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
181
182
183
|
# 2007 May 1
#
# The author disclaims copyright to this source code. In place of
# a legal notice, here is a blessing:
#
# May you do good and not evil.
# May you find forgiveness for yourself and forgive others.
# May you share freely, never taking more than you give.
#
#***********************************************************************
#
# $Id: icu.test,v 1.2 2008/07/12 14:52:20 drh Exp $
#
set testdir [file dirname $argv0]
source $testdir/tester.tcl
ifcapable !icu&&!icu_collations {
finish_test
return
}
# Create a table to work with.
#
execsql {CREATE TABLE test1(i1 int, i2 int, r1 real, r2 real, t1 text, t2 text)}
execsql {INSERT INTO test1 VALUES(1,2,1.1,2.2,'hello','world')}
proc test_expr {name settings expr result} {
do_test $name [format {
lindex [db eval {
BEGIN;
UPDATE test1 SET %s;
SELECT %s FROM test1;
ROLLBACK;
}] 0
} $settings $expr] $result
}
ifcapable icu {
# Tests of the REGEXP operator.
#
test_expr icu-1.1 {i1='hello'} {i1 REGEXP 'hello'} 1
test_expr icu-1.2 {i1='hello'} {i1 REGEXP '.ello'} 1
test_expr icu-1.3 {i1='hello'} {i1 REGEXP '.ell'} 0
test_expr icu-1.4 {i1='hello'} {i1 REGEXP '.ell.*'} 1
test_expr icu-1.5 {i1=NULL} {i1 REGEXP '.ell.*'} {}
# Some non-ascii characters with defined case mappings
#
set ::EGRAVE "\xC8"
set ::egrave "\xE8"
set ::OGRAVE "\xD2"
set ::ograve "\xF2"
# That German letter that looks a bit like a B. The
# upper-case version of which is "SS" (two characters).
#
set ::szlig "\xDF"
# Tests of the upper()/lower() functions.
#
test_expr icu-2.1 {i1='HellO WorlD'} {upper(i1)} {HELLO WORLD}
test_expr icu-2.2 {i1='HellO WorlD'} {lower(i1)} {hello world}
test_expr icu-2.3 {i1=$::egrave} {lower(i1)} $::egrave
test_expr icu-2.4 {i1=$::egrave} {upper(i1)} $::EGRAVE
test_expr icu-2.5 {i1=$::ograve} {lower(i1)} $::ograve
test_expr icu-2.6 {i1=$::ograve} {upper(i1)} $::OGRAVE
test_expr icu-2.3 {i1=$::EGRAVE} {lower(i1)} $::egrave
test_expr icu-2.4 {i1=$::EGRAVE} {upper(i1)} $::EGRAVE
test_expr icu-2.5 {i1=$::OGRAVE} {lower(i1)} $::ograve
test_expr icu-2.6 {i1=$::OGRAVE} {upper(i1)} $::OGRAVE
test_expr icu-2.7 {i1=$::szlig} {upper(i1)} "SS"
test_expr icu-2.8 {i1='SS'} {lower(i1)} "ss"
do_execsql_test icu-2.9 {
SELECT upper(char(0xfb04,0xfb04,0xfb04,0xfb04));
} {FFLFFLFFLFFL}
# In turkish (locale="tr_TR"), the lower case version of I
# is "small dotless i" (code point 0x131 (decimal 305)).
#
set ::small_dotless_i "\u0131"
test_expr icu-3.1 {i1='I'} {lower(i1)} "i"
test_expr icu-3.2 {i1='I'} {lower(i1, 'tr_tr')} $::small_dotless_i
test_expr icu-3.3 {i1='I'} {lower(i1, 'en_AU')} "i"
}
#--------------------------------------------------------------------
# Test the collation sequence function.
#
do_test icu-4.1 {
execsql {
CREATE TABLE fruit(name);
INSERT INTO fruit VALUES('plum');
INSERT INTO fruit VALUES('cherry');
INSERT INTO fruit VALUES('apricot');
INSERT INTO fruit VALUES('peach');
INSERT INTO fruit VALUES('chokecherry');
INSERT INTO fruit VALUES('yamot');
}
} {}
do_test icu-4.2 {
execsql {
SELECT icu_load_collation('en_US', 'AmericanEnglish');
SELECT icu_load_collation('lt_LT', 'Lithuanian');
}
execsql {
SELECT name FROM fruit ORDER BY name COLLATE AmericanEnglish ASC;
}
} {apricot cherry chokecherry peach plum yamot}
# Test collation using Lithuanian rules. In the Lithuanian
# alphabet, "y" comes right after "i".
#
do_test icu-4.3 {
execsql {
SELECT name FROM fruit ORDER BY name COLLATE Lithuanian ASC;
}
} {apricot cherry chokecherry yamot peach plum}
#-------------------------------------------------------------------------
# Test that it is not possible to call the ICU regex() function with
# anything other than exactly two arguments. See also:
#
# http://src.chromium.org/viewvc/chrome/trunk/src/third_party/sqlite/icu-regexp.patch?revision=34807&view=markup
#
ifcapable icu {
do_catchsql_test icu-5.1 { SELECT regexp('a[abc]c.*', 'abc') } {0 1}
do_catchsql_test icu-5.2 {
SELECT regexp('a[abc]c.*')
} {1 {wrong number of arguments to function regexp()}}
do_catchsql_test icu-5.3 {
SELECT regexp('a[abc]c.*', 'abc', 'c')
} {1 {wrong number of arguments to function regexp()}}
do_catchsql_test icu-5.4 {
SELECT 'abc' REGEXP 'a[abc]c.*'
} {0 1}
do_catchsql_test icu-5.5 {SELECT 'abc' REGEXP } {1 {incomplete input}}
do_catchsql_test icu-5.6 {SELECT 'abc' REGEXP, 1} {1 {near ",": syntax error}}
do_malloc_test icu-6.10 -sqlbody {
SELECT upper(char(0xfb04,0xdf,0xfb04,0xe8,0xfb04));
}
}
# 2020-03-19
# The ESCAPE clause on LIKE takes precedence over wildcards
#
do_execsql_test icu-6.0 {
DROP TABLE IF EXISTS t1;
CREATE TABLE t1(id INTEGER PRIMARY KEY, x TEXT);
INSERT INTO t1 VALUES
(1,'abcde'),
(2,'abc_'),
(3,'abc__'),
(4,'abc%'),
(5,'abc%%');
SELECT id FROM t1 WHERE x LIKE 'abc%%' ESCAPE '%';
} {4}
do_execsql_test icu-6.1 {
SELECT id FROM t1 WHERE x LIKE 'abc__' ESCAPE '_';
} {2}
# 2024-04-02
# Optional 3rd argument to icu_load_collation() that specifies
# the "strength" of comparison.
#
reset_db
do_catchsql_test icu-7.1 {
SELECT icu_load_collation('en_US','error','xyzzy');
} {1 {unknown collation strength "xyzzy" - should be one of: PRIMARY SECONDARY TERTIARY DEFAULT QUARTERNARY IDENTICAL}}
do_execsql_test icu-7.2 {
SELECT icu_load_collation('en_US','prim','PRIMARY'),
icu_load_collation('en_US','dflt','DEFAULT');
} {{} {}}
do_execsql_test icu-7.3 {
SELECT char(0x100)=='a', char(0x100)=='a' COLLATE dflt, char(0x100)=='a' COLLATE prim;
} {0 0 1}
finish_test
|
