sanitize.java

// Newlines, tabs and non-printable unicode characters
private static final String sanitizePattern = "(\\r|\\n|\\t|\\p{C})";

private static final String whitespacePattern = " +";
private static final String replacementString = " ";

private static String sanitize(String text) {
    return text.replaceAll(sanitizePattern, replacementString);
}

private static String normalizeWhitespace(String text) {
    return text.replaceAll(whitespacePattern, replacementString);
}