open($fileName); // Read relations and search for officeDocument $relations = simplexml_load_string($package->getFromName("_rels/.rels")); foreach ($relations->Relationship as $rel) { if ($rel["Type"] == Zend_Search_Lucene_Document_OpenXml::SCHEMA_OFFICEDOCUMENT) { // Found office document! Search for slides... $slideRelations = simplexml_load_string($package->getFromName( $this->absoluteZipPath(dirname($rel["Target"]) . "/_rels/" . basename($rel["Target"]) . ".rels")) ); foreach ($slideRelations->Relationship as $slideRel) { if ($slideRel["Type"] == Zend_Search_Lucene_Document_Pptx::SCHEMA_SLIDERELATION) { // Found slide! $slides[ str_replace( 'rId', '', (string)$slideRel["Id"] ) ] = simplexml_load_string( $package->getFromName( $this->absoluteZipPath(dirname($rel["Target"]) . "/" . dirname($slideRel["Target"]) . "/" . basename($slideRel["Target"])) ) ); // Search for slide notes $slideNotesRelations = simplexml_load_string($package->getFromName( $this->absoluteZipPath(dirname($rel["Target"]) . "/" . dirname($slideRel["Target"]) . "/_rels/" . basename($slideRel["Target"]) . ".rels")) ); foreach ($slideNotesRelations->Relationship as $slideNoteRel) { if ($slideNoteRel["Type"] == Zend_Search_Lucene_Document_Pptx::SCHEMA_SLIDENOTESRELATION) { // Found slide notes! $slideNotes[ str_replace( 'rId', '', (string)$slideRel["Id"] ) ] = simplexml_load_string( $package->getFromName( $this->absoluteZipPath(dirname($rel["Target"]) . "/" . dirname($slideRel["Target"]) . "/" . dirname($slideNoteRel["Target"]) . "/" . basename($slideNoteRel["Target"])) ) ); break; } } } } break; } } // Sort slides ksort($slides); ksort($slideNotes); // Extract contents from slides foreach ($slides as $slideKey => $slide) { // Register namespaces $slide->registerXPathNamespace("p", Zend_Search_Lucene_Document_Pptx::SCHEMA_PRESENTATIONML); $slide->registerXPathNamespace("a", Zend_Search_Lucene_Document_Pptx::SCHEMA_DRAWINGML); // Fetch all text $textElements = $slide->xpath('//a:t'); foreach ($textElements as $textElement) { $documentBody[] = (string)$textElement; } // Extract contents from slide notes if (isset($slideNotes[$slideKey])) { // Fetch slide note $slideNote = $slideNotes[$slideKey]; // Register namespaces $slideNote->registerXPathNamespace("p", Zend_Search_Lucene_Document_Pptx::SCHEMA_PRESENTATIONML); $slideNote->registerXPathNamespace("a", Zend_Search_Lucene_Document_Pptx::SCHEMA_DRAWINGML); // Fetch all text $textElements = $slideNote->xpath('//a:t'); foreach ($textElements as $textElement) { $documentBody[] = (string)$textElement; } } } // Read core properties $coreProperties = $this->extractMetaData($package); // Close file $package->close(); // Store filename $this->addField(Zend_Search_Lucene_Field::Text('filename', $fileName, 'UTF-8')); // Store contents if ($storeContent) { $this->addField(Zend_Search_Lucene_Field::Text('body', implode(' ', $documentBody), 'UTF-8')); } else { $this->addField(Zend_Search_Lucene_Field::UnStored('body', implode(' ', $documentBody), 'UTF-8')); } // Store meta data properties foreach ($coreProperties as $key => $value) { $this->addField(Zend_Search_Lucene_Field::Text($key, $value, 'UTF-8')); } // Store title (if not present in meta data) if (!isset($coreProperties['title'])) { $this->addField(Zend_Search_Lucene_Field::Text('title', $fileName, 'UTF-8')); } } /** * Load Pptx document from a file * * @param string $fileName * @param boolean $storeContent * @return Zend_Search_Lucene_Document_Pptx */ public static function loadPptxFile($fileName, $storeContent = false) { return new Zend_Search_Lucene_Document_Pptx($fileName, $storeContent); } } } // end if (class_exists('ZipArchive'))