forked from alibaba/AliSQL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ctype_big5.test
180 lines (157 loc) · 4.99 KB
/
ctype_big5.test
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
-- source include/have_big5.inc
#
# Tests with the big5 character set
#
--disable_warnings
drop table if exists t1;
--enable_warnings
SET @test_character_set= 'big5';
SET @test_collation= 'big5_chinese_ci';
-- source include/ctype_common.inc
SET NAMES big5;
SET collation_connection='big5_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
-- source include/ctype_ascii_order.inc
SET collation_connection='big5_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
#
# Bugs#9357: TEXT columns break string with special word in BIG5 charset.
#
SET NAMES big5;
CREATE TABLE t1 (a text) character set big5;
INSERT INTO t1 VALUES ('ùØ');
SELECT * FROM t1;
DROP TABLE t1;
#
# BUG#12075 - FULLTEXT non-functional for big5 strings
#
CREATE TABLE t1 (a CHAR(50) CHARACTER SET big5 NOT NULL, FULLTEXT(a));
INSERT INTO t1 VALUES(0xA741ADCCA66EB6DC20A7DAADCCABDCA66E);
SELECT HEX(a) FROM t1 WHERE MATCH(a) AGAINST (0xA741ADCCA66EB6DC IN BOOLEAN MODE);
DROP TABLE t1;
#
# Bug#12476 Some big5 codes are still missing.
#
set names big5;
create table t1 (a char character set big5);
insert into t1 values (0xF9D6),(0xF9D7),(0xF9D8),(0xF9D9);
insert into t1 values (0xF9DA),(0xF9DB),(0xF9DC);
# Check round trip
select hex(a) a, hex(@u:=convert(a using utf8)) b,
hex(convert(@u using big5)) c from t1 order by a;
# Check that there is no "illegal mix of collations" error with Unicode.
alter table t1 convert to character set utf8;
select hex(a) from t1 where a = _big5 0xF9DC;
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 0xC840, convert
# it as QUESTION MARK 0x003F and then scan the next
# character, which is a single byte character 0x41.
#
select hex(convert(_big5 0xC84041 using ucs2));
--echo End of 4.1 tests
#
# Bug#26711 "binary content 0x00 sometimes becomes 0x5C 0x00 after dump/load"
#
set names big5;
create table t1 (a blob);
insert into t1 values (0xEE00);
select * into outfile 'test/t1.txt' from t1;
delete from t1;
let $MYSQLD_DATADIR= `select @@datadir`;
--replace_result $MYSQLD_DATADIR MYSQLD_DATADIR
--eval select hex(load_file('$MYSQLD_DATADIR/test/t1.txt'));
load data infile 't1.txt' into table t1;
select hex(a) from t1;
--remove_file $MYSQLD_DATADIR/test/t1.txt
drop table 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=big5_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 values [80..FF][20..FF]
# Expected valid big5 codes: [A1..F9][40..7E,A1..FE] (89x157=13973)
#
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;
SELECT COUNT(*) FROM 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+2160 to U+2169 ROMAN NUMERAL ONE to ROMAN NUMERAL TEN
#
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+0430 to U+0433 CYRILLIC SMALL LETTER A, BE, VE, GHE
# Expect U+043D to U+0442 CYRILLIC SMALL LETTER EN, O, PE, ER, ES, TE
#
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 #
--echo #
--echo # Start of 5.6 tests
--echo #
--echo #
--echo # WL#3664 WEIGHT_STRING
--echo #
set names big5;
--source include/weight_string.inc
--source include/weight_string_l1.inc
--source include/weight_string_A1A1.inc
set collation_connection=big5_bin;
--source include/weight_string.inc
--source include/weight_string_l1.inc
--source include/weight_string_A1A1.inc
--echo #
--echo # Bugs#12635232: VALGRIND WARNINGS: IS_IPV6, IS_IPV4, INET6_ATON,
--echo # INET6_NTOA + MULTIBYTE CHARSET.
--echo #
SET NAMES big5;
--source include/ctype_inet.inc
--echo #
--echo # End of 5.6 tests
--echo #