Bug#11752408 - 43593: DUMP/BACKUP/RESTORE/UPGRADE TOOLS FAILS BECAUSE OF UTF8_GENERAL_CI

Introducing new collations:
utf8_general_mysql500_ci and ucs2_general_mysql500_ci,
to reproduce behaviour of utf8_general_ci and ucs2_general_ci
from mysql-5.1.23 (and earlier).

The collations are added to simplify upgrade from mysql-5.1.23 and earlier.

Note: The patch does not make new server start over old data automatically.
Some manual upgrade procedures are assumed.

Paul: please get in touch with me to discuss upgrade procedures
when documenting this bug.

modified:
  include/m_ctype.h
  mysql-test/r/ctype_utf8.result
  mysql-test/t/ctype_utf8.test
  mysys/charset-def.c
  strings/ctype-ucs2.c
  strings/ctype-utf8.c

include/m_ctype.h

@@ -50,6 +50,8 @@ typedef struct unicase_info_st
 
 extern MY_UNICASE_INFO *my_unicase_default[256];
 extern MY_UNICASE_INFO *my_unicase_turkish[256];
+extern MY_UNICASE_INFO *my_unicase_mysql500[256];
+
 
 typedef struct uni_ctype_st
 {
@@ -311,11 +313,13 @@ extern CHARSET_INFO my_charset_tis620_bin;
 extern CHARSET_INFO my_charset_ucs2_general_ci;
 extern CHARSET_INFO my_charset_ucs2_bin;
 extern CHARSET_INFO my_charset_ucs2_unicode_ci;
+extern CHARSET_INFO my_charset_ucs2_general_mysql500_ci;
 extern CHARSET_INFO my_charset_ujis_japanese_ci;
 extern CHARSET_INFO my_charset_ujis_bin;
 extern CHARSET_INFO my_charset_utf8_general_ci;
 extern CHARSET_INFO my_charset_utf8_unicode_ci;
 extern CHARSET_INFO my_charset_utf8_bin;
+extern CHARSET_INFO my_charset_utf8_general_mysql500_ci;
 extern CHARSET_INFO my_charset_cp1250_czech_ci;
 extern MYSQL_PLUGIN_IMPORT CHARSET_INFO my_charset_filename;
 

mysql-test/r/ctype_utf8.result

@@ -1928,4 +1928,28 @@ D120
 SELECT HEX(INSERT(_utf8 0xD18FD18E, 2, 1, 0x20));
 HEX(INSERT(_utf8 0xD18FD18E, 2, 1, 0x20))
 D120D18E
+#
+# Bug#11752408 - 43593: DUMP/BACKUP/RESTORE/UPGRADE TOOLS FAILS BECAUSE OF UTF8_GENERAL_CI
+#
+CREATE TABLE t1 (a VARCHAR(10) CHARACTER SET utf8 COLLATE utf8_general_mysql500_ci);
+INSERT INTO t1 VALUES ('a'),('r'),('s'),(_latin1 0xDF),(_latin1 0xF7),('t'),('z');
+SELECT * FROM t1 ORDER BY a;
+a
+a
+r
+s
+t
+z
+ß
+÷
+SELECT a, COUNT(*) FROM t1 GROUP BY a;
+a	COUNT(*)
+a	1
+r	1
+s	1
+t	1
+z	1
+ß	1
+÷	1
+DROP TABLE t1;
 End of 5.1 tests

mysql-test/t/ctype_utf8.test

@@ -1484,5 +1484,13 @@ SELECT HEX(LPAD(_utf8 0xD18F, 3, 0x20));
 SELECT HEX(INSERT(_utf8 0xD18F, 2, 1, 0x20));
 SELECT HEX(INSERT(_utf8 0xD18FD18E, 2, 1, 0x20));
 
+--echo #
+--echo # Bug#11752408 - 43593: DUMP/BACKUP/RESTORE/UPGRADE TOOLS FAILS BECAUSE OF UTF8_GENERAL_CI
+--echo #
+CREATE TABLE t1 (a VARCHAR(10) CHARACTER SET utf8 COLLATE utf8_general_mysql500_ci);
+INSERT INTO t1 VALUES ('a'),('r'),('s'),(_latin1 0xDF),(_latin1 0xF7),('t'),('z');
+SELECT * FROM t1 ORDER BY a;
+SELECT a, COUNT(*) FROM t1 GROUP BY a;
+DROP TABLE t1;
 
 --echo End of 5.1 tests

mysys/charset-def.c

@@ -132,6 +132,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
 #ifdef HAVE_CHARSET_ucs2
   add_compiled_collation(&my_charset_ucs2_general_ci);
   add_compiled_collation(&my_charset_ucs2_bin);
+  add_compiled_collation(&my_charset_ucs2_general_mysql500_ci);
 #ifdef HAVE_UCA_COLLATIONS
   add_compiled_collation(&my_charset_ucs2_unicode_ci);
   add_compiled_collation(&my_charset_ucs2_icelandic_uca_ci);
@@ -163,6 +164,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
 #ifdef HAVE_CHARSET_utf8
   add_compiled_collation(&my_charset_utf8_general_ci);
   add_compiled_collation(&my_charset_utf8_bin);
+  add_compiled_collation(&my_charset_utf8_general_mysql500_ci);
 #ifdef HAVE_UTF8_GENERAL_CS
   add_compiled_collation(&my_charset_utf8_general_cs);
 #endif

strings/ctype-ucs2.c

@@ -1732,6 +1732,40 @@ CHARSET_INFO my_charset_ucs2_general_ci=
     &my_collation_ucs2_general_ci_handler
 };
 
+
+CHARSET_INFO my_charset_ucs2_general_mysql500_ci=
+{
+  159, 0, 0,                                       /* number           */
+  MY_CS_COMPILED|MY_CS_STRNXFRM|MY_CS_UNICODE,     /* state */
+  "ucs2",                                          /* cs name          */
+  "ucs2_general_mysql500_ci",                      /* name             */
+  "",                                              /* comment          */
+  NULL,                                            /* tailoring        */
+  ctype_ucs2,                                      /* ctype            */
+  to_lower_ucs2,                                   /* to_lower         */
+  to_upper_ucs2,                                   /* to_upper         */
+  to_upper_ucs2,                                   /* sort_order       */
+  NULL,                                            /* contractions     */
+  NULL,                                            /* sort_order_big   */
+  NULL,                                            /* tab_to_uni       */
+  NULL,                                            /* tab_from_uni     */
+  my_unicase_mysql500,                             /* caseinfo         */
+  NULL,                                            /* state_map        */
+  NULL,                                            /* ident_map        */
+  1,                                               /* strxfrm_multiply */
+  1,                                               /* caseup_multiply  */
+  1,                                               /* casedn_multiply  */
+  2,                                               /* mbminlen         */
+  2,                                               /* mbmaxlen         */
+  0,                                               /* min_sort_char    */
+  0xFFFF,                                          /* max_sort_char    */
+  ' ',                                             /* pad char         */
+  0,                          /* escape_with_backslash_is_dangerous    */
+  &my_charset_ucs2_handler,
+  &my_collation_ucs2_general_ci_handler
+};
+
+
 CHARSET_INFO my_charset_ucs2_bin=
 {
     90,0,0,		/* number       */