BaseIndexSettings - Code Metrics - Inspection of "WIP: Now checking IndexSettingsTest" - gordonbanderson/silverstripe-elastica - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — dev2 ( dd5bec...049fe2 )

by Gordon

created 2015-12-30 05:12 UTC

BaseIndexSettings A

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	244
Duplicated Lines	0 %

Coupling/Cohesion

Components	2
Dependencies	0

Test Coverage

Coverage

97.26%

Metric	Value
wmc	10
lcom	2
cbo	0
dl	0
loc	244
ccs	71
cts	73
cp	0.9726
rs	10

7 Methods

Rating	Name	Size	Complexity
A	setAsciiFolding()	3	1
A	setStopwords()	9	3
A	addFilter()	3	1
A	addAnalyzer()	3	1
B	generateConfig()	147	2
A	getAsciiFolding()	3	1
A	getStopwords()	3	1

<?php

/**
*
* Synonyms
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-synonym-tokenfilter.html
*
* ASCII folding
* https://www.elastic.co/guide/en/elasticsearch/guide/current/asciifolding-token-filter.html
*
* Snowball
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-snowball-analyzer.html
*
* Thai tokenizer
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-thai-tokenizer.html
*
* Reverser
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-reverse-tokenfilter.html
*
* Elisions, possibly suitable for French
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-elision-tokenfilter.html
* Common grams
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-common-grams-tokenfilter.html
*
* This page has a long list
* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-lang-analyzer.html#german-analyzer
*
* Boost weight and mix of stem/unstemmed
* https://www.elastic.co/guide/en/elasticsearch/guide/current/most-fields.html
*
* Extend this class to create your own index settings
*
*/
class BaseIndexSettings {

	/**
	 * If true add a field called folded with likes of está converted to esta
	 * @var boolean
	 */
	private $foldedAscii = false;

	/*
	Stopwords for this index
	 */
	protected $stopWords = array();

	/**
	 * Synonyms for this index in form of CSV terms => actual term
	 * @var array
	 */
	private $synonyms = array();



	/*
	Filters added by the language specific settings
	 */
	private $filters = array();

	/*
	Analyzers added by the language specific settings
	 */
	private $analyzers = array();


	protected $stopWordFilter = null;


	/**
	 * Set to true to add an extra field containing a folded version of terms,
	 * i.e. not accents on the letters
	 * @param boolean $newFolding true for an extra field with no accents
	 */
	public function setAsciiFolding($newFolding) {
		$this->foldedAscii = $newFolding;
	}


	public function getAsciiFolding() {
		return $this->foldedAscii;
	}


	/**
	 * NOTE: Test with _german_ or _english_
	 * Set the stopwords for this index
	 * @param array or string $newStopWords An array of stopwords or a CSV string of stopwords
	 */
	public function setStopwords($newStopWords) {
		if (is_array($newStopWords)) {
			$this->stopWords = $newStopWords;
		} else if (is_string($newStopWords)) {
			$this->stopWords = explode(',', $newStopWords);
		} else {
			throw new Exception("ERROR: Stopwords must be a string or an array");
		}
	}


	/*
	Accessor for stopwords
	 */
	public function getStopwords() {
		return $this->stopWords;
	}


	/**
	 * Add a filter, expressed as an array
	 * @param string $name The name of the filter
	 * @param array $properties The filter modelled as an array
	 */
	public function addFilter($name, $properties) {
		$this->filters[$name] = $properties;
	}


	/**
	 * Add an analyzer, expressed as an array
	 * @param string $name       The name of the analyzer
	 * @param array $properties The analyzer modelled as an array
	 */
	public function addAnalyzer($name, $properties) {
		$this->analyzers[$name] = $properties;
	}


	/*
	Generate an Elasticsearch config representing the configurations previously set.
	 */
	public function generateConfig() {
		$settings = array();
		$settings['analysis'] = array();

		// create redefined filters in this array, e.g. tweaked stopwords

		$properties = array();
		$analyzerNotStemmed = array();
		$analyzerFolded = array();

		$analyzerNotStemmed['type'] = 'custom';

		$this->addFilter('no_single_chars', array(
			'type' => 'length',
			'min' => 2
		));


/*

		if (sizeof($this->stopWords) > 0) {
			$stopwordFilter = array();
			$stopwordFilter['type'] = 'stop';
			$stopwordFilter['stopwords'] = $this->stopWords;
			$this->filters['stopword_filter'] = $stopwordFilter;
		}
*/

		//$analyzerStemmed['char_filter'] = array('html_strip');

		$filterNames = array_keys($this->filters);

		//$analyzerNotStemmed['char_filter'] = array('html_strip');

		$analyzerNotStemmed['tokenizer'] = 'uax_url_email';
		array_push($filterNames, 'lowercase');
		$analyzerNotStemmed['filter'] = array('no_single_chars', 'lowercase', $this->stopWordFilter);

		//Autocomplete filter
		/*

		"autocomplete": {
            "type":      "custom",
            "tokenizer": "standard",
            "filter": [
                "lowercase",
                "autocomplete_filter"
            ]
        }
		 */
		$this->addFilter('autocomplete', array(
			'type' => 'nGram',
			'min_gram' => 2,
			'max_gram' => 20,
			'token_chars' => array('letter', 'digit','punctuation', 'symbol')
		));

		$this->addAnalyzer('autocomplete_index_analyzer',array(
			'type' => 'custom',
			'tokenizer' => 'whitespace',
			'filter' => array(
				'lowercase',
				'asciifolding',
				'autocomplete'
			)
		));

		$this->addAnalyzer('autocomplete_search_analyzer',array(
			'type' => 'custom',
			'tokenizer' => 'whitespace',
			'filter' => array(
				'lowercase',
				'asciifolding'
			)
		));

		//Folded analyzer
		$analyzerFolded['tokenizer'] = 'uax_url_email';
		$analyzerFolded['filters'] = array('lowercase', 'asciifolding');



		//HTML needs to have been removed for all indexes
		//stemmed is set by the specific language provider
		$this->analyzers['unstemmed'] = $analyzerNotStemmed;


		if ($this->foldedAscii) {
			$analyzers['folded'] = $analyzerFolded;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

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

    // do something with $myArray
}
		}

        //Store bigrams in the index, namely pairs of words
		$this->addFilter('filter_shingle', array(
			'type' => 'shingle',
			'min_shingle_size' => 2,
			'max_shingle_size' => 2,
			'output_unigrams' => false
		));

		//See https://www.elastic.co/blog/searching-with-shingles?q=shingle for details
		$this->addAnalyzer('shingles', array(
			// Ensure URLs happily tokenized
			'tokenizer' => 'uax_url_email',
			'filter' => array("lowercase", "filter_shingle"),
			'type' => 'custom'
		));

		$settings['analysis']['analyzer'] = $this->analyzers;
		$settings['analysis']['filter'] = $this->filters;


		$properties['index'] = $settings;

		/*


		if ($this->foldedAscii) {
			$foldingFilter = array('my_ascii_folding' => array(
				"type" => "asciifolding",
				"preserve_original" => 'true'
			));
			array_push($filters, $foldingFilter);
		}
		*/


/*

		$json = '{
		  "settings": {
		    "analysis": {
		      "analyzer": {
		        "stemmed": {
		          "type": "english",
		          "stem_exclusion": [ "organization", "organizations" ],
		          "stopwords": [
		            "a", "an", "and", "are", "as", "at", "be", "but", "by", "for",
		            "if", "in", "into", "is", "it", "of", "on", "or", "such", "that",
		            "the", "their", "then", "there", "these", "they", "this", "to",
		            "was", "will", "with"
		          ]
		        }
		      }
		    }
		  }
		}';
		*/
		//$this->extend('alterIndexingProperties', $properties);

		//
		//

		return $properties;
	}
}


1		<?php
2
3		/**
4		*
5		* Synonyms
6		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-synonym-tokenfilter.html
7		*
8		* ASCII folding
9		* https://www.elastic.co/guide/en/elasticsearch/guide/current/asciifolding-token-filter.html
10		*
11		* Snowball
12		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-snowball-analyzer.html
13		*
14		* Thai tokenizer
15		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-thai-tokenizer.html
16		*
17		* Reverser
18		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-reverse-tokenfilter.html
19		*
20		* Elisions, possibly suitable for French
21		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-elision-tokenfilter.html
22		* Common grams
23		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-common-grams-tokenfilter.html
24		*
25		* This page has a long list
26		* https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-lang-analyzer.html#german-analyzer
27		*
28		* Boost weight and mix of stem/unstemmed
29		* https://www.elastic.co/guide/en/elasticsearch/guide/current/most-fields.html
30		*
31		* Extend this class to create your own index settings
32		*
33		*/
34		class BaseIndexSettings {
35
36		/**
37		* If true add a field called folded with likes of está converted to esta
38		* @var boolean
39		*/
40		private $foldedAscii = false;
41
42		/*
43		Stopwords for this index
44		*/
45		protected $stopWords = array();
46
47		/**
48		* Synonyms for this index in form of CSV terms => actual term
49		* @var array
50		*/
51		private $synonyms = array();
		0 ignored issues – show Unused Code introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report The property `$synonyms` is not used and could be removed. This check marks private properties in classes that are never used. Those properties can be removed. Loading history...
52
53
54		/*
55		Filters added by the language specific settings
56		*/
57		private $filters = array();
58
59		/*
60		Analyzers added by the language specific settings
61		*/
62		private $analyzers = array();
63
64
65		protected $stopWordFilter = null;
66
67
68		/**
69		* Set to true to add an extra field containing a folded version of terms,
70		* i.e. not accents on the letters
71		* @param boolean $newFolding true for an extra field with no accents
72		*/
73	2	public function setAsciiFolding($newFolding) {
74	2	$this->foldedAscii = $newFolding;
75	2	}
76
77
78	1	public function getAsciiFolding() {
79	1	return $this->foldedAscii;
80		}
81
82
83		/**
84		* NOTE: Test with _german_ or _english_
85		* Set the stopwords for this index
86		* @param array or string $newStopWords An array of stopwords or a CSV string of stopwords
87		*/
88	2	public function setStopwords($newStopWords) {
89	2	if (is_array($newStopWords)) {
90		$this->stopWords = $newStopWords;
91	2	} else if (is_string($newStopWords)) {
92	2	$this->stopWords = explode(',', $newStopWords);
93	2	} else {
94		throw new Exception("ERROR: Stopwords must be a string or an array");
95		}
96	2	}
97
98
99		/*
100		Accessor for stopwords
101		*/
102	1	public function getStopwords() {
103	1	return $this->stopWords;
104		}
105
106
107		/**
108		* Add a filter, expressed as an array
109		* @param string $name The name of the filter
110		* @param array $properties The filter modelled as an array
111		*/
112	2	public function addFilter($name, $properties) {
113	2	$this->filters[$name] = $properties;
114	2	}
115
116
117		/**
118		* Add an analyzer, expressed as an array
119		* @param string $name The name of the analyzer
120		* @param array $properties The analyzer modelled as an array
121		*/
122	2	public function addAnalyzer($name, $properties) {
123	2	$this->analyzers[$name] = $properties;
124	2	}
125
126
127		/*
128		Generate an Elasticsearch config representing the configurations previously set.
129		*/
130	2	public function generateConfig() {
131	2	$settings = array();
132	2	$settings['analysis'] = array();
133
134		// create redefined filters in this array, e.g. tweaked stopwords
135
136	2	$properties = array();
137	2	$analyzerNotStemmed = array();
138	2	$analyzerFolded = array();
139
140	2	$analyzerNotStemmed['type'] = 'custom';
141
142	2	$this->addFilter('no_single_chars', array(
143	2	'type' => 'length',
144		'min' => 2
145	2	));
146
147
148		/*
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `57%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
149		if (sizeof($this->stopWords) > 0) {
150		$stopwordFilter = array();
151		$stopwordFilter['type'] = 'stop';
152		$stopwordFilter['stopwords'] = $this->stopWords;
153		$this->filters['stopword_filter'] = $stopwordFilter;
154		}
155		*/
156
157		//$analyzerStemmed['char_filter'] = array('html_strip');
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `75%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
158	2	$filterNames = array_keys($this->filters);
159
160		//$analyzerNotStemmed['char_filter'] = array('html_strip');
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `75%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
161	2	$analyzerNotStemmed['tokenizer'] = 'uax_url_email';
162	2	array_push($filterNames, 'lowercase');
163	2	$analyzerNotStemmed['filter'] = array('no_single_chars', 'lowercase', $this->stopWordFilter);
164
165		//Autocomplete filter
166		/*
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `62%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
167		"autocomplete": {
168		"type": "custom",
169		"tokenizer": "standard",
170		"filter": [
171		"lowercase",
172		"autocomplete_filter"
173		]
174		}
175		*/
176	2	$this->addFilter('autocomplete', array(
177	2	'type' => 'nGram',
178	2	'min_gram' => 2,
179	2	'max_gram' => 20,
180	2	'token_chars' => array('letter', 'digit','punctuation', 'symbol')
181	2	));
182
183	2	$this->addAnalyzer('autocomplete_index_analyzer',array(
184	2	'type' => 'custom',
185	2	'tokenizer' => 'whitespace',
186		'filter' => array(
187	2	'lowercase',
188	2	'asciifolding',
189		'autocomplete'
190	2	)
191	2	));
192
193	2	$this->addAnalyzer('autocomplete_search_analyzer',array(
194	2	'type' => 'custom',
195	2	'tokenizer' => 'whitespace',
196		'filter' => array(
197	2	'lowercase',
198		'asciifolding'
199	2	)
200	2	));
201
202		//Folded analyzer
203	2	$analyzerFolded['tokenizer'] = 'uax_url_email';
204	2	$analyzerFolded['filters'] = array('lowercase', 'asciifolding');
205
206
207
208		//HTML needs to have been removed for all indexes
209		//stemmed is set by the specific language provider
210	2	$this->analyzers['unstemmed'] = $analyzerNotStemmed;
211
212
213	2	if ($this->foldedAscii) {
214	2	$analyzers['folded'] = $analyzerFolded;
		0 ignored issues – show Coding Style Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `$analyzers` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$analyzers = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($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...
215	2	}
216
217		//Store bigrams in the index, namely pairs of words
218	2	$this->addFilter('filter_shingle', array(
219	2	'type' => 'shingle',
220	2	'min_shingle_size' => 2,
221	2	'max_shingle_size' => 2,
222		'output_unigrams' => false
223	2	));
224
225		//See https://www.elastic.co/blog/searching-with-shingles?q=shingle for details
226	2	$this->addAnalyzer('shingles', array(
227		// Ensure URLs happily tokenized
228	2	'tokenizer' => 'uax_url_email',
229	2	'filter' => array("lowercase", "filter_shingle"),
230		'type' => 'custom'
231	2	));
232
233	2	$settings['analysis']['analyzer'] = $this->analyzers;
234	2	$settings['analysis']['filter'] = $this->filters;
235
236
237	2	$properties['index'] = $settings;
238
239		/*
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `56%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
240
241		if ($this->foldedAscii) {
242		$foldingFilter = array('my_ascii_folding' => array(
243		"type" => "asciifolding",
244		"preserve_original" => 'true'
245		));
246		array_push($filters, $foldingFilter);
247		}
248		*/
249
250
251		/*
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `84%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
252		$json = '{
253		"settings": {
254		"analysis": {
255		"analyzer": {
256		"stemmed": {
257		"type": "english",
258		"stem_exclusion": [ "organization", "organizations" ],
259		"stopwords": [
260		"a", "an", "and", "are", "as", "at", "be", "but", "by", "for",
261		"if", "in", "into", "is", "it", "of", "on", "or", "such", "that",
262		"the", "their", "then", "there", "these", "they", "this", "to",
263		"was", "will", "with"
264		]
265		}
266		}
267		}
268		}
269		}';
270		*/
271		//$this->extend('alterIndexingProperties', $properties);
		0 ignored issues – show Unused Code Comprehensibility introduced 2015-12-01 14:39 UTC by Report Bug Copy Issue Report `80%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
272		//
273		//
274
275	2	return $properties;
276		}
277		}
278

gordonbanderson / silverstripe-elastica

Push — dev2 ( dd5bec...049fe2 )

BaseIndexSettings A

Complexity

Size/Duplication

Coupling/Cohesion

Test Coverage

7 Methods

Duplication Side-by-Side

Filter issues like