From: Neil Smith Date: Fri, 21 Oct 2016 12:33:30 +0000 (+0100) Subject: Added more special characters for unaccent X-Git-Url: https://git.njae.me.uk/?a=commitdiff_plain;h=467737b20cdb3cea90c8750d261a3ae084af071a;p=cipher-training.git Added more special characters for unaccent --- diff --git a/language_models.py b/language_models.py index bf00875..644338e 100644 --- a/language_models.py +++ b/language_models.py @@ -11,7 +11,7 @@ import itertools from math import log10 import os -unaccent_specials = ''.maketrans({"’": "'"}) +unaccent_specials = ''.maketrans({"’": "'", '“': '"', '”': '"'}) def letters(text): """Remove all non-alphabetic characters from a text