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 LoggedUpdateMaintenance {
  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                 if ( $wgChangeTagsSchemaMigrationStage === MIGRATION_OLD ) {
  47                         // Return "success", but don't flag it as done so the next run will retry
  48                         $this->output( '... Not run, $wgChangeTagsSchemaMigrationStage === MIGRATION_OLD' . "\n" );
  49                         return true;
  50                 }
  51                 return parent::execute();
  52         }
  53
  54         protected function doDBUpdates() {
  55                 $this->lbFactory = MediaWiki\MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
  56                 $this->setBatchSize( $this->getOption( 'batch-size', $this->getBatchSize() ) );
  57
  58                 if ( $this->lbFactory->getMainLB()->getConnection( DB_REPLICA )->fieldExists(
  59                                 'change_tag',
  60                                 'ct_tag',
  61                                 __METHOD__
  62                         )
  63                 ) {
  64                         if ( !$this->hasOption( 'populate-only' ) ) {
  65                                 $this->updateCountTag();
  66                         }
  67                         $this->backpopulateChangeTagId();
  68                 } else {
  69                         $this->updateCountTagId();
  70                 }
  71
  72                 // TODO: Implement
  73                 // $this->cleanZeroCountRows();
  74
  75                 return true;
  76         }
  77
  78         private function updateCountTagId() {
  79                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
  80
  81                 // This query can be pretty expensive, don't run it on master
  82                 $res = $dbr->select(
  83                         'change_tag',
  84                         [ 'ct_tag_id', 'hitcount' => 'count(*)' ],
  85                         [],
  86                         __METHOD__,
  87                         [ 'GROUP BY' => 'ct_tag_id' ]
  88                 );
  89
  90                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
  91
  92                 foreach ( $res as $row ) {
  93                         if ( !$row->ct_tag_id ) {
  94                                 continue;
  95                         }
  96
  97                         if ( $this->hasOption( 'dry-run' ) ) {
  98                                 $this->output( 'This row will be updated: ' . implode( ', ', $row ) . "\n" );
  99                                 continue;
 100                         }
 101
 102                         $dbw->update(
 103                                 'change_tag_def',
 104                                 [ 'ctd_count' => $row->hitcount ],
 105                                 [ 'ctd_id' => $row->ct_tag_id ],
 106                                 __METHOD__
 107                         );
 108                 }
 109                 $this->lbFactory->waitForReplication();
 110         }
 111
 112         private function updateCountTag() {
 113                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
 114
 115                 // This query can be pretty expensive, don't run it on master
 116                 $res = $dbr->select(
 117                         'change_tag',
 118                         [ 'ct_tag', 'hitcount' => 'count(*)' ],
 119                         [],
 120                         __METHOD__,
 121                         [ 'GROUP BY' => 'ct_tag' ]
 122                 );
 123
 124                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
 125
 126                 foreach ( $res as $row ) {
 127                         // Hygiene check
 128                         if ( !$row->ct_tag ) {
 129                                 continue;
 130                         }
 131
 132                         if ( $this->hasOption( 'dry-run' ) ) {
 133                                 $this->output( 'This row will be updated: ' . $row->ct_tag . $row->hitcount . "\n" );
 134                                 continue;
 135                         }
 136
 137                         $dbw->upsert(
 138                                 'change_tag_def',
 139                                 [
 140                                         'ctd_name' => $row->ct_tag,
 141                                         'ctd_user_defined' => 0,
 142                                         'ctd_count' => $row->hitcount
 143                                 ],
 144                                 [ 'ctd_name' ],
 145                                 [ 'ctd_count' => $row->hitcount ],
 146                                 __METHOD__
 147                         );
 148                 }
 149                 $this->lbFactory->waitForReplication();
 150         }
 151
 152         private function backpopulateChangeTagId() {
 153                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
 154                 $changeTagDefs = $dbr->select(
 155                         'change_tag_def',
 156                         [ 'ctd_name', 'ctd_id' ],
 157                         [],
 158                         __METHOD__,
 159                         [ 'ORDER BY' => 'ctd_id' ]
 160                 );
 161
 162                 foreach ( $changeTagDefs as $row ) {
 163                         $this->backpopulateChangeTagPerTag( $row->ctd_name, $row->ctd_id );
 164                 }
 165         }
 166
 167         private function backpopulateChangeTagPerTag( $tagName, $tagId ) {
 168                 $dbr = $this->lbFactory->getMainLB()->getConnection( DB_REPLICA );
 169                 $dbw = $this->lbFactory->getMainLB()->getConnection( DB_MASTER );
 170                 $sleep = (int)$this->getOption( 'sleep', 10 );
 171                 $lastId = 0;
 172                 $this->output( "Starting to add ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 173                 while ( true ) {
 174                         // Given that indexes might not be there, it's better to use replica
 175                         $ids = $dbr->selectFieldValues(
 176                                 'change_tag',
 177                                 'ct_id',
 178                                 [ 'ct_tag' => $tagName, 'ct_tag_id' => null, 'ct_id > ' . $lastId ],
 179                                 __METHOD__,
 180                                 [ 'LIMIT' => $this->getBatchSize(), 'ORDER BY' => 'ct_id' ]
 181                         );
 182
 183                         if ( !$ids ) {
 184                                 break;
 185                         }
 186                         $lastId = end( $ids );
 187
 188                         if ( $this->hasOption( 'dry-run' ) ) {
 189                                 $this->output(
 190                                         "These ids will be changed to have \"{$tagId}\" as tag id: " . implode( ', ', $ids ) . "\n"
 191                                 );
 192                                 continue;
 193                         } else {
 194                                 $this->output( "Updating ct_tag_id = {$tagId} up to row ct_id = {$lastId}\n" );
 195                         }
 196
 197                         $dbw->update(
 198                                 'change_tag',
 199                                 [ 'ct_tag_id' => $tagId ],
 200                                 [ 'ct_id' => $ids ],
 201                                 __METHOD__
 202                         );
 203
 204                         $this->lbFactory->waitForReplication();
 205                         if ( $sleep > 0 ) {
 206                                 sleep( $sleep );
 207                         }
 208                 }
 209
 210                 $this->output( "Finished adding ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 211         }
 212
 213         protected function getUpdateKey() {
 214                 return __CLASS__;
 215         }
 216 }
 217
 218 $maintClass = PopulateChangeTagDef::class;
 219 require_once RUN_MAINTENANCE_IF_MAIN;