MediaWiki  1.33.0
purgeChangedPages.php
Go to the documentation of this file.
1 <?php
24 require_once __DIR__ . '/Maintenance.php';
25 
27 
38 
39  public function __construct() {
40  parent::__construct();
41  $this->addDescription( 'Send purge requests for edits in date range to squid/varnish' );
42  $this->addOption( 'starttime', 'Starting timestamp', true, true );
43  $this->addOption( 'endtime', 'Ending timestamp', true, true );
44  $this->addOption( 'htcp-dest', 'HTCP announcement destination (IP:port)', false, true );
45  $this->addOption( 'sleep-per-batch', 'Milliseconds to sleep between batches', false, true );
46  $this->addOption( 'dry-run', 'Do not send purge requests' );
47  $this->addOption( 'verbose', 'Show more output', false, false, 'v' );
48  $this->setBatchSize( 100 );
49  }
50 
51  public function execute() {
52  global $wgHTCPRouting;
53 
54  if ( $this->hasOption( 'htcp-dest' ) ) {
55  $parts = explode( ':', $this->getOption( 'htcp-dest' ), 2 );
56  if ( count( $parts ) < 2 ) {
57  // Add default htcp port
58  $parts[] = '4827';
59  }
60 
61  // Route all HTCP messages to provided host:port
62  $wgHTCPRouting = [
63  '' => [ 'host' => $parts[0], 'port' => $parts[1] ],
64  ];
65  if ( $this->hasOption( 'verbose' ) ) {
66  $this->output( "HTCP broadcasts to {$parts[0]}:{$parts[1]}\n" );
67  }
68  }
69 
70  $dbr = $this->getDB( DB_REPLICA );
71  $minTime = $dbr->timestamp( $this->getOption( 'starttime' ) );
72  $maxTime = $dbr->timestamp( $this->getOption( 'endtime' ) );
73 
74  if ( $maxTime < $minTime ) {
75  $this->error( "\nERROR: starttime after endtime\n" );
76  $this->maybeHelp( true );
77  }
78 
79  $stuckCount = 0; // loop breaker
80  while ( true ) {
81  // Adjust bach size if we are stuck in a second that had many changes
82  $bSize = ( $stuckCount + 1 ) * $this->getBatchSize();
83 
84  $res = $dbr->select(
85  [ 'page', 'revision' ],
86  [
87  'rev_timestamp',
88  'page_namespace',
89  'page_title',
90  ],
91  [
92  "rev_timestamp > " . $dbr->addQuotes( $minTime ),
93  "rev_timestamp <= " . $dbr->addQuotes( $maxTime ),
94  // Only get rows where the revision is the latest for the page.
95  // Other revisions would be duplicate and we don't need to purge if
96  // there has been an edit after the interesting time window.
97  "page_latest = rev_id",
98  ],
99  __METHOD__,
100  [ 'ORDER BY' => 'rev_timestamp', 'LIMIT' => $bSize ],
101  [
102  'page' => [ 'JOIN', 'rev_page=page_id' ],
103  ]
104  );
105 
106  if ( !$res->numRows() ) {
107  // nothing more found so we are done
108  break;
109  }
110 
111  // Kludge to not get stuck in loops for batches with the same timestamp
112  list( $rows, $lastTime ) = $this->pageableSortedRows( $res, 'rev_timestamp', $bSize );
113  if ( !count( $rows ) ) {
114  ++$stuckCount;
115  continue;
116  }
117  // Reset suck counter
118  $stuckCount = 0;
119 
120  $this->output( "Processing changes from {$minTime} to {$lastTime}.\n" );
121 
122  // Advance past the last row next time
123  $minTime = $lastTime;
124 
125  // Create list of URLs from page_namespace + page_title
126  $urls = [];
127  foreach ( $rows as $row ) {
128  $title = Title::makeTitle( $row->page_namespace, $row->page_title );
129  $urls[] = $title->getInternalURL();
130  }
131 
132  if ( $this->hasOption( 'dry-run' ) || $this->hasOption( 'verbose' ) ) {
133  $this->output( implode( "\n", $urls ) . "\n" );
134  if ( $this->hasOption( 'dry-run' ) ) {
135  continue;
136  }
137  }
138 
139  // Send batch of purge requests out to squids
140  $squid = new CdnCacheUpdate( $urls, count( $urls ) );
141  $squid->doUpdate();
142 
143  if ( $this->hasOption( 'sleep-per-batch' ) ) {
144  // sleep-per-batch is milliseconds, usleep wants micro seconds.
145  usleep( 1000 * (int)$this->getOption( 'sleep-per-batch' ) );
146  }
147  }
148 
149  $this->output( "Done!\n" );
150  }
151 
171  protected function pageableSortedRows( ResultWrapper $res, $column, $limit ) {
172  $rows = iterator_to_array( $res, false );
173 
174  // Nothing to do
175  if ( !$rows ) {
176  return [ [], null ];
177  }
178 
179  $lastValue = end( $rows )->$column;
180  if ( count( $rows ) < $limit ) {
181  return [ $rows, $lastValue ];
182  }
183 
184  for ( $i = count( $rows ) - 1; $i >= 0; --$i ) {
185  if ( $rows[$i]->$column !== $lastValue ) {
186  break;
187  }
188 
189  unset( $rows[$i] );
190  }
191 
192  // No more rows left
193  if ( !$rows ) {
194  return [ [], null ];
195  }
196 
197  return [ $rows, end( $rows )->$column ];
198  }
199 }
200 
202 require_once RUN_MAINTENANCE_IF_MAIN;
Maintenance\maybeHelp
maybeHelp( $force=false)
Maybe show the help.
Definition: Maintenance.php:1043
captcha-old.count
count
Definition: captcha-old.py:249
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:329
PurgeChangedPages\pageableSortedRows
pageableSortedRows(ResultWrapper $res, $column, $limit)
Remove all the rows in a result set with the highest value for column $column unless the number of ro...
Definition: purgeChangedPages.php:171
PurgeChangedPages\execute
execute()
Do the actual work.
Definition: purgeChangedPages.php:51
PurgeChangedPages\__construct
__construct()
Default constructor.
Definition: purgeChangedPages.php:39
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
$res
$res
Definition: database.txt:21
Wikimedia\Rdbms\ResultWrapper
Result wrapper for grabbing data queried from an IDatabase object.
Definition: ResultWrapper.php:24
Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
PurgeChangedPages
Maintenance script that sends purge requests for pages edited in a date range to squid/varnish.
Definition: purgeChangedPages.php:37
php
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
$dbr
$dbr
Definition: testCompression.php:50
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:925
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:248
$wgHTCPRouting
$wgHTCPRouting
Routing configuration for HTCP multicast purging.
Definition: DefaultSettings.php:2876
use
as see the revision history and available at free of to any person obtaining a copy of this software and associated documentation to deal in the Software without including without limitation the rights to use
Definition: MIT-LICENSE.txt:10
Title\makeTitle
static makeTitle( $ns, $title, $fragment='', $interwiki='')
Create a new Title from a namespace index and a DB key.
Definition: Title.php:576
DB_REPLICA
const DB_REPLICA
Definition: defines.php:25
list
deferred txt A few of the database updates required by various functions here can be deferred until after the result page is displayed to the user For updating the view updating the linked to tables after a etc PHP does not yet have any way to tell the server to actually return and disconnect while still running these but it might have such a feature in the future We handle these by creating a deferred update object and putting those objects on a global list
Definition: deferred.txt:11
null
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that When $user is not null
Definition: hooks.txt:780
$maintClass
$maintClass
Definition: purgeChangedPages.php:201
CdnCacheUpdate
Handles purging appropriate CDN URLs given a title (or titles)
Definition: CdnCacheUpdate.php:30
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:283
$rows
do that in ParserLimitReportFormat instead use this to modify the parameters of the image all existing parser cache entries will be invalid To avoid you ll need to handle that somehow(e.g. with the RejectParserCacheValue hook) because MediaWiki won 't do it for you. & $defaults also a ContextSource after deleting those rows but within the same transaction $rows
Definition: hooks.txt:2636
Maintenance\getBatchSize
getBatchSize()
Returns batch size.
Definition: Maintenance.php:367
as
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
Maintenance\getDB
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
Definition: Maintenance.php:1373
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:462
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:434
class
you have access to all of the normal MediaWiki so you can get a DB use the etc For full docs on the Maintenance class
Definition: maintenance.txt:52
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular option exists.
Definition: Maintenance.php:269
Maintenance\setBatchSize
setBatchSize( $s=0)
Set the batch size.
Definition: Maintenance.php:375