fügt diverse Bugfixes hinzu

src/mono/break_mono.py

@@ -7,34 +7,45 @@ Python module to derive a key from an monoalphabetically encrypted file.
 import re
 
 from collections import Counter
+#from string import ascii_lowercase
 
-
+import pdb
 
 class Breaker():
 
-
     EN_LETTER_FREQ = list("etaoinsrhdlucmfywgpbvkxqjz")
 
-    def __init__(self, ciphertext, word_file):
-
-        most_freq_cipher = Counter(ciphertext).most_common(1)[0][0]
-
-        # excuse me:
+    @staticmethod
+    def read_word_file(word_file):
+        # excuse me
         words = []
         with open(word_file, 'r') as wf:
             for line in wf:
-                words.append(line[:-1])  # remove trailing newline and append
+                word = line[:-1] # remove trailing newline
+                word = word.lower()
+
+                if word == "" or not word.isalpha():
+                    continue
+
+                words.append(word)
+        return words
+
+    def __init__(self, ciphertext, word_file):
+
+        most_freq_cipher = Counter(ciphertext).most_common(1)[0][0]
 
         self.text = ciphertext
         self.key = { Breaker.EN_LETTER_FREQ[0] : most_freq_cipher }
-        self.words = words
+        self.words = Breaker.read_word_file(word_file)
 
     def choose_word(self):
         known_chars = self.key.keys()
         for i in range(len(self.words)):
             word = self.words[i]
 
-            if len(word) == 0: continue
+            if len(word) == 0:
+                self.words.pop(i)
+                continue
 
             # count known chars in word
             n = 0
@@ -42,11 +53,15 @@ class Breaker():
                 if char in known_chars:
                     n +=1
 
-            # skip known words or words with too many unknown
-            if n == len(word) or n / len(word) < 0.3:
+            # remove known words
+            if n == len(word):
+                self.words.pop(i)
                 continue
 
-            return self.words[i]
+            # skip words with too many unknown chars
+            if (n / len(word) < 0.3): continue
+
+            return self.words.pop(i)
 
     def translate_and_regex(self, word: str):
         regex = ""
@@ -58,12 +73,16 @@ class Breaker():
         return regex
 
     def match_ciphertext(self, regex):
-        rx = re.compile(regex)
-        count = Counter(re.findall(self.text))
-        return count.most_common(1)[0][0]
+        regexc = re.compile(regex)
+        count = Counter(regexc.findall(self.text))
+        if len(count) == 0:
+            return ""
+        else:
+            return count.most_common(1)[0][0]
 
     def extract_unknown(self, plain, regex, cipher):
         assert len(plain) == len(regex) == len(cipher)
+        assert "." in regex
 
         for i in range(len(regex)):
             if regex[i] != ".": continue
@@ -81,7 +100,11 @@ class Breaker():
             word   = self.choose_word()
             regex  = self.translate_and_regex(word)
             cipher = self.match_ciphertext(regex)
-            print(word, regex, cipher, self.extract_unknown())
+
+            if cipher == "": continue
+
+            print(word, regex, cipher,
+                  self.extract_unknown(word, regex, cipher))
 
         return self.key_to_str()