static my_bool init_state_maps(CHARSET_INFO *cs)
{
uint i;
uchar *state_map;
uchar *ident_map;
if (!(cs->state_map= state_map= (uchar*) my_once_alloc(256, MYF(MY_WME))))
return 1;
if (!(cs->ident_map= ident_map= (uchar*) my_once_alloc(256, MYF(MY_WME))))
return 1;
/* Fill state_map with states to get a faster parser */
for (i=0; i < 256 ; i++)
{
if (my_isalpha(cs,i))
state_map[i]=(uchar) MY_LEX_IDENT;
else if (my_isdigit(cs,i))
state_map[i]=(uchar) MY_LEX_NUMBER_IDENT;
else if (my_ismb1st(cs, i))
/* To get whether it's a possible leading byte for a charset. */
state_map[i]=(uchar) MY_LEX_IDENT;
else if (my_isspace(cs,i))
state_map[i]=(uchar) MY_LEX_SKIP;
else
state_map[i]=(uchar) MY_LEX_CHAR;
}
state_map[(uchar)'_']=state_map[(uchar)'$']=(uchar) MY_LEX_IDENT;
state_map[(uchar)'\'']=(uchar) MY_LEX_STRING;
state_map[(uchar)'.']=(uchar) MY_LEX_REAL_OR_POINT;
state_map[(uchar)'>']=state_map[(uchar)'=']=state_map[(uchar)'!']= (uchar) MY_LEX_CMP_OP;
state_map[(uchar)'<']= (uchar) MY_LEX_LONG_CMP_OP;
state_map[(uchar)'&']=state_map[(uchar)'|']=(uchar) MY_LEX_BOOL;
state_map[(uchar)'#']=(uchar) MY_LEX_COMMENT;
state_map[(uchar)';']=(uchar) MY_LEX_SEMICOLON;
state_map[(uchar)':']=(uchar) MY_LEX_SET_VAR;
state_map[0]=(uchar) MY_LEX_EOL;
state_map[(uchar)'\\']= (uchar) MY_LEX_ESCAPE;
state_map[(uchar)'/']= (uchar) MY_LEX_LONG_COMMENT;
state_map[(uchar)'*']= (uchar) MY_LEX_END_LONG_COMMENT;
state_map[(uchar)'@']= (uchar) MY_LEX_USER_END;
state_map[(uchar) '`']= (uchar) MY_LEX_USER_VARIABLE_DELIMITER;
state_map[(uchar)'"']= (uchar) MY_LEX_STRING_OR_DELIMITER;
/*
Create a second map to make it faster to find identifiers
*/
for (i=0; i < 256 ; i++)
{
ident_map[i]= (uchar) (state_map[i] == MY_LEX_IDENT ||
state_map[i] == MY_LEX_NUMBER_IDENT);
}
/* Special handling of hex and binary strings */
state_map[(uchar)'x']= state_map[(uchar)'X']= (uchar) MY_LEX_IDENT_OR_HEX;
state_map[(uchar)'b']= state_map[(uchar)'B']= (uchar) MY_LEX_IDENT_OR_BIN;
state_map[(uchar)'n']= state_map[(uchar)'N']= (uchar) MY_LEX_IDENT_OR_NCHAR;
return 0;
}
void *my_once_memdup(const void *src, size_t len, myf myflags)
{
uchar *dst= my_once_alloc(len, myflags);
if (dst)
memcpy(dst, src, len);
return dst;
}
char *my_once_strdup(const char *src,myf myflags)
{
size_t len= strlen(src)+1;
uchar *dst= my_once_alloc(len, myflags);
if (dst)
memcpy(dst, src, len);
return (char*) dst;
}
static void *cs_alloc(size_t size)
{
return my_once_alloc(size, MYF(MY_WME));
}
static int add_collation(CHARSET_INFO *cs)
{
if (cs->name && (cs->number ||
(cs->number=get_collation_number_internal(cs->name))) &&
cs->number < array_elements(all_charsets))
{
if (!all_charsets[cs->number])
{
if (!(all_charsets[cs->number]=
(CHARSET_INFO*) my_once_alloc(sizeof(CHARSET_INFO),MYF(0))))
return MY_XML_ERROR;
bzero((void*)all_charsets[cs->number],sizeof(CHARSET_INFO));
}
if (cs->primary_number == cs->number)
cs->state |= MY_CS_PRIMARY;
if (cs->binary_number == cs->number)
cs->state |= MY_CS_BINSORT;
all_charsets[cs->number]->state|= cs->state;
if (!(all_charsets[cs->number]->state & MY_CS_COMPILED))
{
CHARSET_INFO *newcs= all_charsets[cs->number];
if (cs_copy_data(all_charsets[cs->number],cs))
return MY_XML_ERROR;
newcs->caseup_multiply= newcs->casedn_multiply= 1;
if (!strcmp(cs->csname,"ucs2") )
{
#if defined(HAVE_CHARSET_ucs2) && defined(HAVE_UCA_COLLATIONS)
copy_uca_collation(newcs, &my_charset_ucs2_unicode_ci);
newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED | MY_CS_NONASCII;
#endif
}
else if (!strcmp(cs->csname, "utf8") || !strcmp(cs->csname, "utf8mb3"))
{
#if defined (HAVE_CHARSET_utf8) && defined(HAVE_UCA_COLLATIONS)
copy_uca_collation(newcs, &my_charset_utf8_unicode_ci);
newcs->ctype= my_charset_utf8_unicode_ci.ctype;
if (init_state_maps(newcs))
return MY_XML_ERROR;
#endif
}
else if (!strcmp(cs->csname, "utf8mb4"))
{
#if defined (HAVE_CHARSET_utf8mb4) && defined(HAVE_UCA_COLLATIONS)
copy_uca_collation(newcs, &my_charset_utf8mb4_unicode_ci);
newcs->ctype= my_charset_utf8mb4_unicode_ci.ctype;
newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED;
#endif
}
else if (!strcmp(cs->csname, "utf16"))
{
#if defined (HAVE_CHARSET_utf16) && defined(HAVE_UCA_COLLATIONS)
copy_uca_collation(newcs, &my_charset_utf16_unicode_ci);
newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED | MY_CS_NONASCII;
#endif
}
else if (!strcmp(cs->csname, "utf32"))
{
#if defined (HAVE_CHARSET_utf32) && defined(HAVE_UCA_COLLATIONS)
copy_uca_collation(newcs, &my_charset_utf32_unicode_ci);
newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED | MY_CS_NONASCII;
#endif
}
else
{
uchar *sort_order= all_charsets[cs->number]->sort_order;
simple_cs_init_functions(all_charsets[cs->number]);
newcs->mbminlen= 1;
newcs->mbmaxlen= 1;
if (simple_cs_is_full(all_charsets[cs->number]))
{
all_charsets[cs->number]->state |= MY_CS_LOADED;
}
all_charsets[cs->number]->state|= MY_CS_AVAILABLE;
/*
Check if case sensitive sort order: A < a < B.
We need MY_CS_FLAG for regex library, and for
case sensitivity flag for 5.0 client protocol,
to support isCaseSensitive() method in JDBC driver
*/
if (sort_order && sort_order['A'] < sort_order['a'] &&
sort_order['a'] < sort_order['B'])
all_charsets[cs->number]->state|= MY_CS_CSSORT;
if (my_charset_is_8bit_pure_ascii(all_charsets[cs->number]))
all_charsets[cs->number]->state|= MY_CS_PUREASCII;
if (!my_charset_is_ascii_compatible(cs))
all_charsets[cs->number]->state|= MY_CS_NONASCII;
}
}
else
{
/*
We need the below to make get_charset_name()
and get_charset_number() working even if a
character set has not been really incompiled.
The above functions are used for example
in error message compiler extra/comp_err.c.
If a character set was compiled, this information
will get lost and overwritten in add_compiled_collation().
*/
CHARSET_INFO *dst= all_charsets[cs->number];
dst->number= cs->number;
if (cs->comment)
if (!(dst->comment= my_once_strdup(cs->comment,MYF(MY_WME))))
return MY_XML_ERROR;
if (cs->csname)
if (!(dst->csname= my_once_strdup(cs->csname,MYF(MY_WME))))
return MY_XML_ERROR;
if (cs->name)
if (!(dst->name= my_once_strdup(cs->name,MYF(MY_WME))))
return MY_XML_ERROR;
}
cs->number= 0;
cs->primary_number= 0;
cs->binary_number= 0;
cs->name= NULL;
cs->state= 0;
cs->sort_order= NULL;
cs->state= 0;
}
return MY_XML_OK;
}
