A sample app of converting a file to html with Apache Tika

Main.java

package jusbrasil.test_tika;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;

import javax.xml.transform.OutputKeys;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.sax.SAXTransformerFactory;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.sax.ExpandedTitleContentHandler;
import org.xml.sax.SAXException;

import com.google.common.io.Files;

public class Main {

  public static void main(String[] args) throws IOException, TransformerConfigurationException, SAXException,
      TikaException {

    byte[] file = Files.toByteArray(new File("/path/to/my/file.doc"));
    AutoDetectParser tikaParser = new AutoDetectParser();

    ByteArrayOutputStream out = new ByteArrayOutputStream();
    SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
    TransformerHandler handler = factory.newTransformerHandler();
    handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
    handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
    handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "UTF-8");
    handler.setResult(new StreamResult(out));
    ExpandedTitleContentHandler handler1 = new ExpandedTitleContentHandler(handler);

    tikaParser.parse(new ByteArrayInputStream(file), handler1, new Metadata());
    System.out.println(new String(out.toByteArray(), "UTF-8"));
  }
}

![Uploading a2a0c430-411a-0133-0a47-0e76e5725d9

d.gif…]()
1.

does this work for pdf and work?

How can we do it in scala

tried this code. but what I see is that formatting is not that good when it compares html there, and I think it's better when we do the same with apache poi conversion, but problem in apache poi is that I am not getting proper solution for .docx to .html conversion