유니코드의 코드를 보는 방법?

루비 언어로 간단하게 구현해보았습니다. 로케일에 따라 잘 출력해줄 것입니다.

#!/usr/bin/ruby -Ku

require 'iconv'
require 'strscan'

def get_iconv
  lcall = ENV['LC_ALL'].split('.')[1].gsub(/[^\w]/, '').downcase
  return Iconv.new(lcall, 'utf-8')
end

def convert_utf8(text)
  ss = StringScanner.new(text)
  $_ = ''
  begin
    until ss.eos?
      if ss.scan(/&#/)
        entity = ss.scan_until(/(x?[0-9a-f]+);/i)
        base = entity[0].chr.downcase == 'x' ? 16 : 10
        $_ << [entity[1...-1].to_i(base)].pack('U*')
      else
        $_ << ss.getch
      end
    end
  rescue
    puts "Error:" + $!
  end
  return $_
end

if $0 == __FILE__
  if ARGV.size == 0
    input = $<.read rescue DATA.read
  elsif ARGV[0] =~ /(-h|--help)/
    puts "Usage: \"#$0 < filename\" or \"#$0 filename\""
    exit 1
  else
    input = open(ARGV[0]).read rescue "Cannot find #{ARGV[0]}"
  end
  utf = convert_utf8(input)
  out = get_iconv
  puts out.iconv(utf)
end

# vim: fenc=utf-8 sts=2 sw=2 et