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. 

1 files changed, 40 insertions, 0 deletions

diff --git a/sql/item_strfunc.h b/sql/item_strfunc.h
index 5dcef2e671f..d76e139883c 100644
--- a/sql/item_strfunc.h
+++ b/sql/item_strfunc.h
@@ -657,6 +657,46 @@ public:
 };
 
 
+#ifndef DBUG_OFF
+class Item_func_like_range :public Item_str_func
+{
+protected:
+  String min_str;
+  String max_str;
+  const bool is_min;
+public:
+  Item_func_like_range(Item *a, Item *b, bool is_min_arg)
+    :Item_str_func(a, b), is_min(is_min_arg)
+  { maybe_null= 1; }
+  String *val_str(String *);
+  void fix_length_and_dec()
+  {
+    collation.set(args[0]->collation);
+    decimals=0;
+    max_length= MAX_BLOB_WIDTH;
+  }
+};
+
+
+class Item_func_like_range_min :public Item_func_like_range
+{
+public:
+  Item_func_like_range_min(Item *a, Item *b) 
+    :Item_func_like_range(a, b, true) { }
+  const char *func_name() const { return "like_range_min"; }
+};
+
+
+class Item_func_like_range_max :public Item_func_like_range
+{
+public:
+  Item_func_like_range_max(Item *a, Item *b)
+    :Item_func_like_range(a, b, false) { }
+  const char *func_name() const { return "like_range_max"; }
+};
+#endif
+
+
 class Item_func_binary :public Item_str_func
 {
 public: