X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=language_models.py;h=19f886fcefcb4384184e0bbad108e6925f029bbf;hb=236b087b3891bbedca39de40f0a2cce42fbc62c8;hp=1b90ac2ca425c1a246b410ac2f7a588931105f00;hpb=27abb216333fda20dc857a8a501fbee4a4a962f4;p=cipher-tools.git

diff --git a/language_models.py b/language_models.py
index 1b90ac2..19f886f 100644
--- a/language_models.py
+++ b/language_models.py
@@ -6,6 +6,8 @@ import unicodedata
 import itertools
 from math import log10
 
+unaccent_specials = ''.maketrans({"’": "'"})
+
 def letters(text):
     """Remove all non-alphabetic characters from a text
     >>> letters('The Quick')
@@ -31,7 +33,8 @@ def unaccent(text):
     >>> unaccent('HÉLLÖ')
     'HELLO'
     """
-    return unicodedata.normalize('NFKD', text).\
+    translated_text = text.translate(unaccent_specials)
+    return unicodedata.normalize('NFKD', translated_text).\
         encode('ascii', 'ignore').\
         decode('utf-8')
 
@@ -121,7 +124,7 @@ def log_probability_of_unknown_word(key, N):
 
 Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
 Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
-Pl2 = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
+P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
 
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.