maintenance/updateCollation.php

   1 <?php
   2 /**
   3  * Script will find all rows in the categorylinks table whose collation is
   4  * out-of-date (cl_collation != $wgCategoryCollation) and repopulate cl_sortkey
   5  * using the page title and cl_sortkey_prefix.
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License along
  18  * with this program; if not, write to the Free Software Foundation, Inc.,
  19  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  20  * http://www.gnu.org/copyleft/gpl.html
  21  *
  22  * @file
  23  * @ingroup Maintenance
  24  * @author Aryeh Gregor (Simetrical)
  25  */
  26
  27 #$optionsWithArgs = array( 'begin', 'max-slave-lag' );
  28
  29 require_once( dirname( __FILE__ ) . '/Maintenance.php' );
  30
  31 class UpdateCollation extends Maintenance {
  32         const BATCH_SIZE = 50;
  33
  34         public function __construct() {
  35                 parent::__construct();
  36
  37                 global $wgCategoryCollation;
  38                 $this->mDescription = <<<TEXT
  39 This script will find all rows in the categorylinks table whose collation is
  40 out-of-date (cl_collation != '$wgCategoryCollation') and repopulate cl_sortkey
  41 using the page title and cl_sortkey_prefix.  If everything's collation is
  42 up-to-date, it will do nothing.
  43 TEXT;
  44
  45                 $this->addOption( 'force', 'Run on all rows, even if the collation is ' .
  46                         'supposed to be up-to-date.' );
  47         }
  48
  49         public function syncDBs() {
  50                 $lb = wfGetLB();
  51                 // bug 27975 - Don't try to wait for slaves if there are none
  52                 // Prevents permission error when getting master position
  53                 if ( $lb->getServerCount() > 1 ) {
  54                         $dbw = $lb->getConnection( DB_MASTER );
  55                         $pos = $dbw->getMasterPos();
  56                         $lb->waitForAll( $pos );
  57                 }
  58         }
  59
  60         public function execute() {
  61                 global $wgCategoryCollation, $wgMiserMode;
  62
  63                 $dbw = wfGetDB( DB_MASTER );
  64                 $force = $this->getOption( 'force' );
  65
  66                 $options = array( 'LIMIT' => self::BATCH_SIZE );
  67
  68                 if ( $force ) {
  69                         $options['ORDER BY'] = 'cl_from, cl_to';
  70                         $collationConds = array();
  71                 } else {
  72                         $collationConds = array( 0 =>
  73                                 'cl_collation != ' . $dbw->addQuotes( $wgCategoryCollation ) );
  74
  75                         if ( !$wgMiserMode ) {
  76                                 $count = $dbw->selectField(
  77                                         'categorylinks',
  78                                         'COUNT(*)',
  79                                         $collationConds,
  80                                         __METHOD__
  81                                 );
  82
  83                                 if ( $count == 0 ) {
  84                                         $this->output( "Collations up-to-date.\n" );
  85                                         return;
  86                                 }
  87                                 $this->output( "Fixing collation for $count rows.\n" );
  88                         }
  89                 }
  90
  91                 $count = 0;
  92                 $batchConds = array();
  93                 do {
  94                         $this->output( 'Processing next ' . self::BATCH_SIZE . ' rows... ');
  95                         $res = $dbw->select(
  96                                 array( 'categorylinks', 'page' ),
  97                                 array( 'cl_from', 'cl_to', 'cl_sortkey_prefix', 'cl_collation',
  98                                         'cl_sortkey', 'page_namespace', 'page_title'
  99                                 ),
 100                                 array_merge( $collationConds, $batchConds, array( 'cl_from = page_id' ) ),
 101                                 __METHOD__,
 102                                 $options
 103                         );
 104
 105                         $dbw->begin();
 106                         foreach ( $res as $row ) {
 107                                 $title = Title::newFromRow( $row );
 108                                 if ( !$row->cl_collation ) {
 109                                         # This is an old-style row, so the sortkey needs to be
 110                                         # converted.
 111                                         if ( $row->cl_sortkey == $title->getText()
 112                                         || $row->cl_sortkey == $title->getPrefixedText() ) {
 113                                                 $prefix = '';
 114                                         } else {
 115                                                 # Custom sortkey, use it as a prefix
 116                                                 $prefix = $row->cl_sortkey;
 117                                         }
 118                                 } else {
 119                                         $prefix = $row->cl_sortkey_prefix;
 120                                 }
 121                                 # cl_type will be wrong for lots of pages if cl_collation is 0,
 122                                 # so let's update it while we're here.
 123                                 if ( $title->getNamespace() == NS_CATEGORY ) {
 124                                         $type = 'subcat';
 125                                 } elseif ( $title->getNamespace() == NS_FILE ) {
 126                                         $type = 'file';
 127                                 } else {
 128                                         $type = 'page';
 129                                 }
 130                                 $dbw->update(
 131                                         'categorylinks',
 132                                         array(
 133                                                 'cl_sortkey' => Collation::singleton()->getSortKey(
 134                                                         $title->getCategorySortkey( $prefix ) ),
 135                                                 'cl_sortkey_prefix' => $prefix,
 136                                                 'cl_collation' => $wgCategoryCollation,
 137                                                 'cl_type' => $type,
 138                                                 'cl_timestamp = cl_timestamp',
 139                                         ),
 140                                         array( 'cl_from' => $row->cl_from, 'cl_to' => $row->cl_to ),
 141                                         __METHOD__
 142                                 );
 143                         }
 144                         $dbw->commit();
 145
 146                         if ( $force && $row ) {
 147                                 $encFrom = $dbw->addQuotes( $row->cl_from );
 148                                 $encTo = $dbw->addQuotes( $row->cl_to );
 149                                 $batchConds = array(
 150                                         "(cl_from = $encFrom AND cl_to > $encTo) " .
 151                                         " OR cl_from > $encFrom" );
 152                         }
 153
 154                         $count += $res->numRows();
 155                         $this->output( "$count done.\n" );
 156
 157                         $this->syncDBs();
 158                 } while ( $res->numRows() == self::BATCH_SIZE );
 159         }
 160 }
 161
 162 $maintClass = "UpdateCollation";
 163 require_once( RUN_MAINTENANCE_IF_MAIN );