diff --git a/spacy/tests/regression/test_issue704.py b/spacy/tests/regression/test_issue704.py new file mode 100644 index 000000000..2cecf6219 --- /dev/null +++ b/spacy/tests/regression/test_issue704.py @@ -0,0 +1,14 @@ +# coding: utf8 +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.models +def test_issue704(EN): + """Test that sentence boundaries are detected correctly.""" + + text = '“Atticus said to Jem one day, “I’d rather you shot at tin cans in the backyard, but I know you’ll go after birds. Shoot all the blue jays you want, if you can hit ‘em, but remember it’s a sin to kill a mockingbird.”' + doc = EN(text) + sents = [sent for sent in doc.sents] + assert len(sents) == 3