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 Maintenance {
  26         public function __construct() {
  27                 parent::__construct();
  28                 $this->mDescription = "Populates rev_len";
  29                 $this->setBatchSize( 200 );
  30         }
  31
  32         public function execute() {
  33                 $db = wfGetDB( DB_MASTER );
  34                 if ( !$db->tableExists( 'revision' ) ) {
  35                         $this->error( "revision table does not exist", true );
  36                 }
  37                 $this->output( "Populating rev_len column\n" );
  38                 $start = $db->selectField( 'revision', 'MIN(rev_id)', false, __FUNCTION__ );
  39                 $end = $db->selectField( 'revision', 'MAX(rev_id)', false, __FUNCTION__ );
  40                 if( is_null( $start ) || is_null( $end ) ){
  41                         $this->output( "...revision table seems to be empty.\n" );
  42                         $db->insert( 'updatelog',
  43                                 array( 'ul_key' => 'populate rev_len' ),
  44                                 __METHOD__,
  45                                 'IGNORE' );
  46                         return;
  47                 }
  48                 # Do remaining chunks
  49                 $blockStart = intval( $start );
  50                 $blockEnd = intval( $start ) + $this->mBatchSize - 1;
  51                 $count = 0;
  52                 while( $blockStart <= $end ) {
  53                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  54                         $res = $db->select( 'revision',
  55                                             Revision::selectFields(),
  56                                             array( "rev_id >= $blockStart",
  57                                                    "rev_id <= $blockEnd",
  58                                                    "rev_len IS NULL" ),
  59                                             __METHOD__ );
  60                         # Go through and update rev_len from these rows.
  61                         foreach( $res as $row ) {
  62                                 $rev = new Revision( $row );
  63                                 $text = $rev->getRawText();
  64                                 # Update the row...
  65                                 $db->update( 'revision',
  66                                              array( 'rev_len' => strlen( $text ) ),
  67                                              array( 'rev_id' => $row->rev_id ),
  68                                              __METHOD__ );
  69                                 $count++;
  70                         }
  71                         $blockStart += $this->mBatchSize;
  72                         $blockEnd += $this->mBatchSize;
  73                         wfWaitForSlaves( 5 );
  74                 }
  75                 $logged = $db->insert( 'updatelog',
  76                         array( 'ul_key' => 'populate rev_len' ),
  77                         __METHOD__,
  78                         'IGNORE' );
  79                 if( $logged ) {
  80                         $this->output( "rev_len population complete ... {$count} rows changed\n" );
  81                         return true;
  82                 } else {
  83                         $this->output( "Could not insert rev_len population row.\n" );
  84                         return false;
  85                 }
  86         }
  87 }
  88
  89 $maintClass = "PopulateRevisionLength";
  90 require_once( DO_MAINTENANCE );