spaCy/spacy/tests/lang/da/test_lemma.py
2019-09-29 17:32:12 +02:00

19 lines
454 B
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize(
"string,lemma",
[
("affaldsgruppernes", "affaldsgruppe"),
("detailhandelsstrukturernes", "detailhandelsstruktur"),
("kolesterols", "kolesterol"),
("åsyns", "åsyn"),
],
)
def test_da_lemmatizer_lookup_assigns(da_tokenizer, string, lemma):
tokens = da_tokenizer(string)
assert tokens[0].lemma_ == lemma