public ChineseFilter(TokenStream in) 
{
       
        super(in);
        stopTable = new Hashtable(STOP_WORDS.length);
        for (int i = 0; i <  STOP_WORDS.length; i++)
            stopTable.put(STOP_WORDS[i], STOP_WORDS[i]);
}

 public final Token next() throws IOException 
{
        for (Token token = input.next(); token != null; token = input.next()) {
            String text = token.termText();
          // why not key off token type here assuming ChineseTokenizer comes first?
            if (stopTable.get(text) == null) {
                switch (Character.getType(text.charAt(0))) {
                case Character.LOWERCASE_LETTER:
                case Character.UPPERCASE_LETTER:
                    // English word/token should larger than 1 character.
                    if (text.length() >1) {
                        return token;
                    }
                    break;
                case Character.OTHER_LETTER:
                    // One Chinese character as one Chinese word.
                    // Chinese word extraction to be added later here.
                    return token;
                }
            }
        }
        return null;
}