123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807 |
- /* Copyright (c) 2000, 2016, Oracle and/or its affiliates. All rights reserved.
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; version 2 of the License.
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */
- /*
- A better inplementation of the UNIX ctype(3) library.
- */
- #ifndef _m_ctype_h
- #define _m_ctype_h
- #include "my_global.h" /* uint16, uchar */
- #ifdef __cplusplus
- extern "C" {
- #endif
- #define MY_CS_NAME_SIZE 32
- #define MY_CS_CTYPE_TABLE_SIZE 257
- #define MY_CS_TO_LOWER_TABLE_SIZE 256
- #define MY_CS_TO_UPPER_TABLE_SIZE 256
- #define MY_CS_SORT_ORDER_TABLE_SIZE 256
- #define MY_CS_TO_UNI_TABLE_SIZE 256
- #define CHARSET_DIR "charsets/"
- #define my_wc_t ulong
- #define MY_CS_REPLACEMENT_CHARACTER 0xFFFD
- /*
- On i386 we store Unicode->CS conversion tables for
- some character sets using Big-endian order,
- to copy two bytes at onces.
- This gives some performance improvement.
- */
- #ifdef __i386__
- #define MB2(x) (((x) >> 8) + (((x) & 0xFF) << 8))
- #define MY_PUT_MB2(s, code) { *((uint16*)(s))= (code); }
- #else
- #define MB2(x) (x)
- #define MY_PUT_MB2(s, code) { (s)[0]= code >> 8; (s)[1]= code & 0xFF; }
- #endif
- typedef struct unicase_info_char_st
- {
- uint32 toupper;
- uint32 tolower;
- uint32 sort;
- } MY_UNICASE_CHARACTER;
- typedef struct unicase_info_st
- {
- my_wc_t maxchar;
- const MY_UNICASE_CHARACTER **page;
- } MY_UNICASE_INFO;
- extern MY_UNICASE_INFO my_unicase_default;
- extern MY_UNICASE_INFO my_unicase_turkish;
- extern MY_UNICASE_INFO my_unicase_mysql500;
- extern MY_UNICASE_INFO my_unicase_unicode520;
- #define MY_UCA_MAX_CONTRACTION 6
- #define MY_UCA_MAX_WEIGHT_SIZE 8
- #define MY_UCA_WEIGHT_LEVELS 1
- typedef struct my_contraction_t
- {
- my_wc_t ch[MY_UCA_MAX_CONTRACTION]; /* Character sequence */
- uint16 weight[MY_UCA_MAX_WEIGHT_SIZE];/* Its weight string, 0-terminated */
- my_bool with_context;
- } MY_CONTRACTION;
- typedef struct my_contraction_list_t
- {
- size_t nitems; /* Number of items in the list */
- MY_CONTRACTION *item; /* List of contractions */
- char *flags; /* Character flags, e.g. "is contraction head") */
- } MY_CONTRACTIONS;
- my_bool my_uca_can_be_contraction_head(const MY_CONTRACTIONS *c, my_wc_t wc);
- my_bool my_uca_can_be_contraction_tail(const MY_CONTRACTIONS *c, my_wc_t wc);
- uint16 *my_uca_contraction2_weight(const MY_CONTRACTIONS *c,
- my_wc_t wc1, my_wc_t wc2);
- /* Collation weights on a single level (e.g. primary, secondary, tertiarty) */
- typedef struct my_uca_level_info_st
- {
- my_wc_t maxchar;
- uchar *lengths;
- uint16 **weights;
- MY_CONTRACTIONS contractions;
- } MY_UCA_WEIGHT_LEVEL;
- typedef struct uca_info_st
- {
- MY_UCA_WEIGHT_LEVEL level[MY_UCA_WEIGHT_LEVELS];
- /* Logical positions */
- my_wc_t first_non_ignorable;
- my_wc_t last_non_ignorable;
- my_wc_t first_primary_ignorable;
- my_wc_t last_primary_ignorable;
- my_wc_t first_secondary_ignorable;
- my_wc_t last_secondary_ignorable;
- my_wc_t first_tertiary_ignorable;
- my_wc_t last_tertiary_ignorable;
- my_wc_t first_trailing;
- my_wc_t last_trailing;
- my_wc_t first_variable;
- my_wc_t last_variable;
- } MY_UCA_INFO;
- extern MY_UCA_INFO my_uca_v400;
- typedef struct uni_ctype_st
- {
- uchar pctype;
- uchar *ctype;
- } MY_UNI_CTYPE;
- extern MY_UNI_CTYPE my_uni_ctype[256];
- /* wm_wc and wc_mb return codes */
- #define MY_CS_ILSEQ 0 /* Wrong by sequence: wb_wc */
- #define MY_CS_ILUNI 0 /* Cannot encode Unicode to charset: wc_mb */
- #define MY_CS_TOOSMALL -101 /* Need at least one byte: wc_mb and mb_wc */
- #define MY_CS_TOOSMALL2 -102 /* Need at least two bytes: wc_mb and mb_wc */
- #define MY_CS_TOOSMALL3 -103 /* Need at least three bytes: wc_mb and mb_wc */
- /* These following three are currently not really used */
- #define MY_CS_TOOSMALL4 -104 /* Need at least 4 bytes: wc_mb and mb_wc */
- #define MY_CS_TOOSMALL5 -105 /* Need at least 5 bytes: wc_mb and mb_wc */
- #define MY_CS_TOOSMALL6 -106 /* Need at least 6 bytes: wc_mb and mb_wc */
- /* A helper macros for "need at least n bytes" */
- #define MY_CS_TOOSMALLN(n) (-100-(n))
- #define MY_SEQ_INTTAIL 1
- #define MY_SEQ_SPACES 2
- /* My charsets_list flags */
- #define MY_CS_COMPILED 1 /* compiled-in sets */
- #define MY_CS_CONFIG 2 /* sets that have a *.conf file */
- #define MY_CS_INDEX 4 /* sets listed in the Index file */
- #define MY_CS_LOADED 8 /* sets that are currently loaded */
- #define MY_CS_BINSORT 16 /* if binary sort order */
- #define MY_CS_PRIMARY 32 /* if primary collation */
- #define MY_CS_STRNXFRM 64 /* if strnxfrm is used for sort */
- #define MY_CS_UNICODE 128 /* is a charset is BMP Unicode */
- #define MY_CS_READY 256 /* if a charset is initialized */
- #define MY_CS_AVAILABLE 512 /* If either compiled-in or loaded*/
- #define MY_CS_CSSORT 1024 /* if case sensitive sort order */
- #define MY_CS_HIDDEN 2048 /* don't display in SHOW */
- #define MY_CS_PUREASCII 4096 /* if a charset is pure ascii */
- #define MY_CS_NONASCII 8192 /* if not ASCII-compatible */
- #define MY_CS_UNICODE_SUPPLEMENT 16384 /* Non-BMP Unicode characters */
- #define MY_CS_LOWER_SORT 32768 /* If use lower case as weight */
- #define MY_CHARSET_UNDEFINED 0
- /* Character repertoire flags */
- #define MY_REPERTOIRE_ASCII 1 /* Pure ASCII U+0000..U+007F */
- #define MY_REPERTOIRE_EXTENDED 2 /* Extended characters: U+0080..U+FFFF */
- #define MY_REPERTOIRE_UNICODE30 3 /* ASCII | EXTENDED: U+0000..U+FFFF */
- /* Flags for strxfrm */
- #define MY_STRXFRM_LEVEL1 0x00000001 /* for primary weights */
- #define MY_STRXFRM_LEVEL2 0x00000002 /* for secondary weights */
- #define MY_STRXFRM_LEVEL3 0x00000004 /* for tertiary weights */
- #define MY_STRXFRM_LEVEL4 0x00000008 /* fourth level weights */
- #define MY_STRXFRM_LEVEL5 0x00000010 /* fifth level weights */
- #define MY_STRXFRM_LEVEL6 0x00000020 /* sixth level weights */
- #define MY_STRXFRM_LEVEL_ALL 0x0000003F /* Bit OR for the above six */
- #define MY_STRXFRM_NLEVELS 6 /* Number of possible levels*/
- #define MY_STRXFRM_PAD_WITH_SPACE 0x00000040 /* if pad result with spaces */
- #define MY_STRXFRM_PAD_TO_MAXLEN 0x00000080 /* if pad tail(for filesort) */
- #define MY_STRXFRM_DESC_LEVEL1 0x00000100 /* if desc order for level1 */
- #define MY_STRXFRM_DESC_LEVEL2 0x00000200 /* if desc order for level2 */
- #define MY_STRXFRM_DESC_LEVEL3 0x00000300 /* if desc order for level3 */
- #define MY_STRXFRM_DESC_LEVEL4 0x00000800 /* if desc order for level4 */
- #define MY_STRXFRM_DESC_LEVEL5 0x00001000 /* if desc order for level5 */
- #define MY_STRXFRM_DESC_LEVEL6 0x00002000 /* if desc order for level6 */
- #define MY_STRXFRM_DESC_SHIFT 8
- #define MY_STRXFRM_UNUSED_00004000 0x00004000 /* for future extensions */
- #define MY_STRXFRM_UNUSED_00008000 0x00008000 /* for future extensions */
- #define MY_STRXFRM_REVERSE_LEVEL1 0x00010000 /* if reverse order for level1 */
- #define MY_STRXFRM_REVERSE_LEVEL2 0x00020000 /* if reverse order for level2 */
- #define MY_STRXFRM_REVERSE_LEVEL3 0x00040000 /* if reverse order for level3 */
- #define MY_STRXFRM_REVERSE_LEVEL4 0x00080000 /* if reverse order for level4 */
- #define MY_STRXFRM_REVERSE_LEVEL5 0x00100000 /* if reverse order for level5 */
- #define MY_STRXFRM_REVERSE_LEVEL6 0x00200000 /* if reverse order for level6 */
- #define MY_STRXFRM_REVERSE_SHIFT 16
- typedef struct my_uni_idx_st
- {
- uint16 from;
- uint16 to;
- const uchar *tab;
- } MY_UNI_IDX;
- typedef struct
- {
- uint beg;
- uint end;
- uint mb_len;
- } my_match_t;
- struct charset_info_st;
- typedef struct my_charset_loader_st
- {
- char error[128];
- void *(*once_alloc)(size_t);
- void *(*mem_malloc)(size_t);
- void *(*mem_realloc)(void *, size_t);
- void (*mem_free)(void *);
- void (*reporter)(enum loglevel, const char *format, ...);
- int (*add_collation)(struct charset_info_st *cs);
- } MY_CHARSET_LOADER;
- extern int (*my_string_stack_guard)(int);
- /* See strings/CHARSET_INFO.txt for information about this structure */
- typedef struct my_collation_handler_st
- {
- my_bool (*init)(struct charset_info_st *, MY_CHARSET_LOADER *);
- /* Collation routines */
- int (*strnncoll)(const struct charset_info_st *,
- const uchar *, size_t, const uchar *, size_t, my_bool);
- int (*strnncollsp)(const struct charset_info_st *,
- const uchar *, size_t, const uchar *, size_t,
- my_bool diff_if_only_endspace_difference);
- size_t (*strnxfrm)(const struct charset_info_st *,
- uchar *dst, size_t dstlen, uint nweights,
- const uchar *src, size_t srclen, uint flags);
- size_t (*strnxfrmlen)(const struct charset_info_st *, size_t);
- my_bool (*like_range)(const struct charset_info_st *,
- const char *s, size_t s_length,
- pchar w_prefix, pchar w_one, pchar w_many,
- size_t res_length,
- char *min_str, char *max_str,
- size_t *min_len, size_t *max_len);
- int (*wildcmp)(const struct charset_info_st *,
- const char *str,const char *str_end,
- const char *wildstr,const char *wildend,
- int escape,int w_one, int w_many);
- int (*strcasecmp)(const struct charset_info_st *, const char *,
- const char *);
-
- uint (*instr)(const struct charset_info_st *,
- const char *b, size_t b_length,
- const char *s, size_t s_length,
- my_match_t *match, uint nmatch);
-
- /* Hash calculation */
- void (*hash_sort)(const struct charset_info_st *cs, const uchar *key,
- size_t len, ulong *nr1, ulong *nr2);
- my_bool (*propagate)(const struct charset_info_st *cs, const uchar *str,
- size_t len);
- } MY_COLLATION_HANDLER;
- extern MY_COLLATION_HANDLER my_collation_mb_bin_handler;
- extern MY_COLLATION_HANDLER my_collation_8bit_bin_handler;
- extern MY_COLLATION_HANDLER my_collation_8bit_simple_ci_handler;
- extern MY_COLLATION_HANDLER my_collation_ucs2_uca_handler;
- /* Some typedef to make it easy for C++ to make function pointers */
- typedef int (*my_charset_conv_mb_wc)(const struct charset_info_st *,
- my_wc_t *, const uchar *, const uchar *);
- typedef int (*my_charset_conv_wc_mb)(const struct charset_info_st *, my_wc_t,
- uchar *, uchar *);
- typedef size_t (*my_charset_conv_case)(const struct charset_info_st *,
- char *, size_t, char *, size_t);
- /* See strings/CHARSET_INFO.txt about information on this structure */
- typedef struct my_charset_handler_st
- {
- my_bool (*init)(struct charset_info_st *, MY_CHARSET_LOADER *loader);
- /* Multibyte routines */
- uint (*ismbchar)(const struct charset_info_st *, const char *,
- const char *);
- uint (*mbcharlen)(const struct charset_info_st *, uint c);
- size_t (*numchars)(const struct charset_info_st *, const char *b,
- const char *e);
- size_t (*charpos)(const struct charset_info_st *, const char *b,
- const char *e, size_t pos);
- size_t (*well_formed_len)(const struct charset_info_st *,
- const char *b,const char *e,
- size_t nchars, int *error);
- size_t (*lengthsp)(const struct charset_info_st *, const char *ptr,
- size_t length);
- size_t (*numcells)(const struct charset_info_st *, const char *b,
- const char *e);
-
- /* Unicode conversion */
- my_charset_conv_mb_wc mb_wc;
- my_charset_conv_wc_mb wc_mb;
- /* CTYPE scanner */
- int (*ctype)(const struct charset_info_st *cs, int *ctype,
- const uchar *s, const uchar *e);
-
- /* Functions for case and sort conversion */
- size_t (*caseup_str)(const struct charset_info_st *, char *);
- size_t (*casedn_str)(const struct charset_info_st *, char *);
- my_charset_conv_case caseup;
- my_charset_conv_case casedn;
- /* Charset dependant snprintf() */
- size_t (*snprintf)(const struct charset_info_st *, char *to, size_t n,
- const char *fmt,
- ...) MY_ATTRIBUTE((format(printf, 4, 5)));
- size_t (*long10_to_str)(const struct charset_info_st *, char *to, size_t n,
- int radix, long int val);
- size_t (*longlong10_to_str)(const struct charset_info_st *, char *to,
- size_t n, int radix, longlong val);
-
- void (*fill)(const struct charset_info_st *, char *to, size_t len,
- int fill);
-
- /* String-to-number conversion routines */
- long (*strntol)(const struct charset_info_st *, const char *s,
- size_t l, int base, char **e, int *err);
- ulong (*strntoul)(const struct charset_info_st *, const char *s,
- size_t l, int base, char **e, int *err);
- longlong (*strntoll)(const struct charset_info_st *, const char *s,
- size_t l, int base, char **e, int *err);
- ulonglong (*strntoull)(const struct charset_info_st *, const char *s,
- size_t l, int base, char **e, int *err);
- double (*strntod)(const struct charset_info_st *, char *s,
- size_t l, char **e, int *err);
- longlong (*strtoll10)(const struct charset_info_st *cs,
- const char *nptr, char **endptr, int *error);
- ulonglong (*strntoull10rnd)(const struct charset_info_st *cs,
- const char *str, size_t length,
- int unsigned_fl,
- char **endptr, int *error);
- size_t (*scan)(const struct charset_info_st *, const char *b,
- const char *e, int sq);
- } MY_CHARSET_HANDLER;
- extern MY_CHARSET_HANDLER my_charset_8bit_handler;
- extern MY_CHARSET_HANDLER my_charset_ascii_handler;
- extern MY_CHARSET_HANDLER my_charset_ucs2_handler;
- /*
- We define this CHARSET_INFO_DEFINED here to prevent a repeat of the
- typedef in hash.c, which will cause a compiler error.
- */
- #define CHARSET_INFO_DEFINED
- /* See strings/CHARSET_INFO.txt about information on this structure */
- typedef struct charset_info_st
- {
- uint number;
- uint primary_number;
- uint binary_number;
- uint state;
- const char *csname;
- const char *name;
- const char *comment;
- const char *tailoring;
- const uchar *ctype;
- const uchar *to_lower;
- const uchar *to_upper;
- const uchar *sort_order;
- MY_UCA_INFO *uca; /* This can be changed in apply_one_rule() */
- const uint16 *tab_to_uni;
- const MY_UNI_IDX *tab_from_uni;
- const MY_UNICASE_INFO *caseinfo;
- const struct lex_state_maps_st *state_maps; /* parser internal data */
- const uchar *ident_map; /* parser internal data */
- uint strxfrm_multiply;
- uchar caseup_multiply;
- uchar casedn_multiply;
- uint mbminlen;
- uint mbmaxlen;
- uint mbmaxlenlen;
- my_wc_t min_sort_char;
- my_wc_t max_sort_char; /* For LIKE optimization */
- uchar pad_char;
- my_bool escape_with_backslash_is_dangerous;
- uchar levels_for_compare;
- uchar levels_for_order;
-
- MY_CHARSET_HANDLER *cset;
- MY_COLLATION_HANDLER *coll;
-
- } CHARSET_INFO;
- #define ILLEGAL_CHARSET_INFO_NUMBER (~0U)
- extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_bin;
- extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_latin1;
- extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_filename;
- extern CHARSET_INFO my_charset_big5_chinese_ci;
- extern CHARSET_INFO my_charset_big5_bin;
- extern CHARSET_INFO my_charset_cp932_japanese_ci;
- extern CHARSET_INFO my_charset_cp932_bin;
- extern CHARSET_INFO my_charset_cp1250_czech_ci;
- extern CHARSET_INFO my_charset_eucjpms_japanese_ci;
- extern CHARSET_INFO my_charset_eucjpms_bin;
- extern CHARSET_INFO my_charset_euckr_korean_ci;
- extern CHARSET_INFO my_charset_euckr_bin;
- extern CHARSET_INFO my_charset_gb2312_chinese_ci;
- extern CHARSET_INFO my_charset_gb2312_bin;
- extern CHARSET_INFO my_charset_gbk_chinese_ci;
- extern CHARSET_INFO my_charset_gbk_bin;
- extern CHARSET_INFO my_charset_gb18030_chinese_ci;
- extern CHARSET_INFO my_charset_gb18030_bin;
- extern CHARSET_INFO my_charset_latin1_german2_ci;
- extern CHARSET_INFO my_charset_latin1_bin;
- extern CHARSET_INFO my_charset_latin2_czech_ci;
- extern CHARSET_INFO my_charset_sjis_japanese_ci;
- extern CHARSET_INFO my_charset_sjis_bin;
- extern CHARSET_INFO my_charset_tis620_thai_ci;
- extern CHARSET_INFO my_charset_tis620_bin;
- extern CHARSET_INFO my_charset_ucs2_general_ci;
- extern CHARSET_INFO my_charset_ucs2_bin;
- extern CHARSET_INFO my_charset_ucs2_unicode_ci;
- extern CHARSET_INFO my_charset_ucs2_general_mysql500_ci;
- extern CHARSET_INFO my_charset_ujis_japanese_ci;
- extern CHARSET_INFO my_charset_ujis_bin;
- extern CHARSET_INFO my_charset_utf16_bin;
- extern CHARSET_INFO my_charset_utf16_general_ci;
- extern CHARSET_INFO my_charset_utf16_unicode_ci;
- extern CHARSET_INFO my_charset_utf16le_bin;
- extern CHARSET_INFO my_charset_utf16le_general_ci;
- extern CHARSET_INFO my_charset_utf32_bin;
- extern CHARSET_INFO my_charset_utf32_general_ci;
- extern CHARSET_INFO my_charset_utf32_unicode_ci;
- extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8_general_ci;
- extern CHARSET_INFO my_charset_utf8_tolower_ci;
- extern CHARSET_INFO my_charset_utf8_unicode_ci;
- extern CHARSET_INFO my_charset_utf8_bin;
- extern CHARSET_INFO my_charset_utf8_general_mysql500_ci;
- extern CHARSET_INFO my_charset_utf8mb4_bin;
- extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_utf8mb4_general_ci;
- extern CHARSET_INFO my_charset_utf8mb4_unicode_ci;
- #define MY_UTF8MB3 "utf8"
- #define MY_UTF8MB4 "utf8mb4"
- /* declarations for simple charsets */
- extern size_t my_strnxfrm_simple(const CHARSET_INFO *,
- uchar *dst, size_t dstlen, uint nweights,
- const uchar *src, size_t srclen, uint flags);
- size_t my_strnxfrmlen_simple(const CHARSET_INFO *, size_t);
- extern int my_strnncoll_simple(const CHARSET_INFO *, const uchar *, size_t,
- const uchar *, size_t, my_bool);
- extern int my_strnncollsp_simple(const CHARSET_INFO *, const uchar *, size_t,
- const uchar *, size_t,
- my_bool diff_if_only_endspace_difference);
- extern void my_hash_sort_simple(const CHARSET_INFO *cs,
- const uchar *key, size_t len,
- ulong *nr1, ulong *nr2);
- extern size_t my_lengthsp_8bit(const CHARSET_INFO *cs, const char *ptr,
- size_t length);
- extern uint my_instr_simple(const struct charset_info_st *,
- const char *b, size_t b_length,
- const char *s, size_t s_length,
- my_match_t *match, uint nmatch);
- /* Functions for 8bit */
- extern size_t my_caseup_str_8bit(const CHARSET_INFO *, char *);
- extern size_t my_casedn_str_8bit(const CHARSET_INFO *, char *);
- extern size_t my_caseup_8bit(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern size_t my_casedn_8bit(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern int my_strcasecmp_8bit(const CHARSET_INFO * cs, const char *,
- const char *);
- int my_mb_wc_8bit(const CHARSET_INFO *cs,my_wc_t *wc, const uchar *s,
- const uchar *e);
- int my_wc_mb_8bit(const CHARSET_INFO *cs,my_wc_t wc, uchar *s, uchar *e);
- int my_mb_ctype_8bit(const CHARSET_INFO *,int *, const uchar *,const uchar *);
- int my_mb_ctype_mb(const CHARSET_INFO *,int *, const uchar *,const uchar *);
- size_t my_scan_8bit(const CHARSET_INFO *cs, const char *b, const char *e,
- int sq);
- size_t my_snprintf_8bit(const struct charset_info_st *, char *to, size_t n,
- const char *fmt, ...)
- MY_ATTRIBUTE((format(printf, 4, 5)));
- long my_strntol_8bit(const CHARSET_INFO *, const char *s, size_t l,
- int base, char **e, int *err);
- ulong my_strntoul_8bit(const CHARSET_INFO *, const char *s, size_t l,
- int base, char **e, int *err);
- longlong my_strntoll_8bit(const CHARSET_INFO *, const char *s, size_t l,
- int base, char **e, int *err);
- ulonglong my_strntoull_8bit(const CHARSET_INFO *, const char *s, size_t l,
- int base, char **e, int *err);
- double my_strntod_8bit(const CHARSET_INFO *, char *s, size_t l, char **e,
- int *err);
- size_t my_long10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
- int radix, long int val);
- size_t my_longlong10_to_str_8bit(const CHARSET_INFO *, char *to, size_t l,
- int radix, longlong val);
- longlong my_strtoll10_8bit(const CHARSET_INFO *cs,
- const char *nptr, char **endptr, int *error);
- longlong my_strtoll10_ucs2(const CHARSET_INFO *cs,
- const char *nptr, char **endptr, int *error);
- ulonglong my_strntoull10rnd_8bit(const CHARSET_INFO *cs,
- const char *str, size_t length, int
- unsigned_fl, char **endptr, int *error);
- ulonglong my_strntoull10rnd_ucs2(const CHARSET_INFO *cs,
- const char *str, size_t length,
- int unsigned_fl, char **endptr, int *error);
- void my_fill_8bit(const CHARSET_INFO *cs, char* to, size_t l, int fill);
- /* For 8-bit character set */
- my_bool my_like_range_simple(const CHARSET_INFO *cs,
- const char *ptr, size_t ptr_length,
- pbool escape, pbool w_one, pbool w_many,
- size_t res_length,
- char *min_str, char *max_str,
- size_t *min_length, size_t *max_length);
- /* For ASCII-based multi-byte character sets with mbminlen=1 */
- my_bool my_like_range_mb(const CHARSET_INFO *cs,
- const char *ptr, size_t ptr_length,
- pbool escape, pbool w_one, pbool w_many,
- size_t res_length,
- char *min_str, char *max_str,
- size_t *min_length, size_t *max_length);
- /* For other character sets, with arbitrary mbminlen and mbmaxlen numbers */
- my_bool my_like_range_generic(const CHARSET_INFO *cs,
- const char *ptr, size_t ptr_length,
- pbool escape, pbool w_one, pbool w_many,
- size_t res_length,
- char *min_str, char *max_str,
- size_t *min_length, size_t *max_length);
- 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);
- 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);
- size_t my_numchars_8bit(const CHARSET_INFO *, const char *b, const char *e);
- size_t my_numcells_8bit(const CHARSET_INFO *, const char *b, const char *e);
- size_t my_charpos_8bit(const CHARSET_INFO *, const char *b, const char *e,
- size_t pos);
- size_t my_well_formed_len_8bit(const CHARSET_INFO *, const char *b,
- const char *e, size_t pos, int *error);
- uint my_mbcharlen_8bit(const CHARSET_INFO *, uint c);
- /* Functions for multibyte charsets */
- extern size_t my_caseup_str_mb(const CHARSET_INFO *, char *);
- extern size_t my_casedn_str_mb(const CHARSET_INFO *, char *);
- extern size_t my_caseup_mb(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern size_t my_casedn_mb(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern size_t my_caseup_mb_varlen(const CHARSET_INFO *, char *src,
- size_t srclen, char *dst, size_t dstlen);
- extern size_t my_casedn_mb_varlen(const CHARSET_INFO *, char *src,
- size_t srclen, char *dst, size_t dstlen);
- extern size_t my_caseup_ujis(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern size_t my_casedn_ujis(const CHARSET_INFO *, char *src, size_t srclen,
- char *dst, size_t dstlen);
- extern int my_strcasecmp_mb(const CHARSET_INFO * cs,const char *,
- const char *);
- 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);
- size_t my_numchars_mb(const CHARSET_INFO *, const char *b, const char *e);
- size_t my_numcells_mb(const CHARSET_INFO *, const char *b, const char *e);
- size_t my_charpos_mb(const CHARSET_INFO *, const char *b, const char *e,
- size_t pos);
- size_t my_well_formed_len_mb(const CHARSET_INFO *, const char *b,
- const char *e, size_t pos, int *error);
- uint my_instr_mb(const struct charset_info_st *,
- const char *b, size_t b_length,
- const char *s, size_t s_length,
- my_match_t *match, uint nmatch);
- int my_strnncoll_mb_bin(const CHARSET_INFO * cs,
- const uchar *s, size_t slen,
- const uchar *t, size_t tlen,
- my_bool t_is_prefix);
- int my_strnncollsp_mb_bin(const CHARSET_INFO *cs,
- const uchar *a, size_t a_length,
- const uchar *b, size_t b_length,
- my_bool diff_if_only_endspace_difference);
- 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);
- int my_strcasecmp_mb_bin(const CHARSET_INFO * cs MY_ATTRIBUTE((unused)),
- const char *s, const char *t);
- void my_hash_sort_mb_bin(const CHARSET_INFO *cs MY_ATTRIBUTE((unused)),
- const uchar *key, size_t len,ulong *nr1, ulong *nr2);
- size_t my_strnxfrm_mb(const CHARSET_INFO *,
- uchar *dst, size_t dstlen, uint nweights,
- const uchar *src, size_t srclen, uint flags);
- size_t my_strnxfrm_unicode(const CHARSET_INFO *,
- uchar *dst, size_t dstlen, uint nweights,
- const uchar *src, size_t srclen, uint flags);
- 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);
- size_t my_strnxfrmlen_unicode_full_bin(const CHARSET_INFO *, size_t);
- 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);
- extern my_bool my_parse_charset_xml(MY_CHARSET_LOADER *loader,
- const char *buf, size_t buflen);
- extern char *my_strchr(const CHARSET_INFO *cs, const char *str,
- const char *end, pchar c);
- extern size_t my_strcspn(const CHARSET_INFO *cs, const char *str,
- const char *end, const char *reject,
- size_t reject_length);
- my_bool my_propagate_simple(const CHARSET_INFO *cs, const uchar *str,
- size_t len);
- my_bool my_propagate_complex(const CHARSET_INFO *cs, const uchar *str,
- size_t len);
- uint my_string_repertoire(const CHARSET_INFO *cs, const char *str, size_t len);
- my_bool my_charset_is_ascii_based(const CHARSET_INFO *cs);
- my_bool my_charset_is_8bit_pure_ascii(const CHARSET_INFO *cs);
- uint my_charset_repertoire(const CHARSET_INFO *cs);
- uint my_strxfrm_flag_normalize(uint flags, uint nlevels);
- void my_strxfrm_desc_and_reverse(uchar *str, uchar *strend,
- uint flags, uint level);
- size_t my_strxfrm_pad_desc_and_reverse(const CHARSET_INFO *cs,
- uchar *str, uchar *frmend, uchar *strend,
- uint nweights, uint flags, uint level);
- my_bool my_charset_is_ascii_compatible(const CHARSET_INFO *cs);
- const MY_CONTRACTIONS *my_charset_get_contractions(const CHARSET_INFO *cs,
- int level);
- extern size_t my_vsnprintf_ex(const CHARSET_INFO *cs, char *to, size_t n,
- const char* fmt, va_list ap);
- 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);
- uint my_mbcharlen_ptr(const CHARSET_INFO *cs, const char *s, const char *e);
- #define _MY_U 01 /* Upper case */
- #define _MY_L 02 /* Lower case */
- #define _MY_NMR 04 /* Numeral (digit) */
- #define _MY_SPC 010 /* Spacing character */
- #define _MY_PNT 020 /* Punctuation */
- #define _MY_CTR 040 /* Control character */
- #define _MY_B 0100 /* Blank */
- #define _MY_X 0200 /* heXadecimal digit */
- #define my_isascii(c) (!((c) & ~0177))
- #define my_toascii(c) ((c) & 0177)
- #define my_tocntrl(c) ((c) & 31)
- #define my_toprint(c) ((c) | 64)
- #define my_toupper(s,c) (char) ((s)->to_upper[(uchar) (c)])
- #define my_tolower(s,c) (char) ((s)->to_lower[(uchar) (c)])
- #define my_isalpha(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_U | _MY_L))
- #define my_isupper(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_U)
- #define my_islower(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_L)
- #define my_isdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_NMR)
- #define my_isxdigit(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_X)
- #define my_isalnum(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_U | _MY_L | _MY_NMR))
- #define my_isspace(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_SPC)
- #define my_ispunct(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_PNT)
- #define my_isprint(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR | _MY_B))
- #define my_isgraph(s, c) (((s)->ctype+1)[(uchar) (c)] & (_MY_PNT | _MY_U | _MY_L | _MY_NMR))
- #define my_iscntrl(s, c) (((s)->ctype+1)[(uchar) (c)] & _MY_CTR)
- /* Some macros that should be cleaned up a little */
- #define my_isvar(s,c) (my_isalnum(s,c) || (c) == '_')
- #define my_isvar_start(s,c) (my_isalpha(s,c) || (c) == '_')
- #define my_binary_compare(s) ((s)->state & MY_CS_BINSORT)
- #define use_strnxfrm(s) ((s)->state & MY_CS_STRNXFRM)
- #define my_strnxfrm(cs, d, dl, s, sl) \
- ((cs)->coll->strnxfrm((cs), (d), (dl), (dl), (s), (sl), MY_STRXFRM_PAD_WITH_SPACE))
- #define my_strnncoll(s, a, b, c, d) ((s)->coll->strnncoll((s), (a), (b), (c), (d), 0))
- #define my_like_range(s, a, b, c, d, e, f, g, h, i, j) \
- ((s)->coll->like_range((s), (a), (b), (c), (d), (e), (f), (g), (h), (i), (j)))
- #define my_wildcmp(cs,s,se,w,we,e,o,m) ((cs)->coll->wildcmp((cs),(s),(se),(w),(we),(e),(o),(m)))
- #define my_strcasecmp(s, a, b) ((s)->coll->strcasecmp((s), (a), (b)))
- #define my_charpos(cs, b, e, num) (cs)->cset->charpos((cs), (const char*) (b), (const char *)(e), (num))
- #define use_mb(s) ((s)->cset->ismbchar != NULL)
- #define my_ismbchar(s, a, b) ((s)->cset->ismbchar((s), (a), (b)))
- #define my_mbcharlen(s, a) ((s)->cset->mbcharlen((s),(a)))
- /**
- Get the length of gb18030 code by the given two leading bytes
- @param[in] s charset_info
- @param[in] a first byte of gb18030 code
- @param[in] b second byte of gb18030 code
- @return the length of gb18030 code starting with given two bytes,
- the length would be 2 or 4 for valid gb18030 code,
- or 0 for invalid gb18030 code
- */
- #define my_mbcharlen_2(s, a, b) ((s)->cset->mbcharlen((s),((((a) & 0xFF) << 8) + ((b) & 0xFF))))
- /**
- Get the maximum length of leading bytes needed to determine the length of a
- multi-byte gb18030 code
- @param[in] s charset_info
- @return number of leading bytes we need, would be 2 for gb18030
- and 1 for all other charsets
- */
- #define my_mbmaxlenlen(s) ((s)->mbmaxlenlen)
- /**
- Judge if the given byte is a possible leading byte for a charset.
- For gb18030 whose mbmaxlenlen is 2, we can't determine the length of
- a multi-byte character by looking at the first byte only
- @param[in] s charset_info
- @param[in] i possible leading byte
- @return true if it is, otherwise false
- */
- #define my_ismb1st(s, i) \
- (my_mbcharlen((s), (i)) > 1 || \
- (my_mbmaxlenlen((s)) == 2 && my_mbcharlen((s), (i)) == 0))
- #define my_caseup_str(s, a) ((s)->cset->caseup_str((s), (a)))
- #define my_casedn_str(s, a) ((s)->cset->casedn_str((s), (a)))
- #define my_strntol(s, a, b, c, d, e) ((s)->cset->strntol((s),(a),(b),(c),(d),(e)))
- #define my_strntoul(s, a, b, c, d, e) ((s)->cset->strntoul((s),(a),(b),(c),(d),(e)))
- #define my_strntoll(s, a, b, c, d, e) ((s)->cset->strntoll((s),(a),(b),(c),(d),(e)))
- #define my_strntoull(s, a, b, c,d, e) ((s)->cset->strntoull((s),(a),(b),(c),(d),(e)))
- #define my_strntod(s, a, b, c, d) ((s)->cset->strntod((s),(a),(b),(c),(d)))
- #ifdef __cplusplus
- }
- #endif
- #endif /* _m_ctype_h */
|