OCA\FullTextSearch_ElasticSearch\Service\SearchMappingService

Complexity

Total Complexity

27

Size/Duplication

Total Lines	255
Duplicated Lines	10.2 %

Coupling/Cohesion

Components	1
Dependencies	1

Importance

Changes	5
Bugs	0	Features	0

13 Methods

Rating	Name	Duplication	Size	Complexity
A	__construct()	0	4	1
A	generateSearchQuery()	0	7	1
B	generateSearchQueryParams()	0	24	1
A	improveSearchQuerying()	0	5	1
A	improveSearchWildcardQueries()	13	13	3
A	improveSearchWildcardFilters()	13	13	3
A	improveSearchRegexFilters()	0	13	3
B	generateSearchQueryContent()	0	24	2
A	modifySearchQueryContentOnCompleteWord()	0	8	3
A	complementSearchWithParts()	0	13	3
A	generateSearchQueryAccess()	0	17	3
A	generateSearchQueryTags()	0	9	2
A	generateSearchHighlighting()	0	7	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 <maxence@artificial-owl.com>
 * @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 OCA\FullTextSearch\IFullTextSearchProvider;
use OCA\FullTextSearch\Model\DocumentAccess;
use OCA\FullTextSearch\Model\SearchRequest;
use OCA\FullTextSearch_ElasticSearch\Exceptions\ConfigurationException;


class SearchMappingService {

	/** @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 IFullTextSearchProvider $provider
	 * @param DocumentAccess $access
	 * @param SearchRequest $request
	 *
	 * @return array

Consider making the return type a bit more specific; maybe use array<string,array>.

	 * @throws ConfigurationException
	 */
	public function generateSearchQuery(
		IFullTextSearchProvider $provider, DocumentAccess $access, SearchRequest $request
	) {
		$query['params'] = $this->generateSearchQueryParams($provider, $access, $request);

$query was never initialized. Although not strictly required by PHP, it is generally a good practice to add $query = array(); before regardless.

		return $query;
	}


	/**
	 * @param IFullTextSearchProvider $provider
	 * @param DocumentAccess $access
	 * @param SearchRequest $request
	 *
	 * @return array
	 * @throws ConfigurationException
	 */
	public function generateSearchQueryParams(
		IFullTextSearchProvider $provider, DocumentAccess $access, SearchRequest $request
	) {
		$params = [
			'index' => $this->configService->getElasticIndex(),
			'type'  => 'standard',
			'size'  => $request->getSize(),
			'from'  => (($request->getPage() - 1) * $request->getSize())
		];

		$bool = [];
		$bool['must']['bool']['should'] = $this->generateSearchQueryContent($request);

		$bool['filter'][]['bool']['must'] = ['term' => ['provider' => $provider->getId()]];
		$bool['filter'][]['bool']['should'] = $this->generateSearchQueryAccess($access);
		$bool['filter'][]['bool']['should'] = $this->generateSearchQueryTags($request->getTags());

		$params['body']['query']['bool'] = $bool;
		$params['body']['highlight'] = $this->generateSearchHighlighting();

		$this->improveSearchQuerying($request, $params['body']['query']);

		return $params;
	}


	/**
	 * @param SearchRequest $request
	 * @param array $arr
	 */
	private function improveSearchQuerying(SearchRequest $request, &$arr) {
		$this->improveSearchWildcardQueries($request, $arr);
		$this->improveSearchWildcardFilters($request, $arr);
		$this->improveSearchRegexFilters($request, $arr);
	}


	/**
	 * @param SearchRequest $request
	 * @param array $arr
	 */
	private function improveSearchWildcardQueries(SearchRequest $request, &$arr) {

This method seems to be duplicated in your project.

		$queries = $request->getWildcardQueries();
		foreach ($queries as $query) {
			$wildcards = [];
			foreach ($query as $entry) {
				$wildcards[] = ['wildcard' => $entry];
			}

			array_push($arr['bool']['must']['bool']['should'], $wildcards);
		}

	}


	/**
	 * @param SearchRequest $request
	 * @param array $arr
	 */
	private function improveSearchWildcardFilters(SearchRequest $request, &$arr) {

This method seems to be duplicated in your project.

		$filters = $request->getWildcardFilters();
		foreach ($filters as $filter) {
			$wildcards = [];
			foreach ($filter as $entry) {
				$wildcards[] = ['wildcard' => $entry];
			}

			$arr['bool']['filter'][]['bool']['should'] = $wildcards;
		}

	}


	/**
	 * @param SearchRequest $request
	 * @param array $arr
	 */
	private function improveSearchRegexFilters(SearchRequest $request, &$arr) {

		$filters = $request->getRegexFilters();
		foreach ($filters as $filter) {
			$regex = [];
			foreach ($filter as $entry) {
				$regex[] = ['regexp' => $entry];
			}

			$arr['bool']['filter'][]['bool']['should'] = $regex;
		}

	}


	/**
	 * @param SearchRequest $request
	 *
	 * @return array<string,array<string,array>>
	 */
	private function generateSearchQueryContent(SearchRequest $request) {
		$str = strtolower($request->getSearch());

		$queryTitle = $queryContent = $kwParts = [];
		$words = explode(' ', $str);
		foreach ($words as $word) {

			$kw = 'prefix';
			$this->modifySearchQueryContentOnCompleteWord($kw, $word);

			$queryTitle[] = [$kw => ['title' => $word]];
			$queryContent[] = [$kw => ['content' => $word]];
			$kwParts[] = ['kw' => $kw, 'word' => $word];
		}

		$query = [
			['bool' => ['must' => $queryTitle]],
			['bool' => ['must' => $queryContent]]
		];

		$query = array_merge($query, $this->complementSearchWithParts($request, $kwParts));

		return $query;
	}


	/**
	 * @param string $kw
	 * @param string $word
	 */
	private function modifySearchQueryContentOnCompleteWord(&$kw, &$word) {
		if (substr($word, 0, 1) !== '"' || substr($word, -1) !== '"') {
			return;
		}

		$kw = 'match';
		$word = substr($word, 1, -1);
	}


	/**
	 * @param SearchRequest $request
	 * @param array $kwParts
	 *
	 * @return array
	 */
	private function complementSearchWithParts(SearchRequest $request, $kwParts) {
		$query = [];
		foreach ($request->getParts() as $part) {
			$queryParts = [];
			foreach ($kwParts as $kwPart) {
				$queryParts[] = [$kwPart['kw'] => ['parts.' . $part => $kwPart['word']]];
			}

			$query[] = ['bool' => ['must' => $queryParts]];
		}

		return $query;
	}


	/**
	 * @param DocumentAccess $access
	 *
	 * @return array<string,array>

Should the return type not be array<string,array>[]?

	 */
	private function generateSearchQueryAccess(DocumentAccess $access) {

		$query = [];
		$query[] = ['term' => ['owner' => $access->getViewerId()]];
		$query[] = ['term' => ['users' => $access->getViewerId()]];
		$query[] = ['term' => ['users' => '__all']];

		foreach ($access->getGroups() as $group) {
			$query[] = ['term' => ['groups' => $group]];
		}

		foreach ($access->getCircles() as $circle) {
			$query[] = ['term' => ['circles' => $circle]];
		}

		return $query;
	}


	/**
	 * @param array $tags
	 *
	 * @return array<string,array>
	 */
	private function generateSearchQueryTags($tags) {

		$query = [];
		foreach ($tags as $tag) {
			$query[] = ['term' => ['tags' => $tag]];
		}

		return $query;
	}

	private function generateSearchHighlighting() {
		return [
			'fields'    => ['content' => new \stdClass()],
			'pre_tags'  => [''],
			'post_tags' => ['']
		];
	}


}