maintenance/populateParentId.php

   1 <?php
   2 /**
   3  * Makes the required database updates for rev_parent_id
   4  * to be of any use. It can be used for some simple tracking
   5  * and to find new page edits by users.
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License along
  18  * with this program; if not, write to the Free Software Foundation, Inc.,
  19  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  20  * http://www.gnu.org/copyleft/gpl.html
  21  *
  22  * @file
  23  * @ingroup Maintenance
  24  */
  25
  26 require_once( __DIR__ . '/Maintenance.php' );
  27
  28 /**
  29  * Maintenance script that makes the required database updates for rev_parent_id
  30  * to be of any use.
  31  *
  32  * @ingroup Maintenance
  33  */
  34 class PopulateParentId extends LoggedUpdateMaintenance {
  35         public function __construct() {
  36                 parent::__construct();
  37                 $this->mDescription = "Populates rev_parent_id";
  38         }
  39
  40         protected function getUpdateKey() {
  41                 return 'populate rev_parent_id';
  42         }
  43
  44         protected function updateSkippedMessage() {
  45                 return 'rev_parent_id column of revision table already populated.';
  46         }
  47
  48         protected function doDBUpdates() {
  49                 $db = wfGetDB( DB_MASTER );
  50                 if ( !$db->tableExists( 'revision' ) ) {
  51                         $this->error( "revision table does not exist" );
  52                         return false;
  53                 }
  54                 $this->output( "Populating rev_parent_id column\n" );
  55                 $start = $db->selectField( 'revision', 'MIN(rev_id)', false, __FUNCTION__ );
  56                 $end = $db->selectField( 'revision', 'MAX(rev_id)', false, __FUNCTION__ );
  57                 if ( is_null( $start ) || is_null( $end ) ) {
  58                         $this->output( "...revision table seems to be empty, nothing to do.\n" );
  59                         return true;
  60                 }
  61                 # Do remaining chunk
  62                 $blockStart = intval( $start );
  63                 $blockEnd = intval( $start ) + $this->mBatchSize - 1;
  64                 $count = 0;
  65                 $changed = 0;
  66                 while ( $blockStart <= $end ) {
  67                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  68                         $cond = "rev_id BETWEEN $blockStart AND $blockEnd";
  69                         $res = $db->select( 'revision',
  70                                 array( 'rev_id', 'rev_page', 'rev_timestamp', 'rev_parent_id' ),
  71                                 array( $cond, 'rev_parent_id' => null ), __METHOD__ );
  72                         # Go through and update rev_parent_id from these rows.
  73                         # Assume that the previous revision of the title was
  74                         # the original previous revision of the title when the
  75                         # edit was made...
  76                         foreach ( $res as $row ) {
  77                                 # First, check rows with the same timestamp other than this one
  78                                 # with a smaller rev ID. The highest ID "wins". This avoids loops
  79                                 # as timestamp can only decrease and never loops with IDs (from parent to parent)
  80                                 $previousID = $db->selectField( 'revision', 'rev_id',
  81                                         array( 'rev_page' => $row->rev_page, 'rev_timestamp' => $row->rev_timestamp,
  82                                                 "rev_id < " . intval( $row->rev_id ) ),
  83                                         __METHOD__,
  84                                         array( 'ORDER BY' => 'rev_id DESC' ) );
  85                                 # If there are none, check the the highest ID with a lower timestamp
  86                                 if ( !$previousID ) {
  87                                         # Get the highest older timestamp
  88                                         $lastTimestamp = $db->selectField( 'revision', 'rev_timestamp',
  89                                                 array( 'rev_page' => $row->rev_page, "rev_timestamp < " . $db->addQuotes( $row->rev_timestamp ) ),
  90                                                 __METHOD__,
  91                                                 array( 'ORDER BY' => 'rev_timestamp DESC' ) );
  92                                         # If there is one, let the highest rev ID win
  93                                         if ( $lastTimestamp ) {
  94                                                 $previousID = $db->selectField( 'revision', 'rev_id',
  95                                                         array( 'rev_page' => $row->rev_page, 'rev_timestamp' => $lastTimestamp ),
  96                                                         __METHOD__,
  97                                                         array( 'ORDER BY' => 'rev_id DESC' ) );
  98                                         }
  99                                 }
 100                                 $previousID = intval( $previousID );
 101                                 if ( $previousID != $row->rev_parent_id ) {
 102                                         $changed++;
 103                                 }
 104                                 # Update the row...
 105                                 $db->update( 'revision',
 106                                         array( 'rev_parent_id' => $previousID ),
 107                                         array( 'rev_id' => $row->rev_id ),
 108                                         __METHOD__ );
 109                                 $count++;
 110                         }
 111                         $blockStart += $this->mBatchSize;
 112                         $blockEnd += $this->mBatchSize;
 113                         wfWaitForSlaves();
 114                 }
 115                 $this->output( "rev_parent_id population complete ... {$count} rows [{$changed} changed]\n" );
 116                 return true;
 117         }
 118 }
 119
 120 $maintClass = "PopulateParentId";
 121 require_once( RUN_MAINTENANCE_IF_MAIN );