Fix encoding of dubious string in Ruby

fix_encoding.rb

module FixEncoding
  def FixEncoding.fix_encoding(str)
    # The "b" method returns a copied string with encoding ASCII-8BIT
    str = str.b
    # Strip UTF-8 BOM if it's at start of file
    if str =~ /\A\xEF\xBB\xBF/n
      str = str.gsub(/\A\xEF\xBB\xBF/n, '')
    end
    if str =~ /([\xc0-\xff][\x80-\xbf]{1,3})+/n
      # String has actual UTF-8 characters
      str.force_encoding('UTF-8')
    elsif !str.ascii_only?
      # Get rid of Microsoft stupid quotes
      if str =~ /[\x82\x8b\x91\x92\x9b\xb4\x84\x93\x94]/n
        str = str.tr("\x82\x8b\x91\x92\x9b\xb4\x84\x93\x94".b, "''''''\"\"\"")
      end
      # There was no UTF-8, but there are high characters.  Assume to
      # be Latin-1, and then convert to UTF-8
      str.force_encoding('ISO-8859-1').encode('UTF-8')
    else
      # No high characters, just mark as UTF-8
      str.force_encoding('UTF-8')
    end
  end
end