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   4  * out-of-date (cl_collation != $wgCategoryCollation) and repopulate cl_sortkey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; // Number of rows to process in one batch
  33         const SYNC_INTERVAL = 20; // Wait for slaves after this many batches
  34
  35         public function __construct() {
  36                 parent::__construct();
  37
  38                 global $wgCategoryCollation;
  39                 $this->mDescription = <<<TEXT
  40 This script will find all rows in the categorylinks table whose collation is
  41 out-of-date (cl_collation != '$wgCategoryCollation') and repopulate cl_sortkey
  42 using the page title and cl_sortkey_prefix.  If everything's collation is
  43 up-to-date, it will do nothing.
  44 TEXT;
  45
  46                 $this->addOption( 'force', 'Run on all rows, even if the collation is ' .
  47                         'supposed to be up-to-date.' );
  48                 $this->addOption( 'previous-collation', 'Set the previous value of ' .
  49                         '$wgCategoryCollation here to speed up this script, especially if your ' .
  50                         'categorylinks table is large. This will only update rows with that ' .
  51                         'collation, though, so it may miss out-of-date rows with a different, ' .
  52                         'even older collation.', false, true );
  53         }
  54
  55         public function execute() {
  56                 global $wgCategoryCollation, $wgMiserMode;
  57
  58                 $dbw = $this->getDB( DB_MASTER );
  59                 $force = $this->getOption( 'force' );
  60
  61                 $options = array( 'LIMIT' => self::BATCH_SIZE, 'STRAIGHT_JOIN' );
  62
  63                 if ( $force ) {
  64                         $options['ORDER BY'] = 'cl_from, cl_to';
  65                         $collationConds = array();
  66                 } else {
  67                         if ( $this->hasOption( 'previous-collation' ) ) {
  68                                 $collationConds['cl_collation'] = $this->getOption( 'previous-collation' );
  69                         } else {
  70                                 $collationConds = array( 0 =>
  71                                         'cl_collation != ' . $dbw->addQuotes( $wgCategoryCollation )
  72                                 );
  73                         }
  74
  75                         if ( !$wgMiserMode ) {
  76                                 $count = $dbw->selectField(
  77                                         'categorylinks',
  78                                         'COUNT(*)',
  79                                         $collationConds,
  80                                         __METHOD__
  81                                 );
  82                         } else {
  83                                 $count = $dbw->estimateRowCount(
  84                                         'categorylinks',
  85                                         '',
  86                                         $collationConds,
  87                                         __METHOD__
  88                                 );
  89                         }
  90                         if ( $count == 0 ) {
  91                                 $this->output( "Collations up-to-date.\n" );
  92                                 return;
  93                         }
  94                         $this->output( "Fixing collation for $count rows.\n" );
  95                 }
  96
  97                 $count = 0;
  98                 $batchCount = 0;
  99                 $batchConds = array();
 100                 do {
 101                         $this->output( "Selecting next " . self::BATCH_SIZE . " rows..." );
 102                         $res = $dbw->select(
 103                                 array( 'categorylinks', 'page' ),
 104                                 array( 'cl_from', 'cl_to', 'cl_sortkey_prefix', 'cl_collation',
 105                                         'cl_sortkey', 'page_namespace', 'page_title'
 106                                 ),
 107                                 array_merge( $collationConds, $batchConds, array( 'cl_from = page_id' ) ),
 108                                 __METHOD__,
 109                                 $options
 110                         );
 111                         $this->output( " processing..." );
 112
 113                         $dbw->begin( __METHOD__ );
 114                         foreach ( $res as $row ) {
 115                                 $title = Title::newFromRow( $row );
 116                                 if ( !$row->cl_collation ) {
 117                                         # This is an old-style row, so the sortkey needs to be
 118                                         # converted.
 119                                         if ( $row->cl_sortkey == $title->getText()
 120                                                 || $row->cl_sortkey == $title->getPrefixedText() ) {
 121                                                 $prefix = '';
 122                                         } else {
 123                                                 # Custom sortkey, use it as a prefix
 124                                                 $prefix = $row->cl_sortkey;
 125                                         }
 126                                 } else {
 127                                         $prefix = $row->cl_sortkey_prefix;
 128                                 }
 129                                 # cl_type will be wrong for lots of pages if cl_collation is 0,
 130                                 # so let's update it while we're here.
 131                                 if ( $title->getNamespace() == NS_CATEGORY ) {
 132                                         $type = 'subcat';
 133                                 } elseif ( $title->getNamespace() == NS_FILE ) {
 134                                         $type = 'file';
 135                                 } else {
 136                                         $type = 'page';
 137                                 }
 138                                 $dbw->update(
 139                                         'categorylinks',
 140                                         array(
 141                                                 'cl_sortkey' => Collation::singleton()->getSortKey(
 142                                                         $title->getCategorySortkey( $prefix ) ),
 143                                                 'cl_sortkey_prefix' => $prefix,
 144                                                 'cl_collation' => $wgCategoryCollation,
 145                                                 'cl_type' => $type,
 146                                                 'cl_timestamp = cl_timestamp',
 147                                         ),
 148                                         array( 'cl_from' => $row->cl_from, 'cl_to' => $row->cl_to ),
 149                                         __METHOD__
 150                                 );
 151                         }
 152                         $dbw->commit( __METHOD__ );
 153
 154                         if ( $force && $row ) {
 155                                 $encFrom = $dbw->addQuotes( $row->cl_from );
 156                                 $encTo = $dbw->addQuotes( $row->cl_to );
 157                                 $batchConds = array(
 158                                         "(cl_from = $encFrom AND cl_to > $encTo) " .
 159                                         " OR cl_from > $encFrom" );
 160                         }
 161
 162                         $count += $res->numRows();
 163                         $this->output( "$count done.\n" );
 164
 165                         if ( ++$batchCount % self::SYNC_INTERVAL == 0 ) {
 166                                 $this->output( "Waiting for slaves ... " );
 167                                 wfWaitForSlaves();
 168                                 $this->output( "done\n" );
 169                         }
 170                 } while ( $res->numRows() == self::BATCH_SIZE );
 171         }
 172 }
 173
 174 $maintClass = "UpdateCollation";
 175 require_once( RUN_MAINTENANCE_IF_MAIN );