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:
  Leading non-true-word-characters may also be multi-byte (e.g. in
  gbk character set).
mysql-test/r/fulltext2.result:
  A test case for BUG#29299.
mysql-test/t/fulltext2.test:
  A test case for BUG#29299.

1 files changed, 4 insertions, 2 deletions

diff --git a/myisam/ft_parser.c b/myisam/ft_parser.c
index 6c79f9249cf..6d68542e4e2 100644
--- a/myisam/ft_parser.c
+++ b/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;