Metodo per prendere e convertire un file doc in HTML. Il file verrà restituito tramite string.

convertDocToHTML.java

/**
 * Copyright (c) 2015 Marco Velluto
 * Warning! It only works with doc files, but NOT working with .docx 
*/
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;


import org.apache.poi.hwpf.HWPFDocumentCore;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.converter.WordToHtmlUtils;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.w3c.dom.Document;

private String convertDocToHTML(String docPath)
    {
        ByteArrayOutputStream out = null;
        String result = null;
        try
        {
            out = new ByteArrayOutputStream();
            HWPFDocumentCore wordDocuemnt = WordToHtmlUtils.loadDoc(new FileInputStream(docPath));
            WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder()
                                                                                                    .newDocument());

            wordToHtmlConverter.processDocument(wordDocuemnt);
            Document htmlDocument = wordToHtmlConverter.getDocument();
            DOMSource domSource = new DOMSource(htmlDocument);
            StreamResult streamResult = new StreamResult(out);

            TransformerFactory transformerFactory = TransformerFactory.newInstance();
            Transformer serializer = transformerFactory.newTransformer();
            serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
            serializer.setOutputProperty(OutputKeys.INDENT, "yes");
            serializer.setOutputProperty(OutputKeys.METHOD, "html");
            serializer.transform(domSource, streamResult);

            result = new String(out.toByteArray());

        }
        catch (IOException e)
        {
            log.error("errore in convertDocToHTML - Errore durante il load del documento a questo path " + docPath, e);
        }
        catch (ParserConfigurationException e)
        {
            log.error("errore in convertDocToHTML - Errore durante la creazione dell'oggetto WordToHtmlConverter ", e);
        }
        catch (TransformerConfigurationException e)
        {
            log.error("errore in convertDocToHTML - Errore durante la creazione dell'oggetto Transformer ", e);
        }
        catch (TransformerException e)
        {
            log.error("errore in convertDocToHTML - Errore durante la serializzazione dell'ogetto con domSource e streamResult ", e);
        }
        finally
        {
            if (out != null)
            {
                try
                {
                    out.close();
                }
                catch (IOException e)
                {}
            }
        }
        return result;

    }