public void Convert()
{
byte[] file = Files.toByteArray(new File(@"filename.doc"));
AutoDetectParser tikaParser = new AutoDetectParser();
ByteArrayOutputStream output = new ByteArrayOutputStream();
SAXTransformerFactory factory = (SAXTransformerFactory)TransformerFactory.newInstance();
var inputStream = new ByteArrayInputStream(file);
// ToHTMLContentHandler handler = new ToHTMLContentHandler();
var metaData = new Metadata();
EncodingDetector encodingDetector = new UniversalEncodingDetector();
var encode = encodingDetector.detect(inputStream, metaData) ?? new UTF_32();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, encode.toString());
handler.setResult(new StreamResult(output));
ContentHandler imageRewriting = new ImageRewritingContentHandler(handler);
// ExpandedTitleContentHandler handler1 = new ExpandedTitleContentHandler(handler);
ParseContext context = new ParseContext();
context.set(typeof(EmbeddedDocumentExtractor), new FileEmbeddedDocumentEtractor());
tikaParser.parse(inputStream, imageRewriting, new Metadata(), context);
byte[] array = output.toByteArray();
System.IO.File.WriteAllBytes(@"C:\toHtml\text.html", array);
}
private TransformerHandler getTransformerHandler()
{
SAXTransformerFactory factory = (SAXTransformerFactory)TransformerFactory.newInstance();
TransformerHandler transformerHandler = factory.newTransformerHandler();
transformerHandler.getTransformer().setOutputProperty(OutputKeys.METHOD, "text");
transformerHandler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
_outputWriter = new StringWriter();
transformerHandler.setResult(new StreamResult(_outputWriter));
return(transformerHandler);
}
