module Stringex::Unidecoder

Constants

CODEPOINTS

Contains Unicode codepoints, loading as needed from YAML files

Public Class Methods

decode(string) click to toggle source

Returns string with its UTF-8 characters transliterated to ASCII ones

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

# File lib/stringex/unidecoder.rb, line 16
def decode(string)
  string.chars.map{|char| decoded(char)}.join
end
encode(codepoint) click to toggle source

Returns character for the given Unicode codepoint

# File lib/stringex/unidecoder.rb, line 21
def encode(codepoint)
  ["0x#{codepoint}".to_i(16)].pack("U")
end
get_codepoint(character) click to toggle source

Returns Unicode codepoint for the given character

# File lib/stringex/unidecoder.rb, line 26
def get_codepoint(character)
  "%04x" % character.unpack("U")[0]
end
in_yaml_file(character) click to toggle source

Returns string indicating which file (and line) contains the transliteration value for the character

# File lib/stringex/unidecoder.rb, line 32
def in_yaml_file(character)
  unpacked = character.unpack("U")[0]
  "#{code_group(unpacked)}.yml (line #{grouped_point(unpacked) + 2})"
end

Private Class Methods

code_group(unpacked_character) click to toggle source

Returns the Unicode codepoint grouping for the given character

# File lib/stringex/unidecoder.rb, line 58
def code_group(unpacked_character)
  "x%02x" % (unpacked_character >> 8)
end
decoded(character) click to toggle source
# File lib/stringex/unidecoder.rb, line 39
def decoded(character)
  localized(character) || from_yaml(character)
end
from_yaml(character) click to toggle source
# File lib/stringex/unidecoder.rb, line 47
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
grouped_point(unpacked_character) click to toggle source

Returns the index of the given character in the YAML file for its codepoint group

# File lib/stringex/unidecoder.rb, line 63
def grouped_point(unpacked_character)
  unpacked_character & 255
end
localized(character) click to toggle source
# File lib/stringex/unidecoder.rb, line 43
def localized(character)
  Localization.translate(:transliterations, character)
end