summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/m_ctype.h36
-rw-r--r--mysys/charset.c63
-rw-r--r--sql/sql_show.cc4
-rw-r--r--sql/sql_string.cc6
-rw-r--r--strings/ctype-big5.c2
-rw-r--r--strings/ctype-czech.c2
-rw-r--r--strings/ctype-euc_kr.c2
-rw-r--r--strings/ctype-gb2312.c2
-rw-r--r--strings/ctype-gbk.c2
-rw-r--r--strings/ctype-latin1.c2
-rw-r--r--strings/ctype-sjis.c2
-rw-r--r--strings/ctype-tis620.c2
-rw-r--r--strings/ctype-ucs2.c4
-rw-r--r--strings/ctype-ujis.c2
-rw-r--r--strings/ctype-utf8.c4
-rw-r--r--strings/ctype-win1250ch.c2
-rw-r--r--strings/ctype.c2
17 files changed, 59 insertions, 80 deletions
diff --git a/include/m_ctype.h b/include/m_ctype.h
index e28d5687983..6cf0ecfbb8a 100644
--- a/include/m_ctype.h
+++ b/include/m_ctype.h
@@ -61,6 +61,7 @@ typedef struct unicase_info_st
#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 full unicode */
#define MY_CHARSET_UNDEFINED 0
#define MY_CHARSET_CURRENT (default_charset_info->number)
@@ -185,20 +186,29 @@ typedef struct charset_info_st
extern CHARSET_INFO my_charset_bin;
+extern CHARSET_INFO my_charset_big5_chinese_ci;
+extern CHARSET_INFO my_charset_big5_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_latin1;
-extern CHARSET_INFO my_charset_big5;
-extern CHARSET_INFO my_charset_czech;
-extern CHARSET_INFO my_charset_euc_kr;
-extern CHARSET_INFO my_charset_gb2312;
-extern CHARSET_INFO my_charset_gbk;
-extern CHARSET_INFO my_charset_latin1_de;
-extern CHARSET_INFO my_charset_sjis;
-extern CHARSET_INFO my_charset_tis620;
-extern CHARSET_INFO my_charset_ucs2;
-extern CHARSET_INFO my_charset_ucse;
-extern CHARSET_INFO my_charset_ujis;
-extern CHARSET_INFO my_charset_utf8;
-extern CHARSET_INFO my_charset_win1250ch;
+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_ujis_japanese_ci;
+extern CHARSET_INFO my_charset_ujis_bin;
+extern CHARSET_INFO my_charset_utf8_general_ci;
+extern CHARSET_INFO my_charset_utf8_bin;
+extern CHARSET_INFO my_charset_cp1250_czech_ci;
extern my_bool my_parse_charset_xml(const char *bug, uint len,
diff --git a/mysys/charset.c b/mysys/charset.c
index d685104abac..9b8903bc6b7 100644
--- a/mysys/charset.c
+++ b/mysys/charset.c
@@ -313,6 +313,8 @@ static int add_collation(CHARSET_INFO *cs)
{
if (!all_charsets[cs->number])
{
+ if (cs->state & MY_CS_COMPILED)
+ return MY_XML_OK;
if (!(all_charsets[cs->number]=
(CHARSET_INFO*) my_once_alloc(sizeof(CHARSET_INFO),MYF(0))))
return MY_XML_ERROR;
@@ -422,57 +424,53 @@ CHARSET_INFO *default_charset_info = &my_charset_latin1;
static my_bool init_compiled_charsets(myf flags __attribute__((unused)))
{
CHARSET_INFO *cs;
-
- MY_ADD_CHARSET(&my_charset_latin1);
+ MY_ADD_CHARSET(&my_charset_latin1);
MY_ADD_CHARSET(&my_charset_bin);
+ MY_ADD_CHARSET(&my_charset_latin1_german2_ci);
#ifdef HAVE_CHARSET_big5
- MY_ADD_CHARSET(&my_charset_big5);
+ MY_ADD_CHARSET(&my_charset_big5_chinese_ci);
#endif
#ifdef HAVE_CHARSET_czech
- MY_ADD_CHARSET(&my_charset_czech);
+ MY_ADD_CHARSET(&my_charset_latin2_czech_ci);
#endif
#ifdef HAVE_CHARSET_euc_kr
- MY_ADD_CHARSET(&my_charset_euc_kr);
+ MY_ADD_CHARSET(&my_charset_euckr_korean_ci);
#endif
#ifdef HAVE_CHARSET_gb2312
- MY_ADD_CHARSET(&my_charset_gb2312);
+ MY_ADD_CHARSET(&my_charset_gb2312_chinese_ci);
#endif
#ifdef HAVE_CHARSET_gbk
- MY_ADD_CHARSET(&my_charset_gbk);
-#endif
-
-#ifdef HAVE_CHARSET_latin1_de
- MY_ADD_CHARSET(&my_charset_latin1_de);
+ MY_ADD_CHARSET(&my_charset_gbk_chinese_ci);
#endif
#ifdef HAVE_CHARSET_sjis
- MY_ADD_CHARSET(&my_charset_sjis);
+ MY_ADD_CHARSET(&my_charset_sjis_japanese_ci);
#endif
#ifdef HAVE_CHARSET_tis620
- MY_ADD_CHARSET(&my_charset_tis620);
+ MY_ADD_CHARSET(&my_charset_tis620_thai_ci);
#endif
#ifdef HAVE_CHARSET_ucs2
- MY_ADD_CHARSET(&my_charset_ucs2);
+ MY_ADD_CHARSET(&my_charset_ucs2_general_ci);
#endif
#ifdef HAVE_CHARSET_ujis
- MY_ADD_CHARSET(&my_charset_ujis);
+ MY_ADD_CHARSET(&my_charset_ujis_japanese_ci);
#endif
#ifdef HAVE_CHARSET_utf8
- MY_ADD_CHARSET(&my_charset_utf8);
+ MY_ADD_CHARSET(&my_charset_utf8_general_ci);
#endif
#ifdef HAVE_CHARSET_win1250ch
- MY_ADD_CHARSET(&my_charset_win1250ch);
+ MY_ADD_CHARSET(&my_charset_cp1250_czech_ci);
#endif
/* Copy compiled charsets */
@@ -533,12 +531,6 @@ void free_charsets(void)
}
-static void get_charset_conf_name(const char *cs_name, char *buf)
-{
- strxmov(get_charsets_dir(buf), cs_name, ".conf", NullS);
-}
-
-
uint get_charset_number(const char *charset_name)
{
CHARSET_INFO **cs;
@@ -661,28 +653,3 @@ CHARSET_INFO *get_charset_by_csname(const char *cs_name,
return cs;
}
-
-
-/* Only append name if it doesn't exist from before */
-
-static my_bool charset_in_string(const char *name, DYNAMIC_STRING *s)
-{
- uint length= (uint) strlen(name);
- const char *pos;
- for (pos=s->str ; (pos=strstr(pos,name)) ; pos++)
- {
- if (! pos[length] || pos[length] == ' ')
- return TRUE; /* Already existed */
- }
- return FALSE;
-}
-
-
-static void charset_append(DYNAMIC_STRING *s, const char *name)
-{
- if (!charset_in_string(name, s))
- {
- dynstr_append(s, name);
- dynstr_append(s, " ");
- }
-}
diff --git a/sql/sql_show.cc b/sql/sql_show.cc
index 25bbd4851ba..660b8e7e572 100644
--- a/sql/sql_show.cc
+++ b/sql/sql_show.cc
@@ -1420,8 +1420,8 @@ void mysqld_list_processes(THD *thd,const char *user, bool verbose)
static bool write_collation(Protocol *protocol, CHARSET_INFO *cs)
{
protocol->prepare_for_resend();
- protocol->store(cs->csname, system_charset_info);
protocol->store(cs->name, system_charset_info);
+ protocol->store(cs->csname, system_charset_info);
protocol->store_short((longlong) cs->number);
protocol->store((cs->state & MY_CS_PRIMARY) ? "Y" : "",system_charset_info);
protocol->store((cs->state & MY_CS_COMPILED)? "Y" : "",system_charset_info);
@@ -1440,8 +1440,8 @@ int mysqld_show_collations(THD *thd, const char *wild)
DBUG_ENTER("mysqld_show_charsets");
- field_list.push_back(new Item_empty_string("Charset",30));
field_list.push_back(new Item_empty_string("Collation",30));
+ field_list.push_back(new Item_empty_string("Charset",30));
field_list.push_back(new Item_return_int("Id",11, FIELD_TYPE_SHORT));
field_list.push_back(new Item_empty_string("D",30));
field_list.push_back(new Item_empty_string("C",30));
diff --git a/sql/sql_string.cc b/sql/sql_string.cc
index bd101944160..126fb84d6d9 100644
--- a/sql/sql_string.cc
+++ b/sql/sql_string.cc
@@ -28,9 +28,9 @@
#include <floatingpoint.h>
#endif
-CHARSET_INFO *system_charset_info= &my_charset_utf8;
-CHARSET_INFO *files_charset_info= &my_charset_utf8;
-CHARSET_INFO *national_charset_info= &my_charset_utf8;
+CHARSET_INFO *system_charset_info= &my_charset_utf8_general_ci;
+CHARSET_INFO *files_charset_info= &my_charset_utf8_general_ci;
+CHARSET_INFO *national_charset_info= &my_charset_utf8_general_ci;
extern gptr sql_alloc(unsigned size);
extern void sql_element_free(void *ptr);
diff --git a/strings/ctype-big5.c b/strings/ctype-big5.c
index 57ee2d7c6ae..ec723e8690a 100644
--- a/strings/ctype-big5.c
+++ b/strings/ctype-big5.c
@@ -6226,7 +6226,7 @@ my_mb_wc_big5(CHARSET_INFO *cs __attribute__((unused)),
return 2;
}
-CHARSET_INFO my_charset_big5 =
+CHARSET_INFO my_charset_big5_chinese_ci =
{
1,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-czech.c b/strings/ctype-czech.c
index 9da2103fda3..788cd96ad13 100644
--- a/strings/ctype-czech.c
+++ b/strings/ctype-czech.c
@@ -605,7 +605,7 @@ int my_strnncollsp_czech(CHARSET_INFO * cs,
}
-CHARSET_INFO my_charset_czech =
+CHARSET_INFO my_charset_latin2_czech_ci =
{
2,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-euc_kr.c b/strings/ctype-euc_kr.c
index 21f01b6509c..3bf689910e6 100644
--- a/strings/ctype-euc_kr.c
+++ b/strings/ctype-euc_kr.c
@@ -8634,7 +8634,7 @@ my_mb_wc_euc_kr(CHARSET_INFO *cs __attribute__((unused)),
return 2;
}
-CHARSET_INFO my_charset_euc_kr =
+CHARSET_INFO my_charset_euckr_korean_ci =
{
19,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY, /* state */
diff --git a/strings/ctype-gb2312.c b/strings/ctype-gb2312.c
index f1ec5a9f363..20e1ce888e8 100644
--- a/strings/ctype-gb2312.c
+++ b/strings/ctype-gb2312.c
@@ -5684,7 +5684,7 @@ my_mb_wc_gb2312(CHARSET_INFO *cs __attribute__((unused)),
return 2;
}
-CHARSET_INFO my_charset_gb2312 =
+CHARSET_INFO my_charset_gb2312_chinese_ci =
{
24,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY, /* state */
diff --git a/strings/ctype-gbk.c b/strings/ctype-gbk.c
index b1ea209d6ad..ec0cc01881b 100644
--- a/strings/ctype-gbk.c
+++ b/strings/ctype-gbk.c
@@ -9881,7 +9881,7 @@ my_mb_wc_gbk(CHARSET_INFO *cs __attribute__((unused)),
}
-CHARSET_INFO my_charset_gbk =
+CHARSET_INFO my_charset_gbk_chinese_ci =
{
28,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-latin1.c b/strings/ctype-latin1.c
index 5781013a5e9..4340d0973aa 100644
--- a/strings/ctype-latin1.c
+++ b/strings/ctype-latin1.c
@@ -428,7 +428,7 @@ static int my_strnxfrm_latin1_de(CHARSET_INFO *cs __attribute__((unused)),
return dest - dest_orig;
}
-CHARSET_INFO my_charset_latin1_de =
+CHARSET_INFO my_charset_latin1_german2_ci =
{
31,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-sjis.c b/strings/ctype-sjis.c
index fd911f1867e..058558fa419 100644
--- a/strings/ctype-sjis.c
+++ b/strings/ctype-sjis.c
@@ -4468,7 +4468,7 @@ my_mb_wc_sjis(CHARSET_INFO *cs __attribute__((unused)),
return 2;
}
-CHARSET_INFO my_charset_sjis =
+CHARSET_INFO my_charset_sjis_japanese_ci =
{
13,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-tis620.c b/strings/ctype-tis620.c
index e108ffac6af..9fcecdfdffd 100644
--- a/strings/ctype-tis620.c
+++ b/strings/ctype-tis620.c
@@ -688,7 +688,7 @@ void ThNormalize(uchar* ptr, uint field_length, const uchar* from, uint length)
}
-CHARSET_INFO my_charset_tis620 =
+CHARSET_INFO my_charset_tis620_thai_ci =
{
18,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype-ucs2.c b/strings/ctype-ucs2.c
index d2e75d1de9e..dae0632f754 100644
--- a/strings/ctype-ucs2.c
+++ b/strings/ctype-ucs2.c
@@ -997,10 +997,10 @@ uint my_charpos_ucs2(CHARSET_INFO *cs __attribute__((unused)),
return pos*2;
}
-CHARSET_INFO my_charset_ucs2 =
+CHARSET_INFO my_charset_ucs2_general_ci =
{
35,0,0, /* number */
- MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
+ MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM|MY_CS_UNICODE, /* state */
"ucs2", /* cs name */
"ucs2_general_ci", /* name */
"", /* comment */
diff --git a/strings/ctype-ujis.c b/strings/ctype-ujis.c
index 8a9863f7940..76c69637906 100644
--- a/strings/ctype-ujis.c
+++ b/strings/ctype-ujis.c
@@ -8425,7 +8425,7 @@ my_wc_mb_euc_jp(CHARSET_INFO *c,my_wc_t wc, unsigned char *s, unsigned char *e)
return MY_CS_ILUNI;
}
-CHARSET_INFO my_charset_ujis =
+CHARSET_INFO my_charset_ujis_japanese_ci =
{
12,0,0, /* number */
MY_CS_COMPILED|MY_CS_PRIMARY, /* state */
diff --git a/strings/ctype-utf8.c b/strings/ctype-utf8.c
index e9fc2f6d17d..9f08ca2e169 100644
--- a/strings/ctype-utf8.c
+++ b/strings/ctype-utf8.c
@@ -1950,10 +1950,10 @@ static int my_mbcharlen_utf8(CHARSET_INFO *cs __attribute__((unused)) , uint c)
return 0; /* Illegal mb head */;
}
-CHARSET_INFO my_charset_utf8 =
+CHARSET_INFO my_charset_utf8_general_ci =
{
33,0,0, /* number */
- MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM, /* state */
+ MY_CS_COMPILED|MY_CS_PRIMARY|MY_CS_STRNXFRM|MY_CS_UNICODE, /* state */
"utf8", /* cs name */
"utf8_general_ci", /* name */
"", /* comment */
diff --git a/strings/ctype-win1250ch.c b/strings/ctype-win1250ch.c
index 2769925b54f..87ba58d0553 100644
--- a/strings/ctype-win1250ch.c
+++ b/strings/ctype-win1250ch.c
@@ -640,7 +640,7 @@ static my_bool my_like_range_win1250ch(CHARSET_INFO *cs __attribute__((unused)),
}
-CHARSET_INFO my_charset_win1250ch =
+CHARSET_INFO my_charset_cp1250_czech_ci =
{
34,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM, /* state */
diff --git a/strings/ctype.c b/strings/ctype.c
index 68d9a30048f..ce7bb9ca4a4 100644
--- a/strings/ctype.c
+++ b/strings/ctype.c
@@ -220,6 +220,8 @@ static int cs_value(MY_XML_PARSER *st,const char *attr, uint len)
i->cs.state|= MY_CS_PRIMARY;
else if (!strncmp("binary",attr,len))
i->cs.state|= MY_CS_BINSORT;
+ else if (!strncmp("compiled",attr,len))
+ i->cs.state|= MY_CS_COMPILED;
break;
case _CS_UPPERMAP:
fill_uchar(i->to_upper,MY_CS_TO_UPPER_TABLE_SIZE,attr,len);
View Lorry Controller Status