In this program, you will see complete steps to extract content and metadata of Open Office Document Format (ODF).
import java.io.File; import java.io.FileInputStream; import java.io.IOException; import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.odf.OpenDocumentParser; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.SAXException; public class TikaOpenDocumentParserExample { public static void main(final String[] args) throws IOException, SAXException, TikaException { // detecting the file type BodyContentHandler handler = new BodyContentHandler(); Metadata metadata = new Metadata(); FileInputStream inputstream = new FileInputStream(new File("TIKA-OPEN-DOCUMENT.odp")); ParseContext pcontext = new ParseContext(); // Open Document Parser OpenDocumentParser openofficeparser = new OpenDocumentParser(); openofficeparser.parse(inputstream, handler, metadata, pcontext); System.out.println("Contents of the Open Office document:" + handler.toString()); System.out.println("Metadata of the Open Office document:"); String[] metadataNames = metadata.names(); for (String name : metadataNames) { System.out.println(name + " : " + metadata.get(name)); } } }
Output
Contents of the Open Office document:You are in FacingIssuesOnIT.
Learn from Others Experience.
Metadata of the Open Office document:
editing-cycles: 4
meta:creation-date: 2009-04-16T11:32:32.86
dcterms:modified: 2014-09-28T07:46:13.03
meta:save-date: 2014-09-28T07:46:13.03
Last-Modified: 2014-09-28T07:46:13.03
dcterms:created: 2009-04-16T11:32:32.86
date: 2014-09-28T07:46:13.03
modified: 2014-09-28T07:46:13.03
nbObject: 36
Edit-Time: PT32M6S
Creation-Date: 2009-04-16T11:32:32.86
Object-Count: 36
meta:object-count: 36
generator: OpenOffice/4.1.0$Win32 OpenOffice.org_project/410m18$Build-9764
Content-Type: application/vnd.oasis.opendocument.presentation
Last-Save-Date: 2014-09-28T07:46:13.03
You must log in to post a comment.