Use Apache Tika to extract metadata and convert different content types into plain text

ApacheTikaMetadataConvertPlainText

//Use Apache Tika to extract metadata and convert different content types into plain text
//'Whatson' blog series at johnmiedema.com
//http://johnmiedema.com/?tag=whatson

//source documents include different content types
processDocument("resources/mobydick.htm");
processDocument("resources/robinsoncrusoe.txt");
processDocument("resources/callofthewild.pdf");

private static void processDocument(String pathfilename)  {

  try {
  	InputStream input = new FileInputStream(new File(pathfilename));
  	
  	//Apache Tika
  	ContentHandler textHandler = new BodyContentHandler(10*1024*1024);
  	Metadata meta = new Metadata();
  	Parser parser = new AutoDetectParser(); //handles documents in different formats:
  	ParseContext context = new ParseContext();
  	
  	parser.parse(input, textHandler, meta, context);
  	
  	//extract metadata
  	System.out.println("Title: " + meta.get(DublinCore.TITLE));
  	
  	//content is plain text
  	System.out.println("Body: " + textHandler.toString());
  }
  catch  (Exception ex) {
    System.out.println(ex.getMessage());
  }
}