mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
d03401f532
* Serbian stopwords added. (cyrillic alphabet) * spaCy Contribution agreement included. * Test initialize updated * Serbian language code update. --bugfix * Tokenizer exceptions added. Init file updated. * Norm exceptions and lexical attributes added. * Examples added. * Tests added. * sr_lang examples update. * Tokenizer exceptions updated. (Serbian) * Lemmatizer created. Licence included. * Test updated. * Tag map basic added. * tag_map.py file removed since it uses default spacy tags.
21 lines
553 B
Python
21 lines
553 B
Python
# coding: utf-8
|
||
from __future__ import unicode_literals
|
||
|
||
import pytest
|
||
|
||
|
||
@pytest.mark.parametrize(
|
||
"string,lemma",
|
||
[
|
||
("најадекватнији", "адекватан"),
|
||
("матурирао", "матурирати"),
|
||
("планираћемо", "планирати"),
|
||
("певају", "певати"),
|
||
("нама", "ми"),
|
||
("се", "себе"),
|
||
],
|
||
)
|
||
def test_sr_lemmatizer_lookup_assigns(sr_tokenizer, string, lemma):
|
||
tokens = sr_tokenizer(string)
|
||
assert tokens[0].lemma_ == lemma
|