maintenance/findMissingFiles.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  *
  18  * @file
  19  * @author Aaron Schulz
  20  */
  21
  22 require_once __DIR__ . '/Maintenance.php';
  23
  24 class FindMissingFiles extends Maintenance {
  25         function __construct() {
  26                 parent::__construct();
  27
  28                 $this->mDescription = 'Find registered files with no corresponding file.';
  29                 $this->addOption( 'start', 'Starting file name', false, true );
  30                 $this->addOption( 'mtimeafter', 'Only include files changed since this time', false, true );
  31                 $this->addOption( 'mtimebefore', 'Only includes files changed before this time', false, true );
  32                 $this->setBatchSize( 300 );
  33         }
  34
  35         function execute() {
  36                 $lastName = $this->getOption( 'start', '' );
  37
  38                 $repo = RepoGroup::singleton()->getLocalRepo();
  39                 $dbr = $repo->getSlaveDB();
  40                 $be = $repo->getBackend();
  41
  42                 $mtime1 = $dbr->timestampOrNull( $this->getOption( 'mtimeafter', null ) );
  43                 $mtime2 = $dbr->timestampOrNull( $this->getOption( 'mtimebefore', null ) );
  44
  45                 $joinTables = array( 'image' );
  46                 $joinConds = array( 'image' => array( 'INNER JOIN', 'img_name = page_title' ) );
  47                 if ( $mtime1 || $mtime2 ) {
  48                         $joinTables[] = 'logging';
  49                         $on = array( 'log_page = page_id', 'log_type' => array( 'upload', 'move', 'delete' ) );
  50                         if ( $mtime1 ) {
  51                                 $on[] = "log_timestamp > {$dbr->addQuotes($mtime1)}";
  52                         }
  53                         if ( $mtime2 ) {
  54                                 $on[] = "log_timestamp < {$dbr->addQuotes($mtime2)}";
  55                         }
  56                         $joinConds['logging'] = array( 'INNER JOIN', $on );
  57                 }
  58
  59                 do {
  60                         $res = $dbr->select(
  61                                 array_merge( array( 'page' ), $joinTables ),
  62                                 array( 'name' => 'img_name' ),
  63                                 array( 'page_namespace' => NS_FILE,
  64                                         "page_title >= " . $dbr->addQuotes( $lastName ) ),
  65                                 __METHOD__,
  66                                 // DISTINCT causes a pointless filesort
  67                                 array( 'ORDER BY' => 'name', 'GROUP BY' => 'name',
  68                                         'LIMIT' => $this->mBatchSize ),
  69                                 $joinConds
  70                         );
  71
  72                         // Check if any of these files are missing...
  73                         $pathsByName = array();
  74                         foreach ( $res as $row ) {
  75                                 $file = $repo->newFile( $row->name );
  76                                 $pathsByName[$row->name] = $file->getPath();
  77                                 $lastName = $row->name;
  78                         }
  79                         $be->preloadFileStat( array( 'srcs' => $pathsByName ) );
  80                         foreach ( $pathsByName as $path ) {
  81                                 if ( $be->fileExists( array( 'src' => $path ) ) === false ) {
  82                                         $this->output( "$path\n" );
  83                                 }
  84                         }
  85
  86                         // Find all missing old versions of any of the files in this batch...
  87                         if ( count( $pathsByName ) ) {
  88                                 $ores = $dbr->select( 'oldimage',
  89                                         array( 'oi_name', 'oi_archive_name' ),
  90                                         array( 'oi_name' => array_keys( $pathsByName ) ),
  91                                         __METHOD__
  92                                 );
  93
  94                                 $checkPaths = array();
  95                                 foreach ( $ores as $row ) {
  96                                         if ( !strlen( $row->oi_archive_name ) ) {
  97                                                 continue; // broken row
  98                                         }
  99                                         $file = $repo->newFromArchiveName( $row->oi_name, $row->oi_archive_name );
 100                                         $checkPaths[] = $file->getPath();
 101                                 }
 102
 103                                 foreach ( array_chunk( $checkPaths, $this->mBatchSize ) as $paths ) {
 104                                         $be->preloadFileStat( array( 'srcs' => $paths ) );
 105                                         foreach ( $paths as $path ) {
 106                                                 if ( $be->fileExists( array( 'src' => $path ) ) === false ) {
 107                                                         $this->output( "$path\n" );
 108                                                 }
 109                                         }
 110                                 }
 111                         }
 112                 } while ( $res->numRows() >= $this->mBatchSize );
 113         }
 114 }
 115
 116 $maintClass = 'FindMissingFiles';
 117 require_once RUN_MAINTENANCE_IF_MAIN;