<?php
/**
- * Copyright (C) 2005 Brion Vibber <brion@pobox.com>
+ * Import XML dump files into the current wiki.
+ *
+ * Copyright © 2005 Brion Vibber <brion@pobox.com>
* http://www.mediawiki.org/
*
* This program is free software; you can redistribute it and/or modify
* @ingroup Maintenance
*/
-$optionsWithArgs = array( 'report', 'namespaces' );
-
-require_once( dirname( __FILE__ ) . '/commandLine.inc' );
+require_once( __DIR__ . '/Maintenance.php' );
/**
+ * Maintenance script that imports XML dump files into the current wiki.
+ *
* @ingroup Maintenance
- * @todo port to Maintenance class
*/
-class BackupReader {
- var $reportingInterval = 100;
- var $reporting = true;
- var $pageCount = 0;
- var $revCount = 0;
- var $dryRun = false;
- var $debug = false;
- var $uploads = false;
- var $nsFilter = false;
+class BackupReader extends Maintenance {
+ public $reportingInterval = 100;
+ public $pageCount = 0;
+ public $revCount = 0;
+ public $dryRun = false;
+ public $uploads = false;
+ public $imageBasePath = false;
+ public $nsFilter = false;
function __construct() {
+ parent::__construct();
+ $gz = in_array('compress.zlib', stream_get_wrappers()) ? 'ok' : '(disabled; requires PHP zlib module)';
+ $bz2 = in_array('compress.bzip2', stream_get_wrappers()) ? 'ok' : '(disabled; requires PHP bzip2 module)';
+
+ $this->mDescription = <<<TEXT
+This script reads pages from an XML file as produced from Special:Export or
+dumpBackup.php, and saves them into the current wiki.
+
+Compressed XML files may be read directly:
+ .gz $gz
+ .bz2 $bz2
+ .7z (if 7za executable is in PATH)
+
+Note that for very large data sets, importDump.php may be slow; there are
+alternate methods which can be much faster for full site restoration:
+<http://www.mediawiki.org/wiki/Manual:Importing_XML_dumps>
+TEXT;
$this->stderr = fopen( "php://stderr", "wt" );
+ $this->addOption( 'report',
+ 'Report position and speed after every n pages processed', false, true );
+ $this->addOption( 'namespaces',
+ 'Import only the pages from namespaces belonging to the list of ' .
+ 'pipe-separated namespace names or namespace indexes', false, true );
+ $this->addOption( 'dry-run', 'Parse dump without actually importing pages' );
+ $this->addOption( 'debug', 'Output extra verbose debug information' );
+ $this->addOption( 'uploads', 'Process file upload data if included (experimental)' );
+ $this->addOption( 'no-updates', 'Disable link table updates. Is faster but leaves the wiki in an inconsistent state' );
+ $this->addOption( 'image-base-path', 'Import files from a specified path', false, true );
+ $this->addArg( 'file', 'Dump file to import [else use stdin]', false );
+ }
+
+ public function execute() {
+ if( wfReadOnly() ) {
+ $this->error( "Wiki is in read-only mode; you'll need to disable it for import to work.", true );
+ }
+
+ $this->reportingInterval = intval( $this->getOption( 'report', 100 ) );
+ if ( !$this->reportingInterval ) {
+ $this->reportingInterval = 100; // avoid division by zero
+ }
+
+ $this->dryRun = $this->hasOption( 'dry-run' );
+ $this->uploads = $this->hasOption( 'uploads' ); // experimental!
+ if ( $this->hasOption( 'image-base-path' ) ) {
+ $this->imageBasePath = $this->getOption( 'image-base-path' );
+ }
+ if ( $this->hasOption( 'namespaces' ) ) {
+ $this->setNsfilter( explode( '|', $this->getOption( 'namespaces' ) ) );
+ }
+
+ if( $this->hasArg() ) {
+ $this->importFromFile( $this->getArg() );
+ } else {
+ $this->importFromStdin();
+ }
+
+ $this->output( "Done!\n" );
+ $this->output( "You might want to run rebuildrecentchanges.php to regenerate RecentChanges\n" );
}
function setNsfilter( array $namespaces ) {
if ( strval( $ns ) === $namespace && $wgContLang->getNsText( $ns ) !== false ) {
return $ns;
}
- wfDie( "Unknown namespace text / index specified: $namespace\n" );
+ $this->error( "Unknown namespace text / index specified: $namespace", true );
}
+ /**
+ * @param $obj Title|Revision
+ * @return bool
+ */
private function skippedNamespace( $obj ) {
if ( $obj instanceof Title ) {
$ns = $obj->getNamespace();
$ns = $obj->title->getNamespace();
} else {
echo wfBacktrace();
- wfDie( "Cannot get namespace of object in " . __METHOD__ . "\n" );
+ $this->error( "Cannot get namespace of object in " . __METHOD__, true );
}
return is_array( $this->nsFilter ) && !in_array( $ns, $this->nsFilter );
}
$this->pageCount++;
}
+ /**
+ * @param $rev Revision
+ * @return mixed
+ */
function handleRevision( $rev ) {
$title = $rev->getTitle();
if ( !$title ) {
}
}
+ /**
+ * @param $revision Revision
+ * @return bool
+ */
function handleUpload( $revision ) {
if ( $this->uploads ) {
if ( $this->skippedNamespace( $revision ) ) {
}
function showReport() {
- if ( $this->reporting ) {
- $delta = wfTime() - $this->startTime;
+ if ( !$this->mQuiet ) {
+ $delta = microtime( true ) - $this->startTime;
if ( $delta ) {
$rate = sprintf( "%.2f", $this->pageCount / $delta );
$revrate = sprintf( "%.2f", $this->revCount / $delta );
$revrate = '-';
}
# Logs dumps don't have page tallies
- if ( $this->pageCount )
+ if ( $this->pageCount ) {
$this->progress( "$this->pageCount ($rate pages/sec $revrate revs/sec)" );
- else
+ } else {
$this->progress( "$this->revCount ($revrate revs/sec)" );
+ }
}
- wfWaitForSlaves( 5 );
+ wfWaitForSlaves();
+ // XXX: Don't let deferred jobs array get absurdly large (bug 24375)
+ DeferredUpdates::doUpdates( 'commit' );
}
function progress( $string ) {
function importFromFile( $filename ) {
if ( preg_match( '/\.gz$/', $filename ) ) {
$filename = 'compress.zlib://' . $filename;
- }
- elseif ( preg_match( '/\.bz2$/', $filename ) ) {
+ } elseif ( preg_match( '/\.bz2$/', $filename ) ) {
$filename = 'compress.bzip2://' . $filename;
- }
- elseif ( preg_match( '/\.7z$/', $filename ) ) {
+ } elseif ( preg_match( '/\.7z$/', $filename ) ) {
$filename = 'mediawiki.compress.7z://' . $filename;
}
function importFromStdin() {
$file = fopen( 'php://stdin', 'rt' );
- if( posix_isatty( $file ) ) {
- $this->showHelp();
- exit();
+ if( self::posix_isatty( $file ) ) {
+ $this->maybeHelp( true );
}
return $this->importFromHandle( $file );
}
function importFromHandle( $handle ) {
- $this->startTime = wfTime();
+ $this->startTime = microtime( true );
$source = new ImportStreamSource( $handle );
$importer = new WikiImporter( $source );
- $importer->setDebug( $this->debug );
+ if( $this->hasOption( 'debug' ) ) {
+ $importer->setDebug( true );
+ }
+ if ( $this->hasOption( 'no-updates' ) ) {
+ $importer->setNoUpdates( true );
+ }
$importer->setPageCallback( array( &$this, 'reportPage' ) );
$this->importCallback = $importer->setRevisionCallback(
array( &$this, 'handleRevision' ) );
array( &$this, 'handleUpload' ) );
$this->logItemCallback = $importer->setLogItemCallback(
array( &$this, 'handleLogItem' ) );
+ if ( $this->uploads ) {
+ $importer->setImportUploads( true );
+ }
+ if ( $this->imageBasePath ) {
+ $importer->setImageBasePath( $this->imageBasePath );
+ }
if ( $this->dryRun ) {
$importer->setPageOutCallback( null );
return $importer->doImport();
}
-
- function showHelp() {
- $gz = in_array('compress.zlib', stream_get_wrappers()) ? 'ok' : '(disabled; requires PHP zlib module)';
- $bz2 = in_array('compress.bzip2', stream_get_wrappers()) ? 'ok' : '(disabled; requires PHP bzip2 module)';
- echo "This script reads pages from an XML file as produced from Special:Export\n";
- echo "or dumpBackup.php, and saves them into the current wiki.\n";
- echo "\n";
- echo "Note that for very large data sets, importDump.php may be slow; there are\n";
- echo "alternate methods which can be much faster for full site restoration:\n";
- echo "http://www.mediawiki.org/wiki/Manual:Importing_XML_dumps\n";
- echo "\n";
- echo "Usage: php importDump.php [<options>] [<file>]\n";
- echo "If no file is listed, input may be piped from stdin.\n";
- echo "\n";
- echo "Options:\n";
- echo " --quiet Don't dump status reports to stderr.\n";
- echo " --report=n Report position and speed after every n pages processed.\n";
- echo " --namespaces=a|b|..|z Import only the pages from namespaces belonging to\n";
- echo " the list of pipe-separated namespace names or namespace indexes\n";
- echo " --dry-run Parse dump without actually importing pages.\n";
- echo " --debug Output extra verbose debug information\n";
- echo " --uploads Process file upload data if included (experimental)\n";
- echo "\n";
- echo "Compressed XML files may be read directly:\n";
- echo " .gz $gz\n";
- echo " .bz2 $bz2\n";
- echo " .7z (if 7za executable is in PATH)\n";
- echo "\n";
- }
-}
-
-if ( wfReadOnly() ) {
- wfDie( "Wiki is in read-only mode; you'll need to disable it for import to work.\n" );
-}
-
-$reader = new BackupReader();
-if ( isset( $options['quiet'] ) ) {
- $reader->reporting = false;
-}
-if ( isset( $options['report'] ) ) {
- $reader->reportingInterval = intval( $options['report'] );
-}
-if ( isset( $options['dry-run'] ) ) {
- $reader->dryRun = true;
-}
-if ( isset( $options['debug'] ) ) {
- $reader->debug = true;
-}
-if ( isset( $options['uploads'] ) ) {
- $reader->uploads = true; // experimental!
-}
-if ( isset( $options['namespaces'] ) ) {
- $reader->setNsfilter( explode( '|', $options['namespaces'] ) );
-}
-
-if ( isset( $options['help'] ) ) {
- $reader->showHelp();
- exit();
-} elseif ( isset( $args[0] ) ) {
- $result = $reader->importFromFile( $args[0] );
-} else {
- $result = $reader->importFromStdin();
}
-echo "Done!\n";
-echo "You might want to run rebuildrecentchanges.php to regenerate\n";
-echo "the recentchanges page.\n";
+$maintClass = 'BackupReader';
+require_once( RUN_MAINTENANCE_IF_MAIN );
dépôts / lhc / web / wiklou.git / blobdiff