alvinalexander.com | career | drupal | java | mac | mysql | perl | scala | uml | unix  

What this is

This file is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Other links

The source code

// $Header: /home/cvs/jakarta-jmeter/src/protocol/http/org/apache/jmeter/protocol/http/parser/JTidyHTMLParser.java,v 1.12 2004/03/24 03:00:56 sebb Exp $
/*
 * Copyright 2003-2004 The Apache Software Foundation.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 * 
*/

package org.apache.jmeter.protocol.http.parser;

import java.io.ByteArrayInputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.Iterator;

import org.apache.jorphan.logging.LoggingManager;
import org.apache.log.Logger;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.tidy.Tidy;
import org.xml.sax.SAXException;

/**
 * HtmlParser implementation using JTidy.
 * 
 * @version $Revision: 1.12 $ updated on $Date: 2004/03/24 03:00:56 $
 */
class JTidyHTMLParser extends HTMLParser
{
    /** Used to store the Logger (used for debug and error messages). */
    transient private static Logger log = LoggingManager.getLoggerForClass();

    protected JTidyHTMLParser()
    {
        super();
    }

	protected boolean isReusable()
	{
		return true;
	}

    /* (non-Javadoc)
     * @see org.apache.jmeter.protocol.http.parser.HTMLParser#getEmbeddedResourceURLs(byte[], java.net.URL)
     */
    public Iterator getEmbeddedResourceURLs(byte[] html, URL baseUrl, URLCollection urls)
        throws HTMLParseException
    {
		Document dom = null;
		try
		{
			dom = (Document)getDOM(html);
		}
		catch(SAXException se)
		{
            throw new HTMLParseException(se);
		}
        
		// Now parse the DOM tree
		
		scanNodes(dom,urls, baseUrl);

		return urls.iterator();
	}

    /** 
	 * Scan nodes recursively, looking for embedded resources
	 * @param node - initial node
	 * @param urls - container for URLs
	 * @param baseUrl - used to create absolute URLs
     * 
     * @return new base URL
	 */
	private URL scanNodes(Node node, URLCollection urls, URL baseUrl) throws HTMLParseException
	{
		if ( node == null ) {
		  return baseUrl;
	    }

	    String name = node.getNodeName();

	    int type = node.getNodeType();

	    switch ( type ) {

	    case Node.DOCUMENT_NODE:
		  scanNodes(((Document)node).getDocumentElement(),urls,baseUrl);
		  break;

	    case Node.ELEMENT_NODE:
	   
		  NamedNodeMap attrs = node.getAttributes();
		  if (name.equalsIgnoreCase("base"))
		  {
		  	String tmp=getValue(attrs,"href");
		  	if (tmp!=null) try
            {
                baseUrl= new URL(baseUrl, tmp);
            }
            catch (MalformedURLException e)
            {
            	throw new HTMLParseException(e);
            }
		  	break;
		  }
		  
		  if (name.equalsIgnoreCase("img"))
		  {
		  	urls.addURL(getValue(attrs,"src"),baseUrl);
			break;
          }
          
		  if (name.equalsIgnoreCase("applet"))
		  {
		  	urls.addURL(getValue(attrs,"code"),baseUrl);
			  break;
			}
			if (name.equalsIgnoreCase("input"))
			{
				String src=getValue(attrs,"src");
				String typ=getValue(attrs,"type");
				if ((src!=null) &&(typ.equalsIgnoreCase("image")) ){ 
					urls.addURL(src,baseUrl);
				}
			  break;
			}
			if (name.equalsIgnoreCase("link"))
			{
				urls.addURL(getValue(attrs,"href"),baseUrl);
			  break;
			}
			if (name.equalsIgnoreCase("script"))
			{
				urls.addURL(getValue(attrs,"src"),baseUrl);
			  break;
			}
			String back=getValue(attrs,"background");
			if (back != null){
				urls.addURL(back,baseUrl);
				break;
			}

		  NodeList children = node.getChildNodes();
		  if ( children != null ) {
			 int len = children.getLength();
			 for ( int i = 0; i < len; i++ ) {
				baseUrl= scanNodes(children.item(i),urls,baseUrl);
			 }
		  }
		  break;

//	   case Node.TEXT_NODE:
//		  break;

	   }
       
       return baseUrl;

	}

    /*
     * Helper method to get an attribute value, if it exists
     * @param attrs list of attributs
     * @param attname attribute name
     * @return
     */
    private String getValue(NamedNodeMap attrs, String attname)
    {
    	String v=null;
    	Node n = attrs.getNamedItem(attname);
    	if (n != null) v=n.getNodeValue();
        return v;
    }

    /**
     * Returns tidy as HTML parser.
     *
     * @return  a tidy HTML parser
     */
    private static Tidy getTidyParser()
    {
        log.debug("Start : getParser");
        Tidy tidy = new Tidy();
        tidy.setCharEncoding(org.w3c.tidy.Configuration.UTF8);
        tidy.setQuiet(true);
        tidy.setShowWarnings(false);
        if(log.isDebugEnabled())
        {
            log.debug("getParser : tidy parser created - " + tidy);
        }
        log.debug("End   : getParser");
        return tidy;
    }

    /**
     * Returns a node representing a whole xml given an xml document.
     *
     * @param text  an xml document (as a byte array)
     * @return      a node representing a whole xml
     *
     * @throws SAXException indicates an error parsing the xml document
     */
    private static Node getDOM(byte [] text) throws SAXException
    {
        log.debug("Start : getDOM");
        Node node = getTidyParser().parseDOM(new
          ByteArrayInputStream(text), null);
        if(log.isDebugEnabled())
        {
            log.debug("node : " + node);
        }
        log.debug("End   : getDOM");
        return node;
    }
}
... this post is sponsored by my books ...

#1 New Release!

FP Best Seller

 

new blog posts

 

Copyright 1998-2021 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.