Was mich bewegt Meine Meinung zu Verschiedenem

	import java.io.StringReader;
	import java.io.StringWriter;

	import javax.xml.transform.OutputKeys;
	import javax.xml.transform.Transformer;
	import javax.xml.transform.TransformerFactory;
	import javax.xml.transform.dom.DOMSource;
	import javax.xml.transform.stream.StreamResult;

	import org.apache.html.dom.HTMLDocumentImpl;
	import org.apache.xerces.xni.parser.XMLDocumentFilter;
	import org.cyberneko.html.filters.ElementRemover;
	import org.cyberneko.html.parsers.DOMFragmentParser;
	
	import org.w3c.dom.DocumentFragment;	
	import org.w3c.dom.html.HTMLDocument;
	import org.xml.sax.InputSource;

	org.apache.commons.lang.StringUtils

	…

     /**
	 * cleans up (user provided) string input and makes sure no dangerous markup is left.
	 * 
	 * Allows b, p, br, i, ol, ul,  li, a (with href) and img (with srw, width, height, title) tags
	 * All others are removed with their text content left intact
	 * 
	 * script and iframe tags are removed entirely (including textual content
	 * 
	 * @param input
	 * @return
	 */
	public static String cleanupHtmlFragment(String input) {
		if(isBlank(input))
			return "";
		
		try {
			// create element remover filter
			ElementRemover remover = new ElementRemover();

			// set which elements to accept
			remover.acceptElement("b", null);
			remover.acceptElement("p", null);
			remover.acceptElement("br", null);
			remover.acceptElement("i", null);
			remover.acceptElement("ol", null);
			remover.acceptElement("ul", null);
			remover.acceptElement("li", null);
			remover.acceptElement("a", new String[] { "href", "title" });
			remover.acceptElement("img", new String[] { "src", "width",	"height", "title" });

			// completely remove script and iframe elements
			remover.removeElement("iframe");
			remover.removeElement("script");

			// create writer filter
			org.cyberneko.html.filters.Writer writer = new org.cyberneko.html.filters.Writer();

			// setup filter chain
			XMLDocumentFilter[] filters = { remover, writer, };

			DOMFragmentParser parser = new DOMFragmentParser();
			parser.setProperty("http://cyberneko.org/html/properties/filters",filters);
			parser.setProperty("http://cyberneko.org/html/properties/default-encoding","UTF-8");
			parser.setProperty("http://cyberneko.org/html/properties/names/elems","lower");
			parser.setProperty("http://cyberneko.org/html/properties/doctype/pubid","-//W3C//DTD XHTML 1.0 Transitional//EN");

			HTMLDocument document = new HTMLDocumentImpl();

			DocumentFragment fragment = document.createDocumentFragment();
			parser.parse(new InputSource(new StringReader(input)), fragment);

			Transformer transformer = TransformerFactory.newInstance().newTransformer();
			transformer.setOutputProperty(OutputKeys.INDENT, "yes");
			transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION,"yes");

			StreamResult result = new StreamResult(new StringWriter());
			DOMSource source = new DOMSource(fragment);
			transformer.transform(source, result);
			return result.getWriter().toString();
		} catch (Exception e) {
			log.warn("Couldn't parse string fragment with nekohtml", e);
			return "";
		}
	}