Added more special characters for unaccent
authorNeil Smith <neil.git@njae.me.uk>
Fri, 21 Oct 2016 12:33:30 +0000 (13:33 +0100)
committerNeil Smith <neil.git@njae.me.uk>
Wed, 4 Oct 2017 08:21:59 +0000 (09:21 +0100)
language_models.py

index 5a35b38ec32867dbe00f6fe6e99ada066e858c8e..8824bca4597327623798382288c2bcffb9d8005b 100644 (file)
@@ -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