spaCy/spacy/tests/lang/sv/test_prefix_suffix_infix.py

38 lines
1.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
2019-02-08 16:14:49 +03:00
@pytest.mark.parametrize("text", ["(under)"])
def test_tokenizer_splits_no_special(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 3
2019-02-08 16:14:49 +03:00
@pytest.mark.parametrize("text", ["gitta'r", "Björn's", "Lars'"])
def test_tokenizer_handles_no_punct(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 1
2019-02-08 16:14:49 +03:00
@pytest.mark.parametrize("text", ["svart.Gul", "Hej.Världen"])
def test_tokenizer_splits_period_infix(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 3
2019-02-08 16:14:49 +03:00
@pytest.mark.parametrize("text", ["Hej,Världen", "en,två"])
def test_tokenizer_splits_comma_infix(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 3
assert tokens[0].text == text.split(",")[0]
assert tokens[1].text == ","
assert tokens[2].text == text.split(",")[1]
2019-02-08 16:14:49 +03:00
@pytest.mark.parametrize("text", ["svart...Gul", "svart...gul"])
def test_tokenizer_splits_ellipsis_infix(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 3