IndexMappingService::generateDeleteQuery() - Code Metrics - Inspection of "getdocument(), deletebyquery()" - nextcloud/fulltextsearch_elasticsearch - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 94b632...a799ec )

by Maxence

created 2018-07-27 09:52 UTC

IndexMappingService::generateDeleteQuery() A

↳ Parent: IndexMappingService

Complexity

Conditions	1
Paths	1

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	10
rs	9.9332
c	0
b	0
f	0
cc	1
nc	1
nop	1

<?php
/**
 * FullTextSearch_ElasticSearch - Use Elasticsearch to index the content of your nextcloud
 *
 * This file is licensed under the Affero General Public License version 3 or
 * later. See the COPYING file.
 *
 * @author Maxence Lange <[email protected]>
 * @copyright 2018
 * @license GNU AGPL version 3 or any later version
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 */

namespace OCA\FullTextSearch_ElasticSearch\Service;

use Elasticsearch\Client;
use Elasticsearch\Common\Exceptions\Missing404Exception;
use OCA\FullTextSearch\Model\IndexDocument;
use OCA\FullTextSearch_ElasticSearch\Exceptions\AccessIsEmptyException;
use OCA\FullTextSearch_ElasticSearch\Exceptions\ConfigurationException;


class IndexMappingService {

	/** @var ConfigService */
	private $configService;

	/** @var MiscService */
	private $miscService;


	/**
	 * MappingService constructor.
	 *
	 * @param ConfigService $configService
	 * @param MiscService $miscService
	 */
	public function __construct(ConfigService $configService, MiscService $miscService) {
		$this->configService = $configService;
		$this->miscService = $miscService;
	}


	/**
	 * @param Client $client
	 * @param IndexDocument $document
	 *
	 * @return array

	 * @throws ConfigurationException
	 * @throws AccessIsEmptyException
	 */
	public function indexDocumentNew(Client $client, IndexDocument $document) {
		$index = [
			'index' =>
				[
					'index' => $this->configService->getElasticIndex(),
					'id'    => $document->getProviderId() . ':' . $document->getId(),
					'type'  => 'standard',
					'body'  => $this->generateIndexBody($document)
				]
		];

		$this->onIndexingDocument($document, $index);

		return $client->index($index['index']);
	}


	/**
	 * @param Client $client
	 * @param IndexDocument $document
	 *
	 * @return array

	 * @throws ConfigurationException
	 * @throws AccessIsEmptyException
	 */
	public function indexDocumentUpdate(Client $client, IndexDocument $document) {
		$index = [
			'index' =>
				[
					'index' => $this->configService->getElasticIndex(),
					'id'    => $document->getProviderId() . ':' . $document->getId(),
					'type'  => 'standard',
					'body'  => ['doc' => $this->generateIndexBody($document)]
				]
		];

		$this->onIndexingDocument($document, $index);
		try {
			return $client->update($index['index']);
		} catch (Missing404Exception $e) {
			return $this->indexDocumentNew($client, $document);
		}
	}


	/**
	 * @param Client $client
	 * @param string $providerId
	 * @param string|int $documentId
	 *
	 * @throws ConfigurationException
	 */
	public function indexDocumentRemove(Client $client, $providerId, $documentId) {
		$index = [
			'index' =>
				[
					'index' => $this->configService->getElasticIndex(),
					'id'    => $providerId . ':' . $documentId,
					'type'  => 'standard'
				]
		];

		try {
			$client->delete($index['index']);
		} catch (Missing404Exception $e) {

		}
	}


	/**
	 * @param IndexDocument $document
	 * @param array $arr
	 */
	public function onIndexingDocument(IndexDocument $document, &$arr) {
		if ($document->isContentEncoded() === IndexDocument::ENCODED_BASE64) {
			$arr['index']['pipeline'] = 'attachment';
		}
	}


	/**
	 * @param IndexDocument $document
	 *
	 * @return array
	 * @throws AccessIsEmptyException
	 */
	public function generateIndexBody(IndexDocument $document) {

		$access = $document->getAccess();
		if ($access === null) {
			throw new AccessIsEmptyException('DocumentAccess is Empty');
		}

		$body = [
			'owner'    => $access->getOwnerId(),
			'users'    => $access->getUsers(),
			'groups'   => $access->getGroups(),
			'circles'  => $access->getCircles(),
			'tags'     => $document->getTags(),
			'hash'     => $document->getHash(),
			'provider' => $document->getProviderId(),
			'source'   => $document->getSource(),
			'title'    => $document->getTitle(),
			'parts'    => $document->getParts()
		];

		if ($document->getContent() !== null) {
			$body['content'] = $document->getContent();
		}

		return array_merge($document->getInfoAll(), $body);
	}


	/**
	 * @param bool $complete
	 *
	 * @return array<string,string|array<string,array<string,array<string,array>>>>

	 * @throws ConfigurationException
	 */
	public function generateGlobalMap($complete = true) {

		$params = [
			'index' => $this->configService->getElasticIndex()
		];

		if ($complete === false) {
			return $params;
		}

		$params['body'] = [
			'settings' => [
				'analysis' => [
					'filter'      => [
						'shingle' => [
							'type' => 'shingle'
						]
					],
					'char_filter' => [
						'pre_negs'  => [
							'type'        => 'pattern_replace',
							'pattern'     => '(\\w+)\\s+((?i:never|no|nothing|nowhere|noone|none|not|havent|hasnt|hadnt|cant|couldnt|shouldnt|wont|wouldnt|dont|doesnt|didnt|isnt|arent|aint))\\b',

							'replacement' => '~$1 $2'
						],
						'post_negs' => [
							'type'        => 'pattern_replace',
							'pattern'     => '\\b((?i:never|no|nothing|nowhere|noone|none|not|havent|hasnt|hadnt|cant|couldnt|shouldnt|wont|wouldnt|dont|doesnt|didnt|isnt|arent|aint))\\s+(\\w+)',

							'replacement' => '$1 ~$2'
						]
					],
					'analyzer'    => [
						'analyzer' => [
							'type'      => 'custom',
							'tokenizer' => $this->configService->getAppValue(
								ConfigService::ANALYZER_TOKENIZER
							),
							'filter'    => ['lowercase', 'stop', 'kstem']
						]
					]
				]
			],
			'mappings' => [
				'standard' => [
					'dynamic'    => true,
					'properties' => [
						'source'   => [
							'type' => 'keyword'
						],
						'title'    => [
							'type'        => 'text',
							'analyzer'    => 'keyword',
							'term_vector' => 'yes',
							'copy_to'     => 'combined'
						],
						'provider' => [
							'type' => 'keyword'
						],
						'tags'     => [
							'type' => 'keyword'
						],
						'content'  => [
							'type'        => 'text',
							'analyzer'    => 'analyzer',
							'term_vector' => 'yes',
							'copy_to'     => 'combined'
						],
						'owner'    => [
							'type' => 'keyword'
						],
						'users'    => [
							'type' => 'keyword'
						],
						'groups'   => [
							'type' => 'keyword'
						],
						'circles'  => [
							'type' => 'keyword'
						],
						'hash'     => [
							'type' => 'keyword'
						],
						'combined' => [
							'type'        => 'text',
							'analyzer'    => 'analyzer',
							'term_vector' => 'yes'
						]
						//						,
						//						'topics'   => [

						//							'type'  => 'text',

						//							'index' => 'not_analyzed'

						//						],
						//						'places'   => [

						//							'type'  => 'text',

						//							'index' => 'not_analyzed'

						//						]
					]
				]
			]
		];

		return $params;
	}


	/**
	 * @param bool $complete
	 *
	 * @return array<string,string|array<string,string|array<string,array<string,string|integer>>>>

	 */
	public function generateGlobalIngest($complete = true) {

		$params = ['id' => 'attachment'];

		if ($complete === false) {
			return $params;
		}

		$params['body'] = [
			'description' => 'attachment',
			'processors'  => [
				[
					'attachment' => [
						'field'         => 'content',
						'indexed_chars' => -1
					],
					'convert'    => [
						'field'        => 'attachment.content',
						'type'         => 'string',
						'target_field' => 'content'
					],
					'remove'     => [
						'field'          => 'attachment.content',
						'ignore_failure' => true
					]
				]
			]
		];

		return $params;
	}


	/**
	 * @param string $providerId
	 *
	 * @return array

	 * @throws ConfigurationException
	 */
	public function generateDeleteQuery($providerId) {
		$params = [
			'index' => $this->configService->getElasticIndex(),
			'type'  => 'standard'
		];

		$params['body']['query']['match'] = ['provider' => $providerId];

		return $params;
	}

}


1			<?php
2			/**
3			* FullTextSearch_ElasticSearch - Use Elasticsearch to index the content of your nextcloud
4			*
5			* This file is licensed under the Affero General Public License version 3 or
6			* later. See the COPYING file.
7			*
8			* @author Maxence Lange <[email protected]>
9			* @copyright 2018
10			* @license GNU AGPL version 3 or any later version
11			*
12			* This program is free software: you can redistribute it and/or modify
13			* it under the terms of the GNU Affero General Public License as
14			* published by the Free Software Foundation, either version 3 of the
15			* License, or (at your option) any later version.
16			*
17			* This program is distributed in the hope that it will be useful,
18			* but WITHOUT ANY WARRANTY; without even the implied warranty of
19			* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20			* GNU Affero General Public License for more details.
21			*
22			* You should have received a copy of the GNU Affero General Public License
23			* along with this program. If not, see <http://www.gnu.org/licenses/>.
24			*
25			*/
26
27			namespace OCA\FullTextSearch_ElasticSearch\Service;
28
29			use Elasticsearch\Client;
30			use Elasticsearch\Common\Exceptions\Missing404Exception;
31			use OCA\FullTextSearch\Model\IndexDocument;
32			use OCA\FullTextSearch_ElasticSearch\Exceptions\AccessIsEmptyException;
33			use OCA\FullTextSearch_ElasticSearch\Exceptions\ConfigurationException;
34
35
36			class IndexMappingService {
37
38			/** @var ConfigService */
39			private $configService;
40
41			/** @var MiscService */
42			private $miscService;
43
44
45			/**
46			* MappingService constructor.
47			*
48			* @param ConfigService $configService
49			* @param MiscService $miscService
50			*/
51			public function __construct(ConfigService $configService, MiscService $miscService) {
52			$this->configService = $configService;
53			$this->miscService = $miscService;
54			}
55
56
57			/**
58			* @param Client $client
59			* @param IndexDocument $document
60			*
61			* @return array
			0 ignored issues – show Documentation introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report Should the return type not be `callable`? Also, consider making the array more specific, something like `array<String>`, or `String[]`. This check compares the return type specified in the `@return` annotation of a function or method doc comment with the types returned by the function and raises an issue if they mismatch. If the return type contains the type array, this check recommends the use of a more specific type like `String[]` or `array<String>`. Loading history...
62			* @throws ConfigurationException
63			* @throws AccessIsEmptyException
64			*/
65			public function indexDocumentNew(Client $client, IndexDocument $document) {
66			$index = [
67			'index' =>
68			[
69			'index' => $this->configService->getElasticIndex(),
70			'id' => $document->getProviderId() . ':' . $document->getId(),
71			'type' => 'standard',
72			'body' => $this->generateIndexBody($document)
73			]
74			];
75
76			$this->onIndexingDocument($document, $index);
77
78			return $client->index($index['index']);
79			}
80
81
82			/**
83			* @param Client $client
84			* @param IndexDocument $document
85			*
86			* @return array
			0 ignored issues – show Documentation introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report Should the return type not be `callable`? Also, consider making the array more specific, something like `array<String>`, or `String[]`. This check compares the return type specified in the `@return` annotation of a function or method doc comment with the types returned by the function and raises an issue if they mismatch. If the return type contains the type array, this check recommends the use of a more specific type like `String[]` or `array<String>`. Loading history...
87			* @throws ConfigurationException
88			* @throws AccessIsEmptyException
89			*/
90			public function indexDocumentUpdate(Client $client, IndexDocument $document) {
91			$index = [
92			'index' =>
93			[
94			'index' => $this->configService->getElasticIndex(),
95			'id' => $document->getProviderId() . ':' . $document->getId(),
96			'type' => 'standard',
97			'body' => ['doc' => $this->generateIndexBody($document)]
98			]
99			];
100
101			$this->onIndexingDocument($document, $index);
102			try {
103			return $client->update($index['index']);
104			} catch (Missing404Exception $e) {
105			return $this->indexDocumentNew($client, $document);
106			}
107			}
108
109
110			/**
111			* @param Client $client
112			* @param string $providerId
113			* @param string\|int $documentId
114			*
115			* @throws ConfigurationException
116			*/
117			public function indexDocumentRemove(Client $client, $providerId, $documentId) {
118			$index = [
119			'index' =>
120			[
121			'index' => $this->configService->getElasticIndex(),
122			'id' => $providerId . ':' . $documentId,
123			'type' => 'standard'
124			]
125			];
126
127			try {
128			$client->delete($index['index']);
129			} catch (Missing404Exception $e) {
			0 ignored issues – show Coding Style Comprehensibility introduced 2018-04-09 12:56 UTC by Report Bug Copy Issue Report Consider adding a comment why this CATCH block is empty. Loading history...
130			}
131			}
132
133
134			/**
135			* @param IndexDocument $document
136			* @param array $arr
137			*/
138			public function onIndexingDocument(IndexDocument $document, &$arr) {
139			if ($document->isContentEncoded() === IndexDocument::ENCODED_BASE64) {
140			$arr['index']['pipeline'] = 'attachment';
141			}
142			}
143
144
145			/**
146			* @param IndexDocument $document
147			*
148			* @return array
149			* @throws AccessIsEmptyException
150			*/
151			public function generateIndexBody(IndexDocument $document) {
152
153			$access = $document->getAccess();
154			if ($access === null) {
155			throw new AccessIsEmptyException('DocumentAccess is Empty');
156			}
157
158			$body = [
159			'owner' => $access->getOwnerId(),
160			'users' => $access->getUsers(),
161			'groups' => $access->getGroups(),
162			'circles' => $access->getCircles(),
163			'tags' => $document->getTags(),
164			'hash' => $document->getHash(),
165			'provider' => $document->getProviderId(),
166			'source' => $document->getSource(),
167			'title' => $document->getTitle(),
168			'parts' => $document->getParts()
169			];
170
171			if ($document->getContent() !== null) {
172			$body['content'] = $document->getContent();
173			}
174
175			return array_merge($document->getInfoAll(), $body);
176			}
177
178
179			/**
180			* @param bool $complete
181			*
182			* @return array<string,string\|array<string,array<string,array<string,array>>>>
			0 ignored issues – show Documentation introduced 2018-07-23 10:53 UTC by Report Bug Copy Issue Report Should the return type not be `array<string,string\|arra...tring,array\|boolean>>>>`? This check compares the return type specified in the `@return` annotation of a function or method doc comment with the types returned by the function and raises an issue if they mismatch. Loading history...
183			* @throws ConfigurationException
184			*/
185			public function generateGlobalMap($complete = true) {
186
187			$params = [
188			'index' => $this->configService->getElasticIndex()
189			];
190
191			if ($complete === false) {
192			return $params;
193			}
194
195			$params['body'] = [
196			'settings' => [
197			'analysis' => [
198			'filter' => [
199			'shingle' => [
200			'type' => 'shingle'
201			]
202			],
203			'char_filter' => [
204			'pre_negs' => [
205			'type' => 'pattern_replace',
206			'pattern' => '(\\w+)\\s+((?i:never\|no\|nothing\|nowhere\|noone\|none\|not\|havent\|hasnt\|hadnt\|cant\|couldnt\|shouldnt\|wont\|wouldnt\|dont\|doesnt\|didnt\|isnt\|arent\|aint))\\b',
			0 ignored issues – show Coding Style introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 100 characters; contains 174 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
207			'replacement' => '~$1 $2'
208			],
209			'post_negs' => [
210			'type' => 'pattern_replace',
211			'pattern' => '\\b((?i:never\|no\|nothing\|nowhere\|noone\|none\|not\|havent\|hasnt\|hadnt\|cant\|couldnt\|shouldnt\|wont\|wouldnt\|dont\|doesnt\|didnt\|isnt\|arent\|aint))\\s+(\\w+)',
			0 ignored issues – show Coding Style introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 100 characters; contains 174 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
212			'replacement' => '$1 ~$2'
213			]
214			],
215			'analyzer' => [
216			'analyzer' => [
217			'type' => 'custom',
218			'tokenizer' => $this->configService->getAppValue(
219			ConfigService::ANALYZER_TOKENIZER
220			),
221			'filter' => ['lowercase', 'stop', 'kstem']
222			]
223			]
224			]
225			],
226			'mappings' => [
227			'standard' => [
228			'dynamic' => true,
229			'properties' => [
230			'source' => [
231			'type' => 'keyword'
232			],
233			'title' => [
234			'type' => 'text',
235			'analyzer' => 'keyword',
236			'term_vector' => 'yes',
237			'copy_to' => 'combined'
238			],
239			'provider' => [
240			'type' => 'keyword'
241			],
242			'tags' => [
243			'type' => 'keyword'
244			],
245			'content' => [
246			'type' => 'text',
247			'analyzer' => 'analyzer',
248			'term_vector' => 'yes',
249			'copy_to' => 'combined'
250			],
251			'owner' => [
252			'type' => 'keyword'
253			],
254			'users' => [
255			'type' => 'keyword'
256			],
257			'groups' => [
258			'type' => 'keyword'
259			],
260			'circles' => [
261			'type' => 'keyword'
262			],
263			'hash' => [
264			'type' => 'keyword'
265			],
266			'combined' => [
267			'type' => 'text',
268			'analyzer' => 'analyzer',
269			'term_vector' => 'yes'
270			]
271			// ,
272			// 'topics' => [
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `50%` 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...
273			// 'type' => 'text',
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `58%` 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...
274			// 'index' => 'not_analyzed'
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `50%` 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...
275			// ],
276			// 'places' => [
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `50%` 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...
277			// 'type' => 'text',
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `58%` 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...
278			// 'index' => 'not_analyzed'
			0 ignored issues – show Unused Code Comprehensibility introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report `50%` 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...
279			// ]
280			]
281			]
282			]
283			];
284
285			return $params;
286			}
287
288
289			/**
290			* @param bool $complete
291			*
292			* @return array<string,string\|array<string,string\|array<string,array<string,string\|integer>>>>
			0 ignored issues – show Documentation introduced 2018-01-10 22:16 UTC by Report Bug Copy Issue Report Should the return type not be `array<string,string\|arra...array<string,array>[]>>`? This check compares the return type specified in the `@return` annotation of a function or method doc comment with the types returned by the function and raises an issue if they mismatch. Loading history...
293			*/
294			public function generateGlobalIngest($complete = true) {
295
296			$params = ['id' => 'attachment'];
297
298			if ($complete === false) {
299			return $params;
300			}
301
302			$params['body'] = [
303			'description' => 'attachment',
304			'processors' => [
305			[
306			'attachment' => [
307			'field' => 'content',
308			'indexed_chars' => -1
309			],
310			'convert' => [
311			'field' => 'attachment.content',
312			'type' => 'string',
313			'target_field' => 'content'
314			],
315			'remove' => [
316			'field' => 'attachment.content',
317			'ignore_failure' => true
318			]
319			]
320			]
321			];
322
323			return $params;
324			}
325
326
327			/**
328			* @param string $providerId
329			*
330			* @return array
			0 ignored issues – show Documentation introduced 2018-02-05 12:42 UTC by Report Bug Copy Issue Report Consider making the return type a bit more specific; maybe use `array<string,string>`. This check looks for the generic type `array` as a return type and suggests a more specific type. This type is inferred from the actual code. Loading history...
331			* @throws ConfigurationException
332			*/
333			public function generateDeleteQuery($providerId) {
334			$params = [
335			'index' => $this->configService->getElasticIndex(),
336			'type' => 'standard'
337			];
338
339			$params['body']['query']['match'] = ['provider' => $providerId];
340
341			return $params;
342			}
343
344			}
345

nextcloud / fulltextsearch_elasticsearch

Push — master ( 94b632...a799ec )

IndexMappingService::generateDeleteQuery() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like