mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
21 lines
477 B
Python
21 lines
477 B
Python
|
# coding: utf-8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize(
|
||
|
|
"string,lemma",
|
||
|
|
[
|
||
|
|
("trčao", "trčati"),
|
||
|
|
("adekvatnim", "adekvatan"),
|
||
|
|
("dekontaminacijama", "dekontaminacija"),
|
||
|
|
("filologovih", "filologov"),
|
||
|
|
("je", "biti"),
|
||
|
|
("se", "sebe"),
|
||
|
|
],
|
||
|
|
)
|
||
|
|
def test_hr_lemmatizer_lookup_assigns(hr_tokenizer, string, lemma):
|
||
|
|
tokens = hr_tokenizer(string)
|
||
|
|
assert tokens[0].lemma_ == lemma
|