MySQL 8.0.30
Source Code Documentation
m_ctype.h
Go to the documentation of this file.
1/* Copyright (c) 2000, 2022, Oracle and/or its affiliates.
2
3 This program is free software; you can redistribute it and/or modify
4 it under the terms of the GNU General Public License, version 2.0,
5 as published by the Free Software Foundation.
6
7 This program is also distributed with certain software (including
8 but not limited to OpenSSL) that is licensed under separate terms,
9 as designated in a particular file or component or in included license
10 documentation. The authors of MySQL hereby grant you an additional
11 permission to link the program and your derivative works with the
12 separately licensed software that they have included with MySQL.
13
14 This program is distributed in the hope that it will be useful,
15 but WITHOUT ANY WARRANTY; without even the implied warranty of
16 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 GNU General Public License, version 2.0, for more details.
18
19 You should have received a copy of the GNU General Public License
20 along with this program; if not, write to the Free Software
21 Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */
22
23#ifndef M_CTYPE_INCLUDED
24#define M_CTYPE_INCLUDED
25
26/**
27 @file include/m_ctype.h
28 A better implementation of the UNIX ctype(3) library.
29*/
30
31#ifndef __cplusplus
32#include <stdbool.h>
33#endif
34#include <stddef.h>
35#include <sys/types.h>
36
37#include "my_compiler.h"
38#include "my_inttypes.h"
39#include "my_loglevel.h"
40#include "my_macros.h"
41#include "my_sharedlib.h"
42#include "template_utils.h"
43
44#define MY_CS_NAME_SIZE 32
45#define MY_CS_CTYPE_TABLE_SIZE 257
46#define MY_CS_TO_LOWER_TABLE_SIZE 256
47#define MY_CS_TO_UPPER_TABLE_SIZE 256
48#define MY_CS_SORT_ORDER_TABLE_SIZE 256
49#define MY_CS_TO_UNI_TABLE_SIZE 256
50
51#define CHARSET_DIR "charsets/"
52
53/**
54 Our own version of wchar_t, ie., a type that holds a single Unicode code point
55 ("wide character"). ulong is always big enough to hold any character
56 in the BMP.
57*/
58typedef ulong my_wc_t;
59
60#define MY_CS_REPLACEMENT_CHARACTER 0xFFFD
61
62static inline void MY_PUT_MB2(unsigned char *s, uint16 code) {
63 s[0] = code >> 8;
64 s[1] = code & 0xFF;
65}
66
67typedef struct MY_UNICASE_CHARACTER {
72
73typedef struct MY_UNICASE_INFO {
77
82
83struct MY_UCA_INFO;
84
85typedef struct MY_UNI_CTYPE {
89
90extern MY_UNI_CTYPE my_uni_ctype[256];
91
92/* wm_wc and wc_mb return codes */
93#define MY_CS_ILSEQ 0 /* Wrong by sequence: wb_wc */
94#define MY_CS_ILUNI 0 /* Cannot encode Unicode to charset: wc_mb */
95#define MY_CS_TOOSMALL -101 /* Need at least one byte: wc_mb and mb_wc */
96#define MY_CS_TOOSMALL2 -102 /* Need at least two bytes: wc_mb and mb_wc */
97#define MY_CS_TOOSMALL3 -103 /* Need at least three bytes: wc_mb and mb_wc */
98/* These following three are currently not really used */
99#define MY_CS_TOOSMALL4 -104 /* Need at least 4 bytes: wc_mb and mb_wc */
100#define MY_CS_TOOSMALL5 -105 /* Need at least 5 bytes: wc_mb and mb_wc */
101#define MY_CS_TOOSMALL6 -106 /* Need at least 6 bytes: wc_mb and mb_wc */
102/* A helper macros for "need at least n bytes" */
103#define MY_CS_TOOSMALLN(n) (-100 - (n))
104
105#define MY_SEQ_INTTAIL 1
106#define MY_SEQ_SPACES 2
107
108/* My charsets_list flags */
109#define MY_CS_COMPILED 1 /* compiled-in sets */
110#define MY_CS_CONFIG 2 /* sets that have a *.conf file */
111#define MY_CS_INDEX 4 /* sets listed in the Index file */
112#define MY_CS_LOADED 8 /* sets that are currently loaded */
113#define MY_CS_BINSORT 16 /* if binary sort order */
114#define MY_CS_PRIMARY 32 /* if primary collation */
115#define MY_CS_STRNXFRM \
116 64 /* \
117 if _not_ set, sort_order will \
118 give same result as strnxfrm -- \
119 all new collations should have this \
120 flag set, do not check it in new code \
121 */
122#define MY_CS_UNICODE 128 /* is a charset is BMP Unicode */
123#define MY_CS_READY 256 /* if a charset is initialized */
124#define MY_CS_AVAILABLE 512 /* If either compiled-in or loaded*/
125#define MY_CS_CSSORT 1024 /* if case sensitive sort order */
126#define MY_CS_HIDDEN 2048 /* don't display in SHOW */
127#define MY_CS_PUREASCII 4096 /* if a charset is pure ascii */
128#define MY_CS_NONASCII 8192 /* if not ASCII-compatible */
129#define MY_CS_UNICODE_SUPPLEMENT 16384 /* Non-BMP Unicode characters */
130#define MY_CS_LOWER_SORT 32768 /* If use lower case as weight */
131#define MY_CHARSET_UNDEFINED 0
132
133/* Character repertoire flags */
134#define MY_REPERTOIRE_ASCII 1 /* Pure ASCII U+0000..U+007F */
135#define MY_REPERTOIRE_EXTENDED 2 /* Extended characters: U+0080..U+FFFF */
136#define MY_REPERTOIRE_UNICODE30 3 /* ASCII | EXTENDED: U+0000..U+FFFF */
138/* Flags for strxfrm */
139#define MY_STRXFRM_PAD_TO_MAXLEN 0x00000080 /* if pad tail(for filesort) */
141typedef struct MY_UNI_IDX {
144 const uchar *tab;
146
147typedef struct {
148 uint beg;
149 uint end;
150 uint mb_len;
151} my_match_t;
152
153struct CHARSET_INFO;
154#ifndef __cplusplus
156#endif
159typedef struct MY_CHARSET_LOADER {
161 char errarg[192];
162 void *(*once_alloc)(size_t);
163 void *(*mem_malloc)(size_t);
164 void *(*mem_realloc)(void *, size_t);
165 void (*mem_free)(void *);
166 void (*reporter)(enum loglevel, uint errcode, ...);
169
170extern int (*my_string_stack_guard)(int);
173
174/* See strings/CHARSET_INFO.txt for information about this structure */
175typedef struct MY_COLLATION_HANDLER {
176 bool (*init)(CHARSET_INFO *, MY_CHARSET_LOADER *);
177 void (*uninit)(CHARSET_INFO *);
178 /* Collation routines */
179 int (*strnncoll)(const CHARSET_INFO *, const uchar *, size_t, const uchar *,
180 size_t, bool);
181 /**
182 Compare the two strings under the pad rules given by the collation.
183
184 Thus, for NO PAD collations, this is identical to strnncoll with is_prefix
185 set to false. For PAD SPACE collations, the two strings are conceptually
186 extended infinitely at the end using space characters (0x20) and then
187 compared under the collation's normal comparison rules, so that e.g 'a' is
188 equal to 'a '.
189 */
190 int (*strnncollsp)(const CHARSET_INFO *, const uchar *, size_t, const uchar *,
191 size_t);
192 /**
193 Transform the string into a form such that memcmp() between transformed
194 strings yields the correct collation order.
195
196 @param [out] dst Buffer for the transformed string.
197 @param [out] dstlen Number of bytes available in dstlen.
198 Must be even.
199 @param num_codepoints Treat the string as if it were of type
200 CHAR(num_codepoints). In particular, this means that if the
201 collation is a pad collation (pad_attribute is PAD_SPACE) and
202 string has fewer than "num_codepoints" codepoints, the string
203 will be transformed as if it ended in (num_codepoints-n) extra spaces.
204 If the string has more than "num_codepoints" codepoints,
205 behavior is undefined; may truncate, may crash, or do something
206 else entirely. Note that MY_STRXFRM_PAD_TO_MAXLEN overrides this;
207 if it is given for a PAD SPACE collation, this value is taken to be
208 effectively infinity.
209 @param src The source string, in the required character set
210 for the collation.
211 @param srclen Number of bytes in src.
212 @param flags ORed bitmask of MY_STRXFRM_* flags.
213
214 @return Number of bytes written to dst.
215 */
216 size_t (*strnxfrm)(const CHARSET_INFO *, uchar *dst, size_t dstlen,
217 uint num_codepoints, const uchar *src, size_t srclen,
218 uint flags);
219
220 /**
221 Return the maximum number of output bytes needed for strnxfrm()
222 to output all weights for any string of the given input length.
223 You can use this to e.g. size buffers for sort keys.
224
225 @param num_bytes Number of bytes in the input string. Note that for
226 multibyte character sets, this _must_ be a pessimistic estimate,
227 ie., one that's cs->mbmaxlen * max_num_codepoints. So for e.g.
228 the utf8mb4 string "foo", you will need to give in 12, not 3.
229 */
230 size_t (*strnxfrmlen)(const CHARSET_INFO *, size_t num_bytes);
231 bool (*like_range)(const CHARSET_INFO *, const char *s, size_t s_length,
232 char w_prefix, char w_one, char w_many, size_t res_length,
233 char *min_str, char *max_str, size_t *min_len,
234 size_t *max_len);
235 int (*wildcmp)(const CHARSET_INFO *, const char *str, const char *str_end,
236 const char *wildstr, const char *wildend, int escape,
237 int w_one, int w_many);
238
239 int (*strcasecmp)(const CHARSET_INFO *, const char *, const char *);
240
241 uint (*strstr)(const CHARSET_INFO *, const char *b, size_t b_length,
242 const char *s, size_t s_length, my_match_t *match,
243 uint nmatch);
244
245 /**
246 Compute a sort hash for the given key. This hash must preserve equality
247 under the given collation, so that a=b => H(a)=H(b). Note that this hash
248 is used for hash-based partitioning (PARTITION KEY), so you cannot change
249 it except when writing a new collation; it needs to be unchanged across
250 releases, so that the on-disk format does not change. (It is also used
251 for testing equality in the MEMORY storage engine.)
252
253 nr1 and nr2 are both in/out parameters. nr1 is the actual hash value;
254 nr2 holds extra state between invocations.
255 */
256 void (*hash_sort)(const CHARSET_INFO *cs, const uchar *key, size_t len,
257 uint64 *nr1, uint64 *nr2);
258 bool (*propagate)(const CHARSET_INFO *cs, const uchar *str, size_t len);
260
265
266/* Some typedef to make it easy for C++ to make function pointers */
267typedef int (*my_charset_conv_mb_wc)(const CHARSET_INFO *, my_wc_t *,
268 const uchar *, const uchar *);
269typedef int (*my_charset_conv_wc_mb)(const CHARSET_INFO *, my_wc_t, uchar *,
271typedef size_t (*my_charset_conv_case)(const CHARSET_INFO *, char *, size_t,
272 char *, size_t);
274/* See strings/CHARSET_INFO.txt about information on this structure */
275typedef struct MY_CHARSET_HANDLER {
276 bool (*init)(CHARSET_INFO *, MY_CHARSET_LOADER *loader);
277 /* Multibyte routines */
278 uint (*ismbchar)(const CHARSET_INFO *, const char *, const char *);
279 uint (*mbcharlen)(const CHARSET_INFO *, uint c);
280 size_t (*numchars)(const CHARSET_INFO *, const char *b, const char *e);
281
282 /**
283 Return at which byte codepoint number "pos" begins, relative to
284 the start of the string. If the string is shorter than or is
285 exactly "pos" codepoints long, returns a value equal or greater to
286 (e-b).
287 */
288 size_t (*charpos)(const CHARSET_INFO *, const char *b, const char *e,
289 size_t pos);
290 size_t (*well_formed_len)(const CHARSET_INFO *, const char *b, const char *e,
291 size_t nchars, int *error);
292 /**
293 Given a pointer and a length in bytes, returns a new length in bytes where
294 all trailing space characters are stripped. This holds even for NO PAD
295 collations.
296
297 Exception: The "binary" collation, which is used behind-the-scenes to
298 implement the BINARY type (by mapping it to CHAR(n) COLLATE "binary"),
299 returns just the length back with no stripping. It's done that way so that
300 Field_string (implementing CHAR(n)) returns the full padded width on read
301 (as opposed to a normal CHAR, where we usually strip the spaces on read),
302 but it's suboptimal, since lengthsp() is also used in a number of other
303 places, e.g. stripping trailing spaces from enum values given in by the
304 user. If you call this function, be aware of this special exception and
305 consider the implications.
306 */
307 size_t (*lengthsp)(const CHARSET_INFO *, const char *ptr, size_t length);
308 size_t (*numcells)(const CHARSET_INFO *, const char *b, const char *e);
309
310 /* Unicode conversion */
313
314 /* CTYPE scanner */
315 int (*ctype)(const CHARSET_INFO *cs, int *ctype, const uchar *s,
316 const uchar *e);
318 /* Functions for case and sort conversion */
319 size_t (*caseup_str)(const CHARSET_INFO *, char *);
320 size_t (*casedn_str)(const CHARSET_INFO *, char *);
324
325 /* Charset dependent snprintf() */
326 size_t (*snprintf)(const CHARSET_INFO *, char *to, size_t n, const char *fmt,
327 ...) MY_ATTRIBUTE((format(printf, 4, 5)));
328 size_t (*long10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix,
329 long int val);
330 size_t (*longlong10_to_str)(const CHARSET_INFO *, char *to, size_t n,
331 int radix, longlong val);
332
333 void (*fill)(const CHARSET_INFO *, char *to, size_t len, int fill);
334
335 /* String-to-number conversion routines */
336 long (*strntol)(const CHARSET_INFO *, const char *s, size_t l, int base,
337 const char **e, int *err);
338 ulong (*strntoul)(const CHARSET_INFO *, const char *s, size_t l, int base,
339 const char **e, int *err);
340 longlong (*strntoll)(const CHARSET_INFO *, const char *s, size_t l, int base,
341 const char **e, int *err);
342 ulonglong (*strntoull)(const CHARSET_INFO *, const char *s, size_t l,
343 int base, const char **e, int *err);
344 double (*strntod)(const CHARSET_INFO *, const char *s, size_t l,
345 const char **e, int *err);
346 longlong (*strtoll10)(const CHARSET_INFO *cs, const char *nptr,
347 const char **endptr, int *error);
348 ulonglong (*strntoull10rnd)(const CHARSET_INFO *cs, const char *str,
349 size_t length, int unsigned_fl,
350 const char **endptr, int *error);
351 size_t (*scan)(const CHARSET_INFO *, const char *b, const char *e, int sq);
353
358/* See strings/CHARSET_INFO.txt about information on this structure */
364 const char *csname;
365 const char *m_coll_name;
366 const char *comment;
367 const char *tailoring;
369 const uchar *ctype;
373 struct MY_UCA_INFO *uca; /* This can be changed in apply_one_rule() */
377 const struct lex_state_maps_st *state_maps; /* parser internal data */
378 const uchar *ident_map; /* parser internal data */
386 my_wc_t max_sort_char; /* For LIKE optimization */
390
393
394 /**
395 If this collation is PAD_SPACE, it collates as if all inputs were
396 padded with a given number of spaces at the end (see the "num_codepoints"
397 flag to strnxfrm). NO_PAD simply compares unextended strings.
399 Note that this is fundamentally about the behavior of coll->strnxfrm.
400 */
402};
403#define ILLEGAL_CHARSET_INFO_NUMBER (~0U)
404
405/*
406 NOTE: You cannot use a CHARSET_INFO without it having been initialized first.
407 In particular, they are not initialized when a unit test starts; do not use
408 these globals indiscriminately from there, and do not add more. Instead,
409 load them through a MY_CHARSET_LOADER, using my_collation_get_by_name().
410*/
411
417
426
427#define MY_UTF8MB4 "utf8mb4"
428
429/* declarations for simple charsets */
430extern size_t my_strnxfrm_simple(const CHARSET_INFO *, uchar *dst,
431 size_t dstlen, uint nweights, const uchar *src,
432 size_t srclen, uint flags);
433size_t my_strnxfrmlen_simple(const CHARSET_INFO *, size_t);
434extern int my_strnncoll_simple(const CHARSET_INFO *, const uchar *, size_t,
435 const uchar *, size_t, bool);
436
437extern int my_strnncollsp_simple(const CHARSET_INFO *, const uchar *, size_t,
438 const uchar *, size_t);
439
440extern void my_hash_sort_simple(const CHARSET_INFO *cs, const uchar *key,
441 size_t len, uint64 *nr1, uint64 *nr2);
442
443extern size_t my_lengthsp_8bit(const CHARSET_INFO *cs, const char *ptr,
444 size_t length);
445
446extern uint my_instr_simple(const CHARSET_INFO *, const char *b,
447 size_t b_length, const char *s, size_t s_length,
448 my_match_t *match, uint nmatch);
449
450/* Functions for 8bit */
451extern size_t my_caseup_str_8bit(const CHARSET_INFO *, char *);
452extern size_t my_casedn_str_8bit(const CHARSET_INFO *, char *);
453extern size_t my_caseup_8bit(const CHARSET_INFO *, char *src, size_t srclen,
454 char *dst, size_t dstlen);
455extern size_t my_casedn_8bit(const CHARSET_INFO *, char *src, size_t srclen,
456 char *dst, size_t dstlen);
457
458extern int my_strcasecmp_8bit(const CHARSET_INFO *cs, const char *,
459 const char *);
460
461int my_mb_wc_8bit(const CHARSET_INFO *cs, my_wc_t *wc, const uchar *s,
462 const uchar *e);
463int my_wc_mb_8bit(const CHARSET_INFO *cs, my_wc_t wc, uchar *s, uchar *e);
464
465int my_mb_ctype_8bit(const CHARSET_INFO *, int *, const uchar *, const uchar *);
466int my_mb_ctype_mb(const CHARSET_INFO *, int *, const uchar *, const uchar *);
467
468size_t my_scan_8bit(const CHARSET_INFO *cs, const char *b, const char *e,
469 int sq);
470
471size_t my_snprintf_8bit(const CHARSET_INFO *, char *to, size_t n,
472 const char *fmt, ...)
473 MY_ATTRIBUTE((format(printf, 4, 5)));
474
475long my_strntol_8bit(const CHARSET_INFO *, const char *s, size_t l, int base,
476 const char **e, int *err);
477ulong my_strntoul_8bit(const CHARSET_INFO *, const char *s, size_t l, int base,
478 const char **e, int *err);
479longlong my_strntoll_8bit(const CHARSET_INFO *, const char *s, size_t l,
480 int base, const char **e, int *err);
481ulonglong my_strntoull_8bit(const CHARSET_INFO *, const char *s, size_t l,
482 int base, const char **e, int *err);
483double my_strntod_8bit(const CHARSET_INFO *, const char *s, size_t l,
484 const char **e, int *err);
485size_t my_long10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
486 int radix, long int val);
487size_t my_longlong10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
488 int radix, longlong val);
489
490longlong my_strtoll10_8bit(const CHARSET_INFO *cs, const char *nptr,
491 const char **endptr, int *error);
492longlong my_strtoll10_ucs2(const CHARSET_INFO *cs, const char *nptr,
493 char **endptr, int *error);
494
496 size_t length, int unsigned_fl,
497 const char **endptr, int *error);
499 size_t length, int unsigned_fl, char **endptr,
500 int *error);
501
502void my_fill_8bit(const CHARSET_INFO *cs, char *to, size_t l, int fill);
503
504/* For 8-bit character set */
505bool my_like_range_simple(const CHARSET_INFO *cs, const char *ptr,
506 size_t ptr_length, char escape, char w_one,
507 char w_many, size_t res_length, char *min_str,
508 char *max_str, size_t *min_length,
509 size_t *max_length);
510
511/* For ASCII-based multi-byte character sets with mbminlen=1 */
512bool my_like_range_mb(const CHARSET_INFO *cs, const char *ptr,
513 size_t ptr_length, char escape, char w_one, char w_many,
514 size_t res_length, char *min_str, char *max_str,
515 size_t *min_length, size_t *max_length);
516
517/* For other character sets, with arbitrary mbminlen and mbmaxlen numbers */
518bool my_like_range_generic(const CHARSET_INFO *cs, const char *ptr,
519 size_t ptr_length, char escape, char w_one,
520 char w_many, size_t res_length, char *min_str,
521 char *max_str, size_t *min_length,
522 size_t *max_length);
523
524int my_wildcmp_8bit(const CHARSET_INFO *, const char *str, const char *str_end,
525 const char *wildstr, const char *wildend, int escape,
526 int w_one, int w_many);
527
528int my_wildcmp_bin(const CHARSET_INFO *, const char *str, const char *str_end,
529 const char *wildstr, const char *wildend, int escape,
530 int w_one, int w_many);
531
532size_t my_numchars_8bit(const CHARSET_INFO *, const char *b, const char *e);
533size_t my_numcells_8bit(const CHARSET_INFO *, const char *b, const char *e);
534size_t my_charpos_8bit(const CHARSET_INFO *, const char *b, const char *e,
535 size_t pos);
536size_t my_well_formed_len_8bit(const CHARSET_INFO *, const char *b,
537 const char *e, size_t pos, int *error);
539
540/* Functions for multibyte charsets */
541extern size_t my_caseup_str_mb(const CHARSET_INFO *, char *);
542extern size_t my_casedn_str_mb(const CHARSET_INFO *, char *);
543extern size_t my_caseup_mb(const CHARSET_INFO *, char *src, size_t srclen,
544 char *dst, size_t dstlen);
545extern size_t my_casedn_mb(const CHARSET_INFO *, char *src, size_t srclen,
546 char *dst, size_t dstlen);
547extern size_t my_caseup_mb_varlen(const CHARSET_INFO *, char *src,
548 size_t srclen, char *dst, size_t dstlen);
549extern size_t my_casedn_mb_varlen(const CHARSET_INFO *, char *src,
550 size_t srclen, char *dst, size_t dstlen);
551extern size_t my_caseup_ujis(const CHARSET_INFO *, char *src, size_t srclen,
552 char *dst, size_t dstlen);
553extern size_t my_casedn_ujis(const CHARSET_INFO *, char *src, size_t srclen,
554 char *dst, size_t dstlen);
555extern int my_strcasecmp_mb(const CHARSET_INFO *cs, const char *, const char *);
556
557int my_wildcmp_mb(const CHARSET_INFO *, const char *str, const char *str_end,
558 const char *wildstr, const char *wildend, int escape,
559 int w_one, int w_many);
560size_t my_numchars_mb(const CHARSET_INFO *, const char *b, const char *e);
561size_t my_numcells_mb(const CHARSET_INFO *, const char *b, const char *e);
562size_t my_charpos_mb3(const CHARSET_INFO *, const char *b, const char *e,
563 size_t pos);
564size_t my_well_formed_len_mb(const CHARSET_INFO *, const char *b, const char *e,
565 size_t pos, int *error);
566uint my_instr_mb(const CHARSET_INFO *, const char *b, size_t b_length,
567 const char *s, size_t s_length, my_match_t *match,
568 uint nmatch);
569
570int my_strnncoll_mb_bin(const CHARSET_INFO *cs, const uchar *s, size_t slen,
571 const uchar *t, size_t tlen, bool t_is_prefix);
572
573int my_strnncollsp_mb_bin(const CHARSET_INFO *cs, const uchar *a,
574 size_t a_length, const uchar *b, size_t b_length);
575
576int my_wildcmp_mb_bin(const CHARSET_INFO *cs, const char *str,
577 const char *str_end, const char *wildstr,
578 const char *wildend, int escape, int w_one, int w_many);
579
580int my_strcasecmp_mb_bin(const CHARSET_INFO *cs [[maybe_unused]], const char *s,
581 const char *t);
582
583void my_hash_sort_mb_bin(const CHARSET_INFO *cs [[maybe_unused]],
584 const uchar *key, size_t len, uint64 *nr1,
585 uint64 *nr2);
586
587size_t my_strnxfrm_mb(const CHARSET_INFO *, uchar *dst, size_t dstlen,
588 uint nweights, const uchar *src, size_t srclen,
589 uint flags);
590
591size_t my_strnxfrm_unicode(const CHARSET_INFO *, uchar *dst, size_t dstlen,
592 uint nweights, const uchar *src, size_t srclen,
593 uint flags);
594
596 size_t dstlen, uint nweights,
597 const uchar *src, size_t srclen,
598 uint flags);
599size_t my_strnxfrmlen_unicode_full_bin(const CHARSET_INFO *, size_t);
600
601int my_wildcmp_unicode(const CHARSET_INFO *cs, const char *str,
602 const char *str_end, const char *wildstr,
603 const char *wildend, int escape, int w_one, int w_many,
604 const MY_UNICASE_INFO *weights);
605
606extern bool my_parse_charset_xml(MY_CHARSET_LOADER *loader, const char *buf,
607 size_t buflen);
608extern size_t my_strcspn(const CHARSET_INFO *cs, const char *str,
609 const char *end, const char *reject,
610 size_t reject_length);
611
612bool my_propagate_simple(const CHARSET_INFO *cs, const uchar *str, size_t len);
613bool my_propagate_complex(const CHARSET_INFO *cs, const uchar *str, size_t len);
614
615uint my_string_repertoire(const CHARSET_INFO *cs, const char *str, size_t len);
619
621size_t my_strxfrm_pad(const CHARSET_INFO *cs, uchar *str, uchar *frmend,
622 uchar *strend, uint nweights, uint flags);
623
625
626size_t my_convert(char *to, size_t to_length, const CHARSET_INFO *to_cs,
627 const char *from, size_t from_length,
628 const CHARSET_INFO *from_cs, uint *errors);
629
630uint my_mbcharlen_ptr(const CHARSET_INFO *cs, const char *s, const char *e);
632bool my_is_prefixidx_cand(const CHARSET_INFO *cs, const char *wildstr,
633 const char *wildend, int escape, int w_many,
634 size_t *prefix_len);
636#define _MY_U 01 /* Upper case */
637#define _MY_L 02 /* Lower case */
638#define _MY_NMR 04 /* Numeral (digit) */
639#define _MY_SPC 010 /* Spacing character */
640#define _MY_PNT 020 /* Punctuation */
641#define _MY_CTR 040 /* Control character */
642#define _MY_B 0100 /* Blank */
643#define _MY_X 0200 /* heXadecimal digit */
644
645/* The following macros makes sense only for one-byte character sets.
646They will not fail for multibyte character sets, but will not produce
647the expected results. They may have some limited usability like
648e.g. for utf8mb3/utf8mb4, meaningful results will be produced for
649values < 0x7F. */
650#define my_isascii(c) (!((c) & ~0177))
651#define my_toupper(s, c) (char)((s)->to_upper[(uchar)(c)])
652#define my_tolower(s, c) (char)((s)->to_lower[(uchar)(c)])
653#define my_isalpha(s, c) (((s)->ctype + 1)[(uchar)(c)] & (_MY_U | _MY_L))
654#define my_isupper(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_U)
655#define my_islower(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_L)
656#define my_isdigit(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_NMR)
657#define my_isxdigit(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_X)
658#define my_isalnum(s, c) \
659 (((s)->ctype + 1)[(uchar)(c)] & (_MY_U | _MY_L | _MY_NMR))
660#define my_isspace(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_SPC)
661#define my_ispunct(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_PNT)
662#define my_isprint(s, c) \
663 (((s)->ctype + 1)[(uchar)(c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR | _MY_B))
664#define my_isgraph(s, c) \
665 (((s)->ctype + 1)[(uchar)(c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR))
666#define my_iscntrl(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_CTR)
668/* Some macros that should be cleaned up a little */
669#define my_isvar(s, c) (my_isalnum(s, c) || (c) == '_')
670#define my_isvar_start(s, c) (my_isalpha(s, c) || (c) == '_')
672#define my_binary_compare(s) ((s)->state & MY_CS_BINSORT)
673#define use_strnxfrm(s) ((s)->state & MY_CS_STRNXFRM)
674#define my_strnxfrm(cs, d, dl, s, sl) \
675 ((cs)->coll->strnxfrm((cs), (d), (dl), (dl), (s), (sl), 0))
676#define my_strnncoll(s, a, b, c, d) \
677 ((s)->coll->strnncoll((s), (a), (b), (c), (d), 0))
678#define my_like_range(s, a, b, c, d, e, f, g, h, i, j) \
679 ((s)->coll->like_range((s), (a), (b), (c), (d), (e), (f), (g), (h), (i), (j)))
680#define my_wildcmp(cs, s, se, w, we, e, o, m) \
681 ((cs)->coll->wildcmp((cs), (s), (se), (w), (we), (e), (o), (m)))
682#define my_strcasecmp(s, a, b) ((s)->coll->strcasecmp((s), (a), (b)))
683#define my_charpos(cs, b, e, num) \
684 (cs)->cset->charpos((cs), (const char *)(b), (const char *)(e), (num))
685
686#define use_mb(s) ((s)->cset->ismbchar != NULL)
687static inline uint my_ismbchar(const CHARSET_INFO *cs, const char *str,
688 const char *strend) {
689 return cs->cset->ismbchar(cs, str, strend);
690}
691
692static inline uint my_ismbchar(const CHARSET_INFO *cs, const uchar *str,
693 const uchar *strend) {
694 return cs->cset->ismbchar(cs, pointer_cast<const char *>(str),
695 pointer_cast<const char *>(strend));
696}
697
698#define my_mbcharlen(s, a) ((s)->cset->mbcharlen((s), (a)))
699/**
700 Get the length of gb18030 code by the given two leading bytes
701
702 @param[in] s charset_info
703 @param[in] a first byte of gb18030 code
704 @param[in] b second byte of gb18030 code
705 @return the length of gb18030 code starting with given two bytes,
706 the length would be 2 or 4 for valid gb18030 code,
707 or 0 for invalid gb18030 code
708*/
709#define my_mbcharlen_2(s, a, b) \
710 ((s)->cset->mbcharlen((s), ((((a)&0xFF) << 8) + ((b)&0xFF))))
711/**
712 Get the maximum length of leading bytes needed to determine the length of a
713 multi-byte gb18030 code
715 @param[in] s charset_info
716 @return number of leading bytes we need, would be 2 for gb18030
717 and 1 for all other charsets
718*/
719#define my_mbmaxlenlen(s) ((s)->mbmaxlenlen)
720/**
721 Judge if the given byte is a possible leading byte for a charset.
722 For gb18030 whose mbmaxlenlen is 2, we can't determine the length of
723 a multi-byte character by looking at the first byte only
725 @param[in] s charset_info
726 @param[in] i possible leading byte
727 @return true if it is, otherwise false
729#define my_ismb1st(s, i) \
730 (my_mbcharlen((s), (i)) > 1 || \
731 (my_mbmaxlenlen((s)) == 2 && my_mbcharlen((s), (i)) == 0))
733#define my_caseup_str(s, a) ((s)->cset->caseup_str((s), (a)))
734#define my_casedn_str(s, a) ((s)->cset->casedn_str((s), (a)))
735#define my_strntol(s, a, b, c, d, e) \
736 ((s)->cset->strntol((s), (a), (b), (c), (d), (e)))
737#define my_strntoul(s, a, b, c, d, e) \
738 ((s)->cset->strntoul((s), (a), (b), (c), (d), (e)))
739#define my_strntoll(s, a, b, c, d, e) \
740 ((s)->cset->strntoll((s), (a), (b), (c), (d), (e)))
741#define my_strntoull(s, a, b, c, d, e) \
742 ((s)->cset->strntoull((s), (a), (b), (c), (d), (e)))
743#define my_strntod(s, a, b, c, d) ((s)->cset->strntod((s), (a), (b), (c), (d)))
744
745static inline bool is_supported_parser_charset(const CHARSET_INFO *cs) {
746 return (cs->mbminlen == 1);
747}
748
749#endif // M_CTYPE_INCLUDED
char * pos
Definition: do_ctype.cc:76
static int flags[50]
Definition: hp_test1.cc:39
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, uint *errors)
Convert a string between two character sets.
Definition: ctype.cc:941
size_t my_caseup_mb_varlen(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-mb.cc:185
int my_strcasecmp_8bit(const CHARSET_INFO *cs, const char *, const char *)
Definition: ctype-simple.cc:244
struct MY_UNICASE_INFO MY_UNICASE_INFO
size_t my_casedn_str_mb(const CHARSET_INFO *, char *)
Definition: ctype-mb.cc:60
size_t my_charpos_mb3(const CHARSET_INFO *, const char *b, const char *e, size_t pos)
Definition: ctype-mb.cc:330
static uint my_ismbchar(const CHARSET_INFO *cs, const char *str, const char *strend)
Definition: m_ctype.h:682
size_t my_well_formed_len_mb(const CHARSET_INFO *, const char *b, const char *e, size_t pos, int *error)
Definition: ctype-mb.cc:342
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8_general_ci
Definition: ctype-utf8.cc:5781
double my_strntod_8bit(const CHARSET_INFO *, const char *s, size_t l, const char **e, int *err)
Definition: ctype-simple.cc:645
MY_COLLATION_HANDLER my_collation_ucs2_uca_handler
Definition: ctype-uca.cc:5187
CHARSET_INFO my_charset_latin1_bin
Definition: ctype-latin1.cc:670
size_t my_numchars_8bit(const CHARSET_INFO *, const char *b, const char *e)
Definition: ctype-simple.cc:911
MY_UNICASE_INFO my_unicase_unicode520
Definition: ctype-utf8.cc:4786
size_t my_snprintf_8bit(const CHARSET_INFO *, char *to, size_t n, const char *fmt,...)
Definition: ctype-simple.cc:280
size_t my_strnxfrmlen_simple(const CHARSET_INFO *, size_t)
Definition: ctype-simple.cc:63
struct MY_COLLATION_HANDLER MY_COLLATION_HANDLER
size_t my_strnxfrmlen_unicode_full_bin(const CHARSET_INFO *, size_t)
Definition: ctype-utf8.cc:5173
size_t my_caseup_str_8bit(const CHARSET_INFO *, char *)
Definition: ctype-simple.cc:210
MY_COLLATION_HANDLER my_collation_mb_bin_handler
Definition: ctype-mb.cc:1336
int my_strnncoll_mb_bin(const CHARSET_INFO *cs, const uchar *s, size_t slen, const uchar *t, size_t tlen, bool t_is_prefix)
Definition: ctype-mb.cc:409
ulonglong my_strntoull10rnd_8bit(const CHARSET_INFO *cs, const char *str, size_t length, int unsigned_fl, const char **endptr, int *error)
Definition: ctype-simple.cc:1234
int(* my_charset_conv_wc_mb)(const CHARSET_INFO *, my_wc_t, uchar *, uchar *)
Definition: m_ctype.h:264
size_t my_well_formed_len_8bit(const CHARSET_INFO *, const char *b, const char *e, size_t pos, int *error)
Definition: ctype-simple.cc:927
MY_CHARSET_HANDLER my_charset_ascii_handler
Definition: ctype-simple.cc:1555
static bool is_supported_parser_charset(const CHARSET_INFO *cs)
Definition: m_ctype.h:740
MY_UNICASE_INFO my_unicase_turkish
Definition: ctype-utf8.cc:1878
ulong my_strntoul_8bit(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: ctype-simple.cc:396
struct MY_CHARSET_LOADER MY_CHARSET_LOADER
int my_mb_wc_8bit(const CHARSET_INFO *cs, my_wc_t *wc, const uchar *s, const uchar *e)
Definition: ctype-simple.cc:251
bool my_like_range_simple(const CHARSET_INFO *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)
Definition: ctype-simple.cc:841
size_t my_caseup_mb(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-mb.cc:87
void my_fill_8bit(const CHARSET_INFO *cs, char *to, size_t l, int fill)
Definition: ctype-simple.cc:906
size_t my_casedn_mb(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-mb.cc:114
MY_COLLATION_HANDLER my_collation_8bit_simple_ci_handler
Definition: ctype-simple.cc:1584
CHARSET_INFO my_charset_utf8_tolower_ci
Definition: ctype-utf8.cc:5816
uint my_mbcharlen_8bit(const CHARSET_INFO *, uint c)
Definition: ctype-bin.cc:226
uint my_mbcharlen_ptr(const CHARSET_INFO *cs, const char *s, const char *e)
Get the length of the first code in given sequence of chars.
Definition: ctype.cc:999
MY_COLLATION_HANDLER my_collation_8bit_bin_handler
Definition: ctype-bin.cc:453
MYSQL_PLUGIN_IMPORT CHARSET_INFO * system_charset_info
Definition: mysqld.cc:1525
MY_UNICASE_INFO my_unicase_mysql500
Definition: ctype-utf8.cc:1704
CHARSET_INFO my_charset_utf8_unicode_ci
Definition: ctype-uca.cc:6085
size_t my_casedn_8bit(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-simple.cc:234
size_t my_caseup_str_mb(const CHARSET_INFO *, char *)
Definition: ctype-mb.cc:43
size_t my_longlong10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l, int radix, longlong val)
Definition: ctype-simple.cc:694
struct MY_CHARSET_HANDLER MY_CHARSET_HANDLER
uint my_strxfrm_flag_normalize(uint flags)
Definition: ctype-simple.cc:1506
int my_mb_ctype_8bit(const CHARSET_INFO *, int *, const uchar *, const uchar *)
Definition: ctype-simple.cc:1143
size_t my_caseup_8bit(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-simple.cc:224
size_t my_numchars_mb(const CHARSET_INFO *, const char *b, const char *e)
Definition: ctype-mb.cc:319
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8mb4_general_ci
Definition: ctype-utf8.cc:7761
size_t my_strxfrm_pad(const CHARSET_INFO *cs, uchar *str, uchar *frmend, uchar *strend, uint nweights, uint flags)
Definition: ctype-simple.cc:1511
bool my_charset_is_ascii_compatible(const CHARSET_INFO *cs)
Definition: ctype.cc:855
uint my_string_repertoire(const CHARSET_INFO *cs, const char *str, size_t len)
Definition: ctype.cc:775
int my_strnncoll_simple(const CHARSET_INFO *, const uchar *, size_t, const uchar *, size_t, bool)
Definition: ctype-simple.cc:136
ulonglong my_strntoull10rnd_ucs2(const CHARSET_INFO *cs, const char *str, size_t length, int unsigned_fl, char **endptr, int *error)
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_filename
Definition: ctype-utf8.cc:7043
int my_mb_ctype_mb(const CHARSET_INFO *, int *, const uchar *, const uchar *)
Definition: ctype-mb.cc:1323
long my_strntol_8bit(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: ctype-simple.cc:317
size_t my_lengthsp_8bit(const CHARSET_INFO *cs, const char *ptr, size_t length)
Definition: ctype-simple.cc:935
size_t(* my_charset_conv_case)(const CHARSET_INFO *, char *, size_t, char *, size_t)
Definition: m_ctype.h:266
bool my_charset_is_8bit_pure_ascii(const CHARSET_INFO *cs)
Definition: ctype.cc:841
int my_wildcmp_bin(const CHARSET_INFO *, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many)
Definition: ctype-bin.cc:369
uint my_instr_mb(const CHARSET_INFO *, const char *b, size_t b_length, const char *s, size_t s_length, my_match_t *match, uint nmatch)
Definition: ctype-mb.cc:361
int my_wildcmp_mb(const CHARSET_INFO *, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many)
Definition: ctype-mb.cc:312
struct MY_UNI_IDX MY_UNI_IDX
size_t my_casedn_mb_varlen(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-mb.cc:178
int my_wildcmp_8bit(const CHARSET_INFO *, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many)
Definition: ctype-simple.cc:817
MY_UNICASE_INFO my_unicase_default
Definition: ctype-utf8.cc:1658
CHARSET_INFO my_charset_utf8mb4_bin
Definition: ctype-utf8.cc:7797
struct MY_UNICASE_CHARACTER MY_UNICASE_CHARACTER
MY_CHARSET_HANDLER my_charset_8bit_handler
Definition: ctype-simple.cc:1527
void my_hash_sort_simple(const CHARSET_INFO *cs, const uchar *key, size_t len, uint64 *nr1, uint64 *nr2)
Definition: ctype-simple.cc:290
int my_strnncollsp_mb_bin(const CHARSET_INFO *cs, const uchar *a, size_t a_length, const uchar *b, size_t b_length)
Definition: ctype-mb.cc:439
int my_wildcmp_unicode(const CHARSET_INFO *cs, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many, const MY_UNICASE_INFO *weights)
Definition: ctype-utf8.cc:4929
bool my_is_prefixidx_cand(const CHARSET_INFO *cs, const char *wildstr, const char *wildend, int escape, int w_many, size_t *prefix_len)
Identify whether given like pattern looks like a prefix pattern, which can become candidate for index...
Definition: ctype.cc:1026
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8mb4_0900_bin
Definition: ctype-uca.cc:11436
longlong my_strtoll10_8bit(const CHARSET_INFO *cs, const char *nptr, const char **endptr, int *error)
Definition: ctype-simple.cc:1138
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8mb4_0900_ai_ci
Definition: ctype-uca.cc:9564
static void MY_PUT_MB2(unsigned char *s, uint16 code)
Definition: m_ctype.h:62
struct MY_UNI_CTYPE MY_UNI_CTYPE
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_bin
Definition: ctype-bin.cc:510
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_latin1
Definition: ctype-latin1.cc:367
ulong my_wc_t
Our own version of wchar_t, ie., a type that holds a single Unicode code point ("wide character").
Definition: m_ctype.h:58
int my_strcasecmp_mb_bin(const CHARSET_INFO *cs, const char *s, const char *t)
Definition: ctype-mb.cc:560
size_t my_numcells_8bit(const CHARSET_INFO *, const char *b, const char *e)
Definition: ctype-simple.cc:916
size_t my_long10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l, int radix, long int val)
Definition: ctype-simple.cc:658
uint my_charset_repertoire(const CHARSET_INFO *cs)
Definition: ctype.cc:797
ulonglong my_strntoull_8bit(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: ctype-simple.cc:548
bool my_like_range_generic(const CHARSET_INFO *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)
Calculate min_str and max_str that ranges a LIKE string.
Definition: ctype-mb.cc:808
MY_UNI_CTYPE my_uni_ctype[256]
Definition: my_uctype.h:934
int my_wc_mb_8bit(const CHARSET_INFO *cs, my_wc_t wc, uchar *s, uchar *e)
Definition: ctype-simple.cc:259
size_t my_charpos_8bit(const CHARSET_INFO *, const char *b, const char *e, size_t pos)
Definition: ctype-simple.cc:921
void my_hash_sort_mb_bin(const CHARSET_INFO *cs, const uchar *key, size_t len, uint64 *nr1, uint64 *nr2)
Definition: ctype-mb.cc:565
int my_strcasecmp_mb(const CHARSET_INFO *cs, const char *, const char *)
Definition: ctype-mb.cc:196
size_t my_casedn_str_8bit(const CHARSET_INFO *, char *)
Definition: ctype-simple.cc:217
size_t my_strnxfrm_mb(const CHARSET_INFO *, uchar *dst, size_t dstlen, uint nweights, const uchar *src, size_t srclen, uint flags)
Definition: ctype-mb.cc:501
int(* my_charset_conv_mb_wc)(const CHARSET_INFO *, my_wc_t *, const uchar *, const uchar *)
Definition: m_ctype.h:262
size_t my_strnxfrm_unicode_full_bin(const CHARSET_INFO *, uchar *dst, size_t dstlen, uint nweights, const uchar *src, size_t srclen, uint flags)
Definition: ctype-utf8.cc:5128
bool my_parse_charset_xml(MY_CHARSET_LOADER *loader, const char *buf, size_t buflen)
Definition: ctype.cc:745
CHARSET_INFO my_charset_utf32_unicode_ci
Definition: ctype-uca.cc:7790
bool my_like_range_mb(const CHARSET_INFO *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)
Definition: ctype-mb.cc:660
int(* my_string_stack_guard)(int)
Definition: ctype.cc:64
MY_CHARSET_HANDLER my_charset_ucs2_handler
Definition: ctype-ucs2.cc:2859
bool my_charset_is_ascii_based(const CHARSET_INFO *cs)
Definition: ctype.cc:828
size_t my_strcspn(const CHARSET_INFO *cs, const char *str, const char *end, const char *reject, size_t reject_length)
Calculate the length of the initial segment of 'str' which consists entirely of characters not in 're...
Definition: my_strchr.cc:64
uint my_instr_simple(const CHARSET_INFO *, const char *b, size_t b_length, const char *s, size_t s_length, my_match_t *match, uint nmatch)
Definition: ctype-simple.cc:942
size_t my_scan_8bit(const CHARSET_INFO *cs, const char *b, const char *e, int sq)
Definition: ctype-simple.cc:884
longlong my_strtoll10_ucs2(const CHARSET_INFO *cs, const char *nptr, char **endptr, int *error)
bool my_propagate_complex(const CHARSET_INFO *cs, const uchar *str, size_t len)
Definition: ctype-simple.cc:1489
int my_wildcmp_mb_bin(const CHARSET_INFO *cs, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many)
Definition: ctype-mb.cc:1041
size_t my_strnxfrm_simple(const CHARSET_INFO *, uchar *dst, size_t dstlen, uint nweights, const uchar *src, size_t srclen, uint flags)
Definition: ctype-simple.cc:106
CHARSET_INFO my_charset_utf8_bin
Definition: ctype-utf8.cc:5886
longlong my_strntoll_8bit(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: ctype-simple.cc:469
size_t my_casedn_ujis(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-ujis.cc:35761
size_t my_numcells_mb(const CHARSET_INFO *, const char *b, const char *e)
Definition: ctype-mb.cc:1291
size_t my_strnxfrm_unicode(const CHARSET_INFO *, uchar *dst, size_t dstlen, uint nweights, const uchar *src, size_t srclen, uint flags)
Definition: ctype-utf8.cc:5107
Pad_attribute
Definition: m_ctype.h:167
@ NO_PAD
Definition: m_ctype.h:167
@ PAD_SPACE
Definition: m_ctype.h:167
bool my_propagate_simple(const CHARSET_INFO *cs, const uchar *str, size_t len)
Definition: ctype-simple.cc:1483
size_t my_caseup_ujis(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-ujis.cc:35771
int my_strnncollsp_simple(const CHARSET_INFO *, const uchar *, size_t, const uchar *, size_t)
Definition: ctype-simple.cc:178
static const char * strend(const char *s)
Definition: m_string.h:91
Header for compiler-dependent features.
Some integer typedefs for easier portability.
unsigned long long int ulonglong
Definition: my_inttypes.h:55
unsigned char uchar
Definition: my_inttypes.h:51
long long int longlong
Definition: my_inttypes.h:54
uint64_t uint64
Definition: my_inttypes.h:68
uint16_t uint16
Definition: my_inttypes.h:64
uint32_t uint32
Definition: my_inttypes.h:66
Definition of the global "loglevel" enumeration.
loglevel
Definition: my_loglevel.h:40
Some common macros.
Functions related to handling of plugins and other dynamically loaded libraries.
#define MYSQL_PLUGIN_IMPORT
Definition: my_sharedlib.h:70
Log error(cerr, "ERROR")
std::string str(const mysqlrouter::ConfigGenerator::Options::Endpoint &ep)
Definition: config_generator.cc:1055
Definition: buf0block_hint.cc:29
Definition: commit_order_queue.h:33
static std::string escape(const std::string &str)
Escapes (only) apostrophes.
Definition: st_units_of_measure.cc:36
bool length(const dd::Spatial_reference_system *srs, const Geometry *g1, double *length, bool *null) noexcept
Computes the length of linestrings and multilinestrings.
Definition: length.cc:75
static Value err()
Create a Value object that represents an error condition.
Definition: json_binary.cc:909
Cursor end()
A past-the-end Cursor.
Definition: rules_table_service.cc:191
required string key
Definition: replication_asynchronous_connection_failover.proto:59
Definition: m_ctype.h:354
const uchar * to_lower
Definition: m_ctype.h:365
uchar levels_for_compare
Definition: m_ctype.h:384
const uchar * ident_map
Definition: m_ctype.h:373
uint mbmaxlenlen
Definition: m_ctype.h:379
const struct lex_state_maps_st * state_maps
Definition: m_ctype.h:372
const uchar * ctype
Definition: m_ctype.h:364
uint primary_number
Definition: m_ctype.h:356
const char * csname
Definition: m_ctype.h:359
my_wc_t max_sort_char
Definition: m_ctype.h:381
const MY_UNICASE_INFO * caseinfo
Definition: m_ctype.h:371
bool escape_with_backslash_is_dangerous
Definition: m_ctype.h:383
uint mbminlen
Definition: m_ctype.h:377
uint binary_number
Definition: m_ctype.h:357
uchar caseup_multiply
Definition: m_ctype.h:375
const uchar * sort_order
Definition: m_ctype.h:367
uint mbmaxlen
Definition: m_ctype.h:378
MY_COLLATION_HANDLER * coll
Definition: m_ctype.h:387
MY_CHARSET_HANDLER * cset
Definition: m_ctype.h:386
const char * m_coll_name
Definition: m_ctype.h:360
uint state
Definition: m_ctype.h:358
uchar casedn_multiply
Definition: m_ctype.h:376
const uchar * to_upper
Definition: m_ctype.h:366
const MY_UNI_IDX * tab_from_uni
Definition: m_ctype.h:370
struct Coll_param * coll_param
Definition: m_ctype.h:363
uint number
Definition: m_ctype.h:355
struct MY_UCA_INFO * uca
Definition: m_ctype.h:368
const uint16 * tab_to_uni
Definition: m_ctype.h:369
uchar pad_char
Definition: m_ctype.h:382
my_wc_t min_sort_char
Definition: m_ctype.h:380
enum Pad_attribute pad_attribute
If this collation is PAD_SPACE, it collates as if all inputs were padded with a given number of space...
Definition: m_ctype.h:396
const char * tailoring
Definition: m_ctype.h:362
const char * comment
Definition: m_ctype.h:361
uint strxfrm_multiply
Definition: m_ctype.h:374
Definition: str_uca_type.h:68
Definition: m_ctype.h:270
longlong(* strtoll10)(const CHARSET_INFO *cs, const char *nptr, const char **endptr, int *error)
Definition: m_ctype.h:341
size_t(* lengthsp)(const CHARSET_INFO *, const char *ptr, size_t length)
Given a pointer and a length in bytes, returns a new length in bytes where all trailing space charact...
Definition: m_ctype.h:302
double(* strntod)(const CHARSET_INFO *, const char *s, size_t l, const char **e, int *err)
Definition: m_ctype.h:339
size_t(* well_formed_len)(const CHARSET_INFO *, const char *b, const char *e, size_t nchars, int *error)
Definition: m_ctype.h:285
ulonglong(* strntoull10rnd)(const CHARSET_INFO *cs, const char *str, size_t length, int unsigned_fl, const char **endptr, int *error)
Definition: m_ctype.h:343
size_t(* caseup_str)(const CHARSET_INFO *, char *)
Definition: m_ctype.h:314
uint(* mbcharlen)(const CHARSET_INFO *, uint c)
Definition: m_ctype.h:274
long(* strntol)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:331
size_t(* charpos)(const CHARSET_INFO *, const char *b, const char *e, size_t pos)
Return at which byte codepoint number "pos" begins, relative to the start of the string.
Definition: m_ctype.h:283
ulonglong(* strntoull)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:337
ulong(* strntoul)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:333
longlong(* strntoll)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:335
size_t(* numchars)(const CHARSET_INFO *, const char *b, const char *e)
Definition: m_ctype.h:275
size_t(* numcells)(const CHARSET_INFO *, const char *b, const char *e)
Definition: m_ctype.h:303
int(* ctype)(const CHARSET_INFO *cs, int *ctype, const uchar *s, const uchar *e)
Definition: m_ctype.h:310
void(* fill)(const CHARSET_INFO *, char *to, size_t len, int fill)
Definition: m_ctype.h:328
my_charset_conv_wc_mb wc_mb
Definition: m_ctype.h:307
size_t(* scan)(const CHARSET_INFO *, const char *b, const char *e, int sq)
Definition: m_ctype.h:346
bool(* init)(CHARSET_INFO *, MY_CHARSET_LOADER *loader)
Definition: m_ctype.h:271
my_charset_conv_mb_wc mb_wc
Definition: m_ctype.h:306
my_charset_conv_case caseup
Definition: m_ctype.h:317
size_t(* longlong10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix, longlong val)
Definition: m_ctype.h:325
size_t(* casedn_str)(const CHARSET_INFO *, char *)
Definition: m_ctype.h:315
size_t(* long10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix, long int val)
Definition: m_ctype.h:323
my_charset_conv_case casedn
Definition: m_ctype.h:318
uint(* ismbchar)(const CHARSET_INFO *, const char *, const char *)
Definition: m_ctype.h:273
size_t(* snprintf)(const CHARSET_INFO *, char *to, size_t n, const char *fmt,...)
Definition: m_ctype.h:321
Definition: m_ctype.h:154
void(* mem_free)(void *)
Definition: m_ctype.h:160
char errarg[192]
Definition: m_ctype.h:156
void(* reporter)(enum loglevel, uint errcode,...)
Definition: m_ctype.h:161
uint errcode
Definition: m_ctype.h:155
int(* add_collation)(CHARSET_INFO *cs)
Definition: m_ctype.h:162
Definition: m_ctype.h:170
int(* strcasecmp)(const CHARSET_INFO *, const char *, const char *)
Definition: m_ctype.h:234
bool(* like_range)(const CHARSET_INFO *, const char *s, size_t s_length, char w_prefix, char w_one, char w_many, size_t res_length, char *min_str, char *max_str, size_t *min_len, size_t *max_len)
Definition: m_ctype.h:226
bool(* init)(CHARSET_INFO *, MY_CHARSET_LOADER *)
Definition: m_ctype.h:171
int(* wildcmp)(const CHARSET_INFO *, const char *str, const char *str_end, const char *wildstr, const char *wildend, int escape, int w_one, int w_many)
Definition: m_ctype.h:230
void(* uninit)(CHARSET_INFO *)
Definition: m_ctype.h:172
bool(* propagate)(const CHARSET_INFO *cs, const uchar *str, size_t len)
Definition: m_ctype.h:253
void(* hash_sort)(const CHARSET_INFO *cs, const uchar *key, size_t len, uint64 *nr1, uint64 *nr2)
Compute a sort hash for the given key.
Definition: m_ctype.h:251
int(* strnncoll)(const CHARSET_INFO *, const uchar *, size_t, const uchar *, size_t, bool)
Definition: m_ctype.h:174
int(* strnncollsp)(const CHARSET_INFO *, const uchar *, size_t, const uchar *, size_t)
Compare the two strings under the pad rules given by the collation.
Definition: m_ctype.h:185
uint(* strstr)(const CHARSET_INFO *, const char *b, size_t b_length, const char *s, size_t s_length, my_match_t *match, uint nmatch)
Definition: m_ctype.h:236
size_t(* strnxfrm)(const CHARSET_INFO *, uchar *dst, size_t dstlen, uint num_codepoints, const uchar *src, size_t srclen, uint flags)
Transform the string into a form such that memcmp() between transformed strings yields the correct co...
Definition: m_ctype.h:211
size_t(* strnxfrmlen)(const CHARSET_INFO *, size_t num_bytes)
Return the maximum number of output bytes needed for strnxfrm() to output all weights for any string ...
Definition: m_ctype.h:225
Definition: str_uca_type.h:119
Definition: m_ctype.h:67
uint32 sort
Definition: m_ctype.h:70
uint32 tolower
Definition: m_ctype.h:69
uint32 toupper
Definition: m_ctype.h:68
Definition: m_ctype.h:73
const MY_UNICASE_CHARACTER ** page
Definition: m_ctype.h:75
my_wc_t maxchar
Definition: m_ctype.h:74
Definition: m_ctype.h:85
uchar * ctype
Definition: m_ctype.h:87
uchar pctype
Definition: m_ctype.h:86
Definition: m_ctype.h:136
const uchar * tab
Definition: m_ctype.h:139
uint16 from
Definition: m_ctype.h:137
uint16 to
Definition: m_ctype.h:138
Definition: sql_chars.h:89
Definition: m_ctype.h:142
unsigned int uint
Definition: uca-dump.cc:29
int n
Definition: xcom_base.cc:505