Some changes to separate charset and collation terms

include/m_ctype.h

@@ -49,6 +49,7 @@ typedef struct unicase_info_st {
 #define MY_CS_INDEX     4      /* sets listed in the Index file  */
 #define MY_CS_LOADED    8      /* sets that are currently loaded */
 #define MY_CS_BINSORT	16     /* if binary sort order           */
+#define MY_CS_PRIMARY	32     /* if primary collation           */
 
 #define MY_CHARSET_UNDEFINED 0
 #define MY_CHARSET_CURRENT (default_charset_info->number)
@@ -65,6 +66,7 @@ typedef struct charset_info_st
 {
   uint      number;
   uint      state;
+  const char *csname;
   const char *name;
   const char *comment;
   uchar    *ctype;
@@ -127,6 +129,7 @@ typedef struct charset_info_st
   int  (*l10tostr)(struct charset_info_st *, char *to, uint n, int radix, long int val);
   int (*ll10tostr)(struct charset_info_st *, char *to, uint n, int radix, longlong val);
   
+  /* String-to-number convertion routines */
   long        (*strntol)(struct charset_info_st *, const char *s, uint l,char **e, int base);
   ulong      (*strntoul)(struct charset_info_st *, const char *s, uint l, char **e, int base);
   longlong   (*strntoll)(struct charset_info_st *, const char *s, uint l, char **e, int base);

mysys/charset.c

@@ -165,15 +165,24 @@ static int cs_leave(MY_XML_PARSER *st,const char *attr, uint len)
 {
   struct my_cs_file_info *i = (struct my_cs_file_info *)st->user_data;
   struct my_cs_file_section_st *s = cs_file_sec(attr,len);
+  int    state = s ? s->state : 0;
   
-  if (s && (s->state == _CS_COLLATION) && !all_charsets[i->cs.number])
+  if (state == _CS_COLLATION)
   {
-    if (!(all_charsets[i->cs.number]=
+    if (!all_charsets[i->cs.number])
-         (CHARSET_INFO*) my_once_alloc(sizeof(CHARSET_INFO),i->myflags)))
     {
-      return MY_XML_ERROR;
+      if (!(all_charsets[i->cs.number]=
+         (CHARSET_INFO*) my_once_alloc(sizeof(CHARSET_INFO),i->myflags)))
+      {
+        return MY_XML_ERROR;
+      }
+      all_charsets[i->cs.number][0]=i->cs;
     }
-    all_charsets[i->cs.number][0]=i->cs;
+    else
+    {
+      all_charsets[i->cs.number]->state |= i->cs.state;
+    }
+    i->cs.state=0;
   }
   return MY_XML_OK;
 }
@@ -203,6 +212,16 @@ static int cs_value(MY_XML_PARSER *st,const char *attr, uint len)
         ((char*)(i->cs.name))[len]='\0';
       }
       break;
+    case _CS_NAME:
+      if ((i->cs.csname = (char*) my_once_alloc(len+1,i->myflags)))
+      {
+        memcpy((char*)i->cs.csname,attr,len);
+        ((char*)(i->cs.csname))[len]='\0';
+      }
+      break;
+    case _CS_FLAG:
+      if (!strncmp("primary",attr,len))
+        i->cs.state |= MY_CS_PRIMARY;
   }
   return MY_XML_OK;
 }

sql/sql_show.cc

@@ -1362,10 +1362,14 @@ int mysqld_show_charsets(THD *thd, const char *wild)
   List<Item> field_list;
   CHARSET_INFO **cs;
   Protocol *protocol= thd->protocol;
+  char flags[64];
+
   DBUG_ENTER("mysqld_show_charsets");
 
-  field_list.push_back(new Item_empty_string("Name",30));
+  field_list.push_back(new Item_empty_string("CS_Name",30));
+  field_list.push_back(new Item_empty_string("COL_Name",30));
   field_list.push_back(new Item_return_int("Id",11, FIELD_TYPE_SHORT));
+  field_list.push_back(new Item_empty_string("Flags",30));
   field_list.push_back(new Item_return_int("strx_maxlen",3, FIELD_TYPE_TINY));
   field_list.push_back(new Item_return_int("mb_maxlen",3, FIELD_TYPE_TINY));
 
@@ -1374,14 +1378,17 @@ int mysqld_show_charsets(THD *thd, const char *wild)
 
   for (cs=all_charsets ; cs < all_charsets+255 ; cs++ )
   {
-    if (!cs[0])
+    if (cs[0] && !(wild && wild[0] &&
-      continue;
-    if (!(wild && wild[0] &&
 	  wild_case_compare(system_charset_info,cs[0]->name,wild)))
     {
       protocol->prepare_for_resend();
+      protocol->store(cs[0]->csname);
       protocol->store(cs[0]->name);
       protocol->store_short((longlong) cs[0]->number);
+      flags[0]='\0';
+      if (cs[0]->state & MY_CS_PRIMARY)
+        strcat(flags,"pri");
+      protocol->store(flags);
       protocol->store_tiny((longlong) cs[0]->strxfrm_multiply);
       protocol->store_tiny((longlong) cs[0]->mbmaxlen);
       if (protocol->write())

strings/ctype-big5.c

@@ -6219,6 +6219,7 @@ CHARSET_INFO my_charset_big5 =
 {
     1,			/* number     */
     MY_CS_COMPILED,	/* state      */
+    "big5",		/* cs name    */
     "big5",		/* name       */
     "",			/* comment    */
     ctype_big5,

strings/ctype-bin.c

@@ -260,6 +260,7 @@ static CHARSET_INFO my_charset_bin_st =
 {
     63,				/* number        */
     MY_CS_COMPILED|MY_CS_BINSORT,/* state        */
+    "binary",			/* cs name    */
     "binary",			/* name          */
     "",				/* comment       */
     ctype_bin,			/* ctype         */

strings/ctype-czech.c

@@ -597,6 +597,7 @@ CHARSET_INFO my_charset_czech =
 {
     2,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin2",		/* cs name    */
     "czech",		/* name */
     "",			/* comment    */
     ctype_czech,

strings/ctype-euc_kr.c

@@ -8637,6 +8637,7 @@ CHARSET_INFO my_charset_euc_kr =
 {
     19,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "euc_kr",		/* cs name    */
     "euc_kr",		/* name */
     "",			/* comment    */
     ctype_euc_kr,

strings/ctype-gb2312.c

@@ -5687,6 +5687,7 @@ CHARSET_INFO my_charset_gb2312 =
 {
     24,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "gb2312",		/* cs name    */
     "gb2312",		/* name */
     "",			/* comment    */
     ctype_gb2312,

strings/ctype-gbk.c

@@ -9874,6 +9874,7 @@ CHARSET_INFO my_charset_gbk =
 {
     28,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "gbk",		/* cs name    */
     "gbk",		/* name */
     "",			/* comment    */
     ctype_gbk,

strings/ctype-latin1_de.c

@@ -415,6 +415,7 @@ CHARSET_INFO my_charset_latin1_de =
 {
     31,			/* number    */
     MY_CS_COMPILED,	/* state     */
+    "latin1",		/* cs name    */
     "latin1_de",	/* name      */
     "",			/* comment   */
     ctype_latin1_de,

strings/ctype-mb.c

@@ -201,7 +201,7 @@ int my_wildcmp_mb(CHARSET_INFO *cs,
     {						// Found w_many
       uchar cmp;
       const char* mb = wildstr;
-      int mblen;
+      int mblen=0;
       
       wildstr++;
       /* Remove any '%' and '_' from the wild search string */

strings/ctype-sjis.c

@@ -4461,6 +4461,7 @@ CHARSET_INFO my_charset_sjis =
 {
     13,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "sjis",		/* cs name    */
     "sjis",		/* name */
     "",			/* comment    */
     ctype_sjis,

strings/ctype-tis620.c

@@ -689,6 +689,7 @@ CHARSET_INFO my_charset_tis620 =
 {
     18,			/* number    */
     MY_CS_COMPILED,	/* state     */
+    "tis620",		/* cs name    */
     "tis620",		/* name      */
     "",			/* comment   */
     ctype_tis620,

strings/ctype-ujis.c

@@ -8431,6 +8431,7 @@ CHARSET_INFO my_charset_ujis =
 {
     12,			/* number       */
     MY_CS_COMPILED,	/* state        */
+    "ujis",		/* cs name    */
     "ujis",		/* name         */
     "",			/* comment      */
     ctype_ujis,

strings/ctype-utf8.c

@@ -1959,6 +1959,7 @@ CHARSET_INFO my_charset_utf8 =
 {
     33,			/* number       */
     MY_CS_COMPILED,	/* state        */
+    "utf8",		/* cs name      */
     "utf8",		/* name         */
     "",			/* comment      */
     ctype_utf8,		/* ctype        */
@@ -3025,6 +3026,7 @@ CHARSET_INFO my_charset_ucs2 =
 {
     35,			/* number       */
     MY_CS_COMPILED,	/* state        */
+    "ucs2",		/* cs name    */
     "ucs2",		/* name         */
     "",			/* comment      */
     ctype_ucs2,		/* ctype        */

strings/ctype-win1250ch.c

@@ -623,6 +623,7 @@ CHARSET_INFO my_charset_win1250ch =
 {
     34,				/* number    */
     MY_CS_COMPILED,		/* state     */
+    "cp1250",			/* cs name    */
     "win1250ch",		/* name      */
     "",				/* comment   */
     ctype_win1250ch,

strings/ctype.c

@@ -2811,6 +2811,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     8,			/* number     */
     MY_CS_COMPILED,	/* state      */
+    "latin1",		/* cs name    */
     "latin1",		/* name       */
     "",			/* comment    */
     ctype_latin1,
@@ -2856,6 +2857,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     14,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp1251",		/* cs name    */
     "cp1251",		/* name */
     "",			/* comment    */
     ctype_cp1251,
@@ -2900,6 +2902,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     29,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp1257",		/* cs name    */
     "cp1257",		/* name */
     "",			/* comment    */
     ctype_cp1257,
@@ -2944,6 +2947,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     27,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin2",		/* cs name    */
     "croat",		/* name */
     "",			/* comment    */
     ctype_croat,
@@ -2989,6 +2993,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     15,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin1",		/* cs name    */
     "danish",		/* name */
     "",			/* comment    */
     ctype_danish,
@@ -3033,6 +3038,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     3,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "dec8",		/* cs name    */
     "dec8",		/* name */
     "",			/* comment    */
     ctype_dec8,
@@ -3077,6 +3083,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     4,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp850",		/* cs name    */
     "dos",		/* name */
     "",			/* comment    */
     ctype_dos,
@@ -3121,6 +3128,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     20,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin7",		/* cs name    */
     "estonia",		/* name */
     "",			/* comment    */
     ctype_estonia,
@@ -3166,6 +3174,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     5,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin1",		/* cs name    */
     "german1",		/* name */
     "",			/* comment    */
     ctype_german1,
@@ -3210,6 +3219,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     25,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "greek",		/* cs name    */
     "greek",		/* name */
     "",			/* comment    */
     ctype_greek,
@@ -3254,6 +3264,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     16,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "hebrew",		/* cs name    */
     "hebrew",		/* name */
     "",			/* comment    */
     ctype_hebrew,
@@ -3298,6 +3309,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     6,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "hp8",		/* cs name    */
     "hp8",		/* name */
     "",			/* comment    */
     ctype_hp8,
@@ -3342,6 +3354,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     21,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin2",		/* cs name    */
     "hungarian",	/* name */
     "",			/* comment    */
     ctype_hungarian,
@@ -3386,6 +3399,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     7,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "koi8_ru",		/* cs name    */
     "koi8_ru",		/* name */
     "",			/* comment    */
     ctype_koi8_ru,
@@ -3430,6 +3444,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     22,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "koi8_ukr",		/* cs name    */
     "koi8_ukr",		/* name */
     "",			/* comment    */
     ctype_koi8_ukr,
@@ -3475,6 +3490,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     9,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin2",		/* cs name    */
     "latin2",		/* name */
     "",			/* comment    */
     ctype_latin2,
@@ -3519,6 +3535,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     30,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "latin5",		/* cs name    */
     "latin5",		/* name */
     "",			/* comment    */
     ctype_latin5,
@@ -3564,6 +3581,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     10,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "swe7",		/* cs name    */
     "swe7",		/* name */
     "",			/* comment    */
     ctype_swe7,
@@ -3609,6 +3627,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     11,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "ascii",		/* cs name    */
     "usa7",		/* name */
     "",			/* comment    */
     ctype_usa7,
@@ -3653,6 +3672,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     26,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp1250",		/* cs name    */
     "win1250",		/* name */
     "",			/* comment    */
     ctype_win1250,
@@ -3697,6 +3717,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     23,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp1251",		/* cs name    */
     "win1251ukr",	/* name */
     "",			/* comment    */
     ctype_win1251ukr,
@@ -3741,6 +3762,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     32,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "armscii8",		/* cs name    */
     "armscii8",		/* name */
     "",			/* comment    */
     ctype_armscii8,
@@ -3785,6 +3807,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     17,			/* number */
     MY_CS_COMPILED,	/* state      */
+    "cp1251",		/* cs name    */
     "win1251",		/* name */
     "",			/* comment    */
     ctype_win1251,
@@ -3828,6 +3851,7 @@ static CHARSET_INFO compiled_charsets[] = {
   {
     0,			/* end-of-list marker */
     0,			/* state      */
+    NullS,		/* cs name    */
     NullS,		/* name       */
     NullS,		/* comment    */
     NULL,