MediaWiki  1.28.0
RecentChangesUpdateJob.php
Go to the documentation of this file.
1 <?php
23 
30 class RecentChangesUpdateJob extends Job {
32  parent::__construct( 'recentChangesUpdate', $title, $params );
33 
34  if ( !isset( $params['type'] ) ) {
35  throw new Exception( "Missing 'type' parameter." );
36  }
37 
38  $this->removeDuplicates = true;
39  }
40 
44  final public static function newPurgeJob() {
45  return new self(
46  SpecialPage::getTitleFor( 'Recentchanges' ), [ 'type' => 'purge' ]
47  );
48  }
49 
54  final public static function newCacheUpdateJob() {
55  return new self(
56  SpecialPage::getTitleFor( 'Recentchanges' ), [ 'type' => 'cacheUpdate' ]
57  );
58  }
59 
60  public function run() {
61  if ( $this->params['type'] === 'purge' ) {
62  $this->purgeExpiredRows();
63  } elseif ( $this->params['type'] === 'cacheUpdate' ) {
64  $this->updateActiveUsers();
65  } else {
66  throw new InvalidArgumentException(
67  "Invalid 'type' parameter '{$this->params['type']}'." );
68  }
69 
70  return true;
71  }
72 
73  protected function purgeExpiredRows() {
74  global $wgRCMaxAge, $wgUpdateRowsPerQuery;
75 
76  $lockKey = wfWikiID() . ':recentchanges-prune';
77 
78  $dbw = wfGetDB( DB_MASTER );
79  if ( !$dbw->lockIsFree( $lockKey, __METHOD__ )
80  || !$dbw->lock( $lockKey, __METHOD__, 1 )
81  ) {
82  return; // already in progress
83  }
84 
85  $factory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
86  $ticket = $factory->getEmptyTransactionTicket( __METHOD__ );
87  $cutoff = $dbw->timestamp( time() - $wgRCMaxAge );
88  do {
89  $rcIds = $dbw->selectFieldValues( 'recentchanges',
90  'rc_id',
91  [ 'rc_timestamp < ' . $dbw->addQuotes( $cutoff ) ],
92  __METHOD__,
93  [ 'LIMIT' => $wgUpdateRowsPerQuery ]
94  );
95  if ( $rcIds ) {
96  $dbw->delete( 'recentchanges', [ 'rc_id' => $rcIds ], __METHOD__ );
97  // There might be more, so try waiting for replica DBs
98  try {
99  $factory->commitAndWaitForReplication(
100  __METHOD__, $ticket, [ 'timeout' => 3 ]
101  );
102  } catch ( DBReplicationWaitError $e ) {
103  // Another job will continue anyway
104  break;
105  }
106  }
107  } while ( $rcIds );
108 
109  $dbw->unlock( $lockKey, __METHOD__ );
110  }
111 
112  protected function updateActiveUsers() {
113  global $wgActiveUserDays;
114 
115  // Users that made edits at least this many days ago are "active"
116  $days = $wgActiveUserDays;
117  // Pull in the full window of active users in this update
118  $window = $wgActiveUserDays * 86400;
119 
120  $dbw = wfGetDB( DB_MASTER );
121  // JobRunner uses DBO_TRX, but doesn't call begin/commit itself;
122  // onTransactionIdle() will run immediately since there is no trx.
123  $dbw->onTransactionIdle(
124  function () use ( $dbw, $days, $window ) {
125  $factory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
126  $ticket = $factory->getEmptyTransactionTicket( __METHOD__ );
127  // Avoid disconnect/ping() cycle that makes locks fall off
128  $dbw->setSessionOptions( [ 'connTimeout' => 900 ] );
129 
130  $lockKey = wfWikiID() . '-activeusers';
131  if ( !$dbw->lock( $lockKey, __METHOD__, 1 ) ) {
132  return; // exclusive update (avoids duplicate entries)
133  }
134 
135  $nowUnix = time();
136  // Get the last-updated timestamp for the cache
137  $cTime = $dbw->selectField( 'querycache_info',
138  'qci_timestamp',
139  [ 'qci_type' => 'activeusers' ]
140  );
141  $cTimeUnix = $cTime ? wfTimestamp( TS_UNIX, $cTime ) : 1;
142 
143  // Pick the date range to fetch from. This is normally from the last
144  // update to till the present time, but has a limited window for sanity.
145  // If the window is limited, multiple runs are need to fully populate it.
146  $sTimestamp = max( $cTimeUnix, $nowUnix - $days * 86400 );
147  $eTimestamp = min( $sTimestamp + $window, $nowUnix );
148 
149  // Get all the users active since the last update
150  $res = $dbw->select(
151  [ 'recentchanges' ],
152  [ 'rc_user_text', 'lastedittime' => 'MAX(rc_timestamp)' ],
153  [
154  'rc_user > 0', // actual accounts
155  'rc_type != ' . $dbw->addQuotes( RC_EXTERNAL ), // no wikidata
156  'rc_log_type IS NULL OR rc_log_type != ' . $dbw->addQuotes( 'newusers' ),
157  'rc_timestamp >= ' . $dbw->addQuotes( $dbw->timestamp( $sTimestamp ) ),
158  'rc_timestamp <= ' . $dbw->addQuotes( $dbw->timestamp( $eTimestamp ) )
159  ],
160  __METHOD__,
161  [
162  'GROUP BY' => [ 'rc_user_text' ],
163  'ORDER BY' => 'NULL' // avoid filesort
164  ]
165  );
166  $names = [];
167  foreach ( $res as $row ) {
168  $names[$row->rc_user_text] = $row->lastedittime;
169  }
170 
171  // Rotate out users that have not edited in too long (according to old data set)
172  $dbw->delete( 'querycachetwo',
173  [
174  'qcc_type' => 'activeusers',
175  'qcc_value < ' . $dbw->addQuotes( $nowUnix - $days * 86400 ) // TS_UNIX
176  ],
177  __METHOD__
178  );
179 
180  // Find which of the recently active users are already accounted for
181  if ( count( $names ) ) {
182  $res = $dbw->select( 'querycachetwo',
183  [ 'user_name' => 'qcc_title' ],
184  [
185  'qcc_type' => 'activeusers',
186  'qcc_namespace' => NS_USER,
187  'qcc_title' => array_keys( $names ) ],
188  __METHOD__
189  );
190  foreach ( $res as $row ) {
191  unset( $names[$row->user_name] );
192  }
193  }
194 
195  // Insert the users that need to be added to the list
196  if ( count( $names ) ) {
197  $newRows = [];
198  foreach ( $names as $name => $lastEditTime ) {
199  $newRows[] = [
200  'qcc_type' => 'activeusers',
201  'qcc_namespace' => NS_USER,
202  'qcc_title' => $name,
203  'qcc_value' => wfTimestamp( TS_UNIX, $lastEditTime ),
204  'qcc_namespacetwo' => 0, // unused
205  'qcc_titletwo' => '' // unused
206  ];
207  }
208  foreach ( array_chunk( $newRows, 500 ) as $rowBatch ) {
209  $dbw->insert( 'querycachetwo', $rowBatch, __METHOD__ );
210  $factory->commitAndWaitForReplication( __METHOD__, $ticket );
211  }
212  }
213 
214  // If a transaction was already started, it might have an old
215  // snapshot, so kludge the timestamp range back as needed.
216  $asOfTimestamp = min( $eTimestamp, (int)$dbw->trxTimestamp() );
217 
218  // Touch the data freshness timestamp
219  $dbw->replace( 'querycache_info',
220  [ 'qci_type' ],
221  [ 'qci_type' => 'activeusers',
222  'qci_timestamp' => $dbw->timestamp( $asOfTimestamp ) ], // not always $now
223  __METHOD__
224  );
225 
226  $dbw->unlock( $lockKey, __METHOD__ );
227  },
228  __METHOD__
229  );
230  }
231 }
wfGetDB($db, $groups=[], $wiki=false)
Get a Database object.
the array() calling protocol came about after MediaWiki 1.4rc1.
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
static getTitleFor($name, $subpage=false, $fragment= '')
Get a localised Title object for a specified special page name If you don't need a full Title object...
Definition: SpecialPage.php:82
div flags Integer display flags(NO_ACTION_LINK, NO_EXTRA_USER_LINKS) 'LogException'returning false will NOT prevent logging $e
Definition: hooks.txt:2102
Class to both describe a background job and handle jobs.
Definition: Job.php:31
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency MediaWikiServices
Definition: injection.txt:23
when a variable name is used in a it is silently declared as a new local masking the global
Definition: design.txt:93
const DB_MASTER
Definition: defines.php:23
const TS_UNIX
Unix time - the number of seconds since 1970-01-01 00:00:00 UTC.
Definition: defines.php:6
wfTimestamp($outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
Exception class for replica DB wait timeouts.
$res
Definition: database.txt:21
wfWikiID()
Get an ASCII string identifying this wiki This is used as a prefix in memcached keys.
__construct(Title $title, array $params)
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:9
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
array $params
Array of job parameters.
Definition: Job.php:36
const RC_EXTERNAL
Definition: Defines.php:139
Title $title
Definition: Job.php:42
Job for pruning recent changes.
Allows to change the fields on the form that will be generated $name
Definition: hooks.txt:300