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=5184c96f06f9f97d6af9b3d994e9b227cbb8b76c;hp=ea80d31dac330167760e2dd7850d3bf6ed9036fc;p=cipher-tools.git Added more special characters for unaccent --- diff --git a/language_models.py b/language_models.py index 5a35b38..8824bca 100644 --- a/language_models.py +++ b/language_models.py @@ -7,7 +7,7 @@ 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