media type detection fails for html documents, results in text/plain instead of text/html

@Test
public void testMediaType() throws Exception {
        List<Document> allDocs = DocumentProvider.docsAsList();
	Map<Document, String> failed = new HashMap<Document, String>();
	for (Document doc : allDocs) {
		Tika tika = new Tika();
		String type = tika.detect(TikaInputStream.get(doc.getFile()));

		if(!doc.getMediaType().toString().equals(type))
				failed.put(doc, type);	
	}
	
	for (Document doc : failed.keySet()) {
		log.error("expected: " + doc.getMediaTypeString() + "; actual: " + failed.get(doc) + ";  path to file: " + doc.getFile().getAbsolutePath());
	}
	assertTrue(failed.isEmpty(), "mime type was incorrectly detected for : " + failed.size() + " documents;");
}