From e3dee8a7fd3e16147145b877917d4aa85346dfcb Mon Sep 17 00:00:00 2001
From: Alexander Barkov <bar@mysql.com>
Date: Fri, 26 Nov 2010 13:44:39 +0300
Subject: Bug#57737 Character sets: search fails with like, contraction, index

Problem: LIKE over an indexed column optimized away good results,
because my_like_range_utf32/utf16 returned wrong ranges for contractions.
Contraction related code was missing in my_like_range_utf32/utf16,
but did exist in my_like_range_ucs2/utf8.
It was forgotten in utf32/utf16 versions (during mysql-6.0 push/revert mess).

Fix:
The patch removes individual functions my_like_range_ucs2,
my_like_range_utf16, my_like_range_utf32 and introduces a single function
my_like_range_generic() instead. The new function handles contractions
correctly. It can handle any character set with cs->min_sort_char and
cs->max_sort_char represented in Unicode code points.

added:
  @ mysql-test/include/ctype_czech.inc
  @ mysql-test/include/ctype_like_ignorable.inc
  @ mysql-test/r/ctype_like_range.result
  @ mysql-test/t/ctype_like_range.test
  Adding tests


modified:

  @ include/m_ctype.h
  - Adding helper functions for contractions.
  - Prototypes: removing ucs2,utf16,utf32 functions, adding generic function.
  @ mysql-test/r/ctype_uca.result
  @ mysql-test/r/ctype_utf16_uca.result
  @ mysql-test/r/ctype_utf32_uca.result
  @ mysql-test/t/ctype_uca.test
  @ mysql-test/t/ctype_utf16_uca.test
  @ mysql-test/t/ctype_utf32_uca.test
  - Adding tests.

  @ strings/ctype-mb.c
  - Pad function did not put the last character.
  - Implementing my_like_range_generic() - an universal replacement
    for three separate functions
    my_like_range_ucs2(), my_like_range_utf16() and my_like_range_utf32(),
    with correct contraction handling.

  @ strings/ctype-ucs2.c
  - my_fill_mb2 did not put the high byte, as previously
    it was used to put only characters in ASCII range.
    Now it puts high byte as well
    (needed to pupulate cs->max_sort_char correctly).
  - Adding DBUG_ASSERT()
  - Removing character set specific functions:
    my_like_range_ucs2(), my_like_range_utf16() and my_like_range_utf32().
  - Using my_like_range_generic() instead of the old functions.

  @ strings/ctype-uca.c
  - Using generic function instead of the old character set specific ones.

  @ sql/item_create.cc
  @ sql/item_strfunc.cc
  @ sql/item_strfunc.h
  - Adding SQL functions LIKE_RANGE_MIN and LIKE_RANGE_MAX,
    available only in debug build to make sure like_range()
    works correctly for all character sets and collations.
---
 sql/item_create.cc | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

(limited to 'sql/item_create.cc')

diff --git a/sql/item_create.cc b/sql/item_create.cc
index 672e59986d5..1ae65926013 100644
--- a/sql/item_create.cc
+++ b/sql/item_create.cc
@@ -1330,6 +1330,34 @@ protected:
 };
 
 
+#ifndef DBUG_OFF
+class Create_func_like_range_min : public Create_func_arg2
+{
+public:
+  virtual Item *create(THD *thd, Item *arg1, Item *arg2);
+
+  static Create_func_like_range_min s_singleton;
+
+protected:
+  Create_func_like_range_min() {}
+  virtual ~Create_func_like_range_min() {}
+};
+
+
+class Create_func_like_range_max : public Create_func_arg2
+{
+public:
+  virtual Item *create(THD *thd, Item *arg1, Item *arg2);
+
+  static Create_func_like_range_max s_singleton;
+
+protected:
+  Create_func_like_range_max() {}
+  virtual ~Create_func_like_range_max() {}
+};
+#endif
+
+
 class Create_func_ln : public Create_func_arg1
 {
 public:
@@ -3836,6 +3864,26 @@ Create_func_length::create(THD *thd, Item *arg1)
 }
 
 
+#ifndef DBUG_OFF
+Create_func_like_range_min Create_func_like_range_min::s_singleton;
+
+Item*
+Create_func_like_range_min::create(THD *thd, Item *arg1, Item *arg2)
+{
+  return new (thd->mem_root) Item_func_like_range_min(arg1, arg2);
+}
+
+
+Create_func_like_range_max Create_func_like_range_max::s_singleton;
+
+Item*
+Create_func_like_range_max::create(THD *thd, Item *arg1, Item *arg2)
+{
+  return new (thd->mem_root) Item_func_like_range_max(arg1, arg2);
+}
+#endif
+
+
 Create_func_ln Create_func_ln::s_singleton;
 
 Item*
@@ -4924,6 +4972,10 @@ static Native_func_registry func_array[] =
   { { C_STRING_WITH_LEN("LCASE") }, BUILDER(Create_func_lcase)},
   { { C_STRING_WITH_LEN("LEAST") }, BUILDER(Create_func_least)},
   { { C_STRING_WITH_LEN("LENGTH") }, BUILDER(Create_func_length)},
+#ifndef DBUG_OFF
+  { { C_STRING_WITH_LEN("LIKE_RANGE_MIN") }, BUILDER(Create_func_like_range_min)},
+  { { C_STRING_WITH_LEN("LIKE_RANGE_MAX") }, BUILDER(Create_func_like_range_max)},
+#endif
   { { C_STRING_WITH_LEN("LINEFROMTEXT") }, GEOM_BUILDER(Create_func_geometry_from_text)},
   { { C_STRING_WITH_LEN("LINEFROMWKB") }, GEOM_BUILDER(Create_func_geometry_from_wkb)},
   { { C_STRING_WITH_LEN("LINESTRINGFROMTEXT") }, GEOM_BUILDER(Create_func_geometry_from_text)},
-- 
cgit v1.2.1