unicode string for python 2.7

spacy/lang/en/stop_words.py

@@ -70,6 +70,6 @@ yet you your yours yourself yourselves
 )
 
 for hyphen in ["'", "`", "‘", "´", "’"]:
-    for stopword in "n't 'd 'll 'm 're 's 've".split():
+    for stopword in u"n't 'd 'll 'm 're 's 've".split():
         STOP_WORDS.add(stopword.replace("'", hyphen))
 

spacy/tests/regression/test_issue3521.py

@@ -4,10 +4,10 @@ import pytest
 @pytest.mark.parametrize(
     "word",
     [
-        "don't",
-        "don’t",
-        "I'd",
-        "I’d",
+        u"don't",
+        u"don’t",
+        u"I'd",
+        u"I’d",
     ],
 )
 def test_issue3521(en_tokenizer, word):