maintenance/populateRevisionLength.php

   1 <?php
   2 /**
   3  * Populates the rev_len and ar_len fields for old revisions created
   4  * before MW 1.10.
   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 populates the rev_len and ar_len fields
  29  * for old revisions created before MW 1.10.
  30  *
  31  * @ingroup Maintenance
  32  */
  33 class PopulateRevisionLength extends LoggedUpdateMaintenance {
  34         public function __construct() {
  35                 parent::__construct();
  36                 $this->mDescription = "Populates the rev_len and ar_len fields";
  37                 $this->setBatchSize( 200 );
  38         }
  39
  40         protected function getUpdateKey() {
  41                 return 'populate rev_len and ar_len';
  42         }
  43
  44         public function doDBUpdates() {
  45                 $db = $this->getDB( DB_MASTER );
  46                 if ( !$db->tableExists( 'revision' ) ) {
  47                         $this->error( "revision table does not exist", true );
  48                 } elseif ( !$db->tableExists( 'archive' ) ) {
  49                         $this->error( "archive table does not exist", true );
  50                 } elseif ( !$db->fieldExists( 'revision', 'rev_len', __METHOD__ ) ) {
  51                         $this->output( "rev_len column does not exist\n\n", true );
  52                         return false;
  53                 }
  54
  55                 $this->output( "Populating rev_len column\n" );
  56                 $rev = $this->doLenUpdates( 'revision', 'rev_id', 'rev' );
  57
  58                 $this->output( "Populating ar_len column\n" );
  59                 $ar = $this->doLenUpdates( 'archive', 'ar_id', 'ar' );
  60
  61                 $this->output( "rev_len and ar_len population complete [$rev revision rows, $ar archive rows].\n" );
  62                 return true;
  63         }
  64
  65         /**
  66          * @param $table
  67          * @param $idCol
  68          * @param $prefix
  69          * @return int
  70          */
  71         protected function doLenUpdates( $table, $idCol, $prefix ) {
  72                 $db = $this->getDB( DB_MASTER );
  73                 $start = $db->selectField( $table, "MIN($idCol)", false, __METHOD__ );
  74                 $end = $db->selectField( $table, "MAX($idCol)", false, __METHOD__ );
  75                 if ( !$start || !$end ) {
  76                         $this->output( "...$table table seems to be empty.\n" );
  77                         return 0;
  78                 }
  79
  80                 # Do remaining chunks
  81                 $blockStart = intval( $start );
  82                 $blockEnd = intval( $start ) + $this->mBatchSize - 1;
  83                 $count = 0;
  84                 $fields = Revision::selectFields();
  85                 while ( $blockStart <= $end ) {
  86                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  87                         $res = $db->select(
  88                                 $table,
  89                                 $fields,
  90                                 array(
  91                                         "$idCol >= $blockStart",
  92                                         "$idCol <= $blockEnd",
  93                                         "{$prefix}_len IS NULL"
  94                                 ),
  95                                 __METHOD__
  96                         );
  97
  98                         $db->begin( __METHOD__ );
  99                         # Go through and update rev_len from these rows.
 100                         foreach ( $res as $row ) {
 101                                 if ( $this->upgradeRow( $row, $table, $idCol, $prefix ) ) {
 102                                         $count++;
 103                                 }
 104                         }
 105                         $db->commit( __METHOD__ );
 106
 107                         $blockStart += $this->mBatchSize;
 108                         $blockEnd += $this->mBatchSize;
 109                         wfWaitForSlaves();
 110                 }
 111
 112                 return $count;
 113         }
 114
 115         /**
 116          * @param $row
 117          * @param $table
 118          * @param $idCol
 119          * @param $prefix
 120          * @return bool
 121          */
 122         protected function upgradeRow( $row, $table, $idCol, $prefix ) {
 123                 $db = $this->getDB( DB_MASTER );
 124
 125                 $rev = ( $table === 'archive' )
 126                         ? Revision::newFromArchiveRow( $row )
 127                         : new Revision( $row );
 128
 129                 $content = $rev->getContent();
 130                 if ( !$content ) {
 131                         # This should not happen, but sometimes does (bug 20757)
 132                         $id = $row->$idCol;
 133                         $this->output( "Content of $table $id unavailable!\n" );
 134                         return false;
 135                 }
 136
 137                 # Update the row...
 138                 $db->update( $table,
 139                         array( "{$prefix}_len" => $content->getSize() ),
 140                         array( $idCol => $row->$idCol ),
 141                         __METHOD__
 142                 );
 143
 144                 return true;
 145         }
 146 }
 147
 148 $maintClass = "PopulateRevisionLength";
 149 require_once RUN_MAINTENANCE_IF_MAIN;