maintenance/populateCategory.php

   1 <?php
   2 /**
   3  * Populate the category table.
   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  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Maintenance
  22  * @author Simetrical
  23  */
  24
  25 require_once __DIR__ . '/Maintenance.php';
  26
  27 /**
  28  * Mainteance script to populate the category table.
  29  *
  30  * @ingroup Maintenance
  31  */
  32 class PopulateCategory extends Maintenance {
  33
  34         const REPORTING_INTERVAL = 1000;
  35
  36         public function __construct() {
  37                 parent::__construct();
  38                 $this->mDescription = <<<TEXT
  39 This script will populate the category table, added in MediaWiki 1.13.  It will
  40 print out progress indicators every 1000 categories it adds to the table.  The
  41 script is perfectly safe to run on large, live wikis, and running it multiple
  42 times is harmless.  You may want to use the throttling options if it's causing
  43 too much load; they will not affect correctness.
  44
  45 If the script is stopped and later resumed, you can use the --begin option with
  46 the last printed progress indicator to pick up where you left off.  This is
  47 safe, because any newly-added categories before this cutoff will have been
  48 added after the software update and so will be populated anyway.
  49
  50 When the script has finished, it will make a note of this in the database, and
  51 will not run again without the --force option.
  52 TEXT;
  53 # '
  54                 $this->addOption( 'begin', 'Only do categories whose names are alphabetically after the provided name', false, true );
  55                 $this->addOption( 'max-slave-lag', 'If slave lag exceeds this many seconds, wait until it drops before continuing.  Default: 10', false, true );
  56                 $this->addOption( 'throttle', 'Wait this many milliseconds after each category.  Default: 0', false, true );
  57                 $this->addOption( 'force', 'Run regardless of whether the database says it\'s been run already' );
  58         }
  59
  60         public function execute() {
  61                 $begin = $this->getOption( 'begin', '' );
  62                 $maxSlaveLag = $this->getOption( 'max-slave-lag', 10 );
  63                 $throttle = $this->getOption( 'throttle', 0 );
  64                 $force = $this->getOption( 'force', false );
  65                 $this->doPopulateCategory( $begin, $maxSlaveLag, $throttle, $force );
  66         }
  67
  68         private function doPopulateCategory( $begin, $maxlag, $throttle, $force ) {
  69                 $dbw = wfGetDB( DB_MASTER );
  70
  71                 if ( !$force ) {
  72                         $row = $dbw->selectRow(
  73                                 'updatelog',
  74                                 '1',
  75                                 array( 'ul_key' => 'populate category' ),
  76                                 __METHOD__
  77                         );
  78                         if ( $row ) {
  79                                 $this->output( "Category table already populated.  Use php " .
  80                                 "maintenance/populateCategory.php\n--force from the command line " .
  81                                 "to override.\n" );
  82                                 return true;
  83                         }
  84                 }
  85
  86                 $throttle = intval( $throttle );
  87                 if ( $begin !== '' ) {
  88                         $where = 'cl_to > ' . $dbw->addQuotes( $begin );
  89                 } else {
  90                         $where = null;
  91                 }
  92                 $i = 0;
  93
  94                 while ( true ) {
  95                         # Find which category to update
  96                         $row = $dbw->selectRow(
  97                                 'categorylinks',
  98                                 'cl_to',
  99                                 $where,
 100                                 __METHOD__,
 101                                 array(
 102                                         'ORDER BY' => 'cl_to'
 103                                 )
 104                         );
 105                         if ( !$row ) {
 106                                 # Done, hopefully.
 107                                 break;
 108                         }
 109                         $name = $row->cl_to;
 110                         $where = 'cl_to > ' . $dbw->addQuotes( $name );
 111
 112                         # Use the row to update the category count
 113                         $cat = Category::newFromName( $name );
 114                         if ( !is_object( $cat ) ) {
 115                                 $this->output( "The category named $name is not valid?!\n" );
 116                         } else {
 117                                 $cat->refreshCounts();
 118                         }
 119
 120                         ++$i;
 121                         if ( !( $i % self::REPORTING_INTERVAL ) ) {
 122                                 $this->output( "$name\n" );
 123                                 wfWaitForSlaves();
 124                         }
 125                         usleep( $throttle * 1000 );
 126                 }
 127
 128                 if ( $dbw->insert(
 129                                 'updatelog',
 130                                 array( 'ul_key' => 'populate category' ),
 131                                 __METHOD__,
 132                                 'IGNORE'
 133                         )
 134                 ) {
 135                         $this->output( "Category population complete.\n" );
 136                         return true;
 137                 } else {
 138                         $this->output( "Could not insert category population row.\n" );
 139                         return false;
 140                 }
 141         }
 142 }
 143
 144 $maintClass = "PopulateCategory";
 145 require_once RUN_MAINTENANCE_IF_MAIN;