2017-10-11 11:27:26 +00:00
|
|
|
# coding: utf-8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"string,lemma",
|
|
|
|
[
|
|
|
|
("Abgehängten", "Abgehängte"),
|
|
|
|
("engagierte", "engagieren"),
|
|
|
|
("schließt", "schließen"),
|
|
|
|
("vorgebenden", "vorgebend"),
|
|
|
|
("die", "der"),
|
|
|
|
("Die", "der"),
|
|
|
|
],
|
|
|
|
)
|
2018-07-24 21:38:44 +00:00
|
|
|
def test_de_lemmatizer_lookup_assigns(de_tokenizer, string, lemma):
|
2017-10-11 11:27:26 +00:00
|
|
|
tokens = de_tokenizer(string)
|
|
|
|
assert tokens[0].lemma_ == lemma
|