mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +03:00
30d31fd335
* pymorph2 issues #11620, #11626, #11625: - #11620: pymorphy2_lookup - #11626: handle multiple forms pointing to the same normal form + handling empty POS tag - #11625: matching DET that are labelled as PRON by pymorhp2 * Move lemmatizer algorithm changes back into RussianLemmatizer * Fix uk pymorphy3_lookup mode init * Move and update tests for ru/uk lookup lemmatizer modes * Fix typo * Remove traces of previous behavior for uninflected POS * Refactor to private generic-looking pymorphy methods * Remove xfailed uk lemmatizer cases * Update spacy/lang/ru/lemmatizer.py Co-authored-by: Richard Hudson <richard@explosion.ai> Co-authored-by: Dmytro S Lituiev <d.lituiev@gmail.com> Co-authored-by: Richard Hudson <richard@explosion.ai>
28 lines
837 B
Python
28 lines
837 B
Python
import pytest
|
|
from spacy.tokens import Doc
|
|
|
|
|
|
pytestmark = pytest.mark.filterwarnings("ignore::DeprecationWarning")
|
|
|
|
|
|
def test_uk_lemmatizer(uk_lemmatizer):
|
|
"""Check that the default uk lemmatizer runs."""
|
|
doc = Doc(uk_lemmatizer.vocab, words=["a", "b", "c"])
|
|
assert uk_lemmatizer.mode == "pymorphy3"
|
|
uk_lemmatizer(doc)
|
|
assert [token.lemma for token in doc]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"word,lemma",
|
|
(
|
|
("якийсь", "якийсь"),
|
|
("розповідають", "розповідати"),
|
|
("розповіси", "розповісти"),
|
|
),
|
|
)
|
|
def test_uk_lookup_lemmatizer(uk_lookup_lemmatizer, word, lemma):
|
|
assert uk_lookup_lemmatizer.mode == "pymorphy3_lookup"
|
|
doc = Doc(uk_lookup_lemmatizer.vocab, words=[word])
|
|
assert uk_lookup_lemmatizer(doc)[0].lemma_ == lemma
|