Split classes in Import.php into separate files

Bug: T122532
Change-Id: Ic4463ab8d3a7b2779f43efb92cb790dbc1d88064

7 files changed, 1113 insertions, 991 deletions

diff --git a/autoload.php b/autoload.php
index 8c5ec817317e..75466f52aea2 100644
--- a/autoload.php
+++ b/autoload.php
@@ -571,9 +571,9 @@ $wgAutoloadLocalClasses = array(
 	'ImportReporter' => __DIR__ . '/includes/specials/SpecialImport.php',
 	'ImportSiteScripts' => __DIR__ . '/maintenance/importSiteScripts.php',
 	'ImportSites' => __DIR__ . '/maintenance/importSites.php',
-	'ImportSource' => __DIR__ . '/includes/Import.php',
-	'ImportStreamSource' => __DIR__ . '/includes/Import.php',
-	'ImportStringSource' => __DIR__ . '/includes/Import.php',
+	'ImportSource' => __DIR__ . '/includes/import/ImportSource.php',
+	'ImportStreamSource' => __DIR__ . '/includes/import/ImportStreamSource.php',
+	'ImportStringSource' => __DIR__ . '/includes/import/ImportStringSource.php',
 	'ImportTitleFactory' => __DIR__ . '/includes/title/ImportTitleFactory.php',
 	'IncludableSpecialPage' => __DIR__ . '/includes/specialpage/IncludableSpecialPage.php',
 	'IndexPager' => __DIR__ . '/includes/pager/IndexPager.php',
@@ -1314,7 +1314,7 @@ $wgAutoloadLocalClasses = array(
 	'UploadFromUrl' => __DIR__ . '/includes/upload/UploadFromUrl.php',
 	'UploadFromUrlJob' => __DIR__ . '/includes/jobqueue/jobs/UploadFromUrlJob.php',
 	'UploadLogFormatter' => __DIR__ . '/includes/logging/UploadLogFormatter.php',
-	'UploadSourceAdapter' => __DIR__ . '/includes/Import.php',
+	'UploadSourceAdapter' => __DIR__ . '/includes/import/UploadSourceAdapter.php',
 	'UploadSourceField' => __DIR__ . '/includes/specials/SpecialUpload.php',
 	'UploadStash' => __DIR__ . '/includes/upload/UploadStash.php',
 	'UploadStashBadPathException' => __DIR__ . '/includes/upload/UploadStash.php',
@@ -1388,11 +1388,11 @@ $wgAutoloadLocalClasses = array(
 	'WikiDiff3' => __DIR__ . '/includes/diff/WikiDiff3.php',
 	'WikiExporter' => __DIR__ . '/includes/Export.php',
 	'WikiFilePage' => __DIR__ . '/includes/page/WikiFilePage.php',
-	'WikiImporter' => __DIR__ . '/includes/Import.php',
+	'WikiImporter' => __DIR__ . '/includes/import/WikiImporter.php',
 	'WikiMap' => __DIR__ . '/includes/WikiMap.php',
 	'WikiPage' => __DIR__ . '/includes/page/WikiPage.php',
 	'WikiReference' => __DIR__ . '/includes/WikiMap.php',
-	'WikiRevision' => __DIR__ . '/includes/Import.php',
+	'WikiRevision' => __DIR__ . '/includes/import/WikiRevision.php',
 	'WikiStatsOutput' => __DIR__ . '/maintenance/language/StatOutputs.php',
 	'WikitextContent' => __DIR__ . '/includes/content/WikitextContent.php',
 	'WikitextContentHandler' => __DIR__ . '/includes/content/WikitextContentHandler.php',
diff --git a/includes/import/ImportSource.php b/includes/import/ImportSource.php
new file mode 100644
index 000000000000..75d20b4eaa99
--- /dev/null
+++ b/includes/import/ImportSource.php
@@ -0,0 +1,51 @@
+<?php
+/**
+ * Source interface for XML import.
+ *
+ * Copyright © 2003,2005 Brion Vibber <brion@pobox.com>
+ * https://www.mediawiki.org/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup SpecialPage
+ */
+
+/**
+ * Source interface for XML import.
+ *
+ * @ingroup SpecialPage
+ */
+interface ImportSource {
+
+	/**
+	 * Indicates whether the end of the input has been reached.
+	 * Will return true after a finite number of calls to readChunk.
+	 *
+	 * @return bool true if there is no more input, false otherwise.
+	 */
+	function atEnd();
+
+	/**
+	 * Return a chunk of the input, as a (possibly empty) string.
+	 * When the end of input is reached, readChunk() returns false.
+	 * If atEnd() returns false, readChunk() will return a string.
+	 * If atEnd() returns true, readChunk() will return false.
+	 *
+	 * @return bool|string
+	 */
+	function readChunk();
+}
diff --git a/includes/import/ImportStreamSource.php b/includes/import/ImportStreamSource.php
new file mode 100644
index 000000000000..0e03d9fbcef4
--- /dev/null
+++ b/includes/import/ImportStreamSource.php
@@ -0,0 +1,172 @@
+<?php
+/**
+ * MediaWiki page data importer.
+ *
+ * Copyright © 2003,2005 Brion Vibber <brion@pobox.com>
+ * https://www.mediawiki.org/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup SpecialPage
+ */
+
+/**
+ * Imports a XML dump from a file (either from file upload, files on disk, or HTTP)
+ * @ingroup SpecialPage
+ */
+class ImportStreamSource implements ImportSource {
+	function __construct( $handle ) {
+		$this->mHandle = $handle;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function atEnd() {
+		return feof( $this->mHandle );
+	}
+
+	/**
+	 * @return string
+	 */
+	function readChunk() {
+		return fread( $this->mHandle, 32768 );
+	}
+
+	/**
+	 * @param string $filename
+	 * @return Status
+	 */
+	static function newFromFile( $filename ) {
+		MediaWiki\suppressWarnings();
+		$file = fopen( $filename, 'rt' );
+		MediaWiki\restoreWarnings();
+		if ( !$file ) {
+			return Status::newFatal( "importcantopen" );
+		}
+		return Status::newGood( new ImportStreamSource( $file ) );
+	}
+
+	/**
+	 * @param string $fieldname
+	 * @return Status
+	 */
+	static function newFromUpload( $fieldname = "xmlimport" ) {
+		$upload =& $_FILES[$fieldname];
+
+		if ( $upload === null || !$upload['name'] ) {
+			return Status::newFatal( 'importnofile' );
+		}
+		if ( !empty( $upload['error'] ) ) {
+			switch ( $upload['error'] ) {
+				case 1:
+					# The uploaded file exceeds the upload_max_filesize directive in php.ini.
+					return Status::newFatal( 'importuploaderrorsize' );
+				case 2:
+					# The uploaded file exceeds the MAX_FILE_SIZE directive that
+					# was specified in the HTML form.
+					return Status::newFatal( 'importuploaderrorsize' );
+				case 3:
+					# The uploaded file was only partially uploaded
+					return Status::newFatal( 'importuploaderrorpartial' );
+				case 6:
+					# Missing a temporary folder.
+					return Status::newFatal( 'importuploaderrortemp' );
+				# case else: # Currently impossible
+			}
+
+		}
+		$fname = $upload['tmp_name'];
+		if ( is_uploaded_file( $fname ) ) {
+			return ImportStreamSource::newFromFile( $fname );
+		} else {
+			return Status::newFatal( 'importnofile' );
+		}
+	}
+
+	/**
+	 * @param string $url
+	 * @param string $method
+	 * @return Status
+	 */
+	static function newFromURL( $url, $method = 'GET' ) {
+		wfDebug( __METHOD__ . ": opening $url\n" );
+		# Use the standard HTTP fetch function; it times out
+		# quicker and sorts out user-agent problems which might
+		# otherwise prevent importing from large sites, such
+		# as the Wikimedia cluster, etc.
+		$data = Http::request( $method, $url, array( 'followRedirects' => true ), __METHOD__ );
+		if ( $data !== false ) {
+			$file = tmpfile();
+			fwrite( $file, $data );
+			fflush( $file );
+			fseek( $file, 0 );
+			return Status::newGood( new ImportStreamSource( $file ) );
+		} else {
+			return Status::newFatal( 'importcantopen' );
+		}
+	}
+
+	/**
+	 * @param string $interwiki
+	 * @param string $page
+	 * @param bool $history
+	 * @param bool $templates
+	 * @param int $pageLinkDepth
+	 * @return Status
+	 */
+	public static function newFromInterwiki( $interwiki, $page, $history = false,
+		$templates = false, $pageLinkDepth = 0
+	) {
+		if ( $page == '' ) {
+			return Status::newFatal( 'import-noarticle' );
+		}
+
+		# Look up the first interwiki prefix, and let the foreign site handle
+		# subsequent interwiki prefixes
+		$firstIwPrefix = strtok( $interwiki, ':' );
+		$firstIw = Interwiki::fetch( $firstIwPrefix );
+		if ( !$firstIw ) {
+			return Status::newFatal( 'importbadinterwiki' );
+		}
+
+		$additionalIwPrefixes = strtok( '' );
+		if ( $additionalIwPrefixes ) {
+			$additionalIwPrefixes .= ':';
+		}
+		# Have to do a DB-key replacement ourselves; otherwise spaces get
+		# URL-encoded to +, which is wrong in this case. Similar to logic in
+		# Title::getLocalURL
+		$link = $firstIw->getURL( strtr( "${additionalIwPrefixes}Special:Export/$page",
+			' ', '_' ) );
+
+		$params = array();
+		if ( $history ) {
+			$params['history'] = 1;
+		}
+		if ( $templates ) {
+			$params['templates'] = 1;
+		}
+		if ( $pageLinkDepth ) {
+			$params['pagelink-depth'] = $pageLinkDepth;
+		}
+
+		$url = wfAppendQuery( $link, $params );
+		# For interwikis, use POST to avoid redirects.
+		return ImportStreamSource::newFromURL( $url, "POST" );
+	}
+}
diff --git a/includes/import/ImportStringSource.php b/includes/import/ImportStringSource.php
new file mode 100644
index 000000000000..85983b1a11eb
--- /dev/null
+++ b/includes/import/ImportStringSource.php
@@ -0,0 +1,57 @@
+<?php
+/**
+ * MediaWiki page data importer.
+ *
+ * Copyright © 2003,2005 Brion Vibber <brion@pobox.com>
+ * https://www.mediawiki.org/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup SpecialPage
+ */
+
+/**
+ * Used for importing XML dumps where the content of the dump is in a string.
+ * This class is ineffecient, and should only be used for small dumps.
+ * For larger dumps, ImportStreamSource should be used instead.
+ *
+ * @ingroup SpecialPage
+ */
+class ImportStringSource implements ImportSource {
+	function __construct( $string ) {
+		$this->mString = $string;
+		$this->mRead = false;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function atEnd() {
+		return $this->mRead;
+	}
+
+	/**
+	 * @return bool|string
+	 */
+	function readChunk() {
+		if ( $this->atEnd() ) {
+			return false;
+		}
+		$this->mRead = true;
+		return $this->mString;
+	}
+}
diff --git a/includes/import/UploadSourceAdapter.php b/includes/import/UploadSourceAdapter.php
new file mode 100644
index 000000000000..17fbdfb43a6a
--- /dev/null
+++ b/includes/import/UploadSourceAdapter.php
@@ -0,0 +1,149 @@
+<?php
+/**
+ * MediaWiki page data importer.
+ *
+ * Copyright © 2003,2005 Brion Vibber <brion@pobox.com>
+ * https://www.mediawiki.org/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup SpecialPage
+ */
+
+/**
+ * This is a horrible hack used to keep source compatibility.
+ * @ingroup SpecialPage
+ */
+class UploadSourceAdapter {
+	/** @var array */
+	public static $sourceRegistrations = array();
+
+	/** @var string */
+	private $mSource;
+
+	/** @var string */
+	private $mBuffer;
+
+	/** @var int */
+	private $mPosition;
+
+	/**
+	 * @param ImportSource $source
+	 * @return string
+	 */
+	static function registerSource( ImportSource $source ) {
+		$id = wfRandomString();
+
+		self::$sourceRegistrations[$id] = $source;
+
+		return $id;
+	}
+
+	/**
+	 * @param string $path
+	 * @param string $mode
+	 * @param array $options
+	 * @param string $opened_path
+	 * @return bool
+	 */
+	function stream_open( $path, $mode, $options, &$opened_path ) {
+		$url = parse_url( $path );
+		$id = $url['host'];
+
+		if ( !isset( self::$sourceRegistrations[$id] ) ) {
+			return false;
+		}
+
+		$this->mSource = self::$sourceRegistrations[$id];
+
+		return true;
+	}
+
+	/**
+	 * @param int $count
+	 * @return string
+	 */
+	function stream_read( $count ) {
+		$return = '';
+		$leave = false;
+
+		while ( !$leave && !$this->mSource->atEnd() &&
+				strlen( $this->mBuffer ) < $count ) {
+			$read = $this->mSource->readChunk();
+
+			if ( !strlen( $read ) ) {
+				$leave = true;
+			}
+
+			$this->mBuffer .= $read;
+		}
+
+		if ( strlen( $this->mBuffer ) ) {
+			$return = substr( $this->mBuffer, 0, $count );
+			$this->mBuffer = substr( $this->mBuffer, $count );
+		}
+
+		$this->mPosition += strlen( $return );
+
+		return $return;
+	}
+
+	/**
+	 * @param string $data
+	 * @return bool
+	 */
+	function stream_write( $data ) {
+		return false;
+	}
+
+	/**
+	 * @return mixed
+	 */
+	function stream_tell() {
+		return $this->mPosition;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function stream_eof() {
+		return $this->mSource->atEnd();
+	}
+
+	/**
+	 * @return array
+	 */
+	function url_stat() {
+		$result = array();
+
+		$result['dev'] = $result[0] = 0;
+		$result['ino'] = $result[1] = 0;
+		$result['mode'] = $result[2] = 0;
+		$result['nlink'] = $result[3] = 0;
+		$result['uid'] = $result[4] = 0;
+		$result['gid'] = $result[5] = 0;
+		$result['rdev'] = $result[6] = 0;
+		$result['size'] = $result[7] = 0;
+		$result['atime'] = $result[8] = 0;
+		$result['mtime'] = $result[9] = 0;
+		$result['ctime'] = $result[10] = 0;
+		$result['blksize'] = $result[11] = 0;
+		$result['blocks'] = $result[12] = 0;
+
+		return $result;
+	}
+}
diff --git a/includes/Import.php b/includes/import/WikiImporter.php
index f59cf47d372f..9bf9282aca92 100644
--- a/includes/Import.php
+++ b/includes/import/WikiImporter.php
@@ -25,7 +25,7 @@
  */
 
 /**
- * XML file reader for the page data importer
+ * XML file reader for the page data importer.
  *
  * implements Special:Import
  * @ingroup SpecialPage
@@ -1068,987 +1068,3 @@ class WikiImporter {
 		return array( $title, $foreignTitle );
 	}
 }
-
-/** This is a horrible hack used to keep source compatibility */
-class UploadSourceAdapter {
-	/** @var array */
-	public static $sourceRegistrations = array();
-
-	/** @var string */
-	private $mSource;
-
-	/** @var string */
-	private $mBuffer;
-
-	/** @var int */
-	private $mPosition;
-
-	/**
-	 * @param ImportSource $source
-	 * @return string
-	 */
-	static function registerSource( ImportSource $source ) {
-		$id = wfRandomString();
-
-		self::$sourceRegistrations[$id] = $source;
-
-		return $id;
-	}
-
-	/**
-	 * @param string $path
-	 * @param string $mode
-	 * @param array $options
-	 * @param string $opened_path
-	 * @return bool
-	 */
-	function stream_open( $path, $mode, $options, &$opened_path ) {
-		$url = parse_url( $path );
-		$id = $url['host'];
-
-		if ( !isset( self::$sourceRegistrations[$id] ) ) {
-			return false;
-		}
-
-		$this->mSource = self::$sourceRegistrations[$id];
-
-		return true;
-	}
-
-	/**
-	 * @param int $count
-	 * @return string
-	 */
-	function stream_read( $count ) {
-		$return = '';
-		$leave = false;
-
-		while ( !$leave && !$this->mSource->atEnd() &&
-				strlen( $this->mBuffer ) < $count ) {
-			$read = $this->mSource->readChunk();
-
-			if ( !strlen( $read ) ) {
-				$leave = true;
-			}
-
-			$this->mBuffer .= $read;
-		}
-
-		if ( strlen( $this->mBuffer ) ) {
-			$return = substr( $this->mBuffer, 0, $count );
-			$this->mBuffer = substr( $this->mBuffer, $count );
-		}
-
-		$this->mPosition += strlen( $return );
-
-		return $return;
-	}
-
-	/**
-	 * @param string $data
-	 * @return bool
-	 */
-	function stream_write( $data ) {
-		return false;
-	}
-
-	/**
-	 * @return mixed
-	 */
-	function stream_tell() {
-		return $this->mPosition;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function stream_eof() {
-		return $this->mSource->atEnd();
-	}
-
-	/**
-	 * @return array
-	 */
-	function url_stat() {
-		$result = array();
-
-		$result['dev'] = $result[0] = 0;
-		$result['ino'] = $result[1] = 0;
-		$result['mode'] = $result[2] = 0;
-		$result['nlink'] = $result[3] = 0;
-		$result['uid'] = $result[4] = 0;
-		$result['gid'] = $result[5] = 0;
-		$result['rdev'] = $result[6] = 0;
-		$result['size'] = $result[7] = 0;
-		$result['atime'] = $result[8] = 0;
-		$result['mtime'] = $result[9] = 0;
-		$result['ctime'] = $result[10] = 0;
-		$result['blksize'] = $result[11] = 0;
-		$result['blocks'] = $result[12] = 0;
-
-		return $result;
-	}
-}
-
-/**
- * @todo document (e.g. one-sentence class description).
- * @ingroup SpecialPage
- */
-class WikiRevision {
-	/** @todo Unused? */
-	public $importer = null;
-
-	/** @var Title */
-	public $title = null;
-
-	/** @var int */
-	public $id = 0;
-
-	/** @var string */
-	public $timestamp = "20010115000000";
-
-	/**
-	 * @var int
-	 * @todo Can't find any uses. Public, because that's suspicious. Get clarity. */
-	public $user = 0;
-
-	/** @var string */
-	public $user_text = "";
-
-	/** @var string */
-	public $model = null;
-
-	/** @var string */
-	public $format = null;
-
-	/** @var string */
-	public $text = "";
-
-	/** @var int */
-	protected $size;
-
-	/** @var Content */
-	public $content = null;
-
-	/** @var ContentHandler */
-	protected $contentHandler = null;
-
-	/** @var string */
-	public $comment = "";
-
-	/** @var bool */
-	public $minor = false;
-
-	/** @var string */
-	public $type = "";
-
-	/** @var string */
-	public $action = "";
-
-	/** @var string */
-	public $params = "";
-
-	/** @var string */
-	public $fileSrc = '';
-
-	/** @var bool|string */
-	public $sha1base36 = false;
-
-	/**
-	 * @var bool
-	 * @todo Unused?
-	 */
-	public $isTemp = false;
-
-	/** @var string */
-	public $archiveName = '';
-
-	protected $filename;
-
-	/** @var mixed */
-	protected $src;
-
-	/** @todo Unused? */
-	public $fileIsTemp;
-
-	/** @var bool */
-	private $mNoUpdates = false;
-
-	/** @var Config $config */
-	private $config;
-
-	public function __construct( Config $config ) {
-		$this->config = $config;
-	}
-
-	/**
-	 * @param Title $title
-	 * @throws MWException
-	 */
-	function setTitle( $title ) {
-		if ( is_object( $title ) ) {
-			$this->title = $title;
-		} elseif ( is_null( $title ) ) {
-			throw new MWException( "WikiRevision given a null title in import. "
-				. "You may need to adjust \$wgLegalTitleChars." );
-		} else {
-			throw new MWException( "WikiRevision given non-object title in import." );
-		}
-	}
-
-	/**
-	 * @param int $id
-	 */
-	function setID( $id ) {
-		$this->id = $id;
-	}
-
-	/**
-	 * @param string $ts
-	 */
-	function setTimestamp( $ts ) {
-		# 2003-08-05T18:30:02Z
-		$this->timestamp = wfTimestamp( TS_MW, $ts );
-	}
-
-	/**
-	 * @param string $user
-	 */
-	function setUsername( $user ) {
-		$this->user_text = $user;
-	}
-
-	/**
-	 * @param string $ip
-	 */
-	function setUserIP( $ip ) {
-		$this->user_text = $ip;
-	}
-
-	/**
-	 * @param string $model
-	 */
-	function setModel( $model ) {
-		$this->model = $model;
-	}
-
-	/**
-	 * @param string $format
-	 */
-	function setFormat( $format ) {
-		$this->format = $format;
-	}
-
-	/**
-	 * @param string $text
-	 */
-	function setText( $text ) {
-		$this->text = $text;
-	}
-
-	/**
-	 * @param string $text
-	 */
-	function setComment( $text ) {
-		$this->comment = $text;
-	}
-
-	/**
-	 * @param bool $minor
-	 */
-	function setMinor( $minor ) {
-		$this->minor = (bool)$minor;
-	}
-
-	/**
-	 * @param mixed $src
-	 */
-	function setSrc( $src ) {
-		$this->src = $src;
-	}
-
-	/**
-	 * @param string $src
-	 * @param bool $isTemp
-	 */
-	function setFileSrc( $src, $isTemp ) {
-		$this->fileSrc = $src;
-		$this->fileIsTemp = $isTemp;
-	}
-
-	/**
-	 * @param string $sha1base36
-	 */
-	function setSha1Base36( $sha1base36 ) {
-		$this->sha1base36 = $sha1base36;
-	}
-
-	/**
-	 * @param string $filename
-	 */
-	function setFilename( $filename ) {
-		$this->filename = $filename;
-	}
-
-	/**
-	 * @param string $archiveName
-	 */
-	function setArchiveName( $archiveName ) {
-		$this->archiveName = $archiveName;
-	}
-
-	/**
-	 * @param int $size
-	 */
-	function setSize( $size ) {
-		$this->size = intval( $size );
-	}
-
-	/**
-	 * @param string $type
-	 */
-	function setType( $type ) {
-		$this->type = $type;
-	}
-
-	/**
-	 * @param string $action
-	 */
-	function setAction( $action ) {
-		$this->action = $action;
-	}
-
-	/**
-	 * @param array $params
-	 */
-	function setParams( $params ) {
-		$this->params = $params;
-	}
-
-	/**
-	 * @param bool $noupdates
-	 */
-	public function setNoUpdates( $noupdates ) {
-		$this->mNoUpdates = $noupdates;
-	}
-
-	/**
-	 * @return Title
-	 */
-	function getTitle() {
-		return $this->title;
-	}
-
-	/**
-	 * @return int
-	 */
-	function getID() {
-		return $this->id;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getTimestamp() {
-		return $this->timestamp;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getUser() {
-		return $this->user_text;
-	}
-
-	/**
-	 * @return string
-	 *
-	 * @deprecated Since 1.21, use getContent() instead.
-	 */
-	function getText() {
-		ContentHandler::deprecated( __METHOD__, '1.21' );
-
-		return $this->text;
-	}
-
-	/**
-	 * @return ContentHandler
-	 */
-	function getContentHandler() {
-		if ( is_null( $this->contentHandler ) ) {
-			$this->contentHandler = ContentHandler::getForModelID( $this->getModel() );
-		}
-
-		return $this->contentHandler;
-	}
-
-	/**
-	 * @return Content
-	 */
-	function getContent() {
-		if ( is_null( $this->content ) ) {
-			$handler = $this->getContentHandler();
-			$this->content = $handler->unserializeContent( $this->text, $this->getFormat() );
-		}
-
-		return $this->content;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getModel() {
-		if ( is_null( $this->model ) ) {
-			$this->model = $this->getTitle()->getContentModel();
-		}
-
-		return $this->model;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getFormat() {
-		if ( is_null( $this->format ) ) {
-			$this->format = $this->getContentHandler()->getDefaultFormat();
-		}
-
-		return $this->format;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getComment() {
-		return $this->comment;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function getMinor() {
-		return $this->minor;
-	}
-
-	/**
-	 * @return mixed
-	 */
-	function getSrc() {
-		return $this->src;
-	}
-
-	/**
-	 * @return bool|string
-	 */
-	function getSha1() {
-		if ( $this->sha1base36 ) {
-			return Wikimedia\base_convert( $this->sha1base36, 36, 16 );
-		}
-		return false;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getFileSrc() {
-		return $this->fileSrc;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function isTempSrc() {
-		return $this->isTemp;
-	}
-
-	/**
-	 * @return mixed
-	 */
-	function getFilename() {
-		return $this->filename;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getArchiveName() {
-		return $this->archiveName;
-	}
-
-	/**
-	 * @return mixed
-	 */
-	function getSize() {
-		return $this->size;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getType() {
-		return $this->type;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getAction() {
-		return $this->action;
-	}
-
-	/**
-	 * @return string
-	 */
-	function getParams() {
-		return $this->params;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function importOldRevision() {
-		$dbw = wfGetDB( DB_MASTER );
-
-		# Sneak a single revision into place
-		$user = User::newFromName( $this->getUser() );
-		if ( $user ) {
-			$userId = intval( $user->getId() );
-			$userText = $user->getName();
-			$userObj = $user;
-		} else {
-			$userId = 0;
-			$userText = $this->getUser();
-			$userObj = new User;
-		}
-
-		// avoid memory leak...?
-		Title::clearCaches();
-
-		$page = WikiPage::factory( $this->title );
-		$page->loadPageData( 'fromdbmaster' );
-		if ( !$page->exists() ) {
-			# must create the page...
-			$pageId = $page->insertOn( $dbw );
-			$created = true;
-			$oldcountable = null;
-		} else {
-			$pageId = $page->getId();
-			$created = false;
-
-			$prior = $dbw->selectField( 'revision', '1',
-				array( 'rev_page' => $pageId,
-					'rev_timestamp' => $dbw->timestamp( $this->timestamp ),
-					'rev_user_text' => $userText,
-					'rev_comment' => $this->getComment() ),
-				__METHOD__
-			);
-			if ( $prior ) {
-				// @todo FIXME: This could fail slightly for multiple matches :P
-				wfDebug( __METHOD__ . ": skipping existing revision for [[" .
-					$this->title->getPrefixedText() . "]], timestamp " . $this->timestamp . "\n" );
-				return false;
-			}
-		}
-
-		// Select previous version to make size diffs correct
-		$prevId = $dbw->selectField( 'revision', 'rev_id',
-			array(
-				'rev_page' => $pageId,
-				'rev_timestamp <= ' . $dbw->addQuotes( $dbw->timestamp( $this->timestamp ) ),
-			),
-			__METHOD__,
-			array( 'ORDER BY' => array(
-					'rev_timestamp DESC',
-					'rev_id DESC', // timestamp is not unique per page
-				)
-			)
-		);
-
-		# @todo FIXME: Use original rev_id optionally (better for backups)
-		# Insert the row
-		$revision = new Revision( array(
-			'title' => $this->title,
-			'page' => $pageId,
-			'content_model' => $this->getModel(),
-			'content_format' => $this->getFormat(),
-			// XXX: just set 'content' => $this->getContent()?
-			'text' => $this->getContent()->serialize( $this->getFormat() ),
-			'comment' => $this->getComment(),
-			'user' => $userId,
-			'user_text' => $userText,
-			'timestamp' => $this->timestamp,
-			'minor_edit' => $this->minor,
-			'parent_id' => $prevId,
-			) );
-		$revision->insertOn( $dbw );
-		$changed = $page->updateIfNewerOn( $dbw, $revision );
-
-		if ( $changed !== false && !$this->mNoUpdates ) {
-			wfDebug( __METHOD__ . ": running updates\n" );
-			// countable/oldcountable stuff is handled in WikiImporter::finishImportPage
-			$page->doEditUpdates(
-				$revision,
-				$userObj,
-				array( 'created' => $created, 'oldcountable' => 'no-change' )
-			);
-		}
-
-		return true;
-	}
-
-	function importLogItem() {
-		$dbw = wfGetDB( DB_MASTER );
-
-		$user = User::newFromName( $this->getUser() );
-		if ( $user ) {
-			$userId = intval( $user->getId() );
-			$userText = $user->getName();
-		} else {
-			$userId = 0;
-			$userText = $this->getUser();
-		}
-
-		# @todo FIXME: This will not record autoblocks
-		if ( !$this->getTitle() ) {
-			wfDebug( __METHOD__ . ": skipping invalid {$this->type}/{$this->action} log time, timestamp " .
-				$this->timestamp . "\n" );
-			return;
-		}
-		# Check if it exists already
-		// @todo FIXME: Use original log ID (better for backups)
-		$prior = $dbw->selectField( 'logging', '1',
-			array( 'log_type' => $this->getType(),
-				'log_action' => $this->getAction(),
-				'log_timestamp' => $dbw->timestamp( $this->timestamp ),
-				'log_namespace' => $this->getTitle()->getNamespace(),
-				'log_title' => $this->getTitle()->getDBkey(),
-				'log_comment' => $this->getComment(),
-				# 'log_user_text' => $this->user_text,
-				'log_params' => $this->params ),
-			__METHOD__
-		);
-		// @todo FIXME: This could fail slightly for multiple matches :P
-		if ( $prior ) {
-			wfDebug( __METHOD__
-				. ": skipping existing item for Log:{$this->type}/{$this->action}, timestamp "
-				. $this->timestamp . "\n" );
-			return;
-		}
-		$log_id = $dbw->nextSequenceValue( 'logging_log_id_seq' );
-		$data = array(
-			'log_id' => $log_id,
-			'log_type' => $this->type,
-			'log_action' => $this->action,
-			'log_timestamp' => $dbw->timestamp( $this->timestamp ),
-			'log_user' =>  $userId,
-			'log_user_text' => $userText,
-			'log_namespace' => $this->getTitle()->getNamespace(),
-			'log_title' => $this->getTitle()->getDBkey(),
-			'log_comment' => $this->getComment(),
-			'log_params' => $this->params
-		);
-		$dbw->insert( 'logging', $data, __METHOD__ );
-	}
-
-	/**
-	 * @return bool
-	 */
-	function importUpload() {
-		# Construct a file
-		$archiveName = $this->getArchiveName();
-		if ( $archiveName ) {
-			wfDebug( __METHOD__ . "Importing archived file as $archiveName\n" );
-			$file = OldLocalFile::newFromArchiveName( $this->getTitle(),
-				RepoGroup::singleton()->getLocalRepo(), $archiveName );
-		} else {
-			$file = wfLocalFile( $this->getTitle() );
-			$file->load( File::READ_LATEST );
-			wfDebug( __METHOD__ . 'Importing new file as ' . $file->getName() . "\n" );
-			if ( $file->exists() && $file->getTimestamp() > $this->getTimestamp() ) {
-				$archiveName = $file->getTimestamp() . '!' . $file->getName();
-				$file = OldLocalFile::newFromArchiveName( $this->getTitle(),
-					RepoGroup::singleton()->getLocalRepo(), $archiveName );
-				wfDebug( __METHOD__ . "File already exists; importing as $archiveName\n" );
-			}
-		}
-		if ( !$file ) {
-			wfDebug( __METHOD__ . ': Bad file for ' . $this->getTitle() . "\n" );
-			return false;
-		}
-
-		# Get the file source or download if necessary
-		$source = $this->getFileSrc();
-		$flags = $this->isTempSrc() ? File::DELETE_SOURCE : 0;
-		if ( !$source ) {
-			$source = $this->downloadSource();
-			$flags |= File::DELETE_SOURCE;
-		}
-		if ( !$source ) {
-			wfDebug( __METHOD__ . ": Could not fetch remote file.\n" );
-			return false;
-		}
-		$sha1 = $this->getSha1();
-		if ( $sha1 && ( $sha1 !== sha1_file( $source ) ) ) {
-			if ( $flags & File::DELETE_SOURCE ) {
-				# Broken file; delete it if it is a temporary file
-				unlink( $source );
-			}
-			wfDebug( __METHOD__ . ": Corrupt file $source.\n" );
-			return false;
-		}
-
-		$user = User::newFromName( $this->user_text );
-
-		# Do the actual upload
-		if ( $archiveName ) {
-			$status = $file->uploadOld( $source, $archiveName,
-				$this->getTimestamp(), $this->getComment(), $user, $flags );
-		} else {
-			$status = $file->upload( $source, $this->getComment(), $this->getComment(),
-				$flags, false, $this->getTimestamp(), $user );
-		}
-
-		if ( $status->isGood() ) {
-			wfDebug( __METHOD__ . ": Successful\n" );
-			return true;
-		} else {
-			wfDebug( __METHOD__ . ': failed: ' . $status->getHTML() . "\n" );
-			return false;
-		}
-	}
-
-	/**
-	 * @return bool|string
-	 */
-	function downloadSource() {
-		if ( !$this->config->get( 'EnableUploads' ) ) {
-			return false;
-		}
-
-		$tempo = tempnam( wfTempDir(), 'download' );
-		$f = fopen( $tempo, 'wb' );
-		if ( !$f ) {
-			wfDebug( "IMPORT: couldn't write to temp file $tempo\n" );
-			return false;
-		}
-
-		// @todo FIXME!
-		$src = $this->getSrc();
-		$data = Http::get( $src, array(), __METHOD__ );
-		if ( !$data ) {
-			wfDebug( "IMPORT: couldn't fetch source $src\n" );
-			fclose( $f );
-			unlink( $tempo );
-			return false;
-		}
-
-		fwrite( $f, $data );
-		fclose( $f );
-
-		return $tempo;
-	}
-
-}
-
-/**
- * Source interface for XML import.
- */
-interface ImportSource {
-
-	/**
-	 * Indicates whether the end of the input has been reached.
-	 * Will return true after a finite number of calls to readChunk.
-	 *
-	 * @return bool true if there is no more input, false otherwise.
-	 */
-	function atEnd();
-
-	/**
-	 * Return a chunk of the input, as a (possibly empty) string.
-	 * When the end of input is reached, readChunk() returns false.
-	 * If atEnd() returns false, readChunk() will return a string.
-	 * If atEnd() returns true, readChunk() will return false.
-	 *
-	 * @return bool|string
-	 */
-	function readChunk();
-}
-
-/**
- * Used for importing XML dumps where the content of the dump is in a string.
- * This class is ineffecient, and should only be used for small dumps.
- * For larger dumps, ImportStreamSource should be used instead.
- *
- * @ingroup SpecialPage
- */
-class ImportStringSource implements ImportSource {
-	function __construct( $string ) {
-		$this->mString = $string;
-		$this->mRead = false;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function atEnd() {
-		return $this->mRead;
-	}
-
-	/**
-	 * @return bool|string
-	 */
-	function readChunk() {
-		if ( $this->atEnd() ) {
-			return false;
-		}
-		$this->mRead = true;
-		return $this->mString;
-	}
-}
-
-/**
- * Imports a XML dump from a file (either from file upload, files on disk, or HTTP)
- * @ingroup SpecialPage
- */
-class ImportStreamSource implements ImportSource {
-	function __construct( $handle ) {
-		$this->mHandle = $handle;
-	}
-
-	/**
-	 * @return bool
-	 */
-	function atEnd() {
-		return feof( $this->mHandle );
-	}
-
-	/**
-	 * @return string
-	 */
-	function readChunk() {
-		return fread( $this->mHandle, 32768 );
-	}
-
-	/**
-	 * @param string $filename
-	 * @return Status
-	 */
-	static function newFromFile( $filename ) {
-		MediaWiki\suppressWarnings();
-		$file = fopen( $filename, 'rt' );
-		MediaWiki\restoreWarnings();
-		if ( !$file ) {
-			return Status::newFatal( "importcantopen" );
-		}
-		return Status::newGood( new ImportStreamSource( $file ) );
-	}
-
-	/**
-	 * @param string $fieldname
-	 * @return Status
-	 */
-	static function newFromUpload( $fieldname = "xmlimport" ) {
-		$upload =& $_FILES[$fieldname];
-
-		if ( $upload === null || !$upload['name'] ) {
-			return Status::newFatal( 'importnofile' );
-		}
-		if ( !empty( $upload['error'] ) ) {
-			switch ( $upload['error'] ) {
-				case 1:
-					# The uploaded file exceeds the upload_max_filesize directive in php.ini.
-					return Status::newFatal( 'importuploaderrorsize' );
-				case 2:
-					# The uploaded file exceeds the MAX_FILE_SIZE directive that
-					# was specified in the HTML form.
-					return Status::newFatal( 'importuploaderrorsize' );
-				case 3:
-					# The uploaded file was only partially uploaded
-					return Status::newFatal( 'importuploaderrorpartial' );
-				case 6:
-					# Missing a temporary folder.
-					return Status::newFatal( 'importuploaderrortemp' );
-				# case else: # Currently impossible
-			}
-
-		}
-		$fname = $upload['tmp_name'];
-		if ( is_uploaded_file( $fname ) ) {
-			return ImportStreamSource::newFromFile( $fname );
-		} else {
-			return Status::newFatal( 'importnofile' );
-		}
-	}
-
-	/**
-	 * @param string $url
-	 * @param string $method
-	 * @return Status
-	 */
-	static function newFromURL( $url, $method = 'GET' ) {
-		wfDebug( __METHOD__ . ": opening $url\n" );
-		# Use the standard HTTP fetch function; it times out
-		# quicker and sorts out user-agent problems which might
-		# otherwise prevent importing from large sites, such
-		# as the Wikimedia cluster, etc.
-		$data = Http::request( $method, $url, array( 'followRedirects' => true ), __METHOD__ );
-		if ( $data !== false ) {
-			$file = tmpfile();
-			fwrite( $file, $data );
-			fflush( $file );
-			fseek( $file, 0 );
-			return Status::newGood( new ImportStreamSource( $file ) );
-		} else {
-			return Status::newFatal( 'importcantopen' );
-		}
-	}
-
-	/**
-	 * @param string $interwiki
-	 * @param string $page
-	 * @param bool $history
-	 * @param bool $templates
-	 * @param int $pageLinkDepth
-	 * @return Status
-	 */
-	public static function newFromInterwiki( $interwiki, $page, $history = false,
-		$templates = false, $pageLinkDepth = 0
-	) {
-		if ( $page == '' ) {
-			return Status::newFatal( 'import-noarticle' );
-		}
-
-		# Look up the first interwiki prefix, and let the foreign site handle
-		# subsequent interwiki prefixes
-		$firstIwPrefix = strtok( $interwiki, ':' );
-		$firstIw = Interwiki::fetch( $firstIwPrefix );
-		if ( !$firstIw ) {
-			return Status::newFatal( 'importbadinterwiki' );
-		}
-
-		$additionalIwPrefixes = strtok( '' );
-		if ( $additionalIwPrefixes ) {
-			$additionalIwPrefixes .= ':';
-		}
-		# Have to do a DB-key replacement ourselves; otherwise spaces get
-		# URL-encoded to +, which is wrong in this case. Similar to logic in
-		# Title::getLocalURL
-		$link = $firstIw->getURL( strtr( "${additionalIwPrefixes}Special:Export/$page",
-			' ', '_' ) );
-
-		$params = array();
-		if ( $history ) {
-			$params['history'] = 1;
-		}
-		if ( $templates ) {
-			$params['templates'] = 1;
-		}
-		if ( $pageLinkDepth ) {
-			$params['pagelink-depth'] = $pageLinkDepth;
-		}
-
-		$url = wfAppendQuery( $link, $params );
-		# For interwikis, use POST to avoid redirects.
-		return ImportStreamSource::newFromURL( $url, "POST" );
-	}
-}
diff --git a/includes/import/WikiRevision.php b/includes/import/WikiRevision.php
new file mode 100644
index 000000000000..9b8c74c87884
--- /dev/null
+++ b/includes/import/WikiRevision.php
@@ -0,0 +1,677 @@
+<?php
+/**
+ * MediaWiki page data importer.
+ *
+ * Copyright © 2003,2005 Brion Vibber <brion@pobox.com>
+ * https://www.mediawiki.org/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @file
+ * @ingroup SpecialPage
+ */
+
+/**
+ * Represents a revision, log entry or upload during the import process.
+ * This class sticks closely to the structure of the XML dump.
+ *
+ * @ingroup SpecialPage
+ */
+class WikiRevision {
+	/** @todo Unused? */
+	public $importer = null;
+
+	/** @var Title */
+	public $title = null;
+
+	/** @var int */
+	public $id = 0;
+
+	/** @var string */
+	public $timestamp = "20010115000000";
+
+	/**
+	 * @var int
+	 * @todo Can't find any uses. Public, because that's suspicious. Get clarity. */
+	public $user = 0;
+
+	/** @var string */
+	public $user_text = "";
+
+	/** @var string */
+	public $model = null;
+
+	/** @var string */
+	public $format = null;
+
+	/** @var string */
+	public $text = "";
+
+	/** @var int */
+	protected $size;
+
+	/** @var Content */
+	public $content = null;
+
+	/** @var ContentHandler */
+	protected $contentHandler = null;
+
+	/** @var string */
+	public $comment = "";
+
+	/** @var bool */
+	public $minor = false;
+
+	/** @var string */
+	public $type = "";
+
+	/** @var string */
+	public $action = "";
+
+	/** @var string */
+	public $params = "";
+
+	/** @var string */
+	public $fileSrc = '';
+
+	/** @var bool|string */
+	public $sha1base36 = false;
+
+	/**
+	 * @var bool
+	 * @todo Unused?
+	 */
+	public $isTemp = false;
+
+	/** @var string */
+	public $archiveName = '';
+
+	protected $filename;
+
+	/** @var mixed */
+	protected $src;
+
+	/** @todo Unused? */
+	public $fileIsTemp;
+
+	/** @var bool */
+	private $mNoUpdates = false;
+
+	/** @var Config $config */
+	private $config;
+
+	public function __construct( Config $config ) {
+		$this->config = $config;
+	}
+
+	/**
+	 * @param Title $title
+	 * @throws MWException
+	 */
+	function setTitle( $title ) {
+		if ( is_object( $title ) ) {
+			$this->title = $title;
+		} elseif ( is_null( $title ) ) {
+			throw new MWException( "WikiRevision given a null title in import. "
+				. "You may need to adjust \$wgLegalTitleChars." );
+		} else {
+			throw new MWException( "WikiRevision given non-object title in import." );
+		}
+	}
+
+	/**
+	 * @param int $id
+	 */
+	function setID( $id ) {
+		$this->id = $id;
+	}
+
+	/**
+	 * @param string $ts
+	 */
+	function setTimestamp( $ts ) {
+		# 2003-08-05T18:30:02Z
+		$this->timestamp = wfTimestamp( TS_MW, $ts );
+	}
+
+	/**
+	 * @param string $user
+	 */
+	function setUsername( $user ) {
+		$this->user_text = $user;
+	}
+
+	/**
+	 * @param string $ip
+	 */
+	function setUserIP( $ip ) {
+		$this->user_text = $ip;
+	}
+
+	/**
+	 * @param string $model
+	 */
+	function setModel( $model ) {
+		$this->model = $model;
+	}
+
+	/**
+	 * @param string $format
+	 */
+	function setFormat( $format ) {
+		$this->format = $format;
+	}
+
+	/**
+	 * @param string $text
+	 */
+	function setText( $text ) {
+		$this->text = $text;
+	}
+
+	/**
+	 * @param string $text
+	 */
+	function setComment( $text ) {
+		$this->comment = $text;
+	}
+
+	/**
+	 * @param bool $minor
+	 */
+	function setMinor( $minor ) {
+		$this->minor = (bool)$minor;
+	}
+
+	/**
+	 * @param mixed $src
+	 */
+	function setSrc( $src ) {
+		$this->src = $src;
+	}
+
+	/**
+	 * @param string $src
+	 * @param bool $isTemp
+	 */
+	function setFileSrc( $src, $isTemp ) {
+		$this->fileSrc = $src;
+		$this->fileIsTemp = $isTemp;
+	}
+
+	/**
+	 * @param string $sha1base36
+	 */
+	function setSha1Base36( $sha1base36 ) {
+		$this->sha1base36 = $sha1base36;
+	}
+
+	/**
+	 * @param string $filename
+	 */
+	function setFilename( $filename ) {
+		$this->filename = $filename;
+	}
+
+	/**
+	 * @param string $archiveName
+	 */
+	function setArchiveName( $archiveName ) {
+		$this->archiveName = $archiveName;
+	}
+
+	/**
+	 * @param int $size
+	 */
+	function setSize( $size ) {
+		$this->size = intval( $size );
+	}
+
+	/**
+	 * @param string $type
+	 */
+	function setType( $type ) {
+		$this->type = $type;
+	}
+
+	/**
+	 * @param string $action
+	 */
+	function setAction( $action ) {
+		$this->action = $action;
+	}
+
+	/**
+	 * @param array $params
+	 */
+	function setParams( $params ) {
+		$this->params = $params;
+	}
+
+	/**
+	 * @param bool $noupdates
+	 */
+	public function setNoUpdates( $noupdates ) {
+		$this->mNoUpdates = $noupdates;
+	}
+
+	/**
+	 * @return Title
+	 */
+	function getTitle() {
+		return $this->title;
+	}
+
+	/**
+	 * @return int
+	 */
+	function getID() {
+		return $this->id;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getTimestamp() {
+		return $this->timestamp;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getUser() {
+		return $this->user_text;
+	}
+
+	/**
+	 * @return string
+	 *
+	 * @deprecated Since 1.21, use getContent() instead.
+	 */
+	function getText() {
+		ContentHandler::deprecated( __METHOD__, '1.21' );
+
+		return $this->text;
+	}
+
+	/**
+	 * @return ContentHandler
+	 */
+	function getContentHandler() {
+		if ( is_null( $this->contentHandler ) ) {
+			$this->contentHandler = ContentHandler::getForModelID( $this->getModel() );
+		}
+
+		return $this->contentHandler;
+	}
+
+	/**
+	 * @return Content
+	 */
+	function getContent() {
+		if ( is_null( $this->content ) ) {
+			$handler = $this->getContentHandler();
+			$this->content = $handler->unserializeContent( $this->text, $this->getFormat() );
+		}
+
+		return $this->content;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getModel() {
+		if ( is_null( $this->model ) ) {
+			$this->model = $this->getTitle()->getContentModel();
+		}
+
+		return $this->model;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getFormat() {
+		if ( is_null( $this->format ) ) {
+			$this->format = $this->getContentHandler()->getDefaultFormat();
+		}
+
+		return $this->format;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getComment() {
+		return $this->comment;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function getMinor() {
+		return $this->minor;
+	}
+
+	/**
+	 * @return mixed
+	 */
+	function getSrc() {
+		return $this->src;
+	}
+
+	/**
+	 * @return bool|string
+	 */
+	function getSha1() {
+		if ( $this->sha1base36 ) {
+			return Wikimedia\base_convert( $this->sha1base36, 36, 16 );
+		}
+		return false;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getFileSrc() {
+		return $this->fileSrc;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function isTempSrc() {
+		return $this->isTemp;
+	}
+
+	/**
+	 * @return mixed
+	 */
+	function getFilename() {
+		return $this->filename;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getArchiveName() {
+		return $this->archiveName;
+	}
+
+	/**
+	 * @return mixed
+	 */
+	function getSize() {
+		return $this->size;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getType() {
+		return $this->type;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getAction() {
+		return $this->action;
+	}
+
+	/**
+	 * @return string
+	 */
+	function getParams() {
+		return $this->params;
+	}
+
+	/**
+	 * @return bool
+	 */
+	function importOldRevision() {
+		$dbw = wfGetDB( DB_MASTER );
+
+		# Sneak a single revision into place
+		$user = User::newFromName( $this->getUser() );
+		if ( $user ) {
+			$userId = intval( $user->getId() );
+			$userText = $user->getName();
+			$userObj = $user;
+		} else {
+			$userId = 0;
+			$userText = $this->getUser();
+			$userObj = new User;
+		}
+
+		// avoid memory leak...?
+		Title::clearCaches();
+
+		$page = WikiPage::factory( $this->title );
+		$page->loadPageData( 'fromdbmaster' );
+		if ( !$page->exists() ) {
+			# must create the page...
+			$pageId = $page->insertOn( $dbw );
+			$created = true;
+			$oldcountable = null;
+		} else {
+			$pageId = $page->getId();
+			$created = false;
+
+			$prior = $dbw->selectField( 'revision', '1',
+				array( 'rev_page' => $pageId,
+					'rev_timestamp' => $dbw->timestamp( $this->timestamp ),
+					'rev_user_text' => $userText,
+					'rev_comment' => $this->getComment() ),
+				__METHOD__
+			);
+			if ( $prior ) {
+				// @todo FIXME: This could fail slightly for multiple matches :P
+				wfDebug( __METHOD__ . ": skipping existing revision for [[" .
+					$this->title->getPrefixedText() . "]], timestamp " . $this->timestamp . "\n" );
+				return false;
+			}
+		}
+
+		// Select previous version to make size diffs correct
+		$prevId = $dbw->selectField( 'revision', 'rev_id',
+			array(
+				'rev_page' => $pageId,
+				'rev_timestamp <= ' . $dbw->timestamp( $this->timestamp ),
+			),
+			__METHOD__,
+			array( 'ORDER BY' => array(
+					'rev_timestamp DESC',
+					'rev_id DESC', // timestamp is not unique per page
+				)
+			)
+		);
+
+		# @todo FIXME: Use original rev_id optionally (better for backups)
+		# Insert the row
+		$revision = new Revision( array(
+			'title' => $this->title,
+			'page' => $pageId,
+			'content_model' => $this->getModel(),
+			'content_format' => $this->getFormat(),
+			// XXX: just set 'content' => $this->getContent()?
+			'text' => $this->getContent()->serialize( $this->getFormat() ),
+			'comment' => $this->getComment(),
+			'user' => $userId,
+			'user_text' => $userText,
+			'timestamp' => $this->timestamp,
+			'minor_edit' => $this->minor,
+			'parent_id' => $prevId,
+			) );
+		$revision->insertOn( $dbw );
+		$changed = $page->updateIfNewerOn( $dbw, $revision );
+
+		if ( $changed !== false && !$this->mNoUpdates ) {
+			wfDebug( __METHOD__ . ": running updates\n" );
+			// countable/oldcountable stuff is handled in WikiImporter::finishImportPage
+			$page->doEditUpdates(
+				$revision,
+				$userObj,
+				array( 'created' => $created, 'oldcountable' => 'no-change' )
+			);
+		}
+
+		return true;
+	}
+
+	function importLogItem() {
+		$dbw = wfGetDB( DB_MASTER );
+		# @todo FIXME: This will not record autoblocks
+		if ( !$this->getTitle() ) {
+			wfDebug( __METHOD__ . ": skipping invalid {$this->type}/{$this->action} log time, timestamp " .
+				$this->timestamp . "\n" );
+			return;
+		}
+		# Check if it exists already
+		// @todo FIXME: Use original log ID (better for backups)
+		$prior = $dbw->selectField( 'logging', '1',
+			array( 'log_type' => $this->getType(),
+				'log_action' => $this->getAction(),
+				'log_timestamp' => $dbw->timestamp( $this->timestamp ),
+				'log_namespace' => $this->getTitle()->getNamespace(),
+				'log_title' => $this->getTitle()->getDBkey(),
+				'log_comment' => $this->getComment(),
+				# 'log_user_text' => $this->user_text,
+				'log_params' => $this->params ),
+			__METHOD__
+		);
+		// @todo FIXME: This could fail slightly for multiple matches :P
+		if ( $prior ) {
+			wfDebug( __METHOD__
+				. ": skipping existing item for Log:{$this->type}/{$this->action}, timestamp "
+				. $this->timestamp . "\n" );
+			return;
+		}
+		$log_id = $dbw->nextSequenceValue( 'logging_log_id_seq' );
+		$data = array(
+			'log_id' => $log_id,
+			'log_type' => $this->type,
+			'log_action' => $this->action,
+			'log_timestamp' => $dbw->timestamp( $this->timestamp ),
+			'log_user' => User::idFromName( $this->user_text ),
+			# 'log_user_text' => $this->user_text,
+			'log_namespace' => $this->getTitle()->getNamespace(),
+			'log_title' => $this->getTitle()->getDBkey(),
+			'log_comment' => $this->getComment(),
+			'log_params' => $this->params
+		);
+		$dbw->insert( 'logging', $data, __METHOD__ );
+	}
+
+	/**
+	 * @return bool
+	 */
+	function importUpload() {
+		# Construct a file
+		$archiveName = $this->getArchiveName();
+		if ( $archiveName ) {
+			wfDebug( __METHOD__ . "Importing archived file as $archiveName\n" );
+			$file = OldLocalFile::newFromArchiveName( $this->getTitle(),
+				RepoGroup::singleton()->getLocalRepo(), $archiveName );
+		} else {
+			$file = wfLocalFile( $this->getTitle() );
+			$file->load( File::READ_LATEST );
+			wfDebug( __METHOD__ . 'Importing new file as ' . $file->getName() . "\n" );
+			if ( $file->exists() && $file->getTimestamp() > $this->getTimestamp() ) {
+				$archiveName = $file->getTimestamp() . '!' . $file->getName();
+				$file = OldLocalFile::newFromArchiveName( $this->getTitle(),
+					RepoGroup::singleton()->getLocalRepo(), $archiveName );
+				wfDebug( __METHOD__ . "File already exists; importing as $archiveName\n" );
+			}
+		}
+		if ( !$file ) {
+			wfDebug( __METHOD__ . ': Bad file for ' . $this->getTitle() . "\n" );
+			return false;
+		}
+
+		# Get the file source or download if necessary
+		$source = $this->getFileSrc();
+		$flags = $this->isTempSrc() ? File::DELETE_SOURCE : 0;
+		if ( !$source ) {
+			$source = $this->downloadSource();
+			$flags |= File::DELETE_SOURCE;
+		}
+		if ( !$source ) {
+			wfDebug( __METHOD__ . ": Could not fetch remote file.\n" );
+			return false;
+		}
+		$sha1 = $this->getSha1();
+		if ( $sha1 && ( $sha1 !== sha1_file( $source ) ) ) {
+			if ( $flags & File::DELETE_SOURCE ) {
+				# Broken file; delete it if it is a temporary file
+				unlink( $source );
+			}
+			wfDebug( __METHOD__ . ": Corrupt file $source.\n" );
+			return false;
+		}
+
+		$user = User::newFromName( $this->user_text );
+
+		# Do the actual upload
+		if ( $archiveName ) {
+			$status = $file->uploadOld( $source, $archiveName,
+				$this->getTimestamp(), $this->getComment(), $user, $flags );
+		} else {
+			$status = $file->upload( $source, $this->getComment(), $this->getComment(),
+				$flags, false, $this->getTimestamp(), $user );
+		}
+
+		if ( $status->isGood() ) {
+			wfDebug( __METHOD__ . ": Successful\n" );
+			return true;
+		} else {
+			wfDebug( __METHOD__ . ': failed: ' . $status->getHTML() . "\n" );
+			return false;
+		}
+	}
+
+	/**
+	 * @return bool|string
+	 */
+	function downloadSource() {
+		if ( !$this->config->get( 'EnableUploads' ) ) {
+			return false;
+		}
+
+		$tempo = tempnam( wfTempDir(), 'download' );
+		$f = fopen( $tempo, 'wb' );
+		if ( !$f ) {
+			wfDebug( "IMPORT: couldn't write to temp file $tempo\n" );
+			return false;
+		}
+
+		// @todo FIXME!
+		$src = $this->getSrc();
+		$data = Http::get( $src, array(), __METHOD__ );
+		if ( !$data ) {
+			wfDebug( "IMPORT: couldn't fetch source $src\n" );
+			fclose( $f );
+			unlink( $tempo );
+			return false;
+		}
+
+		fwrite( $f, $data );
+		fclose( $f );
+
+		return $tempo;
+	}
+
+}