decode.py

from math import gcd

lines = []
groups = []
english_freq = "etaoinshrdlcumwfgypbvkjxqz"
ct = ""

def get_gcds():
    # Assemble groups of 4 letters
    for i in range(3, len(ct)):
        groups.append(ct[i-3] + ct[i-2] + ct[i-1] + ct[i])

    # Assemble groups of 3 letters
    for i in range(2, len(ct)):
        groups.append(ct[i-2] + ct[i-1] + ct[i])

    s = []
    # Find repeated groups and record the distance between them
    for n, group in enumerate(groups):
        try:
            s.append(groups.index(group, n + 1) - n)
        except ValueError:
            pass
        except IndexError:
            pass

    gcds = []
    # Find the greatest common denominators present in the distances
    for n, num in enumerate(s):
        gcds.append(gcd(s[n-1], s[n]))
    gcds = list(set(gcds))
    gcds.sort()
    gcds.remove(1)
    print()
    print("Possible key sizes:")
    print(gcds)
    print("Guessed key size:")
    print(min(gcds))
    return min(gcds)

def freq_analysis(keysize):
    print()
    letters = {}
    key = ""
    # Fill the dict with the alphabet
    ct_groups = [ct[i:i+keysize] for i in range(0, len(ct), keysize)]
    for n in range(0, keysize):
        for i in range(0, 26):
            letters[chr(ord('a') + i)] = 0
        for group in ct_groups:
            if len(group) == keysize:
                letters[group[n]] += 1
        sort = [letter[0] for letter in sorted(letters.items(), key=lambda x: x[1], reverse=True)]
        distance = (ord(english_freq[sort.index('e')]) - ord('a')) % 26
        key += chr(ord('a') + distance)
    print("Found key with size", keysize, ":", key)
    return key

def decode(key):
    plaintext = ""
    for n, letter in enumerate(ct):
        val = (ord(letter) - ord(key[n % len(key)]) + 1) - 1
        print(val)
        if val < 0:
            plaintext += chr(26 + val + ord('a'))
        else:
            plaintext += chr(val + ord('a'))
    print(plaintext)

if __name__ == "__main__":
    with open("ciphertext.txt") as f:
        print("Ciphertext:")
        for n, line in enumerate(f):
            print(n, line.replace("\n", ""))
            lines.append(line.replace("\n", ""))
    ct = ''.join(lines)
    decode("mindtrick")