Apache Tika Parse Document (Doc, Docx, PDF and Many More)

Apache Tika

 Download Apache Tika Jar: http://www.apache.org/dyn/closer.cgi/tika/tika-app-1.14.jar
 Example: https://tika.apache.org/1.8/examples.html
 CommandLine: java -jar tika-app-1.14.jar test.docx > test.html
 Java Code:

 String target = "File Path";

        File document = new File(target);
        Parser parser = new AutoDetectParser();
//	        ContentHandler handler = new BodyContentHandler();
        ContentHandler handler = new ToXMLContentHandler();

        Metadata metadata = new Metadata();

        try {
            parser.parse(new FileInputStream(document), handler, metadata, new ParseContext());


        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (TikaException e) {
            e.printStackTrace();
        }

//	        System.out.println(metadata);
        System.out.println(handler.toString());