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
|
/* Copyright (C) 2002 MySQL AB & tommy@valley.ne.jp.
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public
License as published by the Free Software Foundation; version 2
of the License.
This library 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with this library; if not, write to the Free
Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
MA 02111-1307, USA */
/* This file is for binary pseudo charset, created by bar@mysql.com */
#include "m_string.h"
#include "m_ctype.h"
static uchar ctype_bin[]=
{
0,
32, 32, 32, 32, 32, 32, 32, 32, 32, 40, 40, 40, 40, 40, 32, 32,
32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32,
72, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
132,132,132,132,132,132,132,132,132,132, 16, 16, 16, 16, 16, 16,
16,129,129,129,129,129,129, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 16, 16, 16, 16, 16,
16,130,130,130,130,130,130, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 16, 16, 16, 16, 32,
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,
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,
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,
};
/* Dummy array for toupper / tolower / sortorder */
static uchar bin_char_array[] =
{
0, 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
};
static bool
my_coll_init_8bit_bin(CHARSET_INFO *cs,
void *(*alloc)(size_t) __attribute__((unused)))
{
cs->max_sort_char=255;
return false;
}
static int my_strnncoll_binary(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *s, size_t slen,
const uchar *t, size_t tlen,
bool t_is_prefix)
{
size_t len=min(slen,tlen);
int cmp= memcmp(s,t,len);
return cmp ? cmp : (int)((t_is_prefix ? len : slen) - tlen);
}
static size_t my_lengthsp_binary(const CHARSET_INFO * const cs __attribute__((unused)),
const char *ptr __attribute__((unused)),
size_t length)
{
return length;
}
/*
Compare two strings. Result is sign(first_argument - second_argument)
SYNOPSIS
my_strnncollsp_binary()
cs Chararacter set
s String to compare
slen Length of 's'
t String to compare
tlen Length of 't'
NOTE
This function is used for real binary strings, i.e. for
BLOB, BINARY(N) and VARBINARY(N).
It compares trailing spaces as spaces.
RETURN
< 0 s < t
0 s == t
> 0 s > t
*/
static int my_strnncollsp_binary(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *s, size_t slen,
const uchar *t, size_t tlen,
bool diff_if_only_endspace_difference
__attribute__((unused)))
{
return my_strnncoll_binary(cs,s,slen,t,tlen,0);
}
static int my_strnncoll_8bit_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *s, size_t slen,
const uchar *t, size_t tlen,
bool t_is_prefix)
{
size_t len=min(slen,tlen);
int cmp= memcmp(s,t,len);
return cmp ? cmp : (int)((t_is_prefix ? len : slen) - tlen);
}
/*
Compare two strings. Result is sign(first_argument - second_argument)
SYNOPSIS
my_strnncollsp_8bit_bin()
cs Chararacter set
s String to compare
slen Length of 's'
t String to compare
tlen Length of 't'
diff_if_only_endspace_difference
Set to 1 if the strings should be regarded as different
if they only difference in end space
NOTE
This function is used for character strings with binary collations.
The shorter string is extended with end space to be as long as the longer
one.
RETURN
< 0 s < t
0 s == t
> 0 s > t
*/
static int my_strnncollsp_8bit_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *a, size_t a_length,
const uchar *b, size_t b_length,
bool diff_if_only_endspace_difference)
{
const uchar *end;
size_t length;
int res;
#ifndef VARCHAR_WITH_DIFF_ENDSPACE_ARE_DIFFERENT_FOR_UNIQUE
diff_if_only_endspace_difference= 0;
#endif
end= a + (length= min(a_length, b_length));
while (a < end)
{
if (*a++ != *b++)
return ((int) a[-1] - (int) b[-1]);
}
res= 0;
if (a_length != b_length)
{
int swap= 1;
/*
Check the next not space character of the longer key. If it's < ' ',
then it's smaller than the other key.
*/
if (diff_if_only_endspace_difference)
res= 1; /* Assume 'a' is bigger */
if (a_length < b_length)
{
/* put shorter key in s */
a_length= b_length;
a= b;
swap= -1; /* swap sign of result */
res= -res;
}
for (end= a + a_length-length; a < end ; a++)
{
if (*a != ' ')
return (*a < ' ') ? -swap : swap;
}
}
return res;
}
/* This function is used for all conversion functions */
static size_t my_case_str_bin(const CHARSET_INFO * const cs __attribute__((unused)),
char *str __attribute__((unused)))
{
return 0;
}
static size_t my_case_bin(const CHARSET_INFO * const cs __attribute__((unused)),
char *src __attribute__((unused)),
size_t srclen,
char *dst __attribute__((unused)),
size_t dstlen __attribute__((unused)))
{
return srclen;
}
static int my_strcasecmp_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const char *s, const char *t)
{
return strcmp(s,t);
}
uint my_mbcharlen_8bit(const CHARSET_INFO * const cs __attribute__((unused)),
uint c __attribute__((unused)))
{
return 1;
}
static int my_mb_wc_bin(const CHARSET_INFO * const cs __attribute__((unused)),
my_wc_t *wc,
const uchar *str,
const uchar *end __attribute__((unused)))
{
if (str >= end)
return MY_CS_TOOSMALL;
*wc=str[0];
return 1;
}
static int my_wc_mb_bin(const CHARSET_INFO * const cs __attribute__((unused)),
my_wc_t wc,
uchar *s,
uchar *e __attribute__((unused)))
{
if (s >= e)
return MY_CS_TOOSMALL;
if (wc < 256)
{
s[0]= (char) wc;
return 1;
}
return MY_CS_ILUNI;
}
static void my_hash_sort_8bit_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *key, size_t len,
uint32_t *nr1, uint32_t *nr2)
{
const uchar *pos = key;
/*
Remove trailing spaces. We have to do this to be able to compare
'A ' and 'A' as identical
*/
key= skip_trailing_space(key, len);
for (; pos < (uchar*) key ; pos++)
{
nr1[0]^=(ulong) ((((uint) nr1[0] & 63)+nr2[0]) *
((uint)*pos)) + (nr1[0] << 8);
nr2[0]+=3;
}
}
static void my_hash_sort_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const uchar *key, size_t len,
uint32_t *nr1, uint32_t *nr2)
{
const uchar *pos = key;
key+= len;
for (; pos < (uchar*) key ; pos++)
{
nr1[0]^=(ulong) ((((uint) nr1[0] & 63)+nr2[0]) *
((uint)*pos)) + (nr1[0] << 8);
nr2[0]+=3;
}
}
/*
The following defines is here to keep the following code identical to
the one in ctype-simple.c
*/
#define likeconv(s,A) (A)
#define INC_PTR(cs,A,B) (A)++
int my_wildcmp_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 result= -1; /* Not found, using wildcards */
while (wildstr != wildend)
{
while (*wildstr != w_many && *wildstr != w_one)
{
if (*wildstr == escape && wildstr+1 != wildend)
wildstr++;
if (str == str_end || likeconv(cs,*wildstr++) != likeconv(cs,*str++))
return(1); /* No match */
if (wildstr == wildend)
return(str != str_end); /* Match if both are at end */
result=1; /* Found an anchor char */
}
if (*wildstr == w_one)
{
do
{
if (str == str_end) /* Skip one char if possible */
return(result);
INC_PTR(cs,str,str_end);
} while (++wildstr < wildend && *wildstr == w_one);
if (wildstr == wildend)
break;
}
if (*wildstr == w_many)
{ /* Found w_many */
uchar cmp;
wildstr++;
/* Remove any '%' and '_' from the wild search string */
for (; wildstr != wildend ; wildstr++)
{
if (*wildstr == w_many)
continue;
if (*wildstr == w_one)
{
if (str == str_end)
return(-1);
INC_PTR(cs,str,str_end);
continue;
}
break; /* Not a wild character */
}
if (wildstr == wildend)
return(0); /* match if w_many is last */
if (str == str_end)
return(-1);
if ((cmp= *wildstr) == escape && wildstr+1 != wildend)
cmp= *++wildstr;
INC_PTR(cs,wildstr,wildend); /* This is compared through cmp */
cmp=likeconv(cs,cmp);
do
{
while (str != str_end && (uchar) likeconv(cs,*str) != cmp)
str++;
if (str++ == str_end)
return(-1);
{
int tmp=my_wildcmp_bin(cs,str,str_end,wildstr,wildend,escape,w_one,
w_many);
if (tmp <= 0)
return(tmp);
}
} while (str != str_end && wildstr[0] != w_many);
return(-1);
}
}
return(str != str_end ? 1 : 0);
}
static size_t
my_strnxfrm_8bit_bin(const CHARSET_INFO * const cs,
uchar * dst, size_t dstlen, uint nweights,
const uchar *src, size_t srclen, uint flags)
{
set_if_smaller(srclen, dstlen);
set_if_smaller(srclen, nweights);
if (dst != src)
memcpy(dst, src, srclen);
return my_strxfrm_pad_desc_and_reverse(cs, dst, dst + srclen, dst + dstlen,
nweights - srclen, flags, 0);
}
static
uint my_instr_bin(const CHARSET_INFO * const cs __attribute__((unused)),
const char *b, size_t b_length,
const char *s, size_t s_length,
my_match_t *match, uint nmatch)
{
register const uchar *str, *search, *end, *search_end;
if (s_length <= b_length)
{
if (!s_length)
{
if (nmatch)
{
match->beg= 0;
match->end= 0;
match->mb_len= 0;
}
return 1; /* Empty string is always found */
}
str= (const uchar*) b;
search= (const uchar*) s;
end= (const uchar*) b+b_length-s_length+1;
search_end= (const uchar*) s + s_length;
skip:
while (str != end)
{
if ( (*str++) == (*search))
{
register const uchar *i,*j;
i= str;
j= search+1;
while (j != search_end)
if ((*i++) != (*j++))
goto skip;
if (nmatch > 0)
{
match[0].beg= 0;
match[0].end= (size_t) (str- (const uchar*)b-1);
match[0].mb_len= match[0].end;
if (nmatch > 1)
{
match[1].beg= match[0].end;
match[1].end= match[0].end+s_length;
match[1].mb_len= match[1].end-match[1].beg;
}
}
return 2;
}
}
}
return 0;
}
MY_COLLATION_HANDLER my_collation_8bit_bin_handler =
{
my_coll_init_8bit_bin,
my_strnncoll_8bit_bin,
my_strnncollsp_8bit_bin,
my_strnxfrm_8bit_bin,
my_strnxfrmlen_simple,
my_like_range_simple,
my_wildcmp_bin,
my_strcasecmp_bin,
my_instr_bin,
my_hash_sort_8bit_bin,
my_propagate_simple
};
static MY_COLLATION_HANDLER my_collation_binary_handler =
{
NULL, /* init */
my_strnncoll_binary,
my_strnncollsp_binary,
my_strnxfrm_8bit_bin,
my_strnxfrmlen_simple,
my_like_range_simple,
my_wildcmp_bin,
my_strcasecmp_bin,
my_instr_bin,
my_hash_sort_bin,
my_propagate_simple
};
static MY_CHARSET_HANDLER my_charset_handler=
{
NULL, /* init */
NULL, /* ismbchar */
my_mbcharlen_8bit, /* mbcharlen */
my_numchars_8bit,
my_charpos_8bit,
my_well_formed_len_8bit,
my_lengthsp_binary,
my_numcells_8bit,
my_mb_wc_bin,
my_wc_mb_bin,
my_mb_ctype_8bit,
my_case_str_bin,
my_case_str_bin,
my_case_bin,
my_case_bin,
my_snprintf_8bit,
my_long10_to_str_8bit,
my_int64_t10_to_str_8bit,
my_fill_8bit,
my_strntol_8bit,
my_strntoul_8bit,
my_strntoll_8bit,
my_strntoull_8bit,
my_strntod_8bit,
my_strtoll10_8bit,
my_strntoull10rnd_8bit,
my_scan_8bit
};
CHARSET_INFO my_charset_bin =
{
63,0,0, /* number */
MY_CS_COMPILED|MY_CS_BINSORT|MY_CS_PRIMARY,/* state */
"binary", /* cs name */
"binary", /* name */
"", /* comment */
NULL, /* tailoring */
ctype_bin, /* ctype */
bin_char_array, /* to_lower */
bin_char_array, /* to_upper */
NULL, /* sort_order */
NULL, /* contractions */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
my_unicase_default, /* caseinfo */
NULL, /* state_map */
NULL, /* ident_map */
1, /* strxfrm_multiply */
1, /* caseup_multiply */
1, /* casedn_multiply */
1, /* mbminlen */
1, /* mbmaxlen */
0, /* min_sort_char */
255, /* max_sort_char */
0, /* pad char */
0, /* escape_with_backslash_is_dangerous */
1, /* levels_for_compare */
1, /* levels_for_order */
&my_charset_handler,
&my_collation_binary_handler
};
|