1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
-- source include/have_gbk.inc
#
# Tests with the gbk character set
#
--disable_warnings
drop table if exists t1;
--enable_warnings
SET @test_character_set= 'gbk';
SET @test_collation= 'gbk_chinese_ci';
-- source include/ctype_common.inc
SET NAMES gbk;
SET collation_connection='gbk_chinese_ci';
-- source include/ctype_filesort.inc
-- source include/ctype_innodb_like.inc
-- source include/ctype_like_escape.inc
-- source include/ctype_like_range_f1f2.inc
SET collation_connection='gbk_bin';
-- source include/ctype_filesort.inc
-- source include/ctype_innodb_like.inc
-- source include/ctype_like_escape.inc
-- source include/ctype_like_range_f1f2.inc
#
# Bug#11987 mysql will truncate the text when
# the text contain GBK char:"0xA3A0" and "0xA1"
#
SET NAMES gbk;
CREATE TABLE t1 (a text) character set gbk;
INSERT INTO t1 VALUES (0xA3A0),(0xA1A1);
SELECT hex(a) FROM t1 ORDER BY a;
DROP TABLE t1;
#
# Bugs#15375: Unassigned multibyte codes are broken
# into parts when converting to Unicode.
# This query should return 0x003F0041. I.e. it should
# scan unassigned double-byte character 0xA140, convert
# it as QUESTION MARK 0x003F and then scan the next
# character, which is a single byte character 0x41.
#
select hex(convert(_gbk 0xA14041 using ucs2));
# End of 4.1 tests
#
# Bug#21620 ALTER TABLE affects other columns
#
create table t1 (c1 text not null, c2 text not null) character set gbk;
alter table t1 change c1 c1 mediumtext character set gbk not null;
show create table t1;
drop table t1;
#
# Bug#35993: severe memory corruption and crash with multibyte conversion
#
CREATE TABLE t1(a MEDIUMTEXT CHARACTER SET gbk,
b MEDIUMTEXT CHARACTER SET big5);
INSERT INTO t1 VALUES
(REPEAT(0x1125,200000), REPEAT(0x1125,200000)), ('', ''), ('', '');
SELECT a FROM t1 GROUP BY 1 LIMIT 1 INTO @nullll;
SELECT b FROM t1 GROUP BY 1 LIMIT 1 INTO @nullll;
DROP TABLES t1;
--echo End of 5.0 tests
--echo #
--echo # Start of 5.5 tests
--echo #
--echo #
--echo # Testing WL#4583 Case conversion in Asian character sets
--echo #
#
# Populate t1 with all hex digits
#
SET NAMES utf8;
SET collation_connection=gbk_chinese_ci;
CREATE TABLE t1 (b VARCHAR(2));
INSERT INTO t1 VALUES ('0'),('1'),('2'),('3'),('4'),('5'),('6'),('7');
INSERT INTO t1 VALUES ('8'),('9'),('A'),('B'),('C'),('D'),('E'),('F');
#
# Populate tables head and tail with values '00'-'FF'
#
CREATE TEMPORARY TABLE head AS SELECT concat(b1.b, b2.b) AS head FROM t1 b1, t1 b2;
CREATE TEMPORARY TABLE tail AS SELECT concat(b1.b, b2.b) AS tail FROM t1 b1, t1 b2;
DROP TABLE t1;
#
# Populate table t1 with all codes [80..FF][20..FF]
# Expected valid gbk codes [81..FE][40..7E,80..FE]
#
CREATE TABLE t1 AS
SELECT concat(head, tail) AS code, ' ' AS a
FROM head, tail
WHERE (head BETWEEN '80' AND 'FF') AND (tail BETWEEN '20' AND 'FF')
ORDER BY head, tail;
DROP TEMPORARY TABLE head, tail;
SHOW CREATE TABLE t1;
UPDATE t1 SET a=unhex(code) ORDER BY code;
SELECT COUNT(*) FROM t1 WHERE a<>'';
#
# Display all characters that have upper or lower case mapping.
#
SELECT code, hex(upper(a)), hex(lower(a)),a, upper(a), lower(a) FROM t1 WHERE hex(a)<>hex(upper(a)) OR hex(a)<>hex(lower(a));
#
# Make sure all possible conversion happened
#
# Expect U+216A to U+216B ROMAN NUMERAL ELEVEN to ROMAN TWELVE
#
SELECT * FROM t1
WHERE HEX(CAST(LOWER(a) AS CHAR CHARACTER SET utf8)) <>
HEX(LOWER(CAST(a AS CHAR CHARACTER SET utf8))) ORDER BY code;
#
# Expect
# U+00E0 LATIN SMALL LETTER A WITH GRAVE
# U+00E1 LATIN SMALL LETTER A WITH ACUTE
# U+00E8 LATIN SMALL LETTER E WITH GRAVE
# U+00E9 LATIN SMALL LETTER E WITH ACUTE
# U+00EA LATIN SMALL LETTER E WITH CIRCUMFLEX
# U+00EC LATIN SMALL LETTER I WITH GRAVE
# U+00ED LATIN SMALL LETTER I WITH ACUTE
# U+00F2 LATIN SMALL LETTER O WITH GRAVE
# U+00F3 LATIN SMALL LETTER O WITH ACUTE
# U+00F9 LATIN SMALL LETTER U WITH GRAVE
# U+00FA LATIN SMALL LETTER U WITH ACUTE
# U+00FC LATIN SMALL LETTER U WITH DIAERESIS
# U+0101 LATIN SMALL LETTER A WITH MACRON
# U+0113 LATIN SMALL LETTER E WITH MACRON
# U+011B LATIN SMALL LETTER E WITH CARON
# U+012B LATIN SMALL LETTER I WITH MACRON
# U+0144 LATIN SMALL LETTER N WITH ACUTE
# U+0148 LATIN SMALL LETTER N WITH CARON
# U+014D LATIN SMALL LETTER O WITH MACRON
# U+016B LATIN SMALL LETTER U WITH MACRON
# U+01CE LATIN SMALL LETTER A WITH CARON
# U+01D0 LATIN SMALL LETTER I WITH CARON
# U+01D2 LATIN SMALL LETTER O WITH CARON
# U+01D4 LATIN SMALL LETTER U WITH CARON
# U+01D6 LATIN SMALL LETTER U WITH DIAERESIS AND MACRON
# U+01D8 LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE
# U+01DA LATIN SMALL LETTER U WITH DIAERESIS AND CARON
# U+01DC LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE
#
SELECT * FROM t1
WHERE HEX(CAST(UPPER(a) AS CHAR CHARACTER SET utf8)) <>
HEX(UPPER(CAST(a AS CHAR CHARACTER SET utf8))) ORDER BY code;
DROP TABLE t1;
--echo #
--echo # End of 5.5 tests
--echo #
|
