Exclude "were" and "Were" from tokenizer exceptions and add regression test (resolves #744)

spacy/en/tokenizer_exceptions.py

@@ -7,7 +7,7 @@ from ..language_data import PRON_LEMMA
 
 EXC = {}
 
-EXCLUDE_EXC = ["Ill", "ill", "Its", "its", "Hell", "hell", "Well", "well", "Whore", "whore"]
+EXCLUDE_EXC = ["Ill", "ill", "Its", "its", "Hell", "hell", "were", "Were", "Well", "well", "Whore", "whore"]
 
 
 # Pronouns

spacy/tests/regression/test_issue744.py

@@ -0,0 +1,13 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+
+@pytest.mark.parametrize('text', ["We were scared", "We Were Scared"])
+def test_issue744(en_tokenizer, text):
+    """Test that 'were' and 'Were' are excluded from the contractions
+    generated by the English tokenizer exceptions."""
+    tokens = en_tokenizer(text)
+    assert len(tokens) == 3
+    assert tokens[1].text.lower() == "were"