import javax.servlet.http.*;
import javax.servlet.*;
import java.io.*;
import java.net.*;
import org.w3c.tidy.*;
import org.w3c.dom.*;
import javax.xml.transform.*;
import javax.xml.transform.stream.*;
import javax.xml.transform.dom.*;

/**
 * <p>Title: </p>
 * <p>Description: </p>
 * <p>Copyright: Copyright (c) 2004</p>
 * <p>Company: </p>
 * @author not attributable
 * @version 1.0
 */

public class Html2Dom extends HttpServlet {
  public Html2Dom() {
  }

   public void processNode( org.w3c.dom.Node currentNode, String p, PrintWriter so )
   {
      switch ( currentNode.getNodeType() ) {

         // process a Document node
         case org.w3c.dom.Node.DOCUMENT_NODE:
            Document doc = ( Document ) currentNode;

            so.println( 
                 "Document node: " + doc.getNodeName() +
                 "\nRoot element: " +
                 doc.getDocumentElement().getNodeName() + "<p>");
            processChildNodes( doc.getChildNodes() , p , so );
            break;

         // process an Element node
//         case org.w3c.dom.Node.ELEMENT_NODE:   
//            so.println( "\nElement node: " + p +
//                                currentNode.getNodeName() + "<p>" );
//            NamedNodeMap attributeNodes =
//               currentNode.getAttributes();
//            for ( int i = 0; i < attributeNodes.getLength(); i++){
//               Attr attribute = ( Attr ) attributeNodes.item( i );

//               so.println( "\tAttribute: " + 
//                  attribute.getNodeName() + " ; Value = " +
//                  attribute.getNodeValue() + "<p>");
//            }

//            processChildNodes( currentNode.getChildNodes() , p+"/"+currentNode.getNodeName(), so);
//            break;

         // process a text node and a CDATA section
         case org.w3c.dom.Node.CDATA_SECTION_NODE:
         case org.w3c.dom.Node.TEXT_NODE: 
            Text text = ( Text ) currentNode;

            if ( !text.getNodeValue().trim().equals( "" ) )
               so.println( "\tText: " +
                                text.getNodeValue() + "<p>");
            break;
      }
   }

   public void processChildNodes( NodeList children, String p, PrintWriter so )
   {
      if ( children.getLength() != 0 ) 

	 for ( int i = 0; i < children.getLength(); i++) {
	     if (children.item( i ).getNodeType() == org.w3c.dom.Node.ELEMENT_NODE) {
		int index = 1;
		String nn = children.item( i ).getNodeName();
		for ( int j = 0; j < i; j++)  
		  if (children.item( j ).getNodeType() == org.w3c.dom.Node.ELEMENT_NODE &&
		      children.item( j ).getNodeName().equals(nn) ) 
	       		index++;
 		
               so.println( "\nElement node: " + p +"/"+nn+"["+index+"]"+ "<p>" );
               NamedNodeMap attributeNodes =
               children.item( i ).getAttributes();

               for ( int a = 0; a < attributeNodes.getLength(); a++){
                Attr attribute = ( Attr ) attributeNodes.item( a );

                 so.println( "\tAttribute: " + 
                  attribute.getNodeName() + " ; Value = " +
                  attribute.getNodeValue() + "<p>");
               }

               processChildNodes( children.item( i ).getChildNodes() , 
		p +"/"+nn+"["+index+"]", so);
      
	     }	else
             processNode( children.item( i ) , p , so );
	 }
   }



  protected void doGet(HttpServletRequest req, HttpServletResponse resp) throws
      ServletException, IOException {


    // get the parameter
    String sourceUrlStr = req.getParameter("sourceURL");
    String xslt1UrlStr = req.getParameter("xslt1URL");
    String xslt2UrlStr = req.getParameter("xslt2URL");

    // open the connection with that url
    URL sourceURL = new URL(sourceUrlStr);
    URLConnection cn = sourceURL.openConnection();

    // parse the html file into dom
    Tidy tidy = new Tidy();
    tidy.setIndentContent(true);
    tidy.setXHTML(true);
    tidy.setWraplen(Integer.MAX_VALUE);
    Document doc = tidy.parseDOM(cn.getInputStream(), null);

    // print out the Dom
    if (xslt1UrlStr.equals(""))
//      tidy.pprint(doc, resp.getOutputStream());
	processNode ( doc, "", resp.getWriter() );
    else {
      try {
        // create the transformer factory object
        TransformerFactory factory = TransformerFactory.newInstance();
        // create the transformer for output
        Transformer t = factory.newTransformer();
        // open connection with xslt1
        URL xslt1URL = new URL(xslt1UrlStr);
        URLConnection xslt1cn = xslt1URL.openConnection();
        // create the transformer for xslt1
        Transformer t1 = factory.newTransformer(new StreamSource(xslt1cn.
            getInputStream()));
        // transformation with xslt1
        DOMResult result1 = new DOMResult();
        t1.transform(new DOMSource(doc), result1);
        // get result node
        org.w3c.dom.Node result = result1.getNode();
        if (!xslt2UrlStr.equals("")){
          // open connection with xslt2
          URL xslt2URL = new URL(xslt2UrlStr);
          URLConnection xslt2cn = xslt2URL.openConnection();
          // create the transformer for xslt2
          Transformer t2 = factory.newTransformer(new StreamSource(xslt2cn.getInputStream()));
          // transformation with xslt2
          DOMResult result2 = new DOMResult();
          t2.transform(new DOMSource(result), result2);
          result = result2.getNode();
        }
        t.transform(new DOMSource(result), new StreamResult(resp.getOutputStream()));
      }
      catch (TransformerException ex1) {
      }
    }
  }
}