IPv6 address RE written in an intention-revealing way

ipv6-address-re.rb

# IPv6 address regular expression done right
# [email protected] 2010-02-11

# from a NANOG thread:
# (corrected version of) http://gist.github.com/294476
# Use the tests in that gist if you actually want to change this
ORIGINAL_IPV6_REGEX = /^\s*((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?\s*$/

# Now let's write this down in an intention-revealing way instead
# Yes, I could have chosen better names.

H = '[0-9A-Fa-f]{1,4}'                  # 1-4 hex digits
D = '(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)' # 0..255, no leading zeros
E = '(D(\.D){3})'.gsub(/D/, D)          # IPv4 address

IPV6CORE = %w{
  (H:){7}(H|:)
  (H:){6}(:H|E|:)
  (H:){5}(((:H){1,2})|:E|:)
  (H:){4}(((:H){1,3})|((:H)?:E)|:)
  (H:){3}(((:H){1,4})|((:H){0,2}:E)|:)
  (H:){2}(((:H){1,5})|((:H){0,3}:E)|:)
  (H:){1}(((:H){1,6})|((:H){0,4}:E)|:)
  :(((:H){1,7})|((:H){0,5}:E)|:)
}.map { |l| "(#{l})"}.join("|").gsub(/H/, H).gsub(/E/, E)

IPV6_REGEX =
  Regexp.new('^\s*(IPV6CORE)(%.+)?\s*$'.gsub(/IPV6CORE/, IPV6CORE))

# This RE could be fixed in many ways, e.g., by not allowing just any
# junk after the % character, or by using \A and \z, or by fixing its
# numerous performance shortcomings.  But the point here was to show
# how to write down the original expression properly.
# And that's all we test here, therefore:

if __FILE__ == $0
 require 'test/unit'

 class TC_MyTest < Test::Unit::TestCase
   def test_same
     assert_equal ORIGINAL_IPV6_REGEX, IPV6_REGEX
   end
 end
end