Chapter 21 – Hacking the Vigenère Cipher 329

100. if factor <= MAX_KEY_LENGTH:


101. 
     

     factorsByCount is a list of tuples: (factor, factorCount)

     
     


102. 
     

     factorsByCount has a value like: [(3, 497), (2, 487), ...]

     
     


103. factorsByCount.append( (factor, factorCounts[factor]) )


104. 
     


105. 
     

     Sort the list by the factor count.

     
     


106. factorsByCount.sort(key=getItemAtIndexOne, reverse=True)


107. 
     


108. return factorsByCount


109. 
     


110. 
     


111. def kasiskiExamination(ciphertext):


112. 
     

     Find out the sequences of 3 to 5 letters that occur multiple times

     
     


113. 
     

     in the ciphertext. repeatedSeqSpacings has a value like:

     
     


114. 
     

     {'EXG': [192], 'NAF': [339, 972, 633], ... }

     
     


115. repeatedSeqSpacings = findRepeatSequencesSpacings(ciphertext)


116. 
     


117. 
     

     See getMostCommonFactors() for a description of seqFactors.

     
     


118. seqFactors = {}


119. for seq in repeatedSeqSpacings:


120. seqFactors[seq] = []


121. for spacing in repeatedSeqSpacings[seq]:


122. seqFactors[seq].extend(getUsefulFactors(spacing))


123. 
     


124. 
     

     See getMostCommonFactors() for a description of factorsByCount.

     
     


125. factorsByCount = getMostCommonFactors(seqFactors)


126. 
     


127. 
     

     Now we extract the factor counts from factorsByCount and

     
     


128. 
     

     put them in allLikelyKeyLengths so that they are easier to

     
     


129. 
     

     use later.

     
     


130. allLikelyKeyLengths = []


131. for twoIntTuple in factorsByCount:


132. allLikelyKeyLengths.append(twoIntTuple[0])


133. 
     


134. return allLikelyKeyLengths


135. 
     


136. 
     


137. def getNthSubkeysLetters(n, keyLength, message):


138. 
     

     Returns every Nth letter for each keyLength set of letters in text.

     
     


139. 
     

     E.g. getNthSubkeysLetters(1, 3, 'ABCABCABC') returns 'AAA'

     
     


140. 
     

     getNthSubkeysLetters(2, 3, 'ABCABCABC') returns 'BBB'

     
     


141. 
     

     getNthSubkeysLetters(3, 3, 'ABCABCABC') returns 'CCC'

     
     


142. 
     

     getNthSubkeysLetters(1, 5, 'ABCDEFGHI') returns 'AF'

     
     


143. 
     


144. 
     

     Use a regular expression to remove non-letters from the message.

     
     


145. message = NONLETTERS_PATTERN.sub('', message)