IcuWordBoundaryTokenizer::createTokens() - 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

IcuWordBoundaryTokenizer::createTokens() B

↳ Parent: IcuWordBoundaryTokenizer

Complexity

Conditions	6
Paths	2

Size

Total Lines	26
Code Lines	13

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
c	1
b	0
f	1
dl	0
loc	26
rs	8.439
cc	6
eloc	13
nc	2
nop	1

<?php

namespace Onoi\Tesa\Tokenizer;

use IntlRuleBasedBreakIterator;

/**
 * @license GNU GPL v2+
 * @since 0.1
 *
 * @author mwjames
 */
class IcuWordBoundaryTokenizer implements Tokenizer {

	/**
	 * @var Tokenizer
	 */
	private $tokenizer;

	/**
	 * @var string
	 */
	private $locale = 'en';

	/**
	 * @var string
	 */
	private $isWordTokenizer = true;

	/**
	 * @since 0.1
	 *
	 * @param Tokenizer|null $tokenizer
	 */
	public function __construct( Tokenizer $tokenizer = null ) {
		$this->tokenizer = $tokenizer;
	}

	/**
	 * @since 0.1
	 *
	 * {@inheritDoc}
	 */
	public function setOption( $name, $value ) {
		if ( $this->tokenizer !== null ) {
			$this->tokenizer->setOption( $name, $value );
		}
	}

	/**
	 * @since 0.1
	 *
	 * {@inheritDoc}
	 */
	public function isWordTokenizer() {
		return $this->isWordTokenizer;
class Author {
    private $name;

    public function __construct($name) {
        $this->name = $name;
    }

    public function getName() {
        return $this->name;
    }
}

abstract class Post {
    public function getAuthor() {
        return 'Johannes';
    }
}

class BlogPost extends Post {
    public function getAuthor() {
        return new Author('Johannes');
    }
}

class ForumPost extends Post { /* ... */ }

function my_function(Post $post) {
    echo strtoupper($post->getAuthor());
}
	}

	/**
	 * @since 0.1
	 *
	 * {@inheritDoc}
	 */
	public function setWordTokenizerAttribute( $usesWordBoundaries ) {
		return $this->isWordTokenizer = $usesWordBoundaries;
	}

	/**
	 * @since 0.1
	 *
	 * @return boolean
	 */
	public function isAvailable() {
		return class_exists( 'IntlRuleBasedBreakIterator' );
	}

	/**
	 * @since 0.1
	 *
	 * @param string $locale
	 */
	public function setLocale( $locale ) {
		$this->locale = $locale;
	}

	/**
	 * @since 0.1
	 *
	 * @param string $string
	 *
	 * @return array|false
	 */
	public function tokenize( $string ) {

		if ( $this->tokenizer !== null ) {
			$string = implode( " ", $this->tokenizer->tokenize( $string ) );
		}

		if ( !$this->isAvailable() ) {
			return $this->tokenizer !== null ? $this->tokenizer->tokenize( $string ) : array( $string );
		}

		return $this->createTokens( $string );
	}

	private function createTokens( $string ) {

		$tokens = array();

		if ( $tokenizer = IntlRuleBasedBreakIterator::createWordInstance( $this->locale ) ) {
			$tokenizer->setText( $string );
			$prev = 0;

			foreach ( $tokenizer as $token ) {

				if ( $token == 0 ) {
					continue;
				}

				$res = substr( $string, $prev, $token - $prev );

				if ( $res !== '' && $res !== ' ' ) {
					$tokens[] = $res;
				}

				$prev = $token;
			}
		}

		return $tokens;
	}

}


1			<?php
2
3			namespace Onoi\Tesa\Tokenizer;
4
5			use IntlRuleBasedBreakIterator;
6
7			/**
8			* @license GNU GPL v2+
9			* @since 0.1
10			*
11			* @author mwjames
12			*/
13			class IcuWordBoundaryTokenizer implements Tokenizer {
14
15			/**
16			* @var Tokenizer
17			*/
18			private $tokenizer;
19
20			/**
21			* @var string
22			*/
23			private $locale = 'en';
24
25			/**
26			* @var string
27			*/
28			private $isWordTokenizer = true;
29
30			/**
31			* @since 0.1
32			*
33			* @param Tokenizer\|null $tokenizer
34			*/
35			public function __construct( Tokenizer $tokenizer = null ) {
36			$this->tokenizer = $tokenizer;
37			}
38
39			/**
40			* @since 0.1
41			*
42			* {@inheritDoc}
43			*/
44			public function setOption( $name, $value ) {
45			if ( $this->tokenizer !== null ) {
46			$this->tokenizer->setOption( $name, $value );
47			}
48			}
49
50			/**
51			* @since 0.1
52			*
53			* {@inheritDoc}
54			*/
55			public function isWordTokenizer() {
56			return $this->isWordTokenizer;
			0 ignored issues – show Bug Best Practice introduced 2016-08-02 14:35 UTC by Report Bug Copy Issue Report The return type of `return $this->isWordTokenizer;` (`string`) is incompatible with the return type declared by the interface `Onoi\Tesa\Tokenizer\Tokenizer::isWordTokenizer` of type `boolean`. If you return a value from a function or method, it should be a sub-type of the type that is given by the parent type f.e. an interface, or abstract method. This is more formally defined by the Lizkov substitution principle, and guarantees that classes that depend on the parent type can use any instance of a child type interchangably. This principle also belongs to the SOLID principles for object oriented design. Let’s take a look at an example: class Author { private $name; public function __construct($name) { $this->name = $name; } public function getName() { return $this->name; } } abstract class Post { public function getAuthor() { return 'Johannes'; } } class BlogPost extends Post { public function getAuthor() { return new Author('Johannes'); } } class ForumPost extends Post { /* ... */ } function my_function(Post $post) { echo strtoupper($post->getAuthor()); } Our function `my_function` expects a `Post` object, and outputs the author of the post. The base class `Post` returns a simple string and outputting a simple string will work just fine. However, the child class `BlogPost` which is a sub-type of `Post` instead decided to return an `object`, and is therefore violating the SOLID principles. If a `BlogPost` were passed to `my_function`, PHP would not complain, but ultimately fail when executing the `strtoupper` call in its body. Loading history...
57			}
58
59			/**
60			* @since 0.1
61			*
62			* {@inheritDoc}
63			*/
64			public function setWordTokenizerAttribute( $usesWordBoundaries ) {
65			return $this->isWordTokenizer = $usesWordBoundaries;
66			}
67
68			/**
69			* @since 0.1
70			*
71			* @return boolean
72			*/
73			public function isAvailable() {
74			return class_exists( 'IntlRuleBasedBreakIterator' );
75			}
76
77			/**
78			* @since 0.1
79			*
80			* @param string $locale
81			*/
82			public function setLocale( $locale ) {
83			$this->locale = $locale;
84			}
85
86			/**
87			* @since 0.1
88			*
89			* @param string $string
90			*
91			* @return array\|false
92			*/
93			public function tokenize( $string ) {
94
95			if ( $this->tokenizer !== null ) {
96			$string = implode( " ", $this->tokenizer->tokenize( $string ) );
97			}
98
99			if ( !$this->isAvailable() ) {
100			return $this->tokenizer !== null ? $this->tokenizer->tokenize( $string ) : array( $string );
101			}
102
103			return $this->createTokens( $string );
104			}
105
106			private function createTokens( $string ) {
107
108			$tokens = array();
109
110			if ( $tokenizer = IntlRuleBasedBreakIterator::createWordInstance( $this->locale ) ) {
111			$tokenizer->setText( $string );
112			$prev = 0;
113
114			foreach ( $tokenizer as $token ) {
115
116			if ( $token == 0 ) {
117			continue;
118			}
119
120			$res = substr( $string, $prev, $token - $prev );
121
122			if ( $res !== '' && $res !== ' ' ) {
123			$tokens[] = $res;
124			}
125
126			$prev = $token;
127			}
128			}
129
130			return $tokens;
131			}
132
133			}
134

onoi / tesa

Push — master ( 9401a4...2cc7a2 )

IcuWordBoundaryTokenizer::createTokens() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like