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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 1999-2015, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
*
* ucnv_io.cpp:
* initializes global variables and defines functions pertaining to converter
* name resolution aspect of the conversion code.
*
* new implementation:
*
* created on: 1999nov22
* created by: Markus W. Scherer
*
* Use the binary cnvalias.icu (created from convrtrs.txt) to work
* with aliases for converter names.
*
* Date Name Description
* 11/22/1999 markus Created
* 06/28/2002 grhoten Major overhaul of the converter alias design.
* Now an alias can map to different converters
* depending on the specified standard.
*******************************************************************************
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_CONVERSION
#include "unicode/ucnv.h"
#include "unicode/udata.h"
#include "umutex.h"
#include "uarrsort.h"
#include "uassert.h"
#include "udataswp.h"
#include "cstring.h"
#include "cmemory.h"
#include "ucnv_io.h"
#include "uenumimp.h"
#include "ucln_cmn.h"
/* Format of cnvalias.icu -----------------------------------------------------
*
* cnvalias.icu is a binary, memory-mappable form of convrtrs.txt.
* This binary form contains several tables. All indexes are to uint16_t
* units, and not to the bytes (uint8_t units). Addressing everything on
* 16-bit boundaries allows us to store more information with small index
* numbers, which are also 16-bit in size. The majority of the table (except
* the string table) are 16-bit numbers.
*
* First there is the size of the Table of Contents (TOC). The TOC
* entries contain the size of each section. In order to find the offset
* you just need to sum up the previous offsets.
* The TOC length and entries are an array of uint32_t values.
* The first section after the TOC starts immediately after the TOC.
*
* 1) This section contains a list of converters. This list contains indexes
* into the string table for the converter name. The index of this list is
* also used by other sections, which are mentioned later on.
* This list is not sorted.
*
* 2) This section contains a list of tags. This list contains indexes
* into the string table for the tag name. The index of this list is
* also used by other sections, which are mentioned later on.
* This list is in priority order of standards.
*
* 3) This section contains a list of sorted unique aliases. This
* list contains indexes into the string table for the alias name. The
* index of this list is also used by other sections, like the 4th section.
* The index for the 3rd and 4th section is used to get the
* alias -> converter name mapping. Section 3 and 4 form a two column table.
* Some of the most significant bits of each index may contain other
* information (see findConverter for details).
*
* 4) This section contains a list of mapped converter names. Consider this
* as a table that maps the 3rd section to the 1st section. This list contains
* indexes into the 1st section. The index of this list is the same index in
* the 3rd section. There is also some extra information in the high bits of
* each converter index in this table. Currently it's only used to say that
* an alias mapped to this converter is ambiguous. See UCNV_CONVERTER_INDEX_MASK
* and UCNV_AMBIGUOUS_ALIAS_MAP_BIT for more information. This section is
* the predigested form of the 5th section so that an alias lookup can be fast.
*
* 5) This section contains a 2D array with indexes to the 6th section. This
* section is the full form of all alias mappings. The column index is the
* index into the converter list (column header). The row index is the index
* to tag list (row header). This 2D array is the top part a 3D array. The
* third dimension is in the 6th section.
*
* 6) This is blob of variable length arrays. Each array starts with a size,
* and is followed by indexes to alias names in the string table. This is
* the third dimension to the section 5. No other section should be referencing
* this section.
*
* 7) Starting in ICU 3.6, this can be a UConverterAliasOptions struct. Its
* presence indicates that a section 9 exists. UConverterAliasOptions specifies
* what type of string normalization is used among other potential things in the
* future.
*
* 8) This is the string table. All strings are indexed on an even address.
* There are two reasons for this. First many chip architectures locate strings
* faster on even address boundaries. Second, since all indexes are 16-bit
* numbers, this string table can be 128KB in size instead of 64KB when we
* only have strings starting on an even address.
*
* 9) When present this is a set of prenormalized strings from section 8. This
* table contains normalized strings with the dashes and spaces stripped out,
* and all strings lowercased. In the future, the options in section 7 may state
* other types of normalization.
*
* Here is the concept of section 5 and 6. It's a 3D cube. Each tag
* has a unique alias among all converters. That same alias can
* be mentioned in other standards on different converters,
* but only one alias per tag can be unique.
*
*
* Converter Names (Usually in TR22 form)
* -------------------------------------------.
* T / /|
* a / / |
* g / / |
* s / / |
* / / |
* ------------------------------------------/ |
* A | | |
* l | | |
* i | | /
* a | | /
* s | | /
* e | | /
* s | |/
* -------------------------------------------
*
*
*
* Here is what it really looks like. It's like swiss cheese.
* There are holes. Some converters aren't recognized by
* a standard, or they are really old converters that the
* standard doesn't recognize anymore.
*
* Converter Names (Usually in TR22 form)
* -------------------------------------------.
* T /##########################################/|
* a / # # /#
* g / # ## ## ### # ### ### ### #/
* s / # ##### #### ## ## #/#
* / ### # # ## # # # ### # # #/##
* ------------------------------------------/# #
* A |### # # ## # # # ### # # #|# #
* l |# # # # # ## # #|# #
* i |# # # # # # #|#
* a |# #|#
* s | #|#
* e
* s
*
*/
/**
* Used by the UEnumeration API
*/
typedef struct UAliasContext {
uint32_t listOffset;
uint32_t listIdx;
} UAliasContext;
static const char DATA_NAME[] = "cnvalias";
static const char DATA_TYPE[] = "icu";
static UDataMemory *gAliasData=nullptr;
static icu::UInitOnce gAliasDataInitOnce {};
enum {
tocLengthIndex=0,
converterListIndex=1,
tagListIndex=2,
aliasListIndex=3,
untaggedConvArrayIndex=4,
taggedAliasArrayIndex=5,
taggedAliasListsIndex=6,
tableOptionsIndex=7,
stringTableIndex=8,
normalizedStringTableIndex=9,
offsetsCount, /* length of the swapper's temporary offsets[] */
minTocLength=8 /* min. tocLength in the file, does not count the tocLengthIndex! */
};
static const UConverterAliasOptions defaultTableOptions = {
UCNV_IO_UNNORMALIZED,
0 /* containsCnvOptionInfo */
};
static UConverterAlias gMainTable;
#define GET_STRING(idx) (const char *)(gMainTable.stringTable + (idx))
#define GET_NORMALIZED_STRING(idx) (const char *)(gMainTable.normalizedStringTable + (idx))
static UBool U_CALLCONV
isAcceptable(void * /*context*/,
const char * /*type*/, const char * /*name*/,
const UDataInfo *pInfo) {
return
pInfo->size>=20 &&
pInfo->isBigEndian==U_IS_BIG_ENDIAN &&
pInfo->charsetFamily==U_CHARSET_FAMILY &&
pInfo->dataFormat[0]==0x43 && /* dataFormat="CvAl" */
pInfo->dataFormat[1]==0x76 &&
pInfo->dataFormat[2]==0x41 &&
pInfo->dataFormat[3]==0x6c &&
pInfo->formatVersion[0]==3;
}
static UBool U_CALLCONV ucnv_io_cleanup()
{
if (gAliasData) {
udata_close(gAliasData);
gAliasData = nullptr;
}
gAliasDataInitOnce.reset();
uprv_memset(&gMainTable, 0, sizeof(gMainTable));
return true; /* Everything was cleaned up */
}
static void U_CALLCONV initAliasData(UErrorCode &errCode) {
UDataMemory *data;
const uint16_t *table;
const uint32_t *sectionSizes;
uint32_t tableStart;
uint32_t currOffset;
ucln_common_registerCleanup(UCLN_COMMON_UCNV_IO, ucnv_io_cleanup);
U_ASSERT(gAliasData == nullptr);
data = udata_openChoice(nullptr, DATA_TYPE, DATA_NAME, isAcceptable, nullptr, &errCode);
if(U_FAILURE(errCode)) {
return;
}
sectionSizes = static_cast<const uint32_t*>(udata_getMemory(data));
table = reinterpret_cast<const uint16_t*>(sectionSizes);
tableStart = sectionSizes[0];
if (tableStart < minTocLength) {
errCode = U_INVALID_FORMAT_ERROR;
udata_close(data);
return;
}
gAliasData = data;
gMainTable.converterListSize = sectionSizes[1];
gMainTable.tagListSize = sectionSizes[2];
gMainTable.aliasListSize = sectionSizes[3];
gMainTable.untaggedConvArraySize = sectionSizes[4];
gMainTable.taggedAliasArraySize = sectionSizes[5];
gMainTable.taggedAliasListsSize = sectionSizes[6];
gMainTable.optionTableSize = sectionSizes[7];
gMainTable.stringTableSize = sectionSizes[8];
if (tableStart > 8) {
gMainTable.normalizedStringTableSize = sectionSizes[9];
}
currOffset = tableStart * (sizeof(uint32_t)/sizeof(uint16_t)) + (sizeof(uint32_t)/sizeof(uint16_t));
gMainTable.converterList = table + currOffset;
currOffset += gMainTable.converterListSize;
gMainTable.tagList = table + currOffset;
currOffset += gMainTable.tagListSize;
gMainTable.aliasList = table + currOffset;
currOffset += gMainTable.aliasListSize;
gMainTable.untaggedConvArray = table + currOffset;
currOffset += gMainTable.untaggedConvArraySize;
gMainTable.taggedAliasArray = table + currOffset;
/* aliasLists is a 1's based array, but it has a padding character */
currOffset += gMainTable.taggedAliasArraySize;
gMainTable.taggedAliasLists = table + currOffset;
currOffset += gMainTable.taggedAliasListsSize;
if (gMainTable.optionTableSize > 0
&& reinterpret_cast<const UConverterAliasOptions*>(table + currOffset)->stringNormalizationType < UCNV_IO_NORM_TYPE_COUNT)
{
/* Faster table */
gMainTable.optionTable = reinterpret_cast<const UConverterAliasOptions*>(table + currOffset);
}
else {
/* Smaller table, or I can't handle this normalization mode!
Use the original slower table lookup. */
gMainTable.optionTable = &defaultTableOptions;
}
currOffset += gMainTable.optionTableSize;
gMainTable.stringTable = table + currOffset;
currOffset += gMainTable.stringTableSize;
gMainTable.normalizedStringTable = ((gMainTable.optionTable->stringNormalizationType == UCNV_IO_UNNORMALIZED)
? gMainTable.stringTable : (table + currOffset));
}
static UBool
haveAliasData(UErrorCode *pErrorCode) {
umtx_initOnce(gAliasDataInitOnce, &initAliasData, *pErrorCode);
return U_SUCCESS(*pErrorCode);
}
static inline UBool
isAlias(const char *alias, UErrorCode *pErrorCode) {
if(alias==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return false;
}
return *alias != 0;
}
static uint32_t getTagNumber(const char *tagname) {
if (gMainTable.tagList) {
uint32_t tagNum;
for (tagNum = 0; tagNum < gMainTable.tagListSize; tagNum++) {
if (!uprv_stricmp(GET_STRING(gMainTable.tagList[tagNum]), tagname)) {
return tagNum;
}
}
}
return UINT32_MAX;
}
/* character types relevant for ucnv_compareNames() */
enum {
UIGNORE,
ZERO,
NONZERO,
MINLETTER /* any values from here on are lowercase letter mappings */
};
/* character types for ASCII 00..7F */
static const uint8_t asciiTypes[128] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
ZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, 0, 0, 0, 0, 0, 0,
0, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0, 0, 0, 0, 0,
0, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0, 0, 0, 0, 0
};
#define GET_ASCII_TYPE(c) ((int8_t)(c) >= 0 ? asciiTypes[(uint8_t)c] : (uint8_t)UIGNORE)
/* character types for EBCDIC 80..FF */
static const uint8_t ebcdicTypes[128] = {
0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0, 0, 0, 0, 0, 0,
0, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0, 0, 0, 0, 0, 0,
0, 0, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0, 0, 0, 0, 0, 0,
0, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0, 0, 0, 0, 0, 0,
0, 0, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0, 0, 0, 0, 0, 0,
ZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, NONZERO, 0, 0, 0, 0, 0, 0
};
#define GET_EBCDIC_TYPE(c) ((int8_t)(c) < 0 ? ebcdicTypes[(c)&0x7f] : (uint8_t)UIGNORE)
#if U_CHARSET_FAMILY==U_ASCII_FAMILY
# define GET_CHAR_TYPE(c) GET_ASCII_TYPE(c)
#elif U_CHARSET_FAMILY==U_EBCDIC_FAMILY
# define GET_CHAR_TYPE(c) GET_EBCDIC_TYPE(c)
#else
# error U_CHARSET_FAMILY is not valid
#endif
/* @see ucnv_compareNames */
U_CAPI char * U_CALLCONV
ucnv_io_stripASCIIForCompare(char *dst, const char *name) {
char *dstItr = dst;
uint8_t type, nextType;
char c1;
UBool afterDigit = false;
while ((c1 = *name++) != 0) {
type = GET_ASCII_TYPE(c1);
switch (type) {
case UIGNORE:
afterDigit = false;
continue; /* ignore all but letters and digits */
case ZERO:
if (!afterDigit) {
nextType = GET_ASCII_TYPE(*name);
if (nextType == ZERO || nextType == NONZERO) {
continue; /* ignore leading zero before another digit */
}
}
break;
case NONZERO:
afterDigit = true;
break;
default:
c1 = (char)type; /* lowercased letter */
afterDigit = false;
break;
}
*dstItr++ = c1;
}
*dstItr = 0;
return dst;
}
U_CAPI char * U_CALLCONV
ucnv_io_stripEBCDICForCompare(char *dst, const char *name) {
char *dstItr = dst;
uint8_t type, nextType;
char c1;
UBool afterDigit = false;
while ((c1 = *name++) != 0) {
type = GET_EBCDIC_TYPE(c1);
switch (type) {
case UIGNORE:
afterDigit = false;
continue; /* ignore all but letters and digits */
case ZERO:
if (!afterDigit) {
nextType = GET_EBCDIC_TYPE(*name);
if (nextType == ZERO || nextType == NONZERO) {
continue; /* ignore leading zero before another digit */
}
}
break;
case NONZERO:
afterDigit = true;
break;
default:
c1 = (char)type; /* lowercased letter */
afterDigit = false;
break;
}
*dstItr++ = c1;
}
*dstItr = 0;
return dst;
}
/**
* Do a fuzzy compare of two converter/alias names.
* The comparison is case-insensitive, ignores leading zeroes if they are not
* followed by further digits, and ignores all but letters and digits.
* Thus the strings "UTF-8", "utf_8", "u*T@f08" and "Utf 8" are exactly equivalent.
* See section 1.4, Charset Alias Matching in Unicode Technical Standard #22
* at http://www.unicode.org/reports/tr22/
*
* This is a symmetrical (commutative) operation; order of arguments
* is insignificant. This is an important property for sorting the
* list (when the list is preprocessed into binary form) and for
* performing binary searches on it at run time.
*
* @param name1 a converter name or alias, zero-terminated
* @param name2 a converter name or alias, zero-terminated
* @return 0 if the names match, or a negative value if the name1
* lexically precedes name2, or a positive value if the name1
* lexically follows name2.
*
* @see ucnv_io_stripForCompare
*/
U_CAPI int U_EXPORT2
ucnv_compareNames(const char *name1, const char *name2) {
int rc;
uint8_t type, nextType;
char c1, c2;
UBool afterDigit1 = false, afterDigit2 = false;
for (;;) {
while ((c1 = *name1++) != 0) {
type = GET_CHAR_TYPE(c1);
switch (type) {
case UIGNORE:
afterDigit1 = false;
continue; /* ignore all but letters and digits */
case ZERO:
if (!afterDigit1) {
nextType = GET_CHAR_TYPE(*name1);
if (nextType == ZERO || nextType == NONZERO) {
continue; /* ignore leading zero before another digit */
}
}
break;
case NONZERO:
afterDigit1 = true;
break;
default:
c1 = (char)type; /* lowercased letter */
afterDigit1 = false;
break;
}
break; /* deliver c1 */
}
while ((c2 = *name2++) != 0) {
type = GET_CHAR_TYPE(c2);
switch (type) {
case UIGNORE:
afterDigit2 = false;
continue; /* ignore all but letters and digits */
case ZERO:
if (!afterDigit2) {
nextType = GET_CHAR_TYPE(*name2);
if (nextType == ZERO || nextType == NONZERO) {
continue; /* ignore leading zero before another digit */
}
}
break;
case NONZERO:
afterDigit2 = true;
break;
default:
c2 = (char)type; /* lowercased letter */
afterDigit2 = false;
break;
}
break; /* deliver c2 */
}
/* If we reach the ends of both strings then they match */
if ((c1|c2)==0) {
return 0;
}
/* Case-insensitive comparison */
rc = (int)(unsigned char)c1 - (int)(unsigned char)c2;
if (rc != 0) {
return rc;
}
}
}
/*
* search for an alias
* return the converter number index for gConverterList
*/
static inline uint32_t
findConverter(const char *alias, UBool *containsOption, UErrorCode *pErrorCode) {
uint32_t mid, start, limit;
uint32_t lastMid;
int result;
int isUnnormalized = (gMainTable.optionTable->stringNormalizationType == UCNV_IO_UNNORMALIZED);
char strippedName[UCNV_MAX_CONVERTER_NAME_LENGTH];
if (!isUnnormalized) {
if (uprv_strlen(alias) >= UCNV_MAX_CONVERTER_NAME_LENGTH) {
*pErrorCode = U_BUFFER_OVERFLOW_ERROR;
return UINT32_MAX;
}
/* Lower case and remove ignoreable characters. */
ucnv_io_stripForCompare(strippedName, alias);
alias = strippedName;
}
/* do a binary search for the alias */
start = 0;
limit = gMainTable.untaggedConvArraySize;
mid = limit;
lastMid = UINT32_MAX;
for (;;) {
mid = (start + limit) / 2;
if (lastMid == mid) { /* Have we moved? */
break; /* We haven't moved, and it wasn't found. */
}
lastMid = mid;
if (isUnnormalized) {
result = ucnv_compareNames(alias, GET_STRING(gMainTable.aliasList[mid]));
}
else {
result = uprv_strcmp(alias, GET_NORMALIZED_STRING(gMainTable.aliasList[mid]));
}
if (result < 0) {
limit = mid;
} else if (result > 0) {
start = mid;
} else {
/* Since the gencnval tool folds duplicates into one entry,
* this alias in gAliasList is unique, but different standards
* may map an alias to different converters.
*/
if (gMainTable.untaggedConvArray[mid] & UCNV_AMBIGUOUS_ALIAS_MAP_BIT) {
*pErrorCode = U_AMBIGUOUS_ALIAS_WARNING;
}
/* State whether the canonical converter name contains an option.
This information is contained in this list in order to maintain backward & forward compatibility. */
if (containsOption) {
UBool containsCnvOptionInfo = static_cast<UBool>(gMainTable.optionTable->containsCnvOptionInfo);
*containsOption = static_cast<UBool>((containsCnvOptionInfo
&& ((gMainTable.untaggedConvArray[mid] & UCNV_CONTAINS_OPTION_BIT) != 0))
|| !containsCnvOptionInfo);
}
return gMainTable.untaggedConvArray[mid] & UCNV_CONVERTER_INDEX_MASK;
}
}
return UINT32_MAX;
}
/*
* Is this alias in this list?
* alias and listOffset should be non-nullptr.
*/
static inline UBool
isAliasInList(const char *alias, uint32_t listOffset) {
if (listOffset) {
uint32_t currAlias;
uint32_t listCount = gMainTable.taggedAliasLists[listOffset];
/* +1 to skip listCount */
const uint16_t *currList = gMainTable.taggedAliasLists + listOffset + 1;
for (currAlias = 0; currAlias < listCount; currAlias++) {
if (currList[currAlias]
&& ucnv_compareNames(alias, GET_STRING(currList[currAlias]))==0)
{
return true;
}
}
}
return false;
}
/*
* Search for an standard name of an alias (what is the default name
* that this standard uses?)
* return the listOffset for gTaggedAliasLists. If it's 0,
* the it couldn't be found, but the parameters are valid.
*/
static uint32_t
findTaggedAliasListsOffset(const char *alias, const char *standard, UErrorCode *pErrorCode) {
uint32_t idx;
uint32_t listOffset;
uint32_t convNum;
UErrorCode myErr = U_ZERO_ERROR;
uint32_t tagNum = getTagNumber(standard);
/* Make a quick guess. Hopefully they used a TR22 canonical alias. */
convNum = findConverter(alias, nullptr, &myErr);
if (myErr != U_ZERO_ERROR) {
*pErrorCode = myErr;
}
if (tagNum < (gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS) && convNum < gMainTable.converterListSize) {
listOffset = gMainTable.taggedAliasArray[tagNum*gMainTable.converterListSize + convNum];
if (listOffset && gMainTable.taggedAliasLists[listOffset + 1]) {
return listOffset;
}
if (myErr == U_AMBIGUOUS_ALIAS_WARNING) {
/* Uh Oh! They used an ambiguous alias.
We have to search the whole swiss cheese starting
at the highest standard affinity.
This may take a while.
*/
for (idx = 0; idx < gMainTable.taggedAliasArraySize; idx++) {
listOffset = gMainTable.taggedAliasArray[idx];
if (listOffset && isAliasInList(alias, listOffset)) {
uint32_t currTagNum = idx/gMainTable.converterListSize;
uint32_t currConvNum = (idx - currTagNum*gMainTable.converterListSize);
uint32_t tempListOffset = gMainTable.taggedAliasArray[tagNum*gMainTable.converterListSize + currConvNum];
if (tempListOffset && gMainTable.taggedAliasLists[tempListOffset + 1]) {
return tempListOffset;
}
/* else keep on looking */
/* We could speed this up by starting on the next row
because an alias is unique per row, right now.
This would change if alias versioning appears. */
}
}
/* The standard doesn't know about the alias */
}
/* else no default name */
return 0;
}
/* else converter or tag not found */
return UINT32_MAX;
}
/* Return the canonical name */
static uint32_t
findTaggedConverterNum(const char *alias, const char *standard, UErrorCode *pErrorCode) {
uint32_t idx;
uint32_t listOffset;
uint32_t convNum;
UErrorCode myErr = U_ZERO_ERROR;
uint32_t tagNum = getTagNumber(standard);
/* Make a quick guess. Hopefully they used a TR22 canonical alias. */
convNum = findConverter(alias, nullptr, &myErr);
if (myErr != U_ZERO_ERROR) {
*pErrorCode = myErr;
}
if (tagNum < (gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS) && convNum < gMainTable.converterListSize) {
listOffset = gMainTable.taggedAliasArray[tagNum*gMainTable.converterListSize + convNum];
if (listOffset && isAliasInList(alias, listOffset)) {
return convNum;
}
if (myErr == U_AMBIGUOUS_ALIAS_WARNING) {
/* Uh Oh! They used an ambiguous alias.
We have to search one slice of the swiss cheese.
We search only in the requested tag, not the whole thing.
This may take a while.
*/
uint32_t convStart = (tagNum)*gMainTable.converterListSize;
uint32_t convLimit = (tagNum+1)*gMainTable.converterListSize;
for (idx = convStart; idx < convLimit; idx++) {
listOffset = gMainTable.taggedAliasArray[idx];
if (listOffset && isAliasInList(alias, listOffset)) {
return idx-convStart;
}
}
/* The standard doesn't know about the alias */
}
/* else no canonical name */
}
/* else converter or tag not found */
return UINT32_MAX;
}
U_CAPI const char *
ucnv_io_getConverterName(const char *alias, UBool *containsOption, UErrorCode *pErrorCode) {
const char *aliasTmp = alias;
int32_t i = 0;
for (i = 0; i < 2; i++) {
if (i == 1) {
/*
* After the first unsuccess converter lookup, check to see if
* the name begins with 'x-'. If it does, strip it off and try
* again. This behaviour is similar to how ICU4J does it.
*/
if (aliasTmp[0] == 'x' && aliasTmp[1] == '-') {
aliasTmp = aliasTmp+2;
} else {
break;
}
}
if(haveAliasData(pErrorCode) && isAlias(aliasTmp, pErrorCode)) {
uint32_t convNum = findConverter(aliasTmp, containsOption, pErrorCode);
if (convNum < gMainTable.converterListSize) {
return GET_STRING(gMainTable.converterList[convNum]);
}
/* else converter not found */
} else {
break;
}
}
return nullptr;
}
U_CDECL_BEGIN
static int32_t U_CALLCONV
ucnv_io_countStandardAliases(UEnumeration *enumerator, UErrorCode * /*pErrorCode*/) {
int32_t value = 0;
UAliasContext *myContext = (UAliasContext *)(enumerator->context);
uint32_t listOffset = myContext->listOffset;
if (listOffset) {
value = gMainTable.taggedAliasLists[listOffset];
}
return value;
}
static const char * U_CALLCONV
ucnv_io_nextStandardAliases(UEnumeration *enumerator,
int32_t* resultLength,
UErrorCode * /*pErrorCode*/)
{
UAliasContext *myContext = (UAliasContext *)(enumerator->context);
uint32_t listOffset = myContext->listOffset;
if (listOffset) {
uint32_t listCount = gMainTable.taggedAliasLists[listOffset];
const uint16_t *currList = gMainTable.taggedAliasLists + listOffset + 1;
if (myContext->listIdx < listCount) {
const char *myStr = GET_STRING(currList[myContext->listIdx++]);
if (resultLength) {
*resultLength = (int32_t)uprv_strlen(myStr);
}
return myStr;
}
}
/* Either we accessed a zero length list, or we enumerated too far. */
if (resultLength) {
*resultLength = 0;
}
return nullptr;
}
static void U_CALLCONV
ucnv_io_resetStandardAliases(UEnumeration *enumerator, UErrorCode * /*pErrorCode*/) {
((UAliasContext *)(enumerator->context))->listIdx = 0;
}
static void U_CALLCONV
ucnv_io_closeUEnumeration(UEnumeration *enumerator) {
uprv_free(enumerator->context);
uprv_free(enumerator);
}
U_CDECL_END
/* Enumerate the aliases for the specified converter and standard tag */
static const UEnumeration gEnumAliases = {
nullptr,
nullptr,
ucnv_io_closeUEnumeration,
ucnv_io_countStandardAliases,
uenum_unextDefault,
ucnv_io_nextStandardAliases,
ucnv_io_resetStandardAliases
};
U_CAPI UEnumeration * U_EXPORT2
ucnv_openStandardNames(const char *convName,
const char *standard,
UErrorCode *pErrorCode)
{
UEnumeration *myEnum = nullptr;
if (haveAliasData(pErrorCode) && isAlias(convName, pErrorCode)) {
uint32_t listOffset = findTaggedAliasListsOffset(convName, standard, pErrorCode);
/* When listOffset == 0, we want to acknowledge that the
converter name and standard are okay, but there
is nothing to enumerate. */
if (listOffset < gMainTable.taggedAliasListsSize) {
UAliasContext *myContext;
myEnum = static_cast<UEnumeration *>(uprv_malloc(sizeof(UEnumeration)));
if (myEnum == nullptr) {
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
return nullptr;
}
uprv_memcpy(myEnum, &gEnumAliases, sizeof(UEnumeration));
myContext = static_cast<UAliasContext *>(uprv_malloc(sizeof(UAliasContext)));
if (myContext == nullptr) {
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
uprv_free(myEnum);
return nullptr;
}
myContext->listOffset = listOffset;
myContext->listIdx = 0;
myEnum->context = myContext;
}
/* else converter or tag not found */
}
return myEnum;
}
static uint16_t
ucnv_io_countAliases(const char *alias, UErrorCode *pErrorCode) {
if(haveAliasData(pErrorCode) && isAlias(alias, pErrorCode)) {
uint32_t convNum = findConverter(alias, nullptr, pErrorCode);
if (convNum < gMainTable.converterListSize) {
/* tagListNum - 1 is the ALL tag */
int32_t listOffset = gMainTable.taggedAliasArray[(gMainTable.tagListSize - 1)*gMainTable.converterListSize + convNum];
if (listOffset) {
return gMainTable.taggedAliasLists[listOffset];
}
/* else this shouldn't happen. internal program error */
}
/* else converter not found */
}
return 0;
}
static uint16_t
ucnv_io_getAliases(const char *alias, uint16_t start, const char **aliases, UErrorCode *pErrorCode) {
if(haveAliasData(pErrorCode) && isAlias(alias, pErrorCode)) {
uint32_t currAlias;
uint32_t convNum = findConverter(alias, nullptr, pErrorCode);
if (convNum < gMainTable.converterListSize) {
/* tagListNum - 1 is the ALL tag */
int32_t listOffset = gMainTable.taggedAliasArray[(gMainTable.tagListSize - 1)*gMainTable.converterListSize + convNum];
if (listOffset) {
uint32_t listCount = gMainTable.taggedAliasLists[listOffset];
/* +1 to skip listCount */
const uint16_t *currList = gMainTable.taggedAliasLists + listOffset + 1;
for (currAlias = start; currAlias < listCount; currAlias++) {
aliases[currAlias] = GET_STRING(currList[currAlias]);
}
}
/* else this shouldn't happen. internal program error */
}
/* else converter not found */
}
return 0;
}
static const char *
ucnv_io_getAlias(const char *alias, uint16_t n, UErrorCode *pErrorCode) {
if(haveAliasData(pErrorCode) && isAlias(alias, pErrorCode)) {
uint32_t convNum = findConverter(alias, nullptr, pErrorCode);
if (convNum < gMainTable.converterListSize) {
/* tagListNum - 1 is the ALL tag */
int32_t listOffset = gMainTable.taggedAliasArray[(gMainTable.tagListSize - 1)*gMainTable.converterListSize + convNum];
if (listOffset) {
uint32_t listCount = gMainTable.taggedAliasLists[listOffset];
/* +1 to skip listCount */
const uint16_t *currList = gMainTable.taggedAliasLists + listOffset + 1;
if (n < listCount) {
return GET_STRING(currList[n]);
}
*pErrorCode = U_INDEX_OUTOFBOUNDS_ERROR;
}
/* else this shouldn't happen. internal program error */
}
/* else converter not found */
}
return nullptr;
}
static uint16_t
ucnv_io_countStandards(UErrorCode *pErrorCode) {
if (haveAliasData(pErrorCode)) {
/* Don't include the empty list */
return static_cast<uint16_t>(gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS);
}
return 0;
}
U_CAPI const char * U_EXPORT2
ucnv_getStandard(uint16_t n, UErrorCode *pErrorCode) {
if (haveAliasData(pErrorCode)) {
if (n < gMainTable.tagListSize - UCNV_NUM_HIDDEN_TAGS) {
return GET_STRING(gMainTable.tagList[n]);
}
*pErrorCode = U_INDEX_OUTOFBOUNDS_ERROR;
}
return nullptr;
}
U_CAPI const char * U_EXPORT2
ucnv_getStandardName(const char *alias, const char *standard, UErrorCode *pErrorCode) {
if (haveAliasData(pErrorCode) && isAlias(alias, pErrorCode)) {
uint32_t listOffset = findTaggedAliasListsOffset(alias, standard, pErrorCode);
if (0 < listOffset && listOffset < gMainTable.taggedAliasListsSize) {
const uint16_t *currList = gMainTable.taggedAliasLists + listOffset + 1;
/* Get the preferred name from this list */
if (currList[0]) {
return GET_STRING(currList[0]);
}
/* else someone screwed up the alias table. */
/* *pErrorCode = U_INVALID_FORMAT_ERROR */
}
}
return nullptr;
}
U_CAPI uint16_t U_EXPORT2
ucnv_countAliases(const char *alias, UErrorCode *pErrorCode)
{
return ucnv_io_countAliases(alias, pErrorCode);
}
U_CAPI const char* U_EXPORT2
ucnv_getAlias(const char *alias, uint16_t n, UErrorCode *pErrorCode)
{
return ucnv_io_getAlias(alias, n, pErrorCode);
}
U_CAPI void U_EXPORT2
ucnv_getAliases(const char *alias, const char **aliases, UErrorCode *pErrorCode)
{
ucnv_io_getAliases(alias, 0, aliases, pErrorCode);
}
U_CAPI uint16_t U_EXPORT2
ucnv_countStandards()
{
UErrorCode err = U_ZERO_ERROR;
return ucnv_io_countStandards(&err);
}
U_CAPI const char * U_EXPORT2
ucnv_getCanonicalName(const char *alias, const char *standard, UErrorCode *pErrorCode) {
if (haveAliasData(pErrorCode) && isAlias(alias, pErrorCode)) {
uint32_t convNum = findTaggedConverterNum(alias, standard, pErrorCode);
if (convNum < gMainTable.converterListSize) {
return GET_STRING(gMainTable.converterList[convNum]);
}
}
return nullptr;
}
U_CDECL_BEGIN
static int32_t U_CALLCONV
ucnv_io_countAllConverters(UEnumeration * /*enumerator*/, UErrorCode * /*pErrorCode*/) {
return gMainTable.converterListSize;
}
static const char * U_CALLCONV
ucnv_io_nextAllConverters(UEnumeration *enumerator,
int32_t* resultLength,
UErrorCode * /*pErrorCode*/)
{
uint16_t *myContext = (uint16_t *)(enumerator->context);
if (*myContext < gMainTable.converterListSize) {
const char *myStr = GET_STRING(gMainTable.converterList[(*myContext)++]);
if (resultLength) {
*resultLength = (int32_t)uprv_strlen(myStr);
}
return myStr;
}
/* Either we accessed a zero length list, or we enumerated too far. */
if (resultLength) {
*resultLength = 0;
}
return nullptr;
}
static void U_CALLCONV
ucnv_io_resetAllConverters(UEnumeration *enumerator, UErrorCode * /*pErrorCode*/) {
*((uint16_t *)(enumerator->context)) = 0;
}
U_CDECL_END
static const UEnumeration gEnumAllConverters = {
nullptr,
nullptr,
ucnv_io_closeUEnumeration,
ucnv_io_countAllConverters,
uenum_unextDefault,
ucnv_io_nextAllConverters,
ucnv_io_resetAllConverters
};
U_CAPI UEnumeration * U_EXPORT2
ucnv_openAllNames(UErrorCode *pErrorCode) {
UEnumeration *myEnum = nullptr;
if (haveAliasData(pErrorCode)) {
uint16_t *myContext;
myEnum = static_cast<UEnumeration *>(uprv_malloc(sizeof(UEnumeration)));
if (myEnum == nullptr) {
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
return nullptr;
}
uprv_memcpy(myEnum, &gEnumAllConverters, sizeof(UEnumeration));
myContext = static_cast<uint16_t *>(uprv_malloc(sizeof(uint16_t)));
if (myContext == nullptr) {
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
uprv_free(myEnum);
return nullptr;
}
*myContext = 0;
myEnum->context = myContext;
}
return myEnum;
}
U_CAPI uint16_t
ucnv_io_countKnownConverters(UErrorCode *pErrorCode) {
if (haveAliasData(pErrorCode)) {
return (uint16_t)gMainTable.converterListSize;
}
return 0;
}
/* alias table swapping ----------------------------------------------------- */
U_CDECL_BEGIN
typedef char * U_CALLCONV StripForCompareFn(char *dst, const char *name);
U_CDECL_END
/*
* row of a temporary array
*
* gets platform-endian charset string indexes and sorting indexes;
* after sorting this array by strings, the actual arrays are permutated
* according to the sorting indexes
*/
typedef struct TempRow {
uint16_t strIndex, sortIndex;
} TempRow;
typedef struct TempAliasTable {
const char *chars;
TempRow *rows;
uint16_t *resort;
StripForCompareFn *stripForCompare;
} TempAliasTable;
enum {
STACK_ROW_CAPACITY=500
};
static int32_t U_CALLCONV
io_compareRows(const void *context, const void *left, const void *right) {
char strippedLeft[UCNV_MAX_CONVERTER_NAME_LENGTH],
strippedRight[UCNV_MAX_CONVERTER_NAME_LENGTH];
TempAliasTable *tempTable=(TempAliasTable *)context;
const char *chars=tempTable->chars;
return static_cast<int32_t>(uprv_strcmp(
tempTable->stripForCompare(strippedLeft, chars + 2 * static_cast<const TempRow*>(left)->strIndex),
tempTable->stripForCompare(strippedRight, chars + 2 * static_cast<const TempRow*>(right)->strIndex)));
}
U_CAPI int32_t U_EXPORT2
ucnv_swapAliases(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const UDataInfo *pInfo;
int32_t headerSize;
const uint16_t *inTable;
const uint32_t *inSectionSizes;
uint32_t toc[offsetsCount];
uint32_t offsets[offsetsCount]; /* 16-bit-addressed offsets from inTable/outTable */
uint32_t i, count, tocLength, topOffset;
TempRow rows[STACK_ROW_CAPACITY];
uint16_t resort[STACK_ROW_CAPACITY];
TempAliasTable tempTable;
/* udata_swapDataHeader checks the arguments */
headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
/* check data format and format version */
pInfo=(const UDataInfo *)((const char *)inData+4);
if(!(
pInfo->dataFormat[0]==0x43 && /* dataFormat="CvAl" */
pInfo->dataFormat[1]==0x76 &&
pInfo->dataFormat[2]==0x41 &&
pInfo->dataFormat[3]==0x6c &&
pInfo->formatVersion[0]==3
)) {
udata_printError(ds, "ucnv_swapAliases(): data format %02x.%02x.%02x.%02x (format version %02x) is not an alias table\n",
pInfo->dataFormat[0], pInfo->dataFormat[1],
pInfo->dataFormat[2], pInfo->dataFormat[3],
pInfo->formatVersion[0]);
*pErrorCode=U_UNSUPPORTED_ERROR;
return 0;
}
/* an alias table must contain at least the table of contents array */
if(length>=0 && (length-headerSize)<4*(1+minTocLength)) {
udata_printError(ds, "ucnv_swapAliases(): too few bytes (%d after header) for an alias table\n",
length-headerSize);
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
inSectionSizes=(const uint32_t *)((const char *)inData+headerSize);
inTable=(const uint16_t *)inSectionSizes;
uprv_memset(toc, 0, sizeof(toc));
toc[tocLengthIndex]=tocLength=ds->readUInt32(inSectionSizes[tocLengthIndex]);
if(tocLength<minTocLength || offsetsCount<=tocLength) {
udata_printError(ds, "ucnv_swapAliases(): table of contents contains unsupported number of sections (%u sections)\n", tocLength);
*pErrorCode=U_INVALID_FORMAT_ERROR;
return 0;
}
/* read the known part of the table of contents */
for(i=converterListIndex; i<=tocLength; ++i) {
toc[i]=ds->readUInt32(inSectionSizes[i]);
}
/* compute offsets */
uprv_memset(offsets, 0, sizeof(offsets));
offsets[converterListIndex]=2*(1+tocLength); /* count two 16-bit units per toc entry */
for(i=tagListIndex; i<=tocLength; ++i) {
offsets[i]=offsets[i-1]+toc[i-1];
}
/* compute the overall size of the after-header data, in numbers of 16-bit units */
topOffset=offsets[i-1]+toc[i-1];
if(length>=0) {
uint16_t *outTable;
const uint16_t *p, *p2;
uint16_t *q, *q2;
uint16_t oldIndex;
if((length-headerSize)<(2*(int32_t)topOffset)) {
udata_printError(ds, "ucnv_swapAliases(): too few bytes (%d after header) for an alias table\n",
length-headerSize);
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
outTable=(uint16_t *)((char *)outData+headerSize);
/* swap the entire table of contents */
ds->swapArray32(ds, inTable, 4*(1+tocLength), outTable, pErrorCode);
/* swap unormalized strings & normalized strings */
ds->swapInvChars(ds, inTable+offsets[stringTableIndex], 2*(int32_t)(toc[stringTableIndex]+toc[normalizedStringTableIndex]),
outTable+offsets[stringTableIndex], pErrorCode);
if(U_FAILURE(*pErrorCode)) {
udata_printError(ds, "ucnv_swapAliases().swapInvChars(charset names) failed\n");
return 0;
}
if(ds->inCharset==ds->outCharset) {
/* no need to sort, just swap all 16-bit values together */
ds->swapArray16(ds,
inTable+offsets[converterListIndex],
2*(int32_t)(offsets[stringTableIndex]-offsets[converterListIndex]),
outTable+offsets[converterListIndex],
pErrorCode);
} else {
/* allocate the temporary table for sorting */
count=toc[aliasListIndex];
tempTable.chars=(const char *)(outTable+offsets[stringTableIndex]); /* sort by outCharset */
if(count<=STACK_ROW_CAPACITY) {
tempTable.rows=rows;
tempTable.resort=resort;
} else {
tempTable.rows=(TempRow *)uprv_malloc(count*sizeof(TempRow)+count*2);
if(tempTable.rows==nullptr) {
udata_printError(ds, "ucnv_swapAliases(): unable to allocate memory for sorting tables (max length: %u)\n",
count);
*pErrorCode=U_MEMORY_ALLOCATION_ERROR;
return 0;
}
tempTable.resort=(uint16_t *)(tempTable.rows+count);
}
if(ds->outCharset==U_ASCII_FAMILY) {
tempTable.stripForCompare=ucnv_io_stripASCIIForCompare;
} else /* U_EBCDIC_FAMILY */ {
tempTable.stripForCompare=ucnv_io_stripEBCDICForCompare;
}
/*
* Sort unique aliases+mapped names.
*
* We need to sort the list again by outCharset strings because they
* sort differently for different charset families.
* First we set up a temporary table with the string indexes and
* sorting indexes and sort that.
* Then we permutate and copy/swap the actual values.
*/
p=inTable+offsets[aliasListIndex];
q=outTable+offsets[aliasListIndex];
p2=inTable+offsets[untaggedConvArrayIndex];
q2=outTable+offsets[untaggedConvArrayIndex];
for(i=0; i<count; ++i) {
tempTable.rows[i].strIndex=ds->readUInt16(p[i]);
tempTable.rows[i].sortIndex=(uint16_t)i;
}
uprv_sortArray(tempTable.rows, (int32_t)count, sizeof(TempRow),
io_compareRows, &tempTable,
false, pErrorCode);
if(U_SUCCESS(*pErrorCode)) {
/* copy/swap/permutate items */
if(p!=q) {
for(i=0; i<count; ++i) {
oldIndex=tempTable.rows[i].sortIndex;
ds->swapArray16(ds, p+oldIndex, 2, q+i, pErrorCode);
ds->swapArray16(ds, p2+oldIndex, 2, q2+i, pErrorCode);
}
} else {
/*
* If we swap in-place, then the permutation must use another
* temporary array (tempTable.resort)
* before the results are copied to the outBundle.
*/
uint16_t *r=tempTable.resort;
for(i=0; i<count; ++i) {
oldIndex=tempTable.rows[i].sortIndex;
ds->swapArray16(ds, p+oldIndex, 2, r+i, pErrorCode);
}
uprv_memcpy(q, r, 2*(size_t)count);
for(i=0; i<count; ++i) {
oldIndex=tempTable.rows[i].sortIndex;
ds->swapArray16(ds, p2+oldIndex, 2, r+i, pErrorCode);
}
uprv_memcpy(q2, r, 2*(size_t)count);
}
}
if(tempTable.rows!=rows) {
uprv_free(tempTable.rows);
}
if(U_FAILURE(*pErrorCode)) {
udata_printError(ds, "ucnv_swapAliases().uprv_sortArray(%u items) failed\n",
count);
return 0;
}
/* swap remaining 16-bit values */
ds->swapArray16(ds,
inTable+offsets[converterListIndex],
2*(int32_t)(offsets[aliasListIndex]-offsets[converterListIndex]),
outTable+offsets[converterListIndex],
pErrorCode);
ds->swapArray16(ds,
inTable+offsets[taggedAliasArrayIndex],
2*(int32_t)(offsets[stringTableIndex]-offsets[taggedAliasArrayIndex]),
outTable+offsets[taggedAliasArrayIndex],
pErrorCode);
}
}
return headerSize+2*(int32_t)topOffset;
}
#endif
/*
* Hey, Emacs, please set the following:
*
* Local Variables:
* indent-tabs-mode: nil
* End:
*
*/
|