module UTF8Util

def self.clean(str)

Returns a copy of this String as valid UTF-8.

Replace invalid UTF-8 character sequences with a replacement character
def self.clean(str)
  clean!(str.dup)
end

def self.clean!(str)

Returns self as valid UTF-8.

Replace invalid UTF-8 character sequences with a replacement character
def self.clean!(str)
  return str if str.encoding.to_s == "UTF-8"
  str.force_encoding("binary").encode("UTF-8", :invalid => :replace, :undef => :replace, :replace => REPLACEMENT_CHAR)
end