/**
 * GuestbookFilter.java
 * Pete Willemsen
 * CoolServlets.com
 * February 3, 2000
 * Version 1.0.3
 *
 * Any errors or feature requests can be reported on CoolServlets.com.
 * We hope you enjoy this program!
 *
 *    Copyright (C) 2000  Pete Willemsen
 *
 *    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 com.coolservlets.guestbook;

import java.util.Vector;
import java.util.StringTokenizer;

public class GuestbookFilter {

  public GuestbookFilter( boolean b ) {

      _use_filter = b;
      
      if (b) {
	  _filter_vec = new Vector();
	  _filter_vec.addElement( new String( "fuck" ) );
	  _filter_vec.addElement( new String( "fucking" ) );
	  _filter_vec.addElement( new String( "shit" ) );
	  _filter_vec.addElement( new String( "damn" ) );
	  _filter_vec.addElement( new String( "cunt" ) );
	  _filter_vec.addElement( new String( "bitch" ) );
      }
      
  }

  public GuestbookFilter( boolean b, String filter_list ) {

      _use_filter = b;

      _filter_vec = new Vector();

      String delim_list = ",";
      StringTokenizer st = new StringTokenizer(filter_list, delim_list);      

      while (st.hasMoreTokens()) {
	  String token = st.nextToken();

	  // Remove any leading and ending quotes
	  if ( token.charAt( 0 ) == '"' ) 
	      token = token.substring(1);
	  if ( token.charAt( token.length()-1 ) == '"' ) 
	      token = token.substring( 0, token.length()-1 );

	  // make sure to add the space back
	  _filter_vec.addElement( token );
      }

  }

  public String filterWord( String w ) {
      String ret_string = w;

      // make everything lowercase to ease comparison and use this
      // string for comparison
      String tmp_string = w.toLowerCase();
      
      int i;
      for (i=0; i<_filter_vec.size(); i++) {
	  if ( tmp_string.equals( (String)_filter_vec.elementAt( i ) ) ) {
	      ret_string = "xxxxxx";
	      break;
	  }
      }
      
      return ret_string;
  }

  public String filterBadwords(String message) {
      
      if (message == null) 
	  return "";

      if (_use_filter) {

	  String filtered_message = "";

	  // create the StringTokenizer with a decent set of
	  // "delimiters" to try and separate the words from
	  // everything else.  Characters like ' ', ',', ':', ';',
	  // '/', '\', '[', ']', '(', ')', '{', '}'
	  //
	  // NOTE: make sure an escape-out the '\' character
	  //
	  // Also, we need to have the tokenizer treat the delimiters
	  // as tokens so we can always make sure to put back the
	  // delimiter into the output string.
	  String delim_list = " .,:;@!?#$%^&*+-_=|\\/[](){}";
	  StringTokenizer st = new StringTokenizer(message, delim_list, true);

	  while (st.hasMoreTokens()) {
	      String token = st.nextToken();

	      // In this version, it's not clear whether sending the
	      // single character delimiters into the filterWord
	      // function will be more expensize than doing an initial
	      // check right here.  For the time being, the latter
	      // will be done.
	      
	      // do a quick check if the token has a length of 1 to
	      // see if it's a delimiter
	      if ( token.length() == 1 &&
		   (token.charAt( 0 ) == ' ' || token.charAt( 0 ) == '.' ||
		    token.charAt( 0 ) == ',' || token.charAt( 0 ) == ':' ||
		    token.charAt( 0 ) == ';' || token.charAt( 0 ) == '@' ||
		    token.charAt( 0 ) == '!' || token.charAt( 0 ) == '?' ||
		    token.charAt( 0 ) == '#' || token.charAt( 0 ) == '$' ||
		    token.charAt( 0 ) == '%' || token.charAt( 0 ) == '^' ||
		    token.charAt( 0 ) == '&' || token.charAt( 0 ) == '*' ||
		    token.charAt( 0 ) == '+' || token.charAt( 0 ) == '-' ||
		    token.charAt( 0 ) == '_' || token.charAt( 0 ) == '=' ||
		    token.charAt( 0 ) == '|' || token.charAt( 0 ) == '\\' ||
		    token.charAt( 0 ) == '/' || token.charAt( 0 ) == '[' ||
		    token.charAt( 0 ) == ']' || token.charAt( 0 ) == '(' ||
		    token.charAt( 0 ) == ')' || token.charAt( 0 ) == '{' ||
		    token.charAt( 0 ) == '}') ) {
		  
		  // just append the delimiter
		  filtered_message += token;

	      }
	      else {
		  // filter the word and append
		  filtered_message += filterWord( token );
	      }
	  }

	  return filtered_message;  // no filtering being done yet

      }
      else {
	  return message;
      }
  }

  private Vector  _filter_vec;
  private boolean _use_filter = false;

}