maintenance/populateRevisionLength.php

   1 <?php
   2 /**
   3  * Populates the rev_len field for old revisions created before MW 1.10.
   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 /**
  27  * Maintenance script that populates the rev_len field for old revisions
  28  * created before MW 1.10.
  29  *
  30  * @ingroup Maintenance
  31  */
  32 class PopulateRevisionLength extends LoggedUpdateMaintenance {
  33         public function __construct() {
  34                 parent::__construct();
  35                 $this->mDescription = "Populates the rev_len field";
  36                 $this->setBatchSize( 200 );
  37         }
  38
  39         protected function getUpdateKey() {
  40                 return 'populate rev_len';
  41         }
  42
  43         protected function updateSkippedMessage() {
  44                 return 'rev_len column of revision table already populated.';
  45         }
  46
  47         public function doDBUpdates() {
  48                 $db = $this->getDB( DB_MASTER );
  49                 if ( !$db->tableExists( 'revision' ) ) {
  50                         $this->error( "revision table does not exist", true );
  51                 } else if ( !$db->fieldExists( 'revision', 'rev_sha1', __METHOD__ ) ) {
  52                         $this->output( "rev_sha1 column does not exist\n\n", true );
  53                         return false;
  54                 }
  55
  56                 $this->output( "Populating rev_len column\n" );
  57
  58                 $start = $db->selectField( 'revision', 'MIN(rev_id)', false, __METHOD__ );
  59                 $end = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
  60                 if ( !$start || !$end ) {
  61                         $this->output( "...revision table seems to be empty.\n" );
  62                         return true;
  63                 }
  64
  65                 # Do remaining chunks
  66                 $blockStart = intval( $start );
  67                 $blockEnd = intval( $start ) + $this->mBatchSize - 1;
  68                 $count = 0;
  69                 $missing = 0;
  70                 while ( $blockStart <= $end ) {
  71                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  72                         $res = $db->select( 'revision',
  73                                                 Revision::selectFields(),
  74                                                 array( "rev_id >= $blockStart",
  75                                                    "rev_id <= $blockEnd",
  76                                                    "rev_len IS NULL" ),
  77                                                 __METHOD__ );
  78                         # Go through and update rev_len from these rows.
  79                         foreach ( $res as $row ) {
  80                                 $rev = new Revision( $row );
  81                                 $content = $rev->getContent();
  82                                 if ( !$content ) {
  83                                         # This should not happen, but sometimes does (bug 20757)
  84                                         $this->output( "Content of revision {$row->rev_id} unavailable!\n" );
  85                                         $missing++;
  86                                 }
  87                                 else {
  88                                         # Update the row...
  89                                         $db->update( 'revision',
  90                                                          array( 'rev_len' => $content->getSize() ),
  91                                                          array( 'rev_id' => $row->rev_id ),
  92                                                          __METHOD__ );
  93                                         $count++;
  94                                 }
  95                         }
  96                         $blockStart += $this->mBatchSize;
  97                         $blockEnd += $this->mBatchSize;
  98                         wfWaitForSlaves();
  99                 }
 100
 101                 $this->output( "rev_len population complete ... {$count} rows changed ({$missing} missing)\n" );
 102                 return true;
 103         }
 104 }
 105
 106 $maintClass = "PopulateRevisionLength";
 107 require_once( RUN_MAINTENANCE_IF_MAIN );