maintenance/cleanupWatchlist.php

   1 <?php
   2 /*
   3  * Script to remove broken, unparseable titles in the Watchlist.
   4  *
   5  * Usage: php cleanupWatchlist.php [--fix]
   6  * Options:
   7  *   --fix  Actually remove entries; without will only report.
   8  *
   9  * Copyright (C) 2005,2006 Brion Vibber <brion@pobox.com>
  10  * http://www.mediawiki.org/
  11  *
  12  * This program is free software; you can redistribute it and/or modify
  13  * it under the terms of the GNU General Public License as published by
  14  * the Free Software Foundation; either version 2 of the License, or
  15  * (at your option) any later version.
  16  *
  17  * This program is distributed in the hope that it will be useful,
  18  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  19  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  20  * GNU General Public License for more details.
  21  *
  22  * You should have received a copy of the GNU General Public License along
  23  * with this program; if not, write to the Free Software Foundation, Inc.,
  24  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  25  * http://www.gnu.org/copyleft/gpl.html
  26  *
  27  * @file
  28  * @author Brion Vibber <brion at pobox.com>
  29  * @ingroup Maintenance
  30  */
  31
  32 $options = array( 'fix' );
  33
  34 require_once( 'commandLine.inc' );
  35 require_once( 'FiveUpgrade.inc' );
  36
  37 /**
  38  * @ingroup Maintenance
  39  */
  40 class WatchlistCleanup extends FiveUpgrade {
  41         function WatchlistCleanup( $dryrun = false ) {
  42                 parent::FiveUpgrade();
  43
  44                 $this->maxLag = 10; # if slaves are lagged more than 10 secs, wait
  45                 $this->dryrun = $dryrun;
  46         }
  47
  48         function cleanup() {
  49                 $this->runTable( 'watchlist',
  50                         '',
  51                         array( &$this, 'processEntry' ) );
  52         }
  53
  54         function init( $count, $table ) {
  55                 $this->processed = 0;
  56                 $this->updated = 0;
  57                 $this->count = $count;
  58                 $this->startTime = wfTime();
  59                 $this->table = $table;
  60         }
  61
  62         function progress( $updated ) {
  63                 $this->updated += $updated;
  64                 $this->processed++;
  65                 if( $this->processed % 100 != 0 ) {
  66                         return;
  67                 }
  68                 $portion = $this->processed / $this->count;
  69                 $updateRate = $this->updated / $this->processed;
  70
  71                 $now = wfTime();
  72                 $delta = $now - $this->startTime;
  73                 $estimatedTotalTime = $delta / $portion;
  74                 $eta = $this->startTime + $estimatedTotalTime;
  75
  76                 printf( "%s %s: %6.2f%% done on %s; ETA %s [%d/%d] %.2f/sec <%.2f%% updated>\n",
  77                         wfWikiID(),
  78                         wfTimestamp( TS_DB, intval( $now ) ),
  79                         $portion * 100.0,
  80                         $this->table,
  81                         wfTimestamp( TS_DB, intval( $eta ) ),
  82                         $this->processed,
  83                         $this->count,
  84                         $this->processed / $delta,
  85                         $updateRate * 100.0 );
  86                 flush();
  87         }
  88
  89         function runTable( $table, $where, $callback ) {
  90                 $fname = 'WatchlistCleanup::runTable';
  91
  92                 $count = $this->dbw->selectField( $table, 'count(*)', '', $fname );
  93                 $this->init( $count, 'watchlist' );
  94                 $this->log( "Processing $table..." );
  95
  96                 $tableName = $this->dbr->tableName( $table );
  97                 $sql = "SELECT * FROM $tableName $where";
  98                 $result = $this->dbr->query( $sql, $fname );
  99
 100                 while( $row = $this->dbr->fetchObject( $result ) ) {
 101                         call_user_func( $callback, $row );
 102                 }
 103                 $this->log( "Finished $table... $this->updated of $this->processed rows updated" );
 104                 $this->dbr->freeResult( $result );
 105         }
 106
 107         function processEntry( $row ) {
 108                 $current = Title::makeTitle( $row->wl_namespace, $row->wl_title );
 109                 $display = $current->getPrefixedText();
 110
 111                 $verified = UtfNormal::cleanUp( $display );
 112
 113                 $title = Title::newFromText( $verified );
 114
 115                 if( $row->wl_user == 0 || is_null( $title ) || !$title->equals( $current ) ) {
 116                         $this->log( "invalid watch by {$row->wl_user} for ({$row->wl_namespace}, \"{$row->wl_title}\")" );
 117                         $this->removeWatch( $row );
 118                         return $this->progress( 1 );
 119                 }
 120
 121                 $this->progress( 0 );
 122         }
 123
 124         function removeWatch( $row ) {
 125                 if( !$this->dryrun) {
 126                         $dbw = wfGetDB( DB_MASTER );
 127                         $dbw->delete( 'watchlist', array(
 128                                 'wl_user'      => $row->wl_user,
 129                                 'wl_namespace' => $row->wl_namespace,
 130                                 'wl_title'     => $row->wl_title ),
 131                         'WatchlistCleanup::removeWatch' );
 132                         $this->log( '- removed' );
 133                 }
 134         }
 135 }
 136
 137 $wgUser->setName( 'Conversion script' );
 138 $caps = new WatchlistCleanup( !isset( $options['fix'] ) );
 139 $caps->cleanup();
 140
 141