spaCy/spacy/tests/regression/test_issue3521.py
2019-04-03 13:50:33 +02:00

20 lines
365 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize(
"word",
[
"don't",
"dont",
"I'd",
"Id",
],
)
def test_issue3521(en_tokenizer, word):
tok = en_tokenizer(word)[1]
# 'not' and 'would' should be stopwords, also in their abbreviated forms
assert tok.is_stop