mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
13 lines
366 B
Python
13 lines
366 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"word,lemma", [("새로운", "새롭"), ("빨간", "빨갛"), ("클수록", "크"), ("뭡니까", "뭣"), ("됐다", "되")]
|
|
)
|
|
def test_ko_lemmatizer_assigns(ko_tokenizer, word, lemma):
|
|
test_lemma = ko_tokenizer(word)[0].lemma_
|
|
assert test_lemma == lemma
|