mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-12 04:38:28 +03:00
e5055e3cf6
* add danish lemmatizer * fill contributor agreement
14 lines
527 B
Python
14 lines
527 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_lemmatizer_lookup_assigns(da_tokenizer, string, lemma):
|
|
tokens = da_tokenizer(string)
|
|
assert tokens[0].lemma_ == lemma
|