includes/specials/SpecialListDuplicatedFiles.php

   1 <?php
   2 /**
   3  * Implements Special:ListDuplicatedFiles
   4  *
   5  * Copyright © 2013 Brian Wolff
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License along
  18  * with this program; if not, write to the Free Software Foundation, Inc.,
  19  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  20  * http://www.gnu.org/copyleft/gpl.html
  21  *
  22  * @file
  23  * @ingroup SpecialPage
  24  * @author Brian Wolff
  25  */
  26
  27 use Wikimedia\Rdbms\ResultWrapper;
  28 use Wikimedia\Rdbms\IDatabase;
  29
  30 /**
  31  * Special:ListDuplicatedFiles Lists all files where the current version is
  32  *   a duplicate of the current version of some other file.
  33  * @ingroup SpecialPage
  34  */
  35 class ListDuplicatedFilesPage extends QueryPage {
  36         function __construct( $name = 'ListDuplicatedFiles' ) {
  37                 parent::__construct( $name );
  38         }
  39
  40         public function isExpensive() {
  41                 return true;
  42         }
  43
  44         function isSyndicated() {
  45                 return false;
  46         }
  47
  48         /**
  49          * Get all the duplicates by grouping on sha1s.
  50          *
  51          * A cheaper (but less useful) version of this
  52          * query would be to not care how many duplicates a
  53          * particular file has, and do a self-join on image table.
  54          * However this version should be no more expensive then
  55          * Special:MostLinked, which seems to get handled fine
  56          * with however we are doing cached special pages.
  57          * @return array
  58          */
  59         public function getQueryInfo() {
  60                 return [
  61                         'tables' => [ 'image' ],
  62                         'fields' => [
  63                                 'namespace' => NS_FILE,
  64                                 'title' => 'MIN(img_name)',
  65                                 'value' => 'count(*)'
  66                         ],
  67                         'options' => [
  68                                 'GROUP BY' => 'img_sha1',
  69                                 'HAVING' => 'count(*) > 1',
  70                         ],
  71                 ];
  72         }
  73
  74         /**
  75          * Pre-fill the link cache
  76          *
  77          * @param IDatabase $db
  78          * @param ResultWrapper $res
  79          */
  80         function preprocessResults( $db, $res ) {
  81                 $this->executeLBFromResultWrapper( $res );
  82         }
  83
  84         /**
  85          * @param Skin $skin
  86          * @param object $result Result row
  87          * @return string
  88          */
  89         function formatResult( $skin, $result ) {
  90                 // Future version might include a list of the first 5 duplicates
  91                 // perhaps separated by an "↔".
  92                 $image1 = Title::makeTitle( $result->namespace, $result->title );
  93                 $dupeSearch = SpecialPage::getTitleFor( 'FileDuplicateSearch', $image1->getDBkey() );
  94
  95                 $msg = $this->msg( 'listduplicatedfiles-entry' )
  96                         ->params( $image1->getText() )
  97                         ->numParams( $result->value - 1 )
  98                         ->params( $dupeSearch->getPrefixedDBkey() );
  99
 100                 return $msg->parse();
 101         }
 102
 103         protected function getGroupName() {
 104                 return 'media';
 105         }
 106 }