24require_once __DIR__ .
'/Maintenance.php';
37 [
'redirect',
'rd',
'idField' =>
'rd_from' ],
40 [
'protected_titles',
'pt',
'idField' => 0 ],
41 [
'category',
'cat',
'nsField' => 14 ],
42 [
'recentchanges',
'rc' ],
43 [
'watchlist',
'wl' ],
48 [
'pagelinks',
'pl',
'idField' =>
'pl_from' ],
49 [
'templatelinks',
'tl',
'idField' =>
'tl_from' ],
50 [
'categorylinks',
'cl',
'idField' =>
'cl_from',
'nsField' => 14,
'titleField' =>
'cl_to' ],
54 parent::__construct();
56This script cleans up the title fields in various tables to
remove entries that
57will be rejected by the constructor of
TitleValue. This constructor
throws an
58exception when invalid data is encountered, which will not normally occur on
59regular page views, but can happen on query special pages.
61The script targets titles matching the regular expression /^_|[ \r\
n\t]|_$/.
62Because any foreign key relationships involving these titles will already be
63broken, the titles are corrected to a valid version or the rows are deleted
64entirely, depending on the table.
66The script runs with the expectation that STDOUT is redirected to a file.
69 $this->
addOption(
'fix',
'Actually clean up invalid titles. If this parameter is ' .
70 'not specified, the script will report invalid titles but not clean them up.',
72 $this->
addOption(
'table',
'The table(s) to process. This option can be specified ' .
73 'more than once (e.g. -t category -t watchlist). If not specified, all available ' .
74 'tables will be processed. Available tables are: ' .
75 implode(
', ', array_column( static::$tables, 0 ) ),
false,
true,
't',
true );
81 $tablesToProcess = $this->
getOption(
'table' );
82 foreach ( static::$tables as $tableParams ) {
83 if ( !$tablesToProcess || in_array( $tableParams[0], $tablesToProcess ) ) {
90 $dbDomain = WikiMap::getCurrentWikiDbDomain()->getId();
91 $this->
outputStatus(
" Cleaned up invalid DB keys on $dbDomain!\n" );
104 if ( trim( $str ) ) {
105 fwrite( STDOUT,
'*** ' . trim( $str ) .
"\n" );
107 fwrite( STDERR, $str );
116 fwrite( STDOUT, $str );
125 list( $table, $prefix ) = $tableParams;
126 $idField = $tableParams[
'idField'] ??
"{$prefix}_id";
127 $nsField = $tableParams[
'nsField'] ??
"{$prefix}_namespace";
128 $titleField = $tableParams[
'titleField'] ??
"{$prefix}_title";
130 $this->
outputStatus(
"Looking for invalid $titleField entries in $table...\n" );
140 $percent =
$dbr->anyString();
146 'title' => $titleField,
150 $titleField .
$dbr->buildLike( $percent,
' ', $percent ),
151 $titleField .
$dbr->buildLike( $percent,
"\r", $percent ),
152 $titleField .
$dbr->buildLike( $percent,
"\n", $percent ),
153 $titleField .
$dbr->buildLike( $percent,
"\t", $percent ),
154 $titleField .
$dbr->buildLike(
'_', $percent ),
155 $titleField .
$dbr->buildLike( $percent,
'_' ),
158 [
'LIMIT' => $this->getBatchSize() ]
162 if ( !
$res->numRows() ) {
169 $this->
writeToReport( sprintf(
"%10s | ns | dbkey\n", $idField ) );
171 foreach (
$res as $row ) {
172 $this->
writeToReport( sprintf(
"%10d | %3d | %s\n", $row->id, $row->ns, $row->title ) );
179 if ( $table ===
'logging' || $table ===
'archive' ) {
180 $this->
writeToReport(
"The following updates would be run with the --fix flag:\n" );
181 foreach (
$res as $row ) {
184 "$idField={$row->id}: update '{$row->title}' to '$newTitle'\n" );
188 if ( $table !==
'page' && $table !==
'redirect' ) {
189 $this->
outputStatus(
"Run with --fix to clean up these rows\n" );
204IMPORTANT: This script does not fix invalid entries in the $table table.
205Consider repairing these rows, and rows in related tables, by hand.
206You may like to run, or borrow logic from, the cleanupTitles.php script.
219 "Updating these rows, setting $titleField to the closest valid DB key...\n" );
220 $affectedRowCount = 0;
221 foreach (
$res as $row ) {
224 "$idField={$row->id}: updating '{$row->title}' to '$newTitle'\n" );
226 $dbw->update( $table,
227 [ $titleField => $newTitle ],
228 [ $idField => $row->id ],
230 $affectedRowCount += $dbw->affectedRows();
233 $this->
outputStatus(
"Updated $affectedRowCount rows on $table.\n" );
237 case 'recentchanges':
243 $this->
outputStatus(
"Deleting invalid $table rows...\n" );
244 $dbw->delete( $table, [ $idField => $ids ], __METHOD__ );
246 $this->
outputStatus(
'Deleted ' . $dbw->affectedRows() .
" rows from $table.\n" );
249 case 'protected_titles':
253 $this->
outputStatus(
"Deleting invalid $table rows...\n" );
254 $affectedRowCount = 0;
255 foreach (
$res as $row ) {
256 $dbw->delete( $table,
257 [ $nsField => $row->ns, $titleField => $row->title ],
259 $affectedRowCount += $dbw->affectedRows();
262 $this->
outputStatus(
"Deleted $affectedRowCount rows from $table.\n" );
266 case 'templatelinks':
267 case 'categorylinks':
271 $this->
outputStatus(
"Queueing link update jobs for the pages in $idField...\n" );
272 foreach (
$res as $row ) {
273 $wp = WikiPage::newFromID( $row->id );
278 $dbw->delete( $table,
279 [ $idField => $row->id, $nsField => $row->ns, $titleField => $row->title ],
284 $this->
outputStatus(
"Link update jobs have been added to the job queue.\n" );
298 return strtr( trim( $invalidTitle,
'_' ),
299 [
' ' =>
'_',
"\r" =>
'',
"\n" =>
'',
"\t" =>
'_' ] );
wfWaitForSlaves( $ifWritesSince=null, $wiki=false, $cluster=false, $timeout=null)
Waits for the replica DBs to catch up to the master position.
const RUN_MAINTENANCE_IF_MAIN
Maintenance script that cleans up invalid titles in various tables.
static makeValidTitle( $invalidTitle)
Fix possible validation issues in the given title (DB key).
static array[] $tables
List of tables to clean up, and the field prefix for that table.
cleanupTable( $tableParams)
Identifies, and optionally cleans up, invalid titles.
outputStatus( $str, $channel=null)
Prints text to STDOUT, and STDERR if STDOUT was redirected to a file.
writeToReport( $str)
Prints text to STDOUT.
__construct()
Default constructor.
execute()
Do the actual work.
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
hasOption( $name)
Checks to see if a particular option exists.
addDescription( $text)
Set the description text.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
getOption( $name, $default=null)
Get an option, or return the default.
setBatchSize( $s=0)
Set the batch size.
static fixLinksFromArticle( $id, $ns=false)
Run LinksUpdate for all links on a given page_id.
Represents a page (or page fragment) title within MediaWiki.