Module: Stringex::Unidecoder

Defined in:
lib/stringex/unidecoder.rb

Constant Summary collapse

CODEPOINTS =

Contains Unicode codepoints, loading as needed from YAML files

Hash.new{|h, k|
  h[k] = ::YAML.load_file(File.join(File.expand_path(File.dirname(__FILE__)), "unidecoder_data", "#{k}.yml"))
}

Class Method Summary collapse

Class Method Details

.decode(string) ⇒ Object

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

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



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
 
# File 'lib/stringex/unidecoder.rb', line 16

def decode(string)
  string.gsub(/[^\x00-\x00]/u) do |codepoint|
    if localized = translate(codepoint)
      localized
    else
      begin
        unpacked = codepoint.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
    end
  end
end

.encode(codepoint) ⇒ Object

Returns character for the given Unicode codepoint



34
35
36
 
# File 'lib/stringex/unidecoder.rb', line 34

def encode(codepoint)
  ["0x#{codepoint}".to_i(16)].pack("U")
end

.get_codepoint(character) ⇒ Object

Returns Unicode codepoint for the given character



39
40
41
 
# File 'lib/stringex/unidecoder.rb', line 39

def get_codepoint(character)
  "%04x" % character.unpack("U")[0]
end

.in_yaml_file(character) ⇒ Object

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



45
46
47
48
 
# File 'lib/stringex/unidecoder.rb', line 45

def in_yaml_file(character)
  unpacked = character.unpack("U")[0]
  "#{code_group(unpacked)}.yml (line #{grouped_point(unpacked) + 2})"
end