2019-02-07 20:05:11 +00:00
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
2019-02-08 13:14:49 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
|
"text,norms,lemmas",
|
|
|
|
|
[("ім.", ["імені"], ["ім'я"]), ("проф.", ["професор"], ["професор"])],
|
|
|
|
|
)
|
2019-02-07 20:05:11 +00:00
|
|
|
def test_uk_tokenizer_abbrev_exceptions(uk_tokenizer, text, norms, lemmas):
|
|
|
|
|
tokens = uk_tokenizer(text)
|
|
|
|
|
assert len(tokens) == 1
|
|
|
|
|
assert [token.norm_ for token in tokens] == norms
|
