maintenance/populateRevisionSha1.php

   1 <?php
   2 /**
   3  * Fills the rev_sha1 and ar_sha1 columns of revision
   4  * and archive tables for revisions created before MW 1.19.
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License along
  17  * with this program; if not, write to the Free Software Foundation, Inc.,
  18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19  * http://www.gnu.org/copyleft/gpl.html
  20  *
  21  * @file
  22  * @ingroup Maintenance
  23  */
  24
  25 require_once __DIR__ . '/Maintenance.php';
  26
  27 /**
  28  * Maintenance script that fills the rev_sha1 and ar_sha1 columns of revision
  29  * and archive tables for revisions created before MW 1.19.
  30  *
  31  * @ingroup Maintenance
  32  */
  33 class PopulateRevisionSha1 extends LoggedUpdateMaintenance {
  34         public function __construct() {
  35                 parent::__construct();
  36                 $this->addDescription( 'Populates the rev_sha1 and ar_sha1 fields' );
  37                 $this->setBatchSize( 200 );
  38         }
  39
  40         protected function getUpdateKey() {
  41                 return 'populate rev_sha1';
  42         }
  43
  44         protected function doDBUpdates() {
  45                 $db = $this->getDB( DB_PRIMARY );
  46
  47                 if ( !$db->tableExists( 'revision', __METHOD__ ) ) {
  48                         $this->fatalError( "revision table does not exist" );
  49                 } elseif ( !$db->tableExists( 'archive', __METHOD__ ) ) {
  50                         $this->fatalError( "archive table does not exist" );
  51                 } elseif ( !$db->fieldExists( 'revision', 'rev_sha1', __METHOD__ ) ) {
  52                         $this->output( "rev_sha1 column does not exist\n\n", true );
  53                         return false;
  54                 }
  55
  56                 $revStore = $this->getServiceContainer()->getRevisionStore();
  57
  58                 $this->output( "Populating rev_sha1 column\n" );
  59                 $rc = $this->doSha1Updates( $revStore, 'revision', 'rev_id',
  60                         $revStore->getQueryInfo(), 'rev'
  61                 );
  62
  63                 $this->output( "Populating ar_sha1 column\n" );
  64                 $ac = $this->doSha1Updates( $revStore, 'archive', 'ar_rev_id',
  65                         $revStore->getArchiveQueryInfo(), 'ar'
  66                 );
  67
  68                 $this->output( "rev_sha1 and ar_sha1 population complete "
  69                         . "[$rc revision rows, $ac archive rows].\n" );
  70
  71                 return true;
  72         }
  73
  74         /**
  75          * @param MediaWiki\Revision\RevisionStore $revStore
  76          * @param string $table
  77          * @param string $idCol
  78          * @param array $queryInfo
  79          * @param string $prefix
  80          * @return int Rows changed
  81          */
  82         protected function doSha1Updates( $revStore, $table, $idCol, $queryInfo, $prefix ) {
  83                 $db = $this->getDB( DB_PRIMARY );
  84                 $batchSize = $this->getBatchSize();
  85                 $start = $db->newSelectQueryBuilder()
  86                         ->select( "MIN($idCol)" )
  87                         ->from( $table )
  88                         ->caller( __METHOD__ )->fetchField();
  89                 $end = $db->newSelectQueryBuilder()
  90                         ->select( "MAX($idCol)" )
  91                         ->from( $table )
  92                         ->caller( __METHOD__ )->fetchField();
  93                 if ( !$start || !$end ) {
  94                         $this->output( "...$table table seems to be empty.\n" );
  95
  96                         return 0;
  97                 }
  98
  99                 $count = 0;
 100                 # Do remaining chunk
 101                 $end += $batchSize - 1;
 102                 $blockStart = $start;
 103                 $blockEnd = $start + $batchSize - 1;
 104                 while ( $blockEnd <= $end ) {
 105                         $this->output( "...doing $idCol from $blockStart to $blockEnd\n" );
 106
 107                         $cond = "$idCol BETWEEN " . (int)$blockStart . " AND " . (int)$blockEnd .
 108                                 " AND $idCol IS NOT NULL AND {$prefix}_sha1 = ''";
 109                         $res = $db->select(
 110                                 $queryInfo['tables'], $queryInfo['fields'], $cond, __METHOD__, [], $queryInfo['joins']
 111                         );
 112
 113                         $this->beginTransaction( $db, __METHOD__ );
 114                         foreach ( $res as $row ) {
 115                                 if ( $this->upgradeRow( $revStore, $row, $table, $idCol, $prefix ) ) {
 116                                         $count++;
 117                                 }
 118                         }
 119                         $this->commitTransaction( $db, __METHOD__ );
 120
 121                         $blockStart += $batchSize;
 122                         $blockEnd += $batchSize;
 123                 }
 124
 125                 return $count;
 126         }
 127
 128         /**
 129          * @param MediaWiki\Revision\RevisionStore $revStore
 130          * @param stdClass $row
 131          * @param string $table
 132          * @param string $idCol
 133          * @param string $prefix
 134          * @return bool
 135          */
 136         protected function upgradeRow( $revStore, $row, $table, $idCol, $prefix ) {
 137                 $db = $this->getDB( DB_PRIMARY );
 138
 139                 // Create a revision and use it to get the sha1 from the content table, if possible.
 140                 try {
 141                         $rev = ( $table === 'archive' )
 142                                 ? $revStore->newRevisionFromArchiveRow( $row )
 143                                 : $revStore->newRevisionFromRow( $row );
 144                         $sha1 = $rev->getSha1();
 145                 } catch ( Exception $e ) {
 146                         $this->output( "Data of revision with {$idCol}={$row->$idCol} unavailable!\n" );
 147                         return false; // T24624? T22757?
 148                 }
 149
 150                 $db->update( $table,
 151                         [ "{$prefix}_sha1" => $sha1 ],
 152                         [ $idCol => $row->$idCol ],
 153                         __METHOD__
 154                 );
 155
 156                 return true;
 157         }
 158 }
 159
 160 $maintClass = PopulateRevisionSha1::class;
 161 require_once RUN_MAINTENANCE_IF_MAIN;