maintenance/populateFilearchiveSha1.php

   1 <?php
   2 /**
   3  * Optional upgrade script to populate the fa_sha1 field
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Maintenance
  22  */
  23
  24 require_once __DIR__ . '/Maintenance.php';
  25
  26 use MediaWiki\MediaWikiServices;
  27
  28 /**
  29  * Maintenance script to populate the fa_sha1 field.
  30  *
  31  * @ingroup Maintenance
  32  * @since 1.21
  33  */
  34 class PopulateFilearchiveSha1 extends LoggedUpdateMaintenance {
  35         public function __construct() {
  36                 parent::__construct();
  37                 $this->addDescription( 'Populate the fa_sha1 field from fa_storage_key' );
  38         }
  39
  40         protected function getUpdateKey() {
  41                 return 'populate fa_sha1';
  42         }
  43
  44         protected function updateSkippedMessage() {
  45                 return 'fa_sha1 column of filearchive table already populated.';
  46         }
  47
  48         public function doDBUpdates() {
  49                 $startTime = microtime( true );
  50                 $dbw = $this->getDB( DB_MASTER );
  51                 $table = 'filearchive';
  52                 $conds = [ 'fa_sha1' => '', 'fa_storage_key IS NOT NULL' ];
  53
  54                 if ( !$dbw->fieldExists( $table, 'fa_sha1', __METHOD__ ) ) {
  55                         $this->output( "fa_sha1 column does not exist\n\n", true );
  56
  57                         return false;
  58                 }
  59
  60                 $this->output( "Populating fa_sha1 field from fa_storage_key\n" );
  61                 $endId = $dbw->selectField( $table, 'MAX(fa_id)', '', __METHOD__ );
  62
  63                 $batchSize = $this->getBatchSize();
  64                 $done = 0;
  65                 $lbFactory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
  66
  67                 do {
  68                         $res = $dbw->select(
  69                                 $table,
  70                                 [ 'fa_id', 'fa_storage_key' ],
  71                                 $conds,
  72                                 __METHOD__,
  73                                 [ 'LIMIT' => $batchSize ]
  74                         );
  75
  76                         $i = 0;
  77                         foreach ( $res as $row ) {
  78                                 if ( $row->fa_storage_key == '' ) {
  79                                         // Revision was missing pre-deletion
  80                                         continue;
  81                                 }
  82                                 $sha1 = LocalRepo::getHashFromKey( $row->fa_storage_key );
  83                                 $dbw->update( $table,
  84                                         [ 'fa_sha1' => $sha1 ],
  85                                         [ 'fa_id' => $row->fa_id ],
  86                                         __METHOD__
  87                                 );
  88                                 $lastId = $row->fa_id;
  89                                 $i++;
  90                         }
  91
  92                         $done += $i;
  93                         if ( $i !== $batchSize ) {
  94                                 break;
  95                         }
  96
  97                         // print status and let replica DBs catch up
  98                         $this->output( sprintf(
  99                                 "id %d done (up to %d), %5.3f%%  \r", $lastId, $endId, $lastId / $endId * 100 ) );
 100                         $lbFactory->waitForReplication();
 101                 } while ( true );
 102
 103                 $processingTime = microtime( true ) - $startTime;
 104                 $this->output( sprintf( "\nDone %d files in %.1f seconds\n", $done, $processingTime ) );
 105
 106                 // we only updated *some* files, don't log
 107                 return true;
 108         }
 109 }
 110
 111 $maintClass = PopulateFilearchiveSha1::class;
 112 require_once RUN_MAINTENANCE_IF_MAIN;