Source of file Fuzzy.php
Size: 10,985 Bytes - Last Modified: 2021-12-23T10:29:30+00:00
/var/www/docs.ssmods.com/process/src/thirdparty/Zend/Search/Lucene/Search/Query/Preprocessing/Fuzzy.php
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301 | <?php /** * Zend Framework * * LICENSE * * This source file is subject to the new BSD license that is bundled * with this package in the file LICENSE.txt. * It is also available through the world-wide-web at this URL: * http://framework.zend.com/license/new-bsd * If you did not receive a copy of the license and are unable to * obtain it through the world-wide-web, please send an email * to license@zend.com so we can send you a copy immediately. * * @category Zend * @package Zend_Search_Lucene * @subpackage Search * @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com) * @license http://framework.zend.com/license/new-bsd New BSD License * @version $Id: Fuzzy.php 20096 2010-01-06 02:05:09Z bkarwin $ */ /** * Zend_Search_Lucene_Search_Query_Processing */ require_once 'Zend/Search/Lucene/Search/Query/Preprocessing.php'; /** * It's an internal abstract class intended to finalize ase a query processing after query parsing. * This type of query is not actually involved into query execution. * * @category Zend * @package Zend_Search_Lucene * @subpackage Search * @internal * @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com) * @license http://framework.zend.com/license/new-bsd New BSD License */ class Zend_Search_Lucene_Search_Query_Preprocessing_Fuzzy extends Zend_Search_Lucene_Search_Query_Preprocessing { /** * word (query parser lexeme) to find. * * @var string */ private $_word; /** * Word encoding (field name is always provided using UTF-8 encoding since it may be retrieved from index). * * @var string */ private $_encoding; /** * Field name. * * @var string */ private $_field; /** * A value between 0 and 1 to set the required similarity * between the query term and the matching terms. For example, for a * _minimumSimilarity of 0.5 a term of the same length * as the query term is considered similar to the query term if the edit distance * between both terms is less than length(term)*0.5 * * @var float */ private $_minimumSimilarity; /** * Class constructor. Create a new preprocessing object for prase query. * * @param string $word Non-tokenized word (query parser lexeme) to search. * @param string $encoding Word encoding. * @param string $fieldName Field name. * @param float $minimumSimilarity minimum similarity */ public function __construct($word, $encoding, $fieldName, $minimumSimilarity) { $this->_word = $word; $this->_encoding = $encoding; $this->_field = $fieldName; $this->_minimumSimilarity = $minimumSimilarity; } /** * Re-write query into primitive queries in the context of specified index * * @param Zend_Search_Lucene_Interface $index * @return Zend_Search_Lucene_Search_Query */ public function rewrite(Zend_Search_Lucene_Interface $index) { if ($this->_field === null) { include_once 'Zend/Search/Lucene/Search/Query/Boolean.php'; $query = new Zend_Search_Lucene_Search_Query_Boolean(); $hasInsignificantSubqueries = false; include_once 'Zend/Search/Lucene.php'; if (Zend_Search_Lucene::getDefaultSearchField() === null) { $searchFields = $index->getFieldNames(true); } else { $searchFields = array(Zend_Search_Lucene::getDefaultSearchField()); } include_once 'Zend/Search/Lucene/Search/Query/Preprocessing/Fuzzy.php'; foreach ($searchFields as $fieldName) { $subquery = new Zend_Search_Lucene_Search_Query_Preprocessing_Fuzzy( $this->_word, $this->_encoding, $fieldName, $this->_minimumSimilarity ); $rewrittenSubquery = $subquery->rewrite($index); if (!($rewrittenSubquery instanceof Zend_Search_Lucene_Search_Query_Insignificant || $rewrittenSubquery instanceof Zend_Search_Lucene_Search_Query_Empty) ) { $query->addSubquery($rewrittenSubquery); } if ($rewrittenSubquery instanceof Zend_Search_Lucene_Search_Query_Insignificant) { $hasInsignificantSubqueries = true; } } $subqueries = $query->getSubqueries(); if (count($subqueries) == 0) { $this->_matches = array(); if ($hasInsignificantSubqueries) { include_once 'Zend/Search/Lucene/Search/Query/Insignificant.php'; return new Zend_Search_Lucene_Search_Query_Insignificant(); } else { include_once 'Zend/Search/Lucene/Search/Query/Empty.php'; return new Zend_Search_Lucene_Search_Query_Empty(); } } if (count($subqueries) == 1) { $query = reset($subqueries); } $query->setBoost($this->getBoost()); $this->_matches = $query->getQueryTerms(); return $query; } // ------------------------------------- // Recognize exact term matching (it corresponds to Keyword fields stored in the index) // encoding is not used since we expect binary matching include_once 'Zend/Search/Lucene/Index/Term.php'; $term = new Zend_Search_Lucene_Index_Term($this->_word, $this->_field); if ($index->hasTerm($term)) { include_once 'Zend/Search/Lucene/Search/Query/Fuzzy.php'; $query = new Zend_Search_Lucene_Search_Query_Fuzzy($term, $this->_minimumSimilarity); $query->setBoost($this->getBoost()); // Get rewritten query. Important! It also fills terms matching container. $rewrittenQuery = $query->rewrite($index); $this->_matches = $query->getQueryTerms(); return $rewrittenQuery; } // ------------------------------------- // Recognize wildcard queries /** * @todo check for PCRE unicode support may be performed through Zend_Environment in some future */ if (@preg_match('/\pL/u', 'a') == 1) { $subPatterns = preg_split('/[*?]/u', iconv($this->_encoding, 'UTF-8', $this->_word)); } else { $subPatterns = preg_split('/[*?]/', $this->_word); } if (count($subPatterns) > 1) { include_once 'Zend/Search/Lucene/Search/QueryParserException.php'; throw new Zend_Search_Lucene_Search_QueryParserException('Fuzzy search doesn\'t support wildcards (except within Keyword fields).'); } // ------------------------------------- // Recognize one-term multi-term and "insignificant" queries include_once 'Zend/Search/Lucene/Analysis/Analyzer.php'; $tokens = Zend_Search_Lucene_Analysis_Analyzer::getDefault()->tokenize($this->_word, $this->_encoding); if (count($tokens) == 0) { $this->_matches = array(); include_once 'Zend/Search/Lucene/Search/Query/Insignificant.php'; return new Zend_Search_Lucene_Search_Query_Insignificant(); } if (count($tokens) == 1) { include_once 'Zend/Search/Lucene/Index/Term.php'; $term = new Zend_Search_Lucene_Index_Term($tokens[0]->getTermText(), $this->_field); include_once 'Zend/Search/Lucene/Search/Query/Fuzzy.php'; $query = new Zend_Search_Lucene_Search_Query_Fuzzy($term, $this->_minimumSimilarity); $query->setBoost($this->getBoost()); // Get rewritten query. Important! It also fills terms matching container. $rewrittenQuery = $query->rewrite($index); $this->_matches = $query->getQueryTerms(); return $rewrittenQuery; } // Word is tokenized into several tokens include_once 'Zend/Search/Lucene/Search/QueryParserException.php'; throw new Zend_Search_Lucene_Search_QueryParserException('Fuzzy search is supported only for non-multiple word terms'); } /** * Query specific matches highlighting * * @param Zend_Search_Lucene_Search_Highlighter_Interface $highlighter Highlighter object (also contains doc for highlighting) */ protected function _highlightMatches(Zend_Search_Lucene_Search_Highlighter_Interface $highlighter) { /** * Skip fields detection. We don't need it, since we expect all fields presented in the HTML body and don't differentiate them */ /** * Skip exact term matching recognition, keyword fields highlighting is not supported */ // ------------------------------------- // Recognize wildcard queries /** * @todo check for PCRE unicode support may be performed through Zend_Environment in some future */ if (@preg_match('/\pL/u', 'a') == 1) { $subPatterns = preg_split('/[*?]/u', iconv($this->_encoding, 'UTF-8', $this->_word)); } else { $subPatterns = preg_split('/[*?]/', $this->_word); } if (count($subPatterns) > 1) { // Do nothing return; } // ------------------------------------- // Recognize one-term multi-term and "insignificant" queries include_once 'Zend/Search/Lucene/Analysis/Analyzer.php'; $tokens = Zend_Search_Lucene_Analysis_Analyzer::getDefault()->tokenize($this->_word, $this->_encoding); if (count($tokens) == 0) { // Do nothing return; } if (count($tokens) == 1) { include_once 'Zend/Search/Lucene/Index/Term.php'; $term = new Zend_Search_Lucene_Index_Term($tokens[0]->getTermText(), $this->_field); include_once 'Zend/Search/Lucene/Search/Query/Fuzzy.php'; $query = new Zend_Search_Lucene_Search_Query_Fuzzy($term, $this->_minimumSimilarity); $query->_highlightMatches($highlighter); return; } // Word is tokenized into several tokens // But fuzzy search is supported only for non-multiple word terms // Do nothing } /** * Print a query * * @return string */ public function __toString() { // It's used only for query visualisation, so we don't care about characters escaping if ($this->_field !== null) { $query = $this->_field . ':'; } else { $query = ''; } $query .= $this->_word; if ($this->getBoost() != 1) { $query .= '^' . round($this->getBoost(), 4); } return $query; } } |