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 // @codeCoverageIgnoreStart
  20 require_once __DIR__ . '/Maintenance.php';
  21 // @codeCoverageIgnoreEnd
  22
  23 /**
  24  * Populate and improve accuracy of change_tag_def statistics.
  25  *
  26  * @ingroup Maintenance
  27  */
  28 class PopulateChangeTagDef extends LoggedUpdateMaintenance {
  29         public function __construct() {
  30                 parent::__construct();
  31                 $this->addDescription( 'Populate and improve accuracy of change_tag_def statistics' );
  32                 $this->addOption( 'dry-run', 'Print debug info instead of actually deleting' );
  33                 $this->setBatchSize( 1000 );
  34                 $this->addOption(
  35                         'sleep',
  36                         'Sleep time (in seconds) between every batch, defaults to zero',
  37                         false,
  38                         true
  39                 );
  40                 $this->addOption( 'populate-only', 'Do not update change_tag_def table' );
  41                 $this->addOption( 'set-user-tags-only', 'Only update ctd_user_defined from valid_tag table' );
  42         }
  43
  44         protected function doDBUpdates() {
  45                 $this->setBatchSize( $this->getOption( 'batch-size', $this->getBatchSize() ) );
  46
  47                 $dbw = $this->getDB( DB_PRIMARY );
  48                 if ( $dbw->fieldExists(
  49                                 'change_tag',
  50                                 'ct_tag',
  51                                 __METHOD__
  52                         )
  53                 ) {
  54                         if ( $this->hasOption( 'set-user-tags-only' ) ) {
  55                                 $this->setUserDefinedTags();
  56                                 return true;
  57                         }
  58                         if ( !$this->hasOption( 'populate-only' ) ) {
  59                                 $this->updateCountTag();
  60                         }
  61                         $this->backpopulateChangeTagId();
  62                         $this->setUserDefinedTags();
  63                 } else {
  64                         $this->updateCountTagId();
  65                 }
  66
  67                 // TODO: Implement
  68                 // $this->cleanZeroCountRows();
  69
  70                 return true;
  71         }
  72
  73         private function setUserDefinedTags() {
  74                 $dbw = $this->getDB( DB_PRIMARY );
  75
  76                 $userTags = null;
  77                 if ( $dbw->tableExists( 'valid_tag', __METHOD__ ) ) {
  78                         $userTags = $dbw->newSelectQueryBuilder()
  79                                 ->select( 'vt_tag' )
  80                                 ->from( 'valid_tag' )
  81                                 ->caller( __METHOD__ )->fetchFieldValues();
  82                 }
  83
  84                 if ( !$userTags ) {
  85                         $this->output( "No user defined tags to set, moving on...\n" );
  86                         return;
  87                 }
  88
  89                 if ( $this->hasOption( 'dry-run' ) ) {
  90                         $this->output(
  91                                 'These tags will have ctd_user_defined=1 : ' . implode( ', ', $userTags ) . "\n"
  92                         );
  93                         return;
  94                 }
  95
  96                 $dbw->newUpdateQueryBuilder()
  97                         ->update( 'change_tag_def' )
  98                         ->set( [ 'ctd_user_defined' => 1 ] )
  99                         ->where( [ 'ctd_name' => $userTags ] )
 100                         ->caller( __METHOD__ )
 101                         ->execute();
 102                 $this->waitForReplication();
 103                 $this->output( "Finished setting user defined tags in change_tag_def table\n" );
 104         }
 105
 106         private function updateCountTagId() {
 107                 $dbr = $this->getReplicaDB();
 108
 109                 // This query can be pretty expensive, don't run it on master
 110                 $res = $dbr->newSelectQueryBuilder()
 111                         ->select( [ 'ct_tag_id', 'hitcount' => 'count(*)' ] )
 112                         ->from( 'change_tag' )
 113                         ->groupBy( 'ct_tag_id' )
 114                         ->caller( __METHOD__ )->fetchResultSet();
 115
 116                 $dbw = $this->getPrimaryDB();
 117
 118                 foreach ( $res as $row ) {
 119                         if ( !$row->ct_tag_id ) {
 120                                 continue;
 121                         }
 122
 123                         if ( $this->hasOption( 'dry-run' ) ) {
 124                                 $this->output( 'This row will be updated: ' . implode( ', ', $row ) . "\n" );
 125                                 continue;
 126                         }
 127
 128                         $dbw->newUpdateQueryBuilder()
 129                                 ->update( 'change_tag_def' )
 130                                 ->set( [ 'ctd_count' => $row->hitcount ] )
 131                                 ->where( [ 'ctd_id' => $row->ct_tag_id ] )
 132                                 ->caller( __METHOD__ )
 133                                 ->execute();
 134                 }
 135                 $this->waitForReplication();
 136         }
 137
 138         private function updateCountTag() {
 139                 $dbr = $this->getReplicaDB();
 140
 141                 // This query can be pretty expensive, don't run it on master
 142                 $res = $dbr->newSelectQueryBuilder()
 143                         ->select( [ 'ct_tag', 'hitcount' => 'count(*)' ] )
 144                         ->from( 'change_tag' )
 145                         ->groupBy( 'ct_tag' )
 146                         ->caller( __METHOD__ )->fetchResultSet();
 147
 148                 $dbw = $this->getPrimaryDB();
 149
 150                 foreach ( $res as $row ) {
 151                         // Hygiene check
 152                         if ( !$row->ct_tag ) {
 153                                 continue;
 154                         }
 155
 156                         if ( $this->hasOption( 'dry-run' ) ) {
 157                                 $this->output( 'This row will be updated: ' . $row->ct_tag . $row->hitcount . "\n" );
 158                                 continue;
 159                         }
 160                         $dbw->newInsertQueryBuilder()
 161                                 ->insertInto( 'change_tag_def' )
 162                                 ->row( [
 163                                         'ctd_name' => $row->ct_tag,
 164                                         'ctd_user_defined' => 0,
 165                                         'ctd_count' => $row->hitcount
 166                                 ] )
 167                                 ->onDuplicateKeyUpdate()
 168                                 ->uniqueIndexFields( [ 'ctd_name' ] )
 169                                 ->set( [ 'ctd_count' => $row->hitcount ] )
 170                                 ->caller( __METHOD__ )->execute();
 171                 }
 172                 $this->waitForReplication();
 173         }
 174
 175         private function backpopulateChangeTagId() {
 176                 $dbr = $this->getReplicaDB();
 177                 $changeTagDefs = $dbr->newSelectQueryBuilder()
 178                         ->select( [ 'ctd_name', 'ctd_id' ] )
 179                         ->from( 'change_tag_def' )
 180                         ->orderBy( 'ctd_id' )
 181                         ->caller( __METHOD__ )->fetchResultSet();
 182
 183                 foreach ( $changeTagDefs as $row ) {
 184                         $this->backpopulateChangeTagPerTag( $row->ctd_name, $row->ctd_id );
 185                 }
 186         }
 187
 188         private function backpopulateChangeTagPerTag( $tagName, $tagId ) {
 189                 $dbr = $this->getReplicaDB();
 190                 $dbw = $this->getPrimaryDB();
 191                 $sleep = (int)$this->getOption( 'sleep', 0 );
 192                 $lastId = 0;
 193                 $this->output( "Starting to add ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 194                 while ( true ) {
 195                         // Given that indexes might not be there, it's better to use replica
 196                         $ids = $dbr->newSelectQueryBuilder()
 197                                 ->select( 'ct_id' )
 198                                 ->from( 'change_tag' )
 199                                 ->where( [ 'ct_tag' => $tagName, 'ct_tag_id' => null, $dbr->expr( 'ct_id', '>', $lastId ) ] )
 200                                 ->orderBy( 'ct_id' )
 201                                 ->limit( $this->getBatchSize() )
 202                                 ->caller( __METHOD__ )->fetchFieldValues();
 203
 204                         if ( !$ids ) {
 205                                 break;
 206                         }
 207                         $lastId = end( $ids );
 208
 209                         if ( $this->hasOption( 'dry-run' ) ) {
 210                                 $this->output(
 211                                         "These ids will be changed to have \"{$tagId}\" as tag id: " . implode( ', ', $ids ) . "\n"
 212                                 );
 213                                 continue;
 214                         } else {
 215                                 $this->output( "Updating ct_tag_id = {$tagId} up to row ct_id = {$lastId}\n" );
 216                         }
 217
 218                         $dbw->newUpdateQueryBuilder()
 219                                 ->update( 'change_tag' )
 220                                 ->set( [ 'ct_tag_id' => $tagId ] )
 221                                 ->where( [ 'ct_id' => $ids ] )
 222                                 ->caller( __METHOD__ )
 223                                 ->execute();
 224
 225                         $this->waitForReplication();
 226                         if ( $sleep > 0 ) {
 227                                 sleep( $sleep );
 228                         }
 229                 }
 230
 231                 $this->output( "Finished adding ct_tag_id = {$tagId} for ct_tag = {$tagName}\n" );
 232         }
 233
 234         protected function getUpdateKey() {
 235                 return __CLASS__;
 236         }
 237 }
 238
 239 // @codeCoverageIgnoreStart
 240 $maintClass = PopulateChangeTagDef::class;
 241 require_once RUN_MAINTENANCE_IF_MAIN;
 242 // @codeCoverageIgnoreEnd