Solved 2014 challenges 1 and 2

[cipher-tools.git] / cipher.py

diff --git a/cipher.py b/cipher.py
index 6ef01c325d81a7055760d924c400f86b8b718340..c5d542bb915b4cfd0775d5c100e8dce46a271d88 100644 (file)
--- a/cipher.py
+++ b/cipher.py
@@ -1,9 +1,9 @@
 import string
 import collections
 import logging
 import string
 import collections
 import logging

+import math

 from itertools import zip_longest, cycle, chain
 from itertools import zip_longest, cycle, chain

-from counts import *
-
+from language_models import *

 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.FileHandler('cipher.log'))
 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.FileHandler('cipher.log'))


@@ -12,57 +12,12 @@ logger.setLevel(logging.WARNING)
 #logger.setLevel(logging.DEBUG)
 
 
 #logger.setLevel(logging.DEBUG)
 
 

-english_counts = collections.defaultdict(int)
-with open('count_1l.txt', 'r') as f:
-    for line in f:
-        (letter, count) = line.split("\t")
-        english_counts[letter] = int(count)
-normalised_english_counts = norms.normalise(english_counts)
-
-choices, weights = zip(*weighted_choices)
-cumdist = list(itertools.accumulate(weights))
-x = random.random() * cumdist[-1]
-choices[bisect.bisect(cumdist, x)]
-
-
-modular_division_table = [[0]*26 for x in range(26)]
+modular_division_table = [[0]*26 for _ in range(26)]

 for a in range(26):
     for b in range(26):
         c = (a * b) % 26
         modular_division_table[b][c] = a
 
 for a in range(26):
     for b in range(26):
         c = (a * b) % 26
         modular_division_table[b][c] = a
 

-def letters(text):
-    """Remove all non-alphabetic characters from a text
-    >>> letters('The Quick')
-    'TheQuick'
-    >>> letters('The Quick BROWN fox jumped! over... the (9lazy) DOG')
-    'TheQuickBROWNfoxjumpedoverthelazyDOG'
-    """
-    return ''.join([c for c in text if c in string.ascii_letters])
-
-def sanitise(text):
-    """Remove all non-alphabetic characters and convert the text to lowercase
-    
-    >>> sanitise('The Quick')
-    'thequick'
-    >>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
-    'thequickbrownfoxjumpedoverthelazydog'
-    """
-    # sanitised = [c.lower() for c in text if c in string.ascii_letters]
-    # return ''.join(sanitised)
-    return letters(text).lower()
-
-def ngrams(text, n):
-    """Returns all n-grams of a text
-    
-    >>> ngrams(sanitise('the quick brown fox'), 2) # doctest: +NORMALIZE_WHITESPACE
-    ['th', 'he', 'eq', 'qu', 'ui', 'ic', 'ck', 'kb', 'br', 'ro', 'ow', 'wn', 
-     'nf', 'fo', 'ox']
-    >>> ngrams(sanitise('the quick brown fox'), 4) # doctest: +NORMALIZE_WHITESPACE
-    ['theq', 'hequ', 'equi', 'quic', 'uick', 'ickb', 'ckbr', 'kbro', 'brow', 
-     'rown', 'ownf', 'wnfo', 'nfox']
-    """
-    return [text[i:i+n] for i in range(len(text)-n+1)]

 
 def every_nth(text, n, fillvalue=''):
     """Returns n strings, each of which consists of every nth character, 
 
 def every_nth(text, n, fillvalue=''):
     """Returns n strings, each of which consists of every nth character, 


@@ -358,46 +313,29 @@ def keyword_decipher(message, keyword, wrap_alphabet=0):
     cipher_translation = ''.maketrans(cipher_alphabet, string.ascii_lowercase)
     return message.lower().translate(cipher_translation)
 
     cipher_translation = ''.maketrans(cipher_alphabet, string.ascii_lowercase)
     return message.lower().translate(cipher_translation)
 

-def scytale_encipher(message, rows):
-    """Enciphers using the scytale transposition cipher.
-    Message is padded with spaces to allow all rows to be the same length.

 
 

-    >>> scytale_encipher('thequickbrownfox', 3)
-    'tcnhkfeboqrxuo iw '
-    >>> scytale_encipher('thequickbrownfox', 4)
-    'tubnhirfecooqkwx'
-    >>> scytale_encipher('thequickbrownfox', 5)
-    'tubn hirf ecoo qkwx '
-    >>> scytale_encipher('thequickbrownfox', 6)
-    'tqcrnxhukof eibwo '
-    >>> scytale_encipher('thequickbrownfox', 7)
-    'tqcrnx hukof  eibwo  '
+def vigenere_encipher(message, keyword):
+    """Vigenere encipher
+
+    >>> vigenere_encipher('hello', 'abc')
+    'hfnlp'

     """
     """

-    if len(message) % rows != 0:
-        message += ' '*(rows - len(message) % rows)
-    row_length = round(len(message) / rows)
-    slices = [message[i:i+row_length] 
-              for i in range(0, len(message), row_length)]
-    return ''.join([''.join(r) for r in zip_longest(*slices, fillvalue='')])
+    shifts = [ord(l) - ord('a') for l in sanitise(keyword)]
+    pairs = zip(message, cycle(shifts))
+    return ''.join([caesar_encipher_letter(l, k) for l, k in pairs])

 
 

-def scytale_decipher(message, rows):
-    """Deciphers using the scytale transposition cipher.
-    Assumes the message is padded so that all rows are the same length.
-    
-    >>> scytale_decipher('tcnhkfeboqrxuo iw ', 3)
-    'thequickbrownfox  '
-    >>> scytale_decipher('tubnhirfecooqkwx', 4)
-    'thequickbrownfox'
-    >>> scytale_decipher('tubn hirf ecoo qkwx ', 5)
-    'thequickbrownfox    '
-    >>> scytale_decipher('tqcrnxhukof eibwo ', 6)
-    'thequickbrownfox  '
-    >>> scytale_decipher('tqcrnx hukof  eibwo  ', 7)
-    'thequickbrownfox     '
+def vigenere_decipher(message, keyword):
+    """Vigenere decipher
+
+    >>> vigenere_decipher('hfnlp', 'abc')
+    'hello'

     """
     """

-    cols = round(len(message) / rows)
-    columns = [message[i:i+rows] for i in range(0, cols * rows, rows)]
-    return ''.join([''.join(c) for c in zip_longest(*columns, fillvalue='')])
+    shifts = [ord(l) - ord('a') for l in sanitise(keyword)]
+    pairs = zip(message, cycle(shifts))
+    return ''.join([caesar_decipher_letter(l, k) for l, k in pairs])
+
+beaufort_encipher=vigenere_decipher
+beaufort_decipher=vigenere_encipher

 
 
 def transpositions_of(keyword):
 
 
 def transpositions_of(keyword):


@@ -439,20 +377,43 @@ def column_transposition_encipher(message, keyword, fillvalue=' ',
     """Enciphers using the column transposition cipher.
     Message is padded to allow all rows to be the same length.
 
     """Enciphers using the column transposition cipher.
     Message is padded to allow all rows to be the same length.
 

-    >>> column_transposition_encipher('hellothere', 'clever')
+    >>> column_transposition_encipher('hellothere', 'abcdef', fillcolumnwise=True)
+    'hlohr eltee '
+    >>> column_transposition_encipher('hellothere', 'abcdef', fillcolumnwise=True, emptycolumnwise=True)
+    'hellothere  '
+    >>> column_transposition_encipher('hellothere', 'abcdef')
+    'hellothere  '
+    >>> column_transposition_encipher('hellothere', 'abcde')
+    'hellothere'
+    >>> column_transposition_encipher('hellothere', 'abcde', fillcolumnwise=True, emptycolumnwise=True)
+    'hellothere'
+    >>> column_transposition_encipher('hellothere', 'abcde', fillcolumnwise=True, emptycolumnwise=False)
+    'hlohreltee'
+    >>> column_transposition_encipher('hellothere', 'abcde', fillcolumnwise=False, emptycolumnwise=True)
+    'htehlelroe'
+    >>> column_transposition_encipher('hellothere', 'abcde', fillcolumnwise=False, emptycolumnwise=False)
+    'hellothere'
+    >>> column_transposition_encipher('hellothere', 'clever', fillcolumnwise=True, emptycolumnwise=True)
+    'heotllrehe'
+    >>> column_transposition_encipher('hellothere', 'clever', fillcolumnwise=True, emptycolumnwise=False)
+    'holrhetlee'
+    >>> column_transposition_encipher('hellothere', 'clever', fillcolumnwise=False, emptycolumnwise=True)
+    'htleehoelr'
+    >>> column_transposition_encipher('hellothere', 'clever', fillcolumnwise=False, emptycolumnwise=False)

     'hleolteher'
     'hleolteher'

+    >>> column_transposition_encipher('hellothere', 'cleverly')
+    'hleolthre e '

     >>> column_transposition_encipher('hellothere', 'cleverly', fillvalue='!')
     'hleolthre!e!'
     >>> column_transposition_encipher('hellothere', 'cleverly', fillvalue='!')
     'hleolthre!e!'

-    >>> column_transposition_encipher('hellothere', 'clever', columnwise=True)
-    'htleehoelr'
+    >>> column_transposition_encipher('hellothere', 'cleverly', fillvalue=lambda: '*')
+    'hleolthre*e*'

     """
     transpositions = transpositions_of(keyword)
     message += pad(len(message), len(transpositions), fillvalue)
     if fillcolumnwise:
     """
     transpositions = transpositions_of(keyword)
     message += pad(len(message), len(transpositions), fillvalue)
     if fillcolumnwise:

-        rows = every_nth(message, len(transpositions))
+        rows = every_nth(message, len(message) // len(transpositions))

     else:
     else:

-        rows = chunks(mesage, len(transpositions))
-    columns = every_nth(message, len(transpositions), fillvalue=fillvalue)
+        rows = chunks(message, len(transpositions))

     transposed = [transpose(r, transpositions) for r in rows]
     if emptycolumnwise:
         return combine_every_nth(transposed)
     transposed = [transpose(r, transpositions) for r in rows]
     if emptycolumnwise:
         return combine_every_nth(transposed)


@@ -460,48 +421,77 @@ def column_transposition_encipher(message, keyword, fillvalue=' ',
         return ''.join(chain(*transposed))
 
 def column_transposition_decipher(message, keyword, fillvalue=' ', 
         return ''.join(chain(*transposed))
 
 def column_transposition_decipher(message, keyword, fillvalue=' ', 

-      columnwise=False):
+      fillcolumnwise=False,
+      emptycolumnwise=False):

     """Deciphers using the column transposition cipher.
     Message is padded to allow all rows to be the same length.
 
     """Deciphers using the column transposition cipher.
     Message is padded to allow all rows to be the same length.
 

-    >>> column_transposition_decipher('hleolteher', 'clever')
+    >>> column_transposition_decipher('hellothere', 'abcde', fillcolumnwise=True, emptycolumnwise=True)
+    'hellothere'
+    >>> column_transposition_decipher('hlohreltee', 'abcde', fillcolumnwise=True, emptycolumnwise=False)
+    'hellothere'
+    >>> column_transposition_decipher('htehlelroe', 'abcde', fillcolumnwise=False, emptycolumnwise=True)
+    'hellothere'
+    >>> column_transposition_decipher('hellothere', 'abcde', fillcolumnwise=False, emptycolumnwise=False)
+    'hellothere'
+    >>> column_transposition_decipher('heotllrehe', 'clever', fillcolumnwise=True, emptycolumnwise=True)
+    'hellothere'
+    >>> column_transposition_decipher('holrhetlee', 'clever', fillcolumnwise=True, emptycolumnwise=False)

     'hellothere'
     'hellothere'

-    >>> column_transposition_decipher('hleolthre!e!', 'cleverly', fillvalue='?')
-    'hellothere!!'
-    >>> column_transposition_decipher('htleehoelr', 'clever', columnwise=True)
+    >>> column_transposition_decipher('htleehoelr', 'clever', fillcolumnwise=False, emptycolumnwise=True)
+    'hellothere'
+    >>> column_transposition_decipher('hleolteher', 'clever', fillcolumnwise=False, emptycolumnwise=False)

     'hellothere'
     """
     transpositions = transpositions_of(keyword)
     'hellothere'
     """
     transpositions = transpositions_of(keyword)

-    if columnwise:
-        columns = chunks(message, int(len(message) / len(transpositions)))
+    message += pad(len(message), len(transpositions), '*')
+    if emptycolumnwise:
+        rows = every_nth(message, len(message) // len(transpositions))

     else:
     else:

-        columns = every_nth(message, len(transpositions), fillvalue=fillvalue)
-    untransposed_columns = untranspose(columns, transpositions)
-    return combine_every_nth(untransposed_columns)
-
+        rows = chunks(message, len(transpositions))
+    untransposed = [untranspose(r, transpositions) for r in rows]
+    if fillcolumnwise:
+        return combine_every_nth(untransposed)
+    else:
+        return ''.join(chain(*untransposed))

 
 

-def vigenere_encipher(message, keyword):
-    """Vigenere encipher
+def scytale_encipher(message, rows, fillvalue=' '):
+    """Enciphers using the scytale transposition cipher.
+    Message is padded with spaces to allow all rows to be the same length.

 
 

-    >>> vigenere_encipher('hello', 'abc')
-    'hfnlp'
+    >>> scytale_encipher('thequickbrownfox', 3)
+    'tcnhkfeboqrxuo iw '
+    >>> scytale_encipher('thequickbrownfox', 4)
+    'tubnhirfecooqkwx'
+    >>> scytale_encipher('thequickbrownfox', 5)
+    'tubnhirfecooqkwx'
+    >>> scytale_encipher('thequickbrownfox', 6)
+    'tqcrnxhukof eibwo '
+    >>> scytale_encipher('thequickbrownfox', 7)
+    'tqcrnxhukof eibwo '

     """
     """

-    shifts = [ord(l) - ord('a') for l in sanitise(keyword)]
-    pairs = zip(message, cycle(shifts))
-    return ''.join([caesar_encipher_letter(l, k) for l, k in pairs])
-
-def vigenere_decipher(message, keyword):
-    """Vigenere decipher
+    transpositions = [i for i in range(math.ceil(len(message) / rows))]
+    return column_transposition_encipher(message, transpositions, 
+        fillcolumnwise=False, emptycolumnwise=True)

 
 

-    >>> vigenere_decipher('hfnlp', 'abc')
-    'hello'
+def scytale_decipher(message, rows):
+    """Deciphers using the scytale transposition cipher.
+    Assumes the message is padded so that all rows are the same length.
+    
+    >>> scytale_decipher('tcnhkfeboqrxuo iw ', 3)
+    'thequickbrownfox  '
+    >>> scytale_decipher('tubnhirfecooqkwx', 4)
+    'thequickbrownfox'
+    >>> scytale_decipher('tubnhirfecooqkwx', 5)
+    'thequickbrownfox'
+    >>> scytale_decipher('tqcrnxhukof eibwo ', 6)
+    'thequickbrownfox  '
+    >>> scytale_decipher('tqcrnxhukof eibwo ', 7)
+    'thequickbrownfox  '

     """
     """

-    shifts = [ord(l) - ord('a') for l in sanitise(keyword)]
-    pairs = zip(message, cycle(shifts))
-    return ''.join([caesar_decipher_letter(l, k) for l, k in pairs])
-
-beaufort_encipher=vigenere_decipher
-beaufort_decipher=vigenere_encipher
+    transpositions = [i for i in range(math.ceil(len(message) / rows))]
+    return column_transposition_decipher(message, transpositions, 
+        fillcolumnwise=False, emptycolumnwise=True)

 
 
 if __name__ == "__main__":
 
 
 if __name__ == "__main__":