spaCy/spacy/tests/regression/test_issue775.py

14 lines
401 B
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize('text', ["Shell", "shell", "Shed", "shed"])
def test_issue775(en_tokenizer, text):
"""Test that 'Shell' and 'shell' are excluded from the contractions
generated by the English tokenizer exceptions."""
tokens = en_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].text == text