Calculates Index of Coincidence

ic.py

#!/usr/bin/env python

import sys
import collections

# Bag em
cipher_file  = open( sys.argv[ 1 ], 'rb')  
cipher_text  = cipher_file.read()

# remove all non alpha and whitespace and force uppercase
# SOTHATCIPHERTEXTLOOKSLIKETHIS
cipher_flat  = "".join( 
                        [x.upper() for x in cipher_text.split() \
                                   if  x.isalpha() ]
                     )

# Tag em
N            = len(cipher_flat)
freqs        = collections.Counter( cipher_flat )
alphabet     =  map(chr, range( ord('A'), ord('Z')+1))
freqsum      = 0.0

# Do the math
for letter in alphabet:
    freqsum += freqs[ letter ] * ( freqs[ letter ] - 1 )

IC = freqsum / ( N*(N-1) )

print "%.3f" % IC, "({})".format( IC )

sinkov_test_gen_1.py

#!/usr/bin/env python

# Generate test suite number 1 from Sinkov pp 70
# to test Index of Coincidence computation.
# Should produce an IC of .041

al  = "A" * 7
al += "B" * 6
al += "C" * 9
al += "D" * 3
al += "E" * 5
al += "F" * 6
al += "G" * 8
al += "H" * 3
al += "I" * 4
al += "J" * 7
al += "K" * 13
al += "L" * 10
al += "M" * 7
al += "N" * 0 
al += "O" * 1
al += "P" * 5
al += "Q" * 3
al += "R" * 6
al += "S" * 8
al += "T" * 5
al += "U" * 4
al += "V" * 8
al += "W" * 4
al += "X" * 8
al += "Y" * 5
al += "Z" * 5

print al