diff --git a/tests/test_infix.py b/tests/test_infix.py new file mode 100644 index 000000000..a1f6a627e --- /dev/null +++ b/tests/test_infix.py @@ -0,0 +1,17 @@ +from __future__ import unicode_literals + +import pytest + +from spacy.en import EN + + +def test_hyphen(): + tokens = EN.tokenize('best-known') + assert len(tokens) == 3 + + +def test_period(): + tokens = EN.tokenize('best.Known') + assert len(tokens) == 3 + tokens = EN.tokenize('zombo.com') + assert len(tokens) == 1