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  * @author <brion@pobox.com>
  25  * @package MediaWiki
  26  * @subpackage Maintenance
  27  */
  28
  29 $options = array( 'fix' );
  30
  31 /** */
  32 require_once( 'commandLine.inc' );
  33 $wgTitle = Title::newFromText( 'Dupe cur entry cleanup script' );
  34
  35 checkDupes( isset( $options['fix'] ) );
  36
  37 function fixDupes( $fixthem = false) {
  38         $dbw =& wfGetDB( DB_MASTER );
  39         $cur = $dbw->tableName( 'cur' );
  40         $dbw->query( "LOCK TABLES $cur WRITE" );
  41         echo "Checking for duplicate cur table entries... (this may take a while on a large wiki)\n";
  42         $res = $dbw->query( <<<END
  43 SELECT cur_namespace,cur_title,count(*) as c,min(cur_id) as id
  44   FROM $cur
  45  GROUP BY cur_namespace,cur_title
  46 HAVING c > 1
  47 END
  48         );
  49         $n = $dbw->numRows( $res );
  50         echo "Found $n titles with duplicate entries.\n";
  51         if( $n > 0 ) {
  52                 if( $fixthem ) {
  53                         echo "Correcting...\n";
  54                 } else {
  55                         echo "Just a demo...\n";
  56                 }
  57                 while( $row = $dbw->fetchObject( $res ) ) {
  58                         $ns = IntVal( $row->cur_namespace );
  59                         $title = $dbw->addQuotes( $row->cur_title );
  60                         $id = IntVal( $row->id );
  61                         echo "$ns:$row->cur_title (canonical ID $id)\n";
  62                         if( $fixthem ) {
  63                                 $dbw->query( <<<END
  64 DELETE
  65   FROM $cur
  66  WHERE cur_namespace=$ns
  67    AND cur_title=$title
  68    AND cur_id>$id
  69 END
  70                                 );
  71                         }
  72                 }
  73         }
  74         $dbw->query( 'UNLOCK TABLES' );
  75         if( $fixthem ) {
  76                 echo "Done.\n";
  77         } else {
  78                 echo "Run again with --fix option to delete the duplicates.\n";
  79         }
  80 }
  81
  82 function checkDupes( $fixthem = false ) {
  83         $dbw =& wfGetDB( DB_MASTER );
  84         if( $dbw->indexExists( 'cur', 'name_title' ) &&
  85             $dbw->indexUnique( 'cur', 'name_title' ) ) {
  86                 echo "Your cur table has the current unique index; no duplicate entries.\n";
  87         } else {
  88                 echo "Your cur table has the old non-unique index and may have duplicate entries.\n";
  89                 fixDupes( $fixthem );
  90         }
  91 }
  92 ?>