Statistical attack on simple linear substitution ciphers.

brute.py

import sys, string, re
"""

            Brute.py script to statistically break simple replacement ciphers. 
            Named after Ceasars killer.
            Called with
                python brute.py -m 'some text to break'
            or
                python brute.py -f filewithcypher.txt

            ouputs to terminal.

            Only support 1-gram words.

                        TODO:
                            * Implement support for 2 and 3-gram searches
                            * Implement support for interactive decryption with intelligent support from program.

"""


# Data from course in cryptography on LTH, Sweden
letterDensity = [
                    (73, 'A'),
                    (9, 'B'),
                    (30, 'C'),
                    (44, 'D'),
                    (130, 'E'),
                    (28, 'F'),
                    (16, 'G'),
                    (35, 'H'),
                    (74, 'I'),
                    (2, 'J'),
                    (3, 'K'),
                    (35, 'L'),
                    (25, 'M'),
                    (78, 'N'),
                    (74, 'O'),
                    (27, 'P'),
                    (3, 'Q'),
                    (77, 'R'),
                    (63, 'S'),
                    (93, 'T'),
                    (27, 'U'),
                    (13, 'V'),
                    (16, 'W'),
                    (5, 'X'),
                    (19, 'Y'),
                    (1, 'Z'),
                ]

def occurances(cipher):
    totals = []
    for letter in string.uppercase:
        totals.append((cipher.count(letter), letter))
    totals.sort()
    print totals
    return totals

def replace(cipher, inputDensity):
    subst = list(cipher[:])
    letterDensity.reverse()
    print "Letter distribution in english: " + str(letterDensity)
    print "Letter distribution in input text: " + str(inputDensity)
    for letter in inputDensity:
        replaceLetter = letterDensity.pop(0)
        starts = [
            match.start() for match in re.finditer
                (
                    re.escape(str(letter[1])), cipher
                )
            ]
        for pos in starts:
            subst[pos] = str(replaceLetter[1])
    print "".join(subst)

if __name__ == "__main__":
    cipher = ""
    if len(sys.argv) <= 1:
        print "Usage 'python brute.py [-m|-f] ciphertext'"
        print "-m message"
        print "-f filename"
        exit()
    if sys.argv[1] == "-m":
        cipher = sys.argv[2]
    elif sys.argv[1] == "-f":
        f = open(sys.argv[2], 'r')
        for line in f:
            cipher += line
    else:
        print "Parse error"
        exit(1)
    cipher = cipher.upper()
    letterDensity.sort()
    inputDensity = occurances(cipher)
    inputDensity.reverse()
    result = replace(cipher, inputDensity)