NGramTokenizerTest::stringProvider() - Code Metrics - Inspection of "Add SanitizerFactory" - onoi/tesa - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 9401a4...2cc7a2 )

by mw

created 2016-08-02 14:22 UTC

NGramTokenizerTest::stringProvider() B

↳ Parent: NGramTokenizerTest

Complexity

Conditions	1
Paths	1

Size

Total Lines	104
Code Lines	78

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
c	1
b	0
f	1
dl	0
loc	104
rs	8.2857
cc	1
eloc	78
nc	1
nop	0

How to fix Long Method

<?php

namespace Onoi\Tesa\Tests;

use Onoi\Tesa\Tokenizer\NGramTokenizer;

/**
 * @covers \Onoi\Tesa\Tokenizer\NGramTokenizer
 * @group onoi-tesa
 *
 * @license GNU GPL v2+
 * @since 0.1
 *
 * @author mwjames
 */
class NGramTokenizerTest extends \PHPUnit_Framework_TestCase {

	public function testCanConstruct() {

		$this->assertInstanceOf(
			'\Onoi\Tesa\Tokenizer\NGramTokenizer',
			new NGramTokenizer()
		);
	}

	/**
	 * @dataProvider stringProvider
	 */
	public function testTokenize( $string, $ngram, $expected ) {

		$instance = new NGramTokenizer( null, $ngram );

		$this->assertEquals(
			$expected,
			$instance->tokenize( $string )
		);

		$this->assertFalse(
			$instance->isWordTokenizer()
		);
	}

	public function testTokenizeWithStartEndMarker() {

		// http://cloudmark.github.io/Language-Detection
		$string = 'TEXT';

		$expected = array(
			'_tex',
			'text',
			'ext_',
			'xt__',
			't___'
		);

		$instance = new NGramTokenizer( null, 4 );
		$instance->withMarker( true );

		$this->assertEquals(
			$expected,
			$instance->tokenize( $string )
		);
	}

	public function testTokenizeWithStartEndMarker2() {

		$string = '教授は';

		$expected = array(
			'_教授',
			'教授は',
			'授は_',
			'は__'
		);

		$instance = new NGramTokenizer( null, 3 );
		$instance->withMarker( true );

		$this->assertEquals(
			$expected,
			$instance->tokenize( $string )
		);
	}
	public function testTokenizeWithOption() {

		$string = '红色中华';

		$tokenizer = $this->getMockBuilder( '\Onoi\Tesa\Tokenizer\Tokenizer' )
			->disableOriginalConstructor()
			->getMockForAbstractClass();

		$tokenizer->expects( $this->once() )
			->method( 'setOption' );

		$tokenizer->expects( $this->once() )
			->method( 'tokenize' )
			->with( $this->equalTo( $string ) )
			->will( $this->returnValue( array( $string ) ) );

		$instance = new NGramTokenizer( $tokenizer );

		$instance->setOption(
			NGramTokenizer::REGEX_EXEMPTION,
			array( 'Foo' )
		);

		$this->assertEquals(
			array( '红色', '色中', '中华' ),
			$instance->tokenize( $string )
		);
	}

	public function stringProvider() {

		$provider[] = array(
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
			'TEXT',
			'4',
			array(
				'text'
			)
		);

		$provider[] = array(
			'12345678',
			'2',
			array(
				'12',
				'23',
				'34',
				'45',
				'56',
				'67',
				'78'
			)
		);

		$provider[] = array(
			'12345678',
			'3',
			array(
				'123',
				'234',
				'345',
				'456',
				'567',
				'678'
			)
		);

		$provider[] = array(
			'hello',
			'3',
			array(
				'hel',
				'ell',
				'llo'
			)
		);

		$provider[] = array(
			'Hello World!',
			'3',
			array(
				'hel',
				'ell',
				'llo',
				'lo ',
				'o w',
				' wo',
				'wor',
				'orl',
				'rld',
				'ld!'
			)
		);

		$provider[] = array(
			'Новости',
			'3',
			array(
				'нов',
				'ово',
				'вос',
				'ост',
				'сти'
			)
		);

		$provider[] = array(
			'1時36分更新',
			'3',
			array(
				'1時3',
				'時36',
				'36分',
				'6分更',
				'分更新'
			)
		);

		$provider[] = array(
			'こんにちは世界！',
			'2',
			array(
				'こん',
				'んに',
				'にち',
				'ちは',
				'は世',
				'世界',
				'界！'
			)
		);

		return $provider;
	}

}


1			<?php
2
3			namespace Onoi\Tesa\Tests;
4
5			use Onoi\Tesa\Tokenizer\NGramTokenizer;
6
7			/**
8			* @covers \Onoi\Tesa\Tokenizer\NGramTokenizer
9			* @group onoi-tesa
10			*
11			* @license GNU GPL v2+
12			* @since 0.1
13			*
14			* @author mwjames
15			*/
16			class NGramTokenizerTest extends \PHPUnit_Framework_TestCase {
17
18			public function testCanConstruct() {
19
20			$this->assertInstanceOf(
21			'\Onoi\Tesa\Tokenizer\NGramTokenizer',
22			new NGramTokenizer()
23			);
24			}
25
26			/**
27			* @dataProvider stringProvider
28			*/
29			public function testTokenize( $string, $ngram, $expected ) {
30
31			$instance = new NGramTokenizer( null, $ngram );
32
33			$this->assertEquals(
34			$expected,
35			$instance->tokenize( $string )
36			);
37
38			$this->assertFalse(
39			$instance->isWordTokenizer()
40			);
41			}
42
43			public function testTokenizeWithStartEndMarker() {
44
45			// http://cloudmark.github.io/Language-Detection
46			$string = 'TEXT';
47
48			$expected = array(
49			'_tex',
50			'text',
51			'ext_',
52			'xt__',
53			't___'
54			);
55
56			$instance = new NGramTokenizer( null, 4 );
57			$instance->withMarker( true );
58
59			$this->assertEquals(
60			$expected,
61			$instance->tokenize( $string )
62			);
63			}
64
65			public function testTokenizeWithStartEndMarker2() {
66
67			$string = '教授は';
68
69			$expected = array(
70			'_教授',
71			'教授は',
72			'授は_',
73			'は__'
74			);
75
76			$instance = new NGramTokenizer( null, 3 );
77			$instance->withMarker( true );
78
79			$this->assertEquals(
80			$expected,
81			$instance->tokenize( $string )
82			);
83			}
84			public function testTokenizeWithOption() {
85
86			$string = '红色中华';
87
88			$tokenizer = $this->getMockBuilder( '\Onoi\Tesa\Tokenizer\Tokenizer' )
89			->disableOriginalConstructor()
90			->getMockForAbstractClass();
91
92			$tokenizer->expects( $this->once() )
93			->method( 'setOption' );
94
95			$tokenizer->expects( $this->once() )
96			->method( 'tokenize' )
97			->with( $this->equalTo( $string ) )
98			->will( $this->returnValue( array( $string ) ) );
99
100			$instance = new NGramTokenizer( $tokenizer );
101
102			$instance->setOption(
103			NGramTokenizer::REGEX_EXEMPTION,
104			array( 'Foo' )
105			);
106
107			$this->assertEquals(
108			array( '红色', '色中', '中华' ),
109			$instance->tokenize( $string )
110			);
111			}
112
113			public function stringProvider() {
114
115			$provider[] = array(
			0 ignored issues – show Coding Style Comprehensibility introduced 2016-08-02 14:35 UTC by Report Bug Copy Issue Report `$provider` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$provider = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` key is only written conditionally; thus, its value might result from a previous iteration. This might or might not be intended. To make your intention clear, your code more readible and to avoid accidental bugs, we recommend to add an explicit initialization `$myArray = array()` either outside or inside the foreach loop. Loading history...
116			'TEXT',
117			'4',
118			array(
119			'text'
120			)
121			);
122
123			$provider[] = array(
124			'12345678',
125			'2',
126			array(
127			'12',
128			'23',
129			'34',
130			'45',
131			'56',
132			'67',
133			'78'
134			)
135			);
136
137			$provider[] = array(
138			'12345678',
139			'3',
140			array(
141			'123',
142			'234',
143			'345',
144			'456',
145			'567',
146			'678'
147			)
148			);
149
150			$provider[] = array(
151			'hello',
152			'3',
153			array(
154			'hel',
155			'ell',
156			'llo'
157			)
158			);
159
160			$provider[] = array(
161			'Hello World!',
162			'3',
163			array(
164			'hel',
165			'ell',
166			'llo',
167			'lo ',
168			'o w',
169			' wo',
170			'wor',
171			'orl',
172			'rld',
173			'ld!'
174			)
175			);
176
177			$provider[] = array(
178			'Новости',
179			'3',
180			array(
181			'нов',
182			'ово',
183			'вос',
184			'ост',
185			'сти'
186			)
187			);
188
189			$provider[] = array(
190			'1時36分更新',
191			'3',
192			array(
193			'1時3',
194			'時36',
195			'36分',
196			'6分更',
197			'分更新'
198			)
199			);
200
201			$provider[] = array(
202			'こんにちは世界！',
203			'2',
204			array(
205			'こん',
206			'んに',
207			'にち',
208			'ちは',
209			'は世',
210			'世界',
211			'界！'
212			)
213			);
214
215			return $provider;
216			}
217
218			}
219

onoi / tesa

Push — master ( 9401a4...2cc7a2 )

NGramTokenizerTest::stringProvider() B

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like