Many files:

  Adding esperanto collation

5 files changed, 192 insertions, 2 deletions

diff --git a/config/ac-macros/character_sets.m4 b/config/ac-macros/character_sets.m4
index 3ecc4bb5a03..1ab6e7dd780 100644
--- a/config/ac-macros/character_sets.m4
+++ b/config/ac-macros/character_sets.m4
@@ -343,7 +343,7 @@ case $default_charset in
       default_charset_default_collation="ucs2_general_ci"
       define(UCSC1, ucs2_general_ci ucs2_bin)
       define(UCSC2, ucs2_czech_ci ucs2_danish_ci)
-      define(UCSC3, ucs2_estonian_ci ucs2_icelandic_ci)
+      define(UCSC3, ucs2_esperanto_ci ucs2_estonian_ci ucs2_icelandic_ci)
       define(UCSC4, ucs2_latvian_ci ucs2_lithuanian_ci)
       define(UCSC5, ucs2_persian_ci ucs2_polish_ci ucs2_romanian_ci)
       define(UCSC6, ucs2_slovak_ci ucs2_slovenian_ci)
@@ -367,7 +367,7 @@ case $default_charset in
       else
         define(UTFC1, utf8_general_ci utf8_bin)
         define(UTFC2, utf8_czech_ci utf8_danish_ci)
-        define(UTFC3, utf8_estonian_ci utf8_icelandic_ci)
+        define(UTFC3, utf8_esperanto_ci utf8_estonian_ci utf8_icelandic_ci)
         define(UTFC4, utf8_latvian_ci utf8_lithuanian_ci)
         define(UTFC5, utf8_persian_ci utf8_polish_ci utf8_romanian_ci)
         define(UTFC6, utf8_slovak_ci utf8_slovenian_ci)
diff --git a/mysql-test/r/ctype_uca.result b/mysql-test/r/ctype_uca.result
index 3803dd932d7..e2805e41f3a 100644
--- a/mysql-test/r/ctype_uca.result
+++ b/mysql-test/r/ctype_uca.result
@@ -1905,6 +1905,116 @@ 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_esperanto_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,Ċ,ċ,Č,č
+CH,Ch,cH,ch
+Ĉ,ĉ
+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,Ğ,ğ,Ġ,ġ,Ģ,ģ,Ǧ,ǧ,Ǵ,ǵ
+Ĝ,ĝ
+Ǥ,ǥ
+Ɠ
+Ɣ
+Ƣ,ƣ
+H,h
+Ĥ,ĥ
+ƕ,Ƕ
+Ħ,ħ
+I,i,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
+J,j,ǰ
+Ĵ,ĵ
+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,Ş,ş,Š,š,ſ
+SS,Ss,sS,ss,ß
+Ŝ,ŝ
+Ʃ
+ƪ
+T,t,Ţ,ţ,Ť,ť
+ƾ
+Ŧ,ŧ
+ƫ
+Ƭ,ƭ
+Ʈ
+U,u,Ù,Ú,Û,Ü,ù,ú,û,ü,Ũ,ũ,Ū,ū,Ů,ů,Ű,ű,Ų,ų,Ư,ư,Ǔ,ǔ,Ǖ,ǖ,Ǘ,ǘ,Ǚ,ǚ,Ǜ,ǜ
+Ŭ,ŭ
+Ɯ
+Ʊ
+V,v
+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
 drop table t1;
 SET NAMES utf8;
 CREATE TABLE t1 (c varchar(255) NOT NULL COLLATE utf8_general_ci, INDEX (c));
diff --git a/mysql-test/t/ctype_uca.test b/mysql-test/t/ctype_uca.test
index 098ea33c6b2..43ef0cc8755 100644
--- a/mysql-test/t/ctype_uca.test
+++ b/mysql-test/t/ctype_uca.test
@@ -211,6 +211,7 @@ select group_concat(c1 order by c1) from t1 group by c1 collate utf8_lithuanian_
 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;
+select group_concat(c1 order by c1) from t1 group by c1 collate utf8_esperanto_ci;
 
 drop table t1;
 
diff --git a/mysys/charset-def.c b/mysys/charset-def.c
index 0464ba893fb..5b30d1ee135 100644
--- a/mysys/charset-def.c
+++ b/mysys/charset-def.c
@@ -42,6 +42,7 @@ 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;
+extern CHARSET_INFO my_charset_ucs2_esperanto_uca_ci;
 #endif
 
 #ifdef HAVE_CHARSET_utf8
@@ -62,6 +63,7 @@ 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;
+extern CHARSET_INFO my_charset_utf8_esperanto_uca_ci;
 #ifdef HAVE_UTF8_GENERAL_CS
 extern CHARSET_INFO my_charset_utf8_general_cs;
 #endif
@@ -148,6 +150,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   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);
+  add_compiled_collation(&my_charset_ucs2_esperanto_uca_ci);
 #endif
 #endif
 
@@ -180,6 +183,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   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);
+  add_compiled_collation(&my_charset_utf8_esperanto_uca_ci);
 #endif
 #endif
 
diff --git a/strings/ctype-uca.c b/strings/ctype-uca.c
index dcf1c07113e..a280ed59352 100644
--- a/strings/ctype-uca.c
+++ b/strings/ctype-uca.c
@@ -6692,6 +6692,18 @@ static const char persian[]=
              " < \\uFEF5 < \\uFEF6 < \\uFEF7 < \\uFEF8 < \\uFEF9 < \\uFEFA"
              " < \\uFEFB < \\uFEFC";
 
+/*
+  Esperanto tailoring.
+  Contributed by Bertilo Wennergren <bertilow at gmail dot com>
+  September 1, 2005
+*/
+static const char esperanto[]=
+    "& C < \\u0109 <<< \\u0108"
+    "& G < \\u011D <<< \\u011C"
+    "& H < \\u0125 <<< \\u0124"
+    "& J < \\u0135 <<< \\u0134"
+    "& S < \\u015d <<< \\u015c"
+    "& U < \\u016d <<< \\u016c";
 
 /*
   Unicode Collation Algorithm:
@@ -8564,6 +8576,38 @@ CHARSET_INFO my_charset_ucs2_persian_uca_ci=
 };
 
 
+CHARSET_INFO my_charset_ucs2_esperanto_uca_ci=
+{
+    145,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "ucs2",		/* cs name    */
+    "ucs2_esperanto_ci",/* name         */
+    "",			/* comment      */
+    esperanto,		/* 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 */
+    my_unicase_default, /* caseinfo     */
+    NULL,		/* state_map    */
+    NULL,		/* ident_map    */
+    8,			/* strxfrm_multiply */
+    1,                  /* caseup_multiply  */
+    1,                  /* casedn_multiply  */
+    2,			/* mbminlen     */
+    2,			/* mbmaxlen     */
+    9,			/* min_sort_char */
+    0xFFFF,		/* max_sort_char */
+    0,                  /* escape_with_backslash_is_dangerous */
+    &my_charset_ucs2_handler,
+    &my_collation_ucs2_uca_handler
+};
+
+
 #endif
 
 
@@ -9140,6 +9184,37 @@ CHARSET_INFO my_charset_utf8_persian_uca_ci=
     &my_collation_any_uca_handler
 };
 
+CHARSET_INFO my_charset_utf8_esperanto_uca_ci=
+{
+    209,0,0,		/* number       */
+    MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,
+    "utf8",		/* cs name    */
+    "utf8_esperanto_ci",/* name         */
+    "",			/* comment      */
+    esperanto,		/* 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 */
+    my_unicase_default, /* caseinfo     */
+    NULL,		/* state_map    */
+    NULL,		/* ident_map    */
+    8,			/* strxfrm_multiply */
+    1,                  /* caseup_multiply  */
+    1,                  /* casedn_multiply  */
+    1,			/* mbminlen     */
+    3,			/* mbmaxlen     */
+    9,			/* min_sort_char */
+    0xFFFF,		/* max_sort_char */
+    0,                  /* escape_with_backslash_is_dangerous */
+    &my_charset_utf8_handler,
+    &my_collation_any_uca_handler
+};
+
 #endif /* HAVE_CHARSET_utf8 */
 
 #endif /* HAVE_UCA_COLLATIONS */