mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 11:59:14 +03:00
12 lines
359 B
Python
12 lines
359 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,expected_tokens", [("d'un", ["d'", "un"]), ("s'ha", ["s'", "ha"])]
|
|
)
|
|
def test_contractions(ca_tokenizer, text, expected_tokens):
|
|
"""Test that the contractions are split into two tokens"""
|
|
tokens = ca_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|