X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=cipher.py;h=c2038458aee5416fbc66f53b5a3668a42165381a;hb=87384b26b1af0453465bdc0f33584364ef719794;hp=4fa44cf65a2c31fbef399ffa4b3f3a57bc041064;hpb=a573fbbbdcdc110be7b35cbe78a8a45af99da461;p=cipher-tools.git

diff --git a/cipher.py b/cipher.py
index 4fa44cf..c203845 100644
--- a/cipher.py
+++ b/cipher.py
@@ -43,6 +43,14 @@ 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
@@ -52,8 +60,9 @@ 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
@@ -152,11 +161,14 @@ 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)]
-    """
-    counts = collections.defaultdict(int)
-    for c in text: 
-        counts[c] += 1
-    return counts
+    >>> frequencies('abcdefabcdef')['x']
+    0
+    """
+    #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):