bk commit into 4.1 tree (istruewing:1.2609) BUG#24985

[ingo]

Below is the list of changes that have just been committed into a local
4.1 repository of istruewing. When istruewing does a push these changes will
be propagated to the main repository and, within 24 hours after the
push, to the public repository.
For information on how to access the public repository
see http://dev.mysql.com/doc/mysql/en/installing-source-tree.html

ChangeSet@stripped, 2007-03-23 09:54:49+01:00, istruewing@stripped +5 -0
  Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
              causes incorrect duplicate entries
  
  Keys for a BTREE index on an ENUM column of a MEMORY table
  with character set UTF8 were computed incorrectly. Many
  different column values got the same key value.
  
  Apart of possible performance problems it made unique indexes
  of this type unusable because it rejected many different
  values as duplicates.
  
  The problem was that multibyte character detection was tried
  on the internal numeric column value. Many values were not
  identified as characters. Their key value became blank filled.
  
  The solution is modelled after the equivalent behavior of
  MyISAM. A character set is defined for key segments of text
  type only. Binary segments get a pseudo binary charset attached.
  All other types do not get a charset attached.

  heap/hp_hash.c@stripped, 2007-03-23 09:54:46+01:00, istruewing@stripped +11 -4
    Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
                causes incorrect duplicate entries
    Added tests for unset HA_KEYSEG::charset.
    Added DBUG_ASSERT for HA_KEYSEG::charset to be set in
    key segments of text type.
    Fixed a compiler warning.

  heap/hp_write.c@stripped, 2007-03-23 09:54:47+01:00, istruewing@stripped +4 -4
    Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
                causes incorrect duplicate entries
    Fixed two compiler warnings.

  mysql-test/r/heap_btree.result@stripped, 2007-03-23 09:54:47+01:00, istruewing@stripped
+6 -0
    Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
                causes incorrect duplicate entries
    Added test result.

  mysql-test/t/heap_btree.test@stripped, 2007-03-23 09:54:47+01:00, istruewing@stripped
+11 -0
    Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
                causes incorrect duplicate entries
    Added test.

  sql/ha_heap.cc@stripped, 2007-03-23 09:54:47+01:00, istruewing@stripped +12 -1
    Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
                causes incorrect duplicate entries
    Added code to set up the character set for key segments.
    This is modelled after the equivalent code snippet in mi_open().

# This is a BitKeeper patch.  What follows are the unified diffs for the
# set of deltas contained in the patch.  The rest of the patch, the part
# that BitKeeper cares about, is below these diffs.
# User:	istruewing
# Host:	chilla.local
# Root:	/home/mydev/mysql-4.1-bug24985

--- 1.36/heap/hp_hash.c	2007-03-23 09:54:52 +01:00
+++ 1.37/heap/hp_hash.c	2007-03-23 09:54:52 +01:00
@@ -120,7 +120,7 @@ byte *hp_search(HP_INFO *info, HP_KEYDEF
       {
 	switch (nextflag) {
 	case 0:					/* Search after key */
-	  DBUG_PRINT("exit",("found key at %d",pos->ptr_to_rec));
+	  DBUG_PRINT("exit",("found key at 0x%lx", (long) pos->ptr_to_rec));
 	  info->current_hash_ptr=pos;
 	  DBUG_RETURN(info->current_ptr= pos->ptr_to_rec);
 	case 1:					/* Search next */
@@ -263,6 +263,7 @@ ulong hp_hashnr(register HP_KEYDEF *keyd
     {
        CHARSET_INFO *cs= seg->charset;
        uint char_length= (uint) ((uchar*) key - pos);
+       DBUG_ASSERT(cs);
        if (cs->mbmaxlen > 1)
        {
          uint length= char_length;
@@ -306,6 +307,7 @@ ulong hp_rec_hashnr(register HP_KEYDEF *
     {
       CHARSET_INFO *cs= seg->charset;
       uint char_length= seg->length;
+      DBUG_ASSERT(cs);
       if (cs->mbmaxlen > 1)
       {
         char_length= my_charpos(cs, pos, pos + char_length,
@@ -438,6 +440,7 @@ int hp_rec_key_cmp(HP_KEYDEF *keydef, co
       uint char_length2;
       uchar *pos1= (uchar*)rec1 + seg->start;
       uchar *pos2= (uchar*)rec2 + seg->start;
+      DBUG_ASSERT(cs);
       if (cs->mbmaxlen > 1)
       {
         uint char_length= seg->length / cs->mbmaxlen;
@@ -488,6 +491,7 @@ int hp_key_cmp(HP_KEYDEF *keydef, const 
       uint char_length_key;
       uint char_length_rec;
       uchar *pos= (uchar*) rec + seg->start;
+      DBUG_ASSERT(cs);
       if (cs->mbmaxlen > 1)
       {
         uint char_length= seg->length / cs->mbmaxlen;
@@ -530,7 +534,8 @@ void hp_make_key(HP_KEYDEF *keydef, byte
     uchar *pos= (uchar*) rec + seg->start;
     if (seg->null_bit)
       *key++= test(rec[seg->null_pos] & seg->null_bit);
-    if (cs->mbmaxlen > 1)
+    /* Charset is defined for text and binary key segments only. */
+    if (cs && (cs->mbmaxlen > 1))
     {
       char_length= my_charpos(cs, pos, pos + seg->length,
                               char_length / cs->mbmaxlen);
@@ -594,7 +599,8 @@ uint hp_rb_make_key(HP_KEYDEF *keydef, b
       continue;
     }
     char_length= seg->length;
-    if (seg->charset->mbmaxlen > 1)
+    /* Charset is defined for text and binary key segments only. */
+    if (seg->charset && (seg->charset->mbmaxlen > 1))
     {
       char_length= my_charpos(seg->charset, 
                               rec + seg->start, rec + seg->start + char_length,
@@ -644,7 +650,8 @@ uint hp_rb_pack_key(HP_KEYDEF *keydef, u
       continue;
     }
     char_length= seg->length;
-    if (seg->charset->mbmaxlen > 1)
+    /* Charset is defined for text and binary key segments only. */
+    if (seg->charset && (seg->charset->mbmaxlen > 1))
     {
       char_length= my_charpos(seg->charset, old, old+char_length,
                               char_length / seg->charset->mbmaxlen);

--- 1.21/heap/hp_write.c	2007-03-23 09:54:52 +01:00
+++ 1.22/heap/hp_write.c	2007-03-23 09:54:52 +01:00
@@ -144,7 +144,7 @@ static byte *next_free_record_pos(HP_SHA
     pos=info->del_link;
     info->del_link= *((byte**) pos);
     info->deleted--;
-    DBUG_PRINT("exit",("Used old position: %lx",pos));
+    DBUG_PRINT("exit",("Used old position: 0x%lx", (long) pos));
     DBUG_RETURN(pos);
   }
   if (!(block_pos=(info->records % info->block.records_in_block)))
@@ -159,9 +159,9 @@ static byte *next_free_record_pos(HP_SHA
       DBUG_RETURN(NULL);
     info->data_length+=length;
   }
-  DBUG_PRINT("exit",("Used new position: %lx",
-		     (byte*) info->block.level_info[0].last_blocks+block_pos*
-		     info->block.recbuffer));
+  DBUG_PRINT("exit",("Used new position: 0x%lx", 
+                     (long) info->block.level_info[0].last_blocks +
+                     block_pos * info->block.recbuffer));
   DBUG_RETURN((byte*) info->block.level_info[0].last_blocks+
 	      block_pos*info->block.recbuffer);
 }

--- 1.61/sql/ha_heap.cc	2007-03-23 09:54:52 +01:00
+++ 1.62/sql/ha_heap.cc	2007-03-23 09:54:52 +01:00
@@ -549,7 +549,18 @@ int ha_heap::create(const char *name, TA
       seg->start=   (uint) key_part->offset;
       seg->length=  (uint) key_part->length;
       seg->flag =   0;
-      seg->charset= field->charset();
+      /*
+        Set the character set for the key segment. Most segment types do
+        not have/need a charset. For text segments the field has a valid
+        charset. For binary segments we can use a pseudo charset.
+      */
+      seg->charset= NULL;
+      if (seg->type == HA_KEYTYPE_TEXT || seg->type == HA_KEYTYPE_VARTEXT)
+      {
+        seg->charset= field->charset();
+      }
+      else if (seg->type == HA_KEYTYPE_BINARY)
+        seg->charset= &my_charset_bin;
       if (field->null_ptr)
       {
 	seg->null_bit= field->null_bit;

--- 1.19/mysql-test/r/heap_btree.result	2007-03-23 09:54:53 +01:00
+++ 1.20/mysql-test/r/heap_btree.result	2007-03-23 09:54:53 +01:00
@@ -280,4 +280,10 @@ a
 1
 1
 drop table t1;
+CREATE TABLE t1 (
+c1 ENUM('1', '2'),
+UNIQUE USING BTREE(c1)
+) ENGINE= MEMORY DEFAULT CHARSET= utf8;
+INSERT INTO t1 VALUES('1'), ('2');
+DROP TABLE t1;
 End of 4.1 tests

--- 1.15/mysql-test/t/heap_btree.test	2007-03-23 09:54:53 +01:00
+++ 1.16/mysql-test/t/heap_btree.test	2007-03-23 09:54:53 +01:00
@@ -182,4 +182,15 @@ delete from t1 where a >= 2;
 select a from t1 order by a;
 drop table t1;
 
+#
+# Bug#24985 - UTF8 ENUM primary key on MEMORY using BTREE
+#             causes incorrect duplicate entries
+#
+CREATE TABLE t1 (
+  c1 ENUM('1', '2'),
+  UNIQUE USING BTREE(c1)
+) ENGINE= MEMORY DEFAULT CHARSET= utf8;
+INSERT INTO t1 VALUES('1'), ('2');
+DROP TABLE t1;
+
 --echo End of 4.1 tests