Adding Roman (classical Latin) collation.

mysql-test/r/ctype_uca.result

@@ -1655,3 +1655,109 @@ Z,z,Ź,ź,Ż,ż,Ž,ž
 ǁ
 ǂ
 ǃ
+select group_concat(c1 order by c1) from t1 group by c1 collate utf8_roman_ci;
+group_concat(c1 order by c1)
+÷
+×
+A,a,À,Á,Â,Ã,Ä,Å,à,á,â,ã,ä,å,Ā,ā,Ă,ă,Ą,ą,Ǎ,ǎ,Ǟ,ǟ,Ǡ,ǡ,Ǻ,ǻ
+AA,Aa,aA,aa
+Æ,æ,Ǣ,ǣ,Ǽ,ǽ
+B,b
+ƀ
+Ɓ
+Ƃ,ƃ
+C,c,Ç,ç,Ć,ć,Ĉ,ĉ,Ċ,ċ,Č,č
+CH,Ch,cH,ch
+Ƈ,ƈ
+D,d,Ď,ď
+DZ,Dz,dZ,dz,DŽ,Dž,dž,DZ,Dz,dz
+Đ,đ
+Ɖ
+Ɗ
+Ƌ,ƌ
+Ð,ð
+E,e,È,É,Ê,Ë,è,é,ê,ë,Ē,ē,Ĕ,ĕ,Ė,ė,Ę,ę,Ě,ě
+Ǝ,ǝ
+Ə
+Ɛ
+F,f
+Ƒ,ƒ
+G,g,Ĝ,ĝ,Ğ,ğ,Ġ,ġ,Ģ,ģ,Ǧ,ǧ,Ǵ,ǵ
+Ǥ,ǥ
+Ɠ
+Ɣ
+Ƣ,ƣ
+H,h,Ĥ,ĥ
+ƕ,Ƕ
+Ħ,ħ
+I,J,i,j,Ì,Í,Î,Ï,ì,í,î,ï,Ĩ,ĩ,Ī,ī,Ĭ,ĭ,Į,į,İ,Ǐ,ǐ
+IJ,Ij,iJ,ij
+IJ,ij
+ı
+Ɨ
+Ɩ
+Ĵ,ĵ,ǰ
+K,k,Ķ,ķ,Ǩ,ǩ
+Ƙ,ƙ
+L,l,Ĺ,ĺ,Ļ,ļ,Ľ,ľ
+Ŀ,ŀ
+LJ,Lj,lJ,lj
+LJ,Lj,lj
+LL,Ll,lL,ll
+Ł,ł
+ƚ
+ƛ
+M,m
+N,n,Ñ,ñ,Ń,ń,Ņ,ņ,Ň,ň,Ǹ,ǹ
+NJ,Nj,nJ,nj
+NJ,Nj,nj
+Ɲ
+ƞ
+Ŋ,ŋ
+O,o,Ò,Ó,Ô,Õ,Ö,ò,ó,ô,õ,ö,Ō,ō,Ŏ,ŏ,Ő,ő,Ơ,ơ,Ǒ,ǒ,Ǫ,ǫ,Ǭ,ǭ
+OE,Oe,oE,oe,Œ,œ
+Ø,ø,Ǿ,ǿ
+Ɔ
+Ɵ
+P,p
+Ƥ,ƥ
+Q,q
+ĸ
+R,r,Ŕ,ŕ,Ŗ,ŗ,Ř,ř
+RR,Rr,rR,rr
+Ʀ
+S,s,Ś,ś,Ŝ,ŝ,Ş,ş,Š,š,ſ
+SS,Ss,sS,ss,ß
+Ʃ
+ƪ
+T,t,Ţ,ţ,Ť,ť
+ƾ
+Ŧ,ŧ
+ƫ
+Ƭ,ƭ
+Ʈ
+U,V,u,v,Ù,Ú,Û,Ü,ù,ú,û,ü,Ũ,ũ,Ū,ū,Ŭ,ŭ,Ů,ů,Ű,ű,Ų,ų,Ư,ư,Ǔ,ǔ,Ǖ,ǖ,Ǘ,ǘ,Ǚ,ǚ,Ǜ,ǜ
+Ɯ
+Ʊ
+Ʋ
+W,w,Ŵ,ŵ
+X,x
+Y,y,Ý,ý,ÿ,Ŷ,ŷ,Ÿ
+Ƴ,ƴ
+Z,z,Ź,ź,Ż,ż,Ž,ž
+ƍ
+Ƶ,ƶ
+Ʒ,Ǯ,ǯ
+Ƹ,ƹ
+ƺ
+Þ,þ
+ƿ,Ƿ
+ƻ
+Ƨ,ƨ
+Ƽ,ƽ
+Ƅ,ƅ
+ʼn
+ǀ
+ǁ
+ǂ
+ǃ

mysql-test/t/ctype_uca.test

@@ -178,4 +178,5 @@ select group_concat(c1 order by c1) from t1 group by c1 collate utf8_danish_ci;
 select group_concat(c1 order by c1) from t1 group by c1 collate utf8_lithuanian_ci;
 --select group_concat(c1 order by c1) from t1 group by c1 collate utf8_slovak_ci;
 select group_concat(c1 order by c1) from t1 group by c1 collate utf8_spanish2_ci;
+select group_concat(c1 order by c1) from t1 group by c1 collate utf8_roman_ci;
 

mysys/charset-def.c

@@ -38,6 +38,7 @@ extern CHARSET_INFO my_charset_ucs2_danish_uca_ci;
 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;
 #endif
 
 #ifdef HAVE_CHARSET_utf8
@@ -56,6 +57,7 @@ extern CHARSET_INFO my_charset_utf8_danish_uca_ci;
 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;
 #endif
 
 my_bool init_compiled_charsets(myf flags __attribute__((unused)))
@@ -124,6 +126,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   add_compiled_collation(&my_charset_ucs2_lithuanian_uca_ci);
   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);
 #endif
 
 #ifdef HAVE_CHARSET_ujis
@@ -149,6 +152,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   add_compiled_collation(&my_charset_utf8_lithuanian_uca_ci);
   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);
 #endif
 
   /* Copy compiled charsets */

strings/ctype-uca.c

@@ -6653,6 +6653,9 @@ static const char spanish2[]=	/* Also good for Asturian and Galician */
     "&N < \\u00F1 <<< \\u00D1"
     "&R << rr <<< Rr <<< RR";
 
+static const char roman[]= /* i.e. Classical Latin */
+    "& I << j <<< J "
+    "& U << v <<< V ";
 
 /*
   Unicode Collation Algorithm:
@@ -8328,6 +8331,34 @@ CHARSET_INFO my_charset_ucs2_spanish2_uca_ci=
     &my_collation_ucs2_uca_handler
 };
 
+
+CHARSET_INFO my_charset_ucs2_roman_uca_ci=
+{
+    143,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "ucs2",		/* cs name    */
+    "ucs2_roman_ci",	/* name         */
+    "",			/* comment      */
+    roman,		/* 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
 
 
@@ -8779,4 +8810,31 @@ CHARSET_INFO my_charset_utf8_spanish2_uca_ci=
     &my_charset_utf8_handler,
     &my_collation_any_uca_handler
 };
+
+CHARSET_INFO my_charset_utf8_roman_uca_ci=
+{
+    207,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "utf8",		/* cs name    */
+    "utf8_roman_ci",	/* name         */
+    "",			/* comment      */
+    roman,		/* 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