import string
import collections
-import norms
-import logging
-from segment import segment
-
-# To time a run:
-#
-# import timeit
-# c5a = open('2012/5a.ciphertext', 'r').read()
-# timeit.timeit('keyword_break(c5a)', setup='gc.enable() ; from __main__ import c5a ; from cipher import keyword_break', number=1)
-
-
-logger = logging.getLogger(__name__)
-logger.addHandler(logging.FileHandler('cipher.log'))
-logger.setLevel(logging.WARNING)
-#logger.setLevel(logging.INFO)
-
-english_counts = collections.defaultdict(int)
-with open('count_1l.txt', 'r') as f:
- for line in f:
- (letter, count) = line.split("\t")
- english_counts[letter] = int(count)
-normalised_english_counts = norms.normalise(english_counts)
-
-with open('words.txt', 'r') as f:
- keywords = [line.rstrip() for line in f]
-
-modular_division_table = [[0]*26 for x in range(26)]
-for a in range(26):
- for b in range(26):
- c = (a * b) % 26
- modular_division_table[b][c] = a
-
-modular_division_table_one_based = [[0]*27 for x in range(27)]
-for a in range(27):
- for b in range(27):
- c = ((a * b)-1) % 26 + 1
- modular_division_table_one_based[b][c] = a
-
-
-
-def sanitise(text):
- """Remove all non-alphabetic characters and convert the text to lowercase
-
- >>> sanitise('The Quick')
- 'thequick'
- >>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
- 'thequickbrownfoxjumpedoverthelazydog'
+import math
+from enum import Enum
+from itertools import zip_longest, cycle, chain, count
+import numpy as np
+from numpy import matrix
+from numpy import linalg
+from language_models import *
+import pprint
+
+
+
+from utilities import *
+from segment import *
+
+from caesar import *
+from affine import *
+from keyword import *
+from polybius import *
+from column_transposition import *
+from railfence import *
+
+
+def make_cadenus_keycolumn(doubled_letters = 'vw', start='a', reverse=False):
+ """Makes the key column for a Cadenus cipher (the column down between the
+ rows of letters)
+
+ >>> make_cadenus_keycolumn()['a']
+ 0
+ >>> make_cadenus_keycolumn()['b']
+ 1
+ >>> make_cadenus_keycolumn()['c']
+ 2
+ >>> make_cadenus_keycolumn()['v']
+ 21
+ >>> make_cadenus_keycolumn()['w']
+ 21
+ >>> make_cadenus_keycolumn()['z']
+ 24
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['a']
+ 1
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['b']
+ 0
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['c']
+ 24
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['i']
+ 18
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['j']
+ 18
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['v']
+ 6
+ >>> make_cadenus_keycolumn(doubled_letters='ij', start='b', reverse=True)['z']
+ 2
"""
- sanitised = [c.lower() for c in text if c in string.ascii_letters]
- return ''.join(sanitised)
-
-def ngrams(text, n):
- """Returns all n-grams of a text
-
- >>> ngrams(sanitise('the quick brown fox'), 2)
- [('t', 'h'), ('h', 'e'), ('e', 'q'), ('q', 'u'), ('u', 'i'), ('i', 'c'), ('c', 'k'), ('k', 'b'), ('b', 'r'), ('r', 'o'), ('o', 'w'), ('w', 'n'), ('n', 'f'), ('f', 'o'), ('o', 'x')]
- >>> ngrams(sanitise('the quick brown fox'), 4)
- [('t', 'h', 'e', 'q'), ('h', 'e', 'q', 'u'), ('e', 'q', 'u', 'i'), ('q', 'u', 'i', 'c'), ('u', 'i', 'c', 'k'), ('i', 'c', 'k', 'b'), ('c', 'k', 'b', 'r'), ('k', 'b', 'r', 'o'), ('b', 'r', 'o', 'w'), ('r', 'o', 'w', 'n'), ('o', 'w', 'n', 'f'), ('w', 'n', 'f', 'o'), ('n', 'f', 'o', 'x')]
+ index_to_remove = string.ascii_lowercase.find(doubled_letters[0])
+ short_alphabet = string.ascii_lowercase[:index_to_remove] + string.ascii_lowercase[index_to_remove+1:]
+ if reverse:
+ short_alphabet = cat(reversed(short_alphabet))
+ start_pos = short_alphabet.find(start)
+ rotated_alphabet = short_alphabet[start_pos:] + short_alphabet[:start_pos]
+ keycolumn = {l: i for i, l in enumerate(rotated_alphabet)}
+ keycolumn[doubled_letters[0]] = keycolumn[doubled_letters[1]]
+ return keycolumn
+
+def cadenus_encipher(message, keyword, keycolumn, fillvalue='a'):
+ """Encipher with the Cadenus cipher
+
+ >>> cadenus_encipher(sanitise('Whoever has made a voyage up the Hudson ' \
+ 'must remember the Kaatskill mountains. ' \
+ 'They are a dismembered branch of the great'), \
+ 'wink', \
+ make_cadenus_keycolumn(doubled_letters='vw', start='a', reverse=True))
+ 'antodeleeeuhrsidrbhmhdrrhnimefmthgeaetakseomehetyaasuvoyegrastmmuuaeenabbtpchehtarorikswosmvaleatned'
+ >>> cadenus_encipher(sanitise('a severe limitation on the usefulness of ' \
+ 'the cadenus is that every message must be ' \
+ 'a multiple of twenty-five letters long'), \
+ 'easy', \
+ make_cadenus_keycolumn(doubled_letters='vw', start='a', reverse=True))
+ 'systretomtattlusoatleeesfiyheasdfnmschbhneuvsnpmtofarenuseieeieltarlmentieetogevesitfaisltngeeuvowul'
"""
- return [tuple(text[i:i+n]) for i in range(len(text)-n+1)]
-
-def letter_frequencies(text):
- """Count the number of occurrences of each character in text
-
- >>> sorted(letter_frequencies('abcdefabc').items())
- [('a', 2), ('b', 2), ('c', 2), ('d', 1), ('e', 1), ('f', 1)]
- >>> sorted(letter_frequencies('the quick brown fox jumped over the lazy dog').items())
- [(' ', 8), ('a', 1), ('b', 1), ('c', 1), ('d', 2), ('e', 4), ('f', 1), ('g', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('n', 1), ('o', 4), ('p', 1), ('q', 1), ('r', 2), ('t', 2), ('u', 2), ('v', 1), ('w', 1), ('x', 1), ('y', 1), ('z', 1)]
- >>> sorted(letter_frequencies('The Quick BROWN fox jumped! over... the (9lazy) DOG').items())
- [(' ', 8), ('!', 1), ('(', 1), (')', 1), ('.', 3), ('9', 1), ('B', 1), ('D', 1), ('G', 1), ('N', 1), ('O', 2), ('Q', 1), ('R', 1), ('T', 1), ('W', 1), ('a', 1), ('c', 1), ('d', 1), ('e', 4), ('f', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('o', 2), ('p', 1), ('r', 1), ('t', 1), ('u', 2), ('v', 1), ('x', 1), ('y', 1), ('z', 1)]
- >>> sorted(letter_frequencies(sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')).items())
- [('a', 1), ('b', 1), ('c', 1), ('d', 2), ('e', 4), ('f', 1), ('g', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('n', 1), ('o', 4), ('p', 1), ('q', 1), ('r', 2), ('t', 2), ('u', 2), ('v', 1), ('w', 1), ('x', 1), ('y', 1), ('z', 1)]
+ rows = chunks(message, len(message) // 25, fillvalue=fillvalue)
+ columns = zip(*rows)
+ rotated_columns = [col[start:] + col[:start] for start, col in zip([keycolumn[l] for l in keyword], columns)]
+ rotated_rows = zip(*rotated_columns)
+ transpositions = transpositions_of(keyword)
+ transposed = [transpose(r, transpositions) for r in rotated_rows]
+ return cat(chain(*transposed))
+
+def cadenus_decipher(message, keyword, keycolumn, fillvalue='a'):
"""
- counts = collections.defaultdict(int)
- for c in text:
- counts[c] += 1
- return counts
-
-def deduplicate(text):
- return list(collections.OrderedDict.fromkeys(text))
-
-
-
-def caesar_encipher_letter(letter, shift):
- """Encipher a letter, given a shift amount
-
- >>> caesar_encipher_letter('a', 1)
- 'b'
- >>> caesar_encipher_letter('a', 2)
- 'c'
- >>> caesar_encipher_letter('b', 2)
- 'd'
- >>> caesar_encipher_letter('x', 2)
- 'z'
- >>> caesar_encipher_letter('y', 2)
- 'a'
- >>> caesar_encipher_letter('z', 2)
- 'b'
- >>> caesar_encipher_letter('z', -1)
- 'y'
- >>> caesar_encipher_letter('a', -1)
- 'z'
+ >>> cadenus_decipher('antodeleeeuhrsidrbhmhdrrhnimefmthgeaetakseomehetyaa' \
+ 'suvoyegrastmmuuaeenabbtpchehtarorikswosmvaleatned', \
+ 'wink', \
+ make_cadenus_keycolumn(reverse=True))
+ 'whoeverhasmadeavoyageupthehudsonmustrememberthekaatskillmountainstheyareadismemberedbranchofthegreat'
+ >>> cadenus_decipher('systretomtattlusoatleeesfiyheasdfnmschbhneuvsnpmtof' \
+ 'arenuseieeieltarlmentieetogevesitfaisltngeeuvowul', \
+ 'easy', \
+ make_cadenus_keycolumn(reverse=True))
+ 'aseverelimitationontheusefulnessofthecadenusisthateverymessagemustbeamultipleoftwentyfiveletterslong'
"""
- if letter in string.ascii_letters:
- if letter in string.ascii_uppercase:
- alphabet_start = ord('A')
- else:
- alphabet_start = ord('a')
- return chr(((ord(letter) - alphabet_start + shift) % 26) + alphabet_start)
+ rows = chunks(message, len(message) // 25, fillvalue=fillvalue)
+ transpositions = transpositions_of(keyword)
+ untransposed_rows = [untranspose(r, transpositions) for r in rows]
+ columns = zip(*untransposed_rows)
+ rotated_columns = [col[-start:] + col[:-start] for start, col in zip([keycolumn[l] for l in keyword], columns)]
+ rotated_rows = zip(*rotated_columns)
+ # return rotated_columns
+ return cat(chain(*rotated_rows))
+
+
+def hill_encipher(matrix, message_letters, fillvalue='a'):
+ """Hill cipher
+
+ >>> hill_encipher(np.matrix([[7,8], [11,11]]), 'hellothere')
+ 'drjiqzdrvx'
+ >>> hill_encipher(np.matrix([[6, 24, 1], [13, 16, 10], [20, 17, 15]]), \
+ 'hello there')
+ 'tfjflpznvyac'
+ """
+ n = len(matrix)
+ sanitised_message = sanitise(message_letters)
+ if len(sanitised_message) % n != 0:
+ padding = fillvalue[0] * (n - len(sanitised_message) % n)
else:
- return letter
-
-def caesar_decipher_letter(letter, shift):
- """Decipher a letter, given a shift amount
-
- >>> caesar_decipher_letter('b', 1)
- 'a'
- >>> caesar_decipher_letter('b', 2)
- 'z'
+ padding = ''
+ message = [pos(c) for c in sanitised_message + padding]
+ message_chunks = [message[i:i+n] for i in range(0, len(message), n)]
+ # message_chunks = chunks(message, len(matrix), fillvalue=None)
+ enciphered_chunks = [((matrix * np.matrix(c).T).T).tolist()[0]
+ for c in message_chunks]
+ return cat([unpos(round(l))
+ for l in sum(enciphered_chunks, [])])
+
+def hill_decipher(matrix, message, fillvalue='a'):
+ """Hill cipher
+
+ >>> hill_decipher(np.matrix([[7,8], [11,11]]), 'drjiqzdrvx')
+ 'hellothere'
+ >>> hill_decipher(np.matrix([[6, 24, 1], [13, 16, 10], [20, 17, 15]]), \
+ 'tfjflpznvyac')
+ 'hellothereaa'
"""
- return caesar_encipher_letter(letter, -shift)
-
-def caesar_encipher(message, shift):
- """Encipher a message with the Caesar cipher of given shift
-
- >>> caesar_encipher('abc', 1)
- 'bcd'
- >>> caesar_encipher('abc', 2)
- 'cde'
- >>> caesar_encipher('abcxyz', 2)
- 'cdezab'
- >>> caesar_encipher('ab cx yz', 2)
- 'cd ez ab'
+ adjoint = linalg.det(matrix)*linalg.inv(matrix)
+ inverse_determinant = modular_division_table[int(round(linalg.det(matrix))) % 26][1]
+ inverse_matrix = (inverse_determinant * adjoint) % 26
+ return hill_encipher(inverse_matrix, message, fillvalue)
+
+
+# Where each piece of text ends up in the AMSCO transpositon cipher.
+# 'index' shows where the slice appears in the plaintext, with the slice
+# from 'start' to 'end'
+AmscoSlice = collections.namedtuple('AmscoSlice', ['index', 'start', 'end'])
+
+class AmscoFillStyle(Enum):
+ continuous = 1
+ same_each_row = 2
+ reverse_each_row = 3
+
+def amsco_transposition_positions(message, keyword,
+ fillpattern=(1, 2),
+ fillstyle=AmscoFillStyle.continuous,
+ fillcolumnwise=False,
+ emptycolumnwise=True):
+ """Creates the grid for the AMSCO transposition cipher. Each element in the
+ grid shows the index of that slice and the start and end positions of the
+ plaintext that go to make it up.
+
+ >>> amsco_transposition_positions(string.ascii_lowercase, 'freddy', \
+ fillpattern=(1, 2)) # doctest: +NORMALIZE_WHITESPACE
+ [[AmscoSlice(index=3, start=4, end=6),
+ AmscoSlice(index=2, start=3, end=4),
+ AmscoSlice(index=0, start=0, end=1),
+ AmscoSlice(index=1, start=1, end=3),
+ AmscoSlice(index=4, start=6, end=7)],
+ [AmscoSlice(index=8, start=12, end=13),
+ AmscoSlice(index=7, start=10, end=12),
+ AmscoSlice(index=5, start=7, end=9),
+ AmscoSlice(index=6, start=9, end=10),
+ AmscoSlice(index=9, start=13, end=15)],
+ [AmscoSlice(index=13, start=19, end=21),
+ AmscoSlice(index=12, start=18, end=19),
+ AmscoSlice(index=10, start=15, end=16),
+ AmscoSlice(index=11, start=16, end=18),
+ AmscoSlice(index=14, start=21, end=22)],
+ [AmscoSlice(index=18, start=27, end=28),
+ AmscoSlice(index=17, start=25, end=27),
+ AmscoSlice(index=15, start=22, end=24),
+ AmscoSlice(index=16, start=24, end=25),
+ AmscoSlice(index=19, start=28, end=30)]]
"""
- enciphered = [caesar_encipher_letter(l, shift) for l in message]
- return ''.join(enciphered)
-
-def caesar_decipher(message, shift):
- """Encipher a message with the Caesar cipher of given shift
-
- >>> caesar_decipher('bcd', 1)
- 'abc'
- >>> caesar_decipher('cde', 2)
- 'abc'
- >>> caesar_decipher('cd ez ab', 2)
- 'ab cx yz'
+ transpositions = transpositions_of(keyword)
+ fill_iterator = cycle(fillpattern)
+ indices = count()
+ message_length = len(message)
+
+ current_position = 0
+ grid = []
+ current_fillpattern = fillpattern
+ while current_position < message_length:
+ row = []
+ if fillstyle == AmscoFillStyle.same_each_row:
+ fill_iterator = cycle(fillpattern)
+ if fillstyle == AmscoFillStyle.reverse_each_row:
+ fill_iterator = cycle(current_fillpattern)
+ for _ in range(len(transpositions)):
+ index = next(indices)
+ gap = next(fill_iterator)
+ row += [AmscoSlice(index, current_position, current_position + gap)]
+ current_position += gap
+ grid += [row]
+ if fillstyle == AmscoFillStyle.reverse_each_row:
+ current_fillpattern = list(reversed(current_fillpattern))
+ return [transpose(r, transpositions) for r in grid]
+
+def amsco_transposition_encipher(message, keyword,
+ fillpattern=(1,2), fillstyle=AmscoFillStyle.reverse_each_row):
+ """AMSCO transposition encipher.
+
+ >>> amsco_transposition_encipher('hellothere', 'abc', fillpattern=(1, 2))
+ 'hoteelhler'
+ >>> amsco_transposition_encipher('hellothere', 'abc', fillpattern=(2, 1))
+ 'hetelhelor'
+ >>> amsco_transposition_encipher('hellothere', 'acb', fillpattern=(1, 2))
+ 'hotelerelh'
+ >>> amsco_transposition_encipher('hellothere', 'acb', fillpattern=(2, 1))
+ 'hetelorlhe'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'encode')
+ 'etecstthhomoerereenisxip'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'cipher', fillpattern=(1, 2))
+ 'hetcsoeisterereipexthomn'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'cipher', fillpattern=(1, 2), fillstyle=AmscoFillStyle.continuous)
+ 'hecsoisttererteipexhomen'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'cipher', fillpattern=(2, 1))
+ 'heecisoosttrrtepeixhemen'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'cipher', fillpattern=(1, 3, 2))
+ 'hxtomephescieretoeisnter'
+ >>> amsco_transposition_encipher('hereissometexttoencipher', 'cipher', fillpattern=(1, 3, 2), fillstyle=AmscoFillStyle.continuous)
+ 'hxomeiphscerettoisenteer'
"""
- return caesar_encipher(message, -shift)
-
-def affine_encipher_letter(letter, multiplier=1, adder=0, one_based=True):
- """Encipher a letter, given a multiplier and adder
-
- >>> ''.join([affine_encipher_letter(l, 3, 5, True) for l in string.ascii_uppercase])
- 'HKNQTWZCFILORUXADGJMPSVYBE'
- >>> ''.join([affine_encipher_letter(l, 3, 5, False) for l in string.ascii_uppercase])
- 'FILORUXADGJMPSVYBEHKNQTWZC'
+ grid = amsco_transposition_positions(message, keyword,
+ fillpattern=fillpattern, fillstyle=fillstyle)
+ ct_as_grid = [[message[s.start:s.end] for s in r] for r in grid]
+ return combine_every_nth(ct_as_grid)
+
+
+def amsco_transposition_decipher(message, keyword,
+ fillpattern=(1,2), fillstyle=AmscoFillStyle.reverse_each_row):
+ """AMSCO transposition decipher
+
+ >>> amsco_transposition_decipher('hoteelhler', 'abc', fillpattern=(1, 2))
+ 'hellothere'
+ >>> amsco_transposition_decipher('hetelhelor', 'abc', fillpattern=(2, 1))
+ 'hellothere'
+ >>> amsco_transposition_decipher('hotelerelh', 'acb', fillpattern=(1, 2))
+ 'hellothere'
+ >>> amsco_transposition_decipher('hetelorlhe', 'acb', fillpattern=(2, 1))
+ 'hellothere'
+ >>> amsco_transposition_decipher('etecstthhomoerereenisxip', 'encode')
+ 'hereissometexttoencipher'
+ >>> amsco_transposition_decipher('hetcsoeisterereipexthomn', 'cipher', fillpattern=(1, 2))
+ 'hereissometexttoencipher'
+ >>> amsco_transposition_decipher('hecsoisttererteipexhomen', 'cipher', fillpattern=(1, 2), fillstyle=AmscoFillStyle.continuous)
+ 'hereissometexttoencipher'
+ >>> amsco_transposition_decipher('heecisoosttrrtepeixhemen', 'cipher', fillpattern=(2, 1))
+ 'hereissometexttoencipher'
+ >>> amsco_transposition_decipher('hxtomephescieretoeisnter', 'cipher', fillpattern=(1, 3, 2))
+ 'hereissometexttoencipher'
+ >>> amsco_transposition_decipher('hxomeiphscerettoisenteer', 'cipher', fillpattern=(1, 3, 2), fillstyle=AmscoFillStyle.continuous)
+ 'hereissometexttoencipher'
"""
- if letter in string.ascii_letters:
- if letter in string.ascii_uppercase:
- alphabet_start = ord('A')
- else:
- alphabet_start = ord('a')
- letter_number = ord(letter) - alphabet_start
- if one_based:
- letter_number += 1
- raw_cipher_number = (letter_number * multiplier + adder)
- cipher_number = 0
- if one_based:
- cipher_number = (raw_cipher_number - 1) % 26
- else:
- cipher_number = raw_cipher_number % 26
- return chr(cipher_number + alphabet_start)
- else:
- return letter
-def affine_decipher_letter(letter, multiplier=1, adder=0, one_based=True):
- """Encipher a letter, given a multiplier and adder
-
- >>> ''.join([affine_decipher_letter(l, 3, 5, True) for l in 'HKNQTWZCFILORUXADGJMPSVYBE'])
- 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
- >>> ''.join([affine_decipher_letter(l, 3, 5, False) for l in 'FILORUXADGJMPSVYBEHKNQTWZC'])
- 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
- """
- if letter in string.ascii_letters:
- if letter in string.ascii_uppercase:
- alphabet_start = ord('A')
- else:
- alphabet_start = ord('a')
- cipher_number = ord(letter) - alphabet_start
- if one_based:
- cipher_number += 1
- plaintext_number = 0
- if one_based:
- plaintext_number = (modular_division_table_one_based[multiplier][(cipher_number - adder + 26) % 26] - 1) % 26
- else:
- #plaintext_number = (modular_division_table[multiplier][cipher_number] - adder) % 26
- plaintext_number = modular_division_table[multiplier][(cipher_number - adder + 26) % 26]
- return chr(plaintext_number + alphabet_start)
- else:
- return letter
+ grid = amsco_transposition_positions(message, keyword,
+ fillpattern=fillpattern, fillstyle=fillstyle)
+ transposed_sections = [s for c in [l for l in zip(*grid)] for s in c]
+ plaintext_list = [''] * len(transposed_sections)
+ current_pos = 0
+ for slice in transposed_sections:
+ plaintext_list[slice.index] = message[current_pos:current_pos-slice.start+slice.end][:len(message[slice.start:slice.end])]
+ current_pos += len(message[slice.start:slice.end])
+ return cat(plaintext_list)
-def affine_encipher(message, multiplier=1, adder=0, one_based=True):
- """Encipher a message
-
- >>> affine_encipher('hours passed during which jerico tried every trick he could think of', 15, 22, True)
- 'lmyfu bkuusd dyfaxw claol psfaom jfasd snsfg jfaoe ls omytd jlaxe mh'
- """
- enciphered = [affine_encipher_letter(l, multiplier, adder, one_based) for l in message]
- return ''.join(enciphered)
-def affine_decipher(message, multiplier=1, adder=0, one_based=True):
- """Decipher a message
-
- >>> affine_decipher('lmyfu bkuusd dyfaxw claol psfaom jfasd snsfg jfaoe ls omytd jlaxe mh', 15, 22, True)
- 'hours passed during which jerico tried every trick he could think of'
+def bifid_grid(keyword, wrap_alphabet, letter_mapping):
+ """Create the grids for a Bifid cipher
"""
- enciphered = [affine_decipher_letter(l, multiplier, adder, one_based) for l in message]
- return ''.join(enciphered)
-
-
-def keyword_cipher_alphabet_of(keyword, wrap_alphabet=0):
- """Find the cipher alphabet given a keyword.
- wrap_alphabet controls how the rest of the alphabet is added
- after the keyword.
- 0 : from 'a'
- 1 : from the last letter in the sanitised keyword
- 2 : from the largest letter in the sanitised keyword
-
- >>> keyword_cipher_alphabet_of('bayes')
- 'bayescdfghijklmnopqrtuvwxz'
- >>> keyword_cipher_alphabet_of('bayes', 0)
- 'bayescdfghijklmnopqrtuvwxz'
- >>> keyword_cipher_alphabet_of('bayes', 1)
- 'bayestuvwxzcdfghijklmnopqr'
- >>> keyword_cipher_alphabet_of('bayes', 2)
- 'bayeszcdfghijklmnopqrtuvwx'
+ cipher_alphabet = keyword_cipher_alphabet_of(keyword, wrap_alphabet)
+ if letter_mapping is None:
+ letter_mapping = {'j': 'i'}
+ translation = ''.maketrans(letter_mapping)
+ cipher_alphabet = cat(collections.OrderedDict.fromkeys(cipher_alphabet.translate(translation)))
+ f_grid = {k: ((i // 5) + 1, (i % 5) + 1)
+ for i, k in enumerate(cipher_alphabet)}
+ r_grid = {((i // 5) + 1, (i % 5) + 1): k
+ for i, k in enumerate(cipher_alphabet)}
+ return translation, f_grid, r_grid
+
+def bifid_encipher(message, keyword, wrap_alphabet=KeywordWrapAlphabet.from_a,
+ letter_mapping=None, period=None, fillvalue=None):
+ """Bifid cipher
+
+ >>> bifid_encipher("indiajelly", 'iguana')
+ 'ibidonhprm'
+ >>> bifid_encipher("indiacurry", 'iguana', period=4)
+ 'ibnhgaqltm'
+ >>> bifid_encipher("indiacurry", 'iguana', period=4, fillvalue='x')
+ 'ibnhgaqltzml'
"""
- if wrap_alphabet == 0:
- cipher_alphabet = ''.join(deduplicate(sanitise(keyword) + string.ascii_lowercase))
+ translation, f_grid, r_grid = bifid_grid(keyword, wrap_alphabet, letter_mapping)
+
+ t_message = message.translate(translation)
+ pairs0 = [f_grid[l] for l in sanitise(t_message)]
+ if period:
+ chunked_pairs = [pairs0[i:i+period] for i in range(0, len(pairs0), period)]
+ if len(chunked_pairs[-1]) < period and fillvalue:
+ chunked_pairs[-1] += [f_grid[fillvalue]] * (period - len(chunked_pairs[-1]))
else:
- if wrap_alphabet == 1:
- last_keyword_letter = deduplicate(sanitise(keyword))[-1]
- else:
- last_keyword_letter = sorted(sanitise(keyword))[-1]
- last_keyword_position = string.ascii_lowercase.find(last_keyword_letter) + 1
- cipher_alphabet = ''.join(deduplicate(sanitise(keyword) +
- string.ascii_lowercase[last_keyword_position:] +
- string.ascii_lowercase))
- return cipher_alphabet
-
-
-def keyword_encipher(message, keyword, wrap_alphabet=0):
- """Enciphers a message with a keyword substitution cipher.
- wrap_alphabet controls how the rest of the alphabet is added
- after the keyword.
- 0 : from 'a'
- 1 : from the last letter in the sanitised keyword
- 2 : from the largest letter in the sanitised keyword
-
- >>> keyword_encipher('test message', 'bayes')
- 'rsqr ksqqbds'
- >>> keyword_encipher('test message', 'bayes', 0)
- 'rsqr ksqqbds'
- >>> keyword_encipher('test message', 'bayes', 1)
- 'lskl dskkbus'
- >>> keyword_encipher('test message', 'bayes', 2)
- 'qspq jsppbcs'
- """
- cipher_alphabet = keyword_cipher_alphabet_of(keyword, wrap_alphabet)
- cipher_translation = ''.maketrans(string.ascii_lowercase, cipher_alphabet)
- return message.lower().translate(cipher_translation)
-
-def keyword_decipher(message, keyword, wrap_alphabet=0):
- """Deciphers a message with a keyword substitution cipher.
- wrap_alphabet controls how the rest of the alphabet is added
- after the keyword.
- 0 : from 'a'
- 1 : from the last letter in the sanitised keyword
- 2 : from the largest letter in the sanitised keyword
+ chunked_pairs = [pairs0]
- >>> keyword_decipher('rsqr ksqqbds', 'bayes')
- 'test message'
- >>> keyword_decipher('rsqr ksqqbds', 'bayes', 0)
- 'test message'
- >>> keyword_decipher('lskl dskkbus', 'bayes', 1)
- 'test message'
- >>> keyword_decipher('qspq jsppbcs', 'bayes', 2)
- 'test message'
- """
- cipher_alphabet = keyword_cipher_alphabet_of(keyword, wrap_alphabet)
- cipher_translation = ''.maketrans(cipher_alphabet, string.ascii_lowercase)
- return message.lower().translate(cipher_translation)
+ pairs1 = []
+ for c in chunked_pairs:
+ items = sum(list(list(i) for i in zip(*c)), [])
+ p = [(items[i], items[i+1]) for i in range(0, len(items), 2)]
+ pairs1 += p
+
+ return cat(r_grid[p] for p in pairs1)
-def caesar_break(message, metric=norms.euclidean_distance, target_frequencies=normalised_english_counts, message_frequency_scaling=norms.normalise):
- """Breaks a Caesar cipher using frequency analysis
-
- >>> caesar_break('ibxcsyorsaqcheyklxivoexlevmrimwxsfiqevvmihrsasrxliwyrhecjsppsamrkwleppfmergefifvmhixscsymjcsyqeoixlm') # doctest: +ELLIPSIS
- (4, 0.31863952890183...)
- >>> caesar_break('wxwmaxdgheetgwuxztgptedbgznitgwwhpguxyhkxbmhvvtlbhgteeraxlmhiixweblmxgxwmhmaxybkbgztgwztsxwbgmxgmert') # doctest: +ELLIPSIS
- (19, 0.42152901235832...)
- >>> caesar_break('yltbbqnqnzvguvaxurorgenafsbezqvagbnornfgsbevpnaabjurersvaquvzyvxrnznazlybequrvfohgriraabjtbaruraprur') # doctest: +ELLIPSIS
- (13, 0.316029208075451...)
+def bifid_decipher(message, keyword, wrap_alphabet=KeywordWrapAlphabet.from_a,
+ letter_mapping=None, period=None, fillvalue=None):
+ """Decipher with bifid cipher
+
+ >>> bifid_decipher('ibidonhprm', 'iguana')
+ 'indiaielly'
+ >>> bifid_decipher("ibnhgaqltm", 'iguana', period=4)
+ 'indiacurry'
+ >>> bifid_decipher("ibnhgaqltzml", 'iguana', period=4)
+ 'indiacurryxx'
"""
- sanitised_message = sanitise(message)
- best_shift = 0
- best_fit = float("inf")
- for shift in range(26):
- plaintext = caesar_decipher(sanitised_message, shift)
- frequencies = message_frequency_scaling(letter_frequencies(plaintext))
- fit = metric(target_frequencies, frequencies)
- logger.debug('Caesar break attempt using key {0} gives fit of {1} and decrypt starting: {2}'.format(shift, fit, plaintext[:50]))
- if fit < best_fit:
- best_fit = fit
- best_shift = shift
- logger.info('Caesar break best fit: key {0} gives fit of {1} and decrypt starting: {2}'.format(best_shift, best_fit, caesar_decipher(sanitised_message, best_shift)[:50]))
- return best_shift, best_fit
-
-def affine_break(message, metric=norms.euclidean_distance, target_frequencies=normalised_english_counts, message_frequency_scaling=norms.normalise):
- """Breaks an affine cipher using frequency analysis
+ translation, f_grid, r_grid = bifid_grid(keyword, wrap_alphabet, letter_mapping)
- >>> affine_break('lmyfu bkuusd dyfaxw claol psfaom jfasd snsfg jfaoe ls omytd jlaxe mh jm bfmibj umis hfsul axubafkjamx. ls kffkxwsd jls ofgbjmwfkiu olfmxmtmwaokttg jlsx ls kffkxwsd jlsi zg tsxwjl. jlsx ls umfjsd jlsi zg hfsqysxog. ls dmmdtsd mx jls bats mh bkbsf. ls bfmctsd kfmyxd jls lyj, mztanamyu xmc jm clm cku tmmeaxw kj lai kxd clm ckuxj.') # doctest: +ELLIPSIS
- ((15, 22, True), 0.23570361818655...)
+ t_message = message.translate(translation)
+ pairs0 = [f_grid[l] for l in sanitise(t_message)]
+ if period:
+ chunked_pairs = [pairs0[i:i+period] for i in range(0, len(pairs0), period)]
+ if len(chunked_pairs[-1]) < period and fillvalue:
+ chunked_pairs[-1] += [f_grid[fillvalue]] * (period - len(chunked_pairs[-1]))
+ else:
+ chunked_pairs = [pairs0]
+
+ pairs1 = []
+ for c in chunked_pairs:
+ items = [j for i in c for j in i]
+ gap = len(c)
+ p = [(items[i], items[i+gap]) for i in range(gap)]
+ pairs1 += p
+
+ return cat(r_grid[p] for p in pairs1)
+
+
+def autokey_encipher(message, keyword):
+ """Encipher with the autokey cipher
+
+ >>> autokey_encipher('meetatthefountain', 'kilt')
+ 'wmpmmxxaeyhbryoca'
+ """
+ shifts = [pos(l) for l in keyword + message]
+ pairs = zip(message, shifts)
+ return cat([caesar_encipher_letter(l, k) for l, k in pairs])
+
+def autokey_decipher(ciphertext, keyword):
+ """Decipher with the autokey cipher
+
+ >>> autokey_decipher('wmpmmxxaeyhbryoca', 'kilt')
+ 'meetatthefountain'
"""
- sanitised_message = sanitise(message)
- best_multiplier = 0
- best_adder = 0
- best_one_based = True
- best_fit = float("inf")
- for one_based in [True, False]:
- for multiplier in range(1, 26, 2):
- for adder in range(26):
- plaintext = affine_decipher(sanitised_message, multiplier, adder, one_based)
- frequencies = message_frequency_scaling(letter_frequencies(plaintext))
- fit = metric(target_frequencies, frequencies)
- logger.debug('Affine break attempt using key {0}x+{1} ({2}) gives fit of {3} and decrypt starting: {4}'.format(multiplier, adder, one_based, fit, plaintext[:50]))
- if fit < best_fit:
- best_fit = fit
- best_multiplier = multiplier
- best_adder = adder
- best_one_based = one_based
- logger.info('Affine break best fit with key {0}x+{1} ({2}) gives fit of {3} and decrypt starting: {4}'.format(best_multiplier, best_adder, best_one_based, best_fit, affine_decipher(sanitised_message, best_multiplier, best_adder, best_one_based)[:50]))
- return (best_multiplier, best_adder, best_one_based), best_fit
-
-
-def keyword_break(message, wordlist=keywords, metric=norms.euclidean_distance, target_frequencies=normalised_english_counts, message_frequency_scaling=norms.normalise):
- """Breaks a keyword substitution cipher using a dictionary and frequency analysis
-
- >>> keyword_break(keyword_encipher('this is a test message for the keyword decipherment', 'elephant', 1), wordlist=['cat', 'elephant', 'kangaroo']) # doctest: +ELLIPSIS
- (('elephant', 1), 0.41643991598441...)
+ plaintext = []
+ keys = list(keyword)
+ for c in ciphertext:
+ plaintext_letter = caesar_decipher_letter(c, pos(keys[0]))
+ plaintext += [plaintext_letter]
+ keys = keys[1:] + [plaintext_letter]
+ return cat(plaintext)
+
+
+class PocketEnigma(object):
+ """A pocket enigma machine
+ The wheel is internally represented as a 26-element list self.wheel_map,
+ where wheel_map[i] == j shows that the position i places on from the arrow
+ maps to the position j places on.
"""
- best_keyword = ''
- best_wrap_alphabet = True
- best_fit = float("inf")
- for wrap_alphabet in range(3):
- for keyword in wordlist:
- plaintext = keyword_decipher(message, keyword, wrap_alphabet)
- frequencies = message_frequency_scaling(letter_frequencies(plaintext))
- fit = metric(target_frequencies, frequencies)
- logger.debug('Keyword break attempt using key {0} (wrap={1}) gives fit of {2} and decrypt starting: {3}'.format(keyword, wrap_alphabet, fit, sanitise(plaintext)[:50]))
- if fit < best_fit:
- best_fit = fit
- best_keyword = keyword
- best_wrap_alphabet = wrap_alphabet
- logger.info('Keyword break best fit with key {0} (wrap={1}) gives fit of {2} and decrypt starting: {3}'.format(best_keyword, best_wrap_alphabet, best_fit, sanitise(keyword_decipher(message, best_keyword))[:50]))
- return (best_keyword, best_wrap_alphabet), best_fit
+ def __init__(self, wheel=1, position='a'):
+ """initialise the pocket enigma, including which wheel to use and the
+ starting position of the wheel.
+
+ The wheel is either 1 or 2 (the predefined wheels) or a list of letter
+ pairs.
+
+ The position is the letter pointed to by the arrow on the wheel.
+
+ >>> pe.wheel_map
+ [25, 4, 23, 10, 1, 7, 9, 5, 12, 6, 3, 17, 8, 14, 13, 21, 19, 11, 20, 16, 18, 15, 24, 2, 22, 0]
+ >>> pe.position
+ 0
+ """
+ self.wheel1 = [('a', 'z'), ('b', 'e'), ('c', 'x'), ('d', 'k'),
+ ('f', 'h'), ('g', 'j'), ('i', 'm'), ('l', 'r'), ('n', 'o'),
+ ('p', 'v'), ('q', 't'), ('s', 'u'), ('w', 'y')]
+ self.wheel2 = [('a', 'c'), ('b', 'd'), ('e', 'w'), ('f', 'i'),
+ ('g', 'p'), ('h', 'm'), ('j', 'k'), ('l', 'n'), ('o', 'q'),
+ ('r', 'z'), ('s', 'u'), ('t', 'v'), ('x', 'y')]
+ if wheel == 1:
+ self.make_wheel_map(self.wheel1)
+ elif wheel == 2:
+ self.make_wheel_map(self.wheel2)
+ else:
+ self.validate_wheel_spec(wheel)
+ self.make_wheel_map(wheel)
+ if position in string.ascii_lowercase:
+ self.position = pos(position)
+ else:
+ self.position = position
+
+ def make_wheel_map(self, wheel_spec):
+ """Expands a wheel specification from a list of letter-letter pairs
+ into a full wheel_map.
+
+ >>> pe.make_wheel_map(pe.wheel2)
+ [2, 3, 0, 1, 22, 8, 15, 12, 5, 10, 9, 13, 7, 11, 16, 6, 14, 25, 20, 21, 18, 19, 4, 24, 23, 17]
+ """
+ self.validate_wheel_spec(wheel_spec)
+ self.wheel_map = [0] * 26
+ for p in wheel_spec:
+ self.wheel_map[pos(p[0])] = pos(p[1])
+ self.wheel_map[pos(p[1])] = pos(p[0])
+ return self.wheel_map
+
+ def validate_wheel_spec(self, wheel_spec):
+ """Validates that a wheel specificaiton will turn into a valid wheel
+ map.
+
+ >>> pe.validate_wheel_spec([])
+ Traceback (most recent call last):
+ ...
+ ValueError: Wheel specification has 0 pairs, requires 13
+ >>> pe.validate_wheel_spec([('a', 'b', 'c')]*13)
+ Traceback (most recent call last):
+ ...
+ ValueError: Not all mappings in wheel specificationhave two elements
+ >>> pe.validate_wheel_spec([('a', 'b')]*13)
+ Traceback (most recent call last):
+ ...
+ ValueError: Wheel specification does not contain 26 letters
+ """
+ if len(wheel_spec) != 13:
+ raise ValueError("Wheel specification has {} pairs, requires 13".
+ format(len(wheel_spec)))
+ for p in wheel_spec:
+ if len(p) != 2:
+ raise ValueError("Not all mappings in wheel specification"
+ "have two elements")
+ if len(set([p[0] for p in wheel_spec] +
+ [p[1] for p in wheel_spec])) != 26:
+ raise ValueError("Wheel specification does not contain 26 letters")
+
+ def encipher_letter(self, letter):
+ """Enciphers a single letter, by advancing the wheel before looking up
+ the letter on the wheel.
+
+ >>> pe.set_position('f')
+ 5
+ >>> pe.encipher_letter('k')
+ 'h'
+ """
+ self.advance()
+ return self.lookup(letter)
+ decipher_letter = encipher_letter
+
+ def lookup(self, letter):
+ """Look up what a letter enciphers to, without turning the wheel.
+
+ >>> pe.set_position('f')
+ 5
+ >>> cat([pe.lookup(l) for l in string.ascii_lowercase])
+ 'udhbfejcpgmokrliwntsayqzvx'
+ >>> pe.lookup('A')
+ ''
+ """
+ if letter in string.ascii_lowercase:
+ return unpos(
+ (self.wheel_map[(pos(letter) - self.position) % 26] +
+ self.position))
+ else:
+ return ''
+
+ def advance(self):
+ """Advances the wheel one position.
+
+ >>> pe.set_position('f')
+ 5
+ >>> pe.advance()
+ 6
+ """
+ self.position = (self.position + 1) % 26
+ return self.position
+
+ def encipher(self, message, starting_position=None):
+ """Enciphers a whole message.
+
+ >>> pe.set_position('f')
+ 5
+ >>> pe.encipher('helloworld')
+ 'kjsglcjoqc'
+ >>> pe.set_position('f')
+ 5
+ >>> pe.encipher('kjsglcjoqc')
+ 'helloworld'
+ >>> pe.encipher('helloworld', starting_position = 'x')
+ 'egrekthnnf'
+ """
+ if starting_position:
+ self.set_position(starting_position)
+ transformed = ''
+ for l in message:
+ transformed += self.encipher_letter(l)
+ return transformed
+ decipher = encipher
+
+ def set_position(self, position):
+ """Sets the position of the wheel, by specifying the letter the arrow
+ points to.
+
+ >>> pe.set_position('a')
+ 0
+ >>> pe.set_position('m')
+ 12
+ >>> pe.set_position('z')
+ 25
+ """
+ self.position = pos(position)
+ return self.position
if __name__ == "__main__":
import doctest
- doctest.testmod()
+ doctest.testmod(extraglobs={'pe': PocketEnigma(1, 'a')})
projects / cipher-tools.git / blobdiff