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->addDescription( '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                 $batchSize = $this->getBatchSize();
  50                 $db = $this->getDB( DB_MASTER );
  51                 if ( !$db->tableExists( 'revision' ) ) {
  52                         $this->error( "revision table does not exist" );
  53
  54                         return false;
  55                 }
  56                 $this->output( "Populating rev_parent_id column\n" );
  57                 $start = $db->selectField( 'revision', 'MIN(rev_id)', '', __FUNCTION__ );
  58                 $end = $db->selectField( 'revision', 'MAX(rev_id)', '', __FUNCTION__ );
  59                 if ( is_null( $start ) || is_null( $end ) ) {
  60                         $this->output( "...revision table seems to be empty, nothing to do.\n" );
  61
  62                         return true;
  63                 }
  64                 # Do remaining chunk
  65                 $blockStart = intval( $start );
  66                 $blockEnd = intval( $start ) + $batchSize - 1;
  67                 $count = 0;
  68                 $changed = 0;
  69                 while ( $blockStart <= $end ) {
  70                         $this->output( "...doing rev_id from $blockStart to $blockEnd\n" );
  71                         $cond = "rev_id BETWEEN $blockStart AND $blockEnd";
  72                         $res = $db->select( 'revision',
  73                                 [ 'rev_id', 'rev_page', 'rev_timestamp', 'rev_parent_id' ],
  74                                 [ $cond, 'rev_parent_id' => null ], __METHOD__ );
  75                         # Go through and update rev_parent_id from these rows.
  76                         # Assume that the previous revision of the title was
  77                         # the original previous revision of the title when the
  78                         # edit was made...
  79                         foreach ( $res as $row ) {
  80                                 # First, check rows with the same timestamp other than this one
  81                                 # with a smaller rev ID. The highest ID "wins". This avoids loops
  82                                 # as timestamp can only decrease and never loops with IDs (from parent to parent)
  83                                 $previousID = $db->selectField( 'revision', 'rev_id',
  84                                         [ 'rev_page' => $row->rev_page, 'rev_timestamp' => $row->rev_timestamp,
  85                                                 "rev_id < " . intval( $row->rev_id ) ],
  86                                         __METHOD__,
  87                                         [ 'ORDER BY' => 'rev_id DESC' ] );
  88                                 # If there are none, check the highest ID with a lower timestamp
  89                                 if ( !$previousID ) {
  90                                         # Get the highest older timestamp
  91                                         $lastTimestamp = $db->selectField(
  92                                                 'revision',
  93                                                 'rev_timestamp',
  94                                                 [
  95                                                         'rev_page' => $row->rev_page,
  96                                                         "rev_timestamp < " . $db->addQuotes( $row->rev_timestamp )
  97                                                 ],
  98                                                 __METHOD__,
  99                                                 [ 'ORDER BY' => 'rev_timestamp DESC' ]
 100                                         );
 101                                         # If there is one, let the highest rev ID win
 102                                         if ( $lastTimestamp ) {
 103                                                 $previousID = $db->selectField( 'revision', 'rev_id',
 104                                                         [ 'rev_page' => $row->rev_page, 'rev_timestamp' => $lastTimestamp ],
 105                                                         __METHOD__,
 106                                                         [ 'ORDER BY' => 'rev_id DESC' ] );
 107                                         }
 108                                 }
 109                                 $previousID = intval( $previousID );
 110                                 if ( $previousID != $row->rev_parent_id ) {
 111                                         $changed++;
 112                                 }
 113                                 # Update the row...
 114                                 $db->update( 'revision',
 115                                         [ 'rev_parent_id' => $previousID ],
 116                                         [ 'rev_id' => $row->rev_id ],
 117                                         __METHOD__ );
 118                                 $count++;
 119                         }
 120                         $blockStart += $batchSize;
 121                         $blockEnd += $batchSize;
 122                         wfWaitForSlaves();
 123                 }
 124                 $this->output( "rev_parent_id population complete ... {$count} rows [{$changed} changed]\n" );
 125
 126                 return true;
 127         }
 128 }
 129
 130 $maintClass = PopulateParentId::class;
 131 require_once RUN_MAINTENANCE_IF_MAIN;