spaCy/spacy/tests/lang/sr/test_еxceptions.py

15 lines
531 B
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize(
"text,norms,lemmas",
[("о.г.", ["ове године"], ["ова година"]), ("чет.", ["четвртак"], ["четвртак"]),
("гђа", ["госпођа"], ["госпођа"]), ("ил'", ["или"], ["или"])])
def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
tokens = sr_tokenizer(text)
assert len(tokens) == 1
assert [token.norm_ for token in tokens] == norms