maintenance/refreshExternallinksIndex.php

   1 <?php
   2 /**
   3  * Refresh the externallinks table el_index and el_index_60 from el_to
   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  */
  23
  24 require_once __DIR__ . '/Maintenance.php';
  25
  26 use MediaWiki\MediaWikiServices;
  27
  28 /**
  29  * Maintenance script that refreshes the externallinks table el_index and
  30  * el_index_60 from el_to
  31  *
  32  * @ingroup Maintenance
  33  * @since 1.33
  34  */
  35 class RefreshExternallinksIndex extends LoggedUpdateMaintenance {
  36         public function __construct() {
  37                 parent::__construct();
  38                 $this->addDescription(
  39                         'Refresh the externallinks table el_index and el_index_60 from el_to' );
  40                 $this->setBatchSize( 10000 );
  41         }
  42
  43         protected function getUpdateKey() {
  44                 return static::class
  45                         . ' v' . LinkFilter::VERSION
  46                         . ( LinkFilter::supportsIDN() ? '+' : '-' ) . 'IDN';
  47         }
  48
  49         protected function updateSkippedMessage() {
  50                 return 'externallinks table indexes up to date';
  51         }
  52
  53         protected function doDBUpdates() {
  54                 $dbw = $this->getDB( DB_MASTER );
  55                 if ( !$dbw->tableExists( 'externallinks', __METHOD__ ) ) {
  56                         $this->error( "externallinks table does not exist" );
  57                         return false;
  58                 }
  59                 $this->output( "Updating externallinks table index fields\n" );
  60
  61                 $minmax = $dbw->selectRow(
  62                         'externallinks',
  63                         [ 'min' => 'MIN(el_id)', 'max' => 'MAX(el_id)' ],
  64                         '',
  65                         __METHOD__
  66                 );
  67
  68                 $updated = 0;
  69                 $deleted = 0;
  70                 $start = $minmax->min - 1;
  71                 $last = $minmax->max;
  72                 $lbFactory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
  73                 while ( $start < $last ) {
  74                         $end = min( $start + $this->mBatchSize, $last );
  75                         $this->output( "el_id $start - $end of $last\n" );
  76                         $res = $dbw->select( 'externallinks', [ 'el_id', 'el_to', 'el_index' ],
  77                                 [
  78                                         "el_id > $start",
  79                                         "el_id <= $end",
  80                                 ],
  81                                 __METHOD__,
  82                                 [ 'ORDER BY' => 'el_id' ]
  83                         );
  84                         foreach ( $res as $row ) {
  85                                 $newIndexes = LinkFilter::makeIndexes( $row->el_to );
  86                                 if ( !$newIndexes ) {
  87                                         $dbw->delete( 'externallinks', [ 'el_id' => $row->el_id ], __METHOD__ );
  88                                         $deleted++;
  89                                         continue;
  90                                 }
  91                                 if ( in_array( $row->el_index, $newIndexes, true ) ) {
  92                                         continue;
  93                                 }
  94
  95                                 if ( count( $newIndexes ) === 1 ) {
  96                                         $newIndex = $newIndexes[0];
  97                                 } else {
  98                                         // Assume the scheme is the only difference between the different $newIndexes.
  99                                         // Keep this row's scheme, assuming there's another row with the other scheme.
 100                                         $newIndex = substr( $row->el_index, 0, strpos( $row->el_index, ':' ) ) .
 101                                                 substr( $newIndexes[0], strpos( $newIndexes[0], ':' ) );
 102                                 }
 103                                 $dbw->update( 'externallinks',
 104                                         [
 105                                                 'el_index' => $newIndex,
 106                                                 'el_index_60' => substr( $newIndex, 0, 60 ),
 107                                         ],
 108                                         [ 'el_id' => $row->el_id ],
 109                                         __METHOD__
 110                                 );
 111                                 $updated++;
 112                         }
 113                         $lbFactory->waitForReplication();
 114                         $start = $end;
 115                 }
 116                 $this->output( "Done, $updated rows updated, $deleted deleted.\n" );
 117
 118                 return true;
 119         }
 120 }
 121
 122 $maintClass = RefreshExternallinksIndex::class;
 123 require_once RUN_MAINTENANCE_IF_MAIN;