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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
|
#!/www/server/bin/php -qC
<?php
# Tests for it.class
require 'searchlib/search_test.class';
function match( $regex, $string, $exp, $name )
{
$GLOBALS['TEST_MORE_LEVEL'] = 1;
$pass = is( it::match( $regex, $string ), $exp, $name );
if( !$pass ) {
diag( " regex given: $regex" );
diag( " regex converted: " . it::convertregex( $regex ) );
}
$GLOBALS['TEST_MORE_LEVEL'] = 0;
}
match(
'b', 'aaaabaaaa',
'b',
'simple regex'
);
match(
'a/b', ' a/b ',
'a/b',
'regex with /'
);
match(
'aa(bb)aa(cc)aa(dd)qq', 'aabbaaccaaddqq',
array( 'bb', 'cc', 'dd' ),
'return array of captures'
);
match(
'\bblah\b', ' blah ',
'blah',
'match \b at spaces'
);
match(
'\bblah\b', 'blah',
'blah',
'match \b at end of string'
);
match(
'\bblah\b', 'ablahc',
false,
'don\'t match \b at word chars'
);
match(
'\bblah\b', 'Üblahä',
false,
'don\'t match \b at umlaute in latin1'
);
match(
'\Bblah\B', ' blah ',
false,
'don\'t match \B at spaces'
);
match(
'\Bblah\B', 'blah',
false,
'don\'t match \B at end of string'
);
match(
'\Bblah\B', 'ablahc',
'blah',
'match \B at word chars'
);
match(
'\Bblah\B', 'Üblahä',
'blah',
'match \B at umlaute in latin1'
);
match(
'\w+', ' |#Üblahä ',
'Üblahä',
'include umlaute in \w'
);
match(
'\W+', ' |#Üblahä ',
' |#',
'don\'t include umlaute in \W'
);
eval( '$escapedwordregex = "' . it::convertregex( '\w' ) . '";' );
$escapedwordregex = preg_replace( '|[\\\\/]|', '', $escapedwordregex );
match(
'\\\\w+', $escapedwordregex,
false,
'don\'t parse \w in \\\\w at beginning (no match)'
);
match(
'aaa\\\\w+', ' aaa\www ',
'aaa\www',
'don\'t parse \w in \\\\w at beginning (match)'
);
match(
'aaa\\\\w+', 'aaa' . $escapedwordregex,
false,
'don\'t parse \w in \\\\w after chars (no match)'
);
match(
'aaa\\\\w+', ' aaa\www ',
'aaa\www',
'don\'t parse \w in \\\\w after chars (match)'
);
match(
'\\\\\\\\w+', '\\' . $escapedwordregex,
false,
'don\'t parse \w in \\\\\\\w (no match)'
);
match(
'\\\\\\\\w+', ' \\\\www ',
'\\\\www',
'don\'t parse \\\\\\\\w as \w (match)'
);
match(
'[\w]+', '[[[]]]---',
false,
'replace \w in [\w] correctly (no match)'
);
match(
'[\w]+', ' \\\\aword[[[]]] ',
'aword',
'replace \w in [\w] correctly (match)',
);
match(
'[\\\\w]+', ' blabergna ',
false,
'don\'t parse \w in [\\\\w] (no match)'
);
match(
'[\\\\w]+', ' \\\\worda[[[]',
'\\\\w',
'don\'t parse \w in [\\\\w] (match)',
);
match(
'[a\W]+', 'bbbbbbb a a%$+ accccc',
' a a%$+ a',
'\W in []'
);
match(
'\\\\\\w+', ' \Üblahä ',
'\Üblahä',
'parse \w in \\\\\\w at beginning'
);
match(
'aaa\\\\\\w+', ' aaa\Üblahä ',
'aaa\Üblahä',
'parse \w in \\\\\\w after chars'
);
is(
it::replace(
array(
'regex1' => 'repl1',
'regex2' => 'repl2',
'regex3' => 'repl3' ),
'regex2 regex1 regex3' ),
'repl2 repl1 repl3',
'test tr regex function'
);
is(
it::match( '\w+', 'word1 wörd2 word_3', 'all' => true ),
array( 'word1', 'wörd2', 'word_3' ),
"test match_all function"
);
match(
'aBcD', ' aBcD ',
'aBcD',
"caseinsensitive is default"
);
match(
'ö', 'Ö',
'Ö',
'match umlaute in latin1 case insensitive'
);
is(
it::match( 'abc', "aBc", 'casesensitive' => 1 ),
false,
"set case sensitivity by parameter"
);
is(
it::match( '\w+', 'word1 wörd2 word_3', 'all' => 1 ),
array( 'word1', 'wörd2', 'word_3' ),
"test all=>1 without captures"
);
is(
it::match( '\w+\s+(\d+)', 'word1 12 wörd2 3 word_3 4', 'all' => 1 ),
array( '12', '3', '4' ),
"test all=>1 with one capture"
);
is(
it::match( '(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4', 'all' => 1 ),
array( array( 'word1', '12' ), array( 'wörd2', '3' ), array( 'word_3', '4' ) ),
"test all=>1 with captures"
);
is(
it::match( '(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4', 'all' => 1, 'pattern_order' => 1 ),
array( array( 'word1', 'wörd2', 'word_3' ), array( '12', '3', '4' ) ),
"test all=>1,pattern_order=>1",
);
?>
|