Encryptor, decryptor and cracker for the Ceasar cipher

ceasar_cipher_and_cracker.py

import numpy as np


def cipher(text, alphabet='abcdefghijklmnopqrstuvwxyz', key=0):
    result = ""
    alphabet = alphabet.lower()
    n = len(alphabet)
    for char in text:
        if char.isalpha():
            new_char = alphabet[(alphabet.find(char.lower()) + key) % n]
            result += new_char if char.islower() else new_char.upper()
        else:
            result += char

    return result


def decipher(text, alphabet='abcdefghijklmnopqrstuvwxyz', key=0):
    result = ""
    alphabet = alphabet.lower()
    n = len(alphabet)
    for char in text:
        if char.isalpha():
            new_char = alphabet[(alphabet.find(char.lower()) - key + n) % n]
            result += new_char if char.islower() else new_char.upper()
        else:
            result += char

    return result


def test_ceasar_cipher():
    alphabet = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'
    text = 'Съешь же ещё этих мягких французских булок, да выпей чаю.'
    key = 3
    ciphered_phrase = cipher(text, alphabet, key)
    print(ciphered_phrase)
    deciphered_phrase = decipher(ciphered_phrase, alphabet, key)
    print(deciphered_phrase)


# ========= Ceasar cipher cracker ===========

ENGLISH_FREQS = [
    0.08167, 0.01492, 0.02782, 0.04253, 0.12702, 0.02228,
    0.02015, 0.06094, 0.06966, 0.00153, 0.00772, 0.04025,
    0.02406, 0.06749, 0.07507, 0.01929, 0.00095, 0.05987,
    0.06327, 0.09056, 0.02758, 0.00978, 0.02360, 0.00150,
    0.01974, 0.00074
]


# Returns the cross-entropy of the given string with respect to
# the English unigram frequencies, which is a positive
# floating-point number.
def get_entropy(str):
    sum, ignored = 0, 0
    for c in str:
        if c.isalpha():
            sum += np.log(ENGLISH_FREQS[ord(c.lower()) - 97])
        else:
            ignored += 1
    return -sum / np.log(2) / (len(str) - ignored)


# Returns the entropies when the given string is decrypted with
# all 26 possible shifts, where the result is an array of tuples
# (int shift, float enptroy) -
# e.g. [(0, 2.01), (1, 4.95), ..., (25, 3.73)].
def get_all_entropies(str):
    result = []
    for i in range(0, 26):
        result.append((i, get_entropy(decipher(str, key=i))))
    return result


def cmp_to_key(mycmp):
    'Convert a cmp= function into a key= function'
    class K(object):
        def __init__(self, obj, *args):
            self.obj = obj

        def __lt__(self, other):
            return mycmp(self.obj, other.obj) < 0

        def __gt__(self, other):
            return mycmp(self.obj, other.obj) > 0

        def __eq__(self, other):
            return mycmp(self.obj, other.obj) == 0

        def __le__(self, other):
            return mycmp(self.obj, other.obj) <= 0

        def __ge__(self, other):
            return mycmp(self.obj, other.obj) >= 0

        def __ne__(self, other):
            return mycmp(self.obj, other.obj) != 0
    return K


def comparator(x, y):
    if x[1] < y[1]:
        return -1
    elif x[1] > y[1]:
        return 1
    elif x[0] < y[0]:
        return -1
    elif x[0] > y[0]:
        return 1
    else:
        return 0


def crack_ceasar(text):
    entropies = get_all_entropies(text)
    entropies.sort(key=cmp_to_key(comparator))
    best_shift = entropies[0][0]
    cracked_val = decipher(text, key=best_shift)
    print("Best guess:")
    print("%d rotations\nDecrypted text: %s" % (best_shift, cracked_val))

    print("=========\nFull circle:")
    for i in range(0, 26):
        print("%d -\t%s" % (i, decipher(text, key=i)))

letters_frequencies_statistics.py

from collections import defaultdict


def get_letters_statistics(text):
    freq_dict = defaultdict(int)
    res_dict = dict()
    all_letters_count = 0
    for char in text:
        if char.isalpha():
            all_letters_count += 1
            freq_dict[char.lower()] += 1

    for key, value in freq_dict.items():
        res_dict[key] = value * 100 / all_letters_count

    return res_dict


def test_letters_statistics():
    s = "asdgshdkjgasdkghasdkgasd"

    with open('war_and_peace.txt', 'r') as war_and_peace:
        s = war_and_peace.read().replace('\n', '')

    stat_dict = get_letters_statistics(s)
    for key, value in sorted(stat_dict.items(),
                             key=lambda k_v: k_v[1], reverse=True):
        print("Letter '%s' - %.2f%%" % (str(key), value))