4;
else if ((buf[0] & 0xFC) == 0xF8) len = 5;
else if ((buf[0] & 0xFE) == 0xFC) len = 6;
if (len == 0)
return_error(EILSEQ);
else if (bufsize < len)
return_error(EINVAL);
return len;
}
static int
eucjp_mblen(csconv_t *cv, const uchar *buf, int bufsize)
{
if (buf[0] < 0x80) /* ASCII */
return 1;
else if (buf[0] == 0x8E) /* JIS X 0201 */
{
if (bufsize < 2)
return_error(EINVAL);
else if (!(0xA1 <= buf[1] && buf[1] <= 0xDF))
return_error(EILSEQ);
return 2;
}
else if (buf[0] == 0x8F) /* JIS X 0212 */
{
if (bufsize < 3)
return_error(EINVAL);
else if (!(0xA1 <= buf[1] && buf[1] <= 0xFE)
|| !(0xA1 <= buf[2] && buf[2] <= 0xFE))
return_error(EILSEQ);
return 3;
}
else /* JIS X 0208 */
{
if (bufsize < 2)
return_error(EINVAL);
else if (!(0xA1 <= buf[0] && buf[0] <= 0xFE)
|| !(0xA1 <= buf[1] && buf[1] <= 0xFE))
return_error(EILSEQ);
return 2;
}
}
static int
kernel_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize)
{
int len;
len = cv->mblen(cv, buf, bufsize);
if (len == -1)
return -1;
/* If converting from ASCII, reject 8bit
* chars. MultiByteToWideChar() doesn't. Note that for ASCII we
* know that the mblen function is sbcs_mblen() so len is 1.
*/
if (cv->codepage == 20127 && buf[0] >= 0x80)
return_error(EILSEQ);
*wbufsize = MultiByteToWideChar(cv->codepage, mbtowc_flags (cv->codepage),
(const char *)buf, len, (wchar_t *)wbuf, *wbufsize);
if (*wbufsize == 0)
return_error(EILSEQ);
return len;
}
static int
kernel_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize)
{
BOOL usedDefaultChar = 0;
BOOL *p = NULL;
int flags = 0;
int len;
if (bufsize == 0)
return_error(E2BIG);
if (!must_use_null_useddefaultchar(cv->codepage))
{
p = &usedDefaultChar;
#ifdef WC_NO_BEST_FIT_CHARS
if (!(cv->flags & FLAG_TRANSLIT))
flags |= WC_NO_BEST_FIT_CHARS;
#endif
}
len = WideCharToMultiByte(cv->codepage, flags,
(const wchar_t *)wbuf, wbufsize, (char *)buf, bufsize, NULL, p);
if (len == 0)
{
if (GetLastError() == ERROR_INSUFFICIENT_BUFFER)
return_error(E2BIG);
return_error(EILSEQ);
}
else if (usedDefaultChar)
return_error(EILSEQ);
else if (cv->mblen(cv, buf, len) != len) /* validate result */
return_error(EILSEQ);
return len;
}
/*
* It seems that the mode (cv->mode) is fixnum.
* For example, when converting iso-2022-jp(cp50221) to unicode:
* in ascii sequence: mode=0xC42C0000
* in jisx0208 sequence: mode=0xC42C0001
* "C42C" is same for each convert session.
* It should be: ((codepage-1)<<16)|state
*/
static int
mlang_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize)
{
int len;
int insize;
HRESULT hr;
len = cv->mblen(cv, buf, bufsize);
if (len == -1)
return -1;
insize = len;
hr = ConvertINetMultiByteToUnicode(&cv->mode, cv->codepage,
(const char *)buf, &insize, (wchar_t *)wbuf, wbufsize);
if (hr != S_OK || insize != len)
return_error(EILSEQ);
return len;
}
static int
mlang_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize)
{
char tmpbuf[MB_CHAR_MAX]; /* enough room for one character */
int tmpsize = MB_CHAR_MAX;
int insize = wbufsize;
HRESULT hr;
hr = ConvertINetUnicodeToMultiByte(&cv->mode, cv->codepage,
(const wchar_t *)wbuf, &wbufsize, tmpbuf, &tmpsize);
if (hr != S_OK || insize != wbufsize)
return_error(EILSEQ);
else if (bufsize < tmpsize)
return_error(E2BIG);
else if (cv->mblen(cv, (uchar *)tmpbuf, tmpsize) != tmpsize)
return_error(EILSEQ);
memcpy(buf, tmpbuf, tmpsize);
return tmpsize;
}
static int
utf16_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize)
{
if (bufsize < 2)
return_error(EINVAL);
if (cv->codepage == 1200) /* little endian */
wbuf[0] = (buf[1] << 8) | buf[0];
else if (cv->codepage == 1201) /* big endian */
wbuf[0] = (buf[0] << 8) | buf[1];
if (0xDC00 <= wbuf[0] && wbuf[0] <= 0xDFFF)
return_error(EILSEQ);
if (0xD800 <= wbuf[0] && wbuf[0] <= 0xDBFF)
{
if (bufsize < 4)
return_error(EINVAL);
if (cv->codepage == 1200) /* little endian */
wbuf[1] = (buf[3] << 8) | buf[2];
else if (cv->codepage == 1201) /* big endian */
wbuf[1] = (buf[2] << 8) | buf[3];
if (!(0xDC00 <= wbuf[1] && wbuf[1] <= 0xDFFF))
return_error(EILSEQ);
*wbufsize = 2;
return 4;
}
*wbufsize = 1;
return 2;
}
static int
utf16_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize)
{
if (bufsize < 2)
return_error(E2BIG);
if (cv->codepage == 1200) /* little endian */
{
buf[0] = (wbuf[0] & 0x00FF);
buf[1] = (wbuf[0] & 0xFF00) >> 8;
}
else if (cv->codepage == 1201) /* big endian */
{
buf[0] = (wbuf[0] & 0xFF00) >> 8;
buf[1] = (wbuf[0] & 0x00FF);
}
if (0xD800 <= wbuf[0] && wbuf[0] <= 0xDBFF)
{
if (bufsize < 4)
return_error(E2BIG);
if (cv->codepage == 1200) /* little endian */
{
buf[2] = (wbuf[1] & 0x00FF);
buf[3] = (wbuf[1] & 0xFF00) >> 8;
}
else if (cv->codepage == 1201) /* big endian */
{
buf[2] = (wbuf[1] & 0xFF00) >> 8;
buf[3] = (wbuf[1] & 0x00FF);
}
return 4;
}
return 2;
}
static int
utf32_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize)
{
uint wc;
if (bufsize < 4)
return_error(EINVAL);
if (cv->codepage == 12000) /* little endian */
wc = (buf[3] << 24) | (buf[2] << 16) | (buf[1] << 8) | buf[0];
else if (cv->codepage == 12001) /* big endian */
wc = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
if ((0xD800 <= wc && wc <= 0xDFFF) || 0x10FFFF < wc)
return_error(EILSEQ);
ucs4_to_utf16(wc, wbuf, wbufsize);
return 4;
}
static int
utf32_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize)
{
uint wc;
if (bufsize < 4)
return_error(E2BIG);
wc = utf16_to_ucs4(wbuf);
if (cv->codepage == 12000) /* little endian */
{
buf[0] = wc & 0x000000FF;
buf[1] = (wc & 0x0000FF00) >> 8;
buf[2] = (wc & 0x00FF0000) >> 16;
buf[3] = (wc & 0xFF000000) >> 24;
}
else if (cv->codepage == 12001) /* big endian */
{
buf[0] = (wc & 0xFF000000) >> 24;
buf[1] = (wc & 0x00FF0000) >> 16;
buf[2] = (wc & 0x0000FF00) >> 8;
buf[3] = wc & 0x000000FF;
}
return 4;
}
/*
* 50220: ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
* 50221: ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow
* 1 byte Kana)
* 50222: ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte
* Kana - SO/SI)
*
* MultiByteToWideChar() and WideCharToMultiByte() behave differently
* depending on Windows version. On XP, WideCharToMultiByte() doesn't
* terminate result sequence with ascii escape. But Vista does.
* Use MLang instead.
*/
#define ISO2022_MODE(cs, shift) (((cs) << 8) | (shift))
#define ISO2022_MODE_CS(mode) (((mode) >> 8) & 0xFF)
#define ISO2022_MODE_SHIFT(mode) ((mode) & 0xFF)
#define ISO2022_SI 0
#define ISO2022_SO 1
/* shift in */
static const char iso2022_SI_seq[] = "\x0F";
/* shift out */
static const char iso2022_SO_seq[] = "\x0E";
typedef struct iso2022_esc_t iso2022_esc_t;
struct iso2022_esc_t {
const char *esc;
int esc_len;
int len;
int cs;
};
#define ISO2022JP_CS_ASCII 0
#define ISO2022JP_CS_JISX0201_ROMAN 1
#define ISO2022JP_CS_JISX0201_KANA 2
#define ISO2022JP_CS_JISX0208_1978 3
#define ISO2022JP_CS_JISX0208_1983 4
#define ISO2022JP_CS_JISX0212 5
static iso2022_esc_t iso2022jp_esc[] = {
{"\x1B\x28\x42", 3, 1, ISO2022JP_CS_ASCII},
{"\x1B\x28\x4A", 3, 1, ISO2022JP_CS_JISX0201_ROMAN},
{"\x1B\x28\x49", 3, 1, ISO2022JP_CS_JISX0201_KANA},
{"\x1B\x24\x40", 3, 2, ISO2022JP_CS_JISX0208_1983}, /* unify 1978 with 1983 */
{"\x1B\x24\x42", 3, 2, ISO2022JP_CS_JISX0208_1983},
{"\x1B\x24\x28\x44", 4, 2, ISO2022JP_CS_JISX0212},
{NULL, 0, 0, 0}
};
static int
iso2022jp_mbtowc(csconv_t *cv, const uchar *buf, int bufsize, ushort *wbuf, int *wbufsize)
{
iso2022_esc_t *iesc = iso2022jp_esc;
char tmp[MB_CHAR_MAX];
int insize;
HRESULT hr;
DWORD dummy = 0;
int len;
int esc_len;
int cs;
int shift;
int i;
if (buf[0] == 0x1B)
{
for (i = 0; iesc[i].esc != NULL; ++i)
{
esc_len = iesc[i].esc_len;
if (bufsize < esc_len)
{
if (strncmp((char *)buf, iesc[i].esc, bufsize) == 0)
return_error(EINVAL);
}
else
{
if (strncmp((char *)buf, iesc[i].esc, esc_len) == 0)
{
cv->mode = ISO2022_MODE(iesc[i].cs, ISO2022_SI);
*wbufsize = 0;
return esc_len;
}
}
}
/* not supported escape sequence */
return_error(EILSEQ);
}
else if (buf[0] == iso2022_SO_seq[0])
{
cv->mode = ISO2022_MODE(ISO2022_MODE_CS(cv->mode), ISO2022_SO);
*wbufsize = 0;
return 1;
}
else if (buf[0] == iso2022_SI_seq[0])
{
cv->mode = ISO2022_MODE(ISO2022_MODE_CS(cv->mode), ISO2022_SI);
*wbufsize = 0;
return 1;
}
cs = ISO2022_MODE_CS(cv->mode);
shift = ISO2022_MODE_SHIFT(cv->mode);
/* reset the mode for informal sequence */
if (buf[0] < 0x20)
{
cs = ISO2022JP_CS_ASCII;
shift = ISO2022_SI;
}
len = iesc[cs].len;
if (bufsize < len)
return_error(EINVAL);
for (i = 0; i < len; ++i)
if (!(buf[i] < 0x80))
return_error(EILSEQ);
esc_len = iesc[cs].esc_len;
memcpy(tmp, iesc[cs].esc, esc_len);
if (shift == ISO2022_SO)
{
memcpy(tmp + esc_len, iso2022_SO_seq, 1);
esc_len += 1;
}
memcpy(tmp + esc_len, buf, len);
if ((cv->codepage == 50220 || cv->codepage == 50221
|| cv->codepage == 50222) && shift == ISO2022_SO)
{
/* XXX: shift-out cannot be used for mbtowc (both kernel and
* mlang) */
esc_len = iesc[ISO2022JP_CS_JISX0201_KANA].esc_len;
memcpy(tmp, iesc[ISO2022JP_CS_JISX0201_KANA].esc, esc_len);
memcpy(tmp + esc_len, buf, len);
}
insize = len + esc_len;
hr = ConvertINetMultiByteToUnicode(&dummy, cv->codepage,
(const char *)tmp, &insize, (wchar_t *)wbuf, wbufsize);
if (hr != S_OK || insize != len + esc_len)
return_error(EILSEQ);
/* Check for conversion error. Assuming defaultChar is 0x3F. */
/* ascii should be converted from ascii */
if (wbuf[0] == buf[0]
&& cv->mode != ISO2022_MODE(ISO2022JP_CS_ASCII, ISO2022_SI))
return_error(EILSEQ);
/* reset the mode for informal sequence */
if (cv->mode != ISO2022_MODE(cs, shift))
cv->mode = ISO2022_MODE(cs, shift);
return len;
}
static int
iso2022jp_wctomb(csconv_t *cv, ushort *wbuf, int wbufsize, uchar *buf, int bufsize)
{
iso2022_esc_t *iesc = iso2022jp_esc;
char tmp[MB_CHAR_MAX];
int tmpsize = MB_CHAR_MAX;
int insize = wbufsize;
HRESULT hr;
DWORD dummy = 0;
int len;
int esc_len;
int cs;
int shift;
int i;
/*
* MultiByte = [escape sequence] + character + [escape sequence]
*
* Whether trailing escape sequence is added depends on which API is
* used (kernel or MLang, and its version).
*/
hr = ConvertINetUnicodeToMultiByte(&dummy, cv->codepage,
(const wchar_t *)wbuf, &wbufsize, tmp, &tmpsize);
if (hr != S_OK || insize != wbufsize)
return_error(EILSEQ);
else if (bufsize < tmpsize)
return_error(E2BIG);
if (tmpsize == 1)
{
cs = ISO2022JP_CS_ASCII;
esc_len = 0;
}
else
{
for (i = 1; iesc[i].esc != NULL; ++i)
{
esc_len = iesc[i].esc_len;
if (strncmp(tmp, iesc[i].esc, esc_len) == 0)
{
cs = iesc[i].cs;
break;
}
}
if (iesc[i].esc == NULL)
/* not supported escape sequence */
return_error(EILSEQ);
}
shift = ISO2022_SI;
if (tmp[esc_len] == iso2022_SO_seq[0])
{
shift = ISO2022_SO;
esc_len += 1;
}
len = iesc[cs].len;
/* Check for converting error. Assuming defaultChar is 0x3F. */
/* ascii should be converted from ascii */
if (cs == ISO2022JP_CS_ASCII && !(wbuf[0] < 0x80))
return_error(EILSEQ);
else if (tmpsize < esc_len + len)
return_error(EILSEQ);
if (cv->mode == ISO2022_MODE(cs, shift))
{
/* remove escape sequence */
if (esc_len != 0)
memmove(tmp, tmp + esc_len, len);
esc_len = 0;
}
else
{
if (cs == ISO2022JP_CS_ASCII)
{
esc_len = iesc[ISO2022JP_CS_ASCII].esc_len;
memmove(tmp + esc_len, tmp, len);
memcpy(tmp, iesc[ISO2022JP_CS_ASCII].esc, esc_len);
}
if (ISO2022_MODE_SHIFT(cv->mode) == ISO2022_SO)
{
/* shift-in before changing to other mode */
memmove(tmp + 1, tmp, len + esc_len);
memcpy(tmp, iso2022_SI_seq, 1);
esc_len += 1;
}
}
if (bufsize < len + esc_len)
return_error(E2BIG);
memcpy(buf, tmp, len + esc_len);
cv->mode = ISO2022_MODE(cs, shift);
return len + esc_len;
}
static int
iso2022jp_flush(csconv_t *cv, uchar *buf, int bufsize)
{
iso2022_esc_t *iesc = iso2022jp_esc;
int esc_len;
if (cv->mode != ISO2022_MODE(ISO2022JP_CS_ASCII, ISO2022_SI))
{
esc_len = 0;
if (ISO2022_MODE_SHIFT(cv->mode) != ISO2022_SI)
esc_len += 1;
if (ISO2022_MODE_CS(cv->mode) != ISO2022JP_CS_ASCII)
esc_len += iesc[ISO2022JP_CS_ASCII].esc_len;
if (bufsize < esc_len)
return_error(E2BIG);
esc_len = 0;
if (ISO2022_MODE_SHIFT(cv->mode) != ISO2022_SI)
{
memcpy(buf, iso2022_SI_seq, 1);
esc_len += 1;
}
if (ISO2022_MODE_CS(cv->mode) != ISO2022JP_CS_ASCII)
{
memcpy(buf + esc_len, iesc[ISO2022JP_CS_ASCII].esc,
iesc[ISO2022JP_CS_ASCII].esc_len);
esc_len += iesc[ISO2022JP_CS_ASCII].esc_len;
}
return esc_len;
}
return 0;
}
#if defined(MAKE_DLL) && defined(USE_LIBICONV_DLL)
BOOL WINAPI
DllMain(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpReserved)
{
switch( fdwReason )
{
case DLL_PROCESS_ATTACH:
hwiniconv = (HMODULE)hinstDLL;
break;
case DLL_THREAD_ATTACH:
case DLL_THREAD_DETACH:
case DLL_PROCESS_DETACH:
break;
}
return TRUE;
}
#endif
#if defined(MAKE_EXE)
#include <stdio.h>
#include <fcntl.h>
#include <io.h>
int
main(int argc, char **argv)
{
char *fromcode = NULL;
char *tocode = NULL;
int i;
char inbuf[BUFSIZ];
char outbuf[BUFSIZ];
const char *pin;
char *pout;
size_t inbytesleft;
size_t outbytesleft;
size_t rest = 0;
iconv_t cd;
size_t r;
FILE *in = stdin;
_setmode(_fileno(stdin), _O_BINARY);
_setmode(_fileno(stdout), _O_BINARY);
for (i = 1; i < argc; ++i)
{
if (strcmp(argv[i], "-l") == 0)
{
for (i = 0; codepage_alias[i].name != NULL; ++i)
printf("%s\n", codepage_alias[i].name);
return 0;
}
if (strcmp(argv[i], "-f") == 0)
fromcode = argv[++i];
else if (strcmp(argv[i], "-t") == 0)
tocode = argv[++i];
else
{
in = fopen(argv[i], "rb");
if (in == NULL)
{
fprintf(stderr, "cannot open %s\n", argv[i]);
return 1;
}
break;
}
}
if (fromcode == NULL || tocode == NULL)
{
printf("usage: %s -f from-enc -t to-enc [file]\n", argv[0]);
return 0;
}
cd = iconv_open(tocode, fromcode);
if (cd == (iconv_t)(-1))
{
perror("iconv_open error");
return 1;
}
while ((inbytesleft = fread(inbuf + rest, 1, sizeof(inbuf) - rest, in)) != 0
|| rest != 0)
{
inbytesleft += rest;
pin = inbuf;
pout = outbuf;
outbytesleft = sizeof(outbuf);
r = iconv(cd, &pin, &inbytesleft, &pout, &outbytesleft);
fwrite(outbuf, 1, sizeof(outbuf) - outbytesleft, stdout);
if (r == (size_t)(-1) && errno != EINVAL && errno != E2BIG)
{
perror("conversion error");
return 1;
}
memmove(inbuf, pin, inbytesleft);
rest = inbytesleft;
}
pout = outbuf;
outbytesleft = sizeof(outbuf);
r = iconv(cd, NULL, NULL, &pout, &outbytesleft);
fwrite(outbuf, 1, sizeof(outbuf) - outbytesleft, stdout);
if (r == (size_t)(-1))
{
perror("conversion error");
return 1;
}
iconv_close(cd);
return 0;
}
#endif
|