Indexer - Code Metrics - Inspection of "Merge branch 'feature/7-search-component' into dev..." - jenskooij/cloudcontrol - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — develop ( 169afe...f2bd80 )

by Jens

created 2017-03-12 22:05 UTC

Indexer A

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	167
Duplicated Lines	4.79 %

Coupling/Cohesion

Components	1
Dependencies	6

Importance

Changes

Metric	Value
dl	8
loc	167
rs	10
c	0
b	0
f	0
wmc	12
lcom	1
cbo	6

11 Methods

Rating	Name	Duplication	Size	Complexity
A	updateIndex()	0	21	1
A	createDocumentTermCount()	0	5	1
A	createDocumentTermFrequency()	0	5	1
A	resetIndex()	0	13	1
A	createInverseDocumentFrequency()	0	6	1
A	getTotalDocumentCount()	0	4	1
A	createTermFieldLengthNorm()	0	5	1
A	startLogging()	0	5	1
A	addLog()	0	6	1
A	getSearchDbHandle()	8	8	2
A	replaceOldIndex()	0	6	1

How to fix Duplicated Code

<?php
/**
 * User: jensk
 * Date: 21-2-2017
 * Time: 10:29
 */

namespace library\search;


use library\search\indexer\InverseDocumentFrequency;
use library\search\indexer\TermCount;
use library\search\indexer\TermFieldLengthNorm;
use library\search\indexer\TermFrequency;

/**
 * Class Indexer
 * Responsible for creating the search index based on the
 * existing documents
 *
 * @package library\search
 */
class Indexer extends SearchDbConnected
{
	const SQLITE_MAX_COMPOUND_SELECT = 100;
	protected $filters = array(
		'DutchStopWords',
		'EnglishStopWords'
	);
	protected $storageDir;
	/**
	 * @var int
	 */
	protected $loggingStart;
	/**
	 * @var string
	 */
	protected $log;
	/**
	 * @var int
	 */
	protected $lastLog;

	const SEARCH_TEMP_DB = 'search_tmp.db';

	/**
	 * Creates a new temporary search db, cleans it if it exists
	 * then calculates and stores the search index in this db
	 * and finally if indexing completed replaces the current search
	 * db with the temporary one. Returns the log in string format.
	 * @return string
	 */
	public function updateIndex()
	{
		$this->startLogging();
		$this->addLog('Indexing start.');
		$this->addLog('Clearing index.');
		$this->resetIndex();
		$this->addLog('Retrieving documents to be indexed.');
		$documents = $this->storage->getDocuments();
		$this->addLog('Start Document Term Count for ' . count($documents) . ' documents');
		$this->createDocumentTermCount($documents);
		$this->addLog('Start Document Term Frequency.');
		$this->createDocumentTermFrequency();
		$this->addLog('Start Term Field Length Norm.');
		$this->createTermFieldLengthNorm();
		$this->addLog('Start Inverse Document Frequency.');
		$this->createInverseDocumentFrequency();
		$this->addLog('Replacing old index.');
		$this->replaceOldIndex();
		$this->addLog('Indexing complete.');
		return $this->log;
	}

	/**
	 * Count how often a term is used in a document
	 *
	 * @param $documents
	 */
	public function createDocumentTermCount($documents)
	{
		$termCount = new TermCount($this->getSearchDbHandle(), $documents, $this->filters, $this->storage);
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);
		$termCount->execute();
	}

	/**
	 * Calculate the frequency index for a term with
	 * a field
	 */
	public function createDocumentTermFrequency()
	{
		$termFrequency = new TermFrequency($this->getSearchDbHandle());
		$termFrequency->execute();
	}


	/**
	 * Resets the entire index
	 */
	public function resetIndex()
	{
		$db = $this->getSearchDbHandle();
		$sql = '
			DELETE FROM term_count;
			DELETE FROM term_frequency;
			DELETE FROM inverse_document_frequency;
			UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'term_count\';
			UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'term_frequency\';
			UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'inverse_document_frequency\';
		';
		$db->exec($sql);
	}

	/**
	 * Calculates the inverse document frequency for each
	 * term. This is a representation of how often a certain
	 * term is used in comparison to all terms.
	 */
	public function createInverseDocumentFrequency()
	{
		$documentCount = $this->getTotalDocumentCount();
		$inverseDocumentFrequency = new InverseDocumentFrequency($this->getSearchDbHandle(), $documentCount);
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);
		$inverseDocumentFrequency->execute();
	}

	/**
	 * @return int|mixed
	 */
	private function getTotalDocumentCount()
	{
		return $this->storage->getTotalDocumentCount();
	}

	/**
	 * Calculates the Term Field Length Norm.
	 * This is an index determining how important a
	 * term is, based on the total length of the field
	 * it comes from.
	 */
	public function createTermFieldLengthNorm()
	{
		$termFieldLengthNorm = new TermFieldLengthNorm($this->getSearchDbHandle());
		$termFieldLengthNorm->execute();
	}

	/**
	 * Stores the time the indexing started in memory
	 */
	private function startLogging()
	{
		$this->loggingStart = round(microtime(true) * 1000);
$answer = 42;

$correct = false;

$correct = (bool) $answer;
		$this->lastLog = $this->loggingStart;
$answer = 42;

$correct = false;

$correct = (bool) $answer;
	}

	/**
	 * Adds a logline with the time since last log
	 * @param $string
	 */
	private function addLog($string)
	{
		$currentTime = round(microtime(true) * 1000);
		$this->log .= date('d-m-Y H:i:s - ') . str_pad($string, 50, " ", STR_PAD_RIGHT) . "\t" . ($currentTime - $this->lastLog) . 'ms since last log. ' . "\t" . ($currentTime - $this->loggingStart) . 'ms since start.' . PHP_EOL;
		$this->lastLog = round(microtime(true) * 1000);
$answer = 42;

$correct = false;

$correct = (bool) $answer;
	}

	/**
	 * Creates the SQLite \PDO object if it doesnt
	 * exist and returns it.
	 * @return \PDO
	 */
	protected function getSearchDbHandle()

	{
		if ($this->searchDbHandle === null) {
			$path = __DIR__ . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . $this->storageDir . DIRECTORY_SEPARATOR;
			$this->searchDbHandle = new \PDO('sqlite:' . $path . self::SEARCH_TEMP_DB);

		}
		return $this->searchDbHandle;
	}

	/**
	 * Replaces the old search index database with the new one.
	 */
	public function replaceOldIndex()
	{
		$this->searchDbHandle = null;
		$path = __DIR__ . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . $this->storageDir . DIRECTORY_SEPARATOR;
		rename($path . self::SEARCH_TEMP_DB, $path . 'search.db');
	}
}

1		<?php
2		/**
3		* User: jensk
4		* Date: 21-2-2017
5		* Time: 10:29
6		*/
7
8		namespace library\search;
9
10
11		use library\search\indexer\InverseDocumentFrequency;
12		use library\search\indexer\TermCount;
13		use library\search\indexer\TermFieldLengthNorm;
14		use library\search\indexer\TermFrequency;
15
16		/**
17		* Class Indexer
18		* Responsible for creating the search index based on the
19		* existing documents
20		*
21		* @package library\search
22		*/
23		class Indexer extends SearchDbConnected
24		{
25		const SQLITE_MAX_COMPOUND_SELECT = 100;
26		protected $filters = array(
27		'DutchStopWords',
28		'EnglishStopWords'
29		);
30		protected $storageDir;
31		/**
32		* @var int
33		*/
34		protected $loggingStart;
35		/**
36		* @var string
37		*/
38		protected $log;
39		/**
40		* @var int
41		*/
42		protected $lastLog;
43
44		const SEARCH_TEMP_DB = 'search_tmp.db';
45
46		/**
47		* Creates a new temporary search db, cleans it if it exists
48		* then calculates and stores the search index in this db
49		* and finally if indexing completed replaces the current search
50		* db with the temporary one. Returns the log in string format.
51		* @return string
52		*/
53		public function updateIndex()
54		{
55		$this->startLogging();
56		$this->addLog('Indexing start.');
57		$this->addLog('Clearing index.');
58		$this->resetIndex();
59		$this->addLog('Retrieving documents to be indexed.');
60		$documents = $this->storage->getDocuments();
61		$this->addLog('Start Document Term Count for ' . count($documents) . ' documents');
62		$this->createDocumentTermCount($documents);
63		$this->addLog('Start Document Term Frequency.');
64		$this->createDocumentTermFrequency();
65		$this->addLog('Start Term Field Length Norm.');
66		$this->createTermFieldLengthNorm();
67		$this->addLog('Start Inverse Document Frequency.');
68		$this->createInverseDocumentFrequency();
69		$this->addLog('Replacing old index.');
70		$this->replaceOldIndex();
71		$this->addLog('Indexing complete.');
72		return $this->log;
73		}
74
75		/**
76		* Count how often a term is used in a document
77		*
78		* @param $documents
79		*/
80		public function createDocumentTermCount($documents)
81		{
82		$termCount = new TermCount($this->getSearchDbHandle(), $documents, $this->filters, $this->storage);
		0 ignored issues – show Documentation introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report `$this->getSearchDbHandle()` is of type `object<PDO>`, but the function expects a `resource`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
83		$termCount->execute();
84		}
85
86		/**
87		* Calculate the frequency index for a term with
88		* a field
89		*/
90		public function createDocumentTermFrequency()
91		{
92		$termFrequency = new TermFrequency($this->getSearchDbHandle());
93		$termFrequency->execute();
94		}
95
96
97		/**
98		* Resets the entire index
99		*/
100		public function resetIndex()
101		{
102		$db = $this->getSearchDbHandle();
103		$sql = '
104		DELETE FROM term_count;
105		DELETE FROM term_frequency;
106		DELETE FROM inverse_document_frequency;
107		UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'term_count\';
108		UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'term_frequency\';
109		UPDATE `sqlite_sequence` SET `seq`= 0 WHERE `name`=\'inverse_document_frequency\';
110		';
111		$db->exec($sql);
112		}
113
114		/**
115		* Calculates the inverse document frequency for each
116		* term. This is a representation of how often a certain
117		* term is used in comparison to all terms.
118		*/
119		public function createInverseDocumentFrequency()
120		{
121		$documentCount = $this->getTotalDocumentCount();
122		$inverseDocumentFrequency = new InverseDocumentFrequency($this->getSearchDbHandle(), $documentCount);
		0 ignored issues – show Documentation introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report `$this->getSearchDbHandle()` is of type `object<PDO>`, but the function expects a `resource`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
123		$inverseDocumentFrequency->execute();
124		}
125
126		/**
127		* @return int\|mixed
128		*/
129		private function getTotalDocumentCount()
130		{
131		return $this->storage->getTotalDocumentCount();
132		}
133
134		/**
135		* Calculates the Term Field Length Norm.
136		* This is an index determining how important a
137		* term is, based on the total length of the field
138		* it comes from.
139		*/
140		public function createTermFieldLengthNorm()
141		{
142		$termFieldLengthNorm = new TermFieldLengthNorm($this->getSearchDbHandle());
143		$termFieldLengthNorm->execute();
144		}
145
146		/**
147		* Stores the time the indexing started in memory
148		*/
149		private function startLogging()
150		{
151		$this->loggingStart = round(microtime(true) * 1000);
		0 ignored issues – show Documentation Bug introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report The property `$loggingStart` was declared of type `integer`, but `round(microtime(true) * 1000)` is of type `double`. Maybe add a type cast? This check looks for assignments to scalar types that may be of the wrong type. To ensure the code behaves as expected, it may be a good idea to add an explicit type cast. $answer = 42; $correct = false; $correct = (bool) $answer; Loading history...
152		$this->lastLog = $this->loggingStart;
		0 ignored issues – show Documentation Bug introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report The property `$lastLog` was declared of type `integer`, but `$this->loggingStart` is of type `double`. Maybe add a type cast? This check looks for assignments to scalar types that may be of the wrong type. To ensure the code behaves as expected, it may be a good idea to add an explicit type cast. $answer = 42; $correct = false; $correct = (bool) $answer; Loading history...
153		}
154
155		/**
156		* Adds a logline with the time since last log
157		* @param $string
158		*/
159		private function addLog($string)
160		{
161		$currentTime = round(microtime(true) * 1000);
162		$this->log .= date('d-m-Y H:i:s - ') . str_pad($string, 50, " ", STR_PAD_RIGHT) . "\t" . ($currentTime - $this->lastLog) . 'ms since last log. ' . "\t" . ($currentTime - $this->loggingStart) . 'ms since start.' . PHP_EOL;
163		$this->lastLog = round(microtime(true) * 1000);
		0 ignored issues – show Documentation Bug introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report The property `$lastLog` was declared of type `integer`, but `round(microtime(true) * 1000)` is of type `double`. Maybe add a type cast? This check looks for assignments to scalar types that may be of the wrong type. To ensure the code behaves as expected, it may be a good idea to add an explicit type cast. $answer = 42; $correct = false; $correct = (bool) $answer; Loading history...
164		}
165
166		/**
167		* Creates the SQLite \PDO object if it doesnt
168		* exist and returns it.
169		* @return \PDO
170		*/
171	View Code Duplication	protected function getSearchDbHandle()
		0 ignored issues – show Duplication introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
172		{
173		if ($this->searchDbHandle === null) {
174		$path = __DIR__ . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . $this->storageDir . DIRECTORY_SEPARATOR;
175		$this->searchDbHandle = new \PDO('sqlite:' . $path . self::SEARCH_TEMP_DB);
		0 ignored issues – show Documentation Bug introduced 2017-03-12 22:07 UTC by Report Bug Copy Issue Report It seems like `new \PDO('sqlite:' . $pa.... self::SEARCH_TEMP_DB)` of type `object<PDO>` is incompatible with the declared type `resource` of property `$searchDbHandle`. Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property. Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property.. Loading history...
176		}
177		return $this->searchDbHandle;
178		}
179
180		/**
181		* Replaces the old search index database with the new one.
182		*/
183		public function replaceOldIndex()
184		{
185		$this->searchDbHandle = null;
186		$path = __DIR__ . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . '..' . DIRECTORY_SEPARATOR . $this->storageDir . DIRECTORY_SEPARATOR;
187		rename($path . self::SEARCH_TEMP_DB, $path . 'search.db');
188		}
189		}

jenskooij / cloudcontrol

Push — develop ( 169afe...f2bd80 )

Indexer A

Complexity

Size/Duplication

Coupling/Cohesion

Importance

11 Methods

How to fix Duplicated Code

Duplicated Code

Duplication Side-by-Side

Filter issues like