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