forked from mysql/mysql-server
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathctype.cc
1291 lines (1129 loc) · 41.2 KB
/
ctype.cc
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
/* Copyright (c) 2000, 2023, Oracle and/or its affiliates.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License, version 2.0,
as published by the Free Software Foundation.
This program is also distributed with certain software (including
but not limited to OpenSSL) that is licensed under separate terms,
as designated in a particular file or component or in included license
documentation. The authors of MySQL hereby grant you an additional
permission to link the program and your derivative works with the
separately licensed software that they have included with MySQL.
Without limiting anything contained in the foregoing, this file,
which is part of C Driver for MySQL (Connector/C), is also subject to the
Universal FOSS Exception, version 1.0, a copy of which can be found at
http://oss.oracle.com/licenses/universal-foss-exception.
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, version 2.0, for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <memory>
#include "my_byteorder.h"
#include "my_sys.h"
#include "my_xml.h"
#include "mysql/my_loglevel.h"
#include "mysql/strings/collations.h"
#include "mysql/strings/m_ctype.h"
#include "mysys_err.h"
#include "sql_chars.h"
#include "strings/collations_internal.h"
#include "strings/m_ctype_internals.h"
#include "template_utils.h"
/*
This files implements routines which parse XML based
character set and collation description files.
Unicode collations are encoded according to
Unicode Technical Standard #35
Locale Data Markup Language (LDML)
http://www.unicode.org/reports/tr35/
and converted into ICU string according to
Collation Customization
http://oss.software.ibm.com/icu/userguide/Collate_Customization.html
*/
extern CHARSET_INFO my_charset_ucs2_unicode_ci;
extern CHARSET_INFO my_charset_utf16_unicode_ci;
extern CHARSET_INFO my_charset_utf8mb4_unicode_ci;
static char *mstr(char *str, const char *src, size_t l1, size_t l2) {
l1 = l1 < l2 ? l1 : l2;
memcpy(str, src, l1);
str[l1] = '\0';
return str;
}
struct my_cs_file_section_st {
int state;
const char *str;
};
#define _CS_MISC 1
#define _CS_ID 2
#define _CS_CSNAME 3
#define _CS_FAMILY 4
#define _CS_ORDER 5
#define _CS_COLNAME 6
#define _CS_FLAG 7
#define _CS_CHARSET 8
#define _CS_COLLATION 9
#define _CS_UPPERMAP 10
#define _CS_LOWERMAP 11
#define _CS_UNIMAP 12
#define _CS_COLLMAP 13
#define _CS_CTYPEMAP 14
#define _CS_PRIMARY_ID 15
#define _CS_BINARY_ID 16
#define _CS_CSDESCRIPT 17
/* Special purpose commands */
#define _CS_UCA_VERSION 100
#define _CS_CL_SUPPRESS_CONTRACTIONS 101
#define _CS_CL_OPTIMIZE 102
#define _CS_CL_SHIFT_AFTER_METHOD 103
/* Collation Settings */
#define _CS_ST_SETTINGS 200
#define _CS_ST_STRENGTH 201
#define _CS_ST_ALTERNATE 202
#define _CS_ST_BACKWARDS 203
#define _CS_ST_NORMALIZATION 204
#define _CS_ST_CASE_LEVEL 205
#define _CS_ST_CASE_FIRST 206
#define _CS_ST_HIRAGANA_QUATERNARY 207
#define _CS_ST_NUMERIC 208
#define _CS_ST_VARIABLE_TOP 209
#define _CS_ST_MATCH_BOUNDARIES 210
#define _CS_ST_MATCH_STYLE 211
/* Rules */
#define _CS_RULES 300
#define _CS_RESET 301
#define _CS_DIFF1 302
#define _CS_DIFF2 303
#define _CS_DIFF3 304
#define _CS_DIFF4 305
#define _CS_IDENTICAL 306
/* Rules: Expansions */
#define _CS_EXP_X 320
#define _CS_EXP_EXTEND 321
#define _CS_EXP_DIFF1 322
#define _CS_EXP_DIFF2 323
#define _CS_EXP_DIFF3 324
#define _CS_EXP_DIFF4 325
#define _CS_EXP_IDENTICAL 326
/* Rules: Abbreviating Ordering Specifications */
#define _CS_A_DIFF1 351
#define _CS_A_DIFF2 352
#define _CS_A_DIFF3 353
#define _CS_A_DIFF4 354
#define _CS_A_IDENTICAL 355
/* Rules: previous context */
#define _CS_CONTEXT 370
/* Rules: Placing Characters Before Others*/
#define _CS_RESET_BEFORE 380
/* Rules: Logical Reset Positions */
#define _CS_RESET_FIRST_PRIMARY_IGNORABLE 401
#define _CS_RESET_LAST_PRIMARY_IGNORABLE 402
#define _CS_RESET_FIRST_SECONDARY_IGNORABLE 403
#define _CS_RESET_LAST_SECONDARY_IGNORABLE 404
#define _CS_RESET_FIRST_TERTIARY_IGNORABLE 405
#define _CS_RESET_LAST_TERTIARY_IGNORABLE 406
#define _CS_RESET_FIRST_TRAILING 407
#define _CS_RESET_LAST_TRAILING 408
#define _CS_RESET_FIRST_VARIABLE 409
#define _CS_RESET_LAST_VARIABLE 410
#define _CS_RESET_FIRST_NON_IGNORABLE 411
#define _CS_RESET_LAST_NON_IGNORABLE 412
static struct my_cs_file_section_st sec[] = {
{_CS_MISC, "xml"},
{_CS_MISC, "xml/version"},
{_CS_MISC, "xml/encoding"},
{_CS_MISC, "charsets"},
{_CS_MISC, "charsets/max-id"},
{_CS_MISC, "charsets/copyright"},
{_CS_MISC, "charsets/description"},
{_CS_CHARSET, "charsets/charset"},
{_CS_PRIMARY_ID, "charsets/charset/primary-id"},
{_CS_BINARY_ID, "charsets/charset/binary-id"},
{_CS_CSNAME, "charsets/charset/name"},
{_CS_FAMILY, "charsets/charset/family"},
{_CS_CSDESCRIPT, "charsets/charset/description"},
{_CS_MISC, "charsets/charset/alias"},
{_CS_MISC, "charsets/charset/ctype"},
{_CS_CTYPEMAP, "charsets/charset/ctype/map"},
{_CS_MISC, "charsets/charset/upper"},
{_CS_UPPERMAP, "charsets/charset/upper/map"},
{_CS_MISC, "charsets/charset/lower"},
{_CS_LOWERMAP, "charsets/charset/lower/map"},
{_CS_MISC, "charsets/charset/unicode"},
{_CS_UNIMAP, "charsets/charset/unicode/map"},
{_CS_COLLATION, "charsets/charset/collation"},
{_CS_COLNAME, "charsets/charset/collation/name"},
{_CS_ID, "charsets/charset/collation/id"},
{_CS_ORDER, "charsets/charset/collation/order"},
{_CS_FLAG, "charsets/charset/collation/flag"},
{_CS_COLLMAP, "charsets/charset/collation/map"},
/* Special purpose commands */
{_CS_UCA_VERSION, "charsets/charset/collation/version"},
{_CS_CL_SUPPRESS_CONTRACTIONS,
"charsets/charset/collation/suppress_contractions"},
{_CS_CL_OPTIMIZE, "charsets/charset/collation/optimize"},
{_CS_CL_SHIFT_AFTER_METHOD,
"charsets/charset/collation/shift-after-method"},
/* Collation Settings */
{_CS_ST_SETTINGS, "charsets/charset/collation/settings"},
{_CS_ST_STRENGTH, "charsets/charset/collation/settings/strength"},
{_CS_ST_ALTERNATE, "charsets/charset/collation/settings/alternate"},
{_CS_ST_BACKWARDS, "charsets/charset/collation/settings/backwards"},
{_CS_ST_NORMALIZATION, "charsets/charset/collation/settings/normalization"},
{_CS_ST_CASE_LEVEL, "charsets/charset/collation/settings/caseLevel"},
{_CS_ST_CASE_FIRST, "charsets/charset/collation/settings/caseFirst"},
{_CS_ST_HIRAGANA_QUATERNARY,
"charsets/charset/collation/settings/hiraganaQuaternary"},
{_CS_ST_NUMERIC, "charsets/charset/collation/settings/numeric"},
{_CS_ST_VARIABLE_TOP, "charsets/charset/collation/settings/variableTop"},
{_CS_ST_MATCH_BOUNDARIES,
"charsets/charset/collation/settings/match-boundaries"},
{_CS_ST_MATCH_STYLE, "charsets/charset/collation/settings/match-style"},
/* Rules */
{_CS_RULES, "charsets/charset/collation/rules"},
{_CS_RESET, "charsets/charset/collation/rules/reset"},
{_CS_DIFF1, "charsets/charset/collation/rules/p"},
{_CS_DIFF2, "charsets/charset/collation/rules/s"},
{_CS_DIFF3, "charsets/charset/collation/rules/t"},
{_CS_DIFF4, "charsets/charset/collation/rules/q"},
{_CS_IDENTICAL, "charsets/charset/collation/rules/i"},
/* Rules: expansions */
{_CS_EXP_X, "charsets/charset/collation/rules/x"},
{_CS_EXP_EXTEND, "charsets/charset/collation/rules/x/extend"},
{_CS_EXP_DIFF1, "charsets/charset/collation/rules/x/p"},
{_CS_EXP_DIFF2, "charsets/charset/collation/rules/x/s"},
{_CS_EXP_DIFF3, "charsets/charset/collation/rules/x/t"},
{_CS_EXP_DIFF4, "charsets/charset/collation/rules/x/q"},
{_CS_EXP_IDENTICAL, "charsets/charset/collation/rules/x/i"},
/* Rules: previous context */
{_CS_CONTEXT, "charsets/charset/collation/rules/x/context"},
/* Rules: Abbreviating Ordering Specifications */
{_CS_A_DIFF1, "charsets/charset/collation/rules/pc"},
{_CS_A_DIFF2, "charsets/charset/collation/rules/sc"},
{_CS_A_DIFF3, "charsets/charset/collation/rules/tc"},
{_CS_A_DIFF4, "charsets/charset/collation/rules/qc"},
{_CS_A_IDENTICAL, "charsets/charset/collation/rules/ic"},
/* Rules: Placing Characters Before Others*/
{_CS_RESET_BEFORE, "charsets/charset/collation/rules/reset/before"},
/* Rules: Logical Reset Positions */
{_CS_RESET_FIRST_NON_IGNORABLE,
"charsets/charset/collation/rules/reset/first_non_ignorable"},
{_CS_RESET_LAST_NON_IGNORABLE,
"charsets/charset/collation/rules/reset/last_non_ignorable"},
{_CS_RESET_FIRST_PRIMARY_IGNORABLE,
"charsets/charset/collation/rules/reset/first_primary_ignorable"},
{_CS_RESET_LAST_PRIMARY_IGNORABLE,
"charsets/charset/collation/rules/reset/last_primary_ignorable"},
{_CS_RESET_FIRST_SECONDARY_IGNORABLE,
"charsets/charset/collation/rules/reset/first_secondary_ignorable"},
{_CS_RESET_LAST_SECONDARY_IGNORABLE,
"charsets/charset/collation/rules/reset/last_secondary_ignorable"},
{_CS_RESET_FIRST_TERTIARY_IGNORABLE,
"charsets/charset/collation/rules/reset/first_tertiary_ignorable"},
{_CS_RESET_LAST_TERTIARY_IGNORABLE,
"charsets/charset/collation/rules/reset/last_tertiary_ignorable"},
{_CS_RESET_FIRST_TRAILING,
"charsets/charset/collation/rules/reset/first_trailing"},
{_CS_RESET_LAST_TRAILING,
"charsets/charset/collation/rules/reset/last_trailing"},
{_CS_RESET_FIRST_VARIABLE,
"charsets/charset/collation/rules/reset/first_variable"},
{_CS_RESET_LAST_VARIABLE,
"charsets/charset/collation/rules/reset/last_variable"},
{0, nullptr}};
static struct my_cs_file_section_st *cs_file_sec(const char *attr, size_t len) {
struct my_cs_file_section_st *s;
for (s = sec; s->str; s++) {
if (!strncmp(attr, s->str, len) && s->str[len] == 0) return s;
}
return nullptr;
}
#define MY_CS_CSDESCR_SIZE 64
#define MY_CS_CONTEXT_SIZE 64
typedef struct my_cs_file_info {
char csname[MY_CS_NAME_SIZE];
char name[MY_CS_NAME_SIZE];
uint8_t ctype[MY_CS_CTYPE_TABLE_SIZE];
uint8_t to_lower[MY_CS_TO_LOWER_TABLE_SIZE];
uint8_t to_upper[MY_CS_TO_UPPER_TABLE_SIZE];
uint8_t sort_order[MY_CS_SORT_ORDER_TABLE_SIZE];
uint16_t tab_to_uni[MY_CS_TO_UNI_TABLE_SIZE];
char comment[MY_CS_CSDESCR_SIZE];
char *tailoring;
size_t tailoring_length;
size_t tailoring_alloced_length;
char context[MY_CS_CONTEXT_SIZE];
CHARSET_INFO cs;
MY_CHARSET_LOADER *loader;
} MY_CHARSET_FILE;
static void my_charset_file_reset_charset(MY_CHARSET_FILE *i) {
memset(&i->cs, 0, sizeof(i->cs));
}
static void my_charset_file_reset_collation(MY_CHARSET_FILE *i) {
i->tailoring_length = 0;
i->context[0] = '\0';
}
static void my_charset_file_init(MY_CHARSET_FILE *i) {
my_charset_file_reset_charset(i);
my_charset_file_reset_collation(i);
i->tailoring = nullptr;
i->tailoring_alloced_length = 0;
}
static void my_charset_file_free(MY_CHARSET_FILE *i) { free(i->tailoring); }
static int my_charset_file_tailoring_realloc(MY_CHARSET_FILE *i,
size_t newlen) {
if (i->tailoring_alloced_length > newlen ||
(i->tailoring = static_cast<char *>(
realloc(i->tailoring,
(i->tailoring_alloced_length = (newlen + 32U * 1024U)))))) {
return MY_XML_OK;
}
return MY_XML_ERROR;
}
static int fill_uchar(uint8_t *a, unsigned size, const char *str, size_t len) {
unsigned i = 0;
const char *s, *b, *e = str + len;
for (s = str; s < e; i++) {
for (; (s < e) && strchr(" \t\r\n", s[0]); s++)
;
b = s;
for (; (s < e) && !strchr(" \t\r\n", s[0]); s++)
;
if (s == b || i > size) break;
a[i] = (uint8_t)strtoul(b, nullptr, 16);
}
return 0;
}
static int fill_uint16(uint16_t *a, unsigned size, const char *str,
size_t len) {
unsigned i = 0;
const char *s, *b, *e = str + len;
for (s = str; s < e; i++) {
for (; (s < e) && strchr(" \t\r\n", s[0]); s++)
;
b = s;
for (; (s < e) && !strchr(" \t\r\n", s[0]); s++)
;
if (s == b || i > size) break;
a[i] = (uint16_t)strtol(b, nullptr, 16);
}
return 0;
}
static int tailoring_append(MY_XML_PARSER *st, const char *fmt, size_t len,
const char *attr) {
struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
size_t newlen = i->tailoring_length + len + 64; /* 64 for format */
if (MY_XML_OK == my_charset_file_tailoring_realloc(i, newlen)) {
char *dst = i->tailoring + i->tailoring_length;
sprintf(dst, fmt, (int)len, attr);
i->tailoring_length += strlen(dst);
return MY_XML_OK;
}
return MY_XML_ERROR;
}
static int tailoring_append2(MY_XML_PARSER *st, const char *fmt, size_t len1,
const char *attr1, size_t len2,
const char *attr2) {
struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
size_t newlen = i->tailoring_length + len1 + len2 + 64; /* 64 for format */
if (MY_XML_OK == my_charset_file_tailoring_realloc(i, newlen)) {
char *dst = i->tailoring + i->tailoring_length;
sprintf(dst, fmt, (int)len1, attr1, (int)len2, attr2);
i->tailoring_length += strlen(dst);
return MY_XML_OK;
}
return MY_XML_ERROR;
}
static size_t scan_one_character(const char *s, const char *e, my_wc_t *wc) {
CHARSET_INFO *cs = &my_charset_utf8mb3_general_ci;
if (s >= e) return 0;
/* Escape sequence: \uXXXX */
if (s[0] == '\\' && s + 2 < e && s[1] == 'u' && my_isxdigit(cs, s[2])) {
size_t len = 3; /* We have at least one digit */
for (s += 3; s < e && my_isxdigit(cs, s[0]); s++, len++) {
}
wc[0] = 0;
return len;
} else if ((s[0] & 0x80) == 0) /* 7-bit character */
{
wc[0] = 0;
return 1;
} else /* Non-escaped character */
{
int rc = cs->cset->mb_wc(cs, wc, pointer_cast<const uint8_t *>(s),
pointer_cast<const uint8_t *>(e));
if (rc > 0) return (size_t)rc;
}
return 0;
}
static int tailoring_append_abbreviation(MY_XML_PARSER *st, const char *fmt,
size_t len, const char *attr) {
size_t clen;
const char *attrend = attr + len;
my_wc_t wc;
for (; (clen = scan_one_character(attr, attrend, &wc)) > 0; attr += clen) {
assert(attr < attrend);
if (tailoring_append(st, fmt, clen, attr) != MY_XML_OK) return MY_XML_ERROR;
}
return MY_XML_OK;
}
extern "C" {
static int cs_enter(MY_XML_PARSER *st, const char *attr, size_t len) {
struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
struct my_cs_file_section_st *s = cs_file_sec(attr, len);
int state = s ? s->state : 0;
switch (state) {
case 0:
i->loader->reporter(WARNING_LEVEL, EE_UNKNOWN_LDML_TAG, (int)len, attr);
break;
case _CS_CHARSET:
my_charset_file_reset_charset(i);
break;
case _CS_COLLATION:
my_charset_file_reset_collation(i);
break;
case _CS_RESET:
return tailoring_append(st, " &", 0, nullptr);
default:
break;
}
return MY_XML_OK;
}
static int cs_leave(MY_XML_PARSER *st, const char *attr, size_t len) {
struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
struct my_cs_file_section_st *s = cs_file_sec(attr, len);
int state = s ? s->state : 0;
int rc;
switch (state) {
case _CS_COLLATION:
if (i->tailoring_length) i->cs.tailoring = i->tailoring;
rc = i->loader->add_collation(&i->cs);
break;
/* Rules: Logical Reset Positions */
case _CS_RESET_FIRST_NON_IGNORABLE:
rc = tailoring_append(st, "[first non-ignorable]", 0, nullptr);
break;
case _CS_RESET_LAST_NON_IGNORABLE:
rc = tailoring_append(st, "[last non-ignorable]", 0, nullptr);
break;
case _CS_RESET_FIRST_PRIMARY_IGNORABLE:
rc = tailoring_append(st, "[first primary ignorable]", 0, nullptr);
break;
case _CS_RESET_LAST_PRIMARY_IGNORABLE:
rc = tailoring_append(st, "[last primary ignorable]", 0, nullptr);
break;
case _CS_RESET_FIRST_SECONDARY_IGNORABLE:
rc = tailoring_append(st, "[first secondary ignorable]", 0, nullptr);
break;
case _CS_RESET_LAST_SECONDARY_IGNORABLE:
rc = tailoring_append(st, "[last secondary ignorable]", 0, nullptr);
break;
case _CS_RESET_FIRST_TERTIARY_IGNORABLE:
rc = tailoring_append(st, "[first tertiary ignorable]", 0, nullptr);
break;
case _CS_RESET_LAST_TERTIARY_IGNORABLE:
rc = tailoring_append(st, "[last tertiary ignorable]", 0, nullptr);
break;
case _CS_RESET_FIRST_TRAILING:
rc = tailoring_append(st, "[first trailing]", 0, nullptr);
break;
case _CS_RESET_LAST_TRAILING:
rc = tailoring_append(st, "[last trailing]", 0, nullptr);
break;
case _CS_RESET_FIRST_VARIABLE:
rc = tailoring_append(st, "[first variable]", 0, nullptr);
break;
case _CS_RESET_LAST_VARIABLE:
rc = tailoring_append(st, "[last variable]", 0, nullptr);
break;
default:
rc = MY_XML_OK;
}
return rc;
}
} // extern "C"
static const char *diff_fmt[5] = {"<%.*s", "<<%.*s", "<<<%.*s", "<<<<%.*s",
"=%.*s"};
static const char *context_diff_fmt[5] = {
"<%.*s|%.*s", "<<%.*s|%.*s", "<<<%.*s|%.*s", "<<<<%.*s|%.*s", "=%.*s|%.*s"};
extern "C" {
static int cs_value(MY_XML_PARSER *st, const char *attr, size_t len) {
struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
struct my_cs_file_section_st *s;
int state =
(int)((s = cs_file_sec(st->attr.start, st->attr.end - st->attr.start))
? s->state
: 0);
int rc = MY_XML_OK;
switch (state) {
case _CS_MISC:
case _CS_FAMILY:
case _CS_ORDER:
break;
case _CS_ID:
i->cs.number = strtol(attr, (char **)nullptr, 10);
break;
case _CS_BINARY_ID:
i->cs.binary_number = strtol(attr, (char **)nullptr, 10);
break;
case _CS_PRIMARY_ID:
i->cs.primary_number = strtol(attr, (char **)nullptr, 10);
break;
case _CS_COLNAME:
i->cs.m_coll_name = mstr(i->name, attr, len, MY_CS_NAME_SIZE - 1);
break;
case _CS_CSNAME:
// Replace "utf8" with "utf8mb3" for external character sets.
if (0 == strncmp(attr, "utf8", len))
i->cs.csname =
mstr(i->csname, STRING_WITH_LEN("utf8mb3"), MY_CS_NAME_SIZE - 1);
else
i->cs.csname = mstr(i->csname, attr, len, MY_CS_NAME_SIZE - 1);
assert(0 != strcmp(i->cs.csname, "utf8"));
break;
case _CS_CSDESCRIPT:
i->cs.comment = mstr(i->comment, attr, len, MY_CS_CSDESCR_SIZE - 1);
break;
case _CS_FLAG:
if (!strncmp("primary", attr, len))
i->cs.state |= MY_CS_PRIMARY;
else if (!strncmp("binary", attr, len))
i->cs.state |= MY_CS_BINSORT;
else if (!strncmp("compiled", attr, len))
i->cs.state |= MY_CS_COMPILED;
break;
case _CS_UPPERMAP:
fill_uchar(i->to_upper, MY_CS_TO_UPPER_TABLE_SIZE, attr, len);
i->cs.to_upper = i->to_upper;
break;
case _CS_LOWERMAP:
fill_uchar(i->to_lower, MY_CS_TO_LOWER_TABLE_SIZE, attr, len);
i->cs.to_lower = i->to_lower;
break;
case _CS_UNIMAP:
fill_uint16(i->tab_to_uni, MY_CS_TO_UNI_TABLE_SIZE, attr, len);
i->cs.tab_to_uni = i->tab_to_uni;
break;
case _CS_COLLMAP:
fill_uchar(i->sort_order, MY_CS_SORT_ORDER_TABLE_SIZE, attr, len);
i->cs.sort_order = i->sort_order;
break;
case _CS_CTYPEMAP:
fill_uchar(i->ctype, MY_CS_CTYPE_TABLE_SIZE, attr, len);
i->cs.ctype = i->ctype;
break;
/* Special purpose commands */
case _CS_UCA_VERSION:
rc = tailoring_append(st, "[version %.*s]", len, attr);
break;
case _CS_CL_SUPPRESS_CONTRACTIONS:
rc = tailoring_append(st, "[suppress contractions %.*s]", len, attr);
break;
case _CS_CL_OPTIMIZE:
rc = tailoring_append(st, "[optimize %.*s]", len, attr);
break;
case _CS_CL_SHIFT_AFTER_METHOD:
rc = tailoring_append(st, "[shift-after-method %.*s]", len, attr);
break;
/* Collation Settings */
case _CS_ST_STRENGTH:
/* 1, 2, 3, 4, 5, or primary, secondary, tertiary, quaternary, identical
*/
rc = tailoring_append(st, "[strength %.*s]", len, attr);
break;
case _CS_ST_ALTERNATE:
/* non-ignorable, shifted */
rc = tailoring_append(st, "[alternate %.*s]", len, attr);
break;
case _CS_ST_BACKWARDS:
/* on, off, 2 */
rc = tailoring_append(st, "[backwards %.*s]", len, attr);
break;
case _CS_ST_NORMALIZATION:
/*
TODO for WL#896: check collations for normalization: vi.xml
We want precomposed characters work well at this point.
*/
/* on, off */
rc = tailoring_append(st, "[normalization %.*s]", len, attr);
break;
case _CS_ST_CASE_LEVEL:
/* on, off */
rc = tailoring_append(st, "[caseLevel %.*s]", len, attr);
break;
case _CS_ST_CASE_FIRST:
/* upper, lower, off */
rc = tailoring_append(st, "[caseFirst %.*s]", len, attr);
break;
case _CS_ST_HIRAGANA_QUATERNARY:
/* on, off */
rc = tailoring_append(st, "[hiraganaQ %.*s]", len, attr);
break;
case _CS_ST_NUMERIC:
/* on, off */
rc = tailoring_append(st, "[numeric %.*s]", len, attr);
break;
case _CS_ST_VARIABLE_TOP:
/* TODO for WL#896: check value format */
rc = tailoring_append(st, "[variableTop %.*s]", len, attr);
break;
case _CS_ST_MATCH_BOUNDARIES:
/* none, whole-character, whole-word */
rc = tailoring_append(st, "[match-boundaries %.*s]", len, attr);
break;
case _CS_ST_MATCH_STYLE:
/* minimal, medial, maximal */
rc = tailoring_append(st, "[match-style %.*s]", len, attr);
break;
/* Rules */
case _CS_RESET:
rc = tailoring_append(st, "%.*s", len, attr);
break;
case _CS_DIFF1:
case _CS_DIFF2:
case _CS_DIFF3:
case _CS_DIFF4:
case _CS_IDENTICAL:
rc = tailoring_append(st, diff_fmt[state - _CS_DIFF1], len, attr);
break;
/* Rules: Expansion */
case _CS_EXP_EXTEND:
rc = tailoring_append(st, " / %.*s", len, attr);
break;
case _CS_EXP_DIFF1:
case _CS_EXP_DIFF2:
case _CS_EXP_DIFF3:
case _CS_EXP_DIFF4:
case _CS_EXP_IDENTICAL:
if (i->context[0]) {
rc = tailoring_append2(st, context_diff_fmt[state - _CS_EXP_DIFF1],
strlen(i->context), i->context, len, attr);
i->context[0] = 0;
} else
rc = tailoring_append(st, diff_fmt[state - _CS_EXP_DIFF1], len, attr);
break;
/* Rules: Context */
case _CS_CONTEXT:
if (len < sizeof(i->context)) {
memcpy(i->context, attr, len);
i->context[len] = '\0';
}
break;
/* Rules: Abbreviating Ordering Specifications */
case _CS_A_DIFF1:
case _CS_A_DIFF2:
case _CS_A_DIFF3:
case _CS_A_DIFF4:
case _CS_A_IDENTICAL:
rc = tailoring_append_abbreviation(st, diff_fmt[state - _CS_A_DIFF1], len,
attr);
break;
/* Rules: Placing Characters Before Others */
case _CS_RESET_BEFORE:
/*
TODO for WL#896: Add this check into text customization parser:
It is an error if the strength of the before relation is not identical
to the relation after the reset. We'll need this for WL#896.
*/
rc = tailoring_append(st, "[before %.*s]", len, attr);
break;
default:
break;
}
return rc;
}
} // extern "C"
bool my_parse_charset_xml(MY_CHARSET_LOADER *loader, const char *buf,
size_t len, MY_CHARSET_ERRMSG *errmsg) {
MY_XML_PARSER p;
struct my_cs_file_info info;
bool rc;
my_charset_file_init(&info);
my_xml_parser_create(&p);
my_xml_set_enter_handler(&p, cs_enter);
my_xml_set_value_handler(&p, cs_value);
my_xml_set_leave_handler(&p, cs_leave);
info.loader = loader;
my_xml_set_user_data(&p, (void *)&info);
rc = (my_xml_parse(&p, buf, len) == MY_XML_OK) ? false : true;
my_xml_parser_free(&p);
my_charset_file_free(&info);
if (rc != MY_XML_OK) {
const char *errstr = my_xml_error_string(&p);
if (sizeof(errmsg->errarg) > 32 + strlen(errstr)) {
sprintf(errmsg->errarg, "at line %d pos %d: %s",
my_xml_error_lineno(&p) + 1, (int)my_xml_error_pos(&p),
my_xml_error_string(&p));
}
}
return rc;
}
/*
Check repertoire: detect pure ascii strings
*/
unsigned my_string_repertoire(const CHARSET_INFO *cs, const char *str,
size_t length) {
const char *strend = str + length;
if (cs->mbminlen == 1) {
for (; str < strend; str++) {
if (((uint8_t)*str) > 0x7F) return MY_REPERTOIRE_UNICODE30;
}
} else {
my_wc_t wc;
int chlen;
for (; (chlen = cs->cset->mb_wc(cs, &wc, pointer_cast<const uint8_t *>(str),
pointer_cast<const uint8_t *>(strend))) > 0;
str += chlen) {
if (wc > 0x7F) return MY_REPERTOIRE_UNICODE30;
}
}
return MY_REPERTOIRE_ASCII;
}
/*
Returns repertoire for charset
*/
unsigned my_charset_repertoire(const CHARSET_INFO *cs) {
return cs->state & MY_CS_PUREASCII ? MY_REPERTOIRE_ASCII
: MY_REPERTOIRE_UNICODE30;
}
/*
Detect if a character set is 8bit,
and it is pure ascii, i.e. doesn't have
characters outside U+0000..U+007F
This functions is shared between "conf_to_src"
and dynamic charsets loader in "mysqld".
*/
bool my_charset_is_8bit_pure_ascii(const CHARSET_INFO *cs) {
size_t code;
if (!cs->tab_to_uni) return false;
for (code = 0; code < 256; code++) {
if (cs->tab_to_uni[code] > 0x7F) return false;
}
return true;
}
/*
Shared function between conf_to_src and mysys.
Check if a 8bit character set is compatible with
ascii on the range 0x00..0x7F.
*/
bool my_charset_is_ascii_compatible(const CHARSET_INFO *cs) {
if (!cs->tab_to_uni) return true;
for (unsigned i = 0; i < 128; i++) {
if (cs->tab_to_uni[i] != i) return false;
}
return true;
}
/**
Convert a string between two character sets.
'to' must be large enough to store (form_length * to_cs->mbmaxlen) bytes.
@param [out] to Store result here
@param to_length Size of "to" buffer
@param to_cs Character set of result string
@param from Copy from here
@param from_length Length of the "from" string
@param from_cs Character set of the "from" string
@param [out] errors Number of conversion errors
@return Number of bytes copied to 'to' string
*/
static size_t my_convert_internal(char *to, size_t to_length,
const CHARSET_INFO *to_cs, const char *from,
size_t from_length,
const CHARSET_INFO *from_cs,
unsigned *errors) {
int cnvres;
my_wc_t wc;
const uint8_t *from_end = pointer_cast<const uint8_t *>(from) + from_length;
char *to_start = to;
uint8_t *to_end = pointer_cast<uint8_t *>(to) + to_length;
my_charset_conv_mb_wc mb_wc = from_cs->cset->mb_wc;
my_charset_conv_wc_mb wc_mb = to_cs->cset->wc_mb;
unsigned error_count = 0;
while (true) {
if ((cnvres = (*mb_wc)(from_cs, &wc, pointer_cast<const uint8_t *>(from),
from_end)) > 0)
from += cnvres;
else if (cnvres == MY_CS_ILSEQ) {
error_count++;
from++;
wc = '?';
} else if (cnvres > MY_CS_TOOSMALL) {
/*
A correct multibyte sequence detected
But it doesn't have Unicode mapping.
*/
error_count++;
from += (-cnvres);
wc = '?';
} else
break; // Not enough characters
outp:
if ((cnvres = (*wc_mb)(to_cs, wc, pointer_cast<uint8_t *>(to), to_end)) > 0)
to += cnvres;
else if (cnvres == MY_CS_ILUNI && wc != '?') {
error_count++;
wc = '?';
goto outp;
} else
break;
}
*errors = error_count;
return (uint32_t)(to - to_start);
}
/**
Convert a string between two character sets.
Optimized for quick copying of ASCII characters in the range 0x00..0x7F.
'to' must be large enough to store (form_length * to_cs->mbmaxlen) bytes.
@param [out] to Store result here
@param to_length Size of "to" buffer
@param to_cs Character set of result string
@param from Copy from here
@param from_length Length of the "from" string
@param from_cs Character set of the "from" string
@param [out] errors Number of conversion errors
@return Number of bytes copied to 'to' string
*/
size_t my_convert(char *to, size_t to_length, const CHARSET_INFO *to_cs,
const char *from, size_t from_length,
const CHARSET_INFO *from_cs, unsigned *errors) {
size_t length = 0;
size_t length2 = 0;
/*
If any of the character sets is not ASCII compatible,
immediately switch to slow mb_wc->wc_mb method.
*/
if ((to_cs->state | from_cs->state) & MY_CS_NONASCII)
return my_convert_internal(to, to_length, to_cs, from, from_length, from_cs,
errors);
length = length2 = std::min(to_length, from_length);
#if defined(__i386__) || defined(_WIN32) || defined(__x86_64__)
/*
Special loop for i386, it allows to refer to a
non-aligned memory block as UINT32, which makes
it possible to copy four bytes at once. This
gives about 10% performance improvement comparing
to byte-by-byte loop.
*/
for (; length >= 4; length -= 4, from += 4, to += 4) {
if (uint4korr(from) & 0x80808080) break;
int4store(to, uint4korr(from));
}
#endif /* __i386__ */
for (;; *to++ = *from++, length--) {
if (!length) {
*errors = 0;
return length2;
}
if ((static_cast<uint8_t>(*from)) > 0x7F) /* A non-ASCII character */
{
size_t copied_length = length2 - length;
to_length -= copied_length;
from_length -= copied_length;
return copied_length + my_convert_internal(to, to_length, to_cs, from,
from_length, from_cs, errors);
}
}
assert(false); // Should never get to here
return 0; // Make compiler happy
}
/**
Get the length of the first code in given sequence of chars.
This func is introduced because we can't determine the length by
checking the first byte only for gb18030, so we first try my_mbcharlen,
and then my_mbcharlen_2 if necessary to get the length
@param[in] cs charset_info
@param[in] s start of the char sequence
@param[in] e end of the char sequence
@return The length of the first code, or 0 for invalid code
*/
unsigned my_mbcharlen_ptr(const CHARSET_INFO *cs, const char *s,
const char *e) {
unsigned len = my_mbcharlen(cs, (uint8_t)*s);
if (len == 0 && my_mbmaxlenlen(cs) == 2 && s + 1 < e) {
len = my_mbcharlen_2(cs, (uint8_t)*s, (uint8_t) * (s + 1));
/* It could be either a valid multi-byte GB18030 code, or invalid
gb18030 code if return value is 0 */
assert(len == 0 || len == 2 || len == 4);
}
return len;
}
/**
Identify whether given like pattern looks like a prefix pattern, which can
become candidate for index only scan on prefix indexes.
@param cs Character set and collation pointer
@param wildstr Pointer to LIKE pattern.
@param wildend Pointer to end of LIKE pattern.
@param escape Escape character pattern, typically '\'.
@param w_many 'Many characters' pattern, typically '%'.
@param[out] prefix_len Length of LIKE pattern.
@return Optimization status.
@retval TRUE if LIKE pattern can be used for prefix index only scan.
@retval FALSE else.
*/
bool my_is_prefixidx_cand(const CHARSET_INFO *cs, const char *wildstr,
const char *wildend, int escape, int w_many,
size_t *prefix_len) {