Persian collation, contibuted by Jody McIntyre

configure.in

@@ -2715,7 +2715,7 @@ case $default_charset in
       define(UCSC2, ucs2_czech_ci ucs2_danish_ci)
       define(UCSC3, ucs2_estonian_ci ucs2_icelandic_ci)
       define(UCSC4, ucs2_latvian_ci ucs2_lithuanian_ci)
-      define(UCSC5, ucs2_polish_ci ucs2_romanian_ci)
+      define(UCSC5, ucs2_persian_ci ucs2_polish_ci ucs2_romanian_ci)
       define(UCSC6, ucs2_slovak_ci ucs2_slovenian_ci)
       define(UCSC7, ucs2_spanish2_ci ucs2_spanish_ci)
       define(UCSC8, ucs2_swedish_ci ucs2_turkish_ci)
@@ -2733,7 +2733,7 @@ case $default_charset in
       define(UTFC2, utf8_czech_ci utf8_danish_ci)
       define(UTFC3, utf8_estonian_ci utf8_icelandic_ci)
       define(UTFC4, utf8_latvian_ci utf8_lithuanian_ci)
-      define(UTFC5, utf8_polish_ci utf8_romanian_ci)
+      define(UTFC5, utf8_persian_ci utf8_polish_ci utf8_romanian_ci)
       define(UTFC6, utf8_slovak_ci utf8_slovenian_ci)
       define(UTFC7, utf8_spanish2_ci utf8_spanish_ci)
       define(UTFC8, utf8_swedish_ci utf8_turkish_ci)

mysys/charset-def.c

@@ -39,6 +39,7 @@ extern CHARSET_INFO my_charset_ucs2_lithuanian_uca_ci;
 extern CHARSET_INFO my_charset_ucs2_slovak_uca_ci;
 extern CHARSET_INFO my_charset_ucs2_spanish2_uca_ci;
 extern CHARSET_INFO my_charset_ucs2_roman_uca_ci;
+extern CHARSET_INFO my_charset_ucs2_persian_uca_ci;
 #endif
 
 #ifdef HAVE_CHARSET_utf8
@@ -58,6 +59,7 @@ extern CHARSET_INFO my_charset_utf8_lithuanian_uca_ci;
 extern CHARSET_INFO my_charset_utf8_slovak_uca_ci;
 extern CHARSET_INFO my_charset_utf8_spanish2_uca_ci;
 extern CHARSET_INFO my_charset_utf8_roman_uca_ci;
+extern CHARSET_INFO my_charset_utf8_persian_uca_ci;
 #endif
 
 my_bool init_compiled_charsets(myf flags __attribute__((unused)))
@@ -127,6 +129,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   add_compiled_collation(&my_charset_ucs2_slovak_uca_ci);
   add_compiled_collation(&my_charset_ucs2_spanish2_uca_ci);
   add_compiled_collation(&my_charset_ucs2_roman_uca_ci);
+  add_compiled_collation(&my_charset_ucs2_persian_uca_ci);
 #endif
 
 #ifdef HAVE_CHARSET_ujis
@@ -153,6 +156,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   add_compiled_collation(&my_charset_utf8_slovak_uca_ci);
   add_compiled_collation(&my_charset_utf8_spanish2_uca_ci);
   add_compiled_collation(&my_charset_utf8_roman_uca_ci);
+  add_compiled_collation(&my_charset_utf8_persian_uca_ci);
 #endif
 
   /* Copy compiled charsets */

strings/ctype-uca.c

@@ -6657,6 +6657,42 @@ static const char roman[]= /* i.e. Classical Latin */
     "& I << j <<< J "
     "& V << u <<< U ";
 
+/*
+  Persian collation support was provided by 
+  Jody McIntyre <mysql@modernduck.com>
+  
+  To: internals@lists.mysql.com
+  Subject: Persian UTF8 collation support
+  Date: 17.08.2004
+  
+  Contraction is not implemented.  Some implementations do perform
+  contraction but others do not, and it is able to sort all my test
+  strings correctly.
+  
+  Jody.
+*/
+static const char persian[]=
+    "& \\u066D < \\u064E < \\uFE76 < \\uFE77 < \\u0650 < \\uFE7A < \\uFE7B"
+             " < \\u064F < \\uFE78 < \\uFE79 < \\u064B < \\uFE70 < \\uFE71"
+             " < \\u064D < \\uFE74 < \\u064C < \\uFE72"
+    "& \\uFE7F < \\u0653 < \\u0654 < \\u0655 < \\u0670"
+    "& \\u0669 < \\u0622 < \\u0627 < \\u0671 < \\u0621 < \\u0623 < \\u0625"
+             " < \\u0624 < \\u0626"
+    "& \\u0642 < \\u06A9 < \\u0643"
+    "& \\u0648 < \\u0647 < \\u0629 < \\u06C0 < \\u06CC < \\u0649 < \\u064A"
+    "& \\uFE80 < \\uFE81 < \\uFE82 < \\uFE8D < \\uFE8E < \\uFB50 < \\uFB51"
+             " < \\uFE80 < \\uFE83 < \\uFE84 < \\uFE87 < \\uFE88 < \\uFE85"
+             " < \\uFE86 < \\u0689 < \\u068A"
+    "& \\uFEAE < \\uFDFC"
+    "& \\uFED8 < \\uFB8E < \\uFB8F < \\uFB90 < \\uFB91 < \\uFED9 < \\uFEDA"
+             " < \\uFEDB < \\uFEDC"
+    "& \\uFEEE < \\uFEE9 < \\uFEEA < \\uFEEB < \\uFEEC < \\uFE93 < \\uFE94"
+             " < \\uFBA4 < \\uFBA5 < \\uFBFC < \\uFBFD < \\uFBFE < \\uFBFF"
+             " < \\uFEEF < \\uFEF0 < \\uFEF1 < \\uFEF2 < \\uFEF3 < \\uFEF4"
+             " < \\uFEF5 < \\uFEF6 < \\uFEF7 < \\uFEF8 < \\uFEF9 < \\uFEFA"
+             " < \\uFEFB < \\uFEFC";
+
+
 /*
   Unicode Collation Algorithm:
   Collation element (weight) scanner, 
@@ -7671,7 +7707,7 @@ static int my_coll_rule_parse(MY_COLL_RULE *rule, size_t mitems,
   return (size_t) nitems;
 }
 
-#define MY_MAX_COLL_RULE 64
+#define MY_MAX_COLL_RULE 128
 
 /*
   This function copies an UCS2 collation from
@@ -8360,6 +8396,35 @@ CHARSET_INFO my_charset_ucs2_roman_uca_ci=
     &my_collation_ucs2_uca_handler
 };
 
+
+CHARSET_INFO my_charset_ucs2_persian_uca_ci=
+{
+    144,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "ucs2",		/* cs name    */
+    "ucs2_persian_ci",	/* name         */
+    "",			/* comment      */
+    persian,		/* tailoring    */
+    NULL,		/* ctype        */
+    NULL,		/* to_lower     */
+    NULL,		/* to_upper     */
+    NULL,		/* sort_order   */
+    NULL,		/* contractions */
+    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
 
 
@@ -8838,4 +8903,32 @@ CHARSET_INFO my_charset_utf8_roman_uca_ci=
     &my_charset_utf8_handler,
     &my_collation_any_uca_handler
 };
+
+CHARSET_INFO my_charset_utf8_persian_uca_ci=
+{
+    208,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "utf8",		/* cs name    */
+    "utf8_persian_ci",	/* name         */
+    "",			/* comment      */
+    persian,		/* tailoring    */
+    ctype_utf8,		/* ctype        */
+    NULL,		/* to_lower     */
+    NULL,		/* to_upper     */
+    NULL,		/* sort_order   */
+    NULL,		/* contractions */
+    NULL,		/* sort_order_big*/
+    NULL,		/* tab_to_uni   */
+    NULL,		/* tab_from_uni */
+    NULL,		/* state_map    */
+    NULL,		/* ident_map    */
+    8,			/* strxfrm_multiply */
+    1,			/* mbminlen     */
+    2,			/* mbmaxlen     */
+    9,			/* min_sort_char */
+    0xFFFF,		/* max_sort_char */
+    &my_charset_utf8_handler,
+    &my_collation_any_uca_handler
+};
+
 #endif