chardump.rb

#!/usr/bin/ruby
# coding: utf-8

def char_as_4hex(c)
  format("%04x", c.ord)
end

REPLACEMENT = "\ufffd"          # �
FSI = "\u2068"                  # First Strong Isolate
PDI = "\u2069"                  # Pop Directional Isolate
LRM = "\u200e"
LRO = "\u202d"
PDF = "\u202c"

def char_as_isolate(c)
  c = REPLACEMENT if c == "\n" || c == "\t"

  #  "#{FSI}#{c}#{PDI}"
  #  "#{LRM}#{c}#{LRM}"
  "#{LRO}#{c}#{PDF}"
end

def dump_chars(char_array)
  elements = char_array.map {|c| char_as_4hex(c)} +
             [":"] +
             char_array.map {|c| char_as_isolate(c) }
  puts elements.join " "
end

ARGF.each_char.each_slice(16) do |ca|
  dump_chars(ca)
end