MediaWiki  1.23.15
updateCollation.php
Go to the documentation of this file.
1 <?php
27 #$optionsWithArgs = array( 'begin', 'max-slave-lag' );
28 
29 require_once __DIR__ . '/Maintenance.php';
30 
38  const BATCH_SIZE = 10000; // Number of rows to process in one batch
39  const SYNC_INTERVAL = 20; // Wait for slaves after this many batches
40 
41  public $sizeHistogram = array();
42 
43  public function __construct() {
44  parent::__construct();
45 
46  global $wgCategoryCollation;
47  $this->mDescription = <<<TEXT
48 This script will find all rows in the categorylinks table whose collation is
49 out-of-date (cl_collation != '$wgCategoryCollation') and repopulate cl_sortkey
50 using the page title and cl_sortkey_prefix. If all collations are
51 up-to-date, it will do nothing.
52 TEXT;
53 
54  $this->addOption( 'force', 'Run on all rows, even if the collation is ' .
55  'supposed to be up-to-date.' );
56  $this->addOption( 'previous-collation', 'Set the previous value of ' .
57  '$wgCategoryCollation here to speed up this script, especially if your ' .
58  'categorylinks table is large. This will only update rows with that ' .
59  'collation, though, so it may miss out-of-date rows with a different, ' .
60  'even older collation.', false, true );
61  $this->addOption( 'target-collation', 'Set this to the new collation type to ' .
62  'use instead of $wgCategoryCollation. Usually you should not use this, ' .
63  'you should just update $wgCategoryCollation in LocalSettings.php.',
64  false, true );
65  $this->addOption( 'dry-run', 'Don\'t actually change the collations, just ' .
66  'compile statistics.' );
67  $this->addOption( 'verbose-stats', 'Show more statistics.' );
68  }
69 
70  public function execute() {
71  global $wgCategoryCollation;
72 
73  $dbw = $this->getDB( DB_MASTER );
74  $force = $this->getOption( 'force' );
75  $dryRun = $this->getOption( 'dry-run' );
76  $verboseStats = $this->getOption( 'verbose-stats' );
77  if ( $this->hasOption( 'target-collation' ) ) {
78  $collationName = $this->getOption( 'target-collation' );
79  $collation = Collation::factory( $collationName );
80  } else {
81  $collationName = $wgCategoryCollation;
82  $collation = Collation::singleton();
83  }
84 
85  // Collation sanity check: in some cases the constructor will work,
86  // but this will raise an exception, breaking all category pages
87  $collation->getFirstLetter( 'MediaWiki' );
88 
89  $options = array(
90  'LIMIT' => self::BATCH_SIZE,
91  'ORDER BY' => 'cl_to, cl_type, cl_from',
92  'STRAIGHT_JOIN',
93  );
94 
95  if ( $force || $dryRun ) {
96  $collationConds = array();
97  } else {
98  if ( $this->hasOption( 'previous-collation' ) ) {
99  $collationConds['cl_collation'] = $this->getOption( 'previous-collation' );
100  } else {
101  $collationConds = array( 0 =>
102  'cl_collation != ' . $dbw->addQuotes( $collationName )
103  );
104  }
105 
106  $count = $dbw->estimateRowCount(
107  'categorylinks',
108  '*',
109  $collationConds,
110  __METHOD__
111  );
112  // Improve estimate if feasible
113  if ( $count < 1000000 ) {
114  $count = $dbw->selectField(
115  'categorylinks',
116  'COUNT(*)',
117  $collationConds,
118  __METHOD__
119  );
120  }
121  if ( $count == 0 ) {
122  $this->output( "Collations up-to-date.\n" );
123  return;
124  }
125  $this->output( "Fixing collation for $count rows.\n" );
126  }
127 
128  $count = 0;
129  $batchCount = 0;
130  $batchConds = array();
131  do {
132  $this->output( "Selecting next " . self::BATCH_SIZE . " rows..." );
133  $res = $dbw->select(
134  array( 'categorylinks', 'page' ),
135  array( 'cl_from', 'cl_to', 'cl_sortkey_prefix', 'cl_collation',
136  'cl_sortkey', 'cl_type', 'page_namespace', 'page_title'
137  ),
138  array_merge( $collationConds, $batchConds, array( 'cl_from = page_id' ) ),
139  __METHOD__,
140  $options
141  );
142  $this->output( " processing..." );
143 
144  if ( !$dryRun ) {
145  $dbw->begin( __METHOD__ );
146  }
147  foreach ( $res as $row ) {
148  $title = Title::newFromRow( $row );
149  if ( !$row->cl_collation ) {
150  # This is an old-style row, so the sortkey needs to be
151  # converted.
152  if ( $row->cl_sortkey == $title->getText()
153  || $row->cl_sortkey == $title->getPrefixedText() ) {
154  $prefix = '';
155  } else {
156  # Custom sortkey, use it as a prefix
157  $prefix = $row->cl_sortkey;
158  }
159  } else {
160  $prefix = $row->cl_sortkey_prefix;
161  }
162  # cl_type will be wrong for lots of pages if cl_collation is 0,
163  # so let's update it while we're here.
164  if ( $title->getNamespace() == NS_CATEGORY ) {
165  $type = 'subcat';
166  } elseif ( $title->getNamespace() == NS_FILE ) {
167  $type = 'file';
168  } else {
169  $type = 'page';
170  }
171  $newSortKey = $collation->getSortKey(
172  $title->getCategorySortkey( $prefix ) );
173  if ( $verboseStats ) {
174  $this->updateSortKeySizeHistogram( $newSortKey );
175  }
176 
177  if ( !$dryRun ) {
178  $dbw->update(
179  'categorylinks',
180  array(
181  'cl_sortkey' => $newSortKey,
182  'cl_sortkey_prefix' => $prefix,
183  'cl_collation' => $collationName,
184  'cl_type' => $type,
185  'cl_timestamp = cl_timestamp',
186  ),
187  array( 'cl_from' => $row->cl_from, 'cl_to' => $row->cl_to ),
188  __METHOD__
189  );
190  }
191  if ( $row ) {
192  $batchConds = array( $this->getBatchCondition( $row, $dbw ) );
193  }
194  }
195  if ( !$dryRun ) {
196  $dbw->commit( __METHOD__ );
197  }
198 
199  $count += $res->numRows();
200  $this->output( "$count done.\n" );
201 
202  if ( !$dryRun && ++$batchCount % self::SYNC_INTERVAL == 0 ) {
203  $this->output( "Waiting for slaves ... " );
204  wfWaitForSlaves();
205  $this->output( "done\n" );
206  }
207  } while ( $res->numRows() == self::BATCH_SIZE );
208 
209  $this->output( "$count rows processed\n" );
210 
211  if ( $verboseStats ) {
212  $this->output( "\n" );
213  $this->showSortKeySizeHistogram();
214  }
215  }
216 
221  function getBatchCondition( $row, $dbw ) {
222  $fields = array( 'cl_to', 'cl_type', 'cl_from' );
223  $first = true;
224  $cond = false;
225  $prefix = false;
226  foreach ( $fields as $field ) {
227  $encValue = $dbw->addQuotes( $row->$field );
228  $inequality = "$field > $encValue";
229  $equality = "$field = $encValue";
230  if ( $first ) {
231  $cond = $inequality;
232  $prefix = $equality;
233  $first = false;
234  } else {
235  $cond .= " OR ($prefix AND $inequality)";
236  $prefix .= " AND $equality";
237  }
238  }
239  return $cond;
240  }
241 
242  function updateSortKeySizeHistogram( $key ) {
243  $length = strlen( $key );
244  if ( !isset( $this->sizeHistogram[$length] ) ) {
245  $this->sizeHistogram[$length] = 0;
246  }
247  $this->sizeHistogram[$length]++;
248  }
249 
251  $maxLength = max( array_keys( $this->sizeHistogram ) );
252  if ( $maxLength == 0 ) {
253  return;
254  }
255  $numBins = 20;
256  $coarseHistogram = array_fill( 0, $numBins, 0 );
257  $coarseBoundaries = array();
258  $boundary = 0;
259  for ( $i = 0; $i < $numBins - 1; $i++ ) {
260  $boundary += $maxLength / $numBins;
261  $coarseBoundaries[$i] = round( $boundary );
262  }
263  $coarseBoundaries[$numBins - 1] = $maxLength + 1;
264  $raw = '';
265  for ( $i = 0; $i <= $maxLength; $i++ ) {
266  if ( $raw !== '' ) {
267  $raw .= ', ';
268  }
269  if ( !isset( $this->sizeHistogram[$i] ) ) {
270  $val = 0;
271  } else {
272  $val = $this->sizeHistogram[$i];
273  }
274  for ( $coarseIndex = 0; $coarseIndex < $numBins - 1; $coarseIndex++ ) {
275  if ( $coarseBoundaries[$coarseIndex] > $i ) {
276  $coarseHistogram[$coarseIndex] += $val;
277  break;
278  }
279  }
280  if ( $coarseIndex == $numBins - 1 ) {
281  $coarseHistogram[$coarseIndex] += $val;
282  }
283  $raw .= $val;
284  }
285 
286  $this->output( "Sort key size histogram\nRaw data: $raw\n\n" );
287 
288  $maxBinVal = max( $coarseHistogram );
289  $scale = 60 / $maxBinVal;
290  $prevBoundary = 0;
291  for ( $coarseIndex = 0; $coarseIndex < $numBins; $coarseIndex++ ) {
292  if ( !isset( $coarseHistogram[$coarseIndex] ) ) {
293  $val = 0;
294  } else {
295  $val = $coarseHistogram[$coarseIndex];
296  }
297  $boundary = $coarseBoundaries[$coarseIndex];
298  $this->output( sprintf( "%-10s %-10d |%s\n",
299  $prevBoundary . '-' . ( $boundary - 1 ) . ': ',
300  $val,
301  str_repeat( '*', $scale * $val ) ) );
302  $prevBoundary = $boundary;
303  }
304  }
305 }
306 
307 $maintClass = "UpdateCollation";
308 require_once RUN_MAINTENANCE_IF_MAIN;
DB_MASTER
const DB_MASTER
Definition: Defines.php:56
of
globals txt Globals are evil The original MediaWiki code relied on globals for processing context far too often MediaWiki development since then has been a story of slowly moving context out of global variables and into objects Storing processing context in object member variables allows those objects to be reused in a much more flexible way Consider the elegance of
Definition: globals.txt:10
UpdateCollation\SYNC_INTERVAL
const SYNC_INTERVAL
Definition: updateCollation.php:39
php
skin txt MediaWiki includes four core it has been set as the default in MediaWiki since the replacing Monobook it had been been the default skin since before being replaced by Vector largely rewritten in while keeping its appearance Several legacy skins were removed in the as the burden of supporting them became too heavy to bear Those in etc for skin dependent CSS etc for skin dependent JavaScript These can also be customised on a per user by etc This feature has led to a wide variety of user styles becoming that gallery is a good place to ending in php
Definition: skin.txt:62
is
We use the convention $dbr for read and $dbw for write to help you keep track of whether the database object is a the world will explode Or to be a subsequent write query which succeeded on the master may fail when replicated to the slave due to a unique key collision Replication on the slave will stop and it may take hours to repair the database and get it back online Setting read_only in my cnf on the slave will avoid this but given the dire we prefer to have as many checks as possible We provide a but the wrapper functions like please read the documentation for except in special pages derived from QueryPage It s a common pitfall for new developers to submit code containing SQL queries which examine huge numbers of rows Remember that COUNT * is(N), counting rows in atable is like counting beans in a bucket.------------------------------------------------------------------------ Replication------------------------------------------------------------------------The largest installation of MediaWiki, Wikimedia, uses a large set ofslave MySQL servers replicating writes made to a master MySQL server. Itis important to understand the issues associated with this setup if youwant to write code destined for Wikipedia.It 's often the case that the best algorithm to use for a given taskdepends on whether or not replication is in use. Due to our unabashedWikipedia-centrism, we often just use the replication-friendly version, but if you like, you can use wfGetLB() ->getServerCount() > 1 tocheck to see if replication is in use.===Lag===Lag primarily occurs when large write queries are sent to the master.Writes on the master are executed in parallel, but they are executed inserial when they are replicated to the slaves. The master writes thequery to the binlog when the transaction is committed. The slaves pollthe binlog and start executing the query as soon as it appears. They canservice reads while they are performing a write query, but will not readanything more from the binlog and thus will perform no more writes. Thismeans that if the write query runs for a long time, the slaves will lagbehind the master for the time it takes for the write query to complete.Lag can be exacerbated by high read load. MediaWiki 's load balancer willstop sending reads to a slave when it is lagged by more than 30 seconds.If the load ratios are set incorrectly, or if there is too much loadgenerally, this may lead to a slave permanently hovering around 30seconds lag.If all slaves are lagged by more than 30 seconds, MediaWiki will stopwriting to the database. All edits and other write operations will berefused, with an error returned to the user. This gives the slaves achance to catch up. Before we had this mechanism, the slaves wouldregularly lag by several minutes, making review of recent editsdifficult.In addition to this, MediaWiki attempts to ensure that the user seesevents occurring on the wiki in chronological order. A few seconds of lagcan be tolerated, as long as the user sees a consistent picture fromsubsequent requests. This is done by saving the master binlog positionin the session, and then at the start of each request, waiting for theslave to catch up to that position before doing any reads from it. Ifthis wait times out, reads are allowed anyway, but the request isconsidered to be in "lagged slave mode". Lagged slave mode can bechecked by calling wfGetLB() ->getLaggedSlaveMode(). The onlypractical consequence at present is a warning displayed in the pagefooter.===Lag avoidance===To avoid excessive lag, queries which write large numbers of rows shouldbe split up, generally to write one row at a time. Multi-row INSERT ...SELECT queries are the worst offenders should be avoided altogether.Instead do the select first and then the insert.===Working with lag===Despite our best efforts, it 's not practical to guarantee a low-lagenvironment. Lag will usually be less than one second, but mayoccasionally be up to 30 seconds. For scalability, it 's very importantto keep load on the master low, so simply sending all your queries tothe master is not the answer. So when you have a genuine need forup-to-date data, the following approach is advised:1) Do a quick query to the master for a sequence number or timestamp 2) Run the full query on the slave and check if it matches the data you gotfrom the master 3) If it doesn 't, run the full query on the masterTo avoid swamping the master every time the slaves lag, use of thisapproach should be kept to a minimum. In most cases you should just readfrom the slave and let the user deal with the delay.------------------------------------------------------------------------ Lock contention------------------------------------------------------------------------Due to the high write rate on Wikipedia(and some other wikis), MediaWiki developers need to be very careful to structure their writesto avoid long-lasting locks. By default, MediaWiki opens a transactionat the first query, and commits it before the output is sent. Locks willbe held from the time when the query is done until the commit. So youcan reduce lock time by doing as much processing as possible before youdo your write queries.Often this approach is not good enough, and it becomes necessary toenclose small groups of queries in their own transaction. Use thefollowing syntax:$dbw=wfGetDB(DB_MASTER
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false)
Add a parameter to the script.
Definition: Maintenance.php:169
$maintClass
$maintClass
Definition: updateCollation.php:302
NS_FILE
const NS_FILE
Definition: Defines.php:85
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
UpdateCollation\__construct
__construct()
Default constructor.
Definition: updateCollation.php:43
UpdateCollation\BATCH_SIZE
const BATCH_SIZE
Definition: updateCollation.php:38
Collation\singleton
static singleton()
Definition: Collation.php:29
title
to move a page</td >< td > &*You are moving the page across *A non empty talk page already exists under the new or *You uncheck the box below In those you will have to move or merge the page manually if desired</td >< td > be sure to &You are responsible for making sure that links continue to point where they are supposed to go Note that the page will &a page at the new title
Definition: All_system_messages.txt:2703
Maintenance\getDB
& getDB( $db, $groups=array(), $wiki=false)
Returns a database to be used by current maintenance script.
Definition: Maintenance.php:1007
UpdateCollation\getBatchCondition
getBatchCondition( $row, $dbw)
Return an SQL expression selecting rows which sort above the given row, assuming an ordering of cl_to...
Definition: updateCollation.php:221
table
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
Title\newFromRow
static newFromRow( $row)
Make a Title object from a DB row.
Definition: Title.php:345
array
the array() calling protocol came about after MediaWiki 1.4rc1.
List of Api Query prop modules.
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:93
NS_CATEGORY
const NS_CATEGORY
Definition: Defines.php:93
wfWaitForSlaves
wfWaitForSlaves( $maxLag=false, $wiki=false, $cluster=false)
Modern version of wfWaitForSlaves().
Definition: GlobalFunctions.php:3859
will
</td >< td > &</td >< td > t want your writing to be edited mercilessly and redistributed at will
Definition: All_system_messages.txt:914
$options
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped & $options
Definition: hooks.txt:1530
UpdateCollation\execute
execute()
Do the actual work.
Definition: updateCollation.php:70
UpdateCollation\updateSortKeySizeHistogram
updateSortKeySizeHistogram( $key)
Definition: updateCollation.php:242
$title
presenting them properly to the user as errors is done by the caller $title
Definition: hooks.txt:1324
UpdateCollation\showSortKeySizeHistogram
showSortKeySizeHistogram()
Definition: updateCollation.php:250
up
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title after the basic globals have been set up
Definition: hooks.txt:1684
$count
$count
Definition: UtfNormalTest2.php:96
it
=Architecture==Two class hierarchies are used to provide the functionality associated with the different content models:*Content interface(and AbstractContent base class) define functionality that acts on the concrete content of a page, and *ContentHandler base class provides functionality specific to a content model, but not acting on concrete content. The most important function of ContentHandler is to act as a factory for the appropriate implementation of Content. These Content objects are to be used by MediaWiki everywhere, instead of passing page content around as text. All manipulation and analysis of page content must be done via the appropriate methods of the Content object. For each content model, a subclass of ContentHandler has to be registered with $wgContentHandlers. The ContentHandler object for a given content model can be obtained using ContentHandler::getForModelID($id). Also Title, WikiPage and Revision now have getContentHandler() methods for convenience. ContentHandler objects are singletons that provide functionality specific to the content type, but not directly acting on the content of some page. ContentHandler::makeEmptyContent() and ContentHandler::unserializeContent() can be used to create a Content object of the appropriate type. However, it is recommended to instead use WikiPage::getContent() resp. Revision::getContent() to get a page 's content as a Content object. These two methods should be the ONLY way in which page content is accessed. Another important function of ContentHandler objects is to define custom action handlers for a content model, see ContentHandler::getActionOverrides(). This is similar to what WikiPage::getActionOverrides() was already doing.==Serialization==With the ContentHandler facility, page content no longer has to be text based. Objects implementing the Content interface are used to represent and handle the content internally. For storage and data exchange, each content model supports at least one serialization format via ContentHandler::serializeContent($content). The list of supported formats for a given content model can be accessed using ContentHandler::getSupportedFormats(). Content serialization formats are identified using MIME type like strings. The following formats are built in:*text/x-wiki - wikitext *text/javascript - for js pages *text/css - for css pages *text/plain - for future use, e.g. with plain text messages. *text/html - for future use, e.g. with plain html messages. *application/vnd.php.serialized - for future use with the api and for extensions *application/json - for future use with the api, and for use by extensions *application/xml - for future use with the api, and for use by extensions In PHP, use the corresponding CONTENT_FORMAT_XXX constant. Note that when using the API to access page content, especially action=edit, action=parse and action=query &prop=revisions, the model and format of the content should always be handled explicitly. Without that information, interpretation of the provided content is not reliable. The same applies to XML dumps generated via maintenance/dumpBackup.php or Special:Export. Also note that the API will provide encapsulated, serialized content - so if the API was called with format=json, and contentformat is also json(or rather, application/json), the page content is represented as a string containing an escaped json structure. Extensions that use JSON to serialize some types of page content may provide specialized API modules that allow access to that content in a more natural form.==Compatibility==The ContentHandler facility is introduced in a way that should allow all existing code to keep functioning at least for pages that contain wikitext or other text based content. However, a number of functions and hooks have been deprecated in favor of new versions that are aware of the page 's content model, and will now generate warnings when used. Most importantly, the following functions have been deprecated:*Revisions::getText() and Revisions::getRawText() is deprecated in favor Revisions::getContent() *WikiPage::getText() is deprecated in favor WikiPage::getContent() Also, the old Article::getContent()(which returns text) is superceded by Article::getContentObject(). However, both methods should be avoided since they do not provide clean access to the page 's actual content. For instance, they may return a system message for non-existing pages. Use WikiPage::getContent() instead. Code that relies on a textual representation of the page content should eventually be rewritten. However, ContentHandler::getContentText() provides a stop-gap that can be used to get text for a page. Its behavior is controlled by $wgContentHandlerTextFallback it
Definition: contenthandler.txt:107
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:191
in
Prior to maintenance scripts were a hodgepodge of code that had no cohesion or formal method of action Beginning in
Definition: maintenance.txt:1
are
The ContentHandler facility adds support for arbitrary content types on wiki instead of relying on wikitext for everything It was introduced in MediaWiki Each kind of and so on Built in content types are
Definition: contenthandler.txt:5
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\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:314
Collation\factory
static factory( $collationName)
Definition: Collation.php:42
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular param exists.
Definition: Maintenance.php:181
$res
$res
Definition: database.txt:21
UpdateCollation\$sizeHistogram
$sizeHistogram
Definition: updateCollation.php:41
page
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 my talk page
Definition: hooks.txt:1961
UpdateCollation
Maintenance script that will find all rows in the categorylinks table whose collation is out-of-date.
Definition: updateCollation.php:37
$type
$type
Definition: testCompression.php:46