maintenance/cleanupInvalidDbKeys.php

   1 <?php
   2 /**
   3  * Cleans up invalid titles in various tables.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Maintenance
  22  */
  23
  24 require_once __DIR__ . '/Maintenance.php';
  25
  26 /**
  27  * Maintenance script that cleans up invalid titles in various tables.
  28  *
  29  * @since 1.29
  30  * @ingroup Maintenance
  31  */
  32 class CleanupInvalidDbKeys extends Maintenance {
  33         /** @var array[] List of tables to clean up, and the field prefix for that table */
  34         protected static $tables = [
  35                 // Data tables
  36                 [ 'page', 'page' ],
  37                 [ 'redirect', 'rd', 'idField' => 'rd_from' ],
  38                 [ 'archive', 'ar' ],
  39                 [ 'logging', 'log' ],
  40                 [ 'protected_titles', 'pt', 'idField' => 0 ],
  41                 [ 'category', 'cat', 'nsField' => 14 ],
  42                 [ 'recentchanges', 'rc' ],
  43                 [ 'watchlist', 'wl' ],
  44                 // The querycache tables' qc(c)_title and qcc_titletwo may contain titles,
  45                 // but also usernames or other things like that, so we leave them alone
  46
  47                 // Links tables
  48                 [ 'pagelinks', 'pl', 'idField' => 'pl_from' ],
  49                 [ 'templatelinks', 'tl', 'idField' => 'tl_from' ],
  50                 [ 'categorylinks', 'cl', 'idField' => 'cl_from', 'nsField' => 14, 'titleField' => 'cl_to' ],
  51         ];
  52
  53         public function __construct() {
  54                 parent::__construct();
  55                 $this->addDescription( <<<'TEXT'
  56 This script cleans up the title fields in various tables to remove entries that
  57 will be rejected by the constructor of TitleValue.  This constructor throws an
  58 exception when invalid data is encountered, which will not normally occur on
  59 regular page views, but can happen on query special pages.
  60
  61 The script targets titles matching the regular expression /^_|[ \r\n\t]|_$/.
  62 Because any foreign key relationships involving these titles will already be
  63 broken, the titles are corrected to a valid version or the rows are deleted
  64 entirely, depending on the table.
  65
  66 The script runs with the expectation that STDOUT is redirected to a file.
  67 TEXT
  68                 );
  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.',
  71                         false, false );
  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 );
  76
  77                 $this->setBatchSize( 500 );
  78         }
  79
  80         public function execute() {
  81                 $tablesToProcess = $this->getOption( 'table' );
  82                 foreach ( static::$tables as $tableParams ) {
  83                         if ( !$tablesToProcess || in_array( $tableParams[0], $tablesToProcess ) ) {
  84                                 $this->cleanupTable( $tableParams );
  85                         }
  86                 }
  87
  88                 $this->outputStatus( 'Done!' );
  89                 if ( $this->hasOption( 'fix' ) ) {
  90                         $this->outputStatus( ' Cleaned up invalid DB keys on ' . wfWikiID() . "!\n" );
  91                 }
  92         }
  93
  94         /**
  95          * Prints text to STDOUT, and STDERR if STDOUT was redirected to a file.
  96          * Used for progress reporting.
  97          *
  98          * @param string $str Text to write to both places
  99          * @param string|null $channel Ignored
 100          */
 101         protected function outputStatus( $str, $channel = null ) {
 102                 // Make it easier to find progress lines in the STDOUT log
 103                 if ( trim( $str ) ) {
 104                         fwrite( STDOUT, '*** ' . trim( $str ) . "\n" );
 105                 }
 106                 fwrite( STDERR, $str );
 107         }
 108
 109         /**
 110          * Prints text to STDOUT. Used for logging output.
 111          *
 112          * @param string $str Text to write
 113          */
 114         protected function writeToReport( $str ) {
 115                 fwrite( STDOUT, $str );
 116         }
 117
 118         /**
 119          * Identifies, and optionally cleans up, invalid titles.
 120          *
 121          * @param array $tableParams A child array of self::$tables
 122          */
 123         protected function cleanupTable( $tableParams ) {
 124                 list( $table, $prefix ) = $tableParams;
 125                 $idField = $tableParams['idField'] ?? "{$prefix}_id";
 126                 $nsField = $tableParams['nsField'] ?? "{$prefix}_namespace";
 127                 $titleField = $tableParams['titleField'] ?? "{$prefix}_title";
 128
 129                 $this->outputStatus( "Looking for invalid $titleField entries in $table...\n" );
 130
 131                 // Do all the select queries on the replicas, as they are slow (they use
 132                 // unanchored LIKEs). Naturally this could cause problems if rows are
 133                 // modified after selecting and before deleting/updating, but working on
 134                 // the hypothesis that invalid rows will be old and in all likelihood
 135                 // unreferenced, we should be fine to do it like this.
 136                 $dbr = $this->getDB( DB_REPLICA, 'vslow' );
 137
 138                 // Find all TitleValue-invalid titles.
 139                 $percent = $dbr->anyString(); // DBMS-agnostic equivalent of '%' LIKE wildcard
 140                 $res = $dbr->select(
 141                         $table,
 142                         [
 143                                 'id' => $idField,
 144                                 'ns' => $nsField,
 145                                 'title' => $titleField,
 146                         ],
 147                         // The REGEXP operator is not cross-DBMS, so we have to use lots of LIKEs
 148                         [ $dbr->makeList( [
 149                                 $titleField . $dbr->buildLike( $percent, ' ', $percent ),
 150                                 $titleField . $dbr->buildLike( $percent, "\r", $percent ),
 151                                 $titleField . $dbr->buildLike( $percent, "\n", $percent ),
 152                                 $titleField . $dbr->buildLike( $percent, "\t", $percent ),
 153                                 $titleField . $dbr->buildLike( '_', $percent ),
 154                                 $titleField . $dbr->buildLike( $percent, '_' ),
 155                         ], LIST_OR ) ],
 156                         __METHOD__,
 157                         [ 'LIMIT' => $this->getBatchSize() ]
 158                 );
 159
 160                 $this->outputStatus( "Number of invalid rows: " . $res->numRows() . "\n" );
 161                 if ( !$res->numRows() ) {
 162                         $this->outputStatus( "\n" );
 163                         return;
 164                 }
 165
 166                 // Write a table of titles to the report file. Also keep a list of the found
 167                 // IDs, as we might need it later for DB updates
 168                 $this->writeToReport( sprintf( "%10s |  ns | dbkey\n", $idField ) );
 169                 $ids = [];
 170                 foreach ( $res as $row ) {
 171                         $this->writeToReport( sprintf( "%10d | %3d | %s\n", $row->id, $row->ns, $row->title ) );
 172                         $ids[] = $row->id;
 173                 }
 174
 175                 // If we're doing a dry run, output the new titles we would use for the UPDATE
 176                 // queries (if relevant), and finish
 177                 if ( !$this->hasOption( 'fix' ) ) {
 178                         if ( $table === 'logging' || $table === 'archive' ) {
 179                                 $this->writeToReport( "The following updates would be run with the --fix flag:\n" );
 180                                 foreach ( $res as $row ) {
 181                                         $newTitle = self::makeValidTitle( $row->title );
 182                                         $this->writeToReport(
 183                                                 "$idField={$row->id}: update '{$row->title}' to '$newTitle'\n" );
 184                                 }
 185                         }
 186
 187                         if ( $table !== 'page' && $table !== 'redirect' ) {
 188                                 $this->outputStatus( "Run with --fix to clean up these rows\n" );
 189                         }
 190                         $this->outputStatus( "\n" );
 191                         return;
 192                 }
 193
 194                 // Fix the bad data, using different logic for the various tables
 195                 $dbw = $this->getDB( DB_MASTER );
 196                 switch ( $table ) {
 197                         case 'page':
 198                         case 'redirect':
 199                                 // This shouldn't happen on production wikis, and we already have a script
 200                                 // to handle 'page' rows anyway, so just notify the user and let them decide
 201                                 // what to do next.
 202                                 $this->outputStatus( <<<TEXT
 203 IMPORTANT: This script does not fix invalid entries in the $table table.
 204 Consider repairing these rows, and rows in related tables, by hand.
 205 You may like to run, or borrow logic from, the cleanupTitles.php script.
 206
 207 TEXT
 208                                 );
 209                                 break;
 210
 211                         case 'archive':
 212                         case 'logging':
 213                                 // Rename the title to a corrected equivalent. Any foreign key relationships
 214                                 // to the page_title field are already broken, so this will just make sure
 215                                 // users can still access the log entries/deleted revisions from the interface
 216                                 // using a valid page title.
 217                                 $this->outputStatus(
 218                                         "Updating these rows, setting $titleField to the closest valid DB key...\n" );
 219                                 $affectedRowCount = 0;
 220                                 foreach ( $res as $row ) {
 221                                         $newTitle = self::makeValidTitle( $row->title );
 222                                         $this->writeToReport(
 223                                                 "$idField={$row->id}: updating '{$row->title}' to '$newTitle'\n" );
 224
 225                                         $dbw->update( $table,
 226                                                 [ $titleField => $newTitle ],
 227                                                 [ $idField => $row->id ],
 228                                                 __METHOD__ );
 229                                         $affectedRowCount += $dbw->affectedRows();
 230                                 }
 231                                 wfWaitForSlaves();
 232                                 $this->outputStatus( "Updated $affectedRowCount rows on $table.\n" );
 233
 234                                 break;
 235
 236                         case 'recentchanges':
 237                         case 'watchlist':
 238                         case 'category':
 239                                 // Since these broken titles can't exist, there's really nothing to watch,
 240                                 // nothing can be categorised in them, and they can't have been changed
 241                                 // recently, so we can just remove these rows.
 242                                 $this->outputStatus( "Deleting invalid $table rows...\n" );
 243                                 $dbw->delete( $table, [ $idField => $ids ], __METHOD__ );
 244                                 wfWaitForSlaves();
 245                                 $this->outputStatus( 'Deleted ' . $dbw->affectedRows() . " rows from $table.\n" );
 246                                 break;
 247
 248                         case 'protected_titles':
 249                                 // Since these broken titles can't exist, there's really nothing to protect,
 250                                 // so we can just remove these rows. Made more complicated by this table
 251                                 // not having an ID field
 252                                 $this->outputStatus( "Deleting invalid $table rows...\n" );
 253                                 $affectedRowCount = 0;
 254                                 foreach ( $res as $row ) {
 255                                         $dbw->delete( $table,
 256                                                 [ $nsField => $row->ns, $titleField => $row->title ],
 257                                                 __METHOD__ );
 258                                         $affectedRowCount += $dbw->affectedRows();
 259                                 }
 260                                 wfWaitForSlaves();
 261                                 $this->outputStatus( "Deleted $affectedRowCount rows from $table.\n" );
 262                                 break;
 263
 264                         case 'pagelinks':
 265                         case 'templatelinks':
 266                         case 'categorylinks':
 267                                 // Update links tables for each page where these bogus links are supposedly
 268                                 // located. If the invalid rows don't go away after these jobs go through,
 269                                 // they're probably being added by a buggy hook.
 270                                 $this->outputStatus( "Queueing link update jobs for the pages in $idField...\n" );
 271                                 foreach ( $res as $row ) {
 272                                         $wp = WikiPage::newFromID( $row->id );
 273                                         if ( $wp ) {
 274                                                 RefreshLinks::fixLinksFromArticle( $row->id );
 275                                         } else {
 276                                                 // This link entry points to a nonexistent page, so just get rid of it
 277                                                 $dbw->delete( $table,
 278                                                         [ $idField => $row->id, $nsField => $row->ns, $titleField => $row->title ],
 279                                                         __METHOD__ );
 280                                         }
 281                                 }
 282                                 wfWaitForSlaves();
 283                                 $this->outputStatus( "Link update jobs have been added to the job queue.\n" );
 284                                 break;
 285                 }
 286
 287                 $this->outputStatus( "\n" );
 288         }
 289
 290         /**
 291          * Fix possible validation issues in the given title (DB key).
 292          *
 293          * @param string $invalidTitle
 294          * @return string
 295          */
 296         protected static function makeValidTitle( $invalidTitle ) {
 297                 return strtr( trim( $invalidTitle, '_' ),
 298                         [ ' ' => '_', "\r" => '', "\n" => '', "\t" => '_' ] );
 299         }
 300 }
 301
 302 $maintClass = CleanupInvalidDbKeys::class;
 303 require_once RUN_MAINTENANCE_IF_MAIN;