diff options
30 files changed, 606 insertions, 109 deletions
diff --git a/client/sql_string.h b/client/sql_string.h index 242b31e7ed6..e284301b214 100644 --- a/client/sql_string.h +++ b/client/sql_string.h @@ -260,8 +260,6 @@ public: } bool fill(uint32 max_length,char fill); void strip_sp(); - inline void caseup() { my_caseup(str_charset,Ptr,str_length); } - inline void casedn() { my_casedn(str_charset,Ptr,str_length); } friend int sortcmp(const String *a,const String *b, CHARSET_INFO *cs); friend int stringcmp(const String *a,const String *b); friend String *copy_if_not_alloced(String *a,String *b,uint32 arg_length); diff --git a/extra/yassl/mySTL/memory.hpp b/extra/yassl/mySTL/memory.hpp index 729abae7ebc..cc70fbf60d8 100644 --- a/extra/yassl/mySTL/memory.hpp +++ b/extra/yassl/mySTL/memory.hpp @@ -37,16 +37,18 @@ namespace mySTL { -template<typename T, typename Deletor = void (*) (T*)> +template<typename T> struct auto_ptr_ref { + typedef void (*Deletor)(T*); T* ptr_; Deletor del_; auto_ptr_ref(T* p, Deletor d) : ptr_(p), del_(d) {} }; -template<typename T, typename Deletor = void (*) (T*)> +template<typename T> class auto_ptr { + typedef void (*Deletor)(T*); T* ptr_; Deletor del_; diff --git a/extra/yassl/src/handshake.cpp b/extra/yassl/src/handshake.cpp index e49d1ec76cc..45dfb6fa032 100644 --- a/extra/yassl/src/handshake.cpp +++ b/extra/yassl/src/handshake.cpp @@ -718,7 +718,7 @@ void processReply(SSL& ssl) mySTL::auto_ptr<input_buffer> buffered(ysDelete); for (;;) { - mySTL::auto_ptr<input_buffer> tmp = DoProcessReply(ssl, buffered); + mySTL::auto_ptr<input_buffer> tmp(DoProcessReply(ssl, buffered)); if (tmp.get()) // had only part of a record's data, call again buffered = tmp; else diff --git a/include/m_ctype.h b/include/m_ctype.h index 6f304f4ba43..8bb8e5c76df 100644 --- a/include/m_ctype.h +++ b/include/m_ctype.h @@ -44,6 +44,9 @@ typedef struct unicase_info_st uint16 sort; } MY_UNICASE_INFO; +extern MY_UNICASE_INFO *my_unicase_default[256]; +extern MY_UNICASE_INFO *my_unicase_turkish[256]; + #define MY_CS_ILSEQ 0 #define MY_CS_ILUNI 0 #define MY_CS_TOOSMALL -1 @@ -164,8 +167,10 @@ typedef struct my_charset_handler_st /* Functions for case and sort convertion */ void (*caseup_str)(struct charset_info_st *, char *); void (*casedn_str)(struct charset_info_st *, char *); - void (*caseup)(struct charset_info_st *, char *, uint); - void (*casedn)(struct charset_info_st *, char *, uint); + uint (*caseup)(struct charset_info_st *, char *src, uint srclen, + char *dst, uint dstlen); + uint (*casedn)(struct charset_info_st *, char *src, uint srclen, + char *dst, uint dstlen); /* Charset dependant snprintf() */ int (*snprintf)(struct charset_info_st *, char *to, uint n, const char *fmt, @@ -216,9 +221,12 @@ typedef struct charset_info_st uint16 **sort_order_big; uint16 *tab_to_uni; MY_UNI_IDX *tab_from_uni; + MY_UNICASE_INFO **caseinfo; uchar *state_map; uchar *ident_map; uint strxfrm_multiply; + uchar caseup_multiply; + uchar casedn_multiply; uint mbminlen; uint mbmaxlen; uint16 min_sort_char; @@ -286,8 +294,10 @@ extern uint my_instr_simple(struct charset_info_st *, /* Functions for 8bit */ extern void my_caseup_str_8bit(CHARSET_INFO *, char *); extern void my_casedn_str_8bit(CHARSET_INFO *, char *); -extern void my_caseup_8bit(CHARSET_INFO *, char *, uint); -extern void my_casedn_8bit(CHARSET_INFO *, char *, uint); +extern uint my_caseup_8bit(CHARSET_INFO *, char *src, uint srclen, + char *dst, uint dstlen); +extern uint my_casedn_8bit(CHARSET_INFO *, char *src, uint srclen, + char *dst, uint dstlen); extern int my_strcasecmp_8bit(CHARSET_INFO * cs, const char *, const char *); @@ -359,8 +369,10 @@ int my_mbcharlen_8bit(CHARSET_INFO *, uint c); /* Functions for multibyte charsets */ extern void my_caseup_str_mb(CHARSET_INFO *, char *); extern void my_casedn_str_mb(CHARSET_INFO *, char *); -extern void my_caseup_mb(CHARSET_INFO *, char *, uint); -extern void my_casedn_mb(CHARSET_INFO *, char *, uint); +extern uint my_caseup_mb(CHARSET_INFO *, char *src, uint srclen, + char *dst, uint dstlen); +extern uint my_casedn_mb(CHARSET_INFO *, char *src, uint srclen, + char *dst, uint dstlen); extern int my_strcasecmp_mb(CHARSET_INFO * cs,const char *, const char *); int my_wildcmp_mb(CHARSET_INFO *, @@ -441,8 +453,6 @@ my_bool my_propagate_complex(CHARSET_INFO *cs, const uchar *str, uint len); #define my_mbcharlen(s, a) 1 #endif -#define my_caseup(s, a, l) ((s)->cset->caseup((s), (a), (l))) -#define my_casedn(s, a, l) ((s)->cset->casedn((s), (a), (l))) #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))) diff --git a/myisam/mi_test1.c b/myisam/mi_test1.c index aa6cd98ac8e..5727c699469 100644 --- a/myisam/mi_test1.c +++ b/myisam/mi_test1.c @@ -471,20 +471,25 @@ static void update_record(char *record) ptr=blob_key; memcpy_fixed(pos+4,&ptr,sizeof(char*)); /* Store pointer to new key */ if (keyinfo[0].seg[0].type != HA_KEYTYPE_NUM) - my_casedn(default_charset_info,blob_key,length); + default_charset_info->cset->casedn(default_charset_info, + blob_key, length, blob_key, length); pos+=recinfo[1].length; } else if (recinfo[1].type == FIELD_VARCHAR) { uint pack_length= HA_VARCHAR_PACKLENGTH(recinfo[1].length-1); uint length= pack_length == 1 ? (uint) *(uchar*) pos : uint2korr(pos); - my_casedn(default_charset_info,pos+pack_length,length); + default_charset_info->cset->casedn(default_charset_info, + pos + pack_length, length, + pos + pack_length, length); pos+=recinfo[1].length; } else { if (keyinfo[0].seg[0].type != HA_KEYTYPE_NUM) - my_casedn(default_charset_info,pos,keyinfo[0].seg[0].length); + default_charset_info->cset->casedn(default_charset_info, + pos, keyinfo[0].seg[0].length, + pos, keyinfo[0].seg[0].length); pos+=recinfo[1].length; } diff --git a/mysql-test/r/ctype_uca.result b/mysql-test/r/ctype_uca.result index c6e803904a3..3803dd932d7 100644 --- a/mysql-test/r/ctype_uca.result +++ b/mysql-test/r/ctype_uca.result @@ -2396,3 +2396,27 @@ utf8_unicode_ci 6109 utf8_unicode_ci 61 utf8_unicode_ci 6120 drop table t1; +CREATE TABLE t1 (id int, a varchar(30) character set utf8); +INSERT INTO t1 VALUES (1, _ucs2 0x01310069), (2, _ucs2 0x01310131); +INSERT INTO t1 VALUES (3, _ucs2 0x00690069), (4, _ucs2 0x01300049); +INSERT INTO t1 VALUES (5, _ucs2 0x01300130), (6, _ucs2 0x00490049); +SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu +FROM t1 ORDER BY id; +a la l ll u lu +ıi 3 ıi 3 II 2 +ıı 4 ıı 4 II 2 +ii 2 ii 2 II 2 +İI 3 ii 2 İI 3 +İİ 4 ii 2 İİ 4 +II 2 ii 2 II 2 +ALTER TABLE t1 MODIFY a VARCHAR(30) character set utf8 collate utf8_turkish_ci; +SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu +FROM t1 ORDER BY id; +a la l ll u lu +ıi 3 ıi 3 Iİ 3 +ıı 4 ıı 4 II 2 +ii 2 ii 2 İİ 4 +İI 3 iı 3 İI 3 +İİ 4 ii 2 İİ 4 +II 2 ıı 4 II 2 +DROP TABLE t1; diff --git a/mysql-test/t/ctype_uca.test b/mysql-test/t/ctype_uca.test index dfca82fa70a..e5c2acc8b4e 100644 --- a/mysql-test/t/ctype_uca.test +++ b/mysql-test/t/ctype_uca.test @@ -455,3 +455,18 @@ drop table t1; SET collation_connection='utf8_unicode_ci'; -- source include/ctype_filesort.inc + +# +# Check UPPER/LOWER changeing length +# +# Result shorter than argument +CREATE TABLE t1 (id int, a varchar(30) character set utf8); +INSERT INTO t1 VALUES (1, _ucs2 0x01310069), (2, _ucs2 0x01310131); +INSERT INTO t1 VALUES (3, _ucs2 0x00690069), (4, _ucs2 0x01300049); +INSERT INTO t1 VALUES (5, _ucs2 0x01300130), (6, _ucs2 0x00490049); +SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu +FROM t1 ORDER BY id; +ALTER TABLE t1 MODIFY a VARCHAR(30) character set utf8 collate utf8_turkish_ci; +SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu +FROM t1 ORDER BY id; +DROP TABLE t1; diff --git a/sql/item_strfunc.cc b/sql/item_strfunc.cc index 4808159fe98..c43f65c731c 100644 --- a/sql/item_strfunc.cc +++ b/sql/item_strfunc.cc @@ -902,7 +902,7 @@ void Item_func_insert::fix_length_and_dec() } -String *Item_func_lcase::val_str(String *str) +String *Item_str_conv::val_str(String *str) { DBUG_ASSERT(fixed == 1); String *res; @@ -912,24 +912,25 @@ String *Item_func_lcase::val_str(String *str) return 0; /* purecov: inspected */ } null_value=0; - res=copy_if_not_alloced(str,res,res->length()); - res->casedn(); - return res; -} - - -String *Item_func_ucase::val_str(String *str) -{ - DBUG_ASSERT(fixed == 1); - String *res; - if (!(res=args[0]->val_str(str))) + if (multiply == 1) { - null_value=1; /* purecov: inspected */ - return 0; /* purecov: inspected */ + uint len; + res= copy_if_not_alloced(str,res,res->length()); + len= converter(collation.collation, (char*) res->ptr(), res->length(), + (char*) res->ptr(), res->length()); + DBUG_ASSERT(len <= res->length()); + res->length(len); + } + else + { + uint len= res->length() * multiply; + tmp_value.alloc(len); + tmp_value.set_charset(collation.collation); + len= converter(collation.collation, (char*) res->ptr(), res->length(), + (char*) tmp_value.ptr(), len); + tmp_value.length(len); + res= &tmp_value; } - null_value=0; - res=copy_if_not_alloced(str,res,res->length()); - res->caseup(); return res; } diff --git a/sql/item_strfunc.h b/sql/item_strfunc.h index 95979408ccb..6df90cebdff 100644 --- a/sql/item_strfunc.h +++ b/sql/item_strfunc.h @@ -133,13 +133,14 @@ public: class Item_str_conv :public Item_str_func { +protected: + uint multiply; + uint (*converter)(CHARSET_INFO *cs, char *src, uint srclen, + char *dst, uint dstlen); + String tmp_value; public: Item_str_conv(Item *item) :Item_str_func(item) {} - void fix_length_and_dec() - { - collation.set(args[0]->collation); - max_length = args[0]->max_length; - } + String *val_str(String *); }; @@ -147,16 +148,28 @@ class Item_func_lcase :public Item_str_conv { public: Item_func_lcase(Item *item) :Item_str_conv(item) {} - String *val_str(String *); const char *func_name() const { return "lcase"; } + void fix_length_and_dec() + { + collation.set(args[0]->collation); + multiply= collation.collation->casedn_multiply; + converter= collation.collation->cset->casedn; + max_length= args[0]->max_length * multiply; + } }; class Item_func_ucase :public Item_str_conv { public: Item_func_ucase(Item *item) :Item_str_conv(item) {} - String *val_str(String *); const char *func_name() const { return "ucase"; } + void fix_length_and_dec() + { + collation.set(args[0]->collation); + multiply= collation.collation->caseup_multiply; + converter= collation.collation->cset->caseup; + max_length= args[0]->max_length * multiply; + } }; diff --git a/sql/mysql_priv.h b/sql/mysql_priv.h index a3dd19d5f1a..87d27a4bea2 100644 --- a/sql/mysql_priv.h +++ b/sql/mysql_priv.h @@ -1354,7 +1354,8 @@ inline void mark_as_null_row(TABLE *table) inline void table_case_convert(char * name, uint length) { if (lower_case_table_names) - my_casedn(files_charset_info, name, length); + files_charset_info->cset->casedn(files_charset_info, + name, length, name, length); } inline const char *table_case_name(HA_CREATE_INFO *info, const char *name) diff --git a/sql/sql_string.h b/sql/sql_string.h index c05305d9265..ddae6368228 100644 --- a/sql/sql_string.h +++ b/sql/sql_string.h @@ -261,8 +261,6 @@ public: } bool fill(uint32 max_length,char fill); void strip_sp(); - inline void caseup() { my_caseup(str_charset,Ptr,str_length); } - inline void casedn() { my_casedn(str_charset,Ptr,str_length); } friend int sortcmp(const String *a,const String *b, CHARSET_INFO *cs); friend int stringcmp(const String *a,const String *b); friend String *copy_if_not_alloced(String *a,String *b,uint32 arg_length); diff --git a/strings/ctype-big5.c b/strings/ctype-big5.c index 447eea3e635..a4040ed2b90 100644 --- a/strings/ctype-big5.c +++ b/strings/ctype-big5.c @@ -6384,9 +6384,12 @@ CHARSET_INFO my_charset_big5_chinese_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -6412,9 +6415,12 @@ CHARSET_INFO my_charset_big5_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-bin.c b/strings/ctype-bin.c index 56df289158a..13105df9334 100644 --- a/strings/ctype-bin.c +++ b/strings/ctype-bin.c @@ -208,10 +208,13 @@ static void my_case_str_bin(CHARSET_INFO *cs __attribute__((unused)), { } -static void my_case_bin(CHARSET_INFO *cs __attribute__((unused)), - char *str __attribute__((unused)), - uint length __attribute__((unused))) +static uint my_case_bin(CHARSET_INFO *cs __attribute__((unused)), + char *src __attribute__((unused)), + uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { + return srclen; } @@ -526,9 +529,12 @@ CHARSET_INFO my_charset_bin = NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-cp932.c b/strings/ctype-cp932.c index f2f31b1064e..fd2b0fd8e21 100644 --- a/strings/ctype-cp932.c +++ b/strings/ctype-cp932.c @@ -5512,9 +5512,12 @@ CHARSET_INFO my_charset_cp932_japanese_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -5539,9 +5542,12 @@ CHARSET_INFO my_charset_cp932_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-czech.c b/strings/ctype-czech.c index aaf87e97cb8..1361b728b26 100644 --- a/strings/ctype-czech.c +++ b/strings/ctype-czech.c @@ -618,9 +618,12 @@ CHARSET_INFO my_charset_latin2_czech_ci = NULL, /* sort_order_big*/ tab_8859_2_uni, /* tab_to_uni */ idx_uni_8859_2, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 4, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-euc_kr.c b/strings/ctype-euc_kr.c index 21b7b56fdaa..e2167aa315e 100644 --- a/strings/ctype-euc_kr.c +++ b/strings/ctype-euc_kr.c @@ -8696,9 +8696,12 @@ CHARSET_INFO my_charset_euckr_korean_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -8724,9 +8727,12 @@ CHARSET_INFO my_charset_euckr_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-eucjpms.c b/strings/ctype-eucjpms.c index d9171c800bf..784293918ed 100644 --- a/strings/ctype-eucjpms.c +++ b/strings/ctype-eucjpms.c @@ -8698,9 +8698,12 @@ CHARSET_INFO my_charset_eucjpms_japanese_ci= NULL, /* contractions */ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ @@ -8726,9 +8729,12 @@ CHARSET_INFO my_charset_eucjpms_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-extra.c b/strings/ctype-extra.c index 3672dcd0b33..2544245bc42 100644 --- a/strings/ctype-extra.c +++ b/strings/ctype-extra.c @@ -33,9 +33,12 @@ CHARSET_INFO compiled_charsets[] = { NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 0, /* strxfrm_mul */ + 0, /* caseup_mul */ + 0, /* casedn_mul */ 0, /* mbminlen */ 0, /* mbmaxlen */ 0, /* min_sort_ord */ diff --git a/strings/ctype-gb2312.c b/strings/ctype-gb2312.c index 592ee341781..6b582081085 100644 --- a/strings/ctype-gb2312.c +++ b/strings/ctype-gb2312.c @@ -5747,9 +5747,12 @@ CHARSET_INFO my_charset_gb2312_chinese_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -5774,9 +5777,12 @@ CHARSET_INFO my_charset_gb2312_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-gbk.c b/strings/ctype-gbk.c index ec96caa6b91..4150f198722 100644 --- a/strings/ctype-gbk.c +++ b/strings/ctype-gbk.c @@ -9994,9 +9994,12 @@ CHARSET_INFO my_charset_gbk_chinese_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -10021,9 +10024,12 @@ CHARSET_INFO my_charset_gbk_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-latin1.c b/strings/ctype-latin1.c index 7a75992dc4f..afe996d3cda 100644 --- a/strings/ctype-latin1.c +++ b/strings/ctype-latin1.c @@ -424,9 +424,12 @@ CHARSET_INFO my_charset_latin1= NULL, /* sort_order_big*/ cs_to_uni, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ @@ -719,9 +722,12 @@ CHARSET_INFO my_charset_latin1_german2_ci= NULL, /* sort_order_big*/ cs_to_uni, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 2, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ @@ -747,9 +753,12 @@ CHARSET_INFO my_charset_latin1_bin= NULL, /* sort_order_big*/ cs_to_uni, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-mb.c b/strings/ctype-mb.c index b3ec476b8f5..2d9f8b16bfc 100644 --- a/strings/ctype-mb.c +++ b/strings/ctype-mb.c @@ -57,40 +57,48 @@ void my_casedn_str_mb(CHARSET_INFO * cs, char *str) } } -void my_caseup_mb(CHARSET_INFO * cs, char *str, uint length) +uint my_caseup_mb(CHARSET_INFO * cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { register uint32 l; - register char *end=str+length; - register uchar *map=cs->to_upper; - - while (str<end) + register char *srcend= src + srclen; + register uchar *map= cs->to_upper; + + DBUG_ASSERT(src == dst && srclen == dstlen); + while (src < srcend) { - if ((l=my_ismbchar(cs, str,end))) - str+=l; + if ((l=my_ismbchar(cs, src, srcend))) + src+= l; else { - *str=(char) map[(uchar)*str]; - str++; + *src=(char) map[(uchar) *src]; + src++; } } + return srclen; } -void my_casedn_mb(CHARSET_INFO * cs, char *str, uint length) +uint my_casedn_mb(CHARSET_INFO * cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { register uint32 l; - register char *end=str+length; + register char *srcend= src + srclen; register uchar *map=cs->to_lower; - - while (str<end) + + DBUG_ASSERT(src == dst && srclen == dstlen); + while (src < srcend) { - if ((l=my_ismbchar(cs, str,end))) - str+=l; + if ((l= my_ismbchar(cs, src, srcend))) + src+= l; else { - *str=(char) map[(uchar)*str]; - str++; + *src= (char) map[(uchar)*src]; + src++; } } + return srclen; } int my_strcasecmp_mb(CHARSET_INFO * cs,const char *s, const char *t) diff --git a/strings/ctype-simple.c b/strings/ctype-simple.c index d19326d9265..6ed1af846ec 100644 --- a/strings/ctype-simple.c +++ b/strings/ctype-simple.c @@ -201,18 +201,28 @@ void my_casedn_str_8bit(CHARSET_INFO * cs,char *str) str++; } -void my_caseup_8bit(CHARSET_INFO * cs, char *str, uint length) +uint my_caseup_8bit(CHARSET_INFO * cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { - register uchar *map=cs->to_upper; - for ( ; length>0 ; length--, str++) - *str= (char) map[(uchar)*str]; + uint srclen0= srclen; + register uchar *map= cs->to_upper; + DBUG_ASSERT(src == dst && srclen == dstlen); + for ( ; srclen > 0 ; srclen--, src++) + *src= (char) map[(uchar) *src]; + return srclen0; } -void my_casedn_8bit(CHARSET_INFO * cs, char *str, uint length) +uint my_casedn_8bit(CHARSET_INFO * cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { + uint srclen0= srclen; register uchar *map=cs->to_lower; - for ( ; length>0 ; length--, str++) - *str= (char) map[(uchar) *str]; + DBUG_ASSERT(src == dst && srclen == dstlen); + for ( ; srclen > 0 ; srclen--, src++) + *src= (char) map[(uchar) *src]; + return srclen0; } int my_strcasecmp_8bit(CHARSET_INFO * cs,const char *s, const char *t) @@ -1303,6 +1313,8 @@ static my_bool create_fromuni(CHARSET_INFO *cs, void *(*alloc)(uint)) static my_bool my_cset_init_8bit(CHARSET_INFO *cs, void *(*alloc)(uint)) { + cs->caseup_multiply= 1; + cs->casedn_multiply= 1; return create_fromuni(cs, alloc); } diff --git a/strings/ctype-sjis.c b/strings/ctype-sjis.c index a7d75da42c9..9cd5d6d7981 100644 --- a/strings/ctype-sjis.c +++ b/strings/ctype-sjis.c @@ -4681,9 +4681,12 @@ CHARSET_INFO my_charset_sjis_japanese_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -4708,9 +4711,12 @@ CHARSET_INFO my_charset_sjis_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-tis620.c b/strings/ctype-tis620.c index c40e74c3343..4fe8bb4e349 100644 --- a/strings/ctype-tis620.c +++ b/strings/ctype-tis620.c @@ -983,9 +983,12 @@ CHARSET_INFO my_charset_tis620_thai_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 4, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ @@ -1010,9 +1013,12 @@ CHARSET_INFO my_charset_tis620_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-uca.c b/strings/ctype-uca.c index fb7e93e10b6..eb207c9821f 100644 --- a/strings/ctype-uca.c +++ b/strings/ctype-uca.c @@ -8049,9 +8049,12 @@ CHARSET_INFO my_charset_ucs2_general_uca= uca_weight, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8076,9 +8079,12 @@ CHARSET_INFO my_charset_ucs2_icelandic_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8103,9 +8109,12 @@ CHARSET_INFO my_charset_ucs2_latvian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8130,9 +8139,12 @@ CHARSET_INFO my_charset_ucs2_romanian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8157,9 +8169,12 @@ CHARSET_INFO my_charset_ucs2_slovenian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8184,9 +8199,12 @@ CHARSET_INFO my_charset_ucs2_polish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8211,9 +8229,12 @@ CHARSET_INFO my_charset_ucs2_estonian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8238,9 +8259,12 @@ CHARSET_INFO my_charset_ucs2_spanish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8265,9 +8289,12 @@ CHARSET_INFO my_charset_ucs2_swedish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8292,9 +8319,12 @@ CHARSET_INFO my_charset_ucs2_turkish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_turkish, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8319,9 +8349,12 @@ CHARSET_INFO my_charset_ucs2_czech_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8347,9 +8380,12 @@ CHARSET_INFO my_charset_ucs2_danish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8374,9 +8410,12 @@ CHARSET_INFO my_charset_ucs2_lithuanian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8401,9 +8440,12 @@ CHARSET_INFO my_charset_ucs2_slovak_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8428,9 +8470,12 @@ CHARSET_INFO my_charset_ucs2_spanish2_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8456,9 +8501,12 @@ CHARSET_INFO my_charset_ucs2_roman_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8484,9 +8532,12 @@ CHARSET_INFO my_charset_ucs2_persian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8559,9 +8610,12 @@ CHARSET_INFO my_charset_utf8_general_uca_ci= uca_weight, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8587,9 +8641,12 @@ CHARSET_INFO my_charset_utf8_icelandic_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8614,9 +8671,12 @@ CHARSET_INFO my_charset_utf8_latvian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8641,9 +8701,12 @@ CHARSET_INFO my_charset_utf8_romanian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8668,9 +8731,12 @@ CHARSET_INFO my_charset_utf8_slovenian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8695,9 +8761,12 @@ CHARSET_INFO my_charset_utf8_polish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8722,9 +8791,12 @@ CHARSET_INFO my_charset_utf8_estonian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8749,9 +8821,12 @@ CHARSET_INFO my_charset_utf8_spanish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8776,9 +8851,12 @@ CHARSET_INFO my_charset_utf8_swedish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8803,9 +8881,12 @@ CHARSET_INFO my_charset_utf8_turkish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_turkish, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 2, /* caseup_multiply */ + 2, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8830,9 +8911,12 @@ CHARSET_INFO my_charset_utf8_czech_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8858,9 +8942,12 @@ CHARSET_INFO my_charset_utf8_danish_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8885,9 +8972,12 @@ CHARSET_INFO my_charset_utf8_lithuanian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8912,9 +9002,12 @@ CHARSET_INFO my_charset_utf8_slovak_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8939,9 +9032,12 @@ CHARSET_INFO my_charset_utf8_spanish2_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8966,9 +9062,12 @@ CHARSET_INFO my_charset_utf8_roman_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ @@ -8993,9 +9092,12 @@ CHARSET_INFO my_charset_utf8_persian_uca_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 8, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 9, /* min_sort_char */ diff --git a/strings/ctype-ucs2.c b/strings/ctype-ucs2.c index 706d42e3725..4acd75d7a6f 100644 --- a/strings/ctype-ucs2.c +++ b/strings/ctype-ucs2.c @@ -30,7 +30,6 @@ #define EILSEQ ENOENT #endif -extern MY_UNICASE_INFO *uni_plane[256]; static uchar ctype_ucs2[] = { 0, @@ -113,20 +112,26 @@ static int my_uni_ucs2(CHARSET_INFO *cs __attribute__((unused)) , } -static void my_caseup_ucs2(CHARSET_INFO *cs, char *s, uint slen) +static uint my_caseup_ucs2(CHARSET_INFO *cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { my_wc_t wc; int res; - char *e=s+slen; - - while ((s < e) && (res=my_ucs2_uni(cs,&wc, (uchar *)s, (uchar*)e))>0 ) + char *srcend= src + srclen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; + DBUG_ASSERT(src == dst && srclen == dstlen); + + while ((src < srcend) && + (res= my_ucs2_uni(cs, &wc, (uchar *)src, (uchar*) srcend)) > 0) { - int plane = (wc>>8) & 0xFF; - wc = uni_plane[plane] ? uni_plane[plane][wc & 0xFF].toupper : wc; - if (res != my_uni_ucs2(cs,wc,(uchar*)s,(uchar*)e)) + int plane= (wc>>8) & 0xFF; + wc= uni_plane[plane] ? uni_plane[plane][wc & 0xFF].toupper : wc; + if (res != my_uni_ucs2(cs, wc, (uchar*) src, (uchar*) srcend)) break; - s+=res; + src+= res; } + return srclen; } @@ -136,6 +141,7 @@ static void my_hash_sort_ucs2(CHARSET_INFO *cs, const uchar *s, uint slen, my_wc_t wc; int res; const uchar *e=s+slen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while (e > s+1 && e[-1] == ' ' && e[-2] == '\0') e-= 2; @@ -160,22 +166,26 @@ static void my_caseup_str_ucs2(CHARSET_INFO * cs __attribute__((unused)), -static void my_casedn_ucs2(CHARSET_INFO *cs, char *s, uint slen) +static uint my_casedn_ucs2(CHARSET_INFO *cs, char *src, uint srclen, + char *dst __attribute__((unused)), + uint dstlen __attribute__((unused))) { my_wc_t wc; int res; - char *e=s+slen; + char *srcend= src + srclen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; + DBUG_ASSERT(src == dst && srclen == dstlen); - while ((s < e) && (res=my_ucs2_uni(cs, &wc, (uchar*)s, (uchar*)e))>0) + while ((src < srcend) && + (res= my_ucs2_uni(cs, &wc, (uchar*) src, (uchar*) srcend)) > 0) { - int plane = (wc>>8) & 0xFF; - wc = uni_plane[plane] ? uni_plane[plane][wc & 0xFF].tolower : wc; - if (res != my_uni_ucs2(cs, wc, (uchar*)s, (uchar*)e)) - { + int plane= (wc>>8) & 0xFF; + wc= uni_plane[plane] ? uni_plane[plane][wc & 0xFF].tolower : wc; + if (res != my_uni_ucs2(cs, wc, (uchar*) src, (uchar*) srcend)) break; - } - s+=res; + src+= res; } + return srclen; } static void my_casedn_str_ucs2(CHARSET_INFO *cs __attribute__((unused)), @@ -193,6 +203,7 @@ static int my_strnncoll_ucs2(CHARSET_INFO *cs, my_wc_t s_wc,t_wc; const uchar *se=s+slen; const uchar *te=t+tlen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while ( s < se && t < te ) { @@ -256,6 +267,7 @@ static int my_strnncollsp_ucs2(CHARSET_INFO *cs __attribute__((unused)), { const uchar *se, *te; uint minlen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; /* extra safety to make sure the lengths are even numbers */ slen&= ~1; @@ -305,6 +317,7 @@ static int my_strncasecmp_ucs2(CHARSET_INFO *cs, my_wc_t s_wc,t_wc; const char *se=s+len; const char *te=t+len; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while ( s < se && t < te ) { @@ -352,6 +365,7 @@ static int my_strnxfrm_ucs2(CHARSET_INFO *cs, int plane; uchar *de = dst + dstlen; const uchar *se = src + srclen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while( src < se && dst < de ) { @@ -1310,6 +1324,7 @@ int my_wildcmp_ucs2_ci(CHARSET_INFO *cs, const char *wildstr,const char *wildend, int escape, int w_one, int w_many) { + MY_UNICASE_INFO **uni_plane= cs->caseinfo; return my_wildcmp_unicode(cs,str,str_end,wildstr,wildend, escape,w_one,w_many,uni_plane); } @@ -1596,9 +1611,12 @@ CHARSET_INFO my_charset_ucs2_general_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ @@ -1623,9 +1641,12 @@ CHARSET_INFO my_charset_ucs2_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 2, /* mbminlen */ 2, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-ujis.c b/strings/ctype-ujis.c index 5d0c77cee6e..6b704980d0d 100644 --- a/strings/ctype-ujis.c +++ b/strings/ctype-ujis.c @@ -8566,9 +8566,12 @@ CHARSET_INFO my_charset_ujis_japanese_ci= NULL, /* contractions */ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ @@ -8594,9 +8597,12 @@ CHARSET_INFO my_charset_ujis_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-utf8.c b/strings/ctype-utf8.c index 250c57cf265..6f6d24d8643 100644 --- a/strings/ctype-utf8.c +++ b/strings/ctype-utf8.c @@ -172,6 +172,8 @@ static MY_UNICASE_INFO plane00[]={ {0x00DE,0x00FE,0x00DE}, {0x0178,0x00FF,0x0059} }; + + static MY_UNICASE_INFO plane01[]={ {0x0100,0x0101,0x0041}, {0x0100,0x0101,0x0041}, {0x0102,0x0103,0x0041}, {0x0102,0x0103,0x0041}, @@ -1482,7 +1484,7 @@ static MY_UNICASE_INFO planeFF[]={ {0xFFFE,0xFFFE,0xFFFE}, {0xFFFF,0xFFFF,0xFFFF} }; -MY_UNICASE_INFO *uni_plane[256]={ +MY_UNICASE_INFO *my_unicase_default[256]={ plane00, plane01, plane02, plane03, plane04, plane05, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -1520,6 +1522,186 @@ MY_UNICASE_INFO *uni_plane[256]={ /* + Turkish lower/upper mapping: + 1. LOWER(0x0049 LATIN CAPITAL LETTER I) -> + 0x0131 LATIN SMALL LETTER DOTLESS I + 2. UPPER(0x0069 LATIN SMALL LETTER I) -> + 0x0130 LATIN CAPITAL LETTER I WITH DOT ABOVE +*/ + +static MY_UNICASE_INFO turk00[]= +{ + {0x0000,0x0000,0x0000}, {0x0001,0x0001,0x0001}, + {0x0002,0x0002,0x0002}, {0x0003,0x0003,0x0003}, + {0x0004,0x0004,0x0004}, {0x0005,0x0005,0x0005}, + {0x0006,0x0006,0x0006}, {0x0007,0x0007,0x0007}, + {0x0008,0x0008,0x0008}, {0x0009,0x0009,0x0009}, + {0x000A,0x000A,0x000A}, {0x000B,0x000B,0x000B}, + {0x000C,0x000C,0x000C}, {0x000D,0x000D,0x000D}, + {0x000E,0x000E,0x000E}, {0x000F,0x000F,0x000F}, + {0x0010,0x0010,0x0010}, {0x0011,0x0011,0x0011}, + {0x0012,0x0012,0x0012}, {0x0013,0x0013,0x0013}, + {0x0014,0x0014,0x0014}, {0x0015,0x0015,0x0015}, + {0x0016,0x0016,0x0016}, {0x0017,0x0017,0x0017}, + {0x0018,0x0018,0x0018}, {0x0019,0x0019,0x0019}, + {0x001A,0x001A,0x001A}, {0x001B,0x001B,0x001B}, + {0x001C,0x001C,0x001C}, {0x001D,0x001D,0x001D}, + {0x001E,0x001E,0x001E}, {0x001F,0x001F,0x001F}, + {0x0020,0x0020,0x0020}, {0x0021,0x0021,0x0021}, + {0x0022,0x0022,0x0022}, {0x0023,0x0023,0x0023}, + {0x0024,0x0024,0x0024}, {0x0025,0x0025,0x0025}, + {0x0026,0x0026,0x0026}, {0x0027,0x0027,0x0027}, + {0x0028,0x0028,0x0028}, {0x0029,0x0029,0x0029}, + {0x002A,0x002A,0x002A}, {0x002B,0x002B,0x002B}, + {0x002C,0x002C,0x002C}, {0x002D,0x002D,0x002D}, + {0x002E,0x002E,0x002E}, {0x002F,0x002F,0x002F}, + {0x0030,0x0030,0x0030}, {0x0031,0x0031,0x0031}, + {0x0032,0x0032,0x0032}, {0x0033,0x0033,0x0033}, + {0x0034,0x0034,0x0034}, {0x0035,0x0035,0x0035}, + {0x0036,0x0036,0x0036}, {0x0037,0x0037,0x0037}, + {0x0038,0x0038,0x0038}, {0x0039,0x0039,0x0039}, + {0x003A,0x003A,0x003A}, {0x003B,0x003B,0x003B}, + {0x003C,0x003C,0x003C}, {0x003D,0x003D,0x003D}, + {0x003E,0x003E,0x003E}, {0x003F,0x003F,0x003F}, + {0x0040,0x0040,0x0040}, {0x0041,0x0061,0x0041}, + {0x0042,0x0062,0x0042}, {0x0043,0x0063,0x0043}, + {0x0044,0x0064,0x0044}, {0x0045,0x0065,0x0045}, + {0x0046,0x0066,0x0046}, {0x0047,0x0067,0x0047}, + {0x0048,0x0068,0x0048}, {0x0049,0x0131,0x0049}, + {0x004A,0x006A,0x004A}, {0x004B,0x006B,0x004B}, + {0x004C,0x006C,0x004C}, {0x004D,0x006D,0x004D}, + {0x004E,0x006E,0x004E}, {0x004F,0x006F,0x004F}, + {0x0050,0x0070,0x0050}, {0x0051,0x0071,0x0051}, + {0x0052,0x0072,0x0052}, {0x0053,0x0073,0x0053}, + {0x0054,0x0074,0x0054}, {0x0055,0x0075,0x0055}, + {0x0056,0x0076,0x0056}, {0x0057,0x0077,0x0057}, + {0x0058,0x0078,0x0058}, {0x0059,0x0079,0x0059}, + {0x005A,0x007A,0x005A}, {0x005B,0x005B,0x005B}, + {0x005C,0x005C,0x005C}, {0x005D,0x005D,0x005D}, + {0x005E,0x005E,0x005E}, {0x005F,0x005F,0x005F}, + {0x0060,0x0060,0x0060}, {0x0041,0x0061,0x0041}, + {0x0042,0x0062,0x0042}, {0x0043,0x0063,0x0043}, + {0x0044,0x0064,0x0044}, {0x0045,0x0065,0x0045}, + {0x0046,0x0066,0x0046}, {0x0047,0x0067,0x0047}, + {0x0048,0x0068,0x0048}, {0x0130,0x0069,0x0049}, + {0x004A,0x006A,0x004A}, {0x004B,0x006B,0x004B}, + {0x004C,0x006C,0x004C}, {0x004D,0x006D,0x004D}, + {0x004E,0x006E,0x004E}, {0x004F,0x006F,0x004F}, + {0x0050,0x0070,0x0050}, {0x0051,0x0071,0x0051}, + {0x0052,0x0072,0x0052}, {0x0053,0x0073,0x0053}, + {0x0054,0x0074,0x0054}, {0x0055,0x0075,0x0055}, + {0x0056,0x0076,0x0056}, {0x0057,0x0077,0x0057}, + {0x0058,0x0078,0x0058}, {0x0059,0x0079,0x0059}, + {0x005A,0x007A,0x005A}, {0x007B,0x007B,0x007B}, + {0x007C,0x007C,0x007C}, {0x007D,0x007D,0x007D}, + {0x007E,0x007E,0x007E}, {0x007F,0x007F,0x007F}, + {0x0080,0x0080,0x0080}, {0x0081,0x0081,0x0081}, + {0x0082,0x0082,0x0082}, {0x0083,0x0083,0x0083}, + {0x0084,0x0084,0x0084}, {0x0085,0x0085,0x0085}, + {0x0086,0x0086,0x0086}, {0x0087,0x0087,0x0087}, + {0x0088,0x0088,0x0088}, {0x0089,0x0089,0x0089}, + {0x008A,0x008A,0x008A}, {0x008B,0x008B,0x008B}, + {0x008C,0x008C,0x008C}, {0x008D,0x008D,0x008D}, + {0x008E,0x008E,0x008E}, {0x008F,0x008F,0x008F}, + {0x0090,0x0090,0x0090}, {0x0091,0x0091,0x0091}, + {0x0092,0x0092,0x0092}, {0x0093,0x0093,0x0093}, + {0x0094,0x0094,0x0094}, {0x0095,0x0095,0x0095}, + {0x0096,0x0096,0x0096}, {0x0097,0x0097,0x0097}, + {0x0098,0x0098,0x0098}, {0x0099,0x0099,0x0099}, + {0x009A,0x009A,0x009A}, {0x009B,0x009B,0x009B}, + {0x009C,0x009C,0x009C}, {0x009D,0x009D,0x009D}, + {0x009E,0x009E,0x009E}, {0x009F,0x009F,0x009F}, + {0x00A0,0x00A0,0x00A0}, {0x00A1,0x00A1,0x00A1}, + {0x00A2,0x00A2,0x00A2}, {0x00A3,0x00A3,0x00A3}, + {0x00A4,0x00A4,0x00A4}, {0x00A5,0x00A5,0x00A5}, + {0x00A6,0x00A6,0x00A6}, {0x00A7,0x00A7,0x00A7}, + {0x00A8,0x00A8,0x00A8}, {0x00A9,0x00A9,0x00A9}, + {0x00AA,0x00AA,0x00AA}, {0x00AB,0x00AB,0x00AB}, + {0x00AC,0x00AC,0x00AC}, {0x00AD,0x00AD,0x00AD}, + {0x00AE,0x00AE,0x00AE}, {0x00AF,0x00AF,0x00AF}, + {0x00B0,0x00B0,0x00B0}, {0x00B1,0x00B1,0x00B1}, + {0x00B2,0x00B2,0x00B2}, {0x00B3,0x00B3,0x00B3}, + {0x00B4,0x00B4,0x00B4}, {0x039C,0x00B5,0x039C}, + {0x00B6,0x00B6,0x00B6}, {0x00B7,0x00B7,0x00B7}, + {0x00B8,0x00B8,0x00B8}, {0x00B9,0x00B9,0x00B9}, + {0x00BA,0x00BA,0x00BA}, {0x00BB,0x00BB,0x00BB}, + {0x00BC,0x00BC,0x00BC}, {0x00BD,0x00BD,0x00BD}, + {0x00BE,0x00BE,0x00BE}, {0x00BF,0x00BF,0x00BF}, + {0x00C0,0x00E0,0x0041}, {0x00C1,0x00E1,0x0041}, + {0x00C2,0x00E2,0x0041}, {0x00C3,0x00E3,0x0041}, + {0x00C4,0x00E4,0x0041}, {0x00C5,0x00E5,0x0041}, + {0x00C6,0x00E6,0x00C6}, {0x00C7,0x00E7,0x0043}, + {0x00C8,0x00E8,0x0045}, {0x00C9,0x00E9,0x0045}, + {0x00CA,0x00EA,0x0045}, {0x00CB,0x00EB,0x0045}, + {0x00CC,0x00EC,0x0049}, {0x00CD,0x00ED,0x0049}, + {0x00CE,0x00EE,0x0049}, {0x00CF,0x00EF,0x0049}, + {0x00D0,0x00F0,0x00D0}, {0x00D1,0x00F1,0x004E}, + {0x00D2,0x00F2,0x004F}, {0x00D3,0x00F3,0x004F}, + {0x00D4,0x00F4,0x004F}, {0x00D5,0x00F5,0x004F}, + {0x00D6,0x00F6,0x004F}, {0x00D7,0x00D7,0x00D7}, + {0x00D8,0x00F8,0x00D8}, {0x00D9,0x00F9,0x0055}, + {0x00DA,0x00FA,0x0055}, {0x00DB,0x00FB,0x0055}, + {0x00DC,0x00FC,0x0055}, {0x00DD,0x00FD,0x0059}, + {0x00DE,0x00FE,0x00DE}, {0x00DF,0x00DF,0x00DF}, + {0x00C0,0x00E0,0x0041}, {0x00C1,0x00E1,0x0041}, + {0x00C2,0x00E2,0x0041}, {0x00C3,0x00E3,0x0041}, + {0x00C4,0x00E4,0x0041}, {0x00C5,0x00E5,0x0041}, + {0x00C6,0x00E6,0x00C6}, {0x00C7,0x00E7,0x0043}, + {0x00C8,0x00E8,0x0045}, {0x00C9,0x00E9,0x0045}, + {0x00CA,0x00EA,0x0045}, {0x00CB,0x00EB,0x0045}, + {0x00CC,0x00EC,0x0049}, {0x00CD,0x00ED,0x0049}, + {0x00CE,0x00EE,0x0049}, {0x00CF,0x00EF,0x0049}, + {0x00D0,0x00F0,0x00D0}, {0x00D1,0x00F1,0x004E}, + {0x00D2,0x00F2,0x004F}, {0x00D3,0x00F3,0x004F}, + {0x00D4,0x00F4,0x004F}, {0x00D5,0x00F5,0x004F}, + {0x00D6,0x00F6,0x004F}, {0x00F7,0x00F7,0x00F7}, + {0x00D8,0x00F8,0x00D8}, {0x00D9,0x00F9,0x0055}, + {0x00DA,0x00FA,0x0055}, {0x00DB,0x00FB,0x0055}, + {0x00DC,0x00FC,0x0055}, {0x00DD,0x00FD,0x0059}, + {0x00DE,0x00FE,0x00DE}, {0x0178,0x00FF,0x0059} +}; + + + +MY_UNICASE_INFO *my_unicase_turkish[256]= +{ + turk00, plane01, plane02, plane03, plane04, plane05, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, plane1E, plane1F, + NULL, plane21, NULL, NULL, plane24, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, planeFF +}; + + + +/* ** Compare string against string with wildcard ** This function is used in UTF8 and UCS2 ** @@ -1907,20 +2089,26 @@ static int my_uni_utf8 (CHARSET_INFO *cs __attribute__((unused)) , } -static void my_caseup_utf8(CHARSET_INFO *cs, char *s, uint slen) +static uint my_caseup_utf8(CHARSET_INFO *cs, char *src, uint srclen, + char *dst, uint dstlen) { my_wc_t wc; - int res; - char *e=s+slen; + int srcres, dstres; + char *srcend= src + srclen, *dstend= dst + dstlen, *dst0= dst; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; + DBUG_ASSERT(src != dst || cs->caseup_multiply == 1); - while ((s < e) && (res=my_utf8_uni(cs,&wc, (uchar *)s, (uchar*)e))>0 ) + while ((src < srcend) && + (srcres= my_utf8_uni(cs, &wc, (uchar *) src, (uchar*) srcend)) > 0) { - int plane = (wc>>8) & 0xFF; - wc = uni_plane[plane] ? uni_plane[plane][wc & 0xFF].toupper : wc; - if (res != my_uni_utf8(cs,wc,(uchar*)s,(uchar*)e)) + int plane= (wc>>8) & 0xFF; + wc= uni_plane[plane] ? uni_plane[plane][wc & 0xFF].toupper : wc; + if ((dstres= my_uni_utf8(cs, wc, (uchar*) dst, (uchar*) dstend)) <= 0) break; - s+=res; + src+= srcres; + dst+= dstres; } + return dst - dst0; } static void my_hash_sort_utf8(CHARSET_INFO *cs, const uchar *s, uint slen, @@ -1929,6 +2117,7 @@ static void my_hash_sort_utf8(CHARSET_INFO *cs, const uchar *s, uint slen, my_wc_t wc; int res; const uchar *e=s+slen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; /* Remove end space. We have to do this to be able to compare @@ -1952,31 +2141,37 @@ static void my_hash_sort_utf8(CHARSET_INFO *cs, const uchar *s, uint slen, static void my_caseup_str_utf8(CHARSET_INFO * cs, char * s) { - my_caseup_utf8(cs, s, strlen(s)); + uint len= strlen(s); + my_caseup_utf8(cs, s, len, s, len); } -static void my_casedn_utf8(CHARSET_INFO *cs, char *s, uint slen) +static uint my_casedn_utf8(CHARSET_INFO *cs, char *src, uint srclen, + char *dst, uint dstlen) { my_wc_t wc; - int res; - char *e=s+slen; + int srcres, dstres; + char *srcend= src + srclen, *dstend= dst + dstlen, *dst0= dst; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; + DBUG_ASSERT(src != dst || cs->casedn_multiply == 1); - while ((s < e) && (res=my_utf8_uni(cs, &wc, (uchar*)s, (uchar*)e))>0) + while ((src < srcend) && + (srcres= my_utf8_uni(cs, &wc, (uchar*) src, (uchar*)srcend)) > 0) { - int plane = (wc>>8) & 0xFF; - wc = uni_plane[plane] ? uni_plane[plane][wc & 0xFF].tolower : wc; - if (res != my_uni_utf8(cs, wc, (uchar*)s, (uchar*)e)) - { + int plane= (wc>>8) & 0xFF; + wc= uni_plane[plane] ? uni_plane[plane][wc & 0xFF].tolower : wc; + if ((dstres= my_uni_utf8(cs, wc, (uchar*) dst, (uchar*) dstend)) <= 0) break; - } - s+=res; + src+= srcres; + dst+= dstres; } + return dst - dst0; } static void my_casedn_str_utf8(CHARSET_INFO *cs, char * s) { - my_casedn_utf8(cs, s, strlen(s)); + uint len= strlen(s); + my_casedn_utf8(cs, s, len, s, len); } @@ -1989,6 +2184,7 @@ static int my_strnncoll_utf8(CHARSET_INFO *cs, my_wc_t s_wc,t_wc; const uchar *se=s+slen; const uchar *te=t+tlen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while ( s < se && t < te ) { @@ -2057,6 +2253,7 @@ static int my_strnncollsp_utf8(CHARSET_INFO *cs, int s_res, t_res, res; my_wc_t s_wc,t_wc; const uchar *se= s+slen, *te= t+tlen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; #ifndef VARCHAR_WITH_DIFF_ENDSPACE_ARE_DIFFERENT_FOR_UNIQUE diff_if_only_endspace_difference= 0; @@ -2144,6 +2341,7 @@ static int my_strnncollsp_utf8(CHARSET_INFO *cs, static int my_strcasecmp_utf8(CHARSET_INFO *cs, const char *s, const char *t) { + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while (s[0] && t[0]) { my_wc_t s_wc,t_wc; @@ -2228,6 +2426,7 @@ int my_wildcmp_utf8(CHARSET_INFO *cs, const char *wildstr,const char *wildend, int escape, int w_one, int w_many) { + MY_UNICASE_INFO **uni_plane= cs->caseinfo; return my_wildcmp_unicode(cs,str,str_end,wildstr,wildend, escape,w_one,w_many,uni_plane); } @@ -2249,6 +2448,7 @@ static int my_strnxfrm_utf8(CHARSET_INFO *cs, uchar *de= dst + dstlen; uchar *de_beg= de - 1; const uchar *se = src + srclen; + MY_UNICASE_INFO **uni_plane= cs->caseinfo; while (dst < de_beg) { @@ -2367,9 +2567,12 @@ CHARSET_INFO my_charset_utf8_general_ci= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ @@ -2395,9 +2598,12 @@ CHARSET_INFO my_charset_utf8_bin= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ @@ -2561,9 +2767,12 @@ CHARSET_INFO my_charset_utf8_general_cs= NULL, /* sort_order_big*/ NULL, /* tab_to_uni */ NULL, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 1, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 3, /* mbmaxlen */ 0, /* min_sort_char */ diff --git a/strings/ctype-win1250ch.c b/strings/ctype-win1250ch.c index cb8de8f43ac..8ac80ed392b 100644 --- a/strings/ctype-win1250ch.c +++ b/strings/ctype-win1250ch.c @@ -652,9 +652,12 @@ CHARSET_INFO my_charset_cp1250_czech_ci = NULL, /* sort_order_big*/ tab_cp1250_uni, /* tab_to_uni */ idx_uni_cp1250, /* tab_from_uni */ + my_unicase_default, /* caseinfo */ NULL, /* state_map */ NULL, /* ident_map */ 2, /* strxfrm_multiply */ + 1, /* caseup_multiply */ + 1, /* casedn_multiply */ 1, /* mbminlen */ 1, /* mbmaxlen */ 0, /* min_sort_char */ |