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
|
/* 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; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, 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: my_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 toupper;
uint16 tolower;
uint16 sort;
} MY_UNICASE_INFO;
#define MY_CS_ILSEQ 0
#define MY_CS_ILUNI 0
#define MY_CS_TOOSMALL -1
#define MY_CS_TOOFEW(n) (-1-(n))
#define MY_SEQ_INTTAIL 1
#define MY_SEQ_SPACES 2
/* My charsets_list flags */
#define MY_NO_SETS 0
#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_NONTEXT 256 /* if a charset is not sprintf() compatible */
#define MY_CHARSET_UNDEFINED 0
typedef struct my_uni_idx_st
{
uint16 from;
uint16 to;
uchar *tab;
} MY_UNI_IDX;
enum my_lex_states
{
MY_LEX_START, MY_LEX_CHAR, MY_LEX_IDENT,
MY_LEX_IDENT_SEP, MY_LEX_IDENT_START,
MY_LEX_FOUND_IDENT, MY_LEX_REAL, MY_LEX_HEX_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_COLON,
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_IDENT_OR_NCHAR,
MY_LEX_STRING_OR_DELIMITER
};
struct charset_info_st;
typedef struct my_collation_handler_st
{
/* Collation routines */
int (*strnncoll)(struct charset_info_st *,
const uchar *, uint, const uchar *, uint);
int (*strnncollsp)(struct charset_info_st *,
const uchar *, uint, const uchar *, uint);
int (*strnxfrm)(struct charset_info_st *,
uchar *, uint, const uchar *, uint);
my_bool (*like_range)(struct charset_info_st *,
const char *s, uint s_length,
int w_prefix, int w_one, int w_many,
uint res_length,
char *min_str, char *max_str,
uint *min_len, uint *max_len);
int (*wildcmp)(struct charset_info_st *,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape,int w_one, int w_many);
int (*strcasecmp)(struct charset_info_st *, const char *, const char *);
/* Hash calculation */
void (*hash_sort)(struct charset_info_st *cs, const uchar *key, uint len,
ulong *nr1, ulong *nr2);
} MY_COLLATION_HANDLER;
extern MY_COLLATION_HANDLER my_collation_bin_handler;
extern MY_COLLATION_HANDLER my_collation_8bit_simple_ci_handler;
typedef struct my_charset_handler_st
{
/* Multibyte routines */
int (*ismbchar)(struct charset_info_st *, const char *, const char *);
int (*mbcharlen)(struct charset_info_st *, uint);
uint (*numchars)(struct charset_info_st *, const char *b, const char *e);
uint (*charpos)(struct charset_info_st *, const char *b, const char *e, uint pos);
/* Unicode convertion */
int (*mb_wc)(struct charset_info_st *cs,my_wc_t *wc,
const unsigned char *s,const unsigned char *e);
int (*wc_mb)(struct charset_info_st *cs,my_wc_t wc,
unsigned char *s,unsigned char *e);
/* Functions for case and sort convertion */
void (*caseup_str)(struct charset_info_st *, char *);
void (*casedn_str)(struct charset_info_st *, char *);
void (*caseup)(struct charset_info_st *, char *, uint);
void (*casedn)(struct charset_info_st *, char *, uint);
/* Charset dependant snprintf() */
int (*snprintf)(struct charset_info_st *, char *to, uint n, const char *fmt,
...);
int (*long10_to_str)(struct charset_info_st *, char *to, uint n, int radix,
long int val);
int (*longlong10_to_str)(struct charset_info_st *, char *to, uint n,
int radix, longlong val);
void (*fill)(struct charset_info_st *, char *to, uint len, int fill);
/* String-to-number convertion routines */
long (*strntol)(struct charset_info_st *, const char *s, uint l,
int base, char **e, int *err);
ulong (*strntoul)(struct charset_info_st *, const char *s, uint l,
int base, char **e, int *err);
longlong (*strntoll)(struct charset_info_st *, const char *s, uint l,
int base, char **e, int *err);
ulonglong (*strntoull)(struct charset_info_st *, const char *s, uint l,
int base, char **e, int *err);
double (*strntod)(struct charset_info_st *, char *s, uint l, char **e,
int *err);
ulong (*scan)(struct charset_info_st *, const char *b, const char *e,
int sq);
} MY_CHARSET_HANDLER;
extern MY_CHARSET_HANDLER my_charset_8bit_handler;
typedef struct charset_info_st
{
uint number;
uint primary_number;
uint binary_number;
uint state;
const char *csname;
const char *name;
const char *comment;
uchar *ctype;
uchar *to_lower;
uchar *to_upper;
uchar *sort_order;
uint16 *tab_to_uni;
MY_UNI_IDX *tab_from_uni;
uchar state_map[256];
uchar ident_map[256];
uint strxfrm_multiply;
uint mbmaxlen;
char max_sort_char; /* For LIKE optimization */
MY_CHARSET_HANDLER *cset;
MY_COLLATION_HANDLER *coll;
} CHARSET_INFO;
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_euckr_korean_ci;
extern CHARSET_INFO my_charset_euckr_bin;
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_ujis_japanese_ci;
extern CHARSET_INFO my_charset_ujis_bin;
extern CHARSET_INFO my_charset_utf8_general_ci;
extern CHARSET_INFO my_charset_utf8_bin;
extern CHARSET_INFO my_charset_cp1250_czech_ci;
/* declarations for simple charsets */
extern int my_strnxfrm_simple(CHARSET_INFO *, uchar *, uint, const uchar *,
uint);
extern int my_strnncoll_simple(CHARSET_INFO *, const uchar *, uint,
const uchar *, uint);
extern int my_strnncollsp_simple(CHARSET_INFO *, const uchar *, uint,
const uchar *, uint);
extern void my_hash_sort_simple(CHARSET_INFO *cs,
const uchar *key, uint len,
ulong *nr1, ulong *nr2);
/* Functions for 8bit */
extern void my_caseup_str_8bit(CHARSET_INFO *, char *);
extern void my_casedn_str_8bit(CHARSET_INFO *, char *);
extern void my_caseup_8bit(CHARSET_INFO *, char *, uint);
extern void my_casedn_8bit(CHARSET_INFO *, char *, uint);
extern int my_strcasecmp_8bit(CHARSET_INFO * cs, const char *, const char *);
int my_mb_wc_8bit(CHARSET_INFO *cs,my_wc_t *wc, const uchar *s,const uchar *e);
int my_wc_mb_8bit(CHARSET_INFO *cs,my_wc_t wc, uchar *s, uchar *e);
ulong my_scan_8bit(CHARSET_INFO *cs, const char *b, const char *e, int sq);
int my_snprintf_8bit(struct charset_info_st *, char *to, uint n,
const char *fmt, ...);
long my_strntol_8bit(CHARSET_INFO *, const char *s, uint l, int base,
char **e, int *err);
ulong my_strntoul_8bit(CHARSET_INFO *, const char *s, uint l, int base,
char **e, int *err);
longlong my_strntoll_8bit(CHARSET_INFO *, const char *s, uint l, int base,
char **e, int *err);
ulonglong my_strntoull_8bit(CHARSET_INFO *, const char *s, uint l, int base,
char **e, int *err);
double my_strntod_8bit(CHARSET_INFO *, char *s, uint l,char **e,
int *err);
int my_long10_to_str_8bit(CHARSET_INFO *, char *to, uint l, int radix,
long int val);
int my_longlong10_to_str_8bit(CHARSET_INFO *, char *to, uint l, int radix,
longlong val);
void my_fill_8bit(CHARSET_INFO *cs, char* to, uint l, int fill);
my_bool my_like_range_simple(CHARSET_INFO *cs,
const char *ptr, uint ptr_length,
int escape, int w_one, int w_many,
uint res_length,
char *min_str, char *max_str,
uint *min_length, uint *max_length);
int my_wildcmp_8bit(CHARSET_INFO *,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
uint my_numchars_8bit(CHARSET_INFO *, const char *b, const char *e);
uint my_charpos_8bit(CHARSET_INFO *, const char *b, const char *e, uint pos);
/* Functions for multibyte charsets */
extern void my_caseup_str_mb(CHARSET_INFO *, char *);
extern void my_casedn_str_mb(CHARSET_INFO *, char *);
extern void my_caseup_mb(CHARSET_INFO *, char *, uint);
extern void my_casedn_mb(CHARSET_INFO *, char *, uint);
extern int my_strcasecmp_mb(CHARSET_INFO * cs,const char *, const char *);
int my_wildcmp_mb(CHARSET_INFO *,
const char *str,const char *str_end,
const char *wildstr,const char *wildend,
int escape, int w_one, int w_many);
uint my_numchars_mb(CHARSET_INFO *, const char *b, const char *e);
uint my_charpos_mb(CHARSET_INFO *, const char *b, const char *e, uint pos);
extern my_bool my_parse_charset_xml(const char *bug, uint len,
int (*add)(CHARSET_INFO *cs));
#define _U 01 /* Upper case */
#define _L 02 /* Lower case */
#define _NMR 04 /* Numeral (digit) */
#define _SPC 010 /* Spacing character */
#define _PNT 020 /* Punctuation */
#define _CTR 040 /* Control character */
#define _B 0100 /* Blank */
#define _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)] & (_U | _L))
#define my_isupper(s, c) (((s)->ctype+1)[(uchar) (c)] & _U)
#define my_islower(s, c) (((s)->ctype+1)[(uchar) (c)] & _L)
#define my_isdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _NMR)
#define my_isxdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _X)
#define my_isalnum(s, c) (((s)->ctype+1)[(uchar) (c)] & (_U | _L | _NMR))
#define my_isspace(s, c) (((s)->ctype+1)[(uchar) (c)] & _SPC)
#define my_ispunct(s, c) (((s)->ctype+1)[(uchar) (c)] & _PNT)
#define my_isprint(s, c) (((s)->ctype+1)[(uchar) (c)] & (_PNT | _U | _L | _NMR | _B))
#define my_isgraph(s, c) (((s)->ctype+1)[(uchar) (c)] & (_PNT | _U | _L | _NMR))
#define my_iscntrl(s, c) (((s)->ctype+1)[(uchar) (c)] & _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 use_strnxfrm(s) ((s)->state & MY_CS_STRNXFRM)
#define my_strnxfrm(s, a, b, c, d) ((s)->coll->strnxfrm((s), (a), (b), (c), (d)))
#define my_strnncoll(s, a, b, c, d) ((s)->coll->strnncoll((s), (a), (b), (c), (d)))
#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 use_mb(s) ((s)->cset->ismbchar != NULL)
#define my_ismbchar(s, a, b) ((s)->cset->ismbchar((s), (a), (b)))
#define my_mbcharlen(s, a) ((s)->cset->mbcharlen((s),(a)))
#define my_caseup(s, a, l) ((s)->cset->caseup((s), (a), (l)))
#define my_casedn(s, a, l) ((s)->cset->casedn((s), (a), (l)))
#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 "t_ctype.h"
#endif
#ifdef __cplusplus
}
#endif
#endif /* _m_ctype_h */
|