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
|
<?php
/**
* @covers \Collation
* @covers \IcuCollation
* @covers \IdentityCollation
* @covers \UppercaseCollation
*/
class CollationTest extends MediaWikiLangTestCase {
/**
* Test to make sure, that if you
* have "X" and "XY", the binary
* sortkey also has "X" being a
* prefix of "XY". Our collation
* code makes this assumption.
*
* @param string $lang Language code for collator
* @param string $base
* @param string $extended String containing base as a prefix.
*
* @covers \Collation::getSortKey()
* @covers \IcuCollation::getSortKey()
* @covers \IdentityCollation::getSortKey()
* @covers \UppercaseCollation::getSortKey()
* @dataProvider prefixDataProvider
*/
public function testIsPrefix( $lang, $base, $extended ) {
$cp = Collator::create( $lang );
$cp->setStrength( Collator::PRIMARY );
$baseBin = $cp->getSortKey( $base );
$extendedBin = $cp->getSortKey( $extended );
$this->assertStringStartsWith( $baseBin, $extendedBin, "$base is not a prefix of $extended" );
}
public static function prefixDataProvider() {
return [
[ 'en', 'A', 'AA' ],
[ 'en', 'A', 'AAA' ],
[ 'en', 'Д', 'ДЂ' ],
[ 'en', 'Д', 'ДA' ],
// 'Ʒ' should expand to 'Z ' (note space).
[ 'fi', 'Z', 'Ʒ' ],
// 'Þ' should expand to 'th'
[ 'sv', 't', 'Þ' ],
// Javanese is a limited use alphabet, so should have 3 bytes
// per character, so do some tests with it.
[ 'en', 'ꦲ', 'ꦲꦤ' ],
[ 'en', 'ꦲ', 'ꦲД' ],
[ 'en', 'A', 'Aꦲ' ],
];
}
/**
* Opposite of testIsPrefix
*
* @covers \Collation::getSortKey()
* @covers \IcuCollation::getSortKey()
* @covers \IdentityCollation::getSortKey()
* @covers \UppercaseCollation::getSortKey()
* @dataProvider notPrefixDataProvider
*/
public function testNotIsPrefix( $lang, $base, $extended ) {
$cp = Collator::create( $lang );
$cp->setStrength( Collator::PRIMARY );
$baseBin = $cp->getSortKey( $base );
$extendedBin = $cp->getSortKey( $extended );
$this->assertStringStartsNotWith( $baseBin, $extendedBin, "$base is a prefix of $extended" );
}
public static function notPrefixDataProvider() {
return [
[ 'en', 'A', 'B' ],
[ 'en', 'AC', 'ABC' ],
[ 'en', 'Z', 'Ʒ' ],
[ 'en', 'A', 'ꦲ' ],
];
}
/**
* Test correct first letter is fetched.
*
* @param string $collation Collation name (aka uca-en)
* @param string $string String to get first letter of
* @param string $firstLetter Expected first letter.
*
* @covers \Collation::getFirstLetter()
* @covers \IcuCollation::getFirstLetter()
* @covers \IdentityCollation::getFirstLetter()
* @covers \UppercaseCollation::getFirstLetter()
* @dataProvider firstLetterProvider
*/
public function testGetFirstLetter( $collation, $string, $firstLetter ) {
$col = $this->getServiceContainer()->getCollationFactory()->makeCollation( $collation );
$this->assertEquals( $firstLetter, $col->getFirstLetter( $string ) );
}
public static function firstLetterProvider() {
return [
[ 'uppercase', 'Abc', 'A' ],
[ 'uppercase', 'abc', 'A' ],
[ 'identity', 'abc', 'a' ],
[ 'uca-en', 'abc', 'A' ],
[ 'uca-en', ' ', ' ' ],
[ 'uca-en', 'Êveryone', 'E' ],
[ 'uca-vi', 'Êveryone', 'Ê' ],
// Make sure thorn is not a first letter.
[ 'uca-sv', 'The', 'T' ],
[ 'uca-sv', 'Å', 'Å' ],
[ 'uca-hu', 'dzsdo', 'Dzs' ],
[ 'uca-hu', 'dzdso', 'Dz' ],
[ 'uca-hu', 'CSD', 'Cs' ],
[ 'uca-root', 'CSD', 'C' ],
[ 'uca-fi', 'Ǥ', 'G' ],
[ 'uca-fi', 'Ŧ', 'T' ],
[ 'uca-fi', 'Ʒ', 'Z' ],
[ 'uca-fi', 'Ŋ', 'N' ],
[ 'uppercase-ba', 'в', 'В' ],
[ 'uppercase-smn', 'đ', 'Đ' ],
];
}
}
|
