gistfile1.rb

  def to_ascii
    s = nil
    begin
      # fast but fails on bad UTF-8 data
      s = self.to_s.unpack('U*').collect { |c| (c <= 127) ? c.chr : translation_hash[c] }.join
    rescue => ex
      # much slower but doesn't
      s = self.chars.split('').collect { |c| (c[0] <= 127) ? c : translation_hash[c[0]] }.join
    end
      
    converter = Iconv.new('ASCII//IGNORE//TRANSLIT', 'UTF-8') 
    converter.iconv(s).unpack('U*').select{ |cp| cp < 127 }.pack('U*')
  end

  def translation_hash
    @@translation_hash ||= setup_translation_hash
  end

  def setup_translation_hash
    accented_chars   = "–—ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝàáâãäåçèéêëìíîïñòóôõöøùúûüý’”‘“\240".chars.split('')
    unaccented_chars = "--AAAAAACEEEEIIIIDNOOOOOxOUUUUYaaaaaaceeeeiiiinoooooouuuuy'\"'\" ".split('')

    translation_hash = {}
    accented_chars.each_with_index { |char, idx| translation_hash[char[0]] = unaccented_chars[idx] }
    translation_hash["Æ".chars[0]] = 'AE'
    translation_hash["æ".chars[0]] = 'ae'
    translation_hash
  end