Hooked up tokenizer tests

This commit is contained in:
luvogels 2017-04-26 23:21:41 +02:00
parent b331929a7e
commit d12a0b6431
1 changed files with 6 additions and 1 deletions

View File

@ -13,6 +13,8 @@ from ..hu import Hungarian
from ..fi import Finnish from ..fi import Finnish
from ..bn import Bengali from ..bn import Bengali
from ..he import Hebrew from ..he import Hebrew
from ..nb import Norwegian
from ..tokens import Doc from ..tokens import Doc
from ..strings import StringStore from ..strings import StringStore
@ -26,7 +28,7 @@ import pytest
LANGUAGES = [English, German, Spanish, Italian, French, Portuguese, Dutch, LANGUAGES = [English, German, Spanish, Italian, French, Portuguese, Dutch,
Swedish, Hungarian, Finnish, Bengali] Swedish, Hungarian, Finnish, Bengali, Norwegian]
@pytest.fixture(params=LANGUAGES) @pytest.fixture(params=LANGUAGES)
@ -88,6 +90,9 @@ def bn_tokenizer():
def he_tokenizer(): def he_tokenizer():
return Hebrew.Defaults.create_tokenizer() return Hebrew.Defaults.create_tokenizer()
@pytest.fixture
def nb_tokenizer():
return Norwegian.Defaults.create_tokenizer()
@pytest.fixture @pytest.fixture
def stringstore(): def stringstore():