File: TextTruncatorTest.php

package info (click to toggle)
mediawiki 1%3A1.35.13-1%2Bdeb11u2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 274,932 kB
  • sloc: php: 677,563; javascript: 572,709; sql: 11,565; python: 4,447; xml: 3,145; sh: 892; perl: 788; ruby: 496; pascal: 365; makefile: 128
file content (178 lines) | stat: -rw-r--r-- 4,296 bytes parent folder | download | duplicates (2)
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
<?php

namespace TextExtracts\Test;

use TextExtracts\TextTruncator;

/**
 * @covers \TextExtracts\TextTruncator
 * @group TextExtracts
 *
 * @license GPL-2.0-or-later
 */
class TextTruncatorTest extends \PHPUnit\Framework\TestCase {
	/**
	 * @dataProvider provideGetFirstSentences
	 * @param string $text
	 * @param string $sentences
	 * @param string $expected
	 */
	public function testGetFirstSentences( $text, $sentences, $expected ) {
		$truncator = new TextTruncator( false );
		$this->assertSame( $expected, $truncator->getFirstSentences( $text, $sentences ) );
	}

	public function provideGetFirstSentences() {
		$longLine = str_repeat( 'word ', 1000000 );
		return [
			[
				'Foo is a bar. Such a smart boy. But completely useless.',
				2,
				'Foo is a bar. Such a smart boy.',
			],
			[
				'Foo is a bar. Such a smart boy. But completely useless.',
				1,
				'Foo is a bar.',
			],
			[
				'Foo is a bar. Such a smart boy.',
				2,
				'Foo is a bar. Such a smart boy.',
			],
			[
				'Foo is a bar.',
				1,
				'Foo is a bar.',
			],
			[
				'Foo is a bar.',
				2,
				'Foo is a bar.',
			],
			[
				'',
				1,
				'',
			],
			'0 sentences mean empty result' => [
				'Foo is a bar. Such a smart boy.',
				0,
				'',
			],
			"Don't explode on negative input" => [
				'Foo is a bar. Such a smart boy.',
				-1,
				'',
			],
			'More sentences requested than is available' => [
				'Foo is a bar. Such a smart boy.',
				3,
				'Foo is a bar. Such a smart boy.',
			],
			// Exclamation points too!!!
			[
				'Foo is a bar! Such a smart boy! But completely useless!',
				1,
				'Foo is a bar!',
			],
			// A tricky one
			[
				"Acid phosphatase (EC 3.1.3.2) is a chemical you don't want to mess with. " .
					"Polyvinyl acetate, however, is another story.",
				1,
				"Acid phosphatase (EC 3.1.3.2) is a chemical you don't want to mess with.",
			],
			// No clear sentences
			[
				"foo\nbar\nbaz",
				2,
				'foo',
			],
			// Bug T118621
			[
				'Foo was born in 1977. He enjoys listening to Siouxsie and the Banshees.',
				1,
				'Foo was born in 1977.',
			],
			// Bug T115795 - Test no cropping after initials
			[
				'P.J. Harvey is a singer. She is awesome!',
				1,
				'P.J. Harvey is a singer.',
			],
			// Bug T115817 - Non-breaking space is not a delimiter
			[
				html_entity_decode( 'Pigeons (lat.&nbsp;Columbidae) are birds. ' .
					'They primarily feed on seeds.' ),
				1,
				html_entity_decode( 'Pigeons (lat.&nbsp;Columbidae) are birds.' ),
			],
			// Bug T145231 - various problems with regexes
			[
				$longLine,
				3,
				trim( $longLine ),
			],
			[
				str_repeat( 'Sentence. ', 70000 ),
				65536,
				trim( str_repeat( 'Sentence. ', 65536 ) ),
			],

			'Preserve whitespace before end character' => [
				'Aa . Bb',
				1,
				'Aa .',
			],
		];
	}

	/**
	 * @dataProvider provideGetFirstChars
	 * @param string $text
	 * @param string $chars
	 * @param string $expected
	 */
	public function testGetFirstChars( $text, $chars, $expected ) {
		$truncator = new TextTruncator( false );
		$this->assertSame( $expected, $truncator->getFirstChars( $text, $chars ) );
	}

	public function provideGetFirstChars() {
		$text = 'Lullzy lulz are lullzy!';
		$html = 'foo<tag>bar</tag>';
		$longText = str_repeat( 'тест ', 50000 );
		$longTextExpected = trim( str_repeat( 'тест ', 13108 ) );

		return [
			[ $text, -8, '' ],
			[ $text, 0, '' ],
			[ $text, 100, $text ],
			[ $text, 1, 'Lullzy' ],
			[ $text, 6, 'Lullzy' ],
			// [ $text, 7, 'Lullzy' ],
			[ $text, 8, 'Lullzy lulz' ],
			// HTML processing
			[ $html, 1, 'foo' ],
			// let HTML sanitizer clean it up later
			[ $html, 4, 'foo<tag>' ],
			[ $html, 12, 'foo<tag>bar</tag>' ],
			[ $html, 13, 'foo<tag>bar</tag>' ],
			[ $html, 16, 'foo<tag>bar</tag>' ],
			[ $html, 17, 'foo<tag>bar</tag>' ],
			// T143178 - previously, characters were extracted using regexps which failed when
			// requesting 64K chars or more.
			[ $longText, 65536, $longTextExpected ],
		];
	}

	public function testTidyIntegration() {
		$truncator = new TextTruncator( true );

		$text = '<b>Aa. Bb.</b>';
		$this->assertSame( '<p><b>Aa.</b></p>', $truncator->getFirstSentences( $text, 1 ) );
		$this->assertSame( '<p><b>Aa</b></p>', $truncator->getFirstChars( $text, 4 ) );
	}

}