module Stringex::Unidecoder

def code_group(unpacked_character)

Returns the Unicode codepoint grouping for the given character
def code_group(unpacked_character)
  "x%02x" % (unpacked_character >> 8)
end

def decode(string)

You're probably better off just using the added String#to_ascii

Returns string with its UTF-8 characters transliterated to ASCII ones
def decode(string)
  string.chars.map{|char| decoded(char)}.join
end

def decoded(character)

def decoded(character)
  localized(character) || from_yaml(character)
end

def encode(codepoint)

Returns character for the given Unicode codepoint
def encode(codepoint)
  ["0x#{codepoint}".to_i(16)].pack("U")
end

def from_yaml(character)

def from_yaml(character)
  return character unless character.ord > 128
  unpacked = character.unpack("U")[0]
  CODEPOINTS[code_group(unpacked)][grouped_point(unpacked)]
rescue
  # Hopefully this won't come up much
  # TODO: Make this note something to the user that is reportable to me perhaps
  "?"
end

def get_codepoint(character)

Returns Unicode codepoint for the given character
def get_codepoint(character)
  "%04x" % character.unpack("U")[0]
end

def grouped_point(unpacked_character)

Returns the index of the given character in the YAML file for its codepoint group
def grouped_point(unpacked_character)
  unpacked_character & 255
end

def in_yaml_file(character)

transliteration value for the character
Returns string indicating which file (and line) contains the
def in_yaml_file(character)
  unpacked = character.unpack("U")[0]
  "#{code_group(unpacked)}.yml (line #{grouped_point(unpacked) + 2})"
end

def localized(character)

def localized(character)
  Localization.translate(:transliterations, character)
end