mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +03:00
15 lines
417 B
Python
15 lines
417 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,expected_tokens", [("c'è", ["c'", "è"]), ("l'ha", ["l'", "ha"])]
|
|
)
|
|
def test_contractions(it_tokenizer, text, expected_tokens):
|
|
""" Test that the contractions are split into two tokens"""
|
|
tokens = it_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|