Zodiac cipher 408: freestanding Python 3 script for converting the plaintext and ciphertext to OpenFst assets

z408.py

#!/usr/bin/env python
#
# Constructs resources for Zodiac cipher 408:
#
#   * Plaintext and ciphertext FARs
#   * Unweighted "key" FSTs and "channel" (hypothesis space) FSTs
#   * A textual symbol table for plaintext and ciphertext
#
# Requires: Pynini and OpenFst with the FAR extension.

import itertools
import os
import subprocess

import pynini


# Output filenames.
PLAINTEXT_TXT = "plaintext.txt"
PLAINTEXT_STD_FST = "plaintext.fst"
PLAINTEXT_LOG_FST = "plaintext-log.fst"
CIPHERTEXT_TXT = "ciphertext.txt"
CIPHERTEXT_STD_FST = "ciphertext.fst"
CIPHERTEXT_LOG_FST = "ciphertext-log.fst"
KEY_STD_FST = "key.fst"
KEY_LOG_FST = "key-log.fst"
CHANNEL_STD_FST = "channel.fst"
CHANNEL_LOG_FST = "channel-log.fst"
SYMBOL_TABLE = "sym.map"


# Plaintext, ciphertext, and a table from plaintext to ciphertext characters.
# The data is drawn from the "Harper key" available here:
#
#     http://zodiackillerciphers.com/408/key.html
#
# Visually similar Unicode codepoints for the non-ASCII ciphertext characters
# were selected using:
#
#     http://shapecatcher.com/
#
# The following interpretations are applied.
#
# Misspellings unlikely to be due to polyphony or encipherment mistakes:
#
# * FORREST for FOREST (fn. 6)
# * EXPERENCE for EXPERIENCE (fn. 10)
# * PARADICE for PARADISE (fn. 14)
# * ANAMAL for ANIMAL (ciphertext ▲, plaintext A [4] and S [3]; could be due to
#   overinking of ciphertext △, read as plaintext I, but treating this as a
#   mispelling allows us to preserve two early cycles)
#
# Mispellings which are probably encipherment mistakes:
#
# * DANGERTUE for DANGEROUS (fn. 8; ciphertext 🜴YE)
# * THAE for THAT (fn. 13; ciphertext N, plaintext E [8])
# * SND for AND (fn. 15; ciphertext ◭, plaintext S [2])
# * SLOI for SLOW (fn. 18; ciphertext △, plaintext I [13])
#
# Other plaintext typos:
#
# * "...AND ALL THE [people?--ed.] I HAVE KILLED"
#
# True polyphones:
#
# * Ciphertext ▲ for plaintext A [4] and S [3]

PLAINTEXT = ("I", "L", "I", "K", "E", "K", "I", "L", "L", "I", "N", "G", "P",
             "E", "O", "P", "L", "E", "B", "E", "C", "A", "U", "S", "E", "I",
             "T", "I", "S", "S", "O", "M", "U", "C", "H", "F", "U", "N", "I",
             "T", "I", "S", "M", "O", "R", "E", "F", "U", "N", "T", "H", "A",
             "N", "K", "I", "L", "L", "I", "N", "G", "W", "I", "L", "D", "G",
             "A", "M", "E", "I", "N", "T", "H", "E", "F", "O", "R", "R", "E",
             "S", "T", "B", "E", "C", "A", "U", "S", "E", "M", "A", "N", "I",
             "S", "T", "H", "E", "M", "O", "S", "T", "D", "A", "N", "G", "E",
             "R", "T", "U", "E", "A", "N", "A", "M", "A", "L", "O", "F", "A",
             "L", "L", "T", "O", "K", "I", "L", "L", "S", "O", "M", "E", "T",
             "H", "I", "N", "G", "G", "I", "V", "E", "S", "M", "E", "T", "H",
             "E", "M", "O", "S", "T", "T", "H", "R", "I", "L", "L", "I", "N",
             "G", "E", "X", "P", "E", "R", "E", "N", "C", "E", "I", "T", "I",
             "S", "E", "V", "E", "N", "B", "E", "T", "T", "E", "R", "T", "H",
             "A", "N", "G", "E", "T", "T", "I", "N", "G", "Y", "O", "U", "R",
             "R", "O", "C", "K", "S", "O", "F", "F", "W", "I", "T", "H", "A",
             "G", "I", "R", "L", "T", "H", "E", "B", "E", "S", "T", "P", "A",
             "R", "T", "O", "F", "I", "T", "I", "S", "T", "H", "A", "E", "W",
             "H", "E", "N", "I", "D", "I", "E", "I", "W", "I", "L", "L", "B",
             "E", "R", "E", "B", "O", "R", "N", "I", "N", "P", "A", "R", "A",
             "D", "I", "C", "E", "S", "N", "D", "A", "L", "L", "T", "H", "E",
             "I", "H", "A", "V", "E", "K", "I", "L", "L", "E", "D", "W", "I",
             "L", "L", "B", "E", "C", "O", "M", "E", "M", "Y", "S", "L", "A",
             "V", "E", "S", "I", "W", "I", "L", "L", "N", "O", "T", "G", "I",
             "V", "E", "Y", "O", "U", "M", "Y", "N", "A", "M", "E", "B", "E",
             "C", "A", "U", "S", "E", "Y", "O", "U", "W", "I", "L", "L", "T",
             "R", "Y", "T", "O", "S", "L", "O", "I", "D", "O", "W", "N", "O",
             "R", "S", "T", "O", "P", "M", "Y", "C", "O", "L", "L", "E", "C",
             "T", "I", "N", "G", "O", "F", "S", "L", "A", "V", "E", "S", "F",
             "O", "R", "M", "Y", "A", "F", "T", "E", "R", "L", "I", "F", "E",
             "E", "B", "E", "O", "R", "I", "E", "T", "E", "M", "E", "T", "H",
             "H", "P", "I", "T", "I",)
assert len(PLAINTEXT) == 408
# A relatively loose reading of the plaintext, with errors corrected, spaces
# and punctuation inserted, and the final padding removed, would read:
#
# "I like killing people because it is so much fun. It is more fun than killing
# wild game in the forest because man is the most dangerous animal of all. To
# kill something gives me the most thrilling experience. It is even better than
# getting your rocks off with a girl. The best part of it is that when I die, I
# will be reborn in paradise and all the people I have killed will become my
# slaves. I will not give you my name because you will try to slow down or stop
# my collecting of slaves for my afterlife."

CIPHERTEXT = (
              # Part 1.
              "△", "◪", "P", "⟋", "Z", "⟋", "U", "B", "◪", "𝈲", "O",
              "R", "⚻", "ꟼ", "X", "⚻", "B",
              "W", "V", "+", "Ǝ", "G", "Y", "F", "ტ", "△", "H", "P",
              "⊡", "K", "🜴", "⌕", "Y", "Ǝ",
              "M", "J", "Y", "Λ", "U", "I", "𝈲", "◭", "⌕", "T", "⥿",
              "N", "Q", "Y", "D", "●", "ꝋ",
              "S", "ϕ", "⟋", "△", "■", "B", "P", "O", "R", "A", "U",
              "◪", "ꟻ", "R", "⅃", "⌕", "E",
              "𝈲", "Λ", "L", "M", "Z", "J", "ᗡ", "Я", "⟍", "ꟼ", "F",
              "H", "V", "W", "Ǝ", "▲", "Y",
              "⊡", "+", "⌕", "G", "D", "△", "K", "I", "ꝋ", "ტ", "⌕",
              "X", "▲", "●", "⌖", "S", "ϕ",
              "R", "N", "⥿", "I", "Y", "E", "⅃", "O", "▲", "⌕", "G",
              "B", "T", "Q", "S", "■", "B",
              "L", "ᗡ", "⟋", "P", "■", "B", "⊡", "X", "⌕", "E", "H",
              "M", "U", "Λ", "R", "R", "𝈲",
              # Part 2.
              "ɔ", "Z", "K", "⌕", "ꟼ", "I", "ꝋ", "W", "⌕", "🜴", "▲",
              "●", "L", "M", "Я", "△", "■",
              "B", "P", "D", "R", "+", "Ꚍ", "⚻", "ტ", "⟍", "N", "ϕ",
              "Ǝ", "E", "U", "H", "𝈲", "F",
              "Z", "ɔ", "ꟼ", "O", "V", "W", "I", "●", "+", "⥿", "L",
              "ꝋ", "⅃", "Λ", "R", "ტ", "H",
              "I", "△", "D", "R", "□", "T", "Y", "Я", "⟍", "ᗡ", "Ǝ",
              "⟋", "⊡", "X", "J", "Q", "A",
              "P", "●", "M", "▲", "R", "U", "⥿", "◪", "L", "ꝋ", "N",
              "V", "E", "K", "H", "⚻", "G",
              "Я", "I", "🜴", "J", "𝈲", "●", "△", "▲", "L", "M", "⅃",
              "N", "A", "ꝋ", "Z", "ϕ", "P",
              "⌖", "U", "ꟼ", "𝈲", "A", "△", "■", "B", "V", "W", "⟍",
              "+", "V", "T", "⥿", "O", "P",
              "Λ", "⚻", "S", "Я", "⅃", "ꟻ", "U", "Ǝ", "ტ", "◭", "D",
              "⌖", "G", "◪", "◪", "I", "M",
              # Part 3.
              "N", "𝈲", "ꝋ", "S", "ɔ", "E", "⟋", "△", "◪", "◪", "Z",
              "ꟻ", "A", "P", "■", "B", "V",
              "ꟼ", "Ǝ", "X", "⌕", "W", "⌕", "□", "F", "■", "▲", "ɔ",
              "+", "⊡", "△", "A", "△", "B",
              "◪", "O", "T", "●", "R", "U", "ɔ", "+", "□", "ᗡ", "Y",
              "⌕", "□", "Λ", "S", "⌕", "W",
              "V", "Z", "Ǝ", "G", "Y", "K", "E", "□", "T", "Y", "A",
              "△", "◪", "■", "L", "⥿", "□",
              "H", "🜴", "F", "B", "X", "△", "⌖", "X", "A", "D", "ᗡ",
              "⟍", "◭", "L", "🜴", "⚻", "⌕",
              "□", "Ǝ", "ᗡ", "■", "■", "ტ", "Ǝ", "●", "P", "O", "R",
              "X", "Q", "F", "◪", "G", "ɔ",
              "Z", "⊡", "J", "T", "⥿", "⌕", "□", "▲", "J", "I", "+",
              "Я", "B", "P", "Q", "W", "ტ",
              "V", "E", "X", "Я", "△", "W", "I", "ტ", "⌕", "E", "H",
              "M", "ꝋ", "⚻", "U", "I", "𝈲",)
assert len(CIPHERTEXT) == 408

KEY = {"A": {"G", "S", "⅃", "▲",},
       "B": {"V",},
       "C": {"Ǝ",},
       "D": {"ꟻ", "⌖",},
       "E": {"Z", "ꟼ", "W", "+", "ტ", "N", "E",},
       "F": {"J", "Q",},
       "G": {"R",},
       "H": {"M", "ꝋ",},
       "I": {"△", "P", "U", "𝈲",},
       "K": {"⟋",},
       "L": {"◪", "B", "■",},
       "M": {"⌕",},
       "N": {"O", "Λ", "D", "ϕ",},
       "O": {"X", "🜴", "T", "ᗡ",},
       "P": {"⚻",},
       "R": {"⥿", "Я", "⟍",},
       "S": {"F", "⊡", "K", "◭", "▲",},
       "T": {"H", "I", "●", "L",},
       "U": {"Y",},
       "V": {"ɔ",},
       "W": {"A",},
       "X": {"Ꚍ",},
       "Y": {"□",},}


def _check_alignment():
  return all(c in KEY[p] for (p, c) in zip(PLAINTEXT, CIPHERTEXT))


def _make_plaintext():
  with open(PLAINTEXT_TXT, "w") as sink:
    print(" ".join(str(ord(p)) for p in PLAINTEXT), file=sink)
  subprocess.check_call(("farcompilestrings", "--arc_type=standard",
                         "--far_type=fst", "--fst_type=compact",
                         PLAINTEXT_TXT, PLAINTEXT_STD_FST))
  subprocess.check_call(("farcompilestrings", "--arc_type=log",
                         "--far_type=fst", "--fst_type=compact",
                         PLAINTEXT_TXT, PLAINTEXT_LOG_FST))
  os.remove(PLAINTEXT_TXT)


def _make_ciphertext():
  with open(CIPHERTEXT_TXT, "w") as sink:
    print(" ".join(str(ord(c)) for c in CIPHERTEXT), file=sink)
  subprocess.check_call(("farcompilestrings", "--arc_type=standard",
                         "--far_type=fst", "--fst_type=compact",
                         CIPHERTEXT_TXT, CIPHERTEXT_STD_FST))
  subprocess.check_call(("farcompilestrings", "--arc_type=log",
                         "--far_type=fst", "--fst_type=compact",
                         CIPHERTEXT_TXT, CIPHERTEXT_LOG_FST))
  os.remove(CIPHERTEXT_TXT)


def _make_key():
  eps = pynini.epsilon_machine()
  # Adds arcs.
  for (plaintext, ciphertexts) in KEY.items():
    plaintext_label = ord(plaintext)
    for ciphertext in ciphertexts:
      ciphertext_label = ord(ciphertext)
      eps.add_arc(0, pynini.Arc(plaintext_label, ciphertext_label, 0, 0))
  # Writes it out.
  eps.write(KEY_STD_FST)
  pynini.arcmap(eps, map_type="to_log").write(KEY_LOG_FST)


def _make_channel():
  eps = pynini.epsilon_machine()
  # Adds arcs.
  for plaintext in KEY.keys():
    plaintext_label = ord(plaintext)
    for ciphertexts in KEY.values():
      for ciphertext in ciphertexts:
        ciphertext_label = ord(ciphertext)
        eps.add_arc(0, pynini.Arc(plaintext_label, ciphertext_label, 0, 0))
  eps = pynini.arcmap(eps, map_type="arc_sum")
  # Writes it out.
  eps.write(CHANNEL_STD_FST)
  pynini.arcmap(eps, map_type="to_log").write(CHANNEL_LOG_FST)


def _make_symbol_table():
  symbols = set()
  # Adds plaintext symbols.
  for plaintext in KEY.keys():
    symbols.add(plaintext)
  # Adds ciphertext symbols.
  for ciphertexts in KEY.values():
    symbols.update(ciphertexts)
  # Writes them into a symbol table.
  sym = pynini.SymbolTable()
  for symbol in sorted(symbols):
    sym.add_symbol(symbol, ord(symbol))
  # Writes it out.
  sym.write_text(SYMBOL_TABLE)


def main():
  assert _check_alignment()
  _make_plaintext()
  _make_ciphertext()
  _make_key()
  _make_channel()
  _make_symbol_table()


if __name__ == "__main__":
  main()

maybe this, not tested:

f = pynini.Fst()
s = f.add_state()
f.set_start(s)
f.set_final(s)