Merge pull request #1 from pwry/master

make check_code unicode-compatible
teuben · Aug 29, 2017 · 182ec2f · 182ec2f
2 parents 70a8ee1 + 6c995a0
commit 182ec2f
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/check_code.py b/check_code.py
@@ -9,7 +9,7 @@
 #from __future__ import division  # Python 2 users only
 #from __future__ import print_function
 import sys, os
-
+import codecs
 import nltk, re, pprint
 
 #from nltk import word_tokenize
@@ -21,7 +21,7 @@
 
 def try1(txtfile):
     #f = open('1408.6846v1.txt')
-    f = open(txtfile)
+    f = codecs.open(txtfile, encoding='utf-8')
     raw = f.read()
     #
     tokens = nltk.word_tokenize(raw)