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
|
/* Copyright (C) 2000 MySQL AB
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; version 2 of the License.
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, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
/*
A better inplementation of the UNIX ctype(3) library.
Notes: drizzled/global.h should be included before ctype.h
*/
#ifndef _m_ctype_h
#define _m_ctype_h
#ifdef __cplusplus
extern "C" {
#endif
#define MY_CS_NAME_SIZE 32
#define MY_CS_CTYPE_TABLE_SIZE 257
#define MY_CS_TO_LOWER_TABLE_SIZE 256
#define MY_CS_TO_UPPER_TABLE_SIZE 256
#define MY_CS_SORT_ORDER_TABLE_SIZE 256
#define MY_CS_TO_UNI_TABLE_SIZE 256
#define CHARSET_DIR "charsets/"
#define my_wc_t ulong
typedef struct unicase_info_st
{
uint16_t toupper;
uint16_t tolower;
uint16_t sort;
} MY_UNICASE_INFO;
extern MY_UNICASE_INFO *my_unicase_default[256];
extern MY_UNICASE_INFO *my_unicase_turkish[256];
typedef struct uni_ctype_st
{
uchar pctype;
uchar *ctype;
} MY_UNI_CTYPE;
extern MY_UNI_CTYPE my_uni_ctype[256];
/* wm_wc and wc_mb return codes */
#define MY_CS_ILSEQ 0 /* Wrong by sequence: wb_wc */
#define MY_CS_ILUNI 0 /* Cannot encode Unicode to charset: wc_mb */
#define MY_CS_TOOSMALL -101 /* Need at least one byte: wc_mb and mb_wc */
#define MY_CS_TOOSMALL2 -102 /* Need at least two bytes: wc_mb and mb_wc */
#define MY_CS_TOOSMALL3 -103 /* Need at least three bytes: wc_mb and mb_wc */
/* These following three are currently not really used */
#define MY_CS_TOOSMALL4 -104 /* Need at least 4 bytes: wc_mb and mb_wc */
#define MY_CS_TOOSMALL5 -105 /* Need at least 5 bytes: wc_mb and mb_wc */
#define MY_CS_TOOSMALL6 -106 /* Need at least 6 bytes: wc_mb and mb_wc */
/* A helper macros for "need at least n bytes" */
#define MY_CS_TOOSMALLN(n) (-100-(n))
#define MY_SEQ_INTTAIL 1
#define MY_SEQ_SPACES 2
/* My charsets_list flags */
#define MY_CS_COMPILED 1 /* compiled-in sets */
#define MY_CS_CONFIG 2 /* sets that have a *.conf file */
#define MY_CS_INDEX 4 /* sets listed in the Index file */
#define MY_CS_LOADED 8 /* sets that are currently loaded */
#define MY_CS_BINSORT 16 /* if binary sort order */
#define MY_CS_PRIMARY 32 /* if primary collation */
#define MY_CS_STRNXFRM 64 /* if strnxfrm is used for sort */
#define MY_CS_UNICODE 128 /* is a charset is full unicode */
#define MY_CS_READY 256 /* if a charset is initialized */
#define MY_CS_AVAILABLE 512 /* If either compiled-in or loaded*/
#define MY_CS_CSSORT 1024 /* if case sensitive sort order */
#define MY_CS_HIDDEN 2048 /* don't display in SHOW */
#define MY_CS_PUREASCII 4096 /* if a charset is pure ascii */
#define MY_CS_NONASCII 8192 /* if not ASCII-compatible */
#define MY_CHARSET_UNDEFINED 0
/* Character repertoire flags */
#define MY_REPERTOIRE_ASCII 1 /* Pure ASCII U+0000..U+007F */
#define MY_REPERTOIRE_EXTENDED 2 /* Extended characters: U+0080..U+FFFF */
#define MY_REPERTOIRE_UNICODE30 3 /* ASCII | EXTENDED: U+0000..U+FFFF */
/* Flags for strxfrm */
#define MY_STRXFRM_LEVEL1 0x00000001 /* for primary weights */
#define MY_STRXFRM_LEVEL2 0x00000002 /* for secondary weights */
#define MY_STRXFRM_LEVEL3 0x00000004 /* for tertiary weights */
#define MY_STRXFRM_LEVEL4 0x00000008 /* fourth level weights */
#define MY_STRXFRM_LEVEL5 0x00000010 /* fifth level weights */
#define MY_STRXFRM_LEVEL6 0x00000020 /* sixth level weights */
#define MY_STRXFRM_LEVEL_ALL 0x0000003F /* Bit OR for the above six */
#define MY_STRXFRM_NLEVELS 6 /* Number of possible levels*/
#define MY_STRXFRM_PAD_WITH_SPACE 0x00000040 /* if pad result with spaces */
#define MY_STRXFRM_UNUSED_00000080 0x00000080 /* for future extensions */
#define MY_STRXFRM_DESC_LEVEL1 0x00000100 /* if desc order for level1 */
#define MY_STRXFRM_DESC_LEVEL2 0x00000200 /* if desc order for level2 */
#define MY_STRXFRM_DESC_LEVEL3 0x00000300 /* if desc order for level3 */
#define MY_STRXFRM_DESC_LEVEL4 0x00000800 /* if desc order for level4 */
#define MY_STRXFRM_DESC_LEVEL5 0x00001000 /* if desc order for level5 */
#define MY_STRXFRM_DESC_LEVEL6 0x00002000 /* if desc order for level6 */
#define MY_STRXFRM_DESC_SHIFT 8
#define MY_STRXFRM_UNUSED_00004000 0x00004000 /* for future extensions */
#define MY_STRXFRM_UNUSED_00008000 0x00008000 /* for future extensions */
#define MY_STRXFRM_REVERSE_LEVEL1 0x00010000 /* if reverse order for level1 */
#define MY_STRXFRM_REVERSE_LEVEL2 0x00020000 /* if reverse order for level2 */
#define MY_STRXFRM_REVERSE_LEVEL3 0x00040000 /* if reverse order for level3 */
#define MY_STRXFRM_REVERSE_LEVEL4 0x00080000 /* if reverse order for level4 */
#define MY_STRXFRM_REVERSE_LEVEL5 0x00100000 /* if reverse order for level5 */
#define MY_STRXFRM_REVERSE_LEVEL6 0x00200000 /* if reverse order for level6 */
#define MY_STRXFRM_REVERSE_SHIFT 16
typedef struct my_uni_idx_st
{
uint16_t from;
uint16_t to;
uchar *tab;
} MY_UNI_IDX;
typedef struct
{
uint beg;
uint end;
uint mb_len;
} my_match_t;
enum my_lex_states
{
MY_LEX_START, MY_LEX_CHAR, MY_LEX_IDENT,
MY_LEX_IDENT_SEP, MY_LEX_IDENT_START,
MY_LEX_REAL, MY_LEX_HEX_NUMBER, MY_LEX_BIN_NUMBER,
MY_LEX_CMP_OP, MY_LEX_LONG_CMP_OP, MY_LEX_STRING, MY_LEX_COMMENT, MY_LEX_END,
MY_LEX_OPERATOR_OR_IDENT, MY_LEX_NUMBER_IDENT, MY_LEX_INT_OR_REAL,
MY_LEX_REAL_OR_POINT, MY_LEX_BOOL, MY_LEX_EOL, MY_LEX_ESCAPE,
MY_LEX_LONG_COMMENT, MY_LEX_END_LONG_COMMENT, MY_LEX_SEMICOLON,
MY_LEX_SET_VAR, MY_LEX_USER_END, MY_LEX_HOSTNAME, MY_LEX_SKIP,
MY_LEX_USER_VARIABLE_DELIMITER, MY_LEX_SYSTEM_VAR,
MY_LEX_IDENT_OR_KEYWORD,
MY_LEX_IDENT_OR_HEX, MY_LEX_IDENT_OR_BIN,
MY_LEX_STRING_OR_DELIMITER
};
struct charset_info_st;
/* See strings/CHARSET_INFO.txt for information about this structure */
typedef struct my_collation_handler_st
{
bool (*init)(struct charset_info_st *, void *(*alloc)(size_t));
/* Collation routines */
int (*strnncoll)(const struct charset_info_st * const,
const uchar *, size_t, const uchar *, size_t, bool);
int (*strnncollsp)(const struct charset_info_st * const,
const uchar *, size_t, const uchar *, size_t,
bool diff_if_only_endspace_difference);
size_t (*strnxfrm)(const struct charset_info_st * const,
uchar *dst, size_t dstlen, uint nweights,
const uchar *src, size_t srclen, uint flags);
size_t (*strnxfrmlen)(const struct charset_info_st * const, size_t);
bool (*like_range)(const struct charset_info_st * const,
const char *s, size_t s_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_len, size_t *max_len);
int (*wildcmp)(const struct charset_info_st * const,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape,int w_one, int w_many);
int (*strcasecmp)(const struct charset_info_st * const, const char *, const char *);
uint (*instr)(const struct charset_info_st * const,
const char *b, size_t b_length,
const char *s, size_t s_length,
my_match_t *match, uint nmatch);
/* Hash calculation */
void (*hash_sort)(const struct charset_info_st *cs, const uchar *key, size_t len,
uint32_t *nr1, uint32_t *nr2);
bool (*propagate)(const struct charset_info_st *cs, const uchar *str, size_t len);
} MY_COLLATION_HANDLER;
extern MY_COLLATION_HANDLER my_collation_mb_bin_handler;
extern MY_COLLATION_HANDLER my_collation_8bit_bin_handler;
extern MY_COLLATION_HANDLER my_collation_8bit_simple_ci_handler;
extern MY_COLLATION_HANDLER my_collation_ucs2_uca_handler;
/* Some typedef to make it easy for C++ to make function pointers */
typedef int (*my_charset_conv_mb_wc)(const struct charset_info_st * const, my_wc_t *,
const uchar *, const uchar *);
typedef int (*my_charset_conv_wc_mb)(const struct charset_info_st * const, my_wc_t,
uchar *, uchar *);
typedef size_t (*my_charset_conv_case)(const struct charset_info_st * const,
char *, size_t, char *, size_t);
/* See strings/CHARSET_INFO.txt about information on this structure */
typedef struct my_charset_handler_st
{
bool (*init)(struct charset_info_st *, void *(*alloc)(size_t));
/* Multibyte routines */
uint (*ismbchar)(const struct charset_info_st * const, const char *, const char *);
uint (*mbcharlen)(const struct charset_info_st * const, uint c);
size_t (*numchars)(const struct charset_info_st * const, const char *b, const char *e);
size_t (*charpos)(const struct charset_info_st * const, const char *b, const char *e,
size_t pos);
size_t (*well_formed_len)(const struct charset_info_st * const,
const char *b,const char *e,
size_t nchars, int *error);
size_t (*lengthsp)(const struct charset_info_st * const, const char *ptr, size_t length);
size_t (*numcells)(const struct charset_info_st * const, const char *b, const char *e);
/* Unicode conversion */
my_charset_conv_mb_wc mb_wc;
my_charset_conv_wc_mb wc_mb;
/* CTYPE scanner */
int (*ctype)(const struct charset_info_st *cs, int *ctype,
const uchar *s, const uchar *e);
/* Functions for case and sort conversion */
size_t (*caseup_str)(const struct charset_info_st * const, char *);
size_t (*casedn_str)(const struct charset_info_st * const, char *);
my_charset_conv_case caseup;
my_charset_conv_case casedn;
/* Charset dependant snprintf() */
size_t (*snprintf)(const struct charset_info_st * const, char *to, size_t n,
const char *fmt,
...) __attribute__((format(printf, 4, 5)));
size_t (*long10_to_str)(const struct charset_info_st * const, char *to, size_t n,
int radix, long int val);
size_t (*int64_t10_to_str)(const struct charset_info_st * const, char *to, size_t n,
int radix, int64_t val);
void (*fill)(const struct charset_info_st * const, char *to, size_t len, int fill);
/* String-to-number conversion routines */
long (*strntol)(const struct charset_info_st * const, const char *s, size_t l,
int base, char **e, int *err);
ulong (*strntoul)(const struct charset_info_st * const, const char *s, size_t l,
int base, char **e, int *err);
int64_t (*strntoll)(const struct charset_info_st * const, const char *s, size_t l,
int base, char **e, int *err);
uint64_t (*strntoull)(const struct charset_info_st * const, const char *s, size_t l,
int base, char **e, int *err);
double (*strntod)(const struct charset_info_st * const, char *s, size_t l, char **e,
int *err);
int64_t (*strtoll10)(const struct charset_info_st *cs,
const char *nptr, char **endptr, int *error);
uint64_t (*strntoull10rnd)(const struct charset_info_st *cs,
const char *str, size_t length,
int unsigned_fl,
char **endptr, int *error);
size_t (*scan)(const struct charset_info_st * const, const char *b, const char *e,
int sq);
} MY_CHARSET_HANDLER;
extern MY_CHARSET_HANDLER my_charset_8bit_handler;
extern MY_CHARSET_HANDLER my_charset_ucs2_handler;
/* See strings/CHARSET_INFO.txt about information on this structure */
typedef struct charset_info_st
{
uint number;
uint primary_number;
uint binary_number;
uint state;
const char *csname;
const char *name;
const char *comment;
const char *tailoring;
uchar *ctype;
uchar *to_lower;
uchar *to_upper;
uchar *sort_order;
uint16_t *contractions;
uint16_t **sort_order_big;
uint16_t *tab_to_uni;
MY_UNI_IDX *tab_from_uni;
MY_UNICASE_INFO **caseinfo;
uchar *state_map;
uchar *ident_map;
uint strxfrm_multiply;
uchar caseup_multiply;
uchar casedn_multiply;
uint mbminlen;
uint mbmaxlen;
uint16_t min_sort_char;
uint16_t max_sort_char; /* For LIKE optimization */
uchar pad_char;
bool escape_with_backslash_is_dangerous;
uchar levels_for_compare;
uchar levels_for_order;
MY_CHARSET_HANDLER *cset;
MY_COLLATION_HANDLER *coll;
} CHARSET_INFO;
#define ILLEGAL_CHARSET_INFO_NUMBER (~0U)
extern CHARSET_INFO my_charset_bin;
extern CHARSET_INFO my_charset_big5_chinese_ci;
extern CHARSET_INFO my_charset_big5_bin;
extern CHARSET_INFO my_charset_cp932_japanese_ci;
extern CHARSET_INFO my_charset_cp932_bin;
extern CHARSET_INFO my_charset_cp1250_czech_ci;
extern CHARSET_INFO my_charset_eucjpms_japanese_ci;
extern CHARSET_INFO my_charset_eucjpms_bin;
extern CHARSET_INFO my_charset_euckr_korean_ci;
extern CHARSET_INFO my_charset_euckr_bin;
extern CHARSET_INFO my_charset_filename;
extern CHARSET_INFO my_charset_gb2312_chinese_ci;
extern CHARSET_INFO my_charset_gb2312_bin;
extern CHARSET_INFO my_charset_gbk_chinese_ci;
extern CHARSET_INFO my_charset_gbk_bin;
extern CHARSET_INFO my_charset_latin1;
extern CHARSET_INFO my_charset_latin1_german2_ci;
extern CHARSET_INFO my_charset_latin1_bin;
extern CHARSET_INFO my_charset_latin2_czech_ci;
extern CHARSET_INFO my_charset_sjis_japanese_ci;
extern CHARSET_INFO my_charset_sjis_bin;
extern CHARSET_INFO my_charset_tis620_thai_ci;
extern CHARSET_INFO my_charset_tis620_bin;
extern CHARSET_INFO my_charset_ucs2_general_ci;
extern CHARSET_INFO my_charset_ucs2_bin;
extern CHARSET_INFO my_charset_ucs2_unicode_ci;
extern CHARSET_INFO my_charset_ujis_japanese_ci;
extern CHARSET_INFO my_charset_ujis_bin;
extern CHARSET_INFO my_charset_utf16_bin;
extern CHARSET_INFO my_charset_utf16_general_ci;
extern CHARSET_INFO my_charset_utf16_unicode_ci;
extern CHARSET_INFO my_charset_utf32_bin;
extern CHARSET_INFO my_charset_utf32_general_ci;
extern CHARSET_INFO my_charset_utf32_unicode_ci;
extern CHARSET_INFO my_charset_utf8mb3_bin;
extern CHARSET_INFO my_charset_utf8mb3_general_ci;
extern CHARSET_INFO my_charset_utf8mb3_unicode_ci;
extern CHARSET_INFO my_charset_utf8mb4_bin;
extern CHARSET_INFO my_charset_utf8mb4_general_ci;
extern CHARSET_INFO my_charset_utf8mb4_unicode_ci;
#define MY_UTF8MB3 "utf8mb3"
#define MY_UTF8MB4 "utf8"
#define my_charset_utf8_general_ci my_charset_utf8mb4_general_ci
#define my_charset_utf8_bin my_charset_utf8mb4_bin
/* declarations for simple charsets */
extern size_t my_strnxfrm_simple(const CHARSET_INFO * const,
uchar *dst, size_t dstlen, uint nweights,
const uchar *src, size_t srclen, uint flags);
size_t my_strnxfrmlen_simple(const CHARSET_INFO * const, size_t);
extern int my_strnncoll_simple(const CHARSET_INFO * const, const uchar *, size_t,
const uchar *, size_t, bool);
extern int my_strnncollsp_simple(const CHARSET_INFO * const, const uchar *, size_t,
const uchar *, size_t,
bool diff_if_only_endspace_difference);
extern void my_hash_sort_simple(const CHARSET_INFO * const cs,
const uchar *key, size_t len,
uint32_t *nr1, uint32_t *nr2);
extern size_t my_lengthsp_8bit(const CHARSET_INFO * const cs, const char *ptr, size_t length);
extern uint my_instr_simple(const CHARSET_INFO * const,
const char *b, size_t b_length,
const char *s, size_t s_length,
my_match_t *match, uint nmatch);
/* Functions for 8bit */
extern size_t my_caseup_str_8bit(const CHARSET_INFO * const, char *);
extern size_t my_casedn_str_8bit(const CHARSET_INFO * const, char *);
extern size_t my_caseup_8bit(const CHARSET_INFO * const, char *src, size_t srclen,
char *dst, size_t dstlen);
extern size_t my_casedn_8bit(const CHARSET_INFO * const, char *src, size_t srclen,
char *dst, size_t dstlen);
extern int my_strcasecmp_8bit(const CHARSET_INFO * const cs, const char *, const char *);
int my_mb_wc_8bit(const CHARSET_INFO * const cs,my_wc_t *wc, const uchar *s,const uchar *e);
int my_wc_mb_8bit(const CHARSET_INFO * const cs,my_wc_t wc, uchar *s, uchar *e);
int my_mb_ctype_8bit(const CHARSET_INFO * const,int *, const uchar *,const uchar *);
int my_mb_ctype_mb(const CHARSET_INFO * const,int *, const uchar *,const uchar *);
size_t my_scan_8bit(const CHARSET_INFO * const cs, const char *b, const char *e, int sq);
size_t my_snprintf_8bit(const CHARSET_INFO * const, char *to, size_t n,
const char *fmt, ...)
__attribute__((format(printf, 4, 5)));
long my_strntol_8bit(const CHARSET_INFO * const, const char *s, size_t l, int base,
char **e, int *err);
ulong my_strntoul_8bit(const CHARSET_INFO * const, const char *s, size_t l, int base,
char **e, int *err);
int64_t my_strntoll_8bit(const CHARSET_INFO * const, const char *s, size_t l, int base,
char **e, int *err);
uint64_t my_strntoull_8bit(const CHARSET_INFO * const, const char *s, size_t l, int base,
char **e, int *err);
double my_strntod_8bit(const CHARSET_INFO * const, char *s, size_t l,char **e,
int *err);
size_t my_long10_to_str_8bit(const CHARSET_INFO * const, char *to, size_t l, int radix,
long int val);
size_t my_int64_t10_to_str_8bit(const CHARSET_INFO * const, char *to, size_t l, int radix,
int64_t val);
int64_t my_strtoll10_8bit(const CHARSET_INFO * const cs,
const char *nptr, char **endptr, int *error);
int64_t my_strtoll10_ucs2(CHARSET_INFO *cs,
const char *nptr, char **endptr, int *error);
uint64_t my_strntoull10rnd_8bit(const CHARSET_INFO * const cs,
const char *str, size_t length, int
unsigned_fl, char **endptr, int *error);
uint64_t my_strntoull10rnd_ucs2(CHARSET_INFO *cs,
const char *str, size_t length,
int unsigned_fl, char **endptr, int *error);
void my_fill_8bit(const CHARSET_INFO * const cs, char* to, size_t l, int fill);
bool my_like_range_simple(const CHARSET_INFO * const cs,
const char *ptr, size_t ptr_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_length, size_t *max_length);
bool my_like_range_mb(const CHARSET_INFO * const cs,
const char *ptr, size_t ptr_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_length, size_t *max_length);
bool my_like_range_ucs2(const CHARSET_INFO * const cs,
const char *ptr, size_t ptr_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_length, size_t *max_length);
bool my_like_range_utf16(const CHARSET_INFO * const cs,
const char *ptr, size_t ptr_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_length, size_t *max_length);
bool my_like_range_utf32(const CHARSET_INFO * const cs,
const char *ptr, size_t ptr_length,
char escape, char w_one, char w_many,
size_t res_length,
char *min_str, char *max_str,
size_t *min_length, size_t *max_length);
int my_wildcmp_8bit(const CHARSET_INFO * const,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
int my_wildcmp_bin(const CHARSET_INFO * const,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
size_t my_numchars_8bit(const CHARSET_INFO * const, const char *b, const char *e);
size_t my_numcells_8bit(const CHARSET_INFO * const, const char *b, const char *e);
size_t my_charpos_8bit(const CHARSET_INFO * const, const char *b, const char *e, size_t pos);
size_t my_well_formed_len_8bit(const CHARSET_INFO * const, const char *b, const char *e,
size_t pos, int *error);
uint my_mbcharlen_8bit(const CHARSET_INFO * const, uint c);
/* Functions for multibyte charsets */
extern size_t my_caseup_str_mb(const CHARSET_INFO * const, char *);
extern size_t my_casedn_str_mb(const CHARSET_INFO * const, char *);
extern size_t my_caseup_mb(const CHARSET_INFO * const, char *src, size_t srclen,
char *dst, size_t dstlen);
extern size_t my_casedn_mb(const CHARSET_INFO * const, char *src, size_t srclen,
char *dst, size_t dstlen);
extern int my_strcasecmp_mb(const CHARSET_INFO * const cs, const char *s, const char *t);
int my_wildcmp_mb(const CHARSET_INFO * const,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
size_t my_numchars_mb(const CHARSET_INFO * const, const char *b, const char *e);
size_t my_numcells_mb(const CHARSET_INFO * const, const char *b, const char *e);
size_t my_charpos_mb(const CHARSET_INFO * const, const char *b, const char *e, size_t pos);
size_t my_well_formed_len_mb(const CHARSET_INFO * const, const char *b, const char *e,
size_t pos, int *error);
uint my_instr_mb(const CHARSET_INFO * const,
const char *b, size_t b_length,
const char *s, size_t s_length,
my_match_t *match, uint nmatch);
int my_strnncoll_mb_bin(const CHARSET_INFO * const cs,
const uchar *s, size_t slen,
const uchar *t, size_t tlen,
bool t_is_prefix);
int my_strnncollsp_mb_bin(const CHARSET_INFO * const cs,
const uchar *a, size_t a_length,
const uchar *b, size_t b_length,
bool diff_if_only_endspace_difference);
int my_wildcmp_mb_bin(const CHARSET_INFO * const cs,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
int my_strcasecmp_mb_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const char *s, const char *t);
void my_hash_sort_mb_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *key, size_t len, uint32_t *nr1, uint32_t *nr2);
size_t my_strnxfrm_mb(const CHARSET_INFO * const,
uchar *dst, size_t dstlen, uint nweights,
const uchar *src, size_t srclen, uint flags);
int my_wildcmp_unicode(const CHARSET_INFO * const cs,
const char *str, const char *str_end,
const char *wildstr, const char *wildend,
int escape, int w_one, int w_many,
MY_UNICASE_INFO **weights);
extern bool my_parse_charset_xml(const char *bug, size_t len,
int (*add)(CHARSET_INFO *cs));
bool my_propagate_simple(const CHARSET_INFO * const cs, const uchar *str, size_t len);
bool my_propagate_complex(const CHARSET_INFO * const cs, const uchar *str, size_t len);
uint my_string_repertoire(const CHARSET_INFO * const cs, const char *str, ulong len);
bool my_charset_is_ascii_based(const CHARSET_INFO * const cs);
bool my_charset_is_8bit_pure_ascii(const CHARSET_INFO * const cs);
uint my_strxfrm_flag_normalize(uint flags, uint nlevels);
void my_strxfrm_desc_and_reverse(uchar *str, uchar *strend,
uint flags, uint level);
size_t my_strxfrm_pad_desc_and_reverse(const CHARSET_INFO * const cs,
uchar *str, uchar *frmend, uchar *strend,
uint nweights, uint flags, uint level);
bool my_charset_is_ascii_compatible(const CHARSET_INFO * const cs);
#define _MY_U 01 /* Upper case */
#define _MY_L 02 /* Lower case */
#define _MY_NMR 04 /* Numeral (digit) */
#define _MY_SPC 010 /* Spacing character */
#define _MY_PNT 020 /* Punctuation */
#define _MY_CTR 040 /* Control character */
#define _MY_B 0100 /* Blank */
#define _MY_X 0200 /* heXadecimal digit */
#define my_isascii(c) (!((c) & ~0177))
#define my_toascii(c) ((c) & 0177)
#define my_tocntrl(c) ((c) & 31)
#define my_toprint(c) ((c) | 64)
#define my_toupper(s,c) (char) ((s)->to_upper[(uchar) (c)])
#define my_tolower(s,c) (char) ((s)->to_lower[(uchar) (c)])
#define my_isalpha(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_U | _MY_L))
#define my_isupper(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_U)
#define my_islower(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_L)
#define my_isdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_NMR)
#define my_isxdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_X)
#define my_isalnum(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_U | _MY_L | _MY_NMR))
#define my_isspace(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_SPC)
#define my_ispunct(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_PNT)
#define my_isprint(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR | _MY_B))
#define my_isgraph(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR))
#define my_iscntrl(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_CTR)
/* Some macros that should be cleaned up a little */
#define my_isvar(s,c) (my_isalnum(s,c) || (c) == '_')
#define my_isvar_start(s,c) (my_isalpha(s,c) || (c) == '_')
#define my_binary_compare(s) ((s)->state & MY_CS_BINSORT)
#define use_strnxfrm(s) ((s)->state & MY_CS_STRNXFRM)
#define my_strnxfrm(cs, d, dl, s, sl) \
((cs)->coll->strnxfrm((cs), (d), (dl), (dl), (s), (sl), MY_STRXFRM_PAD_WITH_SPACE))
#define my_strnncoll(s, a, b, c, d) ((s)->coll->strnncoll((s), (a), (b), (c), (d), 0))
#define my_like_range(s, a, b, c, d, e, f, g, h, i, j) \
((s)->coll->like_range((s), (a), (b), (c), (d), (e), (f), (g), (h), (i), (j)))
#define my_wildcmp(cs,s,se,w,we,e,o,m) ((cs)->coll->wildcmp((cs),(s),(se),(w),(we),(e),(o),(m)))
#define my_strcasecmp(s, a, b) ((s)->coll->strcasecmp((s), (a), (b)))
#define my_charpos(cs, b, e, num) (cs)->cset->charpos((cs), (const char*) (b), (const char *)(e), (num))
#define use_mb(s) ((s)->cset->ismbchar != NULL)
#define my_ismbchar(s, a, b) ((s)->cset->ismbchar((s), (a), (b)))
#ifdef USE_MB
#define my_mbcharlen(s, a) ((s)->cset->mbcharlen((s),(a)))
#else
#define my_mbcharlen(s, a) 1
#endif
#define my_caseup_str(s, a) ((s)->cset->caseup_str((s), (a)))
#define my_casedn_str(s, a) ((s)->cset->casedn_str((s), (a)))
#define my_strntol(s, a, b, c, d, e) ((s)->cset->strntol((s),(a),(b),(c),(d),(e)))
#define my_strntoul(s, a, b, c, d, e) ((s)->cset->strntoul((s),(a),(b),(c),(d),(e)))
#define my_strntoll(s, a, b, c, d, e) ((s)->cset->strntoll((s),(a),(b),(c),(d),(e)))
#define my_strntoull(s, a, b, c,d, e) ((s)->cset->strntoull((s),(a),(b),(c),(d),(e)))
#define my_strntod(s, a, b, c, d) ((s)->cset->strntod((s),(a),(b),(c),(d)))
/* XXX: still need to take care of this one */
#ifdef MY_CHARSET_TIS620
#error The TIS620 charset is broken at the moment. Tell tim to fix it.
#define USE_TIS620
#include <mystrings/t_ctype.h>
#endif
#ifdef __cplusplus
}
#endif
#endif /* _m_ctype_h */
|