MySQL 8.0.32
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#include <stddef.h>
32#include <sys/types.h>
33#include <cstdint>
34
35#include "my_compiler.h"
36#include "my_inttypes.h"
37#include "my_loglevel.h"
38#include "my_macros.h"
39#include "my_sharedlib.h"
40#include "template_utils.h"
41
42#define MY_CS_NAME_SIZE 32
43#define MY_CS_CTYPE_TABLE_SIZE 257
44#define MY_CS_TO_LOWER_TABLE_SIZE 256
45#define MY_CS_TO_UPPER_TABLE_SIZE 256
46#define MY_CS_SORT_ORDER_TABLE_SIZE 256
47#define MY_CS_TO_UNI_TABLE_SIZE 256
48
49#define CHARSET_DIR "charsets/"
50
51/**
52 Our own version of wchar_t, ie., a type that holds a single Unicode code point
53 ("wide character"). ulong is always big enough to hold any character
54 in the BMP.
55*/
56typedef ulong my_wc_t;
57
58#define MY_CS_REPLACEMENT_CHARACTER 0xFFFD
59
60static inline void MY_PUT_MB2(unsigned char *s, uint16 code) {
61 s[0] = code >> 8;
62 s[1] = code & 0xFF;
63}
64
65typedef struct MY_UNICASE_CHARACTER {
70
71typedef struct MY_UNICASE_INFO {
75
80
81struct MY_UCA_INFO;
82
83typedef struct MY_UNI_CTYPE {
87
88extern MY_UNI_CTYPE my_uni_ctype[256];
89
90/* wm_wc and wc_mb return codes */
91#define MY_CS_ILSEQ 0 /* Wrong by sequence: wb_wc */
92#define MY_CS_ILUNI 0 /* Cannot encode Unicode to charset: wc_mb */
93#define MY_CS_TOOSMALL -101 /* Need at least one byte: wc_mb and mb_wc */
94#define MY_CS_TOOSMALL2 -102 /* Need at least two bytes: wc_mb and mb_wc */
95#define MY_CS_TOOSMALL3 -103 /* Need at least three bytes: wc_mb and mb_wc */
96/* These following three are currently not really used */
97#define MY_CS_TOOSMALL4 -104 /* Need at least 4 bytes: wc_mb and mb_wc */
98#define MY_CS_TOOSMALL5 -105 /* Need at least 5 bytes: wc_mb and mb_wc */
99#define MY_CS_TOOSMALL6 -106 /* Need at least 6 bytes: wc_mb and mb_wc */
100/* A helper macros for "need at least n bytes" */
101#define MY_CS_TOOSMALLN(n) (-100 - (n))
102
103#define MY_SEQ_INTTAIL 1
104#define MY_SEQ_SPACES 2
105
106/* CHARSET_INFO::state flags */
107/* clang-format off */
108static constexpr uint32_t
109 MY_CHARSET_UNDEFINED = 0; // for unit testing
110static constexpr uint32_t
111 MY_CS_COMPILED = 1 << 0; // compiled-in charsets
112static constexpr uint32_t
113 MY_CS_CONFIG_UNUSED = 1 << 1; // unused bitmask
114static constexpr uint32_t
115 MY_CS_INDEX_UNUSED = 1 << 2; // unused bitmask
116static constexpr uint32_t
117 MY_CS_LOADED = 1 << 3; // charsets that are currently loaded
118static constexpr uint32_t
119 MY_CS_BINSORT = 1 << 4; // if binary sort order
120static constexpr uint32_t
121 MY_CS_PRIMARY = 1 << 5; // if primary collation
122static constexpr uint32_t
123 MY_CS_STRNXFRM = 1 << 6; // if _not_ set, sort_order will
124 // give same result as strnxfrm --
125 // all new collations should have
126 // this flag set,
127 // do not check it in new code
128static constexpr uint32_t
129 MY_CS_UNICODE = 1 << 7; // if a charset is BMP Unicode
130static constexpr uint32_t
131 MY_CS_READY = 1 << 8; // if a charset is initialized
132static constexpr uint32_t
133 MY_CS_AVAILABLE = 1 << 9; // if either compiled-in or loaded
134static constexpr uint32_t
135 MY_CS_CSSORT = 1 << 10; // if case sensitive sort order
136static constexpr uint32_t
137 MY_CS_HIDDEN = 1 << 11; // don't display in SHOW
138static constexpr uint32_t
139 MY_CS_PUREASCII = 1 << 12; // if a charset is pure ascii
140static constexpr uint32_t
141 MY_CS_NONASCII = 1 << 13; // if not ASCII-compatible
142static constexpr uint32_t
143 MY_CS_UNICODE_SUPPLEMENT = 1 << 14; // Non-BMP Unicode characters
144static constexpr uint32_t
145 MY_CS_LOWER_SORT = 1 << 15; // if use lower case as weight
146/* clang-format on */
147
148/* Character repertoire flags */
149#define MY_REPERTOIRE_ASCII 1 /* Pure ASCII U+0000..U+007F */
150#define MY_REPERTOIRE_EXTENDED 2 /* Extended characters: U+0080..U+FFFF */
151#define MY_REPERTOIRE_UNICODE30 3 /* ASCII | EXTENDED: U+0000..U+FFFF */
152
153/* Flags for strxfrm */
154#define MY_STRXFRM_PAD_TO_MAXLEN 0x00000080 /* if pad tail(for filesort) */
155
156typedef struct MY_UNI_IDX {
159 const uchar *tab;
161
162typedef struct {
166} my_match_t;
167
168struct CHARSET_INFO;
170
173 char errarg[192]{};
174
175 virtual ~MY_CHARSET_LOADER() = default;
176
177 // Memory management. By default we use mysys allocation functions.
178 virtual void *once_alloc(size_t);
179 virtual void *mem_malloc(size_t);
180 virtual void *mem_realloc(void *, size_t);
181 virtual void mem_free(void *);
182
183 // Error reporting. By default all warnings/errors are ignored.
184 // Set the global pointer my_charset_error_reporter to override this
185 // behaviour.
186 void reporter(enum loglevel, uint, const char *);
187 void reporter(enum loglevel, uint, int, const char *);
188
189 // Inserts a new charset/collation into the global all_charsets array.
190 virtual int add_collation(CHARSET_INFO *);
191};
192
193extern int (*my_string_stack_guard)(int);
194
196
197/* See strings/CHARSET_INFO.txt for information about this structure */
198typedef struct MY_COLLATION_HANDLER {
201 /* Collation routines */
202 int (*strnncoll)(const CHARSET_INFO *, const uchar *, size_t, const uchar *,
203 size_t, bool);
204 /**
205 Compare the two strings under the pad rules given by the collation.
206
207 Thus, for NO PAD collations, this is identical to strnncoll with is_prefix
208 set to false. For PAD SPACE collations, the two strings are conceptually
209 extended infinitely at the end using space characters (0x20) and then
210 compared under the collation's normal comparison rules, so that e.g 'a' is
211 equal to 'a '.
212 */
213 int (*strnncollsp)(const CHARSET_INFO *, const uchar *, size_t, const uchar *,
214 size_t);
215 /**
216 Transform the string into a form such that memcmp() between transformed
217 strings yields the correct collation order.
218
219 @param [out] dst Buffer for the transformed string.
220 @param [out] dstlen Number of bytes available in dstlen.
221 Must be even.
222 @param num_codepoints Treat the string as if it were of type
223 CHAR(num_codepoints). In particular, this means that if the
224 collation is a pad collation (pad_attribute is PAD_SPACE) and
225 string has fewer than "num_codepoints" codepoints, the string
226 will be transformed as if it ended in (num_codepoints-n) extra spaces.
227 If the string has more than "num_codepoints" codepoints,
228 behavior is undefined; may truncate, may crash, or do something
229 else entirely. Note that MY_STRXFRM_PAD_TO_MAXLEN overrides this;
230 if it is given for a PAD SPACE collation, this value is taken to be
231 effectively infinity.
232 @param src The source string, in the required character set
233 for the collation.
234 @param srclen Number of bytes in src.
235 @param flags ORed bitmask of MY_STRXFRM_* flags.
236
237 @return Number of bytes written to dst.
238 */
239 size_t (*strnxfrm)(const CHARSET_INFO *, uchar *dst, size_t dstlen,
240 uint num_codepoints, const uchar *src, size_t srclen,
241 uint flags);
242
243 /**
244 Return the maximum number of output bytes needed for strnxfrm()
245 to output all weights for any string of the given input length.
246 You can use this to e.g. size buffers for sort keys.
247
248 @param num_bytes Number of bytes in the input string. Note that for
249 multibyte character sets, this _must_ be a pessimistic estimate,
250 ie., one that's cs->mbmaxlen * max_num_codepoints. So for e.g.
251 the utf8mb4 string "foo", you will need to give in 12, not 3.
252 */
253 size_t (*strnxfrmlen)(const CHARSET_INFO *, size_t num_bytes);
254 bool (*like_range)(const CHARSET_INFO *, const char *s, size_t s_length,
255 char w_prefix, char w_one, char w_many, size_t res_length,
256 char *min_str, char *max_str, size_t *min_len,
257 size_t *max_len);
258 int (*wildcmp)(const CHARSET_INFO *, const char *str, const char *str_end,
259 const char *wildstr, const char *wildend, int escape,
260 int w_one, int w_many);
261
262 int (*strcasecmp)(const CHARSET_INFO *, const char *, const char *);
263
264 uint (*strstr)(const CHARSET_INFO *, const char *b, size_t b_length,
265 const char *s, size_t s_length, my_match_t *match,
266 uint nmatch);
267
268 /**
269 Compute a sort hash for the given key. This hash must preserve equality
270 under the given collation, so that a=b => H(a)=H(b). Note that this hash
271 is used for hash-based partitioning (PARTITION KEY), so you cannot change
272 it except when writing a new collation; it needs to be unchanged across
273 releases, so that the on-disk format does not change. (It is also used
274 for testing equality in the MEMORY storage engine.)
275
276 nr1 and nr2 are both in/out parameters. nr1 is the actual hash value;
277 nr2 holds extra state between invocations.
278 */
279 void (*hash_sort)(const CHARSET_INFO *cs, const uchar *key, size_t len,
280 uint64 *nr1, uint64 *nr2);
281 bool (*propagate)(const CHARSET_INFO *cs, const uchar *str, size_t len);
283
288
289/* Some typedef to make it easy for C++ to make function pointers */
291 const uchar *, const uchar *);
293 uchar *);
294typedef size_t (*my_charset_conv_case)(const CHARSET_INFO *, char *, size_t,
295 char *, size_t);
296
297/* See strings/CHARSET_INFO.txt about information on this structure */
298typedef struct MY_CHARSET_HANDLER {
300 /* Multibyte routines */
301 uint (*ismbchar)(const CHARSET_INFO *, const char *, const char *);
303 size_t (*numchars)(const CHARSET_INFO *, const char *b, const char *e);
304
305 /**
306 Return at which byte codepoint number "pos" begins, relative to
307 the start of the string. If the string is shorter than or is
308 exactly "pos" codepoints long, returns a value equal or greater to
309 (e-b).
310 */
311 size_t (*charpos)(const CHARSET_INFO *, const char *b, const char *e,
312 size_t pos);
313 size_t (*well_formed_len)(const CHARSET_INFO *, const char *b, const char *e,
314 size_t nchars, int *error);
315 /**
316 Given a pointer and a length in bytes, returns a new length in bytes where
317 all trailing space characters are stripped. This holds even for NO PAD
318 collations.
319
320 Exception: The "binary" collation, which is used behind-the-scenes to
321 implement the BINARY type (by mapping it to CHAR(n) COLLATE "binary"),
322 returns just the length back with no stripping. It's done that way so that
323 Field_string (implementing CHAR(n)) returns the full padded width on read
324 (as opposed to a normal CHAR, where we usually strip the spaces on read),
325 but it's suboptimal, since lengthsp() is also used in a number of other
326 places, e.g. stripping trailing spaces from enum values given in by the
327 user. If you call this function, be aware of this special exception and
328 consider the implications.
329 */
330 size_t (*lengthsp)(const CHARSET_INFO *, const char *ptr, size_t length);
331 size_t (*numcells)(const CHARSET_INFO *, const char *b, const char *e);
332
333 /* Unicode conversion */
336
337 /* CTYPE scanner */
338 int (*ctype)(const CHARSET_INFO *cs, int *ctype, const uchar *s,
339 const uchar *e);
340
341 /* Functions for case and sort conversion */
342 size_t (*caseup_str)(const CHARSET_INFO *, char *);
343 size_t (*casedn_str)(const CHARSET_INFO *, char *);
344
347
348 /* Charset dependent snprintf() */
349 size_t (*snprintf)(const CHARSET_INFO *, char *to, size_t n, const char *fmt,
350 ...) MY_ATTRIBUTE((format(printf, 4, 5)));
351 size_t (*long10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix,
352 long int val);
353 size_t (*longlong10_to_str)(const CHARSET_INFO *, char *to, size_t n,
354 int radix, longlong val);
355
356 void (*fill)(const CHARSET_INFO *, char *to, size_t len, int fill);
357
358 /* String-to-number conversion routines */
359 long (*strntol)(const CHARSET_INFO *, const char *s, size_t l, int base,
360 const char **e, int *err);
361 ulong (*strntoul)(const CHARSET_INFO *, const char *s, size_t l, int base,
362 const char **e, int *err);
363 longlong (*strntoll)(const CHARSET_INFO *, const char *s, size_t l, int base,
364 const char **e, int *err);
365 ulonglong (*strntoull)(const CHARSET_INFO *, const char *s, size_t l,
366 int base, const char **e, int *err);
367 double (*strntod)(const CHARSET_INFO *, const char *s, size_t l,
368 const char **e, int *err);
369 longlong (*strtoll10)(const CHARSET_INFO *cs, const char *nptr,
370 const char **endptr, int *error);
372 size_t length, int unsigned_fl,
373 const char **endptr, int *error);
374 size_t (*scan)(const CHARSET_INFO *, const char *b, const char *e, int sq);
376
380
381/* See strings/CHARSET_INFO.txt about information on this structure */
387 const char *csname;
388 const char *m_coll_name;
389 const char *comment;
390 const char *tailoring;
392 const uchar *ctype;
396 struct MY_UCA_INFO *uca; /* This can be changed in apply_one_rule() */
400 const struct lex_state_maps_st *state_maps; /* parser internal data */
401 const uchar *ident_map; /* parser internal data */
409 my_wc_t max_sort_char; /* For LIKE optimization */
413
416
417 /**
418 If this collation is PAD_SPACE, it collates as if all inputs were
419 padded with a given number of spaces at the end (see the "num_codepoints"
420 flag to strnxfrm). NO_PAD simply compares unextended strings.
421
422 Note that this is fundamentally about the behavior of coll->strnxfrm.
423 */
425};
426#define ILLEGAL_CHARSET_INFO_NUMBER (~0U)
427
428/*
429 NOTE: You cannot use a CHARSET_INFO without it having been initialized first.
430 In particular, they are not initialized when a unit test starts; do not use
431 these globals indiscriminately from there, and do not add more. Instead,
432 load them through a MY_CHARSET_LOADER, using my_collation_get_by_name().
433*/
434
440
449
450#define MY_UTF8MB4 "utf8mb4"
451
452/* declarations for simple charsets */
453extern size_t my_strnxfrm_simple(const CHARSET_INFO *, uchar *dst,
454 size_t dstlen, uint nweights, const uchar *src,
455 size_t srclen, uint flags);
456size_t my_strnxfrmlen_simple(const CHARSET_INFO *, size_t);
457extern int my_strnncoll_simple(const CHARSET_INFO *, const uchar *, size_t,
458 const uchar *, size_t, bool);
459
460extern int my_strnncollsp_simple(const CHARSET_INFO *, const uchar *, size_t,
461 const uchar *, size_t);
462
463extern void my_hash_sort_simple(const CHARSET_INFO *cs, const uchar *key,
464 size_t len, uint64 *nr1, uint64 *nr2);
465
466extern size_t my_lengthsp_8bit(const CHARSET_INFO *cs, const char *ptr,
467 size_t length);
468
469extern uint my_instr_simple(const CHARSET_INFO *, const char *b,
470 size_t b_length, const char *s, size_t s_length,
471 my_match_t *match, uint nmatch);
472
473/* Functions for 8bit */
474extern size_t my_caseup_str_8bit(const CHARSET_INFO *, char *);
475extern size_t my_casedn_str_8bit(const CHARSET_INFO *, char *);
476extern size_t my_caseup_8bit(const CHARSET_INFO *, char *src, size_t srclen,
477 char *dst, size_t dstlen);
478extern size_t my_casedn_8bit(const CHARSET_INFO *, char *src, size_t srclen,
479 char *dst, size_t dstlen);
480
481extern int my_strcasecmp_8bit(const CHARSET_INFO *cs, const char *,
482 const char *);
483
484int my_mb_wc_8bit(const CHARSET_INFO *cs, my_wc_t *wc, const uchar *s,
485 const uchar *e);
486int my_wc_mb_8bit(const CHARSET_INFO *cs, my_wc_t wc, uchar *s, uchar *e);
487
488int my_mb_ctype_8bit(const CHARSET_INFO *, int *, const uchar *, const uchar *);
489int my_mb_ctype_mb(const CHARSET_INFO *, int *, const uchar *, const uchar *);
490
491size_t my_scan_8bit(const CHARSET_INFO *cs, const char *b, const char *e,
492 int sq);
493
494size_t my_snprintf_8bit(const CHARSET_INFO *, char *to, size_t n,
495 const char *fmt, ...)
496 MY_ATTRIBUTE((format(printf, 4, 5)));
497
498long my_strntol_8bit(const CHARSET_INFO *, const char *s, size_t l, int base,
499 const char **e, int *err);
500ulong my_strntoul_8bit(const CHARSET_INFO *, const char *s, size_t l, int base,
501 const char **e, int *err);
502longlong my_strntoll_8bit(const CHARSET_INFO *, const char *s, size_t l,
503 int base, const char **e, int *err);
504ulonglong my_strntoull_8bit(const CHARSET_INFO *, const char *s, size_t l,
505 int base, const char **e, int *err);
506double my_strntod_8bit(const CHARSET_INFO *, const char *s, size_t l,
507 const char **e, int *err);
508size_t my_long10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
509 int radix, long int val);
510size_t my_longlong10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
511 int radix, longlong val);
512
513longlong my_strtoll10_8bit(const CHARSET_INFO *cs, const char *nptr,
514 const char **endptr, int *error);
515longlong my_strtoll10_ucs2(const CHARSET_INFO *cs, const char *nptr,
516 char **endptr, int *error);
517
519 size_t length, int unsigned_fl,
520 const char **endptr, int *error);
522 size_t length, int unsigned_fl, char **endptr,
523 int *error);
524
525void my_fill_8bit(const CHARSET_INFO *cs, char *to, size_t l, int fill);
526
527/* For 8-bit character set */
528bool my_like_range_simple(const CHARSET_INFO *cs, const char *ptr,
529 size_t ptr_length, char escape, char w_one,
530 char w_many, size_t res_length, char *min_str,
531 char *max_str, size_t *min_length,
532 size_t *max_length);
533
534/* For ASCII-based multi-byte character sets with mbminlen=1 */
535bool my_like_range_mb(const CHARSET_INFO *cs, const char *ptr,
536 size_t ptr_length, char escape, char w_one, char w_many,
537 size_t res_length, char *min_str, char *max_str,
538 size_t *min_length, size_t *max_length);
539
540/* For other character sets, with arbitrary mbminlen and mbmaxlen numbers */
541bool my_like_range_generic(const CHARSET_INFO *cs, const char *ptr,
542 size_t ptr_length, char escape, char w_one,
543 char w_many, size_t res_length, char *min_str,
544 char *max_str, size_t *min_length,
545 size_t *max_length);
546
547int my_wildcmp_8bit(const CHARSET_INFO *, const char *str, const char *str_end,
548 const char *wildstr, const char *wildend, int escape,
549 int w_one, int w_many);
550
551int my_wildcmp_bin(const CHARSET_INFO *, const char *str, const char *str_end,
552 const char *wildstr, const char *wildend, int escape,
553 int w_one, int w_many);
554
555size_t my_numchars_8bit(const CHARSET_INFO *, const char *b, const char *e);
556size_t my_numcells_8bit(const CHARSET_INFO *, const char *b, const char *e);
557size_t my_charpos_8bit(const CHARSET_INFO *, const char *b, const char *e,
558 size_t pos);
559size_t my_well_formed_len_8bit(const CHARSET_INFO *, const char *b,
560 const char *e, size_t pos, int *error);
562
563/* Functions for multibyte charsets */
564extern size_t my_caseup_str_mb(const CHARSET_INFO *, char *);
565extern size_t my_casedn_str_mb(const CHARSET_INFO *, char *);
566extern size_t my_caseup_mb(const CHARSET_INFO *, char *src, size_t srclen,
567 char *dst, size_t dstlen);
568extern size_t my_casedn_mb(const CHARSET_INFO *, char *src, size_t srclen,
569 char *dst, size_t dstlen);
570extern size_t my_caseup_mb_varlen(const CHARSET_INFO *, char *src,
571 size_t srclen, char *dst, size_t dstlen);
572extern size_t my_casedn_mb_varlen(const CHARSET_INFO *, char *src,
573 size_t srclen, char *dst, size_t dstlen);
574extern size_t my_caseup_ujis(const CHARSET_INFO *, char *src, size_t srclen,
575 char *dst, size_t dstlen);
576extern size_t my_casedn_ujis(const CHARSET_INFO *, char *src, size_t srclen,
577 char *dst, size_t dstlen);
578extern int my_strcasecmp_mb(const CHARSET_INFO *cs, const char *, const char *);
579
580int my_wildcmp_mb(const CHARSET_INFO *, const char *str, const char *str_end,
581 const char *wildstr, const char *wildend, int escape,
582 int w_one, int w_many);
583size_t my_numchars_mb(const CHARSET_INFO *, const char *b, const char *e);
584size_t my_numcells_mb(const CHARSET_INFO *, const char *b, const char *e);
585size_t my_charpos_mb3(const CHARSET_INFO *, const char *b, const char *e,
586 size_t pos);
587size_t my_well_formed_len_mb(const CHARSET_INFO *, const char *b, const char *e,
588 size_t pos, int *error);
589uint my_instr_mb(const CHARSET_INFO *, const char *b, size_t b_length,
590 const char *s, size_t s_length, my_match_t *match,
591 uint nmatch);
592
593int my_strnncoll_mb_bin(const CHARSET_INFO *cs, const uchar *s, size_t slen,
594 const uchar *t, size_t tlen, bool t_is_prefix);
595
596int my_strnncollsp_mb_bin(const CHARSET_INFO *cs, const uchar *a,
597 size_t a_length, const uchar *b, size_t b_length);
598
599int my_wildcmp_mb_bin(const CHARSET_INFO *cs, const char *str,
600 const char *str_end, const char *wildstr,
601 const char *wildend, int escape, int w_one, int w_many);
602
603int my_strcasecmp_mb_bin(const CHARSET_INFO *cs [[maybe_unused]], const char *s,
604 const char *t);
605
606void my_hash_sort_mb_bin(const CHARSET_INFO *cs [[maybe_unused]],
607 const uchar *key, size_t len, uint64 *nr1,
608 uint64 *nr2);
609
610size_t my_strnxfrm_mb(const CHARSET_INFO *, uchar *dst, size_t dstlen,
611 uint nweights, const uchar *src, size_t srclen,
612 uint flags);
613
614size_t my_strnxfrm_unicode(const CHARSET_INFO *, uchar *dst, size_t dstlen,
615 uint nweights, const uchar *src, size_t srclen,
616 uint flags);
617
619 size_t dstlen, uint nweights,
620 const uchar *src, size_t srclen,
621 uint flags);
622size_t my_strnxfrmlen_unicode_full_bin(const CHARSET_INFO *, size_t);
623
624int my_wildcmp_unicode(const CHARSET_INFO *cs, const char *str,
625 const char *str_end, const char *wildstr,
626 const char *wildend, int escape, int w_one, int w_many,
627 const MY_UNICASE_INFO *weights);
628
629extern bool my_parse_charset_xml(MY_CHARSET_LOADER *loader, const char *buf,
630 size_t buflen);
631extern size_t my_strcspn(const CHARSET_INFO *cs, const char *str,
632 const char *end, const char *reject,
633 size_t reject_length);
634
635bool my_propagate_simple(const CHARSET_INFO *cs, const uchar *str, size_t len);
636bool my_propagate_complex(const CHARSET_INFO *cs, const uchar *str, size_t len);
637
638uint my_string_repertoire(const CHARSET_INFO *cs, const char *str, size_t len);
639/**
640 Detect whether a character set is ASCII compatible.
641*/
642static inline bool my_charset_is_ascii_based(const CHARSET_INFO *cs) {
643 return (cs->state & MY_CS_NONASCII) ? false : true;
644}
645
648
650size_t my_strxfrm_pad(const CHARSET_INFO *cs, uchar *str, uchar *frmend,
651 uchar *strend, uint nweights, uint flags);
652
654
655size_t my_convert(char *to, size_t to_length, const CHARSET_INFO *to_cs,
656 const char *from, size_t from_length,
657 const CHARSET_INFO *from_cs, uint *errors);
658
659uint my_mbcharlen_ptr(const CHARSET_INFO *cs, const char *s, const char *e);
660
661bool my_is_prefixidx_cand(const CHARSET_INFO *cs, const char *wildstr,
662 const char *wildend, int escape, int w_many,
663 size_t *prefix_len);
664
665#define _MY_U 01 /* Upper case */
666#define _MY_L 02 /* Lower case */
667#define _MY_NMR 04 /* Numeral (digit) */
668#define _MY_SPC 010 /* Spacing character */
669#define _MY_PNT 020 /* Punctuation */
670#define _MY_CTR 040 /* Control character */
671#define _MY_B 0100 /* Blank */
672#define _MY_X 0200 /* heXadecimal digit */
673
674/* The following macros makes sense only for one-byte character sets.
675They will not fail for multibyte character sets, but will not produce
676the expected results. They may have some limited usability like
677e.g. for utf8mb3/utf8mb4, meaningful results will be produced for
678values < 0x7F. */
679#define my_isascii(c) (!((c) & ~0177))
680#define my_toupper(s, c) (char)((s)->to_upper[(uchar)(c)])
681#define my_tolower(s, c) (char)((s)->to_lower[(uchar)(c)])
682#define my_isalpha(s, c) (((s)->ctype + 1)[(uchar)(c)] & (_MY_U | _MY_L))
683#define my_isupper(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_U)
684#define my_islower(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_L)
685#define my_isdigit(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_NMR)
686#define my_isxdigit(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_X)
687#define my_isalnum(s, c) \
688 (((s)->ctype + 1)[(uchar)(c)] & (_MY_U | _MY_L | _MY_NMR))
689#define my_isspace(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_SPC)
690#define my_ispunct(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_PNT)
691#define my_isprint(s, c) \
692 (((s)->ctype + 1)[(uchar)(c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR | _MY_B))
693#define my_isgraph(s, c) \
694 (((s)->ctype + 1)[(uchar)(c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR))
695#define my_iscntrl(s, c) (((s)->ctype + 1)[(uchar)(c)] & _MY_CTR)
696
697/* Some macros that should be cleaned up a little */
698#define my_isvar(s, c) (my_isalnum(s, c) || (c) == '_')
699#define my_isvar_start(s, c) (my_isalpha(s, c) || (c) == '_')
700
701#define my_binary_compare(s) ((s)->state & MY_CS_BINSORT)
702#define use_strnxfrm(s) ((s)->state & MY_CS_STRNXFRM)
703#define my_strnxfrm(cs, d, dl, s, sl) \
704 ((cs)->coll->strnxfrm((cs), (d), (dl), (dl), (s), (sl), 0))
705#define my_strnncoll(s, a, b, c, d) \
706 ((s)->coll->strnncoll((s), (a), (b), (c), (d), 0))
707#define my_like_range(s, a, b, c, d, e, f, g, h, i, j) \
708 ((s)->coll->like_range((s), (a), (b), (c), (d), (e), (f), (g), (h), (i), (j)))
709#define my_wildcmp(cs, s, se, w, we, e, o, m) \
710 ((cs)->coll->wildcmp((cs), (s), (se), (w), (we), (e), (o), (m)))
711#define my_strcasecmp(s, a, b) ((s)->coll->strcasecmp((s), (a), (b)))
712#define my_charpos(cs, b, e, num) \
713 (cs)->cset->charpos((cs), (const char *)(b), (const char *)(e), (num))
714
715#define use_mb(s) ((s)->cset->ismbchar != NULL)
716static inline uint my_ismbchar(const CHARSET_INFO *cs, const char *str,
717 const char *strend) {
718 return cs->cset->ismbchar(cs, str, strend);
719}
720
721static inline uint my_ismbchar(const CHARSET_INFO *cs, const uchar *str,
722 const uchar *strend) {
723 return cs->cset->ismbchar(cs, pointer_cast<const char *>(str),
724 pointer_cast<const char *>(strend));
725}
726
727#define my_mbcharlen(s, a) ((s)->cset->mbcharlen((s), (a)))
728/**
729 Get the length of gb18030 code by the given two leading bytes
730
731 @param[in] s charset_info
732 @param[in] a first byte of gb18030 code
733 @param[in] b second byte of gb18030 code
734 @return the length of gb18030 code starting with given two bytes,
735 the length would be 2 or 4 for valid gb18030 code,
736 or 0 for invalid gb18030 code
737*/
738#define my_mbcharlen_2(s, a, b) \
739 ((s)->cset->mbcharlen((s), ((((a)&0xFF) << 8) + ((b)&0xFF))))
740/**
741 Get the maximum length of leading bytes needed to determine the length of a
742 multi-byte gb18030 code
743
744 @param[in] s charset_info
745 @return number of leading bytes we need, would be 2 for gb18030
746 and 1 for all other charsets
747*/
748#define my_mbmaxlenlen(s) ((s)->mbmaxlenlen)
749/**
750 Judge if the given byte is a possible leading byte for a charset.
751 For gb18030 whose mbmaxlenlen is 2, we can't determine the length of
752 a multi-byte character by looking at the first byte only
753
754 @param[in] s charset_info
755 @param[in] i possible leading byte
756 @return true if it is, otherwise false
757*/
758#define my_ismb1st(s, i) \
759 (my_mbcharlen((s), (i)) > 1 || \
760 (my_mbmaxlenlen((s)) == 2 && my_mbcharlen((s), (i)) == 0))
761
762#define my_caseup_str(s, a) ((s)->cset->caseup_str((s), (a)))
763#define my_casedn_str(s, a) ((s)->cset->casedn_str((s), (a)))
764#define my_strntol(s, a, b, c, d, e) \
765 ((s)->cset->strntol((s), (a), (b), (c), (d), (e)))
766#define my_strntoul(s, a, b, c, d, e) \
767 ((s)->cset->strntoul((s), (a), (b), (c), (d), (e)))
768#define my_strntoll(s, a, b, c, d, e) \
769 ((s)->cset->strntoll((s), (a), (b), (c), (d), (e)))
770#define my_strntoull(s, a, b, c, d, e) \
771 ((s)->cset->strntoull((s), (a), (b), (c), (d), (e)))
772#define my_strntod(s, a, b, c, d) ((s)->cset->strntod((s), (a), (b), (c), (d)))
773
774static inline bool is_supported_parser_charset(const CHARSET_INFO *cs) {
775 return (cs->mbminlen == 1);
776}
777
778#endif // M_CTYPE_INCLUDED
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:908
size_t my_caseup_mb_varlen(const CHARSET_INFO *, char *src, size_t srclen, char *dst, size_t dstlen)
Definition: ctype-mb.cc:185
static constexpr uint32_t MY_CS_PUREASCII
Definition: m_ctype.h:139
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:716
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
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:292
static constexpr uint32_t MY_CS_READY
Definition: m_ctype.h:131
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:774
static constexpr uint32_t MY_CS_NONASCII
Definition: m_ctype.h:141
MY_UNICASE_INFO my_unicase_turkish
Definition: ctype-utf8.cc:1878
static constexpr uint32_t MY_CS_STRNXFRM
Definition: m_ctype.h:123
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
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
CHARSET_INFO my_charset_utf8mb3_bin
Definition: ctype-utf8.cc:5886
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
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:966
MY_COLLATION_HANDLER my_collation_8bit_bin_handler
Definition: ctype-bin.cc:453
MYSQL_PLUGIN_IMPORT CHARSET_INFO * system_charset_info
Definition: mysqld.cc:1536
static constexpr uint32_t MY_CS_BINSORT
Definition: m_ctype.h:119
MY_UNICASE_INFO my_unicase_mysql500
Definition: ctype-utf8.cc:1704
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
static constexpr uint32_t MY_CS_LOWER_SORT
Definition: m_ctype.h:145
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
static bool my_charset_is_ascii_based(const CHARSET_INFO *cs)
Detect whether a character set is ASCII compatible.
Definition: m_ctype.h:642
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
static constexpr uint32_t MY_CS_UNICODE_SUPPLEMENT
Definition: m_ctype.h:143
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:822
uint my_string_repertoire(const CHARSET_INFO *cs, const char *str, size_t len)
Definition: ctype.cc:774
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:294
bool my_charset_is_8bit_pure_ascii(const CHARSET_INFO *cs)
Definition: ctype.cc:808
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
static constexpr uint32_t MY_CS_AVAILABLE
Definition: m_ctype.h:133
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
static constexpr uint32_t MY_CHARSET_UNDEFINED
Definition: m_ctype.h:109
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:993
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:60
static constexpr uint32_t MY_CS_UNICODE
Definition: m_ctype.h:129
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:56
static constexpr uint32_t MY_CS_HIDDEN
Definition: m_ctype.h:137
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:796
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
CHARSET_INFO my_charset_utf8mb3_tolower_ci
Definition: ctype-utf8.cc:5816
size_t my_charpos_8bit(const CHARSET_INFO *, const char *b, const char *e, size_t pos)
Definition: ctype-simple.cc:921
static constexpr uint32_t MY_CS_CONFIG_UNUSED
Definition: m_ctype.h:113
MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8mb3_general_ci
Definition: ctype-utf8.cc:5781
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
static constexpr uint32_t MY_CS_LOADED
Definition: m_ctype.h:117
static constexpr uint32_t MY_CS_INDEX_UNUSED
Definition: m_ctype.h:115
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:290
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:744
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
static constexpr uint32_t MY_CS_PRIMARY
Definition: m_ctype.h:121
static constexpr uint32_t MY_CS_COMPILED
Definition: m_ctype.h:111
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
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
CHARSET_INFO my_charset_utf8mb3_unicode_ci
Definition: ctype-uca.cc:6085
static constexpr uint32_t MY_CS_CSSORT
Definition: m_ctype.h:135
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:195
@ NO_PAD
Definition: m_ctype.h:195
@ PAD_SPACE
Definition: m_ctype.h:195
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:1063
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:382
const uchar * to_lower
Definition: m_ctype.h:393
uchar levels_for_compare
Definition: m_ctype.h:412
const uchar * ident_map
Definition: m_ctype.h:401
uint mbmaxlenlen
Definition: m_ctype.h:407
const struct lex_state_maps_st * state_maps
Definition: m_ctype.h:400
const uchar * ctype
Definition: m_ctype.h:392
uint primary_number
Definition: m_ctype.h:384
const char * csname
Definition: m_ctype.h:387
my_wc_t max_sort_char
Definition: m_ctype.h:409
const MY_UNICASE_INFO * caseinfo
Definition: m_ctype.h:399
bool escape_with_backslash_is_dangerous
Definition: m_ctype.h:411
uint mbminlen
Definition: m_ctype.h:405
uint binary_number
Definition: m_ctype.h:385
uchar caseup_multiply
Definition: m_ctype.h:403
const uchar * sort_order
Definition: m_ctype.h:395
uint mbmaxlen
Definition: m_ctype.h:406
MY_COLLATION_HANDLER * coll
Definition: m_ctype.h:415
MY_CHARSET_HANDLER * cset
Definition: m_ctype.h:414
const char * m_coll_name
Definition: m_ctype.h:388
uint state
Definition: m_ctype.h:386
uchar casedn_multiply
Definition: m_ctype.h:404
const uchar * to_upper
Definition: m_ctype.h:394
const MY_UNI_IDX * tab_from_uni
Definition: m_ctype.h:398
struct Coll_param * coll_param
Definition: m_ctype.h:391
uint number
Definition: m_ctype.h:383
struct MY_UCA_INFO * uca
Definition: m_ctype.h:396
const uint16 * tab_to_uni
Definition: m_ctype.h:397
uchar pad_char
Definition: m_ctype.h:410
my_wc_t min_sort_char
Definition: m_ctype.h:408
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:424
const char * tailoring
Definition: m_ctype.h:390
const char * comment
Definition: m_ctype.h:389
uint strxfrm_multiply
Definition: m_ctype.h:402
Definition: str_uca_type.h:68
Definition: m_ctype.h:298
longlong(* strtoll10)(const CHARSET_INFO *cs, const char *nptr, const char **endptr, int *error)
Definition: m_ctype.h:369
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:330
double(* strntod)(const CHARSET_INFO *, const char *s, size_t l, const char **e, int *err)
Definition: m_ctype.h:367
size_t(* well_formed_len)(const CHARSET_INFO *, const char *b, const char *e, size_t nchars, int *error)
Definition: m_ctype.h:313
ulonglong(* strntoull10rnd)(const CHARSET_INFO *cs, const char *str, size_t length, int unsigned_fl, const char **endptr, int *error)
Definition: m_ctype.h:371
size_t(* caseup_str)(const CHARSET_INFO *, char *)
Definition: m_ctype.h:342
uint(* mbcharlen)(const CHARSET_INFO *, uint c)
Definition: m_ctype.h:302
long(* strntol)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:359
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:311
ulonglong(* strntoull)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:365
ulong(* strntoul)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:361
longlong(* strntoll)(const CHARSET_INFO *, const char *s, size_t l, int base, const char **e, int *err)
Definition: m_ctype.h:363
size_t(* numchars)(const CHARSET_INFO *, const char *b, const char *e)
Definition: m_ctype.h:303
size_t(* numcells)(const CHARSET_INFO *, const char *b, const char *e)
Definition: m_ctype.h:331
int(* ctype)(const CHARSET_INFO *cs, int *ctype, const uchar *s, const uchar *e)
Definition: m_ctype.h:338
void(* fill)(const CHARSET_INFO *, char *to, size_t len, int fill)
Definition: m_ctype.h:356
my_charset_conv_wc_mb wc_mb
Definition: m_ctype.h:335
size_t(* scan)(const CHARSET_INFO *, const char *b, const char *e, int sq)
Definition: m_ctype.h:374
bool(* init)(CHARSET_INFO *, MY_CHARSET_LOADER *loader)
Definition: m_ctype.h:299
my_charset_conv_mb_wc mb_wc
Definition: m_ctype.h:334
my_charset_conv_case caseup
Definition: m_ctype.h:345
size_t(* longlong10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix, longlong val)
Definition: m_ctype.h:353
size_t(* casedn_str)(const CHARSET_INFO *, char *)
Definition: m_ctype.h:343
size_t(* long10_to_str)(const CHARSET_INFO *, char *to, size_t n, int radix, long int val)
Definition: m_ctype.h:351
my_charset_conv_case casedn
Definition: m_ctype.h:346
uint(* ismbchar)(const CHARSET_INFO *, const char *, const char *)
Definition: m_ctype.h:301
size_t(* snprintf)(const CHARSET_INFO *, char *to, size_t n, const char *fmt,...)
Definition: m_ctype.h:349
Definition: m_ctype.h:171
void reporter(enum loglevel, uint, const char *)
Definition: charset.cc:349
virtual void * mem_malloc(size_t)
Definition: charset.cc:339
virtual void * mem_realloc(void *, size_t)
Definition: charset.cc:343
virtual void * once_alloc(size_t)
Definition: charset.cc:335
char errarg[192]
Definition: m_ctype.h:173
virtual void mem_free(void *)
Definition: charset.cc:347
virtual ~MY_CHARSET_LOADER()=default
uint errcode
Definition: m_ctype.h:172
virtual int add_collation(CHARSET_INFO *)
Definition: charset.cc:223
Definition: m_ctype.h:198
int(* strcasecmp)(const CHARSET_INFO *, const char *, const char *)
Definition: m_ctype.h:262
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:254
bool(* init)(CHARSET_INFO *, MY_CHARSET_LOADER *)
Definition: m_ctype.h:199
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:258
void(* uninit)(CHARSET_INFO *)
Definition: m_ctype.h:200
bool(* propagate)(const CHARSET_INFO *cs, const uchar *str, size_t len)
Definition: m_ctype.h:281
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:279
int(* strnncoll)(const CHARSET_INFO *, const uchar *, size_t, const uchar *, size_t, bool)
Definition: m_ctype.h:202
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:213
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:264
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:239
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:253
Definition: str_uca_type.h:119
Definition: m_ctype.h:65
uint32 sort
Definition: m_ctype.h:68
uint32 tolower
Definition: m_ctype.h:67
uint32 toupper
Definition: m_ctype.h:66
Definition: m_ctype.h:71
const MY_UNICASE_CHARACTER ** page
Definition: m_ctype.h:73
my_wc_t maxchar
Definition: m_ctype.h:72
Definition: m_ctype.h:83
uchar * ctype
Definition: m_ctype.h:85
uchar pctype
Definition: m_ctype.h:84
Definition: m_ctype.h:156
const uchar * tab
Definition: m_ctype.h:159
uint16 from
Definition: m_ctype.h:157
uint16 to
Definition: m_ctype.h:158
Definition: sql_chars.h:90
Definition: m_ctype.h:162
uint mb_len
Definition: m_ctype.h:165
uint end
Definition: m_ctype.h:164
uint beg
Definition: m_ctype.h:163
unsigned int uint
Definition: uca-dump.cc:29
int n
Definition: xcom_base.cc:508