MediaWiki  master
populateIpChanges.php
Go to the documentation of this file.
1 <?php
27 require_once __DIR__ . '/Maintenance.php';
28 
30 
39  public function __construct() {
40  parent::__construct();
41 
42  $this->addDescription( <<<TEXT
43 This script will find all rows in the revision table where the user is an IP,
44 and copy relevant fields to the ip_changes table. This backfilled data will
45 then be available when querying for IP ranges at Special:Contributions.
46 TEXT
47  );
48  $this->addOption( 'rev-id', 'The rev_id to start copying from. Default: 0', false, true );
49  $this->addOption(
50  'max-rev-id',
51  'The rev_id to stop at. Default: result of MAX(rev_id)',
52  false,
53  true
54  );
55  $this->addOption(
56  'throttle',
57  'Wait this many milliseconds after copying each batch of revisions. Default: 0',
58  false,
59  true
60  );
61  $this->addOption( 'force', 'Run regardless of whether the database says it\'s been run already' );
62  }
63 
64  public function doDBUpdates() {
65  $dbw = $this->getDB( DB_MASTER );
66 
67  if ( !$dbw->tableExists( 'ip_changes' ) ) {
68  $this->fatalError( 'ip_changes table does not exist' );
69  }
70 
71  $lbFactory = MediaWikiServices::getInstance()->getDBLoadBalancerFactory();
72  $dbr = $this->getDB( DB_REPLICA, [ 'vslow' ] );
73  $throttle = intval( $this->getOption( 'throttle', 0 ) );
74  $maxRevId = intval( $this->getOption( 'max-rev-id', 0 ) );
75  $start = $this->getOption( 'rev-id', 0 );
76  $end = $maxRevId > 0
77  ? $maxRevId
78  : $dbw->selectField( 'revision', 'MAX(rev_id)', '', __METHOD__ );
79 
80  if ( empty( $end ) ) {
81  $this->output( "No revisions found, aborting.\n" );
82  return true;
83  }
84 
85  $blockStart = $start;
86  $attempted = 0;
87  $inserted = 0;
88 
89  $this->output( "Copying IP revisions to ip_changes, from rev_id $start to rev_id $end\n" );
90 
91  $actorMigration = ActorMigration::newMigration();
92  $actorQuery = $actorMigration->getJoin( 'rev_user' );
93  $revUserIsAnon = $actorMigration->isAnon( $actorQuery['fields']['rev_user'] );
94 
95  while ( $blockStart <= $end ) {
96  $blockEnd = min( $blockStart + $this->getBatchSize(), $end );
97  $rows = $dbr->select(
98  [ 'revision' ] + $actorQuery['tables'],
99  [ 'rev_id', 'rev_timestamp', 'rev_user_text' => $actorQuery['fields']['rev_user_text'] ],
100  [ "rev_id BETWEEN " . (int)$blockStart . " AND " . (int)$blockEnd, $revUserIsAnon ],
101  __METHOD__,
102  [],
103  $actorQuery['joins']
104  );
105 
106  $numRows = $rows->numRows();
107 
108  if ( !$rows || $numRows === 0 ) {
109  $blockStart = $blockEnd + 1;
110  continue;
111  }
112 
113  $this->output( "...checking $numRows revisions for IP edits that need copying, " .
114  "between rev_ids $blockStart and $blockEnd\n" );
115 
116  $insertRows = [];
117  foreach ( $rows as $row ) {
118  // Make sure this is really an IP, e.g. not maintenance user or imported revision.
119  if ( IP::isValid( $row->rev_user_text ) ) {
120  $insertRows[] = [
121  'ipc_rev_id' => $row->rev_id,
122  'ipc_rev_timestamp' => $row->rev_timestamp,
123  'ipc_hex' => IP::toHex( $row->rev_user_text ),
124  ];
125 
126  $attempted++;
127  }
128  }
129 
130  if ( $insertRows ) {
131  $dbw->insert( 'ip_changes', $insertRows, __METHOD__, [ 'IGNORE' ] );
132 
133  $inserted += $dbw->affectedRows();
134  }
135 
136  $lbFactory->waitForReplication();
137  usleep( $throttle * 1000 );
138 
139  $blockStart = $blockEnd + 1;
140  }
141 
142  $this->output( "Attempted to insert $attempted IP revisions, $inserted actually done.\n" );
143 
144  return true;
145  }
146 
147  protected function getUpdateKey() {
148  return 'populate ip_changes';
149  }
150 }
151 
153 require_once RUN_MAINTENANCE_IF_MAIN;
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 copy
Definition: LICENSE.txt:10
and how to run hooks for an and one after Each event has a preferably in CamelCase For ArticleDelete hook A clump of code and data that should be run when an event happens This can be either a function and a chunk of data
Definition: hooks.txt:6
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:2633
static toHex( $ip)
Return a zero-padded upper case hexadecimal representation of an IP address.
Definition: IP.php:404
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
getOption( $name, $default=null)
Get an option, or return the default.
wiki Special
null for the local wiki Added in
Definition: hooks.txt:1585
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
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
const DB_MASTER
Definition: defines.php:26
This document provides an overview of the usage of PageUpdater and that is
Definition: pageupdater.txt:3
static newMigration()
Static constructor.
static isValid( $ip)
Validate an IP address.
Definition: IP.php:111
addDescription( $text)
Set the description text.
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 and we might be restricted by PHP settings such as safe mode or open_basedir We cannot assume that the software even has read access anywhere useful Many shared hosts run all users web applications under the same user
Wikitext formatted, in the key only.
Definition: distributors.txt:9
Maintenance script that will find all rows in the revision table where rev_user = 0 (user is an IP)...
and(b) You must cause any modified files to carry prominent notices stating that You changed the files
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
output( $out, $channel=null)
Throw some output to the user.
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
Class for scripts that perform database maintenance and want to log the update in updatelog so we can...
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 then executing the whole list after the page is displayed We don t do anything smart like collating updates to the same table or such because the list is almost always going to have just one item on if so it s not worth the trouble Since there is a job queue in the jobs table
Definition: deferred.txt:11
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
getBatchSize()
Returns batch size.
In both all secondary updates will be triggered handle like object that caches derived data representing a revision
Definition: pageupdater.txt:78
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
const DB_REPLICA
Definition: defines.php:25
</td >< td > &</td >< td > t want your writing to be edited mercilessly and redistributed at will
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
skin txt MediaWiki includes four core it has been set as the default in MediaWiki since the replacing Monobook it had been the default skin since then
Definition: skin.txt:10