docContents = docContents.replaceAll("_", " ");
String[] words = docContents.split("\\s+");
ArrayList<String> tokens = new ArrayList<String>();
for (int i = 0; i < words.length; i++) {
    words[i] = words[i].replaceAll("\\W", "");
    words[i] = words[i].replaceAll("\\d", "");
    if (words[i].length() > 0) {
        tokens.add(words[i]);
    }
}
return tokens;