BUG#29299 - repeatable myisam fulltext index corruption

Fulltext index may get corrupt by certain gbk characters.

The problem was that when skipping leading non-true-word-characters,
we assumed that these characters are always 1 byte long. This is not
the case with gbk character set, since non-true-word-characters may
be 2 bytes long.

Affects 5.0 only.

myisam/ft_parser.c

@@ -111,7 +111,7 @@ byte ft_get_word(CHARSET_INFO *cs, byte **start, byte *end,
 
   while (doc<end)
   {
-    for (;doc<end;doc++)
+    for (; doc < end; doc+= mbl)
     {
       if (true_word_char(cs,*doc)) break;
       if (*doc == FTB_RQUOT && param->quot)
@@ -120,6 +120,7 @@ byte ft_get_word(CHARSET_INFO *cs, byte **start, byte *end,
         *start=doc+1;
         return 3; /* FTB_RBR */
       }
+      mbl= my_mbcharlen(cs, *(uchar *)doc);
       if (!param->quot)
       {
         if (*doc == FTB_LBR || *doc == FTB_RBR || *doc == FTB_LQUOT)
@@ -187,10 +188,11 @@ byte ft_simple_get_word(CHARSET_INFO *cs, byte **start, const byte *end,
 
   do
   {
-    for (;; doc++)
+    for (;; doc+= mbl)
     {
       if (doc >= end) DBUG_RETURN(0);
       if (true_word_char(cs, *doc)) break;
+      mbl= my_mbcharlen(cs, *(uchar *)doc);
     }
 
     mwc= length= 0;

mysql-test/r/fulltext2.result

@@ -241,3 +241,15 @@ select * from t1 where match a against('ab c' in boolean mode);
 a
 drop table t1;
 set names latin1;
+CREATE TABLE t1(a VARCHAR(255) CHARACTER SET gbk, FULLTEXT(a));
+SET NAMES utf8;
+INSERT INTO t1 VALUES(0xF043616161),(0xBEF361616197C22061616161);
+SELECT HEX(a) FROM t1 WHERE MATCH(a) AGAINST(0x97C22061616161 IN BOOLEAN MODE);
+HEX(a)
+BEF361616197C22061616161
+DELETE FROM t1 LIMIT 1;
+CHECK TABLE t1;
+Table	Op	Msg_type	Msg_text
+test.t1	check	status	OK
+SET NAMES latin1;
+DROP TABLE t1;

mysql-test/t/fulltext2.test

@@ -220,4 +220,16 @@ select * from t1 where match a against('ab c' in boolean mode);
 drop table t1;
 set names latin1;
 
+#
+# BUG#29299 - repeatable myisam fulltext index corruption
+#
+CREATE TABLE t1(a VARCHAR(255) CHARACTER SET gbk, FULLTEXT(a));
+SET NAMES utf8;
+INSERT INTO t1 VALUES(0xF043616161),(0xBEF361616197C22061616161);
+SELECT HEX(a) FROM t1 WHERE MATCH(a) AGAINST(0x97C22061616161 IN BOOLEAN MODE);
+DELETE FROM t1 LIMIT 1;
+CHECK TABLE t1;
+SET NAMES latin1;
+DROP TABLE t1;
+
 # End of 4.1 tests