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
  29 /**
  30  * Special:ListDuplicatedFiles Lists all files where the current version is
  31  *   a duplicate of the current version of some other file.
  32  * @ingroup SpecialPage
  33  */
  34 class ListDuplicatedFilesPage extends QueryPage {
  35         function __construct( $name = 'ListDuplicatedFiles' ) {
  36                 parent::__construct( $name );
  37         }
  38
  39         public function isExpensive() {
  40                 return true;
  41         }
  42
  43         function isSyndicated() {
  44                 return false;
  45         }
  46
  47         /**
  48          * Get all the duplicates by grouping on sha1s.
  49          *
  50          * A cheaper (but less useful) version of this
  51          * query would be to not care how many duplicates a
  52          * particular file has, and do a self-join on image table.
  53          * However this version should be no more expensive then
  54          * Special:MostLinked, which seems to get handled fine
  55          * with however we are doing cached special pages.
  56          * @return array
  57          */
  58         public function getQueryInfo() {
  59                 return [
  60                         'tables' => [ 'image' ],
  61                         'fields' => [
  62                                 'namespace' => NS_FILE,
  63                                 'title' => 'MIN(img_name)',
  64                                 'value' => 'count(*)'
  65                         ],
  66                         'options' => [
  67                                 'GROUP BY' => 'img_sha1',
  68                                 'HAVING' => 'count(*) > 1',
  69                         ],
  70                 ];
  71         }
  72
  73         /**
  74          * Pre-fill the link cache
  75          *
  76          * @param IDatabase $db
  77          * @param ResultWrapper $res
  78          */
  79         function preprocessResults( $db, $res ) {
  80                 $this->executeLBFromResultWrapper( $res );
  81         }
  82
  83         /**
  84          * @param Skin $skin
  85          * @param object $result Result row
  86          * @return string
  87          */
  88         function formatResult( $skin, $result ) {
  89                 // Future version might include a list of the first 5 duplicates
  90                 // perhaps separated by an "↔".
  91                 $image1 = Title::makeTitle( $result->namespace, $result->title );
  92                 $dupeSearch = SpecialPage::getTitleFor( 'FileDuplicateSearch', $image1->getDBkey() );
  93
  94                 $msg = $this->msg( 'listduplicatedfiles-entry' )
  95                         ->params( $image1->getText() )
  96                         ->numParams( $result->value - 1 )
  97                         ->params( $dupeSearch->getPrefixedDBkey() );
  98
  99                 return $msg->parse();
 100         }
 101
 102         protected function getGroupName() {
 103                 return 'media';
 104         }
 105 }