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 require_once( "commandLine.inc" );
  29 require_once( "rebuildtextindex.inc" );
  30 $wgTitle = Title::newFromText( "Rebuild text index script" );
  31
  32 checkDupes();
  33
  34 function fixDupes() {
  35         $dbw =& wfGetDB( DB_MASTER );
  36         $cur = $dbw->tableName( 'cur' );
  37         $dbw->query( "LOCK TABLES $cur WRITE" );
  38         echo "Checking for duplicate cur table entries... (this may take a while on a large wiki)\n";
  39         $res = $dbw->query( <<<END
  40 SELECT cur_namespace,cur_title,count(*) as c,max(cur_id) as id
  41   FROM $cur
  42  GROUP BY cur_namespace,cur_title
  43 HAVING c > 1
  44 END
  45         );
  46         $n = $dbw->numRows( $res );
  47         echo "Found $n titles with duplicate entries.\n";
  48         if( $n > 0 ) {
  49                 echo "Correcting...\n";
  50                 while( $row = $dbw->fetchObject( $res ) ) {
  51                         $ns = IntVal( $row->cur_namespace );
  52                         $title = $dbw->addQuotes( $row->cur_title );
  53                         $id = IntVal( $row->id );
  54                         $dbw->query( <<<END
  55 DELETE
  56   FROM $cur
  57  WHERE cur_namespace=$ns
  58    AND cur_title=$title
  59    AND cur_id<$id
  60 END
  61                         );
  62                 }
  63         }
  64         $dbw->query( 'UNLOCK TABLES' );
  65         echo "Done.\n";
  66 }
  67
  68 function checkDupes() {
  69         $dbw =& wfGetDB( DB_MASTER );
  70         if( $dbw->indexExists( 'cur', 'name_title' ) &&
  71             $dbw->indexUnique( 'cur', 'name_title' ) ) {
  72                 echo "Your cur table has the current unique index; no duplicate entries.\n";
  73         } else {
  74                 echo "Your cur table has the old non-unique index and may have duplicate entries.\n";
  75                 fixDupes();
  76         }
  77 }
  78
  79 ?>