Merge mysql.com:/home/hf/mysql-5.0.mrg

into  mysql.com:/home/hf/mysql-5.1.mrg


include/m_ctype.h:
  Auto merged
mysql-test/r/ctype_utf8.result:
  Auto merged
mysql-test/r/type_enum.result:
  Auto merged
mysql-test/t/ctype_utf8.test:
  Auto merged
sql/item_func.cc:
  Auto merged
sql/sql_select.cc:
  Auto merged
sql/table.cc:
  Auto merged
sql/unireg.cc:
  Auto merged
strings/CHARSET_INFO.txt:
  Auto merged
strings/ctype-mb.c:
  Auto merged
strings/ctype-utf8.c:
  Auto merged

3 files changed, 37 insertions, 9 deletions

diff --git a/strings/CHARSET_INFO.txt b/strings/CHARSET_INFO.txt
index 40f171440a4..1336d5ae3bb 100644
--- a/strings/CHARSET_INFO.txt
+++ b/strings/CHARSET_INFO.txt
@@ -33,7 +33,7 @@ typedef struct charset_info_st
   uint      strxfrm_multiply;
   uint      mbminlen;
   uint      mbmaxlen;
-  char      max_sort_char; /* For LIKE optimization */
+  uint16    max_sort_char; /* For LIKE optimization */
 
   MY_CHARSET_HANDLER *cset;
   MY_COLLATION_HANDLER *coll;
@@ -134,7 +134,15 @@ Misc fields
   mbmaxlen         - maximum multibyte sequence length.
                      1 for 8bit charsets. Can be also 2 or 3.
 
-
+  max_sort_char    - for LIKE range
+                     in case of 8bit character sets - native code
+		     of maximum character (max_str pad byte);
+                     in case of UTF8 and UCS2 - Unicode code of the maximum
+		     possible character (usually U+FFFF). This code is
+		     converted to multibyte representation (usually 0xEFBFBF)
+		     and then used as a pad sequence for max_str.
+		     in case of other multibyte character sets -
+		     max_str pad byte (usually 0xFF).
 
 MY_CHARSET_HANDLER
 ==================
diff --git a/strings/ctype-mb.c b/strings/ctype-mb.c
index 898b7a4a57d..c945164ac9c 100644
--- a/strings/ctype-mb.c
+++ b/strings/ctype-mb.c
@@ -474,15 +474,35 @@ static void my_hash_sort_mb_bin(CHARSET_INFO *cs __attribute__((unused)),
 
 
 /* 
-  Write max key: create a buffer with multibyte
-  representation of the max_sort_char character,
-  and copy it into max_str in a loop. 
+  Fill the given buffer with 'maximum character' for given charset
+  SYNOPSIS
+      pad_max_char()
+      cs   Character set
+      str  Start of buffer to fill
+      end  End of buffer to fill
+
+  DESCRIPTION
+      Write max key:
+      - for non-Unicode character sets:
+        just set to 255.
+      - for Unicode character set (utf-8):
+        create a buffer with multibyte representation of the max_sort_char
+        character, and copy it into max_str in a loop. 
 */
 static void pad_max_char(CHARSET_INFO *cs, char *str, char *end)
 {
   char buf[10];
-  char buflen= cs->cset->wc_mb(cs, cs->max_sort_char, (uchar*) buf,
-                               (uchar*) buf + sizeof(buf));
+  char buflen;
+  
+  if (!(cs->state & MY_CS_UNICODE))
+  {
+    bfill(str, end - str, 255);
+    return;
+  }
+  
+  buflen= cs->cset->wc_mb(cs, cs->max_sort_char, (uchar*) buf,
+                          (uchar*) buf + sizeof(buf));
+  
   DBUG_ASSERT(buflen > 0);
   do
   {
@@ -943,7 +963,7 @@ MY_COLLATION_HANDLER my_collation_mb_bin_handler =
     my_strnncollsp_mb_bin,
     my_strnxfrm_mb_bin,
     my_strnxfrmlen_simple,
-    my_like_range_simple,
+    my_like_range_mb,
     my_wildcmp_mb_bin,
     my_strcasecmp_mb_bin,
     my_instr_mb,
diff --git a/strings/ctype-utf8.c b/strings/ctype-utf8.c
index e221297eb55..6c3ceaf868b 100644
--- a/strings/ctype-utf8.c
+++ b/strings/ctype-utf8.c
@@ -2615,7 +2615,7 @@ CHARSET_INFO my_charset_utf8_bin=
     1,                  /* mbminlen     */
     3,                  /* mbmaxlen     */
     0,                  /* min_sort_char */
-    255,                /* max_sort_char */
+    0xFFFF,             /* max_sort_char */
     ' ',                /* pad char      */
     0,                  /* escape_with_backslash_is_dangerous */
     &my_charset_utf8_handler,