import matplotlib.pyplot as plt
from cipher import *
+from language_models import *
# To time a run:
#
# timeit.timeit('keyword_break(c5a)', setup='gc.enable() ; from __main__ import c5a ; from cipher import keyword_break', number=1)
# timeit.repeat('keyword_break_mp(c5a, chunksize=500)', setup='gc.enable() ; from __main__ import c5a ; from cipher import keyword_break_mp', repeat=5, number=1)
-
-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)
-
-english_bigram_counts = collections.defaultdict(int)
-with open('count_2l.txt', 'r') as f:
- for line in f:
- (bigram, count) = line.split("\t")
- english_bigram_counts[bigram] = int(count)
-normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
-
-english_trigram_counts = collections.defaultdict(int)
-with open('count_3l.txt', 'r') as f:
- for line in f:
- (trigram, count) = line.split("\t")
- english_trigram_counts[trigram] = int(count)
-normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
-
-
-with open('words.txt', 'r') as f:
- keywords = [line.rstrip() for line in f]
-
transpositions = collections.defaultdict(list)
for word in keywords:
transpositions[transpositions_of(word)] += [word]
'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
+ 'bfmctsd kfmyxd jls lyj, mztanamyu xmc jm clm cku tmmeaxw kj lai ' \
+ 'kxd clm ckuxj.') # doctest: +ELLIPSIS
((15, 22, True), 0.0598745365924...)
"""
sanitised_message = sanitise(message)
chunksize=500):
"""Breaks a column transposition cipher using a dictionary and
n-gram frequency analysis
-
- >>> column_transposition_break_mp(column_transposition_encipher(sanitise( \
- "It is a truth universally acknowledged, that a single man in \
- possession of a good fortune, must be in want of a wife. However \
- little known the feelings or views of such a man may be on his \
- first entering a neighbourhood, this truth is so well fixed in the \
- minds of the surrounding families, that he is considered the \
- rightful property of some one or other of their daughters."), \
- 'encipher'), \
- translist={(2, 0, 5, 3, 1, 4, 6): ['encipher'], \
- (5, 0, 6, 1, 3, 4, 2): ['fourteen'], \
- (6, 1, 0, 4, 5, 3, 2): ['keyword']}) # doctest: +ELLIPSIS
- (((2, 0, 5, 3, 1, 4, 6), False), 0.0628106372...)
- >>> column_transposition_break_mp(column_transposition_encipher(sanitise( \
- "It is a truth universally acknowledged, that a single man in \
- possession of a good fortune, must be in want of a wife. However \
- little known the feelings or views of such a man may be on his \
- first entering a neighbourhood, this truth is so well fixed in the \
- minds of the surrounding families, that he is considered the \
- rightful property of some one or other of their daughters."), \
- 'encipher'), \
- translist={(2, 0, 5, 3, 1, 4, 6): ['encipher'], \
- (5, 0, 6, 1, 3, 4, 2): ['fourteen'], \
- (6, 1, 0, 4, 5, 3, 2): ['keyword']}, \
- target_counts=normalised_english_trigram_counts) # doctest: +ELLIPSIS
- (((2, 0, 5, 3, 1, 4, 6), False), 0.0592259560...)
"""
+ # >>> column_transposition_break_mp(column_transposition_encipher(sanitise( \
+ # "It is a truth universally acknowledged, that a single man in \
+ # possession of a good fortune, must be in want of a wife. However \
+ # little known the feelings or views of such a man may be on his \
+ # first entering a neighbourhood, this truth is so well fixed in the \
+ # minds of the surrounding families, that he is considered the \
+ # rightful property of some one or other of their daughters."), \
+ # 'encipher'), \
+ # translist={(2, 0, 5, 3, 1, 4, 6): ['encipher'], \
+ # (5, 0, 6, 1, 3, 4, 2): ['fourteen'], \
+ # (6, 1, 0, 4, 5, 3, 2): ['keyword']}) # doctest: +ELLIPSIS
+ # (((2, 0, 5, 3, 1, 4, 6), False), 0.0628106372...)
+ # >>> column_transposition_break_mp(column_transposition_encipher(sanitise( \
+ # "It is a truth universally acknowledged, that a single man in \
+ # possession of a good fortune, must be in want of a wife. However \
+ # little known the feelings or views of such a man may be on his \
+ # first entering a neighbourhood, this truth is so well fixed in the \
+ # minds of the surrounding families, that he is considered the \
+ # rightful property of some one or other of their daughters."), \
+ # 'encipher'), \
+ # translist={(2, 0, 5, 3, 1, 4, 6): ['encipher'], \
+ # (5, 0, 6, 1, 3, 4, 2): ['fourteen'], \
+ # (6, 1, 0, 4, 5, 3, 2): ['keyword']}, \
+ # target_counts=normalised_english_trigram_counts) # doctest: +ELLIPSIS
+ # (((2, 0, 5, 3, 1, 4, 6), False), 0.0592259560...)
+ # """
ngram_length = len(next(iter(target_counts.keys())))
with Pool() as pool:
helper_args = [(message, trans, columnwise, metric, target_counts, ngram_length,
vigenere_decipher(message, best_keyword))[:50]))
return best_keyword, best_fit
-def vigenere_keyword_break_mp(message,
- wordlist=keywords,
- metric=norms.euclidean_distance,
- target_counts=normalised_english_counts,
- message_frequency_scaling=norms.normalise,
+def vigenere_keyword_break_mp(message,
+ wordlist=keywords,
+ metric=norms.euclidean_distance,
+ target_counts=normalised_english_counts,
+ message_frequency_scaling=norms.normalise,
chunksize=500):
"""Breaks a vigenere cipher using a dictionary and
frequency analysis
projects / cipher-tools.git / blobdiff