mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 11:59:14 +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
20 lines
741 B
Python
20 lines
741 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
# fmt: off
|
|
GA_TOKEN_EXCEPTION_TESTS = [
|
|
("Niall Ó Domhnaill, Rialtas na hÉireann 1977 (lch. 600).", ["Niall", "Ó", "Domhnaill", ",", "Rialtas", "na", "hÉireann", "1977", "(", "lch.", "600", ")", "."]),
|
|
("Daoine a bhfuil Gaeilge acu, m.sh. tusa agus mise", ["Daoine", "a", "bhfuil", "Gaeilge", "acu", ",", "m.sh.", "tusa", "agus", "mise"])
|
|
]
|
|
# fmt: on
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", GA_TOKEN_EXCEPTION_TESTS)
|
|
def test_ga_tokenizer_handles_exception_cases(ga_tokenizer, text, expected_tokens):
|
|
tokens = ga_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|