#!/usr/bin/env ruby
# vim:ts=2 sw=2 et
# charucs.rb : 將所輸入的字轉換成 ucs2/ucs4/utf8/big5 hex.
# Edward G.J. Lee (06/13/06)
# 2007/08/29 加入 gb2312

require 'iconv'

pname = File.basename($0)
if ARGV.length == 0 or ARGV[0] =~ /-*[Hh].*/
  puts
  puts "Usage: #{pname} your characters"
  puts "       Use space to seperate each character."
  puts
  exit
end

locale = `echo $LC_ALL`.chomp
if locale == ""
  locale = `echo $LC_CTYPE`.chomp
  if locale == ""
    locale = `echo $LANG`.chomp
  end
end
enc = locale.split('.')

def outPut(a, b)
  printf("UCS2/4 : 0x%X (%d)\n", a[0], a[0])
  size = b.length
  if size == 1
    printf("UTF-8  : 0x%X\n", b[0])
  elsif size == 2
    printf("UTF-8  : 0x%X%X\n", b[0], b[1])
  elsif size == 3
    printf("UTF-8  : 0x%X%X%X\n", b[0], b[1], b[2])
  elsif size == 4
    printf("UTF-8  : 0x%X%X%X%X\n", b[0], b[1], b[2], b[3])
  end
end

def outPutb5(b = ["na"])
  puts "Big-5  : 0x" + b[0].to_s.upcase
end

def outPutgb(g = ["na"])
  puts "gb2312 : 0x" + g[0].to_s.upcase
end

ARGV.each do |s|
  if locale =~ /UTF/i
    ucs = s.unpack('U*')
    b5 = Iconv.new('big-5//IGNORE', 'utf-8').iconv(s).unpack('H*')
    gb = Iconv.new('gb2312//IGNORE', 'utf-8').iconv(s).unpack('H*')
    outPut(ucs, s)
    outPutb5(b5)
    outPutgb(gb)
  elsif locale =~ /Big5|BIG5/
    u8 = Iconv.new('utf-8', enc[1]).iconv(s)
    ucs = Iconv.new('utf-8', enc[1]).iconv(s).unpack('U*')
    b5 = s.unpack('H*')
    gb = Iconv.new('gb2312//IGNORE', enc[1]).iconv(s).unpack('H*')
    outPut(ucs, u8)
    outPutb5(b5)
    outPutgb(gb)
  else
    puts "Please use under UTF-8 or Big5 locale."
  end
end