maintenance/refreshFileHeaders.php

   1 <?php
   2 /**
   3  * Refresh file headers from metadata.
   4  *
   5  * Usage: php refreshFileHeaders.php
   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 Maintenance
  24  */
  25
  26 use MediaWiki\FileRepo\File\FileSelectQueryBuilder;
  27 use MediaWiki\Maintenance\Maintenance;
  28 use Wikimedia\Rdbms\SelectQueryBuilder;
  29
  30 // @codeCoverageIgnoreStart
  31 require_once __DIR__ . '/Maintenance.php';
  32 // @codeCoverageIgnoreEnd
  33
  34 /**
  35  * Maintenance script to refresh file headers from metadata
  36  *
  37  * @ingroup Maintenance
  38  */
  39 class RefreshFileHeaders extends Maintenance {
  40         public function __construct() {
  41                 parent::__construct();
  42                 $this->addDescription( 'Script to update file HTTP headers' );
  43                 $this->addOption( 'verbose', 'Output information about each file.', false, false, 'v' );
  44                 $this->addOption( 'start', 'Name of file to start with', false, true );
  45                 $this->addOption( 'end', 'Name of file to end with', false, true );
  46                 $this->addOption( 'media_type', 'Media type to filter for', false, true );
  47                 $this->addOption( 'major_mime', 'Major mime type to filter for', false, true );
  48                 $this->addOption( 'minor_mime', 'Minor mime type to filter for', false, true );
  49                 $this->addOption(
  50                         'refreshContentType',
  51                         'Set true to refresh file content type from mime data in db',
  52                         false,
  53                         false
  54                 );
  55                 $this->setBatchSize( 200 );
  56         }
  57
  58         public function execute() {
  59                 $repo = $this->getServiceContainer()->getRepoGroup()->getLocalRepo();
  60                 $start = str_replace( ' ', '_', $this->getOption( 'start', '' ) ); // page on img_name
  61                 $end = str_replace( ' ', '_', $this->getOption( 'end', '' ) ); // page on img_name
  62                 // filter by img_media_type
  63                 $media_type = str_replace( ' ', '_', $this->getOption( 'media_type', '' ) );
  64                 // filter by img_major_mime
  65                 $major_mime = str_replace( ' ', '_', $this->getOption( 'major_mime', '' ) );
  66                 // filter by img_minor_mime
  67                 $minor_mime = str_replace( ' ', '_', $this->getOption( 'minor_mime', '' ) );
  68
  69                 $count = 0;
  70                 $dbr = $this->getReplicaDB();
  71
  72                 do {
  73                         $queryBuilder = FileSelectQueryBuilder::newForFile( $dbr );
  74
  75                         $queryBuilder->where( $dbr->expr( 'img_name', '>', $start ) );
  76                         if ( strlen( $end ) ) {
  77                                 $queryBuilder->andWhere( $dbr->expr( 'img_name', '<=', $end ) );
  78                         }
  79
  80                         if ( strlen( $media_type ) ) {
  81                                 $queryBuilder->andWhere( [ 'img_media_type' => $media_type ] );
  82                         }
  83
  84                         if ( strlen( $major_mime ) ) {
  85                                 $queryBuilder->andWhere( [ 'img_major_mime' => $major_mime ] );
  86                         }
  87
  88                         if ( strlen( $minor_mime ) ) {
  89                                 $queryBuilder->andWhere( [ 'img_minor_mime' => $minor_mime ] );
  90                         }
  91
  92                         $res = $queryBuilder
  93                                 ->orderBy( 'img_name', SelectQueryBuilder::SORT_ASC )
  94                                 ->limit( $this->getBatchSize() )
  95                                 ->caller( __METHOD__ )->fetchResultSet();
  96
  97                         if ( $res->numRows() > 0 ) {
  98                                 $row1 = $res->current();
  99                                 $this->output( "Processing next {$res->numRows()} row(s) starting with {$row1->img_name}.\n" );
 100                                 $res->rewind();
 101                         }
 102
 103                         $backendOperations = [];
 104
 105                         foreach ( $res as $row ) {
 106                                 $file = $repo->newFileFromRow( $row );
 107                                 $headers = $file->getContentHeaders();
 108                                 if ( $this->getOption( 'refreshContentType', false ) ) {
 109                                         $headers['Content-Type'] = $row->img_major_mime . '/' . $row->img_minor_mime;
 110                                 }
 111
 112                                 if ( count( $headers ) ) {
 113                                         $backendOperations[] = [
 114                                                 'op' => 'describe', 'src' => $file->getPath(), 'headers' => $headers
 115                                         ];
 116                                 }
 117
 118                                 // Do all of the older file versions...
 119                                 foreach ( $file->getHistory() as $oldFile ) {
 120                                         $headers = $oldFile->getContentHeaders();
 121                                         if ( count( $headers ) ) {
 122                                                 $backendOperations[] = [
 123                                                         'op' => 'describe', 'src' => $oldFile->getPath(), 'headers' => $headers
 124                                                 ];
 125                                         }
 126                                 }
 127
 128                                 if ( $this->hasOption( 'verbose' ) ) {
 129                                         $this->output( "Queued headers update for file '{$row->img_name}'.\n" );
 130                                 }
 131
 132                                 $start = $row->img_name; // advance
 133                         }
 134
 135                         $backendOperationsCount = count( $backendOperations );
 136                         $count += $backendOperationsCount;
 137
 138                         $this->output( "Updating headers for {$backendOperationsCount} file(s).\n" );
 139                         $this->updateFileHeaders( $repo, $backendOperations );
 140                 } while ( $res->numRows() === $this->getBatchSize() );
 141
 142                 $this->output( "Done. Updated headers for $count file(s).\n" );
 143         }
 144
 145         /**
 146          * @param LocalRepo $repo
 147          * @param array $backendOperations
 148          */
 149         protected function updateFileHeaders( $repo, $backendOperations ) {
 150                 $status = $repo->getBackend()->doQuickOperations( $backendOperations );
 151
 152                 if ( !$status->isGood() ) {
 153                         $this->error( $status );
 154                 }
 155         }
 156 }
 157
 158 // @codeCoverageIgnoreStart
 159 $maintClass = RefreshFileHeaders::class;
 160 require_once RUN_MAINTENANCE_IF_MAIN;
 161 // @codeCoverageIgnoreEnd