xref: /sqlite-3.40.0/test/icu.test (revision 3b328522) 
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
15set testdir [file dirname $argv0]
16source $testdir/tester.tcl
17
18ifcapable !icu {
19  finish_test
20  return
21}
22
23# Create a table to work with.
24#
25execsql {CREATE TABLE test1(i1 int, i2 int, r1 real, r2 real, t1 text, t2 text)}
26execsql {INSERT INTO test1 VALUES(1,2,1.1,2.2,'hello','world')}
27proc 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] $result
36}
37
38# Tests of the REGEXP operator.
39#
40test_expr icu-1.1 {i1='hello'} {i1 REGEXP 'hello'}  1
41test_expr icu-1.2 {i1='hello'} {i1 REGEXP '.ello'}  1
42test_expr icu-1.3 {i1='hello'} {i1 REGEXP '.ell'}   0
43test_expr icu-1.4 {i1='hello'} {i1 REGEXP '.ell.*'} 1
44test_expr icu-1.5 {i1=NULL}    {i1 REGEXP '.ell.*'} {}
45
46# Some non-ascii characters with defined case mappings
47#
48set ::EGRAVE "\xC8"
49set ::egrave "\xE8"
50
51set ::OGRAVE "\xD2"
52set ::ograve "\xF2"
53
54# That German letter that looks a bit like a B. The
55# upper-case version of which is "SS" (two characters).
56#
57set ::szlig "\xDF"
58
59# Tests of the upper()/lower() functions.
60#
61test_expr icu-2.1 {i1='HellO WorlD'} {upper(i1)} {HELLO WORLD}
62test_expr icu-2.2 {i1='HellO WorlD'} {lower(i1)} {hello world}
63test_expr icu-2.3 {i1=$::egrave} {lower(i1)}     $::egrave
64test_expr icu-2.4 {i1=$::egrave} {upper(i1)}     $::EGRAVE
65test_expr icu-2.5 {i1=$::ograve} {lower(i1)}     $::ograve
66test_expr icu-2.6 {i1=$::ograve} {upper(i1)}     $::OGRAVE
67test_expr icu-2.3 {i1=$::EGRAVE} {lower(i1)}     $::egrave
68test_expr icu-2.4 {i1=$::EGRAVE} {upper(i1)}     $::EGRAVE
69test_expr icu-2.5 {i1=$::OGRAVE} {lower(i1)}     $::ograve
70test_expr icu-2.6 {i1=$::OGRAVE} {upper(i1)}     $::OGRAVE
71
72test_expr icu-2.7 {i1=$::szlig} {upper(i1)}      "SS"
73test_expr icu-2.8 {i1='SS'} {lower(i1)}          "ss"
74
75do_execsql_test icu-2.9 {
76  SELECT upper(char(0xfb04,0xfb04,0xfb04,0xfb04));
77} {FFLFFLFFLFFL}
78
79# In turkish (locale="tr_TR"), the lower case version of I
80# is "small dotless i" (code point 0x131 (decimal 305)).
81#
82set ::small_dotless_i "\u0131"
83test_expr icu-3.1 {i1='I'} {lower(i1)}           "i"
84test_expr icu-3.2 {i1='I'} {lower(i1, 'tr_tr')}  $::small_dotless_i
85test_expr icu-3.3 {i1='I'} {lower(i1, 'en_AU')}  "i"
86
87#--------------------------------------------------------------------
88# Test the collation sequence function.
89#
90do_test icu-4.1 {
91  execsql {
92    CREATE TABLE fruit(name);
93    INSERT INTO fruit VALUES('plum');
94    INSERT INTO fruit VALUES('cherry');
95    INSERT INTO fruit VALUES('apricot');
96    INSERT INTO fruit VALUES('peach');
97    INSERT INTO fruit VALUES('chokecherry');
98    INSERT INTO fruit VALUES('yamot');
99  }
100} {}
101do_test icu-4.2 {
102  execsql {
103    SELECT icu_load_collation('en_US', 'AmericanEnglish');
104    SELECT icu_load_collation('lt_LT', 'Lithuanian');
105  }
106  execsql {
107    SELECT name FROM fruit ORDER BY name COLLATE AmericanEnglish ASC;
108  }
109} {apricot cherry chokecherry peach plum yamot}
110
111
112# Test collation using Lithuanian rules. In the Lithuanian
113# alphabet, "y" comes right after "i".
114#
115do_test icu-4.3 {
116  execsql {
117    SELECT name FROM fruit ORDER BY name COLLATE Lithuanian ASC;
118  }
119} {apricot cherry chokecherry yamot peach plum}
120
121#-------------------------------------------------------------------------
122# Test that it is not possible to call the ICU regex() function with
123# anything other than exactly two arguments. See also:
124#
125#   http://src.chromium.org/viewvc/chrome/trunk/src/third_party/sqlite/icu-regexp.patch?revision=34807&view=markup
126#
127do_catchsql_test icu-5.1 { SELECT regexp('a[abc]c.*', 'abc') } {0 1}
128do_catchsql_test icu-5.2 {
129  SELECT regexp('a[abc]c.*')
130} {1 {wrong number of arguments to function regexp()}}
131do_catchsql_test icu-5.3 {
132  SELECT regexp('a[abc]c.*', 'abc', 'c')
133} {1 {wrong number of arguments to function regexp()}}
134do_catchsql_test icu-5.4 {
135  SELECT 'abc' REGEXP 'a[abc]c.*'
136} {0 1}
137do_catchsql_test icu-5.4 { SELECT 'abc' REGEXP }    {1 {near " ": syntax error}}
138do_catchsql_test icu-5.5 { SELECT 'abc' REGEXP, 1 } {1 {near ",": syntax error}}
139
140
141do_malloc_test icu-6.10 -sqlbody {
142  SELECT upper(char(0xfb04,0xdf,0xfb04,0xe8,0xfb04));
143}
144
145finish_test
146