fügt match_ciphertext in break_mono hinzu

src/mono/break_mono.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 """
 Python module to derive a key from an monoalphabetically encrypted file.
 """
@@ -27,7 +29,7 @@ class Breaker():
     def derive_alphabet_freq(freq: Counter):
         most_freq = [ item[0] for item in freq.most_common() ]
         #return OrderedDict(zip(EN_LETTER_FREQ, most_freq))
-        return OrderedDict(zip(EN_LETTER_FREQ, most_freq))
+        return OrderedDict(zip(Breaker.EN_LETTER_FREQ, most_freq))
 
 
     ## pattern matching
@@ -40,32 +42,65 @@ class Breaker():
         TUPLE(word, pos) where `pos' is a LIST of matching positions.
         """
         with open(word_file, 'r') as f:
-            for word in f:
+            for line in f:
+                word = line[:-1]
                 pos = []
                 for char in char_list:
-                    pos += word.find(char)
+                    pos.append(word.find(char))
                 if -1 not in pos:
                     return word, pos
-        return None
+        return None, None
+
+    @staticmethod
+    def positions(text: str, sub):
+        index = text.find(sub)
+        while index != -1:
+            yield index
+            index = text.find(sub, index + 1)
+        return index
 
 
+    @staticmethod
+    def match_ciphertext(text: str, word_pos: tuple, char: tuple):
+        word, wposl = word_pos
+        wpos = wposl[0]
+        wlen = len(word)
+
+        snip_count = Counter()
+        for pos in Breaker.positions(text, char):
+            word_begin = pos - wpos
+            snippet = text[word_begin : word_begin + wlen]
+
+            if snippet not in snip_count.elements():
+                snip_count[snippet] = text.count(snippet)
+
+        return snip_count.most_common(1)[0][0]
+
     def __init__(self, ciphertext, word_file):
-        self.alph = derive_alphabet_freq(get_frequency(ciphertext))
-        self.word_file = None  # TODO
+        self.ciphertext = ciphertext
+        self.alph = self.derive_alphabet_freq(self.get_frequency(ciphertext))
+        self.word_file = word_file
 
 
     def get_key(self):
-        most_freq = next(iter(self.alph))  # most frequent char
-        word_having_char, pos = get_word_containing(self.word_file, most_freq)
-
-        pass
 
 
 
-text = "gryticdettpjcjgtmtntajgryticdkrqstmkojgjgtmtrmjgtatnrgdpmatmjgcdnrpmhgoqmatpetopzsoqqtmfcajgtoaeatrmrpmjgtfozdatnmcpjqotjgtinltrscfgdwrpmontrntedjktmckgrjktkrpjrpmktjgopskgrjktlqtrntgryticdqoytmjgttultaotphtgryticdkojptnntmjgtlqrzdtltclqtwrsopzereotnncwtjowtnxdnjjctnhrltopjgonqrpmcfhcwltjojocpjgthcwlrnnocponzcptitjktozpcatjgtpttmirpmktsttlldngopzcpktsttlldngopzcpjgononxdnjrldpsachsncpzkaojjtpfcajgtltclqtkgchrpnttncwtjgopznkacpzqostrpjnoprhcqcpiktmccdangratedjjgtatnncwrpicjgtafdhsopopnthjncdjjgtatrpmjgononxdnjrldpsachsncpzqostkcastanoprfrhjcaiktmccdangratedjjgtatnncwrpicjgtafdhsopacecjncdjjgtatgryticdyonojtmjgtbdrzwoatgryticdnkrwopjgtngojjgtlrajihcpytpjocpnrpmjgtatrqlcqojosjgtfrhtnrqkrinmofftatpjjgtagtjcaohjgtnrwtedjktnkrqqckojrpmktnttpcjgopzhgrpztpcjgopzgrnhgrpztmjtpwoqqocpmcqqrancprqcnopzhrwlrozpjktpjiwoqqocpnjrayopzrpmkaojgopzoplropeoznjacpzltclqtdpkoqqopzjczoytnwrqqopyonocprpmltanlthjoytcptopfoytsomnetqckjgtlcytajiqoptcptlcldqrjocpadppopcdjcfjowt"
+        # most frequent char in English and corresponding most common char in text
+        #most_freq = self.alph.popitem(last=False)
+        most_freq = next(iter(self.alph))
+        word_pos = Breaker.get_word_containing(
+            self.word_file,
+            #most_freq[0]
+            most_freq
+        )
+        most_common = Breaker.match_ciphertext(
+            self.ciphertext,
+            word_pos,
+            most_freq
+        )
 
+        print("most_freq", most_freq, "word_pos:", word_pos, "most_common:", most_common)
 
-freq = get_frequency(text)
-alph = derive_alphabet(freq)
 
-print(alph.values())
+    ## end Breaker