From: Date: February 2 2009 2:29pm
Subject: bzr commit into mysql-5.1-bugteam branch (bar:2781) Bug#41084
List-Archive: http://lists.mysql.com/commits/64870
X-Bug: 41084
Message-Id: <200902021329.n12DT70u028806@bar.myoffice.izhnet.ru>
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit

#At file:///home/bar/mysql-bzr/mysql-5.1-b41084/

 2781 Alexander Barkov	2009-02-02
      Bug#41084 full-text index added to custom UCA collation not working
      
      Problem:
      Custom UCA collations didn't set the MY_CS_STRNXFRM flag,
      which resulted in "prefix_search" method instead of
      the required "seq_search".
      
      Problem2: (not metioned in the bug report)
      Custom UCA collations didn't also set the MY_CS_UNICODE flag,
      so an attempt to compare a column with a custom UCA collation
      to another column with a non-Unicode character set led to
      the "illegal mix of collation" error.
      
      Fix:
      the two missing flags was added into collation initialization.
      
        Upgrade:
      
        - All fulltext indexes with custom UCA collations should be rebuilt.
      
        - Non-fulltext custom UCA indexes should likely be rebuild as well.
modified:
  mysql-test/r/ctype_ldml.result
  mysql-test/t/ctype_ldml.test
  mysys/charset.c

=== modified file 'mysql-test/r/ctype_ldml.result'
--- a/mysql-test/r/ctype_ldml.result	2007-06-07 12:55:55 +0000
+++ b/mysql-test/r/ctype_ldml.result	2009-02-02 13:25:42 +0000
@@ -21,6 +21,25 @@ select * from t1 where c1='b';
 c1
 a
 drop table t1;
+CREATE TABLE t1 (
+col1 varchar(100) character set utf8 collate utf8_test_ci
+);
+INSERT INTO t1 (col1) VALUES ('abcd'),('efgh'),('ijkl');
+ALTER TABLE t1 ADD FULLTEXT INDEX (col1);
+SELECT * FROM t1 where match (col1) against ('abcd');
+col1
+abcd
+SELECT * FROM t1 where match (col1) against ('abcd' IN BOOLEAN MODE);
+col1
+abcd
+ALTER TABLE t1 ADD (col2 varchar(100) character set latin1);
+UPDATE t1 SET col2=col1;
+SELECT * FROM t1 WHERE col1=col2 ORDER BY col1;
+col1	col2
+abcd	abcd
+efgh	efgh
+ijkl	ijkl
+DROP TABLE t1;
 show collation like 'ucs2_vn_ci';
 Collation	Charset	Id	Default	Compiled	Sortlen
 ucs2_vn_ci	ucs2	242			8

=== modified file 'mysql-test/t/ctype_ldml.test'
--- a/mysql-test/t/ctype_ldml.test	2007-06-07 12:55:55 +0000
+++ b/mysql-test/t/ctype_ldml.test	2009-02-02 13:25:42 +0000
@@ -21,6 +21,22 @@ insert into t1 values ('a');
 select * from t1 where c1='b';
 drop table t1;
 
+
+#
+# Bug#41084 full-text index added to custom UCA collation not working
+#
+CREATE TABLE t1 (
+  col1 varchar(100) character set utf8 collate utf8_test_ci
+);
+INSERT INTO t1 (col1) VALUES ('abcd'),('efgh'),('ijkl');
+ALTER TABLE t1 ADD FULLTEXT INDEX (col1);
+SELECT * FROM t1 where match (col1) against ('abcd');
+SELECT * FROM t1 where match (col1) against ('abcd' IN BOOLEAN MODE);
+ALTER TABLE t1 ADD (col2 varchar(100) character set latin1);
+UPDATE t1 SET col2=col1;
+SELECT * FROM t1 WHERE col1=col2 ORDER BY col1;
+DROP TABLE t1;
+
 #
 #  Vietnamese experimental collation
 #

=== modified file 'mysys/charset.c'
--- a/mysys/charset.c	2008-02-18 22:29:39 +0000
+++ b/mysys/charset.c	2009-02-02 13:25:42 +0000
@@ -212,6 +212,8 @@ copy_uca_collation(CHARSET_INFO *to, CHA
   to->max_sort_char= from->max_sort_char;
   to->mbminlen= from->mbminlen;
   to->mbmaxlen= from->mbmaxlen;
+  to->state|= MY_CS_AVAILABLE | MY_CS_LOADED |
+              MY_CS_STRNXFRM  | MY_CS_UNICODE;
 }
 
 
@@ -246,14 +248,12 @@ static int add_collation(CHARSET_INFO *c
       {
 #if defined(HAVE_CHARSET_ucs2) && defined(HAVE_UCA_COLLATIONS)
         copy_uca_collation(newcs, &my_charset_ucs2_unicode_ci);
-        newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED;
 #endif        
       }
       else if (!strcmp(cs->csname, "utf8"))
       {
 #if defined (HAVE_CHARSET_utf8) && defined(HAVE_UCA_COLLATIONS)
         copy_uca_collation(newcs, &my_charset_utf8_unicode_ci);
-        newcs->state|= MY_CS_AVAILABLE | MY_CS_LOADED;
 #endif
       }
       else