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
|
/* Determine a canonical name for the current locale's character encoding.
Copyright (C) 2000-2006, 2008-2020 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License along
with this program; if not, see <https://www.gnu.org/licenses/>. */
/* Written by Bruno Haible <bruno@clisp.org>. */
#include <config.h>
/* Specification. */
#include "localcharset.h"
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#if defined __APPLE__ && defined __MACH__ && HAVE_LANGINFO_CODESET
# define DARWIN7 /* Darwin 7 or newer, i.e. Mac OS X 10.3 or newer */
#endif
#if defined _WIN32 && !defined __CYGWIN__
# define WINDOWS_NATIVE
# include <locale.h>
#endif
#if defined __EMX__
/* Assume EMX program runs on OS/2, even if compiled under DOS. */
# ifndef OS2
# define OS2
# endif
#endif
#if !defined WINDOWS_NATIVE
# if HAVE_LANGINFO_CODESET
# include <langinfo.h>
# else
# if 0 /* see comment regarding use of setlocale(), below */
# include <locale.h>
# endif
# endif
# ifdef __CYGWIN__
# define WIN32_LEAN_AND_MEAN
# include <windows.h>
# endif
#elif defined WINDOWS_NATIVE
# define WIN32_LEAN_AND_MEAN
# include <windows.h>
/* For the use of setlocale() below, the Gnulib override in setlocale.c is
not needed; see the platform lists in setlocale_null.m4. */
# undef setlocale
#endif
#if defined OS2
# define INCL_DOS
# include <os2.h>
#endif
/* For MB_CUR_MAX_L */
#if defined DARWIN7
# include <xlocale.h>
#endif
#if HAVE_LANGINFO_CODESET || defined WINDOWS_NATIVE || defined OS2
/* On these platforms, we use a mapping from non-canonical encoding name
to GNU canonical encoding name. */
/* With glibc-2.1 or newer, we don't need any canonicalization,
because glibc has iconv and both glibc and libiconv support all
GNU canonical names directly. */
# if !((defined __GNU_LIBRARY__ && __GLIBC__ >= 2) || defined __UCLIBC__)
struct table_entry
{
const char alias[11+1];
const char canonical[11+1];
};
/* Table of platform-dependent mappings, sorted in ascending order. */
static const struct table_entry alias_table[] =
{
# if defined __FreeBSD__ /* FreeBSD */
/*{ "ARMSCII-8", "ARMSCII-8" },*/
{ "Big5", "BIG5" },
{ "C", "ASCII" },
/*{ "CP1131", "CP1131" },*/
/*{ "CP1251", "CP1251" },*/
/*{ "CP866", "CP866" },*/
/*{ "GB18030", "GB18030" },*/
/*{ "GB2312", "GB2312" },*/
/*{ "GBK", "GBK" },*/
/*{ "ISCII-DEV", "?" },*/
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-13", "ISO-8859-13" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-9", "ISO-8859-9" },
/*{ "KOI8-R", "KOI8-R" },*/
/*{ "KOI8-U", "KOI8-U" },*/
{ "SJIS", "SHIFT_JIS" },
{ "US-ASCII", "ASCII" },
{ "eucCN", "GB2312" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" }
# define alias_table_defined
# endif
# if defined __NetBSD__ /* NetBSD */
{ "646", "ASCII" },
/*{ "ARMSCII-8", "ARMSCII-8" },*/
/*{ "BIG5", "BIG5" },*/
{ "Big5-HKSCS", "BIG5-HKSCS" },
/*{ "CP1251", "CP1251" },*/
/*{ "CP866", "CP866" },*/
/*{ "GB18030", "GB18030" },*/
/*{ "GB2312", "GB2312" },*/
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-13", "ISO-8859-13" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
/*{ "KOI8-R", "KOI8-R" },*/
/*{ "KOI8-U", "KOI8-U" },*/
/*{ "PT154", "PT154" },*/
{ "SJIS", "SHIFT_JIS" },
{ "eucCN", "GB2312" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" },
{ "eucTW", "EUC-TW" }
# define alias_table_defined
# endif
# if defined __OpenBSD__ /* OpenBSD */
{ "646", "ASCII" },
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-13", "ISO-8859-13" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "US-ASCII", "ASCII" }
# define alias_table_defined
# endif
# if defined __APPLE__ && defined __MACH__ /* Mac OS X */
/* Darwin 7.5 has nl_langinfo(CODESET), but sometimes its value is
useless:
- It returns the empty string when LANG is set to a locale of the
form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
LC_CTYPE file.
- The environment variables LANG, LC_CTYPE, LC_ALL are not set by
the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
- The documentation says:
"... all code that calls BSD system routines should ensure
that the const *char parameters of these routines are in UTF-8
encoding. All BSD system functions expect their string
parameters to be in UTF-8 encoding and nothing else."
It also says
"An additional caveat is that string parameters for files,
paths, and other file-system entities must be in canonical
UTF-8. In a canonical UTF-8 Unicode string, all decomposable
characters are decomposed ..."
but this is not true: You can pass non-decomposed UTF-8 strings
to file system functions, and it is the OS which will convert
them to decomposed UTF-8 before accessing the file system.
- The Apple Terminal application displays UTF-8 by default.
- However, other applications are free to use different encodings:
- xterm uses ISO-8859-1 by default.
- TextEdit uses MacRoman by default.
We prefer UTF-8 over decomposed UTF-8-MAC because one should
minimize the use of decomposed Unicode. Unfortunately, through the
Darwin file system, decomposed UTF-8 strings are leaked into user
space nevertheless.
Then there are also the locales with encodings other than US-ASCII
and UTF-8. These locales can be occasionally useful to users (e.g.
when grepping through ISO-8859-1 encoded text files), when all their
file names are in US-ASCII.
*/
{ "ARMSCII-8", "ARMSCII-8" },
{ "Big5", "BIG5" },
{ "Big5HKSCS", "BIG5-HKSCS" },
{ "CP1131", "CP1131" },
{ "CP1251", "CP1251" },
{ "CP866", "CP866" },
{ "CP949", "CP949" },
{ "GB18030", "GB18030" },
{ "GB2312", "GB2312" },
{ "GBK", "GBK" },
/*{ "ISCII-DEV", "?" },*/
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-13", "ISO-8859-13" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-9", "ISO-8859-9" },
{ "KOI8-R", "KOI8-R" },
{ "KOI8-U", "KOI8-U" },
{ "PT154", "PT154" },
{ "SJIS", "SHIFT_JIS" },
{ "eucCN", "GB2312" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" }
# define alias_table_defined
# endif
# if defined _AIX /* AIX */
/*{ "GBK", "GBK" },*/
{ "IBM-1046", "CP1046" },
{ "IBM-1124", "CP1124" },
{ "IBM-1129", "CP1129" },
{ "IBM-1252", "CP1252" },
{ "IBM-850", "CP850" },
{ "IBM-856", "CP856" },
{ "IBM-921", "ISO-8859-13" },
{ "IBM-922", "CP922" },
{ "IBM-932", "CP932" },
{ "IBM-943", "CP943" },
{ "IBM-eucCN", "GB2312" },
{ "IBM-eucJP", "EUC-JP" },
{ "IBM-eucKR", "EUC-KR" },
{ "IBM-eucTW", "EUC-TW" },
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-6", "ISO-8859-6" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-8", "ISO-8859-8" },
{ "ISO8859-9", "ISO-8859-9" },
{ "TIS-620", "TIS-620" },
/*{ "UTF-8", "UTF-8" },*/
{ "big5", "BIG5" }
# define alias_table_defined
# endif
# if defined __hpux /* HP-UX */
{ "SJIS", "SHIFT_JIS" },
{ "arabic8", "HP-ARABIC8" },
{ "big5", "BIG5" },
{ "cp1251", "CP1251" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" },
{ "eucTW", "EUC-TW" },
{ "gb18030", "GB18030" },
{ "greek8", "HP-GREEK8" },
{ "hebrew8", "HP-HEBREW8" },
{ "hkbig5", "BIG5-HKSCS" },
{ "hp15CN", "GB2312" },
{ "iso88591", "ISO-8859-1" },
{ "iso885913", "ISO-8859-13" },
{ "iso885915", "ISO-8859-15" },
{ "iso88592", "ISO-8859-2" },
{ "iso88594", "ISO-8859-4" },
{ "iso88595", "ISO-8859-5" },
{ "iso88596", "ISO-8859-6" },
{ "iso88597", "ISO-8859-7" },
{ "iso88598", "ISO-8859-8" },
{ "iso88599", "ISO-8859-9" },
{ "kana8", "HP-KANA8" },
{ "koi8r", "KOI8-R" },
{ "roman8", "HP-ROMAN8" },
{ "tis620", "TIS-620" },
{ "turkish8", "HP-TURKISH8" },
{ "utf8", "UTF-8" }
# define alias_table_defined
# endif
# if defined __sgi /* IRIX */
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-9", "ISO-8859-9" },
{ "eucCN", "GB2312" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" },
{ "eucTW", "EUC-TW" }
# define alias_table_defined
# endif
# if defined __osf__ /* OSF/1 */
/*{ "GBK", "GBK" },*/
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-8", "ISO-8859-8" },
{ "ISO8859-9", "ISO-8859-9" },
{ "KSC5601", "CP949" },
{ "SJIS", "SHIFT_JIS" },
{ "TACTIS", "TIS-620" },
/*{ "UTF-8", "UTF-8" },*/
{ "big5", "BIG5" },
{ "cp850", "CP850" },
{ "dechanyu", "DEC-HANYU" },
{ "dechanzi", "GB2312" },
{ "deckanji", "DEC-KANJI" },
{ "deckorean", "EUC-KR" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" },
{ "eucTW", "EUC-TW" },
{ "sdeckanji", "EUC-JP" }
# define alias_table_defined
# endif
# if defined __sun /* Solaris */
{ "5601", "EUC-KR" },
{ "646", "ASCII" },
/*{ "BIG5", "BIG5" },*/
{ "Big5-HKSCS", "BIG5-HKSCS" },
{ "GB18030", "GB18030" },
/*{ "GBK", "GBK" },*/
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-11", "TIS-620" },
{ "ISO8859-13", "ISO-8859-13" },
{ "ISO8859-15", "ISO-8859-15" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-3", "ISO-8859-3" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-6", "ISO-8859-6" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-8", "ISO-8859-8" },
{ "ISO8859-9", "ISO-8859-9" },
{ "PCK", "SHIFT_JIS" },
{ "TIS620.2533", "TIS-620" },
/*{ "UTF-8", "UTF-8" },*/
{ "ansi-1251", "CP1251" },
{ "cns11643", "EUC-TW" },
{ "eucJP", "EUC-JP" },
{ "gb2312", "GB2312" },
{ "koi8-r", "KOI8-R" }
# define alias_table_defined
# endif
# if defined __minix /* Minix */
{ "646", "ASCII" }
# define alias_table_defined
# endif
# if defined WINDOWS_NATIVE || defined __CYGWIN__ /* Windows */
{ "CP1361", "JOHAB" },
{ "CP20127", "ASCII" },
{ "CP20866", "KOI8-R" },
{ "CP20936", "GB2312" },
{ "CP21866", "KOI8-RU" },
{ "CP28591", "ISO-8859-1" },
{ "CP28592", "ISO-8859-2" },
{ "CP28593", "ISO-8859-3" },
{ "CP28594", "ISO-8859-4" },
{ "CP28595", "ISO-8859-5" },
{ "CP28596", "ISO-8859-6" },
{ "CP28597", "ISO-8859-7" },
{ "CP28598", "ISO-8859-8" },
{ "CP28599", "ISO-8859-9" },
{ "CP28605", "ISO-8859-15" },
{ "CP38598", "ISO-8859-8" },
{ "CP51932", "EUC-JP" },
{ "CP51936", "GB2312" },
{ "CP51949", "EUC-KR" },
{ "CP51950", "EUC-TW" },
{ "CP54936", "GB18030" },
{ "CP65001", "UTF-8" },
{ "CP936", "GBK" }
# define alias_table_defined
# endif
# if defined OS2 /* OS/2 */
/* The list of encodings is taken from "List of OS/2 Codepages"
by Alex Taylor:
<http://altsan.org/os2/toolkits/uls/index.html#codepages>.
See also "__convcp() of kLIBC":
<https://github.com/bitwiseworks/libc/blob/master/src/emx/src/lib/locale/__convcp.c>. */
{ "CP1004", "CP1252" },
/*{ "CP1041", "CP943" },*/
/*{ "CP1088", "CP949" },*/
{ "CP1089", "ISO-8859-6" },
/*{ "CP1114", "CP950" },*/
/*{ "CP1115", "GB2312" },*/
{ "CP1208", "UTF-8" },
/*{ "CP1380", "GB2312" },*/
{ "CP1381", "GB2312" },
{ "CP1383", "GB2312" },
{ "CP1386", "GBK" },
/*{ "CP301", "CP943" },*/
{ "CP3372", "EUC-JP" },
{ "CP4946", "CP850" },
/*{ "CP5048", "JIS_X0208-1990" },*/
/*{ "CP5049", "JIS_X0212-1990" },*/
/*{ "CP5067", "KS_C_5601-1987" },*/
{ "CP813", "ISO-8859-7" },
{ "CP819", "ISO-8859-1" },
{ "CP878", "KOI8-R" },
/*{ "CP897", "CP943" },*/
{ "CP912", "ISO-8859-2" },
{ "CP913", "ISO-8859-3" },
{ "CP914", "ISO-8859-4" },
{ "CP915", "ISO-8859-5" },
{ "CP916", "ISO-8859-8" },
{ "CP920", "ISO-8859-9" },
{ "CP921", "ISO-8859-13" },
{ "CP923", "ISO-8859-15" },
/*{ "CP941", "CP943" },*/
/*{ "CP947", "CP950" },*/
/*{ "CP951", "CP949" },*/
/*{ "CP952", "JIS_X0208-1990" },*/
/*{ "CP953", "JIS_X0212-1990" },*/
{ "CP954", "EUC-JP" },
{ "CP964", "EUC-TW" },
{ "CP970", "EUC-KR" },
/*{ "CP971", "KS_C_5601-1987" },*/
{ "IBM-1004", "CP1252" },
/*{ "IBM-1006", "?" },*/
/*{ "IBM-1008", "?" },*/
/*{ "IBM-1041", "CP943" },*/
/*{ "IBM-1051", "?" },*/
/*{ "IBM-1088", "CP949" },*/
{ "IBM-1089", "ISO-8859-6" },
/*{ "IBM-1098", "?" },*/
/*{ "IBM-1114", "CP950" },*/
/*{ "IBM-1115", "GB2312" },*/
/*{ "IBM-1116", "?" },*/
/*{ "IBM-1117", "?" },*/
/*{ "IBM-1118", "?" },*/
/*{ "IBM-1119", "?" },*/
{ "IBM-1124", "CP1124" },
{ "IBM-1125", "CP1125" },
{ "IBM-1131", "CP1131" },
{ "IBM-1208", "UTF-8" },
{ "IBM-1250", "CP1250" },
{ "IBM-1251", "CP1251" },
{ "IBM-1252", "CP1252" },
{ "IBM-1253", "CP1253" },
{ "IBM-1254", "CP1254" },
{ "IBM-1255", "CP1255" },
{ "IBM-1256", "CP1256" },
{ "IBM-1257", "CP1257" },
/*{ "IBM-1275", "?" },*/
/*{ "IBM-1276", "?" },*/
/*{ "IBM-1277", "?" },*/
/*{ "IBM-1280", "?" },*/
/*{ "IBM-1281", "?" },*/
/*{ "IBM-1282", "?" },*/
/*{ "IBM-1283", "?" },*/
/*{ "IBM-1380", "GB2312" },*/
{ "IBM-1381", "GB2312" },
{ "IBM-1383", "GB2312" },
{ "IBM-1386", "GBK" },
/*{ "IBM-301", "CP943" },*/
{ "IBM-3372", "EUC-JP" },
{ "IBM-367", "ASCII" },
{ "IBM-437", "CP437" },
{ "IBM-4946", "CP850" },
/*{ "IBM-5048", "JIS_X0208-1990" },*/
/*{ "IBM-5049", "JIS_X0212-1990" },*/
/*{ "IBM-5067", "KS_C_5601-1987" },*/
{ "IBM-813", "ISO-8859-7" },
{ "IBM-819", "ISO-8859-1" },
{ "IBM-850", "CP850" },
/*{ "IBM-851", "?" },*/
{ "IBM-852", "CP852" },
{ "IBM-855", "CP855" },
{ "IBM-856", "CP856" },
{ "IBM-857", "CP857" },
/*{ "IBM-859", "?" },*/
{ "IBM-860", "CP860" },
{ "IBM-861", "CP861" },
{ "IBM-862", "CP862" },
{ "IBM-863", "CP863" },
{ "IBM-864", "CP864" },
{ "IBM-865", "CP865" },
{ "IBM-866", "CP866" },
/*{ "IBM-868", "?" },*/
{ "IBM-869", "CP869" },
{ "IBM-874", "CP874" },
{ "IBM-878", "KOI8-R" },
/*{ "IBM-895", "?" },*/
/*{ "IBM-897", "CP943" },*/
/*{ "IBM-907", "?" },*/
/*{ "IBM-909", "?" },*/
{ "IBM-912", "ISO-8859-2" },
{ "IBM-913", "ISO-8859-3" },
{ "IBM-914", "ISO-8859-4" },
{ "IBM-915", "ISO-8859-5" },
{ "IBM-916", "ISO-8859-8" },
{ "IBM-920", "ISO-8859-9" },
{ "IBM-921", "ISO-8859-13" },
{ "IBM-922", "CP922" },
{ "IBM-923", "ISO-8859-15" },
{ "IBM-932", "CP932" },
/*{ "IBM-941", "CP943" },*/
/*{ "IBM-942", "?" },*/
{ "IBM-943", "CP943" },
/*{ "IBM-947", "CP950" },*/
{ "IBM-949", "CP949" },
{ "IBM-950", "CP950" },
/*{ "IBM-951", "CP949" },*/
/*{ "IBM-952", "JIS_X0208-1990" },*/
/*{ "IBM-953", "JIS_X0212-1990" },*/
{ "IBM-954", "EUC-JP" },
/*{ "IBM-955", "?" },*/
{ "IBM-964", "EUC-TW" },
{ "IBM-970", "EUC-KR" },
/*{ "IBM-971", "KS_C_5601-1987" },*/
{ "IBM-eucCN", "GB2312" },
{ "IBM-eucJP", "EUC-JP" },
{ "IBM-eucKR", "EUC-KR" },
{ "IBM-eucTW", "EUC-TW" },
{ "IBM33722", "EUC-JP" },
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-3", "ISO-8859-3" },
{ "ISO8859-4", "ISO-8859-4" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-6", "ISO-8859-6" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-8", "ISO-8859-8" },
{ "ISO8859-9", "ISO-8859-9" },
/*{ "JISX0201-1976", "JISX0201-1976" },*/
/*{ "JISX0208-1978", "?" },*/
/*{ "JISX0208-1983", "JIS_X0208-1983" },*/
/*{ "JISX0208-1990", "JIS_X0208-1990" },*/
/*{ "JISX0212-1990", "JIS_X0212-1990" },*/
/*{ "KSC5601-1987", "KS_C_5601-1987" },*/
{ "SJIS-1", "CP943" },
{ "SJIS-2", "CP943" },
{ "eucJP", "EUC-JP" },
{ "eucKR", "EUC-KR" },
{ "eucTW-1993", "EUC-TW" }
# define alias_table_defined
# endif
# if defined VMS /* OpenVMS */
/* The list of encodings is taken from the OpenVMS 7.3-1 documentation
"Compaq C Run-Time Library Reference Manual for OpenVMS systems"
section 10.7 "Handling Different Character Sets". */
{ "DECHANYU", "DEC-HANYU" },
{ "DECHANZI", "GB2312" },
{ "DECKANJI", "DEC-KANJI" },
{ "DECKOREAN", "EUC-KR" },
{ "ISO8859-1", "ISO-8859-1" },
{ "ISO8859-2", "ISO-8859-2" },
{ "ISO8859-5", "ISO-8859-5" },
{ "ISO8859-7", "ISO-8859-7" },
{ "ISO8859-8", "ISO-8859-8" },
{ "ISO8859-9", "ISO-8859-9" },
{ "SDECKANJI", "EUC-JP" },
{ "SJIS", "SHIFT_JIS" },
{ "eucJP", "EUC-JP" },
{ "eucTW", "EUC-TW" }
# define alias_table_defined
# endif
# ifndef alias_table_defined
/* Just a dummy entry, to avoid a C syntax error. */
{ "", "" }
# endif
};
# endif
#else
/* On these platforms, we use a mapping from locale name to GNU canonical
encoding name. */
struct table_entry
{
const char locale[17+1];
const char canonical[11+1];
};
/* Table of platform-dependent mappings, sorted in ascending order. */
static const struct table_entry locale_table[] =
{
# if defined __FreeBSD__ /* FreeBSD 4.2 */
{ "cs_CZ.ISO_8859-2", "ISO-8859-2" },
{ "da_DK.DIS_8859-15", "ISO-8859-15" },
{ "da_DK.ISO_8859-1", "ISO-8859-1" },
{ "de_AT.DIS_8859-15", "ISO-8859-15" },
{ "de_AT.ISO_8859-1", "ISO-8859-1" },
{ "de_CH.DIS_8859-15", "ISO-8859-15" },
{ "de_CH.ISO_8859-1", "ISO-8859-1" },
{ "de_DE.DIS_8859-15", "ISO-8859-15" },
{ "de_DE.ISO_8859-1", "ISO-8859-1" },
{ "en_AU.DIS_8859-15", "ISO-8859-15" },
{ "en_AU.ISO_8859-1", "ISO-8859-1" },
{ "en_CA.DIS_8859-15", "ISO-8859-15" },
{ "en_CA.ISO_8859-1", "ISO-8859-1" },
{ "en_GB.DIS_8859-15", "ISO-8859-15" },
{ "en_GB.ISO_8859-1", "ISO-8859-1" },
{ "en_US.DIS_8859-15", "ISO-8859-15" },
{ "en_US.ISO_8859-1", "ISO-8859-1" },
{ "es_ES.DIS_8859-15", "ISO-8859-15" },
{ "es_ES.ISO_8859-1", "ISO-8859-1" },
{ "fi_FI.DIS_8859-15", "ISO-8859-15" },
{ "fi_FI.ISO_8859-1", "ISO-8859-1" },
{ "fr_BE.DIS_8859-15", "ISO-8859-15" },
{ "fr_BE.ISO_8859-1", "ISO-8859-1" },
{ "fr_CA.DIS_8859-15", "ISO-8859-15" },
{ "fr_CA.ISO_8859-1", "ISO-8859-1" },
{ "fr_CH.DIS_8859-15", "ISO-8859-15" },
{ "fr_CH.ISO_8859-1", "ISO-8859-1" },
{ "fr_FR.DIS_8859-15", "ISO-8859-15" },
{ "fr_FR.ISO_8859-1", "ISO-8859-1" },
{ "hr_HR.ISO_8859-2", "ISO-8859-2" },
{ "hu_HU.ISO_8859-2", "ISO-8859-2" },
{ "is_IS.DIS_8859-15", "ISO-8859-15" },
{ "is_IS.ISO_8859-1", "ISO-8859-1" },
{ "it_CH.DIS_8859-15", "ISO-8859-15" },
{ "it_CH.ISO_8859-1", "ISO-8859-1" },
{ "it_IT.DIS_8859-15", "ISO-8859-15" },
{ "it_IT.ISO_8859-1", "ISO-8859-1" },
{ "ja_JP.EUC", "EUC-JP" },
{ "ja_JP.SJIS", "SHIFT_JIS" },
{ "ja_JP.Shift_JIS", "SHIFT_JIS" },
{ "ko_KR.EUC", "EUC-KR" },
{ "la_LN.ASCII", "ASCII" },
{ "la_LN.DIS_8859-15", "ISO-8859-15" },
{ "la_LN.ISO_8859-1", "ISO-8859-1" },
{ "la_LN.ISO_8859-2", "ISO-8859-2" },
{ "la_LN.ISO_8859-4", "ISO-8859-4" },
{ "lt_LN.ASCII", "ASCII" },
{ "lt_LN.DIS_8859-15", "ISO-8859-15" },
{ "lt_LN.ISO_8859-1", "ISO-8859-1" },
{ "lt_LN.ISO_8859-2", "ISO-8859-2" },
{ "lt_LT.ISO_8859-4", "ISO-8859-4" },
{ "nl_BE.DIS_8859-15", "ISO-8859-15" },
{ "nl_BE.ISO_8859-1", "ISO-8859-1" },
{ "nl_NL.DIS_8859-15", "ISO-8859-15" },
{ "nl_NL.ISO_8859-1", "ISO-8859-1" },
{ "no_NO.DIS_8859-15", "ISO-8859-15" },
{ "no_NO.ISO_8859-1", "ISO-8859-1" },
{ "pl_PL.ISO_8859-2", "ISO-8859-2" },
{ "pt_PT.DIS_8859-15", "ISO-8859-15" },
{ "pt_PT.ISO_8859-1", "ISO-8859-1" },
{ "ru_RU.CP866", "CP866" },
{ "ru_RU.ISO_8859-5", "ISO-8859-5" },
{ "ru_RU.KOI8-R", "KOI8-R" },
{ "ru_SU.CP866", "CP866" },
{ "ru_SU.ISO_8859-5", "ISO-8859-5" },
{ "ru_SU.KOI8-R", "KOI8-R" },
{ "sl_SI.ISO_8859-2", "ISO-8859-2" },
{ "sv_SE.DIS_8859-15", "ISO-8859-15" },
{ "sv_SE.ISO_8859-1", "ISO-8859-1" },
{ "uk_UA.KOI8-U", "KOI8-U" },
{ "zh_CN.EUC", "GB2312" },
{ "zh_TW.BIG5", "BIG5" },
{ "zh_TW.Big5", "BIG5" }
# define locale_table_defined
# endif
# if defined __DJGPP__ /* DOS / DJGPP 2.03 */
/* The encodings given here may not all be correct.
If you find that the encoding given for your language and
country is not the one your DOS machine actually uses, just
correct it in this file, and send a mail to
Juan Manuel Guerrero <juan.guerrero@gmx.de>
and <bug-gnulib@gnu.org>. */
{ "C", "ASCII" },
{ "ar", "CP864" },
{ "ar_AE", "CP864" },
{ "ar_DZ", "CP864" },
{ "ar_EG", "CP864" },
{ "ar_IQ", "CP864" },
{ "ar_IR", "CP864" },
{ "ar_JO", "CP864" },
{ "ar_KW", "CP864" },
{ "ar_MA", "CP864" },
{ "ar_OM", "CP864" },
{ "ar_QA", "CP864" },
{ "ar_SA", "CP864" },
{ "ar_SY", "CP864" },
{ "be", "CP866" },
{ "be_BE", "CP866" },
{ "bg", "CP866" }, /* not CP855 ?? */
{ "bg_BG", "CP866" }, /* not CP855 ?? */
{ "ca", "CP850" },
{ "ca_ES", "CP850" },
{ "cs", "CP852" },
{ "cs_CZ", "CP852" },
{ "da", "CP865" }, /* not CP850 ?? */
{ "da_DK", "CP865" }, /* not CP850 ?? */
{ "de", "CP850" },
{ "de_AT", "CP850" },
{ "de_CH", "CP850" },
{ "de_DE", "CP850" },
{ "el", "CP869" },
{ "el_GR", "CP869" },
{ "en", "CP850" },
{ "en_AU", "CP850" }, /* not CP437 ?? */
{ "en_CA", "CP850" },
{ "en_GB", "CP850" },
{ "en_NZ", "CP437" },
{ "en_US", "CP437" },
{ "en_ZA", "CP850" }, /* not CP437 ?? */
{ "eo", "CP850" },
{ "eo_EO", "CP850" },
{ "es", "CP850" },
{ "es_AR", "CP850" },
{ "es_BO", "CP850" },
{ "es_CL", "CP850" },
{ "es_CO", "CP850" },
{ "es_CR", "CP850" },
{ "es_CU", "CP850" },
{ "es_DO", "CP850" },
{ "es_EC", "CP850" },
{ "es_ES", "CP850" },
{ "es_GT", "CP850" },
{ "es_HN", "CP850" },
{ "es_MX", "CP850" },
{ "es_NI", "CP850" },
{ "es_PA", "CP850" },
{ "es_PE", "CP850" },
{ "es_PY", "CP850" },
{ "es_SV", "CP850" },
{ "es_UY", "CP850" },
{ "es_VE", "CP850" },
{ "et", "CP850" },
{ "et_EE", "CP850" },
{ "eu", "CP850" },
{ "eu_ES", "CP850" },
{ "fi", "CP850" },
{ "fi_FI", "CP850" },
{ "fr", "CP850" },
{ "fr_BE", "CP850" },
{ "fr_CA", "CP850" },
{ "fr_CH", "CP850" },
{ "fr_FR", "CP850" },
{ "ga", "CP850" },
{ "ga_IE", "CP850" },
{ "gd", "CP850" },
{ "gd_GB", "CP850" },
{ "gl", "CP850" },
{ "gl_ES", "CP850" },
{ "he", "CP862" },
{ "he_IL", "CP862" },
{ "hr", "CP852" },
{ "hr_HR", "CP852" },
{ "hu", "CP852" },
{ "hu_HU", "CP852" },
{ "id", "CP850" }, /* not CP437 ?? */
{ "id_ID", "CP850" }, /* not CP437 ?? */
{ "is", "CP861" }, /* not CP850 ?? */
{ "is_IS", "CP861" }, /* not CP850 ?? */
{ "it", "CP850" },
{ "it_CH", "CP850" },
{ "it_IT", "CP850" },
{ "ja", "CP932" },
{ "ja_JP", "CP932" },
{ "kr", "CP949" }, /* not CP934 ?? */
{ "kr_KR", "CP949" }, /* not CP934 ?? */
{ "lt", "CP775" },
{ "lt_LT", "CP775" },
{ "lv", "CP775" },
{ "lv_LV", "CP775" },
{ "mk", "CP866" }, /* not CP855 ?? */
{ "mk_MK", "CP866" }, /* not CP855 ?? */
{ "mt", "CP850" },
{ "mt_MT", "CP850" },
{ "nb", "CP865" }, /* not CP850 ?? */
{ "nb_NO", "CP865" }, /* not CP850 ?? */
{ "nl", "CP850" },
{ "nl_BE", "CP850" },
{ "nl_NL", "CP850" },
{ "nn", "CP865" }, /* not CP850 ?? */
{ "nn_NO", "CP865" }, /* not CP850 ?? */
{ "no", "CP865" }, /* not CP850 ?? */
{ "no_NO", "CP865" }, /* not CP850 ?? */
{ "pl", "CP852" },
{ "pl_PL", "CP852" },
{ "pt", "CP850" },
{ "pt_BR", "CP850" },
{ "pt_PT", "CP850" },
{ "ro", "CP852" },
{ "ro_RO", "CP852" },
{ "ru", "CP866" },
{ "ru_RU", "CP866" },
{ "sk", "CP852" },
{ "sk_SK", "CP852" },
{ "sl", "CP852" },
{ "sl_SI", "CP852" },
{ "sq", "CP852" },
{ "sq_AL", "CP852" },
{ "sr", "CP852" }, /* CP852 or CP866 or CP855 ?? */
{ "sr_CS", "CP852" }, /* CP852 or CP866 or CP855 ?? */
{ "sr_YU", "CP852" }, /* CP852 or CP866 or CP855 ?? */
{ "sv", "CP850" },
{ "sv_SE", "CP850" },
{ "th", "CP874" },
{ "th_TH", "CP874" },
{ "tr", "CP857" },
{ "tr_TR", "CP857" },
{ "uk", "CP1125" },
{ "uk_UA", "CP1125" },
{ "zh_CN", "GBK" },
{ "zh_TW", "CP950" } /* not CP938 ?? */
# define locale_table_defined
# endif
# ifndef locale_table_defined
/* Just a dummy entry, to avoid a C syntax error. */
{ "", "" }
# endif
};
#endif
/* Determine the current locale's character encoding, and canonicalize it
into one of the canonical names listed below.
The result must not be freed; it is statically allocated. The result
becomes invalid when setlocale() is used to change the global locale, or
when the value of one of the environment variables LC_ALL, LC_CTYPE, LANG
is changed; threads in multithreaded programs should not do this.
If the canonical name cannot be determined, the result is a non-canonical
name. */
#ifdef STATIC
STATIC
#endif
const char *
locale_charset (void)
{
const char *codeset;
/* This function must be multithread-safe. To achieve this without using
thread-local storage, we use a simple strcpy or memcpy to fill this static
buffer. Filling it through, for example, strcpy + strcat would not be
guaranteed to leave the buffer's contents intact if another thread is
currently accessing it. If necessary, the contents is first assembled in
a stack-allocated buffer. */
#if HAVE_LANGINFO_CODESET || defined WINDOWS_NATIVE || defined OS2
# if HAVE_LANGINFO_CODESET
/* Most systems support nl_langinfo (CODESET) nowadays. */
codeset = nl_langinfo (CODESET);
# ifdef __CYGWIN__
/* Cygwin < 1.7 does not have locales. nl_langinfo (CODESET) always
returns "US-ASCII". Return the suffix of the locale name from the
environment variables (if present) or the codepage as a number. */
if (codeset != NULL && strcmp (codeset, "US-ASCII") == 0)
{
const char *locale;
static char resultbuf[2 + 10 + 1];
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
/* If the locale name contains an encoding after the dot, return
it. */
const char *dot = strchr (locale, '.');
if (dot != NULL)
{
const char *modifier;
dot++;
/* Look for the possible @... trailer and remove it, if any. */
modifier = strchr (dot, '@');
if (modifier == NULL)
return dot;
if (modifier - dot < sizeof (resultbuf))
{
/* This way of filling resultbuf is multithread-safe. */
memcpy (resultbuf, dot, modifier - dot);
resultbuf [modifier - dot] = '\0';
return resultbuf;
}
}
}
/* The Windows API has a function returning the locale's codepage as a
number: GetACP(). This encoding is used by Cygwin, unless the user
has set the environment variable CYGWIN=codepage:oem (which very few
people do).
Output directed to console windows needs to be converted (to
GetOEMCP() if the console is using a raster font, or to
GetConsoleOutputCP() if it is using a TrueType font). Cygwin does
this conversion transparently (see winsup/cygwin/fhandler_console.cc),
converting to GetConsoleOutputCP(). This leads to correct results,
except when SetConsoleOutputCP has been called and a raster font is
in use. */
{
char buf[2 + 10 + 1];
sprintf (buf, "CP%u", GetACP ());
strcpy (resultbuf, buf);
codeset = resultbuf;
}
}
# endif
if (codeset == NULL)
/* The canonical name cannot be determined. */
codeset = "";
# elif defined WINDOWS_NATIVE
char buf[2 + 10 + 1];
static char resultbuf[2 + 10 + 1];
/* The Windows API has a function returning the locale's codepage as
a number, but the value doesn't change according to what the
'setlocale' call specified. So we use it as a last resort, in
case the string returned by 'setlocale' doesn't specify the
codepage. */
char *current_locale = setlocale (LC_CTYPE, NULL);
char *pdot = strrchr (current_locale, '.');
if (pdot && 2 + strlen (pdot + 1) + 1 <= sizeof (buf))
sprintf (buf, "CP%s", pdot + 1);
else
{
/* The Windows API has a function returning the locale's codepage as a
number: GetACP().
When the output goes to a console window, it needs to be provided in
GetOEMCP() encoding if the console is using a raster font, or in
GetConsoleOutputCP() encoding if it is using a TrueType font.
But in GUI programs and for output sent to files and pipes, GetACP()
encoding is the best bet. */
sprintf (buf, "CP%u", GetACP ());
}
/* For a locale name such as "French_France.65001", in Windows 10,
setlocale now returns "French_France.utf8" instead. */
if (strcmp (buf + 2, "65001") == 0 || strcmp (buf + 2, "utf8") == 0)
codeset = "UTF-8";
else
{
strcpy (resultbuf, buf);
codeset = resultbuf;
}
# elif defined OS2
const char *locale;
static char resultbuf[2 + 10 + 1];
ULONG cp[3];
ULONG cplen;
codeset = NULL;
/* Allow user to override the codeset, as set in the operating system,
with standard language environment variables. */
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
/* If the locale name contains an encoding after the dot, return it. */
const char *dot = strchr (locale, '.');
if (dot != NULL)
{
const char *modifier;
dot++;
/* Look for the possible @... trailer and remove it, if any. */
modifier = strchr (dot, '@');
if (modifier == NULL)
return dot;
if (modifier - dot < sizeof (resultbuf))
{
/* This way of filling resultbuf is multithread-safe. */
memcpy (resultbuf, dot, modifier - dot);
resultbuf [modifier - dot] = '\0';
return resultbuf;
}
}
/* For the POSIX locale, don't use the system's codepage. */
if (strcmp (locale, "C") == 0 || strcmp (locale, "POSIX") == 0)
codeset = "";
}
if (codeset == NULL)
{
/* OS/2 has a function returning the locale's codepage as a number. */
if (DosQueryCp (sizeof (cp), cp, &cplen))
codeset = "";
else
{
char buf[2 + 10 + 1];
sprintf (buf, "CP%u", cp[0]);
strcpy (resultbuf, buf);
codeset = resultbuf;
}
}
# else
# error "Add code for other platforms here."
# endif
/* Resolve alias. */
{
# ifdef alias_table_defined
/* On some platforms, UTF-8 locales are the most frequently used ones.
Speed up the common case and slow down the less common cases by
testing for this case first. */
# if defined __OpenBSD__ || (defined __APPLE__ && defined __MACH__) || defined __sun || defined __CYGWIN__
if (strcmp (codeset, "UTF-8") == 0)
goto done_table_lookup;
else
# endif
{
const struct table_entry * const table = alias_table;
size_t const table_size =
sizeof (alias_table) / sizeof (struct table_entry);
/* The table is sorted. Perform a binary search. */
size_t hi = table_size;
size_t lo = 0;
while (lo < hi)
{
/* Invariant:
for i < lo, strcmp (table[i].alias, codeset) < 0,
for i >= hi, strcmp (table[i].alias, codeset) > 0. */
size_t mid = (hi + lo) >> 1; /* >= lo, < hi */
int cmp = strcmp (table[mid].alias, codeset);
if (cmp < 0)
lo = mid + 1;
else if (cmp > 0)
hi = mid;
else
{
/* Found an i with
strcmp (table[i].alias, codeset) == 0. */
codeset = table[mid].canonical;
goto done_table_lookup;
}
}
}
if (0)
done_table_lookup: ;
else
# endif
{
/* Did not find it in the table. */
/* On Mac OS X, all modern locales use the UTF-8 encoding.
BeOS and Haiku have a single locale, and it has UTF-8 encoding. */
# if (defined __APPLE__ && defined __MACH__) || defined __BEOS__ || defined __HAIKU__
codeset = "UTF-8";
# else
/* Don't return an empty string. GNU libc and GNU libiconv interpret
the empty string as denoting "the locale's character encoding",
thus GNU libiconv would call this function a second time. */
if (codeset[0] == '\0')
codeset = "ASCII";
# endif
}
}
#else
/* On old systems which lack it, use setlocale or getenv. */
const char *locale = NULL;
/* But most old systems don't have a complete set of locales. Some
(like DJGPP) have only the C locale. Therefore we don't use setlocale
here; it would return "C" when it doesn't support the locale name the
user has set. */
# if 0
locale = setlocale (LC_CTYPE, NULL);
# endif
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
if (locale == NULL)
locale = "";
}
}
/* Map locale name to canonical encoding name. */
{
# ifdef locale_table_defined
const struct table_entry * const table = locale_table;
size_t const table_size =
sizeof (locale_table) / sizeof (struct table_entry);
/* The table is sorted. Perform a binary search. */
size_t hi = table_size;
size_t lo = 0;
while (lo < hi)
{
/* Invariant:
for i < lo, strcmp (table[i].locale, locale) < 0,
for i >= hi, strcmp (table[i].locale, locale) > 0. */
size_t mid = (hi + lo) >> 1; /* >= lo, < hi */
int cmp = strcmp (table[mid].locale, locale);
if (cmp < 0)
lo = mid + 1;
else if (cmp > 0)
hi = mid;
else
{
/* Found an i with
strcmp (table[i].locale, locale) == 0. */
codeset = table[mid].canonical;
goto done_table_lookup;
}
}
if (0)
done_table_lookup: ;
else
# endif
{
/* Did not find it in the table. */
/* On Mac OS X, all modern locales use the UTF-8 encoding.
BeOS and Haiku have a single locale, and it has UTF-8 encoding. */
# if (defined __APPLE__ && defined __MACH__) || defined __BEOS__ || defined __HAIKU__
codeset = "UTF-8";
# else
/* The canonical name cannot be determined. */
/* Don't return an empty string. GNU libc and GNU libiconv interpret
the empty string as denoting "the locale's character encoding",
thus GNU libiconv would call this function a second time. */
codeset = "ASCII";
# endif
}
}
#endif
#ifdef DARWIN7
/* Mac OS X sets MB_CUR_MAX to 1 when LC_ALL=C, and "UTF-8"
(the default codeset) does not work when MB_CUR_MAX is 1. */
if (strcmp (codeset, "UTF-8") == 0 && MB_CUR_MAX_L (uselocale (NULL)) <= 1)
codeset = "ASCII";
#endif
return codeset;
}
|
