2017-01-25 12:16:52 +00:00
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
2017-02-18 13:10:41 +00:00
|
|
|
@pytest.mark.parametrize('text', ["Shell", "shell", "Shed", "shed"])
|
2017-01-25 12:16:52 +00:00
|
|
|
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
|
