spaCy/spacy/tests/regression/test_issue704.py

16 lines
541 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
import pytest
@pytest.mark.xfail
@pytest.mark.models('en')
def test_issue704(EN):
"""Test that sentence boundaries are detected correctly."""
text = '“Atticus said to Jem one day, “Id rather you shot at tin cans in the backyard, but I know youll go after birds. Shoot all the blue jays you want, if you can hit em, but remember its a sin to kill a mockingbird.”'
doc = EN(text)
sents = list([sent for sent in doc.sents])
assert len(sents) == 3