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 Key progress output is printed to STDERR, while a full log of all entries that
  67 are deleted is sent to STDOUT. You are strongly advised to capture STDOUT into
  68 a file.
  69 TEXT
  70                 );
  71                 $this->addOption( 'fix', 'Actually clean up invalid titles. If this parameter is ' .
  72                         'not specified, the script will report invalid titles but not clean them up.',
  73                         false, false );
  74                 $this->addOption( 'table', 'The table(s) to process. This option can be specified ' .
  75                         'more than once (e.g. -t category -t watchlist). If not specified, all available ' .
  76                         'tables will be processed. Available tables are: ' .
  77                         implode( ', ', array_column( static::$tables, 0 ) ), false, true, 't', true );
  78
  79                 $this->setBatchSize( 500 );
  80         }
  81
  82         public function execute() {
  83                 $tablesToProcess = $this->getOption( 'table' );
  84                 foreach ( static::$tables as $tableParams ) {
  85                         if ( !$tablesToProcess || in_array( $tableParams[0], $tablesToProcess ) ) {
  86                                 $this->cleanupTable( $tableParams );
  87                         }
  88                 }
  89
  90                 $this->output( 'Done! Cleaned up invalid DB keys on ' . wfWikiID() . "!\n" );
  91         }
  92
  93         /**
  94          * Prints text to STDOUT, and STDERR if STDOUT was redirected to a file.
  95          * Used for progress reporting.
  96          *
  97          * @param string $str Text to write to both places
  98          * @param string|null $channel Ignored
  99          */
 100         protected function output( $str, $channel = null ) {
 101                 // Make it easier to find progress lines in the STDOUT log
 102                 if ( trim( $str ) ) {
 103                         fwrite( STDOUT, '*** ' );
 104                 }
 105                 fwrite( STDERR, $str );
 106         }
 107
 108         /**
 109          * Prints text to STDOUT. Used for logging output.
 110          *
 111          * @param string $str Text to write
 112          */
 113         protected function writeToReport( $str ) {
 114                 fwrite( STDOUT, $str );
 115         }
 116
 117         /**
 118          * Identifies, and optionally cleans up, invalid titles.
 119          *
 120          * @param array $tableParams A child array of self::$tables
 121          */
 122         protected function cleanupTable( $tableParams ) {
 123                 $table = $tableParams[0];
 124                 $prefix = $tableParams[1];
 125                 $idField = isset( $tableParams['idField'] ) ?
 126                         $tableParams['idField'] :
 127                         "{$prefix}_id";
 128                 $nsField = isset( $tableParams['nsField'] ) ?
 129                         $tableParams['nsField'] :
 130                         "{$prefix}_namespace";
 131                 $titleField = isset( $tableParams['titleField'] ) ?
 132                         $tableParams['titleField'] :
 133                         "{$prefix}_title";
 134
 135                 $this->output( "Looking for invalid $titleField entries in $table...\n" );
 136
 137                 // Do all the select queries on the replicas, as they are slow (they use
 138                 // unanchored LIKEs). Naturally this could cause problems if rows are
 139                 // modified after selecting and before deleting/updating, but working on
 140                 // the hypothesis that invalid rows will be old and in all likelihood
 141                 // unreferenced, we should be fine to do it like this.
 142                 $dbr = $this->getDB( DB_REPLICA, 'vslow' );
 143
 144                 // Find all TitleValue-invalid titles.
 145                 $percent = $dbr->anyString(); // DBMS-agnostic equivalent of '%' LIKE wildcard
 146                 $res = $dbr->select(
 147                         $table,
 148                         [
 149                                 'id' => $idField,
 150                                 'ns' => $nsField,
 151                                 'title' => $titleField,
 152                         ],
 153                         // The REGEXP operator is not cross-DBMS, so we have to use lots of LIKEs
 154                         [ $dbr->makeList( [
 155                                 $titleField . $dbr->buildLike( $percent, ' ', $percent ),
 156                                 $titleField . $dbr->buildLike( $percent, '\r', $percent ),
 157                                 $titleField . $dbr->buildLike( $percent, '\n', $percent ),
 158                                 $titleField . $dbr->buildLike( $percent, '\t', $percent ),
 159                                 $titleField . $dbr->buildLike( '_', $percent ),
 160                                 $titleField . $dbr->buildLike( $percent, '_' ),
 161                         ], LIST_OR ) ],
 162                         __METHOD__,
 163                         [ 'LIMIT' => $this->mBatchSize ]
 164                 );
 165
 166                 $this->output( "Number of invalid rows: " . $res->numRows() . "\n" );
 167                 if ( !$res->numRows() ) {
 168                         $this->output( "\n" );
 169                         return;
 170                 }
 171
 172                 // Write a table of titles to the report file. Also keep a list of the found
 173                 // IDs, as we might need it later for DB updates
 174                 $this->writeToReport( sprintf( "%10s |  ns | dbkey\n", $idField ) );
 175                 $ids = [];
 176                 foreach ( $res as $row ) {
 177                         $this->writeToReport( sprintf( "%10d | %3d | %s\n", $row->id, $row->ns, $row->title ) );
 178                         $ids[] = $row->id;
 179                 }
 180
 181                 // If we're doing a dry run, output the new titles we would use for the UPDATE
 182                 // queries (if relevant), and finish
 183                 if ( !$this->hasOption( 'fix' ) ) {
 184                         if ( $table === 'logging' || $table === 'archive' ) {
 185                                 $this->writeToReport( "The following updates would be run with the --fix flag:\n" );
 186                                 foreach ( $res as $row ) {
 187                                         $newTitle = self::makeValidTitle( $row->title );
 188                                         $this->writeToReport(
 189                                                 "$idField={$row->id}: update '{$row->title}' to '$newTitle'\n" );
 190                                 }
 191                         }
 192
 193                         if ( $table !== 'page' && $table !== 'redirect' ) {
 194                                 $this->output( "Run with --fix to clean up these rows\n" );
 195                         }
 196                         $this->output( "\n" );
 197                         return;
 198                 }
 199
 200                 // Fix the bad data, using different logic for the various tables
 201                 $dbw = $this->getDB( DB_MASTER );
 202                 switch ( $table ) {
 203                         case 'page':
 204                         case 'redirect':
 205                                 // This shouldn't happen on production wikis, and we already have a script
 206                                 // to handle 'page' rows anyway, so just notify the user and let them decide
 207                                 // what to do next.
 208                                 $this->output( <<<TEXT
 209 IMPORTANT: This script does not fix invalid entries in the $table table.
 210 Consider repairing these rows, and rows in related tables, by hand.
 211 You may like to run, or borrow logic from, the cleanupTitles.php script.
 212
 213 TEXT
 214                                 );
 215                                 break;
 216
 217                         case 'archive':
 218                         case 'logging':
 219                                 // Rename the title to a corrected equivalent. Any foreign key relationships
 220                                 // to the page_title field are already broken, so this will just make sure
 221                                 // users can still access the log entries/deleted revisions from the interface
 222                                 // using a valid page title.
 223                                 $this->output(
 224                                         "Updating these rows, setting $titleField to the closest valid DB key...\n" );
 225                                 $affectedRowCount = 0;
 226                                 foreach ( $res as $row ) {
 227                                         $newTitle = self::makeValidTitle( $row->title );
 228                                         $this->writeToReport(
 229                                                 "$idField={$row->id}: updating '{$row->title}' to '$newTitle'\n" );
 230
 231                                         $dbw->update( $table,
 232                                                 [ $titleField => $newTitle ],
 233                                                 [ $idField => $row->id ],
 234                                                 __METHOD__ );
 235                                         $affectedRowCount += $dbw->affectedRows();
 236                                 }
 237                                 wfWaitForSlaves();
 238                                 $this->output( "Updated $affectedRowCount rows on $table.\n" );
 239
 240                                 break;
 241
 242                         case 'recentchanges':
 243                         case 'watchlist':
 244                         case 'category':
 245                                 // Since these broken titles can't exist, there's really nothing to watch,
 246                                 // nothing can be categorised in them, and they can't have been changed
 247                                 // recently, so we can just remove these rows.
 248                                 $this->output( "Deleting invalid $table rows...\n" );
 249                                 $dbw->delete( $table, [ $idField => $ids ], __METHOD__ );
 250                                 wfWaitForSlaves();
 251                                 $this->output( 'Deleted ' . $dbw->affectedRows() . " rows from $table.\n" );
 252                                 break;
 253
 254                         case 'protected_titles':
 255                                 // Since these broken titles can't exist, there's really nothing to protect,
 256                                 // so we can just remove these rows. Made more complicated by this table
 257                                 // not having an ID field
 258                                 $this->output( "Deleting invalid $table rows...\n" );
 259                                 $affectedRowCount = 0;
 260                                 foreach ( $res as $row ) {
 261                                         $dbw->delete( $table,
 262                                                 [ $nsField => $row->ns, $titleField => $row->title ],
 263                                                 __METHOD__ );
 264                                         $affectedRowCount += $dbw->affectedRows();
 265                                 }
 266                                 wfWaitForSlaves();
 267                                 $this->output( "Deleted $affectedRowCount rows from $table.\n" );
 268                                 break;
 269
 270                         case 'pagelinks':
 271                         case 'templatelinks':
 272                         case 'categorylinks':
 273                                 // Update links tables for each page where these bogus links are supposedly
 274                                 // located. If the invalid rows don't go away after these jobs go through,
 275                                 // they're probably being added by a buggy hook.
 276                                 $this->output( "Queueing link update jobs for the pages in $idField...\n" );
 277                                 foreach ( $res as $row ) {
 278                                         $wp = WikiPage::newFromID( $row->id );
 279                                         if ( $wp ) {
 280                                                 RefreshLinks::fixLinksFromArticle( $row->id );
 281                                         } else {
 282                                                 // This link entry points to a nonexistent page, so just get rid of it
 283                                                 $dbw->delete( $table,
 284                                                         [ $idField => $row->id, $nsField => $row->ns, $titleField => $row->title ],
 285                                                         __METHOD__ );
 286                                         }
 287                                 }
 288                                 wfWaitForSlaves();
 289                                 $this->output( "Link update jobs have been added to the job queue.\n" );
 290                                 break;
 291                 }
 292
 293                 $this->output( "\n" );
 294                 return;
 295         }
 296
 297         /**
 298          * Fix possible validation issues in the given title (DB key).
 299          *
 300          * @param string $invalidTitle
 301          * @return string
 302          */
 303         protected static function makeValidTitle( $invalidTitle ) {
 304                 return strtr( trim( $invalidTitle, '_' ),
 305                         [ ' ' => '_', "\r" => '', "\n" => '', "\t" => '_' ] );
 306         }
 307 }
 308
 309 $maintClass = 'CleanupInvalidDbKeys';
 310 require_once RUN_MAINTENANCE_IF_MAIN;