Unicode 'property' Web app parser

unicode_property_range_parse.rb

# This snippet is for parsing output from the Unicode 'property' Web app at
# http://unicode.org/cldr/utility/properties.html
#
# Be sure to check the 'Abbreviate' and 'UCD format' boxes, and leave
# 'Escape' unchecked. Copy the hex ranges to an external file, and set its
# path in FILE below.
# Last tested on 2011/06/12
#
# Written by Abe Voelker (http://abevoelker.com)
# Released to the public domain

require 'json' #Could be replaced by active_support

FILE = '' #Set input file here

raise ArgumentError.new("You must set an input file to parse") if FILE == ''

#Monkeypatch the String class to load .. Ranges
class String
  def to_range
    raise ArgumentError.new("Couldn't convert to Range: #{self}") \
      if self.count('.') != 2
    elements = self.split('..')
    return Range.new(elements[0].hex, elements[1].hex)
  end
end

def is_range(range_str)
  return /\.\./ =~ range_str
end

master_array = []
File.foreach(FILE) do |line|
  range_str = line.split(' ')[0]
  if !is_range(range_str)
    master_array.push(range_str.hex)
  else
    master_array.concat(range_str.to_range.to_a)
  end
end

puts master_array.to_json