includes/SearchTsearch2.php

   1 <?php
   2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com>, Domas Mituzas <domas.mituzas@gmail.com>
   3 # http://www.mediawiki.org/
   4 #
   5 # This program is free software; you can redistribute it and/or modify
   6 # it under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 2 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # This program is distributed in the hope that it will be useful,
  11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License along
  16 # with this program; if not, write to the Free Software Foundation, Inc.,
  17 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  * Search engine hook for PostgreSQL / Tsearch2
  22  * @file
  23  * @ingroup Search
  24  */
  25
  26 /**
  27  * @todo document
  28  * @ingroup Search
  29  */
  30 class SearchTsearch2 extends SearchEngine {
  31         var $strictMatching = false;
  32
  33         function __construct( $db ) {
  34                 $this->db = $db;
  35                 $this->mRanking = true;
  36         }
  37
  38         function getIndexField( $fulltext ) {
  39                 return $fulltext ? 'si_text' : 'si_title';
  40         }
  41
  42         function parseQuery( $filteredText, $fulltext ) {
  43                 global $wgContLang;
  44                 $lc = SearchEngine::legalSearchChars();
  45                 $searchon = '';
  46                 $this->searchTerms = array();
  47
  48                 # FIXME: This doesn't handle parenthetical expressions.
  49                 $m = array();
  50                 if( preg_match_all( '/([-+<>~]?)(([' . $lc . ']+)(\*?)|"[^"]*")/',
  51                           $filteredText, $m, PREG_SET_ORDER ) ) {
  52                         foreach( $m as $terms ) {
  53                                 if( $searchon !== '' ) $searchon .= ' ';
  54                                 if( $this->strictMatching && ($terms[1] == '') ) {
  55                                         $terms[1] = '+';
  56                                 }
  57                                 $searchon .= $terms[1] . $wgContLang->stripForSearch( $terms[2] );
  58                                 if( !empty( $terms[3] ) ) {
  59                                         $regexp = preg_quote( $terms[3], '/' );
  60                                         if( $terms[4] ) $regexp .= "[0-9A-Za-z_]+";
  61                                 } else {
  62                                         $regexp = preg_quote( str_replace( '"', '', $terms[2] ), '/' );
  63                                 }
  64                                 $this->searchTerms[] = $regexp;
  65                         }
  66                         wfDebug( "Would search with '$searchon'\n" );
  67                         wfDebug( 'Match with /\b' . implode( '\b|\b', $this->searchTerms ) . "\b/\n" );
  68                 } else {
  69                         wfDebug( "Can't understand search query '{$this->filteredText}'\n" );
  70                 }
  71
  72                 $searchon = preg_replace( '/(\s+)/', '&', $searchon );
  73                 $searchon = $this->db->strencode( $searchon );
  74                 return $searchon;
  75         }
  76
  77         function queryRanking( $filteredTerm, $fulltext ) {
  78                 $field = $this->getIndexField( $fulltext );
  79                 $searchon = $this->parseQuery( $filteredTerm, $fulltext );
  80                 if ($this->mRanking)
  81                         return " ORDER BY rank($field,to_tsquery('$searchon')) DESC";
  82                 else
  83                         return "";
  84         }
  85
  86
  87         function queryMain( $filteredTerm, $fulltext ) {
  88                 $match = $this->parseQuery( $filteredTerm, $fulltext );
  89                 $field = $this->getIndexField( $fulltext );
  90                 $cur = $this->db->tableName( 'cur' );
  91                 $searchindex = $this->db->tableName( 'searchindex' );
  92                 return 'SELECT cur_id, cur_namespace, cur_title, cur_text ' .
  93                         "FROM $cur,$searchindex " .
  94                         'WHERE cur_id=si_page AND ' .
  95                         " $field @@ to_tsquery ('$match') " ;
  96         }
  97
  98         function update( $id, $title, $text ) {
  99                 $dbw = wfGetDB( DB_MASTER );
 100                 $searchindex = $dbw->tableName( 'searchindex' );
 101                 $sql = "DELETE FROM $searchindex WHERE si_page={$id}";
 102                 $dbw->query( $sql, __METHOD__ );
 103                 $sql = "INSERT INTO $searchindex (si_page,si_title,si_text) ".
 104                         " VALUES ( $id, to_tsvector('".
 105                                 $dbw->strencode($title).
 106                                 "'),to_tsvector('".
 107                                 $dbw->strencode( $text)."')) ";
 108                 $dbw->query($sql, __METHOD__ );
 109         }
 110
 111         function updateTitle($id,$title) {
 112                 $dbw = wfGetDB(DB_MASTER);
 113                 $searchindex = $dbw->tableName( 'searchindex' );
 114                 $sql = "UPDATE $searchindex SET si_title=to_tsvector('" .
 115                                 $dbw->strencode( $title ) .
 116                                 "') WHERE si_page={$id}";
 117
 118                 $dbw->query( $sql, __METHOD__ );
 119         }
 120 }