Go to the documentation of this file.
26 require_once __DIR__ .
'/Maintenance.php';
40 parent::__construct();
42 $this->
addOption(
'dfn-only',
'Delete links from nonexistent articles only' );
43 $this->
addOption(
'new-only',
'Only affect articles with just a single edit' );
44 $this->
addOption(
'redirects-only',
'Only fix redirects, not all links' );
45 $this->
addOption(
'old-redirects-only',
'Only fix redirects with no redirect table entry' );
46 $this->
addOption(
'e',
'Last page id to refresh',
false,
true );
47 $this->
addOption(
'dfn-chunk-size',
'Maximum number of existent IDs to check per ' .
48 'query, default 100000',
false,
true );
49 $this->
addOption(
'namespace',
'Only fix pages in this namespace',
false,
true );
50 $this->
addOption(
'category',
'Only fix pages in this category',
false,
true );
51 $this->
addOption(
'tracking-category',
'Only fix pages in this tracking category',
false,
true );
52 $this->
addArg(
'start',
'Page_id to start from, default 1',
false );
61 $start = (int)$this->
getArg( 0 ) ?:
null;
62 $end = (int)$this->
getOption(
'e' ) ?:
null;
63 $dfnChunkSize = (int)$this->
getOption(
'dfn-chunk-size', 100000 );
66 $this->
namespace =
false;
68 $this->
namespace = (int)$ns;
70 if ( ( $category = $this->
getOption(
'category',
false ) ) !==
false ) {
73 $this->
error(
"'$category' is an invalid category name!\n",
true );
76 } elseif ( ( $category = $this->
getOption(
'tracking-category',
false ) ) !==
false ) {
78 } elseif ( !$this->
hasOption(
'dfn-only' ) ) {
80 $redir = $this->
hasOption(
'redirects-only' );
81 $oldRedir = $this->
hasOption(
'old-redirects-only' );
90 return $this->
namespace !==
false
104 $end =
null, $redirectsOnly =
false, $oldRedirectsOnly =
false
108 if ( $start ===
null ) {
113 Hooks::run(
'MaintenanceRefreshLinksInit', [ $this ] );
115 $what = $redirectsOnly ?
"redirects" :
"links";
117 if ( $oldRedirectsOnly ) {
118 # This entire code path is cut-and-pasted from below. Hurrah.
121 "page_is_redirect=1",
127 [
'page',
'redirect' ],
132 [
'redirect' => [
"LEFT JOIN",
"page_id=rd_from" ] ]
134 $num =
$res->numRows();
135 $this->
output(
"Refreshing $num old redirects from $start...\n" );
139 foreach (
$res as $row ) {
146 } elseif ( $newOnly ) {
147 $this->
output(
"Refreshing $what from " );
152 self::intervalCond(
$dbr,
'page_id', $start, $end ),
156 $num =
$res->numRows();
157 $this->
output(
"$num new articles...\n" );
160 foreach (
$res as $row ) {
165 if ( $redirectsOnly ) {
173 $maxPage =
$dbr->selectField(
'page',
'max(page_id)',
false );
174 $maxRD =
$dbr->selectField(
'redirect',
'max(rd_from)',
false );
175 $end = max( $maxPage, $maxRD );
177 $this->
output(
"Refreshing redirects table.\n" );
178 $this->
output(
"Starting from page_id $start of $end.\n" );
180 for ( $id = $start; $id <= $end; $id++ ) {
188 if ( !$redirectsOnly ) {
189 $this->
output(
"Refreshing links tables.\n" );
190 $this->
output(
"Starting from page_id $start of $end.\n" );
192 for ( $id = $start; $id <= $end; $id++ ) {
219 if ( $page ===
null ) {
222 $dbw->delete(
'redirect', [
'rd_from' => $id ],
226 } elseif ( $this->
namespace !==
false
227 && !$page->getTitle()->inNamespace( $this->
namespace )
234 if ( $content !==
null ) {
235 $rt = $content->getUltimateRedirectTarget();
238 if ( $rt ===
null ) {
241 $dbw->delete(
'redirect', [
'rd_from' => $id ], __METHOD__ );
244 $page->insertRedirectEntry( $rt );
249 $dbw->update(
'page', [
'page_is_redirect' => $fieldValue ],
250 [
'page_id' => $id ], __METHOD__ );
263 if ( $page ===
null ) {
265 } elseif ( $ns !==
false
266 && !$page->getTitle()->inNamespace( $ns ) ) {
271 if ( $content ===
null ) {
275 $updates = $content->getSecondaryDataUpdates(
276 $page->getTitle(),
null,
false );
277 foreach ( $updates
as $update ) {
298 $this->
output(
"Deleting illegal entries from the links tables...\n" );
303 $nextStart =
$dbr->selectField(
306 [ self::intervalCond(
$dbr,
'page_id', $start, $end ) ]
309 [
'ORDER BY' =>
'page_id',
'OFFSET' => $chunkSize ]
312 if ( $nextStart !==
false ) {
317 $chunkEnd = $nextStart - 1;
323 $fmtStart = $start !==
null ?
"[$start" :
'(-INF';
324 $fmtChunkEnd = $chunkEnd !==
null ?
"$chunkEnd]" :
'INF)';
325 $this->
output(
" Checking interval $fmtStart, $fmtChunkEnd\n" );
330 }
while ( $nextStart !==
false );
344 'pagelinks' =>
'pl_from',
345 'imagelinks' =>
'il_from',
346 'categorylinks' =>
'cl_from',
347 'templatelinks' =>
'tl_from',
348 'externallinks' =>
'el_from',
349 'iwlinks' =>
'iwl_from',
350 'langlinks' =>
'll_from',
351 'redirect' =>
'rd_from',
352 'page_props' =>
'pp_page',
355 foreach ( $linksTables
as $table => $field ) {
356 $this->
output(
" $table: 0" );
357 $tableStart = $start;
360 $ids =
$dbr->selectFieldValues(
364 self::intervalCond(
$dbr, $field, $tableStart, $end ),
365 "$field NOT IN ({$dbr->selectSQLText( 'page', 'page_id' )})",
368 [
'DISTINCT',
'ORDER BY' => $field,
'LIMIT' => $batchSize ]
371 $numIds =
count( $ids );
374 $dbw->delete( $table, [ $field => $ids ], __METHOD__ );
375 $this->
output(
", $counter" );
376 $tableStart = $ids[$numIds - 1] + 1;
380 }
while ( $numIds >= $batchSize && ( $end ===
null || $tableStart <= $end ) );
382 $this->
output(
" deleted.\n" );
399 if ( $start ===
null && $end ===
null ) {
400 return "$var IS NOT NULL";
401 } elseif ( $end ===
null ) {
402 return "$var >= {$db->addQuotes( $start )}";
403 } elseif ( $start ===
null ) {
404 return "$var <= {$db->addQuotes( $end )}";
406 return "$var BETWEEN {$db->addQuotes( $start )} AND {$db->addQuotes( $end )}";
419 $this->
error(
"Tracking category '$category' is disabled\n" );
423 foreach ( $cats
as $cat ) {
434 $this->
output(
"Refreshing pages in category '{$category->getText()}'...\n" );
441 if ( $this->
namespace !==
false ) {
449 $finalConds = $conds;
450 $timestamp =
$dbr->addQuotes( $timestamp );
452 "(cl_timestamp > $timestamp OR (cl_timestamp = $timestamp AND cl_from > $lastId))";
453 $res =
$dbr->select( [
'page',
'categorylinks' ],
454 [
'page_id',
'cl_timestamp' ],
458 'ORDER BY' => [
'cl_timestamp',
'cl_from' ],
459 'LIMIT' => $this->mBatchSize,
463 foreach (
$res as $row ) {
468 $lastId = $row->page_id;
469 $timestamp = $row->cl_timestamp;
484 $cats = $trackingCategories->getTrackingCategories();
485 if ( isset( $cats[$categoryKey] ) ) {
486 return $cats[$categoryKey][
'cats'];
488 $this->
error(
"Unknown tracking category {$categoryKey}\n",
true );
int $mBatchSize
Batch size.
processing should stop and the error should be shown to the user * false
refreshTrackingCategory( $category)
Refershes links for pages in a tracking category.
dfnCheckInterval( $start=null, $end=null, $batchSize=100)
__construct()
Default constructor.
addDescription( $text)
Set the description text.
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
static addUpdate(DeferrableUpdate $update, $stage=self::POSTSEND)
Add an update to the deferred list to be run later by execute()
require_once RUN_MAINTENANCE_IF_MAIN
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
wfWaitForSlaves( $ifWritesSince=null, $wiki=false, $cluster=false, $timeout=null)
Waits for the replica DBs to catch up to the master position.
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
getDBkey()
Get the main part with underscores.
namespace and then decline to actually register it file or subcat img or subcat $title
static intervalCond(IDatabase $db, $var, $start, $end)
Build a SQL expression for a closed interval (i.e.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Maintenance script to refresh link tables.
refreshCategory(Title $category)
Refreshes links to a category.
static makeTitleSafe( $ns, $title, $fragment='', $interwiki='')
Create a new Title from a namespace index and a DB key.
getPossibleCategories( $categoryKey)
Returns a list of possible categories for a given tracking category key.
doRefreshLinks( $start, $newOnly=false, $end=null, $redirectsOnly=false, $oldRedirectsOnly=false)
Do the actual link refreshing.
static newFromID( $id, $from='fromdb')
Constructor from a page id.
static doUpdates( $mode='run', $stage=self::ALL)
Do any deferred updates and clear the list.
This class performs some operations related to tracking categories, such as creating a list of all su...
static fixLinksFromArticle( $id, $ns=false)
Run LinksUpdate for all links on a given page_id.
Represents a title within MediaWiki.
deleteLinksFromNonexistent( $start=null, $end=null, $batchSize=100, $chunkSize=100000)
Removes non-existing links from pages from pagelinks, imagelinks, categorylinks, templatelinks,...
getOption( $name, $default=null)
Get an option, or return the default.
static singleton()
Get an instance of this class.
addArg( $arg, $description, $required=true)
Add some args that are needed.
fixRedirect( $id)
Update the redirect entry for a given page.
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
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
execute()
Do the actual work.
error( $err, $die=0)
Throw an error to the user.
output( $out, $channel=null)
Throw some output to the user.
hasOption( $name)
Checks to see if a particular param exists.
getArg( $argId=0, $default=null)
Get an argument.
static run( $event, array $args=[], $deprecatedVersion=null)
Call hook functions defined in Hooks::register and $wgHooks.
setBatchSize( $s=0)
Set the batch size.