spaCy/spacy/tests/regression/test_issue3449.py

23 lines
626 B
Python
Raw Normal View History

2019-04-02 11:06:37 +00:00
import pytest
from spacy.lang.en import English
@pytest.mark.xfail(reason="Current default suffix rules avoid one upper-case letter before a dot.")
def test_issue3449():
nlp = English()
nlp.add_pipe(nlp.create_pipe('sentencizer'))
text1 = "He gave the ball to I. Do you want to go to the movies with I?"
text2 = "He gave the ball to I. Do you want to go to the movies with I?"
text3 = "He gave the ball to I.\nDo you want to go to the movies with I?"
t1 = nlp(text1)
t2 = nlp(text2)
t3 = nlp(text3)
assert t1[5].text == 'I'
assert t2[5].text == 'I'
assert t3[5].text == 'I'