mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +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]
12 lines
360 B
Python
12 lines
360 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,expected_tokens", [("c'è", ["c'", "è"]), ("l'ha", ["l'", "ha"])]
|
|
)
|
|
def test_contractions(it_tokenizer, text, expected_tokens):
|
|
""" Test that the contractions are split into two tokens"""
|
|
tokens = it_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|