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
|
/* 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 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))
/* 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_CHARSET_UNDEFINED 0
#define MY_CHARSET_CURRENT (default_charset_info->number)
typedef struct my_uni_idx_st {
uint16 from;
uint16 to;
uchar *tab;
} MY_UNI_IDX;
typedef struct charset_info_st
{
uint number;
uint state;
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;
/* Collation routines */
uint strxfrm_multiply;
int (*strnncoll)(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 *, uint, pchar, uint,
char *, char *, uint *, uint *);
/* Multibyte routines */
uint mbmaxlen;
int (*ismbchar)(struct charset_info_st *, const char *, const char *);
my_bool (*ismbhead)(struct charset_info_st *, uint);
int (*mbcharlen)(struct charset_info_st *, uint);
/* 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);
void (*tosort)(struct charset_info_st *, char *, uint);
/* Functions for case comparison */
int (*strcasecmp)(struct charset_info_st *, const char *, const char *);
int (*strncasecmp)(struct charset_info_st *, const char *, const char *,
uint);
/* Hash calculation */
uint (*hash_caseup)(struct charset_info_st *cs, const byte *key, uint len);
void (*hash_sort)(struct charset_info_st *cs, const uchar *key, uint len,
ulong *nr1, ulong *nr2);
char max_sort_char; /* For LIKE optimization */
/* Charset dependant snprintf() */
int (*snprintf)(struct charset_info_st *, char *to, uint n, const char *fmt, ...);
long (*strtol)(struct charset_info_st *, const char *s, char **e, int base);
ulong (*strtoul)(struct charset_info_st *, const char *s, char **e, int base);
longlong (*strtoll)(struct charset_info_st *, const char *s, char **e, int base);
ulonglong (*strtoull)(struct charset_info_st *, const char *s, char **e, int base);
double (*strtod)(struct charset_info_st *, const char *s, char **e);
} CHARSET_INFO;
extern CHARSET_INFO *my_charset_bin;
extern CHARSET_INFO *my_charset_latin1;
extern CHARSET_INFO *default_charset_info;
extern CHARSET_INFO *system_charset_info;
extern CHARSET_INFO *all_charsets[256];
extern my_bool init_compiled_charsets(myf flags);
/* 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 uint my_hash_caseup_simple(CHARSET_INFO *cs,
const byte *key, uint len);
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 void my_tosort_8bit(CHARSET_INFO *, char *, uint);
extern int my_strcasecmp_8bit(CHARSET_INFO * cs, const char *, const char *);
extern int my_strncasecmp_8bit(CHARSET_INFO * cs, const char *, const char *, uint);
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);
int my_snprintf_8bit(struct charset_info_st *, char *to, uint n, const char *fmt, ...);
long my_strtol_8bit(CHARSET_INFO *, const char *s, char **e, int base);
ulong my_strtoul_8bit(CHARSET_INFO *, const char *s, char **e, int base);
longlong my_strtoll_8bit(CHARSET_INFO *, const char *s, char **e, int base);
ulonglong my_strtoull_8bit(CHARSET_INFO *, const char *s, char **e, int base);
double my_strtod_8bit(CHARSET_INFO *, const char *s, char **e);
#ifdef USE_MB
/* 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 *);
extern int my_strncasecmp_mb(CHARSET_INFO * cs,const char *, const char *t, uint);
#endif
#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)->strnxfrm != NULL)
#define my_strnxfrm(s, a, b, c, d) ((s)->strnxfrm((s), (a), (b), (c), (d)))
#define my_strnncoll(s, a, b, c, d) ((s)->strnncoll((s), (a), (b), (c), (d)))
#define my_like_range(s, a, b, c, d, e, f, g, h) \
((s)->like_range((s), (a), (b), (c), (d), (e), (f), (g), (h)))
#define use_mb(s) ((s)->ismbchar != NULL)
#define my_ismbchar(s, a, b) ((s)->ismbchar((s), (a), (b)))
#define my_ismbhead(s, a) ((s)->ismbhead((s), (a)))
#define my_mbcharlen(s, a) ((s)->mbcharlen((s),(a)))
#define my_caseup(s, a, l) ((s)->caseup((s), (a), (l)))
#define my_casedn(s, a, l) ((s)->casedn((s), (a), (l)))
#define my_tosort(s, a, l) ((s)->tosort((s), (a), (l)))
#define my_caseup_str(s, a) ((s)->caseup_str((s), (a)))
#define my_casedn_str(s, a) ((s)->casedn_str((s), (a)))
#define my_strcasecmp(s, a, b) ((s)->strcasecmp((s), (a), (b)))
#define my_strncasecmp(s, a, b, l) ((s)->strncasecmp((s), (a), (b), (l)))
#define my_strtol(s, a, b, c) ((s)->strtol((s),(a),(b),(c)))
#define my_strtoul(s, a, b, c) ((s)->strtoul((s),(a),(b),(c)))
#define my_strtoll(s, a, b, c) ((s)->strtoll((s),(a),(b),(c)))
#define my_strtoull(s, a, b, c) ((s)->strtoull((s),(a),(b),(c)))
#define my_strtod(s, a, b) ((s)->strtod((s),(a),(b)))
/* 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 */
|
