X-Git-Url: http://git.heureux-cyclage.org/?a=blobdiff_plain;f=maintenance%2FimportDump.php;h=c160b0368ac385ab665d27f3a1baf1dc6f001762;hb=bdc31bb9bc995e28b2cf79cba8e95e44513da635;hp=5f47635eb6141dc0cbe0aadec0e4bad924bcbcc4;hpb=617a5b1e15eb52f2fe0b0f7493e6e66eee26c6dd;p=lhc%2Fweb%2Fwiklou.git diff --git a/maintenance/importDump.php b/maintenance/importDump.php index 5f47635eb6..c160b0368a 100644 --- a/maintenance/importDump.php +++ b/maintenance/importDump.php @@ -22,24 +22,108 @@ * @ingroup Maintenance */ -$optionsWithArgs = array( 'report' ); - -require_once( dirname( __FILE__ ) . '/commandLine.inc' ); +require_once( dirname( __FILE__ ) . '/Maintenance.php' ); /** * @ingroup Maintenance */ -class BackupReader { +class BackupReader extends Maintenance { var $reportingInterval = 100; - var $reporting = true; var $pageCount = 0; var $revCount = 0; var $dryRun = false; - var $debug = false; var $uploads = false; + var $imageBasePath = false; + var $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->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( '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 ) ); + $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 ( count( $namespaces ) == 0 ) { + $this->nsFilter = false; + return; + } + $this->nsFilter = array_unique( array_map( array( $this, 'getNsIndex' ), $namespaces ) ); + } + + private function getNsIndex( $namespace ) { + global $wgContLang; + if ( ( $result = $wgContLang->getNsIndex( $namespace ) ) !== false ) { + return $result; + } + $ns = intval( $namespace ); + if ( strval( $ns ) === $namespace && $wgContLang->getNsText( $ns ) !== false ) { + return $ns; + } + $this->error( "Unknown namespace text / index specified: $namespace", true ); + } + + private function skippedNamespace( $obj ) { + if ( $obj instanceof Title ) { + $ns = $obj->getNamespace(); + } elseif ( $obj instanceof Revision ) { + $ns = $obj->getTitle()->getNamespace(); + } elseif ( $obj instanceof WikiRevision ) { + $ns = $obj->title->getNamespace(); + } else { + echo wfBacktrace(); + $this->error( "Cannot get namespace of object in " . __METHOD__, true ); + } + return is_array( $this->nsFilter ) && !in_array( $ns, $this->nsFilter ); } function reportPage( $page ) { @@ -53,6 +137,10 @@ class BackupReader { return; } + if ( $this->skippedNamespace( $title ) ) { + return; + } + $this->revCount++; $this->report(); @@ -63,6 +151,9 @@ class BackupReader { function handleUpload( $revision ) { if ( $this->uploads ) { + if ( $this->skippedNamespace( $revision ) ) { + return; + } $this->uploadCount++; // $this->report(); $this->progress( "upload: " . $revision->getFilename() ); @@ -77,6 +168,9 @@ class BackupReader { } function handleLogItem( $rev ) { + if ( $this->skippedNamespace( $rev ) ) { + return; + } $this->revCount++; $this->report(); @@ -92,7 +186,7 @@ class BackupReader { } function showReport() { - if ( $this->reporting ) { + if ( $this->mQuiet ) { $delta = wfTime() - $this->startTime; if ( $delta ) { $rate = sprintf( "%.2f", $this->pageCount / $delta ); @@ -102,12 +196,15 @@ class BackupReader { $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) + wfDoUpdates( 'commit' ); } function progress( $string ) { @@ -131,6 +228,9 @@ class BackupReader { function importFromStdin() { $file = fopen( 'php://stdin', 'rt' ); + if( posix_isatty( $file ) ) { + $this->maybeHelp( true ); + } return $this->importFromHandle( $file ); } @@ -140,7 +240,9 @@ class BackupReader { $source = new ImportStreamSource( $handle ); $importer = new WikiImporter( $source ); - $importer->setDebug( $this->debug ); + if( $this->hasOption( 'debug' ) ) { + $importer->setDebug( true ); + } $importer->setPageCallback( array( &$this, 'reportPage' ) ); $this->importCallback = $importer->setRevisionCallback( array( &$this, 'handleRevision' ) ); @@ -148,6 +250,12 @@ class BackupReader { 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 ) { $importer->setPageOutCallback( null ); @@ -157,33 +265,5 @@ class BackupReader { } } -if ( wfReadOnly() ) { - wfDie( "Wiki is in read-only mode; you'll need to disable it for import to work.\n" ); -} - -$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( $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 );