Using ngram length for scytale break

[cipher-tools.git] / cipher.py

diff --git a/cipher.py b/cipher.py
index bd07596815fd629ddf348b5bca12fbd75f080a2f..0e22a2a85bbc0afa5c6dc1b5caaf6c80459fcb2e 100644 (file)
--- a/cipher.py
+++ b/cipher.py
@@ -51,6 +51,14 @@ for a 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
@@ -60,8 +68,9 @@ def sanitise(text):
     >>> 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)
+    # 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
@@ -160,11 +169,14 @@ def frequencies(text):
      ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('n', 1), 
      ('o', 4), ('p', 1), ('q', 1), ('r', 2), ('t', 2), ('u', 2), ('v', 1), 
      ('w', 1), ('x', 1), ('y', 1), ('z', 1)]
+    >>> frequencies('abcdefabcdef')['x']
+    0
     """
-    counts = collections.defaultdict(int)
-    for c in text: 
-        counts[c] += 1
-    return counts
+    #counts = collections.defaultdict(int)
+    #for c in text: 
+    #    counts[c] += 1
+    #return counts
+    return collections.Counter(c for c in text)
 letter_frequencies = frequencies
 
 def deduplicate(text):
@@ -643,11 +655,12 @@ def scytale_break(message,
     """
     best_key = 0
     best_fit = float("inf")
+    ngram_length = len(next(iter(target_counts.keys())))
     for key in range(1, 20):
         if len(message) % key == 0:
             plaintext = scytale_decipher(message, key)
             counts = message_frequency_scaling(frequencies(
-                         ngrams(sanitise(plaintext), 2)))
+                         ngrams(sanitise(plaintext), ngram_length)))
             fit = metric(target_counts, counts)
             logger.debug('Scytale break attempt using key {0} gives fit of '
                          '{1} and decrypt starting: {2}'.format(key,