MediaWiki REL1_30
cleanupTable.inc
Go to the documentation of this file.
1<?php
24require_once __DIR__ . '/Maintenance.php';
25
32 protected $defaultParams = [
33 'table' => 'page',
34 'conds' => [],
35 'index' => 'page_id',
36 'callback' => 'processRow',
37 ];
38
39 protected $dryrun = false;
40 public $batchSize = 100;
41 public $reportInterval = 100;
42
44
45 public function __construct() {
46 parent::__construct();
47 $this->addOption( 'dry-run', 'Perform a dry run' );
48 }
49
50 public function execute() {
51 global $wgUser;
52 $this->dryrun = $this->hasOption( 'dry-run' );
53 if ( $this->dryrun ) {
54 $wgUser = User::newFromName( 'Conversion script' );
55 $this->output( "Checking for bad titles...\n" );
56 } else {
57 $wgUser = User::newSystemUser( 'Conversion script', [ 'steal' => true ] );
58 $this->output( "Checking and fixing bad titles...\n" );
59 }
60 $this->runTable( $this->defaultParams );
61 }
62
63 protected function init( $count, $table ) {
64 $this->processed = 0;
65 $this->updated = 0;
66 $this->count = $count;
67 $this->startTime = microtime( true );
68 $this->table = $table;
69 }
70
74 protected function progress( $updated ) {
75 $this->updated += $updated;
76 $this->processed++;
77 if ( $this->processed % $this->reportInterval != 0 ) {
78 return;
79 }
80 $portion = $this->processed / $this->count;
81 $updateRate = $this->updated / $this->processed;
82
83 $now = microtime( true );
84 $delta = $now - $this->startTime;
85 $estimatedTotalTime = $delta / $portion;
86 $eta = $this->startTime + $estimatedTotalTime;
87
88 $this->output(
89 sprintf( "%s %s: %6.2f%% done on %s; ETA %s [%d/%d] %.2f/sec <%.2f%% updated>\n",
90 wfWikiID(),
91 wfTimestamp( TS_DB, intval( $now ) ),
92 $portion * 100.0,
93 $this->table,
94 wfTimestamp( TS_DB, intval( $eta ) ),
95 $this->processed,
96 $this->count,
97 $this->processed / $delta,
98 $updateRate * 100.0
99 )
100 );
101 flush();
102 }
103
108 public function runTable( $params ) {
109 $dbr = $this->getDB( DB_REPLICA );
110
111 if ( array_diff( array_keys( $params ),
112 [ 'table', 'conds', 'index', 'callback' ] )
113 ) {
114 throw new MWException( __METHOD__ . ': Missing parameter ' . implode( ', ', $params ) );
115 }
116
117 $table = $params['table'];
118 // count(*) would melt the DB for huge tables, we can estimate here
119 $count = $dbr->estimateRowCount( $table, '*', '', __METHOD__ );
120 $this->init( $count, $table );
121 $this->output( "Processing $table...\n" );
122
123 $index = (array)$params['index'];
124 $indexConds = [];
125 $options = [
126 'ORDER BY' => implode( ',', $index ),
127 'LIMIT' => $this->batchSize
128 ];
129 $callback = [ $this, $params['callback'] ];
130
131 while ( true ) {
132 $conds = array_merge( $params['conds'], $indexConds );
133 $res = $dbr->select( $table, '*', $conds, __METHOD__, $options );
134 if ( !$res->numRows() ) {
135 // Done
136 break;
137 }
138
139 foreach ( $res as $row ) {
140 call_user_func( $callback, $row );
141 }
142
143 if ( $res->numRows() < $this->batchSize ) {
144 // Done
145 break;
146 }
147
148 // Update the conditions to select the next batch.
149 // Construct a condition string by starting with the least significant part
150 // of the index, and adding more significant parts progressively to the left
151 // of the string.
152 $nextCond = '';
153 foreach ( array_reverse( $index ) as $field ) {
154 $encValue = $dbr->addQuotes( $row->$field );
155 if ( $nextCond === '' ) {
156 $nextCond = "$field > $encValue";
157 } else {
158 $nextCond = "$field > $encValue OR ($field = $encValue AND ($nextCond))";
159 }
160 }
161 $indexConds = [ $nextCond ];
162 }
163
164 $this->output( "Finished $table... $this->updated of $this->processed rows updated\n" );
165 }
166
171 protected function hexChar( $matches ) {
172 return sprintf( "\\x%02x", ord( $matches[1] ) );
173 }
174}
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
wfWikiID()
Get an ASCII string identifying this wiki This is used as a prefix in memcached keys.
$wgUser
Definition Setup.php:817
MediaWiki exception.
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
hasOption( $name)
Checks to see if a particular param exists.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Generic class to cleanup a database table.
progress( $updated)
init( $count, $table)
execute()
Do the actual work.
hexChar( $matches)
runTable( $params)
__construct()
Default constructor.
if(! $regexes) $dbr
Definition cleanup.php:94
$res
Definition database.txt:21
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:16
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
the array() calling protocol came about after MediaWiki 1.4rc1.
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:1971
const DB_REPLICA
Definition defines.php:25
$params