unicode strings for 2.7 compatibility

Author: chsasank

intermediate_source/char_rnn_classification_tutorial.py

@@ -64,7 +64,8 @@
 ``{language: [names ...]}``. The generic variables "category" and "line"
 (for language and name in our case) are used for later extensibility.
 """
-
+from __future__ import unicode_literals, print_function, division
+from io import open
 import glob
 
 def findFiles(path): return glob.glob(path)
@@ -93,7 +94,7 @@ def unicodeToAscii(s):
 
 # Read a file and split into lines
 def readLines(filename):
-    lines = open(filename).read().strip().split('\n')
+    lines = open(filename, encoding='utf-8').read().strip().split('\n')
     return [unicodeToAscii(line) for line in lines]
 
 for filename in findFiles('data/names/*.txt'):

intermediate_source/char_rnn_generation_tutorial.py

@@ -74,6 +74,8 @@
 and end up with a dictionary ``{language: [names ...]}``.
 
 """
+from __future__ import unicode_literals, print_function, division
+from io import open
 import glob
 import unicodedata
 import string
@@ -93,7 +95,7 @@ def unicodeToAscii(s):
 
 # Read a file and split into lines
 def readLines(filename):
-    lines = open(filename).read().strip().split('\n')
+    lines = open(filename, encoding='utf-8').read().strip().split('\n')
     return [unicodeToAscii(line) for line in lines]
 
 # Build the category_lines dictionary, a list of lines per category

intermediate_source/seq2seq_translation_tutorial.py

@@ -83,7 +83,8 @@
 
 **Requirements**
 """
-
+from __future__ import unicode_literals, print_function, division
+from io import open
 import unicodedata
 import string
 import re
@@ -208,7 +209,8 @@ def readLangs(lang1, lang2, reverse=False):
     print("Reading lines...")
 
     # Read the file and split into lines
-    lines = open('data/%s-%s.txt' % (lang1, lang2)).read().strip().split('\n')
+    lines = open('data/%s-%s.txt' % (lang1, lang2), encoding='utf-8').\
+        read().strip().split('\n')
 
     # Split every line into pairs and normalize
     pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]