Debian Codegraph @

test/icu.test

raw
1 # 2007 May 1
2 #
3 # The author disclaims copyright to this source code. In place of
4 # a legal notice, here is a blessing:
5 #
6 # May you do good and not evil.
7 # May you find forgiveness for yourself and forgive others.
8 # May you share freely, never taking more than you give.
9 #
10 #***********************************************************************
11 #
12 # $Id: icu.test,v 1.2 2008/07/12 14:52:20 drh Exp $
13 #
14
15 set testdir [file dirname $argv0]
16 source $testdir/tester.tcl
17
18 ifcapable !icu&&!icu_collations {
19 finish_test
20 return
21 }
22
23 # Create a table to work with.
24 #
25 execsql {CREATE TABLE test1(i1 int, i2 int, r1 real, r2 real, t1 text, t2 text)}
26 execsql {INSERT INTO test1 VALUES(1,2,1.1,2.2,'hello','world')}
27 proc test_expr {name settings expr result} {
28 do_test $name [format {
29 lindex [db eval {
30 BEGIN;
31 UPDATE test1 SET %s;
32 SELECT %s FROM test1;
33 ROLLBACK;
34 }] 0
35 } $settings $expr] $result
36 }
37
38 ifcapable icu {
39
40 # Tests of the REGEXP operator.
41 #
42 test_expr icu-1.1 {i1='hello'} {i1 REGEXP 'hello'} 1
43 test_expr icu-1.2 {i1='hello'} {i1 REGEXP '.ello'} 1
44 test_expr icu-1.3 {i1='hello'} {i1 REGEXP '.ell'} 0
45 test_expr icu-1.4 {i1='hello'} {i1 REGEXP '.ell.*'} 1
46 test_expr icu-1.5 {i1=NULL} {i1 REGEXP '.ell.*'} {}
47
48 # Some non-ascii characters with defined case mappings
49 #
50 set ::EGRAVE "\xC8"
51 set ::egrave "\xE8"
52
53 set ::OGRAVE "\xD2"
54 set ::ograve "\xF2"
55
56 # That German letter that looks a bit like a B. The
57 # upper-case version of which is "SS" (two characters).
58 #
59 set ::szlig "\xDF"
60
61 # Tests of the upper()/lower() functions.
62 #
63 test_expr icu-2.1 {i1='HellO WorlD'} {upper(i1)} {HELLO WORLD}
64 test_expr icu-2.2 {i1='HellO WorlD'} {lower(i1)} {hello world}
65 test_expr icu-2.3 {i1=$::egrave} {lower(i1)} $::egrave
66 test_expr icu-2.4 {i1=$::egrave} {upper(i1)} $::EGRAVE
67 test_expr icu-2.5 {i1=$::ograve} {lower(i1)} $::ograve
68 test_expr icu-2.6 {i1=$::ograve} {upper(i1)} $::OGRAVE
69 test_expr icu-2.3 {i1=$::EGRAVE} {lower(i1)} $::egrave
70 test_expr icu-2.4 {i1=$::EGRAVE} {upper(i1)} $::EGRAVE
71 test_expr icu-2.5 {i1=$::OGRAVE} {lower(i1)} $::ograve
72 test_expr icu-2.6 {i1=$::OGRAVE} {upper(i1)} $::OGRAVE
73
74 test_expr icu-2.7 {i1=$::szlig} {upper(i1)} "SS"
75 test_expr icu-2.8 {i1='SS'} {lower(i1)} "ss"
76
77 do_execsql_test icu-2.9 {
78 SELECT upper(char(0xfb04,0xfb04,0xfb04,0xfb04));
79 } {FFLFFLFFLFFL}
80
81 # In turkish (locale="tr_TR"), the lower case version of I
82 # is "small dotless i" (code point 0x131 (decimal 305)).
83 #
84 set ::small_dotless_i "\u0131"
85 test_expr icu-3.1 {i1='I'} {lower(i1)} "i"
86 test_expr icu-3.2 {i1='I'} {lower(i1, 'tr_tr')} $::small_dotless_i
87 test_expr icu-3.3 {i1='I'} {lower(i1, 'en_AU')} "i"
88 }
89
90 #--------------------------------------------------------------------
91 # Test the collation sequence function.
92 #
93 do_test icu-4.1 {
94 execsql {
95 CREATE TABLE fruit(name);
96 INSERT INTO fruit VALUES('plum');
97 INSERT INTO fruit VALUES('cherry');
98 INSERT INTO fruit VALUES('apricot');
99 INSERT INTO fruit VALUES('peach');
100 INSERT INTO fruit VALUES('chokecherry');
101 INSERT INTO fruit VALUES('yamot');
102 }
103 } {}
104 do_test icu-4.2 {
105 execsql {
106 SELECT icu_load_collation('en_US', 'AmericanEnglish');
107 SELECT icu_load_collation('lt_LT', 'Lithuanian');
108 }
109 execsql {
110 SELECT name FROM fruit ORDER BY name COLLATE AmericanEnglish ASC;
111 }
112 } {apricot cherry chokecherry peach plum yamot}
113
114
115 # Test collation using Lithuanian rules. In the Lithuanian
116 # alphabet, "y" comes right after "i".
117 #
118 do_test icu-4.3 {
119 execsql {
120 SELECT name FROM fruit ORDER BY name COLLATE Lithuanian ASC;
121 }
122 } {apricot cherry chokecherry yamot peach plum}
123
124 #-------------------------------------------------------------------------
125 # Test that it is not possible to call the ICU regex() function with
126 # anything other than exactly two arguments. See also:
127 #
128 # http://src.chromium.org/viewvc/chrome/trunk/src/third_party/sqlite/icu-regexp.patch?revision=34807&view=markup
129 #
130 ifcapable icu {
131 do_catchsql_test icu-5.1 { SELECT regexp('a[abc]c.*', 'abc') } {0 1}
132 do_catchsql_test icu-5.2 {
133 SELECT regexp('a[abc]c.*')
134 } {1 {wrong number of arguments to function regexp()}}
135 do_catchsql_test icu-5.3 {
136 SELECT regexp('a[abc]c.*', 'abc', 'c')
137 } {1 {wrong number of arguments to function regexp()}}
138 do_catchsql_test icu-5.4 {
139 SELECT 'abc' REGEXP 'a[abc]c.*'
140 } {0 1}
141 do_catchsql_test icu-5.5 {SELECT 'abc' REGEXP } {1 {incomplete input}}
142 do_catchsql_test icu-5.6 {SELECT 'abc' REGEXP, 1} {1 {near ",": syntax error}}
143
144 do_malloc_test icu-6.10 -sqlbody {
145 SELECT upper(char(0xfb04,0xdf,0xfb04,0xe8,0xfb04));
146 }
147 }
148
149 # 2020-03-19
150 # The ESCAPE clause on LIKE takes precedence over wildcards
151 #
152 do_execsql_test icu-6.0 {
153 DROP TABLE IF EXISTS t1;
154 CREATE TABLE t1(id INTEGER PRIMARY KEY, x TEXT);
155 INSERT INTO t1 VALUES
156 (1,'abcde'),
157 (2,'abc_'),
158 (3,'abc__'),
159 (4,'abc%'),
160 (5,'abc%%');
161 SELECT id FROM t1 WHERE x LIKE 'abc%%' ESCAPE '%';
162 } {4}
163 do_execsql_test icu-6.1 {
164 SELECT id FROM t1 WHERE x LIKE 'abc__' ESCAPE '_';
165 } {2}
166
167 # 2024-04-02
168 # Optional 3rd argument to icu_load_collation() that specifies
169 # the "strength" of comparison.
170 #
171 reset_db
172 do_catchsql_test icu-7.1 {
173 SELECT icu_load_collation('en_US','error','xyzzy');
174 } {1 {unknown collation strength "xyzzy" - should be one of: PRIMARY SECONDARY TERTIARY DEFAULT QUARTERNARY IDENTICAL}}
175 do_execsql_test icu-7.2 {
176 SELECT icu_load_collation('en_US','prim','PRIMARY'),
177 icu_load_collation('en_US','dflt','DEFAULT');
178 } {{} {}}
179 do_execsql_test icu-7.3 {
180 SELECT char(0x100)=='a', char(0x100)=='a' COLLATE dflt, char(0x100)=='a' COLLATE prim;
181 } {0 0 1}
182
183 finish_test