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 use MediaWiki\MediaWikiServices;
  28
  29 /**
  30  * Maintenance script that fills the rev_sha1 and ar_sha1 columns of revision
  31  * and archive tables for revisions created before MW 1.19.
  32  *
  33  * @ingroup Maintenance
  34  */
  35 class PopulateRevisionSha1 extends LoggedUpdateMaintenance {
  36         public function __construct() {
  37                 parent::__construct();
  38                 $this->addDescription( 'Populates the rev_sha1 and ar_sha1 fields' );
  39                 $this->setBatchSize( 200 );
  40         }
  41
  42         protected function getUpdateKey() {
  43                 return 'populate rev_sha1';
  44         }
  45
  46         protected function doDBUpdates() {
  47                 $db = $this->getDB( DB_PRIMARY );
  48
  49                 if ( !$db->tableExists( 'revision', __METHOD__ ) ) {
  50                         $this->fatalError( "revision table does not exist" );
  51                 } elseif ( !$db->tableExists( 'archive', __METHOD__ ) ) {
  52                         $this->fatalError( "archive table does not exist" );
  53                 } elseif ( !$db->fieldExists( 'revision', 'rev_sha1', __METHOD__ ) ) {
  54                         $this->output( "rev_sha1 column does not exist\n\n", true );
  55                         return false;
  56                 }
  57
  58                 $revStore = MediaWikiServices::getInstance()->getRevisionStore();
  59
  60                 $this->output( "Populating rev_sha1 column\n" );
  61                 $rc = $this->doSha1Updates( $revStore, 'revision', 'rev_id',
  62                         $revStore->getQueryInfo(), 'rev'
  63                 );
  64
  65                 $this->output( "Populating ar_sha1 column\n" );
  66                 $ac = $this->doSha1Updates( $revStore, 'archive', 'ar_rev_id',
  67                         $revStore->getArchiveQueryInfo(), 'ar'
  68                 );
  69
  70                 $this->output( "rev_sha1 and ar_sha1 population complete "
  71                         . "[$rc revision rows, $ac archive rows].\n" );
  72
  73                 return true;
  74         }
  75
  76         /**
  77          * @param MediaWiki\Revision\RevisionStore $revStore
  78          * @param string $table
  79          * @param string $idCol
  80          * @param array $queryInfo
  81          * @param string $prefix
  82          * @return int Rows changed
  83          */
  84         protected function doSha1Updates( $revStore, $table, $idCol, $queryInfo, $prefix ) {
  85                 $db = $this->getDB( DB_PRIMARY );
  86                 $batchSize = $this->getBatchSize();
  87                 $start = $db->selectField( $table, "MIN($idCol)", '', __METHOD__ );
  88                 $end = $db->selectField( $table, "MAX($idCol)", '', __METHOD__ );
  89                 if ( !$start || !$end ) {
  90                         $this->output( "...$table table seems to be empty.\n" );
  91
  92                         return 0;
  93                 }
  94
  95                 $count = 0;
  96                 # Do remaining chunk
  97                 $end += $batchSize - 1;
  98                 $blockStart = $start;
  99                 $blockEnd = $start + $batchSize - 1;
 100                 while ( $blockEnd <= $end ) {
 101                         $this->output( "...doing $idCol from $blockStart to $blockEnd\n" );
 102
 103                         $cond = "$idCol BETWEEN " . (int)$blockStart . " AND " . (int)$blockEnd .
 104                                 " AND $idCol IS NOT NULL AND {$prefix}_sha1 = ''";
 105                         $res = $db->select(
 106                                 $queryInfo['tables'], $queryInfo['fields'], $cond, __METHOD__, [], $queryInfo['joins']
 107                         );
 108
 109                         $this->beginTransaction( $db, __METHOD__ );
 110                         foreach ( $res as $row ) {
 111                                 if ( $this->upgradeRow( $revStore, $row, $table, $idCol, $prefix ) ) {
 112                                         $count++;
 113                                 }
 114                         }
 115                         $this->commitTransaction( $db, __METHOD__ );
 116
 117                         $blockStart += $batchSize;
 118                         $blockEnd += $batchSize;
 119                 }
 120
 121                 return $count;
 122         }
 123
 124         /**
 125          * @param MediaWiki\Revision\RevisionStore $revStore
 126          * @param stdClass $row
 127          * @param string $table
 128          * @param string $idCol
 129          * @param string $prefix
 130          * @return bool
 131          */
 132         protected function upgradeRow( $revStore, $row, $table, $idCol, $prefix ) {
 133                 $db = $this->getDB( DB_PRIMARY );
 134
 135                 // Create a revision and use it to get the sha1 from the content table, if possible.
 136                 try {
 137                         $rev = ( $table === 'archive' )
 138                                 ? $revStore->newRevisionFromArchiveRow( $row )
 139                                 : $revStore->newRevisionFromRow( $row );
 140                         $sha1 = $rev->getSha1();
 141                 } catch ( Exception $e ) {
 142                         $this->output( "Data of revision with {$idCol}={$row->$idCol} unavailable!\n" );
 143                         return false; // T24624? T22757?
 144                 }
 145
 146                 $db->update( $table,
 147                         [ "{$prefix}_sha1" => $sha1 ],
 148                         [ $idCol => $row->$idCol ],
 149                         __METHOD__
 150                 );
 151
 152                 return true;
 153         }
 154 }
 155
 156 $maintClass = PopulateRevisionSha1::class;
 157 require_once RUN_MAINTENANCE_IF_MAIN;