mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-29 23:17:59 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
24 lines
686 B
Python
24 lines
686 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
NB_TOKEN_EXCEPTION_TESTS = [
|
|
(
|
|
"Smørsausen brukes bl.a. til fisk",
|
|
["Smørsausen", "brukes", "bl.a.", "til", "fisk"],
|
|
),
|
|
(
|
|
"Jeg kommer først kl. 13 pga. diverse forsinkelser",
|
|
["Jeg", "kommer", "først", "kl.", "13", "pga.", "diverse", "forsinkelser"],
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", NB_TOKEN_EXCEPTION_TESTS)
|
|
def test_nb_tokenizer_handles_exception_cases(nb_tokenizer, text, expected_tokens):
|
|
tokens = nb_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|