maintenance/cleanupDupes.php

   1 <?php
   2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com>
   3 # http://www.mediawiki.org/
   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 # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  * If on the old non-unique indexes, check the cur table for duplicate
  22  * entries and remove them...
  23  *
  24  * @package MediaWiki
  25  * @subpackage Maintenance
  26  */
  27
  28 $options = array( 'fix' );
  29
  30 require_once( "commandLine.inc" );
  31 $wgTitle = Title::newFromText( "Dupe cur entry cleanup script" );
  32
  33 checkDupes( isset( $options['fix'] ) );
  34
  35 function fixDupes( $fixthem = false) {
  36         $dbw =& wfGetDB( DB_MASTER );
  37         $cur = $dbw->tableName( 'cur' );
  38         $dbw->query( "LOCK TABLES $cur WRITE" );
  39         echo "Checking for duplicate cur table entries... (this may take a while on a large wiki)\n";
  40         $res = $dbw->query( <<<END
  41 SELECT cur_namespace,cur_title,count(*) as c,min(cur_id) as id
  42   FROM $cur
  43  GROUP BY cur_namespace,cur_title
  44 HAVING c > 1
  45 END
  46         );
  47         $n = $dbw->numRows( $res );
  48         echo "Found $n titles with duplicate entries.\n";
  49         if( $n > 0 ) {
  50                 if( $fixthem ) {
  51                         echo "Correcting...\n";
  52                 } else {
  53                         echo "Just a demo...\n";
  54                 }
  55                 while( $row = $dbw->fetchObject( $res ) ) {
  56                         $ns = IntVal( $row->cur_namespace );
  57                         $title = $dbw->addQuotes( $row->cur_title );
  58                         $id = IntVal( $row->id );
  59                         echo "$ns:$row->cur_title (canonical ID $id)\n";
  60                         if( $fixthem ) {
  61                                 $dbw->query( <<<END
  62 DELETE
  63   FROM $cur
  64  WHERE cur_namespace=$ns
  65    AND cur_title=$title
  66    AND cur_id>$id
  67 END
  68                                 );
  69                         }
  70                 }
  71         }
  72         $dbw->query( 'UNLOCK TABLES' );
  73         if( $fixthem ) {
  74                 echo "Done.\n";
  75         } else {
  76                 echo "Run again with --fix option to delete the duplicates.\n";
  77         }
  78 }
  79
  80 function checkDupes( $fixthem = false ) {
  81         $dbw =& wfGetDB( DB_MASTER );
  82         if( $dbw->indexExists( 'cur', 'name_title' ) &&
  83             $dbw->indexUnique( 'cur', 'name_title' ) ) {
  84                 echo "Your cur table has the current unique index; no duplicate entries.\n";
  85         } else {
  86                 echo "Your cur table has the old non-unique index and may have duplicate entries.\n";
  87                 fixDupes( $fixthem );
  88         }
  89 }
  90
  91 ?>