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, 87 insertions, 0 deletions

diff --git a/mysql-test/t/ctype_like_range.test b/mysql-test/t/ctype_like_range.test
new file mode 100644
index 00000000000..34a7637222b
--- /dev/null
+++ b/mysql-test/t/ctype_like_range.test
@@ -0,0 +1,87 @@
+--source include/have_debug.inc
+--source include/have_ucs2.inc
+--source include/have_utf16.inc
+--source include/have_utf32.inc
+
+--disable_warnings
+DROP TABLE IF EXISTS t1;
+DROP VIEW IF EXISTS v1;
+--enable_warnings
+
+CREATE TABLE t1 (id INT NOT NULL AUTO_INCREMENT PRIMARY KEY, a VARBINARY(32));
+INSERT INTO t1 (a) VALUES (''),('_'),('%'),('\_'),('\%'),('\\');
+INSERT INTO t1 (a) VALUES ('a'),('c');
+INSERT INTO t1 (a) VALUES ('a_'),('c_');
+INSERT INTO t1 (a) VALUES ('a%'),('c%');
+INSERT INTO t1 (a) VALUES ('aa'),('cc'),('ch');
+INSERT INTO t1 (a) VALUES ('aa_'),('cc_'),('ch_');
+INSERT INTO t1 (a) VALUES ('aa%'),('cc%'),('ch%');
+INSERT INTO t1 (a) VALUES ('aaa'),('ccc'),('cch');
+INSERT INTO t1 (a) VALUES ('aaa_'),('ccc_'),('cch_');
+INSERT INTO t1 (a) VALUES ('aaa%'),('ccc%'),('cch%');
+INSERT INTO t1 (a) VALUES ('aaaaaaaaaaaaaaaaaaaa');
+
+CREATE VIEW v1 AS
+  SELECT id, 'a' AS name, a AS val FROM t1
+UNION
+  SELECT id, 'mn', HEX(LIKE_RANGE_MIN(a, 16)) AS min FROM t1
+UNION
+  SELECT id, 'mx', HEX(LIKE_RANGE_MAX(a, 16)) AS max FROM t1
+UNION
+  SELECT id, 'sp', REPEAT('-', 32) AS sep FROM t1
+ORDER BY id, name;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET latin1;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf8;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf8 COLLATE utf8_unicode_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf8 COLLATE utf8_czech_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf8 COLLATE utf8_danish_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET ucs2;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET ucs2 COLLATE ucs2_unicode_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET ucs2 COLLATE ucs2_czech_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET ucs2 COLLATE ucs2_danish_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf16;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf16 COLLATE utf16_unicode_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf16 COLLATE utf16_czech_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf16 COLLATE utf16_danish_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf32;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf32 COLLATE utf32_unicode_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf32 COLLATE utf32_czech_ci;
+SELECT * FROM v1;
+
+ALTER TABLE t1 MODIFY a VARCHAR(32) CHARACTER SET utf32 COLLATE utf32_danish_ci;
+SELECT * FROM v1;
+
+DROP VIEW v1;
+DROP TABLE t1;