Add regression test for #775

This commit is contained in:
Ines Montani 2017-01-25 13:16:52 +01:00
parent 209c37bbcf
commit 19501f3340
1 changed files with 13 additions and 0 deletions

View File

@ -0,0 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize('text', ["Shell", "shell"])
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