/* Kweelt - a framework to query XML documents
 * Copyright (C) 2000,  Arnaud Sahuguet (Arnaud.Sahuguet@polytechnique.org)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 */


package xacute.util;

import java.io.PrintWriter;
import java.util.StringTokenizer;

import org.xml.sax.AttributeList;
import org.xml.sax.DocumentHandler;
import org.xml.sax.Locator;
import org.xml.sax.InputSource;

import org.apache.xerces.parsers.SAXParser;

import java.io.FileReader;
import java.util.Iterator;
import java.util.TreeMap;
import java.security.MessageDigest;

/**
 * This class computes the hash of an XML document.
 * Two equivalent documents should have the same hash.
 * issues:
 * - blank spaces
 * - order or attributes
 * We deliberately ignore DTD -- default values, etc. --
 **/

public class HashHandler 
    implements DocumentHandler
{

    MessageDigest md;
    TreeMap sorted;
    
    public HashHandler()
	throws Exception
    {
	this.md = MessageDigest.getInstance("MD5");
	this.sorted = new TreeMap();
    }

    public String toString()
    {
	byte[] hash = md.digest();
	StringBuffer buf = new StringBuffer(hash.length * 2);
	for (int i = 0; i < hash.length; i++)
	    {
                if (((int) hash[i] & 0xff) < 0x10) 
		    buf.append("0");
		buf.append(Long.toString((int) hash[i] & 0xff, 16));
              }
	return buf.toString();
    }
    
    public void characters(char[] ch, int start, int length)
    {
	String data = new String(ch, start, length).replace('\n',' ').replace('\r',' ').replace('\t',' ').trim();
	if (data.length() > 0)
	    md.update( data.getBytes());
	return;
    }
    
    public void endDocument()
    {
	return;
    }
    
    public  void endElement(String name)
    {	
	return;
    }
    
    public void ignorableWhitespace(char[] ch, int start, int length)
    {
	return;
    }

    public void processingInstruction(String target, String data)
    {
            return;
    }

    public void setDocumentLocator(Locator locator)
    {                                   
	return;
    }

    public void startDocument()
    {
	return;
    }

    public void startElement(String name, AttributeList atts)
    {
	md.update(name.getBytes());
	if (atts.getLength() > 0)
	    {
		sorted.clear();
		for (int i=0; i < atts.getLength(); i++)
		    {
			String attName = atts.getName(i);
			String attValue = atts.getValue(i);
			sorted.put(attName, attValue);
		    }
		Iterator keyIter = sorted.keySet().iterator();
		for( ; keyIter.hasNext(); )
		    {
			String attName = (String) keyIter.next();
			md.update(attName.getBytes());
			String attValue = (String) sorted.get(attName);
			md.update(attValue.getBytes());
		    }
	    }
	return;
    }


    public static void main(String args[])
	throws Exception
    {
	 SAXParser parser = new SAXParser(); 
 
	HashHandler hasher = new HashHandler();
	parser.setDocumentHandler(hasher);
	parser.parse( new InputSource( new FileReader(args[0]) ) );
	System.out.println( hasher.toString());
    }
}