all_utf8_chars_in_file.rb

require "set"

def all_chars_in_file(file)
  all_chars = Set.new
  File.open(file).each_line do |line|
    line.chars.inject(all_chars) { |s,c| s << c }
  end
  all_chars
end

def all_utf8_chars_in_file(file)
  Hash[all_chars_in_file(file).select { |c| c.ord > 255 }.map{|c| ['u%04x' % c.ord, c]}]
end