def test_stripped_text_properties(self):
stripped_text1 = alphabetic.StrippedText("LET US GO! IT IS TIME. ",
alphabetic.Alphabet("ABCDEFGHIJKLMNOPQRSTUVWXYZ"))
self.assertEqual(stripped_text1.ends_of_words, {2: 0, 4: 1, 6: 2, 8: 3, 10: 4, 14: 5})
self.assertEqual(stripped_text1.stripped_part, [" ", " ", "! ", " ", " ", ". ", ""])
self.assertEqual(stripped_text1.get_non_stripped_text(), "LET US GO! IT IS TIME. ")
self.assertEqual(stripped_text1.positions["L"], set([0]))
self.assertEqual(stripped_text1.positions["E"], set([1, 14]))
stripped_text2 = alphabetic.StrippedText(" LET US GO! IT IS TIME",
alphabetic.Alphabet("ABCDEFGHIJKLMNOPQRSTUVWXYZ"))
self.assertEqual(stripped_text2.ends_of_words, {-1: 0, 2: 1, 4: 2, 6: 3, 8: 4, 10: 5, 14: 6})
self.assertEqual(stripped_text2.stripped_part, [" ", " ", " ", "! ", " ", " ", ""])
self.assertEqual(stripped_text2.get_non_stripped_text(), " LET US GO! IT IS TIME")
stripped_text2[3] = "F"
self.assertEqual(stripped_text2[3], "F")
self.assertEqual(stripped_text2.positions["F"], set([3]))
def generate_log_distribution_from_file(filename, alphabet, n_gram_length, additional_chars=""):
new_alphabet = alphabetic.Alphabet(alphabet.complete_alphabet + list(additional_chars))
f = open(filename, "r")
lines = f.readlines()
freqs = {}
for i in lines:
freqs[i.split()[0]] = log(float(i.split()[1]))
for i in alphabetic.n_gram_dict(new_alphabet, n_gram_length):
if i not in freqs:
freqs[i] = 0
return freqs
def setUp(self):
self.alphabet = alphabetic.Alphabet("ABCDEFGHIJKLMNOPQRSTUVWXYZ")
swap_permutation_and_update_decryption(
current_decryption, current_guessed_encoding_key, swap)
common.update_frequency(current_frequencies, frequency_change)
current_dist += dist_change
aux = current_order[swapp[0]]
current_order[swapp[0]] = current_order[swapp[1]]
current_order[swapp[1]] = aux
if current_dist > max_dist:
max_dist = current_dist
max_state = copy.deepcopy(current_guessed_decoding_key)
print(current_decryption.get_non_stripped_text())
return get_reverse_permutation(alphabet, max_state)
alphabett = alphabetic.Alphabet("ABCDEFGHIJKLMNOPQRSTUVWXYZ")
plain = alphabetic.StrippedText(
data_generator.get_string_cleared(
data_generator.generate_random_excerpt("../data/1984.txt",
2000)).upper(), alphabett)
standard2 = data_generator.get_log_distribution_from_json(
"../data/bigram_log_distributions_uppercase.json")
standard1 = data_generator.get_log_distribution_from_json(
"../data/monogram_log_distributions_uppercase.json")
all_printable = data_generator.get_string_cleared(string.printable + " ")
upper_printable = all_printable[:10] + all_printable[36:]
complete_alphabet = alphabetic.Alphabet(
data_generator.get_string_cleared(string.printable + " "))
upper_alphabet = alphabetic.Alphabet(upper_printable)
def setUp(self):
self.alphabet = alphabetic.Alphabet("ABCDEFGHIJKLMNOPQRSTUVWXYZ")
self.coprimes = extended.get_coprimes(self.alphabet.length)
def test_operators(self):
self.assertEqual(alphabetic.Alphabet("ABC")[1], "B")
self.assertTrue("B" in alphabetic.Alphabet("ABC"))
self.assertFalse("D" in alphabetic.Alphabet("ABC"))