includes/search/SearchExactMatchRescorer.php

   1 <?php
   2 /**
   3  * Rescores results from a prefix search/opensearch to make sure the
   4  * exact match is the first result.
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License along
  17  * with this program; if not, write to the Free Software Foundation, Inc.,
  18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19  * http://www.gnu.org/copyleft/gpl.html
  20  *
  21  * @file
  22  */
  23
  24 /**
  25  * An utility class to rescore search results by looking for an exact match
  26  * in the db and add the page found to the first position.
  27  *
  28  * NOTE: extracted from TitlePrefixSearch
  29  * @ingroup Search
  30  */
  31 class SearchExactMatchRescorer {
  32         /**
  33          * Default search backend does proper prefix searching, but custom backends
  34          * may sort based on other algorithms that may cause the exact title match
  35          * to not be in the results or be lower down the list.
  36          * @param string $search the query
  37          * @param int[] $namespaces the namespaces
  38          * @param int $limit the max number of results to return
  39          * @param string[] $srchres results
  40          * @return string[] munged results
  41          */
  42         public function rescore( $search, $namespaces, $srchres, $limit ) {
  43                 // Pick namespace (based on PrefixSearch::defaultSearchBackend)
  44                 $ns = in_array( NS_MAIN, $namespaces ) ? NS_MAIN : $namespaces[0];
  45                 $t = Title::newFromText( $search, $ns );
  46                 if ( !$t || !$t->exists() ) {
  47                         // No exact match so just return the search results
  48                         return $srchres;
  49                 }
  50                 $string = $t->getPrefixedText();
  51                 $key = array_search( $string, $srchres );
  52                 if ( $key !== false ) {
  53                         // Exact match was in the results so just move it to the front
  54                         return $this->pullFront( $key, $srchres );
  55                 }
  56                 // Exact match not in the search results so check for some redirect handling cases
  57                 if ( $t->isRedirect() ) {
  58                         $target = $this->getRedirectTarget( $t );
  59                         $key = array_search( $target, $srchres );
  60                         if ( $key !== false ) {
  61                                 // Exact match is a redirect to one of the returned matches so pull the
  62                                 // returned match to the front.  This might look odd but the alternative
  63                                 // is to put the redirect in front and drop the match.  The name of the
  64                                 // found match is often more descriptive/better formed than the name of
  65                                 // the redirect AND by definition they share a prefix.  Hopefully this
  66                                 // choice is less confusing and more helpful.  But it might not be.  But
  67                                 // it is the choice we're going with for now.
  68                                 return $this->pullFront( $key, $srchres );
  69                         }
  70                         $redirectTargetsToRedirect = $this->redirectTargetsToRedirect( $srchres );
  71                         if ( isset( $redirectTargetsToRedirect[$target] ) ) {
  72                                 // The exact match and something in the results list are both redirects
  73                                 // to the same thing!  In this case we'll pull the returned match to the
  74                                 // top following the same logic above.  Again, it might not be a perfect
  75                                 // choice but it'll do.
  76                                 return $this->pullFront( $redirectTargetsToRedirect[$target], $srchres );
  77                         }
  78                 } else {
  79                         $redirectTargetsToRedirect = $this->redirectTargetsToRedirect( $srchres );
  80                         if ( isset( $redirectTargetsToRedirect[$string] ) ) {
  81                                 // The exact match is the target of a redirect already in the results list so remove
  82                                 // the redirect from the results list and push the exact match to the front
  83                                 array_splice( $srchres, $redirectTargetsToRedirect[$string], 1 );
  84                                 array_unshift( $srchres, $string );
  85                                 return $srchres;
  86                         }
  87                 }
  88
  89                 // Exact match is totally unique from the other results so just add it to the front
  90                 array_unshift( $srchres, $string );
  91                 // And roll one off the end if the results are too long
  92                 if ( count( $srchres ) > $limit ) {
  93                         array_pop( $srchres );
  94                 }
  95                 return $srchres;
  96         }
  97
  98         /**
  99          * @param string[] $titles as strings
 100          * @return array redirect target prefixedText to index of title in titles
 101          *   that is a redirect to it.
 102          */
 103         private function redirectTargetsToRedirect( $titles ) {
 104                 $result = array();
 105                 foreach ( $titles as $key => $titleText ) {
 106                         $title = Title::newFromText( $titleText );
 107                         if ( !$title || !$title->isRedirect() ) {
 108                                 continue;
 109                         }
 110                         $target = $this->getRedirectTarget( $title );
 111                         if ( !$target ) {
 112                                 continue;
 113                         }
 114                         $result[$target] = $key;
 115                 }
 116                 return $result;
 117         }
 118
 119         /**
 120          * Returns an array where the element of $array at index $key becomes
 121          * the first element.
 122          * @param int $key key to pull to the front
 123          * @return array $array with the item at $key pulled to the front
 124          */
 125         private function pullFront( $key, $array ) {
 126                 $cut = array_splice( $array, $key, 1 );
 127                 array_unshift( $array, $cut[0] );
 128                 return $array;
 129         }
 130
 131         /**
 132          * Get a redirect's destination from a title
 133          * @param Title $title A title to redirect. It may not redirect or even exist
 134          * @return null|string If title exists and redirects, get the destination's prefixed name
 135          */
 136         private function getRedirectTarget( $title ) {
 137                 $page = WikiPage::factory( $title );
 138                 if ( !$page->exists() ) {
 139                         return null;
 140                 }
 141                 $redir = $page->getRedirectTarget();
 142                 return $redir ? $redir->getPrefixedText() : null;
 143         }
 144 }