MediaWiki  1.30.0
dumpIterator.php
Go to the documentation of this file.
1 <?php
29 require_once __DIR__ . '/Maintenance.php';
30 
36 abstract class DumpIterator extends Maintenance {
37 
38  private $count = 0;
39  private $startTime;
40 
41  public function __construct() {
42  parent::__construct();
43  $this->addDescription( 'Does something with a dump' );
44  $this->addOption( 'file', 'File with text to run.', false, true );
45  $this->addOption( 'dump', 'XML dump to execute all revisions.', false, true );
46  $this->addOption( 'from', 'Article from XML dump to start from.', false, true );
47  }
48 
49  public function execute() {
50  if ( !( $this->hasOption( 'file' ) ^ $this->hasOption( 'dump' ) ) ) {
51  $this->error( "You must provide a file or dump", true );
52  }
53 
54  $this->checkOptions();
55 
56  if ( $this->hasOption( 'file' ) ) {
57  $revision = new WikiRevision( $this->getConfig() );
58 
59  $revision->setText( file_get_contents( $this->getOption( 'file' ) ) );
60  $revision->setTitle( Title::newFromText(
61  rawurldecode( basename( $this->getOption( 'file' ), '.txt' ) )
62  ) );
63  $this->handleRevision( $revision );
64 
65  return;
66  }
67 
68  $this->startTime = microtime( true );
69 
70  if ( $this->getOption( 'dump' ) == '-' ) {
71  $source = new ImportStreamSource( $this->getStdin() );
72  } else {
73  $this->error( "Sorry, I don't support dump filenames yet. "
74  . "Use - and provide it on stdin on the meantime.", true );
75  }
76  $importer = new WikiImporter( $source, $this->getConfig() );
77 
78  $importer->setRevisionCallback(
79  [ $this, 'handleRevision' ] );
80 
81  $this->from = $this->getOption( 'from', null );
82  $this->count = 0;
83  $importer->doImport();
84 
85  $this->conclusions();
86 
87  $delta = microtime( true ) - $this->startTime;
88  $this->error( "Done {$this->count} revisions in " . round( $delta, 2 ) . " seconds " );
89  if ( $delta > 0 ) {
90  $this->error( round( $this->count / $delta, 2 ) . " pages/sec" );
91  }
92 
93  # Perform the memory_get_peak_usage() when all the other data has been
94  # output so there's no damage if it dies. It is only available since
95  # 5.2.0 (since 5.2.1 if you haven't compiled with --enable-memory-limit)
96  $this->error( "Memory peak usage of " . memory_get_peak_usage() . " bytes\n" );
97  }
98 
99  public function finalSetup() {
100  parent::finalSetup();
101 
102  if ( $this->getDbType() == Maintenance::DB_NONE ) {
104  $wgUseDatabaseMessages = false;
105  $wgLocalisationCacheConf['storeClass'] = 'LCStoreNull';
106  $wgHooks['InterwikiLoadPrefix'][] = 'DumpIterator::disableInterwikis';
107  }
108  }
109 
110  static function disableInterwikis( $prefix, &$data ) {
111  # Title::newFromText will check on each namespaced article if it's an interwiki.
112  # We always answer that it is not.
113 
114  return false;
115  }
116 
122  public function handleRevision( $rev ) {
123  $title = $rev->getTitle();
124  if ( !$title ) {
125  $this->error( "Got bogus revision with null title!" );
126 
127  return;
128  }
129 
130  $this->count++;
131  if ( isset( $this->from ) ) {
132  if ( $this->from != $title ) {
133  return;
134  }
135  $this->output( "Skipped " . ( $this->count - 1 ) . " pages\n" );
136 
137  $this->count = 1;
138  $this->from = null;
139  }
140 
141  $this->processRevision( $rev );
142  }
143 
144  /* Stub function for processing additional options */
145  public function checkOptions() {
146  return;
147  }
148 
149  /* Stub function for giving data about what was computed */
150  public function conclusions() {
151  return;
152  }
153 
154  /* Core function which does whatever the maintenance script is designed to do */
155  abstract public function processRevision( $rev );
156 }
157 
163 class SearchDump extends DumpIterator {
164 
165  public function __construct() {
166  parent::__construct();
167  $this->addDescription( 'Runs a regex in the revisions from a dump' );
168  $this->addOption( 'regex', 'Searching regex', true, true );
169  }
170 
171  public function getDbType() {
172  return Maintenance::DB_NONE;
173  }
174 
178  public function processRevision( $rev ) {
179  if ( preg_match( $this->getOption( 'regex' ), $rev->getContent()->getTextForSearchIndex() ) ) {
180  $this->output( $rev->getTitle() . " matches at edit from " . $rev->getTimestamp() . "\n" );
181  }
182  }
183 }
184 
185 $maintClass = "SearchDump";
186 require_once RUN_MAINTENANCE_IF_MAIN;
WikiImporter
XML file reader for the page data importer.
Definition: WikiImporter.php:34
Title\newFromText
static newFromText( $text, $defaultNamespace=NS_MAIN)
Create a new Title from text, such as what one would find in a link.
Definition: Title.php:268
DumpIterator\__construct
__construct()
Default constructor.
Definition: dumpIterator.php:41
Maintenance\getStdin
getStdin( $len=null)
Return input from stdin.
Definition: Maintenance.php:346
Maintenance\getDbType
getDbType()
Does the script need different DB access? By default, we give Maintenance scripts normal rights to th...
Definition: Maintenance.php:459
DumpIterator\handleRevision
handleRevision( $rev)
Callback function for each revision, child classes should override processRevision instead.
Definition: dumpIterator.php:122
SearchDump\getDbType
getDbType()
Does the script need different DB access? By default, we give Maintenance scripts normal rights to th...
Definition: dumpIterator.php:171
captcha-old.count
count
Definition: captcha-old.py:249
SearchDump\processRevision
processRevision( $rev)
Definition: dumpIterator.php:178
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:287
$maintClass
$maintClass
Definition: dumpIterator.php:185
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
ImportStreamSource
Imports a XML dump from a file (either from file upload, files on disk, or HTTP)
Definition: ImportStreamSource.php:32
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
DumpIterator\execute
execute()
Do the actual work.
Definition: dumpIterator.php:49
DumpIterator\$startTime
$startTime
Definition: dumpIterator.php:39
DumpIterator\processRevision
processRevision( $rev)
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:932
Maintenance\getConfig
getConfig()
Definition: Maintenance.php:504
SearchDump
Maintenance script that runs a regex in the revisions from a dump.
Definition: dumpIterator.php:163
DumpIterator\$count
$count
Definition: dumpIterator.php:38
SearchDump\__construct
__construct()
Default constructor.
Definition: dumpIterator.php:165
$wgUseDatabaseMessages
$wgUseDatabaseMessages
Translation using MediaWiki: namespace.
Definition: DefaultSettings.php:3017
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:215
$wgLocalisationCacheConf
$wgLocalisationCacheConf
Localisation cache configuration.
Definition: DefaultSettings.php:2511
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:93
DumpIterator\checkOptions
checkOptions()
Definition: dumpIterator.php:145
DumpIterator\disableInterwikis
static disableInterwikis( $prefix, &$data)
Definition: dumpIterator.php:110
Maintenance\DB_NONE
const DB_NONE
Constants for DB access type.
Definition: Maintenance.php:62
DumpIterator
Base class for interating over a dump.
Definition: dumpIterator.php:36
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:250
WikiRevision
Represents a revision, log entry or upload during the import process.
Definition: WikiRevision.php:35
$wgHooks
$wgHooks['ArticleShow'][]
Definition: hooks.txt:108
$rev
presenting them properly to the user as errors is done by the caller return true use this to change the list i e etc $rev
Definition: hooks.txt:1750
from
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for and distribution as defined by Sections through of this document Licensor shall mean the copyright owner or entity authorized by the copyright owner that is granting the License Legal Entity shall mean the union of the acting entity and all other entities that control are controlled by or are under common control with that entity For the purposes of this definition control direct or to cause the direction or management of such whether by contract or including but not limited to software source documentation and configuration files Object form shall mean any form resulting from mechanical transformation or translation of a Source including but not limited to compiled object generated and conversions to other media types Work shall mean the work of whether in Source or Object made available under the as indicated by a copyright notice that is included in or attached to the whether in Source or Object that is based or other modifications as a an original work of authorship For the purposes of this Derivative Works shall not include works that remain separable from
Definition: APACHE-LICENSE-2.0.txt:43
$source
$source
Definition: mwdoc-filter.php:46
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:392
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:373
DumpIterator\finalSetup
finalSetup()
Handle some last-minute setup here.
Definition: dumpIterator.php:99
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular param exists.
Definition: Maintenance.php:236
DumpIterator\conclusions
conclusions()
Definition: dumpIterator.php:150