module Addressable::IDNA

Constants

ACE_MAX_LENGTH

ACE_PREFIX

This module is loosely based on idn_actionmailer by Mick Staugaard, the unicode library by Yoshida Masato, and the punycode implementation by Kazuhiro Nishiyama. Most of the code was copied verbatim, but some reformatting was done, and some translation from C was done.

Without their code to work from as a base, we'd all still be relying on the presence of libidn. Which nobody ever seems to have installed.

Original sources: github.com/staugaard/idn_actionmailer www.yoshidam.net/Ruby.html#unicode rubyforge.org/frs/?group_id=2550

COMPOSITION_TABLE

PUNYCODE_BASE

PUNYCODE_DAMP

PUNYCODE_DELIMITER

PUNYCODE_INITIAL_BIAS

PUNYCODE_INITIAL_N

PUNYCODE_MAXINT

PUNYCODE_PRINT_ASCII

PUNYCODE_SKEW

PUNYCODE_TMAX

PUNYCODE_TMIN

UNICODE_DATA

UNICODE_DATA_CANONICAL

UNICODE_DATA_COMBINING_CLASS

UNICODE_DATA_COMPATIBILITY

UNICODE_DATA_EXCLUSION

UNICODE_DATA_LOWERCASE

UNICODE_DATA_TITLECASE

UNICODE_DATA_UPPERCASE

UNICODE_MAX_LENGTH

UTF8_REGEX

UTF8_REGEX_MULTIBYTE

Public Class Methods

to_ascii(value) click to toggle source

# File lib/addressable/idna/native.rb, line 42
def self.to_ascii(value)
  value.to_s.split('.', -1).map do |segment|
    if segment.size > 0 && segment.size < 64
      IDN::Idna.toASCII(segment, IDN::Idna::ALLOW_UNASSIGNED)
    elsif segment.size >= 64
      segment
    else
      ''
    end
  end.join('.')
end

to_unicode(value) click to toggle source

# File lib/addressable/idna/native.rb, line 54
def self.to_unicode(value)
  value.to_s.split('.', -1).map do |segment|
    if segment.size > 0 && segment.size < 64
      IDN::Idna.toUnicode(segment, IDN::Idna::ALLOW_UNASSIGNED)
    elsif segment.size >= 64
      segment
    else
      ''
    end
  end.join('.')
end

unicode_normalize_kc(value) click to toggle source

@deprecated Use {String#unicode_normalize(:nfkc)} instead

# File lib/addressable/idna/native.rb, line 34
def unicode_normalize_kc(value)
  value.to_s.unicode_normalize(:nfkc)
end

Private Class Methods

lookup_unicode_lowercase(codepoint) click to toggle source

# File lib/addressable/idna/pure.rb, line 135
def self.lookup_unicode_lowercase(codepoint)
  codepoint_data = UNICODE_DATA[codepoint]
  (codepoint_data ?
    (codepoint_data[UNICODE_DATA_LOWERCASE] || codepoint) :
    codepoint)
end

punycode_adapt(delta, numpoints, firsttime) click to toggle source

Bias adaptation method

# File lib/addressable/idna/pure.rb, line 4703
def self.punycode_adapt(delta, numpoints, firsttime)
  delta = firsttime ? delta / PUNYCODE_DAMP : delta >> 1
  # delta >> 1 is a faster way of doing delta / 2
  delta += delta / numpoints
  difference = PUNYCODE_BASE - PUNYCODE_TMIN

  k = 0
  while delta > (difference * PUNYCODE_TMAX) / 2
    delta /= difference
    k += PUNYCODE_BASE
  end

  k + (difference + 1) * delta / (delta + PUNYCODE_SKEW)
end

punycode_basic?(codepoint) click to toggle source

# File lib/addressable/idna/pure.rb, line 4671
def self.punycode_basic?(codepoint)
  codepoint < 0x80
end

punycode_decode(value) click to toggle source

# File lib/addressable/idna/native.rb, line 28
def self.punycode_decode(value)
  IDN::Punycode.decode(value.to_s)
end

punycode_decode_digit(codepoint) click to toggle source

Returns the numeric value of a basic codepoint (for use in representing integers) in the range 0 to base - 1, or PUNYCODE_BASE if codepoint does not represent a value.

# File lib/addressable/idna/pure.rb, line 4689
def self.punycode_decode_digit(codepoint)
  if codepoint - 48 < 10
    codepoint - 22
  elsif codepoint - 65 < 26
    codepoint - 65
  elsif codepoint - 97 < 26
    codepoint - 97
  else
    PUNYCODE_BASE
  end
end

punycode_delimiter?(codepoint) click to toggle source

# File lib/addressable/idna/pure.rb, line 4676
def self.punycode_delimiter?(codepoint)
  codepoint == PUNYCODE_DELIMITER
end

punycode_encode(value) click to toggle source

# File lib/addressable/idna/native.rb, line 24
def self.punycode_encode(value)
  IDN::Punycode.encode(value.to_s)
end

punycode_encode_digit(d) click to toggle source

# File lib/addressable/idna/pure.rb, line 4681
def self.punycode_encode_digit(d)
  d + 22 + 75 * ((d < 26) ? 1 : 0)
end

unicode_downcase(input) click to toggle source

Unicode aware downcase method.

@api private @param [String] input

The input string.

@return [String] The downcased result.

# File lib/addressable/idna/pure.rb, line 127
def self.unicode_downcase(input)
  input = input.to_s unless input.is_a?(String)
  unpacked = input.unpack("U*")
  unpacked.map! { |codepoint| lookup_unicode_lowercase(codepoint) }
  return unpacked.pack("U*")
end