mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
21 lines
591 B
Python
21 lines
591 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
ABBREVIATION_TESTS = [
|
|
(
|
|
"Hyvää uutta vuotta t. siht. Niemelä!",
|
|
["Hyvää", "uutta", "vuotta", "t.", "siht.", "Niemelä", "!"],
|
|
),
|
|
("Paino on n. 2.2 kg", ["Paino", "on", "n.", "2.2", "kg"]),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", ABBREVIATION_TESTS)
|
|
def test_fi_tokenizer_handles_testcases(fi_tokenizer, text, expected_tokens):
|
|
tokens = fi_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|