maintenance/populateChangeTagDef.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  */
  18
  19 require_once __DIR__ . '/Maintenance.php';
  20
  21 /**
  22  * Populate and improve accuracy of change_tag_def statistics.
  23  *
  24  * @ingroup Maintenance
  25  */
  26 class PopulateChangeTagDef extends Maintenance {
  27         /** @var Wikimedia\Rdbms\ILBFactory */
  28         protected $lbFactory;
  29
  30         public function __construct() {
  31                 parent::__construct();
  32                 $this->addDescription( 'Populate and improve accuracy of change_tag_def statistics' );
  33                 $this->addOption( 'dry-run', 'Print debug info instead of actually deleting' );
  34                 $this->setBatchSize( 1000 );
  35                 $this->addOption(
  36                         'sleep',
  37                         'Sleep time (in seconds) between every batch',
  38                         false,
  39                         true
  40                 );
  41                 $this->addOption( 'populate-only', 'Do not update change_tag_def table' );
  42         }
  43
  44         public function execute() {
  45                 global $wgChangeTagsSchemaMigrationStage;
  46                 $this->lbFactory = MediaWiki\MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
  47                 $this->setBatchSize( $this->getOption( 'batch-size', $this->getBatchSize() ) );
  48
  49                 $this->countDown( 5 );
  50                 if ( $wgChangeTagsSchemaMigrationStage < MIGRATION_NEW ) {
  51                         if ( !$this->hasOption( 'populate-only' ) ) {
  52                                 $this->updateCountTag();
  53                         }
  54                         $this->backpopulateChangeTagId();
  55                 } else {
  56                         $this->updateCountTagId();
  57                 }
  58
  59                 // TODO: Implement
  60                 // $this->cleanZeroCountRows();
  61         }
  62
  63         private function updateCountTagId() {
  64                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
  65
  66                 // This query can be pretty expensive, don't run it on master
  67                 $res = $dbr->select(
  68                         'change_tag',
  69                         [ 'ct_tag_id', 'hitcount' => 'count(*)' ],
  70                         [],
  71                         __METHOD__,
  72                         [ 'GROUP BY' => 'ct_tag_id' ]
  73                 );
  74
  75                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
  76
  77                 foreach ( $res as $row ) {
  78                         if ( !$row->ct_tag_id ) {
  79                                 continue;
  80                         }
  81
  82                         if ( $this->hasOption( 'dry-run' ) ) {
  83                                 $this->output( 'This row will be updated: ' . implode( ', ', $row ) . "\n" );
  84                                 continue;
  85                         }
  86
  87                         $dbw->update(
  88                                 'change_tag_def',
  89                                 [ 'ctd_count' => $row->hitcount ],
  90                                 [ 'ctd_id' => $row->ct_tag_id ],
  91                                 __METHOD__
  92                         );
  93                 }
  94                 $this->lbFactory->waitForReplication();
  95         }
  96
  97         private function updateCountTag() {
  98                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
  99
 100                 // This query can be pretty expensive, don't run it on master
 101                 $res = $dbr->select(
 102                         'change_tag',
 103                         [ 'ct_tag', 'hitcount' => 'count(*)' ],
 104                         [],
 105                         __METHOD__,
 106                         [ 'GROUP BY' => 'ct_tag' ]
 107                 );
 108
 109                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
 110
 111                 foreach ( $res as $row ) {
 112                         // Hygiene check
 113                         if ( !$row->ct_tag ) {
 114                                 continue;
 115                         }
 116
 117                         if ( $this->hasOption( 'dry-run' ) ) {
 118                                 $this->output( 'This row will be updated: ' . $row->ct_tag . $row->hitcount . "\n" );
 119                                 continue;
 120                         }
 121
 122                         $dbw->upsert(
 123                                 'change_tag_def',
 124                                 [
 125                                         'ctd_name' => $row->ct_tag,
 126                                         'ctd_user_defined' => 0,
 127                                         'ctd_count' => $row->hitcount
 128                                 ],
 129                                 [ 'ctd_name' ],
 130                                 [ 'ctd_count' => $row->hitcount ],
 131                                 __METHOD__
 132                         );
 133                 }
 134                 $this->lbFactory->waitForReplication();
 135         }
 136
 137         private function backpopulateChangeTagId() {
 138                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
 139                 $changeTagDefs = $dbr->select(
 140                         'change_tag_def',
 141                         [ 'ctd_name', 'ctd_id' ],
 142                         [],
 143                         __METHOD__,
 144                         [ 'ORDER BY' => 'ctd_id' ]
 145                 );
 146
 147                 foreach ( $changeTagDefs as $row ) {
 148                         $this->backpopulateChangeTagPerTag( $row->ctd_name, $row->ctd_id );
 149                 }
 150         }
 151
 152         private function backpopulateChangeTagPerTag( $tagName, $tagId ) {
 153                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
 154                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
 155                 $sleep = (int)$this->getOption( 'sleep', 10 );
 156                 $lastId = 0;
 157                 $this->output( "Starting to add ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 158                 while ( true ) {
 159                         // Given that indexes might not be there, it's better to use replica
 160                         $ids = $dbr->selectFieldValues(
 161                                 'change_tag',
 162                                 'ct_id',
 163                                 [ 'ct_tag' => $tagName, 'ct_tag_id' => null, 'ct_id > ' . $lastId ],
 164                                 __METHOD__,
 165                                 [ 'LIMIT' => $this->getBatchSize(), 'ORDER BY' => 'ct_id' ]
 166                         );
 167
 168                         if ( !$ids ) {
 169                                 break;
 170                         }
 171                         $lastId = end( $ids );
 172
 173                         if ( $this->hasOption( 'dry-run' ) ) {
 174                                 $this->output(
 175                                         "These ids will be changed to have \"{$tagId}\" as tag id: " . implode( ', ', $ids ) . "\n"
 176                                 );
 177                                 continue;
 178                         } else {
 179                                 $this->output( "Updating ct_tag_id = {$tagId} up to row ct_id = {$lastId}\n" );
 180                         }
 181
 182                         $dbw->update(
 183                                 'change_tag',
 184                                 [ 'ct_tag_id' => $tagId ],
 185                                 [ 'ct_id' => $ids ],
 186                                 __METHOD__
 187                         );
 188
 189                         $this->lbFactory->waitForReplication();
 190                         if ( $sleep > 0 ) {
 191                                 sleep( $sleep );
 192                         }
 193                 }
 194
 195                 $this->output( "Finished adding ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 196         }
 197
 198 }
 199
 200 $maintClass = PopulateChangeTagDef::class;
 201 require_once RUN_MAINTENANCE_IF_MAIN;