MediaWiki  1.23.14
upgradeLogging.php
Go to the documentation of this file.
1 <?php
24 require __DIR__ . '/../commandLine.inc';
25 
33 
37  public $dbw;
38  public $batchSize = 1000;
39  public $minTs = false;
40 
41  function execute() {
42  $this->dbw = wfGetDB( DB_MASTER );
43  $logging = $this->dbw->tableName( 'logging' );
44  $logging_1_10 = $this->dbw->tableName( 'logging_1_10' );
45  $logging_pre_1_10 = $this->dbw->tableName( 'logging_pre_1_10' );
46 
47  if ( $this->dbw->tableExists( 'logging_pre_1_10' ) && !$this->dbw->tableExists( 'logging' ) ) {
48  # Fix previous aborted run
49  echo "Cleaning up from previous aborted run\n";
50  $this->dbw->query( "RENAME TABLE $logging_pre_1_10 TO $logging", __METHOD__ );
51  }
52 
53  if ( $this->dbw->tableExists( 'logging_pre_1_10' ) ) {
54  echo "This script has already been run to completion\n";
55  return;
56  }
57 
58  # Create the target table
59  if ( !$this->dbw->tableExists( 'logging_1_10' ) ) {
60  global $wgDBTableOptions;
61 
62  $sql = <<<EOT
63 CREATE TABLE $logging_1_10 (
64  -- Log ID, for referring to this specific log entry, probably for deletion and such.
65  log_id int unsigned NOT NULL auto_increment,
66 
67  -- Symbolic keys for the general log type and the action type
68  -- within the log. The output format will be controlled by the
69  -- action field, but only the type controls categorization.
70  log_type varbinary(10) NOT NULL default '',
71  log_action varbinary(10) NOT NULL default '',
72 
73  -- Timestamp. Duh.
74  log_timestamp binary(14) NOT NULL default '19700101000000',
75 
76  -- The user who performed this action; key to user_id
77  log_user int unsigned NOT NULL default 0,
78 
79  -- Key to the page affected. Where a user is the target,
80  -- this will point to the user page.
81  log_namespace int NOT NULL default 0,
82  log_title varchar(255) binary NOT NULL default '',
83 
84  -- Freeform text. Interpreted as edit history comments.
85  log_comment varchar(255) NOT NULL default '',
86 
87  -- LF separated list of miscellaneous parameters
88  log_params blob NOT NULL,
89 
90  -- rev_deleted for logs
91  log_deleted tinyint unsigned NOT NULL default '0',
92 
93  PRIMARY KEY log_id (log_id),
94  KEY type_time (log_type, log_timestamp),
95  KEY user_time (log_user, log_timestamp),
96  KEY page_time (log_namespace, log_title, log_timestamp),
97  KEY times (log_timestamp)
98 
99 ) $wgDBTableOptions
100 EOT;
101  echo "Creating table logging_1_10\n";
102  $this->dbw->query( $sql, __METHOD__ );
103  }
104 
105  # Synchronise the tables
106  echo "Doing initial sync...\n";
107  $this->sync( 'logging', 'logging_1_10' );
108  echo "Sync done\n\n";
109 
110  # Rename the old table away
111  echo "Renaming the old table to $logging_pre_1_10\n";
112  $this->dbw->query( "RENAME TABLE $logging TO $logging_pre_1_10", __METHOD__ );
113 
114  # Copy remaining old rows
115  # Done before the new table is active so that $copyPos is accurate
116  echo "Doing final sync...\n";
117  $this->sync( 'logging_pre_1_10', 'logging_1_10' );
118 
119  # Move the new table in
120  echo "Moving the new table in...\n";
121  $this->dbw->query( "RENAME TABLE $logging_1_10 TO $logging", __METHOD__ );
122  echo "Finished.\n";
123  }
124 
128  function sync( $srcTable, $dstTable ) {
129  $batchSize = 1000;
130  $minTs = $this->dbw->selectField( $srcTable, 'MIN(log_timestamp)', false, __METHOD__ );
131  $minTsUnix = wfTimestamp( TS_UNIX, $minTs );
132  $numRowsCopied = 0;
133 
134  while ( true ) {
135  $maxTs = $this->dbw->selectField( $srcTable, 'MAX(log_timestamp)', false, __METHOD__ );
136  $copyPos = $this->dbw->selectField( $dstTable, 'MAX(log_timestamp)', false, __METHOD__ );
137  $maxTsUnix = wfTimestamp( TS_UNIX, $maxTs );
138  $copyPosUnix = wfTimestamp( TS_UNIX, $copyPos );
139 
140  if ( $copyPos === null ) {
141  $percent = 0;
142  } else {
143  $percent = ( $copyPosUnix - $minTsUnix ) / ( $maxTsUnix - $minTsUnix ) * 100;
144  }
145  printf( "%s %.2f%%\n", $copyPos, $percent );
146 
147  # Handle all entries with timestamp equal to $copyPos
148  if ( $copyPos !== null ) {
149  $numRowsCopied += $this->copyExactMatch( $srcTable, $dstTable, $copyPos );
150  }
151 
152  # Now copy a batch of rows
153  if ( $copyPos === null ) {
154  $conds = false;
155  } else {
156  $conds = array( 'log_timestamp > ' . $this->dbw->addQuotes( $copyPos ) );
157  }
158  $srcRes = $this->dbw->select( $srcTable, '*', $conds, __METHOD__,
159  array( 'LIMIT' => $batchSize, 'ORDER BY' => 'log_timestamp' ) );
160 
161  if ( ! $srcRes->numRows() ) {
162  # All done
163  break;
164  }
165 
166  $batch = array();
167  foreach ( $srcRes as $srcRow ) {
168  $batch[] = (array)$srcRow;
169  }
170  $this->dbw->insert( $dstTable, $batch, __METHOD__ );
171  $numRowsCopied += count( $batch );
172 
174  }
175  echo "Copied $numRowsCopied rows\n";
176  }
177 
178  function copyExactMatch( $srcTable, $dstTable, $copyPos ) {
179  $numRowsCopied = 0;
180  $srcRes = $this->dbw->select( $srcTable, '*', array( 'log_timestamp' => $copyPos ), __METHOD__ );
181  $dstRes = $this->dbw->select( $dstTable, '*', array( 'log_timestamp' => $copyPos ), __METHOD__ );
182 
183  if ( $srcRes->numRows() ) {
184  $srcRow = $srcRes->fetchObject();
185  $srcFields = array_keys( (array)$srcRow );
186  $srcRes->seek( 0 );
187  $dstRowsSeen = array();
188 
189  # Make a hashtable of rows that already exist in the destination
190  foreach ( $dstRes as $dstRow ) {
191  $reducedDstRow = array();
192  foreach ( $srcFields as $field ) {
193  $reducedDstRow[$field] = $dstRow->$field;
194  }
195  $hash = md5( serialize( $reducedDstRow ) );
196  $dstRowsSeen[$hash] = true;
197  }
198 
199  # Copy all the source rows that aren't already in the destination
200  foreach ( $srcRes as $srcRow ) {
201  $hash = md5( serialize( (array)$srcRow ) );
202  if ( !isset( $dstRowsSeen[$hash] ) ) {
203  $this->dbw->insert( $dstTable, (array)$srcRow, __METHOD__ );
204  $numRowsCopied++;
205  }
206  }
207  }
208  return $numRowsCopied;
209  }
210 }
211 
212 $ul = new UpdateLogging;
213 $ul->execute();
ID
occurs before session is loaded can be modified ID
Definition: hooks.txt:2829
UpdateLogging\$dbw
DatabaseBase $dbw
Definition: upgradeLogging.php:36
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
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
wfGetDB
& wfGetDB( $db, $groups=array(), $wiki=false)
Get a Database object.
Definition: GlobalFunctions.php:3714
text
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add text
Definition: design.txt:12
wfTimestamp
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
Definition: GlobalFunctions.php:2530
UpdateLogging\$batchSize
$batchSize
Definition: upgradeLogging.php:37
UpdateLogging\$minTs
$minTs
Definition: upgradeLogging.php:38
key
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add in any and then calling but I prefer the flexibility This should also do the output encoding The system allocates a global one in $wgOut Title Represents the title of an and does all the work of translating among various forms such as plain database key
Definition: design.txt:25
UpdateLogging\execute
execute()
Definition: upgradeLogging.php:40
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
wfWaitForSlaves
wfWaitForSlaves( $maxLag=false, $wiki=false, $cluster=false)
Modern version of wfWaitForSlaves().
Definition: GlobalFunctions.php:3859
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
will
</td >< td > &</td >< td > t want your writing to be edited mercilessly and redistributed at will
Definition: All_system_messages.txt:914
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 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
Definition: distributors.txt:9
action
action
Definition: parserTests.txt:378
$ul
$ul
Definition: upgradeLogging.php:173
DatabaseBase
Database abstraction object.
Definition: Database.php:219
only
published in in Madrid In the first edition of the Vocabolario for was published In in Rotterdam was the Dictionnaire Universel ! html< p > The first monolingual dictionary written in a Romance language was< i > Sebastián Covarrubias</i >< i > Tesoro de la lengua castellana o published in in Madrid In the first edition of the< i > Vocabolario dell< a href="/index.php?title=Accademia_della_Crusca&amp;action=edit&amp;redlink=1" class="new" title="Accademia della Crusca (page does not exist)"> Accademia della Crusca</a ></i > for was published In in Rotterdam was the< i > Dictionnaire Universel</i ></p > ! end ! test Italics and ! wikitext foo ! html< p >< i > foo</i ></p > !end ! test Italics and ! wikitext foo ! html< p >< i > foo</i ></p > !end ! test Italics and ! wikitext foo ! html< p >< i > foo</i ></p > !end ! test Italics and ! wikitext foo ! html php< p >< i > foo</i ></p > ! html parsoid< p >< i > foo</i >< b ></b ></p > !end ! test Italics and ! wikitext foo ! html< p >< i > foo</i ></p > !end ! test Italics and ! wikitext foo ! html< p >< b > foo</b ></p > !end ! test Italics and ! wikitext foo ! html< p >< b > foo</b ></p > !end ! test Italics and ! wikitext foo ! html php< p >< b > foo</b ></p > ! html parsoid< p >< b > foo</b >< i ></i ></p > !end ! test Italics and ! wikitext foo ! html< p >< i > foo</i ></p > !end ! test Italics and ! wikitext foo ! html< p >< b > foo</b ></p > !end ! test Italics and ! wikitext foo ! html< p >< b > foo</b ></p > !end ! test Italics and ! wikitext foo ! html php< p >< b > foo</b ></p > ! html parsoid< p >< b > foo</b >< i ></i ></p > !end ! test Italics and ! options ! wikitext foo ! html< p >< b >< i > foo</i ></b ></p > !end ! test Italics and ! wikitext foo ! html< p >< i >< b > foo</b ></i ></p > !end ! test Italics and ! wikitext foo ! html< p >< i >< b > foo</b ></i ></p > !end ! test Italics and ! wikitext foo ! html< p >< i >< b > foo</b ></i ></p > !end ! test Italics and ! wikitext foo bar ! html< p >< i > foo< b > bar</b ></i ></p > !end ! test Italics and ! wikitext foo bar ! html< p >< i > foo< b > bar</b ></i ></p > !end ! test Italics and ! wikitext foo bar ! html< p >< i > foo< b > bar</b ></i ></p > !end ! test Italics and ! wikitext foo bar ! html php< p >< b > foo</b > bar</p > ! html parsoid< p >< b > foo</b > bar< i ></i ></p > !end ! test Italics and ! wikitext foo bar ! html php< p >< b > foo</b > bar</p > ! html parsoid< p >< b > foo</b > bar< b ></b ></p > !end ! test Italics and ! wikitext this is about foo s family ! html< p >< i > this is about< b > foo s family</b ></i ></p > !end ! test Italics and ! wikitext this is about foo s family ! html< p >< i > this is about< b > foo s</b > family</i ></p > !end ! test Italics and ! wikitext this is about foo s family ! html< p >< b > this is about< i > foo</i ></b >< i > s family</i ></p > !end ! test Italics and ! options ! wikitext this is about foo s family ! html< p >< i > this is about</i > foo< b > s family</b ></p > !end ! test Italics and ! wikitext this is about foo s family ! html< p >< b > this is about< i > foo s</i > family</b ></p > !end ! test Italicized possessive ! wikitext The s talk page ! html< p > The< i >< a href="/wiki/Main_Page" title="Main Page"> Main Page</a ></i > s talk page</p > ! end ! test Parsoid only
Definition: parserTests.txt:396
$hash
return false to override stock group addition can be modified try getUserPermissionsErrors userCan checks are continued by internal code can override on output return false to not delete it return false to override the default password checks & $hash
Definition: hooks.txt:2708
type
This document describes the state of Postgres support in and is fairly well maintained The main code is very well while extensions are very hit and miss it is probably the most supported database after MySQL Much of the work in making MediaWiki database agnostic came about through the work of creating Postgres as and are nearing end of but without copying over all the usage comments General notes on the but these can almost always be programmed around *Although Postgres has a true BOOLEAN type
Definition: postgres.txt:22
UpdateLogging\sync
sync( $srcTable, $dstTable)
Copy all rows from $srcTable to $dstTable.
Definition: upgradeLogging.php:127
output
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add in any and then calling output() to send it all. It could be easily changed to send incrementally if that becomes useful
TS_UNIX
const TS_UNIX
Unix time - the number of seconds since 1970-01-01 00:00:00 UTC.
Definition: GlobalFunctions.php:2473
UpdateLogging\copyExactMatch
copyExactMatch( $srcTable, $dstTable, $copyPos)
Definition: upgradeLogging.php:177
format
if the prop value should be in the metadata multi language array format
Definition: hooks.txt:1230
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
such
it sets a lot of them automatically from query and such
Definition: design.txt:93
$batch
$batch
Definition: linkcache.txt:23
UpdateLogging
Maintenance script that upgrade for log_id/log_deleted fields in a replication-safe way.
Definition: upgradeLogging.php:32
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