Merge branch 'develop' of https://github.com/explosion/spaCy into develop

This commit is contained in:
Matthew Honnibal 2019-03-11 01:07:34 +01:00
commit 04ca710da7

View File

@ -12,12 +12,14 @@ from spacy.lang.en import English
from ..util import add_vecs_to_vocab, get_doc
@pytest.mark.xfail(
reason="The dot is now properly split off, but the prefix/suffix rules are not applied again afterwards."
"This means that the quote will still be attached to the remaining token."
)
@pytest.mark.xfail
def test_issue2070():
"""Test that checks that a dot followed by a quote is handled appropriately."""
"""Test that checks that a dot followed by a quote is handled
appropriately.
"""
# Problem: The dot is now properly split off, but the prefix/suffix rules
# are not applied again afterwards. This means that the quote will still be
# attached to the remaining token.
nlp = English()
doc = nlp('First sentence."A quoted sentence" he said ...')
assert len(doc) == 11