MediaWiki  1.28.0
updateSearchIndex.php
Go to the documentation of this file.
1 <?php
31 require_once __DIR__ . '/Maintenance.php';
32 
39 
40  public function __construct() {
41  parent::__construct();
42  $this->addDescription( 'Script for periodic off-peak updating of the search index' );
43  $this->addOption( 's', 'starting timestamp', false, true );
44  $this->addOption( 'e', 'Ending timestamp', false, true );
45  $this->addOption(
46  'p',
47  'File for saving/loading timestamps, searchUpdate.WIKI_ID.pos by default',
48  false,
49  true
50  );
51  $this->addOption(
52  'l',
53  'How long the searchindex and revision tables will be locked for',
54  false,
55  true
56  );
57  }
58 
59  public function getDbType() {
60  return Maintenance::DB_ADMIN;
61  }
62 
63  public function execute() {
64  $posFile = $this->getOption( 'p', 'searchUpdate.' . wfWikiID() . '.pos' );
65  $end = $this->getOption( 'e', wfTimestampNow() );
66  if ( $this->hasOption( 's' ) ) {
67  $start = $this->getOption( 's' );
68  } elseif ( is_readable( 'searchUpdate.pos' ) ) {
69  # B/c to the old position file name which was hardcoded
70  # We can safely delete the file when we're done though.
71  $start = file_get_contents( 'searchUpdate.pos' );
72  unlink( 'searchUpdate.pos' );
73  } elseif ( is_readable( $posFile ) ) {
74  $start = file_get_contents( $posFile );
75  } else {
76  $start = wfTimestamp( TS_MW, time() - 86400 );
77  }
78  $lockTime = $this->getOption( 'l', 20 );
79 
80  $this->doUpdateSearchIndex( $start, $end, $lockTime );
81  if ( is_writable( dirname( realpath( $posFile ) ) ) ) {
82  $file = fopen( $posFile, 'w' );
83  if ( $file !== false ) {
84  fwrite( $file, $end );
85  fclose( $file );
86  } else {
87  $this->error( "*** Couldn't write to the $posFile!\n" );
88  }
89  } else {
90  $this->error( "*** Couldn't write to the $posFile!\n" );
91  }
92  }
93 
94  private function doUpdateSearchIndex( $start, $end, $maxLockTime ) {
95  global $wgDisableSearchUpdate;
96 
97  $wgDisableSearchUpdate = false;
98 
99  $dbw = $this->getDB( DB_MASTER );
100  $recentchanges = $dbw->tableName( 'recentchanges' );
101 
102  $this->output( "Updating searchindex between $start and $end\n" );
103 
104  # Select entries from recentchanges which are on top and between the specified times
105  $start = $dbw->timestamp( $start );
106  $end = $dbw->timestamp( $end );
107 
108  $page = $dbw->tableName( 'page' );
109  $sql = "SELECT rc_cur_id FROM $recentchanges
110  JOIN $page ON rc_cur_id=page_id AND rc_this_oldid=page_latest
111  WHERE rc_type != " . RC_LOG . " AND rc_timestamp BETWEEN '$start' AND '$end'";
112  $res = $dbw->query( $sql, __METHOD__ );
113 
114  $this->updateSearchIndex( $maxLockTime, [ $this, 'searchIndexUpdateCallback' ], $dbw, $res );
115 
116  $this->output( "Done\n" );
117  }
118 
119  public function searchIndexUpdateCallback( $dbw, $row ) {
120  $this->updateSearchIndexForPage( $dbw, $row->rc_cur_id );
121  }
122 }
123 
124 $maintClass = "UpdateSearchIndex";
125 require_once RUN_MAINTENANCE_IF_MAIN;
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
getDB($db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
hasOption($name)
Checks to see if a particular param exists.
Maintenance script for periodic off-peak updating of the search index.
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
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
wfTimestamp($outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
addOption($name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
updateSearchIndex($maxLockTime, $callback, $dbw, $results)
Perform a search index update with locking.
$res
Definition: database.txt:21
const DB_ADMIN
Definition: Maintenance.php:59
wfTimestampNow()
Convenience function; returns MediaWiki timestamp for the present time.
searchIndexUpdateCallback($dbw, $row)
const TS_MW
MediaWiki concatenated string timestamp (YYYYMMDDHHMMSS)
Definition: defines.php:11
wfWikiID()
Get an ASCII string identifying this wiki This is used as a prefix in memcached keys.
addDescription($text)
Set the description text.
getOption($name, $default=null)
Get an option, or return the default.
output($out, $channel=null)
Throw some output to the user.
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 $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
doUpdateSearchIndex($start, $end, $maxLockTime)
error($err, $die=0)
Throw an error to the user.
updateSearchIndexForPage($dbw, $pageId)
Update the searchindex table for a given pageid.
do that in ParserLimitReportFormat instead use this to modify the parameters of the image and a DIV can begin in one section and end in another Make sure your code can handle that case gracefully See the EditSectionClearerLink extension for an example zero but section is usually empty its values are the globals values before the output is cached $page
Definition: hooks.txt:2491
const RC_LOG
Definition: Defines.php:138