maintenance/fetchText.php

   1 <?php
   2 /**
   3  * Communications protocol.
   4  * This is used by dumpTextPass.php when the --spawn option is present.
   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  * @file
  22  * @ingroup Maintenance
  23  */
  24
  25 require_once __DIR__ . '/Maintenance.php';
  26
  27 use MediaWiki\MediaWikiServices;
  28 use MediaWiki\Storage\BlobAccessException;
  29 use MediaWiki\Storage\SqlBlobStore;
  30
  31 /**
  32  * Maintenance script used to fetch page text in a subprocess.
  33  *
  34  * @ingroup Maintenance
  35  */
  36 class FetchText extends Maintenance {
  37
  38         public function __construct() {
  39                 parent::__construct();
  40
  41                 $this->addDescription( "Fetch the raw revision blob from a blob address.\n" .
  42                         "Integer IDs are interpreted as referring to text.old_id for backwards compatibility.\n" .
  43                         "NOTE: Export transformations are NOT applied. " .
  44                         "This is left to dumpTextPass.php"
  45                 );
  46         }
  47
  48         /**
  49          * @return SqlBlobStore
  50          */
  51         private function getBlobStore() {
  52                 return MediaWikiServices::getInstance()->getBlobStore();
  53         }
  54
  55         /**
  56          * returns a string containing the following in order:
  57          *   textid
  58          *   \n
  59          *   length of text (-1 on error = failure to retrieve/unserialize/gunzip/etc)
  60          *   \n
  61          *   text  (may be empty)
  62          *
  63          * note that the text string itself is *not* followed by newline
  64          */
  65         public function execute() {
  66                 $stdin = $this->getStdin();
  67                 while ( !feof( $stdin ) ) {
  68                         $line = fgets( $stdin );
  69                         if ( $line === false ) {
  70                                 // We appear to have lost contact...
  71                                 break;
  72                         }
  73                         $blobAddress = trim( $line );
  74
  75                         // Plain integers are supported for backwards compatibility with pre-MCR dumps.
  76                         if ( strpos( $blobAddress, ':' ) === false && is_numeric( $blobAddress ) ) {
  77                                 $blobAddress = SqlBlobStore::makeAddressFromTextId( intval( $blobAddress ) );
  78                         }
  79
  80                         try {
  81                                 $text = $this->getBlobStore()->getBlob( $blobAddress );
  82                                 $textLen = strlen( $text );
  83                         } catch ( BlobAccessException $ex ) {
  84                                 // XXX: log $ex to stderr?
  85                                 $textLen = '-1';
  86                                 $text = '';
  87                         } catch ( InvalidArgumentException $ex ) {
  88                                 // XXX: log $ex to stderr?
  89                                 $textLen = '-1';
  90                                 $text = '';
  91                         }
  92
  93                         $this->output( $blobAddress . "\n" . $textLen . "\n" . $text );
  94                 }
  95         }
  96
  97 }
  98
  99 $maintClass = FetchText::class;
 100 require_once RUN_MAINTENANCE_IF_MAIN;