Skip to content

M
MariaDB
Commit 9155e8de authored by unknown's avatar unknown
Browse files
Options

Move UCA language specific definitions into ctype-ucs.c.

parent da7b7d55
Show whitespace changes
Inline Side-by-side
Showing with 356 additions and 144 deletions
mysys/charset-def.c
View file @ 9155e8de
...@@ -22,6 +22,19 @@ ...@@ -22,6 +22,19 @@
init_compiled_charsets() that only adds those that he wants init_compiled_charsets() that only adds those that he wants
*/ */
#ifdef HAVE_CHARSET_ucs2
extern CHARSET_INFO my_charset_ucs2_general_uca;
extern CHARSET_INFO my_charset_ucs2_icelandic_uca_ci;
extern CHARSET_INFO my_charset_ucs2_latvian_uca_ci;
extern CHARSET_INFO my_charset_ucs2_romanian_uca_ci;
extern CHARSET_INFO my_charset_ucs2_slovenian_uca_ci;
extern CHARSET_INFO my_charset_ucs2_polish_uca_ci;
extern CHARSET_INFO my_charset_ucs2_estonian_uca_ci;
extern CHARSET_INFO my_charset_ucs2_spanish_uca_ci;
extern CHARSET_INFO my_charset_ucs2_swedish_uca_ci;
extern CHARSET_INFO my_charset_ucs2_turkish_uca_ci;
#endif
my_bool init_compiled_charsets(myf flags __attribute__((unused))) my_bool init_compiled_charsets(myf flags __attribute__((unused)))
{ {
CHARSET_INFO *cs; CHARSET_INFO *cs;
...@@ -74,6 +87,16 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused))) ...@@ -74,6 +87,16 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
add_compiled_collation(&my_charset_ucs2_general_ci); add_compiled_collation(&my_charset_ucs2_general_ci);
add_compiled_collation(&my_charset_ucs2_bin); add_compiled_collation(&my_charset_ucs2_bin);
add_compiled_collation(&my_charset_ucs2_general_uca); add_compiled_collation(&my_charset_ucs2_general_uca);
add_compiled_collation(&my_charset_ucs2_general_uca);
add_compiled_collation(&my_charset_ucs2_icelandic_uca_ci);
add_compiled_collation(&my_charset_ucs2_latvian_uca_ci);
add_compiled_collation(&my_charset_ucs2_romanian_uca_ci);
add_compiled_collation(&my_charset_ucs2_slovenian_uca_ci);
add_compiled_collation(&my_charset_ucs2_polish_uca_ci);
add_compiled_collation(&my_charset_ucs2_estonian_uca_ci);
add_compiled_collation(&my_charset_ucs2_spanish_uca_ci);
add_compiled_collation(&my_charset_ucs2_swedish_uca_ci);
add_compiled_collation(&my_charset_ucs2_turkish_uca_ci);
#endif #endif
#ifdef HAVE_CHARSET_ujis #ifdef HAVE_CHARSET_ujis
......
mysys/charset.c
View file @ 9155e8de
...@@ -177,127 +177,6 @@ static int cs_copy_data(CHARSET_INFO *to, CHARSET_INFO *from) ...@@ -177,127 +177,6 @@ static int cs_copy_data(CHARSET_INFO *to, CHARSET_INFO *from)
} }
#ifdef HAVE_CHARSET_ucs2
typedef struct my_tailoring_st
{
uint number;
const char *name;
const char *tailoring;
} my_tailoring;
static my_tailoring tailoring[]=
{
{
0, "icelandic",
/*
Some sources treat LETTER A WITH DIARESIS (00E4,00C4)
secondary greater than LETTER AE (00E6,00C6).
http://www.evertype.com/alphabets/icelandic.pdf
http://developer.mimer.com/collations/charts/icelandic.htm
Other sources do not provide any special rules
for LETTER A WITH DIARESIS:
http://www.omniglot.com/writing/icelandic.htm
http://en.wikipedia.org/wiki/Icelandic_alphabet
http://oss.software.ibm.com/icu/charts/collation/is.html
Let's go the first way.
*/
"& A < \\u00E1 <<< \\u00C1 "
"& D < \\u00F0 <<< \\u00D0 "
"& E < \\u00E9 <<< \\u00C9 "
"& I < \\u00ED <<< \\u00CD "
"& O < \\u00F3 <<< \\u00D3 "
"& U < \\u00FA <<< \\u00DA "
"& Y < \\u00FD <<< \\u00DD "
"& Z < \\u00FE <<< \\u00DE "
"< \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4 "
"< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "
"< \\u00E5 <<< \\u00C5 "
},
{
1, "latvian",
/*
Some sources treat I and Y primary different.
Other sources treat I and Y the same on primary level.
We'll go the first way.
*/
"& C < \\u010D <<< \\u010C "
"& G < \\u0123 <<< \\u0122 "
"& I < \\u0079 <<< \\u0059 "
"& K < \\u0137 <<< \\u0136 "
"& L < \\u013C <<< \\u013B "
"& N < \\u0146 <<< \\u0145 "
"& R < \\u0157 <<< \\u0156 "
"& S < \\u0161 <<< \\u0160 "
"& Z < \\u017E <<< \\u017D "
},
{
2, "romanian",
"& A < \\u0103 <<< \\u0102 < \\u00E2 <<< \\u00C2 "
"& I < \\u00EE <<< \\u00CE "
"& S < \\u0219 <<< \\u0218 << \\u015F <<< \\u015E "
"& T < \\u021B <<< \\u021A << \\u0163 <<< \\u0162 "
},
{
3, "slovenian",
"& C < \\u010D <<< \\u010C "
"& S < \\u0161 <<< \\u0160 "
"& Z < \\u017E <<< \\u017D "
},
{
4, "polish",
"& A < \\u0105 <<< \\u0104 "
"& C < \\u0107 <<< \\u0106 "
"& E < \\u0119 <<< \\u0118 "
"& L < \\u0142 <<< \\u0141 "
"& N < \\u0144 <<< \\u0143 "
"& O < \\u00F3 <<< \\u00D3 "
"& S < \\u015B <<< \\u015A "
"& Z < \\u017A <<< \\u017B "
},
{
5, "estonian",
"& S < \\u0161 <<< \\u0160 "
" < \\u007A <<< \\u005A "
" < \\u017E <<< \\u017D "
"& W < \\u00F5 <<< \\u00D5 "
"< \\u00E4 <<< \\u00C4 "
"< \\u00F6 <<< \\u00D6 "
"< \\u00FC <<< \\u00DC "
},
{
6, "spanish",
"& N < \\u00F1 <<< \\u00D1 "
},
{
7, "swedish",
/*
Some sources treat V and W as similar on primary level.
We'll treat V and W as different on primary level.
*/
"& Y <<\\u00FC <<< \\u00DC "
"& Z < \\u00E5 <<< \\u00C5 "
"< \\u00E4 <<< \\u00C4 << \\u00E6 <<< \\u00C6 "
"< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "
},
{
8, "turkish",
"& C < \\u00E7 <<< \\u00C7 "
"& G < \\u011F <<< \\u011E "
"& H < \\u0131 <<< \\u0049 "
"& O < \\u00F6 <<< \\u00D6 "
"& S < \\u015F <<< \\u015E "
"& U < \\u00FC <<< \\u00DC "
},
{
0, NULL, NULL
}
};
#endif
static my_bool simple_cs_is_full(CHARSET_INFO *cs) static my_bool simple_cs_is_full(CHARSET_INFO *cs)
{ {
...@@ -393,25 +272,6 @@ static int add_collation(CHARSET_INFO *cs) ...@@ -393,25 +272,6 @@ static int add_collation(CHARSET_INFO *cs)
return MY_XML_OK; return MY_XML_OK;
} }
#ifdef HAVE_CHARSET_ucs2
static my_bool init_uca_charsets()
{
my_tailoring *t;
CHARSET_INFO cs= my_charset_ucs2_general_uca;
char name[64];
cs.state= MY_CS_STRNXFRM|MY_CS_UNICODE;
for (t= tailoring; t->tailoring; t++)
{
cs.number= 128 + t->number;
cs.tailoring= t->tailoring;
cs.name= name;
sprintf(name, "ucs2_%s_ci", t->name);
add_collation(&cs);
}
return 0;
}
#endif
#define MY_MAX_ALLOWED_BUF 1024*1024 #define MY_MAX_ALLOWED_BUF 1024*1024
#define MY_CHARSET_INDEX "Index.xml" #define MY_CHARSET_INDEX "Index.xml"
...@@ -515,9 +375,6 @@ static my_bool init_available_charsets(myf myflags) ...@@ -515,9 +375,6 @@ static my_bool init_available_charsets(myf myflags)
bzero(&all_charsets,sizeof(all_charsets)); bzero(&all_charsets,sizeof(all_charsets));
init_compiled_charsets(myflags); init_compiled_charsets(myflags);
#ifdef HAVE_CHARSET_ucs2
init_uca_charsets();
#endif
/* Copy compiled charsets */ /* Copy compiled charsets */
for (cs=all_charsets; for (cs=all_charsets;
......
strings/ctype-uca.c
View file @ 9155e8de
...@@ -6521,6 +6521,104 @@ NULL ,page0F9data,page0FAdata,page0FBdata, ...@@ -6521,6 +6521,104 @@ NULL ,page0F9data,page0FAdata,page0FBdata,
page0FCdata,page0FDdata,page0FEdata,page0FFdata page0FCdata,page0FDdata,page0FEdata,page0FFdata
}; };
/*
Some sources treat LETTER A WITH DIARESIS (00E4,00C4)
secondary greater than LETTER AE (00E6,00C6).
http://www.evertype.com/alphabets/icelandic.pdf
http://developer.mimer.com/collations/charts/icelandic.htm
Other sources do not provide any special rules
for LETTER A WITH DIARESIS:
http://www.omniglot.com/writing/icelandic.htm
http://en.wikipedia.org/wiki/Icelandic_alphabet
http://oss.software.ibm.com/icu/charts/collation/is.html
Let's go the first way.
*/
static const char icelandic[]=
"& A < \\u00E1 <<< \\u00C1 "
"& D < \\u00F0 <<< \\u00D0 "
"& E < \\u00E9 <<< \\u00C9 "
"& I < \\u00ED <<< \\u00CD "
"& O < \\u00F3 <<< \\u00D3 "
"& U < \\u00FA <<< \\u00DA "
"& Y < \\u00FD <<< \\u00DD "
"& Z < \\u00FE <<< \\u00DE "
"< \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4 "
"< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "
"< \\u00E5 <<< \\u00C5 ";
/*
Some sources treat I and Y primary different.
Other sources treat I and Y the same on primary level.
We'll go the first way.
*/
static const char latvian[]=
"& C < \\u010D <<< \\u010C "
"& G < \\u0123 <<< \\u0122 "
"& I < \\u0079 <<< \\u0059 "
"& K < \\u0137 <<< \\u0136 "
"& L < \\u013C <<< \\u013B "
"& N < \\u0146 <<< \\u0145 "
"& R < \\u0157 <<< \\u0156 "
"& S < \\u0161 <<< \\u0160 "
"& Z < \\u017E <<< \\u017D ";
static const char romanian[]=
"& A < \\u0103 <<< \\u0102 < \\u00E2 <<< \\u00C2 "
"& I < \\u00EE <<< \\u00CE "
"& S < \\u0219 <<< \\u0218 << \\u015F <<< \\u015E "
"& T < \\u021B <<< \\u021A << \\u0163 <<< \\u0162 ";
static const char slovenian[]=
"& C < \\u010D <<< \\u010C "
"& S < \\u0161 <<< \\u0160 "
"& Z < \\u017E <<< \\u017D ";
static const char polish[]=
"& A < \\u0105 <<< \\u0104 "
"& C < \\u0107 <<< \\u0106 "
"& E < \\u0119 <<< \\u0118 "
"& L < \\u0142 <<< \\u0141 "
"& N < \\u0144 <<< \\u0143 "
"& O < \\u00F3 <<< \\u00D3 "
"& S < \\u015B <<< \\u015A "
"& Z < \\u017A <<< \\u017B ";
static const char estonian[]=
"& S < \\u0161 <<< \\u0160 "
" < \\u007A <<< \\u005A "
" < \\u017E <<< \\u017D "
"& W < \\u00F5 <<< \\u00D5 "
"< \\u00E4 <<< \\u00C4 "
"< \\u00F6 <<< \\u00D6 "
"< \\u00FC <<< \\u00DC ";
static const char spanish[]= "& N < \\u00F1 <<< \\u00D1 ";
/*
Some sources treat V and W as similar on primary level.
We'll treat V and W as different on primary level.
*/
static const char swedish[]=
"& Y <<\\u00FC <<< \\u00DC "
"& Z < \\u00E5 <<< \\u00C5 "
"< \\u00E4 <<< \\u00C4 << \\u00E6 <<< \\u00C6 "
"< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 ";
static const char turkish[]=
"& C < \\u00E7 <<< \\u00C7 "
"& G < \\u011F <<< \\u011E "
"& H < \\u0131 <<< \\u0049 "
"& O < \\u00F6 <<< \\u00D6 "
"& S < \\u015F <<< \\u015E "
"& U < \\u00FC <<< \\u00DC ";
/* /*
Unicode Collation Algorithm: Unicode Collation Algorithm:
...@@ -7509,7 +7607,7 @@ CHARSET_INFO my_charset_ucs2_general_uca= ...@@ -7509,7 +7607,7 @@ CHARSET_INFO my_charset_ucs2_general_uca=
45,0,0, /* number */ 45,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE, MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */ "ucs2", /* cs name */
"ucs2_general_uca", /* name */ "ucs2_uca_ci", /* name */
"", /* comment */ "", /* comment */
NULL, /* tailoring */ NULL, /* tailoring */
NULL, /* ctype */ NULL, /* ctype */
...@@ -7531,4 +7629,238 @@ CHARSET_INFO my_charset_ucs2_general_uca= ...@@ -7531,4 +7629,238 @@ CHARSET_INFO my_charset_ucs2_general_uca=
}; };
CHARSET_INFO my_charset_ucs2_icelandic_uca_ci=
{
128,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_icelandic_ci",/* name */
"", /* comment */
icelandic, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_latvian_uca_ci=
{
129,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_latvian_ci", /* name */
"", /* comment */
latvian, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_romanian_uca_ci=
{
130,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_romanian_ci", /* name */
"", /* comment */
romanian, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_slovenian_uca_ci=
{
131,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_slovenian_ci",/* name */
"", /* comment */
slovenian, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_polish_uca_ci=
{
132,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_polish_ci", /* name */
"", /* comment */
polish, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_estonian_uca_ci=
{
133,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_estonian_ci", /* name */
"", /* comment */
estonian, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_spanish_uca_ci=
{
134,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_spanish_ci", /* name */
"", /* comment */
spanish, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_swedish_uca_ci=
{
135,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_swedish_ci", /* name */
"", /* comment */
swedish, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
CHARSET_INFO my_charset_ucs2_turkish_uca_ci=
{
136,0,0, /* number */
MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
"ucs2", /* cs name */
"ucs2_turkish_ci", /* name */
"", /* comment */
turkish, /* tailoring */
NULL, /* ctype */
NULL, /* to_lower */
NULL, /* to_upper */
NULL, /* sort_order */
NULL, /* sort_order_big*/
NULL, /* tab_to_uni */
NULL, /* tab_from_uni */
NULL, /* state_map */
NULL, /* ident_map */
8, /* strxfrm_multiply */
2, /* mbminlen */
2, /* mbmaxlen */
9, /* min_sort_char */
0xFFFF, /* max_sort_char */
&my_charset_ucs2_handler,
&my_collation_ucs2_uca_handler
};
#endif #endif
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7