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   4  * out-of-date (cl_collation != $wgCategoryCollation) and repopulate cl_sortkey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 = 1000;
  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  40 out-of-date (cl_collation != '$wgCategoryCollation') and repopulate cl_sortkey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                 $dbw = $lb->getConnection( DB_MASTER );
  52                 $pos = $dbw->getMasterPos();
  53                 $lb->waitForAll( $pos );
  54         }
  55
  56         public function execute() {
  57                 global $wgCategoryCollation, $wgMiserMode;
  58
  59                 $dbw = wfGetDB( DB_MASTER );
  60                 $force = $this->getOption( 'force' );
  61
  62                 $options = array( 'LIMIT' => self::BATCH_SIZE );
  63
  64                 if ( $force ) {
  65                         $options['ORDER BY'] = 'cl_from, cl_to';
  66                 } else {
  67                         $collationConds = array( 0 =>
  68                                 'cl_collation != ' . $dbw->addQuotes( $wgCategoryCollation ) );
  69
  70                         if ( !$wgMiserMode ) {
  71                                 $count = $dbw->selectField(
  72                                         'categorylinks',
  73                                         'COUNT(*)',
  74                                         $collationConds,
  75                                         __METHOD__
  76                                 );
  77
  78                                 if ( $count == 0 ) {
  79                                         $this->output( "Collations up-to-date.\n" );
  80                                         return;
  81                                 }
  82                                 $this->output( "Fixing collation for $count rows.\n" );
  83                         }
  84                 }
  85
  86                 $count = 0;
  87                 $row = false;
  88                 $batchConds = array();
  89                 do {
  90                         $this->output( 'Processing next ' . self::BATCH_SIZE . ' rows... ');
  91                         $res = $dbw->select(
  92                                 array( 'categorylinks', 'page' ),
  93                                 array( 'cl_from', 'cl_to', 'cl_sortkey_prefix', 'cl_collation',
  94                                         'cl_sortkey', 'page_namespace', 'page_title'
  95                                 ),
  96                                 array_merge( $collationConds, $batchConds, array( 'cl_from = page_id' ) ),
  97                                 __METHOD__,
  98                                 $options
  99                         );
 100
 101                         $dbw->begin();
 102                         foreach ( $res as $row ) {
 103                                 $title = Title::newFromRow( $row );
 104                                 if ( !$row->cl_collation ) {
 105                                         # This is an old-style row, so the sortkey needs to be
 106                                         # converted.
 107                                         if ( $row->cl_sortkey == $title->getText()
 108                                         || $row->cl_sortkey == $title->getPrefixedText() ) {
 109                                                 $prefix = '';
 110                                         } else {
 111                                                 # Custom sortkey, use it as a prefix
 112                                                 $prefix = $row->cl_sortkey;
 113                                         }
 114                                 } else {
 115                                         $prefix = $row->cl_sortkey_prefix;
 116                                 }
 117                                 # cl_type will be wrong for lots of pages if cl_collation is 0,
 118                                 # so let's update it while we're here.
 119                                 if ( $title->getNamespace() == NS_CATEGORY ) {
 120                                         $type = 'subcat';
 121                                 } elseif ( $title->getNamespace() == NS_FILE ) {
 122                                         $type = 'file';
 123                                 } else {
 124                                         $type = 'page';
 125                                 }
 126                                 $dbw->update(
 127                                         'categorylinks',
 128                                         array(
 129                                                 'cl_sortkey' => Collation::singleton()->getSortKey(
 130                                                         $title->getCategorySortkey( $prefix ) ),
 131                                                 'cl_sortkey_prefix' => $prefix,
 132                                                 'cl_collation' => $wgCategoryCollation,
 133                                                 'cl_type' => $type,
 134                                                 'cl_timestamp = cl_timestamp',
 135                                         ),
 136                                         array( 'cl_from' => $row->cl_from, 'cl_to' => $row->cl_to ),
 137                                         __METHOD__
 138                                 );
 139                         }
 140                         $dbw->commit();
 141
 142                         if ( $force && $row ) {
 143                                 $encFrom = $dbw->addQuotes( $row->cl_from );
 144                                 $encTo = $dbw->addQuotes( $row->cl_to );
 145                                 $batchConds = array(
 146                                         "(cl_from = $encFrom AND cl_to > $encTo) " .
 147                                         " OR cl_from > $encFrom" );
 148                         }
 149
 150                         $count += $res->numRows();
 151                         $this->output( "$count done.\n" );
 152
 153                         $this->syncDBs();
 154                 } while ( $res->numRows() == self::BATCH_SIZE );
 155         }
 156 }
 157
 158 $maintClass = "UpdateCollation";
 159 require_once( RUN_MAINTENANCE_IF_MAIN );