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
|
<?php
namespace Wikimedia\Tests;
use MediaWikiCoversValidator;
use PHPUnit\Framework\TestCase;
use StringUtils;
/**
* @covers \StringUtils
*/
class StringUtilsTest extends TestCase {
use MediaWikiCoversValidator;
/**
* @dataProvider provideStringsForIsUtf8Check
*/
public function testIsUtf8( bool $expected, string $string ) {
$this->assertEquals( $expected, StringUtils::isUtf8( $string ),
'Testing string "' . $this->escaped( $string ) . '"' );
}
/**
* Print high range characters as a hexadecimal
*/
private function escaped( string $string ): string {
return preg_replace_callback( '/[\x80-\xFF]/',
static fn ( $m ) => '\x' . dechex( ord( $m[0] ) ),
$string
);
}
/**
* See also "UTF-8 decoder capability and stress test" by
* Markus Kuhn:
* http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
*/
public static function provideStringsForIsUtf8Check() {
// Expected return values for StringUtils::isUtf8()
$PASS = true;
$FAIL = false;
return [
'some ASCII' => [ $PASS, 'Some ASCII' ],
'euro sign' => [ $PASS, "Euro sign €" ],
'first possible sequence 1 byte' => [ $PASS, "\x00" ],
'first possible sequence 2 bytes' => [ $PASS, "\xc2\x80" ],
'first possible sequence 3 bytes' => [ $PASS, "\xe0\xa0\x80" ],
'first possible sequence 4 bytes' => [ $PASS, "\xf0\x90\x80\x80" ],
'first possible sequence 5 bytes' => [ $FAIL, "\xf8\x88\x80\x80\x80" ],
'first possible sequence 6 bytes' => [ $FAIL, "\xfc\x84\x80\x80\x80\x80" ],
'last possible sequence 1 byte' => [ $PASS, "\x7f" ],
'last possible sequence 2 bytes' => [ $PASS, "\xdf\xbf" ],
'last possible sequence 3 bytes' => [ $PASS, "\xef\xbf\xbf" ],
'last possible sequence 4 bytes (U+1FFFFF)' => [ $FAIL, "\xf7\xbf\xbf\xbf" ],
'last possible sequence 5 bytes' => [ $FAIL, "\xfb\xbf\xbf\xbf\xbf" ],
'last possible sequence 6 bytes' => [ $FAIL, "\xfd\xbf\xbf\xbf\xbf\xbf" ],
'boundary 1' => [ $PASS, "\xed\x9f\xbf" ],
'boundary 2' => [ $PASS, "\xee\x80\x80" ],
'boundary 3' => [ $PASS, "\xef\xbf\xbd" ],
'boundary 4' => [ $PASS, "\xf2\x80\x80\x80" ],
'boundary 5 (U+FFFFF)' => [ $PASS, "\xf3\xbf\xbf\xbf" ],
'boundary 6 (U+100000)' => [ $PASS, "\xf4\x80\x80\x80" ],
'boundary 7 (U+10FFFF)' => [ $PASS, "\xf4\x8f\xbf\xbf" ],
'boundary 8 (U+110000)' => [ $FAIL, "\xf4\x90\x80\x80" ],
'malformed 1' => [ $FAIL, "\x80" ],
'malformed 2' => [ $FAIL, "\xbf" ],
'malformed 3' => [ $FAIL, "\x80\xbf" ],
'malformed 4' => [ $FAIL, "\x80\xbf\x80" ],
'malformed 5' => [ $FAIL, "\x80\xbf\x80\xbf" ],
'malformed 6' => [ $FAIL, "\x80\xbf\x80\xbf\x80" ],
'malformed 7' => [ $FAIL, "\x80\xbf\x80\xbf\x80\xbf" ],
'malformed 8' => [ $FAIL, "\x80\xbf\x80\xbf\x80\xbf\x80" ],
'last byte missing 1' => [ $FAIL, "\xc0" ],
'last byte missing 2' => [ $FAIL, "\xe0\x80" ],
'last byte missing 3' => [ $FAIL, "\xf0\x80\x80" ],
'last byte missing 4' => [ $FAIL, "\xf8\x80\x80\x80" ],
'last byte missing 5' => [ $FAIL, "\xfc\x80\x80\x80\x80" ],
'last byte missing 6' => [ $FAIL, "\xdf" ],
'last byte missing 7' => [ $FAIL, "\xef\xbf" ],
'last byte missing 8' => [ $FAIL, "\xf7\xbf\xbf" ],
'last byte missing 9' => [ $FAIL, "\xfb\xbf\xbf\xbf" ],
'last byte missing 10' => [ $FAIL, "\xfd\xbf\xbf\xbf\xbf" ],
'extra continuation byte 1' => [ $FAIL, "e\xaf" ],
'extra continuation byte 2' => [ $FAIL, "\xc3\x89\xaf" ],
'extra continuation byte 3' => [ $FAIL, "\xef\xbc\xa5\xaf" ],
'extra continuation byte 4' => [ $FAIL, "\xf0\x9d\x99\xb4\xaf" ],
'impossible bytes 1' => [ $FAIL, "\xfe" ],
'impossible bytes 2' => [ $FAIL, "\xff" ],
'impossible bytes 3' => [ $FAIL, "\xfe\xfe\xff\xff" ],
'overlong sequences 1' => [ $FAIL, "\xc0\xaf" ],
'overlong sequences 2' => [ $FAIL, "\xc1\xaf" ],
'overlong sequences 3' => [ $FAIL, "\xe0\x80\xaf" ],
'overlong sequences 4' => [ $FAIL, "\xf0\x80\x80\xaf" ],
'overlong sequences 5' => [ $FAIL, "\xf8\x80\x80\x80\xaf" ],
'overlong sequences 6' => [ $FAIL, "\xfc\x80\x80\x80\x80\xaf" ],
'maximum overlong sequences 1' => [ $FAIL, "\xc1\xbf" ],
'maximum overlong sequences 2' => [ $FAIL, "\xe0\x9f\xbf" ],
'maximum overlong sequences 3' => [ $FAIL, "\xf0\x8f\xbf\xbf" ],
'maximum overlong sequences 4' => [ $FAIL, "\xf8\x87\xbf\xbf" ],
'maximum overlong sequences 5' => [ $FAIL, "\xfc\x83\xbf\xbf\xbf\xbf" ],
'surrogates 1 (U+D799)' => [ $PASS, "\xed\x9f\xbf" ],
'surrogates 2 (U+E000)' => [ $PASS, "\xee\x80\x80" ],
'surrogates 3 (U+D800)' => [ $FAIL, "\xed\xa0\x80" ],
'surrogates 4 (U+DBFF)' => [ $FAIL, "\xed\xaf\xbf" ],
'surrogates 5 (U+DC00)' => [ $FAIL, "\xed\xb0\x80" ],
'surrogates 6 (U+DFFF)' => [ $FAIL, "\xed\xbf\xbf" ],
'surrogates 7 (U+D800 U+DC00)' => [ $FAIL, "\xed\xa0\x80\xed\xb0\x80" ],
'noncharacters 1' => [ $PASS, "\xef\xbf\xbe" ],
'noncharacters 2' => [ $PASS, "\xef\xbf\xbf" ],
];
}
/**
* @dataProvider provideRegexps
*/
public function testIsValidPCRERegex( string $input, bool $expected ) {
$this->assertSame( $expected, StringUtils::isValidPCRERegex( $input ) );
}
public static function provideRegexps() {
return [
[ 'foo', false ],
[ '/foo/', true ],
[ '//', true ],
[ '/(foo/', false ],
[ '!(f[o]{2})!', true ],
[ '/foo\/', false ]
];
}
/**
* @dataProvider provideRegexReplacements
*/
public function testEscapeRegexReplacement( string $replacement ) {
$escaped = StringUtils::escapeRegexReplacement( $replacement );
$result = preg_replace( '/(placeholder)/', $escaped, 'placeholder' );
$this->assertSame( $replacement, $result );
}
public function provideRegexReplacements() {
return [
'meaningless characters' => [ ' "()*+-./?[]^a{|}ä' ],
'backslash' => [ '\\1' ],
'backslash, already escaped' => [ '\\\\1' ],
'dollar' => [ '$1' ],
'dollar, already escaped' => [ '\$1' ],
];
}
}
|
