maintenance/populateRevisionSha1.php

   1 <?php
   2 /**
   3  * Fills the rev_sha1 and ar_sha1 columns of revision
   4  * and archive tables for revisions created before MW 1.19.
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License along
  17  * with this program; if not, write to the Free Software Foundation, Inc.,
  18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19  * http://www.gnu.org/copyleft/gpl.html
  20  *
  21  * @ingroup Maintenance
  22  */
  23
  24 require_once( dirname( __FILE__ ) . '/Maintenance.php' );
  25
  26 class PopulateRevisionSha1 extends LoggedUpdateMaintenance {
  27         public function __construct() {
  28                 parent::__construct();
  29                 $this->mDescription = "Populates the rev_sha1 and ar_sha1 fields";
  30                 $this->setBatchSize( 200 );
  31         }
  32
  33         protected function getUpdateKey() {
  34                 return 'populate rev_sha1';
  35         }
  36
  37         protected function updateSkippedMessage() {
  38                 return 'rev_sha1 column of revision table already populated.';
  39         }
  40
  41         protected function updatelogFailedMessage() {
  42                 return 'Could not insert rev_sha1 population row.';
  43         }
  44
  45         protected function doDBUpdates() {
  46                 $db = $this->getDB( DB_MASTER );
  47                 if ( !$db->tableExists( 'revision' ) ) {
  48                         $this->error( "revision table does not exist", true );
  49                 }
  50                 if ( !$db->tableExists( 'archive' ) ) {
  51                         $this->error( "archive table does not exist", true );
  52                 }
  53
  54                 $this->output( "Populating rev_sha1 column\n" );
  55                 $rc = $this->doSha1Updates( $db, 'revision', 'rev_id', 'rev' );
  56
  57                 $this->output( "Populating ar_sha1 column\n" );
  58                 $ac = $this->doSha1Updates( $db, 'archive', 'ar_rev_id', 'ar' );
  59
  60                 $this->output( "rev_sha1 and ar_sha1 population complete [$rc revision rows, $ac archive rows].\n" );
  61                 return true;
  62         }
  63
  64         /**
  65          * @return Integer Rows changed
  66          */
  67         protected function doSha1Updates( $db, $table, $idCol, $prefix ) {
  68                 $start = $db->selectField( $table, "MIN($idCol)", false, __METHOD__ );
  69                 $end = $db->selectField( $table, "MAX($idCol)", false, __METHOD__ );
  70                 if ( !$start || !$end ) {
  71                         $this->output( "...revision table seems to be empty.\n" );
  72                         return true;
  73                 }
  74
  75                 $count = 0;
  76                 # Do remaining chunk
  77                 $end += $this->mBatchSize - 1;
  78                 $blockStart = $start;
  79                 $blockEnd = $start + $this->mBatchSize - 1;
  80                 while ( $blockEnd <= $end ) {
  81                         $this->output( "...doing $idCol from $blockStart to $blockEnd\n" );
  82                         $cond = "$idCol BETWEEN $blockStart AND $blockEnd
  83                                 AND $idCol IS NOT NULL AND {$prefix}_sha1 = ''";
  84                         $res = $db->select( $table, '*', $cond, __METHOD__ );
  85
  86                         $db->begin();
  87                         foreach ( $res as $row ) {
  88                                 if ( $table === 'archive' ) {
  89                                         $rev = Revision::newFromArchiveRow( $row );
  90                                 } else {
  91                                         $rev = new Revision( $row );
  92                                 }
  93                                 $text = $rev->getRawText();
  94                                 if ( !is_string( $text ) ) {
  95                                         # This should not happen, but sometimes does (bug 20757)
  96                                         $this->output( "Text of revision {$row->$idCol} unavailable!\n" );
  97                                 } else {
  98                                         $db->update( $table,
  99                                                 array( "{$prefix}_sha1" => Revision::base36Sha1( $text ) ),
 100                                                 array( $idCol => $row->$idCol ),
 101                                                 __METHOD__ );
 102                                         $count++;
 103                                 }
 104                         }
 105                         $db->commit();
 106
 107                         $blockStart += $this->mBatchSize;
 108                         $blockEnd += $this->mBatchSize;
 109                         wfWaitForSlaves();
 110                 }
 111                 return $count;
 112         }
 113 }
 114
 115 $maintClass = "PopulateRevisionSha1";
 116 require_once( RUN_MAINTENANCE_IF_MAIN );