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  * @ingroup Maintenance
  21  */
  22
  23 require_once( dirname( __FILE__ ) . '/Maintenance.php' );
  24
  25 class PopulateRevisionLength extends LoggedUpdateMaintenance {
  26         public function __construct() {
  27                 parent::__construct();
  28                 $this->mDescription = "Populates the rev_len field";
  29                 $this->setBatchSize( 200 );
  30         }
  31
  32         protected function getUpdateKey() {
  33                 return 'populate rev_len';
  34         }
  35
  36         protected function updateSkippedMessage() {
  37                 return 'rev_len column of revision table already populated.';
  38         }
  39
  40         public function doDBUpdates() {
  41                 $db = $this->getDB( DB_MASTER );
  42                 if ( !$db->tableExists( 'revision' ) ) {
  43                         $this->error( "revision table does not exist", true );
  44                 }
  45                 $this->output( "Populating rev_len column\n" );
  46
  47                 $start = $db->selectField( 'revision', 'MIN(rev_id)', false, __METHOD__ );
  48                 $end = $db->selectField( 'revision', 'MAX(rev_id)', false, __METHOD__ );
  49                 if ( !$start || !$end ) {
  50                         $this->output( "...revision table seems to be empty.\n" );
  51                         return true;
  52                 }
  53
  54                 # Do remaining chunks
  55                 $blockStart = intval( $start );
  56                 $blockEnd = intval( $start ) + $this->mBatchSize - 1;
  57                 $count = 0;
  58                 $missing = 0;
  59                 while ( $blockStart <= $end ) {
  60                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  61                         $res = $db->select( 'revision',
  62                                                 Revision::selectFields(),
  63                                                 array( "rev_id >= $blockStart",
  64                                                    "rev_id <= $blockEnd",
  65                                                    "rev_len IS NULL" ),
  66                                                 __METHOD__ );
  67                         # Go through and update rev_len from these rows.
  68                         foreach ( $res as $row ) {
  69                                 $rev = new Revision( $row );
  70                                 $text = $rev->getRawText();
  71                                 if ( !is_string( $text ) ) {
  72                                         # This should not happen, but sometimes does (bug 20757)
  73                                         $this->output( "Text of revision {$row->rev_id} unavailable!\n" );
  74                                         $missing++;
  75                                 }
  76                                 else {
  77                                         # Update the row...
  78                                         $db->update( 'revision',
  79                                                          array( 'rev_len' => strlen( $text ) ),
  80                                                          array( 'rev_id' => $row->rev_id ),
  81                                                          __METHOD__ );
  82                                         $count++;
  83                                 }
  84                         }
  85                         $blockStart += $this->mBatchSize;
  86                         $blockEnd += $this->mBatchSize;
  87                         wfWaitForSlaves();
  88                 }
  89
  90                 $this->output( "rev_len population complete ... {$count} rows changed ({$missing} missing)\n" );
  91                 return true;
  92         }
  93 }
  94
  95 $maintClass = "PopulateRevisionLength";
  96 require_once( RUN_MAINTENANCE_IF_MAIN );