spaCy/spacy/tests/lang/it/test_prefix_suffix_infix.py

12 lines
359 B
Python
Raw Normal View History

import pytest
@pytest.mark.parametrize(
"text,expected_tokens", [("c'è", ["c'", "è"]), ("l'ha", ["l'", "ha"])]
)
def test_contractions(it_tokenizer, text, expected_tokens):
2021-07-02 07:48:26 +00:00
"""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