spaCy/spacy/tests/regression/test_issue744.py

14 lines
411 B
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize('text', ["We were scared", "We Were Scared"])
def test_issue744(en_tokenizer, text):
"""Test that 'were' and 'Were' are excluded from the contractions
generated by the English tokenizer exceptions."""
tokens = en_tokenizer(text)
assert len(tokens) == 3
assert tokens[1].text.lower() == "were"