path: root/mysql-test/main/ctype_utf32_uca.test

-- source include/have_ucs2.inc
-- source include/have_utf32.inc

--disable_warnings
DROP TABLE IF EXISTS t1;
--enable_warnings

--echo #
--echo # Start of 5.5 tests
--echo #
--disable_service_connection

set names utf8;
set collation_connection=utf32_unicode_ci;
select hex('a'), hex('a ');
-- source include/endspace.inc

#
# Bug #6787 LIKE not working properly with _ and utf8 data
#
select 'c' like '\_' as want0; 

#
# Bug #5679 utf8_unicode_ci LIKE--trailing % doesn't equal zero characters
#
CREATE TABLE t (
  c char(20) NOT NULL
) ENGINE=MyISAM DEFAULT CHARACTER SET utf32 COLLATE=utf32_unicode_ci;
INSERT INTO t VALUES ('a'),('ab'),('aba');
ALTER TABLE t ADD INDEX (c);
SELECT c FROM t WHERE c LIKE 'a%';
DROP TABLE t;


create table t1 (c1 char(10) character set utf32 collate utf32_bin);

--source include/ctype_unicode_latin.inc

select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_unicode_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_icelandic_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_latvian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_romanian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_slovenian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_polish_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_estonian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_spanish_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_swedish_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_turkish_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_czech_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_danish_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_lithuanian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_slovak_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_spanish2_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_roman_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_esperanto_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_hungarian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_croatian_mysql561_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_croatian_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_german2_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_unicode_520_ci;
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_vietnamese_ci;

drop table t1;

#
# Bug#5324
#
SET NAMES utf8;
#test1
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_general_ci NOT NULL, INDEX (c));
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
#Check one row
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025 COLLATE utf32_general_ci;
INSERT INTO t1 VALUES (CONVERT(_ucs2 0x039C03C903B4 USING utf8));
#Check two rows
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025
COLLATE utf32_general_ci ORDER BY c;
DROP TABLE t1;
#test2
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_unicode_ci NOT NULL, INDEX (c));
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
#Check one row
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025 COLLATE utf32_unicode_ci;
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B4);
#Check two rows
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025
COLLATE utf32_unicode_ci ORDER BY c;
DROP TABLE t1;
#test 3
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_unicode_ci NOT NULL, INDEX (c));
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
#Check one row row
SELECT * FROM t1 WHERE c LIKE CONVERT(_ucs2 0x039C0025 USING utf32) COLLATE utf32_unicode_ci;
INSERT INTO t1 VALUES (CONVERT(_ucs2 0x039C03C903B4 USING utf8));
#Check two rows
SELECT * FROM t1 WHERE c LIKE CONVERT(_ucs2 0x039C0025 USING utf32)
COLLATE utf32_unicode_ci ORDER BY c;
DROP TABLE t1;


SET NAMES utf8;
SET @test_character_set='utf32';
SET @test_collation='utf32_swedish_ci';
-- source include/ctype_common.inc


SET collation_connection='utf32_unicode_ci';
-- source include/ctype_filesort.inc
-- source include/ctype_like_escape.inc
-- source include/ctype_german.inc

--echo End of 4.1 tests

#
# Check UPPER/LOWER changing length
#
# Result shorter than argument
CREATE TABLE t1 (id int, a varchar(30) character set utf32);
INSERT INTO t1 VALUES (1, _ucs2 0x01310069), (2, _ucs2 0x01310131);
INSERT INTO t1 VALUES (3, _ucs2 0x00690069), (4, _ucs2 0x01300049);
INSERT INTO t1 VALUES (5, _ucs2 0x01300130), (6, _ucs2 0x00490049);
SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu
FROM t1 ORDER BY id;
ALTER TABLE t1 MODIFY a VARCHAR(30) character set utf32 collate utf32_turkish_ci;
SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu
FROM t1 ORDER BY id;
DROP TABLE t1;

#
# Bug #27079 Crash while grouping empty ucs2 strings
#
CREATE TABLE t1 (
 c1 text character set utf32 collate utf32_polish_ci NOT NULL
) ENGINE=MyISAM;
insert into t1 values (''),('a');
SELECT COUNT(*), c1 FROM t1 GROUP BY c1;
DROP TABLE IF EXISTS t1;


#
# Test basic regex functionality
#
set collation_connection=utf32_unicode_ci;
--source include/ctype_regex.inc


#
# Test like_range and contractions
#
SET collation_connection=utf32_czech_ci;
--source include/ctype_czech.inc
--source include/ctype_like_ignorable.inc

--echo #
--echo # Bug #12319710 : INVALID MEMORY READ AND/OR CRASH IN 
--echo #   MY_UCA_CHARCMP WITH UTF32
--echo #

SET collation_connection=utf32_unicode_ci;
CREATE TABLE t1 (a TEXT CHARACTER SET utf32 COLLATE utf32_turkish_ci NOT NULL);
INSERT INTO t1 VALUES ('a'), ('b');
CREATE TABLE t2 (b VARBINARY(5) NOT NULL);

--echo #insert chars outside of BMP
INSERT INTO t2 VALUEs (0x082837),(0x082837);

--echo #test for read-out-of-bounds with non-BMP chars as a LIKE pattern
SELECT * FROM t1,t2 WHERE a LIKE b;

--echo #test the original statement
SELECT 1 FROM t1 AS t1_0 NATURAL LEFT OUTER JOIN t2 AS t2_0
RIGHT JOIN t1 AS t1_1 ON t1_0.a LIKE t2_0.b;

DROP TABLE t1,t2;

--echo #
--echo # End of 5.5 tests
--echo #


--echo #
--echo # Start of 5.6 tests
--echo #

--echo #
--echo # WL#3664 WEIGHT_STRING
--echo #

set collation_connection=utf32_unicode_ci;
--source include/weight_string.inc
--source include/weight_string_euro.inc
select hex(weight_string(_utf32 0x10000 collate utf32_unicode_ci));
select hex(weight_string(_utf32 0x10001 collate utf32_unicode_ci));
--source include/weight_string_l1.inc

set @@collation_connection=utf32_czech_ci;
--source include/weight_string_chde.inc

#
# WL#4013 Unicode german2 collation
#
SET NAMES utf8;
SET collation_connection=utf32_german2_ci;
--source include/ctype_german.inc

--echo #
--echo # WL#2673 Unicode Collation Algorithm new version
--echo #
SET NAMES utf8mb4;
SET collation_connection=utf32_unicode_520_ci;
--source include/ctype_unicode520.inc

--echo #
--echo # End of 5.6 tests
--echo #


--echo #
--echo # Start of MariaDB-10.0 tests
--echo #
--echo

--echo #
--echo # MDEV-4929 Myanmar collation
--echo #
SET NAMES utf8;
SET collation_connection=utf32_myanmar_ci;
--source include/ctype_myanmar.inc

--echo #
--echo # End of MariaDB-10.0 tests
--echo #

--echo #
--echo # Start of 10.1 tests
--echo #

SET NAMES utf8;
SET collation_connection=utf32_thai_520_w2;
--source include/ctype_uca_w2.inc
--source include/ctype_thai.inc

--echo #
--echo # End of 10.1 tests
--echo #


--echo #
--echo # Start of 10.2 tests
--echo #

--echo #
--echo # MDEV-10877 xxx_unicode_nopad_ci collations
--echo #
SET NAMES utf8, character_set_connection=utf32;
let $coll='utf32_unicode_nopad_ci';
let $coll_pad='utf32_unicode_ci';
--source include/ctype_pad_all_engines.inc

let $coll='utf32_unicode_520_nopad_ci';
let $coll_pad='utf32_unicode_520_ci';
--source include/ctype_pad_all_engines.inc

SET NAMES utf8, collation_connection=utf32_unicode_520_nopad_ci;
--source include/ctype_like_range_mdev14350.inc
SET NAMES utf8;


--echo #
--echo # MDEV-25402 Assertion `!str || str != Ptr' failed in String::copy
--echo #

SET @c:="SET SESSION collation_connection=utf32_spanish_ci";
PREPARE s FROM @c;
EXECUTE s;
CREATE PROCEDURE p (IN i INT) EXECUTE s;
SET SESSION character_set_connection=latin1;
SET @c:="SET @b=get_format(DATE,'EUR')";
PREPARE s FROM @c;
EXECUTE s;
CALL p (@a);
DEALLOCATE PREPARE s;
DROP PROCEDURE p;

SET NAMES utf8;
SET @c:="SET @b=get_format(DATE,'EUR')";
PREPARE s FROM @c;
EXECUTE s;
SET collation_connection=utf32_spanish_ci;
EXECUTE s;
DEALLOCATE PREPARE s;
SET NAMES utf8;

--echo #
--echo # MDEV-23210 Assertion `(length % 4) == 0' failed in my_lengthsp_utf32 on ALTER TABLE, SELECT and INSERT
--echo #

CREATE TABLE t1 (a CHAR(1));
SET COLLATION_CONNECTION=utf32_myanmar_ci, CHARACTER_SET_CLIENT=binary;
--error ER_DUPLICATED_VALUE_IN_TYPE
ALTER TABLE t1 CHANGE a a ENUM('a','a') CHARACTER SET utf32;
ALTER TABLE t1 CHANGE a a ENUM('a','b') CHARACTER SET utf32;
SHOW CREATE TABLE t1;
DROP TABLE t1;
SET NAMES utf8;

--enable_service_connection

--echo #
--echo # End of 10.2 tests
--echo #


--echo #
--echo # Start of 10.4 tests
--echo #

--echo #
--echo # MDEV-22499 Assertion `(uint) (table_check_constraints - share->check_constraints) == (uint) (share->table_check_constraints - share->field_check_constraints)' failed in TABLE_SHARE::init_from_binary_frm_image
--echo #

SET @@SESSION.collation_connection=utf32_estonian_ci;
CREATE TABLE t1(c1 SET('a') COLLATE 'Binary',c2 JSON);
SHOW CREATE TABLE t1;
DROP TABLE t1;
SET NAMES utf8;

--echo #
--echo # End of 10.4 tests
--echo #


--echo #
--echo # Start of 10.9 tests
--echo #

--echo #
--echo # MDEV-27009 Add UCA-14.0.0 collations
--echo # Collation IDs in the protocol
--echo #

SET @charset='utf32';
--source include/ctype_uca1400_ids_using_convert.inc

--echo #
--echo # End of 10.9 tests
--echo #