import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import static org.apache.tika.metadata.Property.ValueType.URL;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.html.BoilerpipeContentHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ToHTMLContentHandler;
import org.apache.tika.sax.ToXMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

/**
 *
 * @author jonat
 */
public class Rex2nlp {

    /**
     * @param args the command line arguments
     * @return
     * @throws java.io.IOException
     * @throws org.xml.sax.SAXException
     * @throws org.apache.tika.exception.TikaException
     */
 /*   public static void main(String[] args)throws IOException, SAXException, TikaException {
    ContentHandler handler = new BodyContentHandler(
            new ToXMLContentHandler());
  String target = "C:\\Users\\jonat\\Documents\\NetBeansProjects\\rex2nlp\\test.docx";
  File document = new File(target);
    AutoDetectParser parser = new AutoDetectParser();
    Metadata metadata = new Metadata();
        FileInputStream inputstream = new FileInputStream(document);
  parser.parse(inputstream, handler, metadata, new ParseContext());
  System.out.println(handler.toString());
    }
    */
    public static void main(String args[]) throws IOException, SAXException, TikaException {
        AutoDetectParser parser = new AutoDetectParser();
        ContentHandler textHandler = new BodyContentHandler(new ToHTMLContentHandler());

        Metadata xmetadata = new Metadata();
        String target = "C:\\Users\\jonat\\Documents\\NetBeansProjects\\rex2nlp\\test2.docx";
        File document = new File(target);
        FileInputStream inputstream = new FileInputStream(document);
        try  (InputStream stream = inputstream){
            parser.parse(stream, new BoilerpipeContentHandler(textHandler), xmetadata);
            System.out.println("text:\n" + textHandler.toString());
        }
    }

}