Fiddling with cracking dictionaries

[cipher-tools.git] / segment.py

diff --git a/segment.py b/segment.py
index 27bf103c573f0d228a03741ef34dd360138ad072..dd0b2a8347ee800c4addf996f369ea0293b47bb7 100644 (file)
--- a/segment.py
+++ b/segment.py
@@ -1,20 +1,12 @@
-# import re, string, random, glob, operator, heapq
 import string
 import collections
 from math import log10
 import itertools
+import sys
+from functools import lru_cache
+sys.setrecursionlimit(1000000)
 
-def memo(f):
-    "Memoize function f."
-    table = {}
-    def fmemo(*args):
-        if args not in table:
-            table[args] = f(*args)
-        return table[args]
-    fmemo.memo = table
-    return fmemo
-
-@memo
+@lru_cache()
 def segment(text):
     """Return a list of words that is the best segmentation of text.
     """
@@ -31,7 +23,7 @@ def splits(text, L=20):
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.
     """
-    return sum(Pw[w] for w in words)
+    return sum(Pw[w.lower()] for w in words)
 
 class Pdist(dict):
     """A probability distribution estimated from counts in datafile.