mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
21 lines
630 B
Python
21 lines
630 B
Python
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
|