spaCy/spacy/tests/lang/sv/test_tokenizer.py
Ines Montani b6e991440c 💫 Tidy up and auto-format tests (#2967)
* Auto-format tests with black

* Add flake8 config

* Tidy up and remove unused imports

* Fix redefinitions of test functions

* Replace orths_and_spaces with words and spaces

* Fix compatibility with pytest 4.0

* xfail test for now

Test was previously overwritten by following test due to naming conflict, so failure wasn't reported

* Unfail passing test

* Only use fixture via arguments

Fixes pytest 4.0 compatibility
2018-11-27 01:09:36 +01:00

35 lines
1.0 KiB
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
SV_TOKEN_EXCEPTION_TESTS = [
(
"Smörsåsen används bl.a. till fisk",
["Smörsåsen", "används", "bl.a.", "till", "fisk"],
),
(
"Jag kommer först kl. 13 p.g.a. diverse förseningar",
["Jag", "kommer", "först", "kl.", "13", "p.g.a.", "diverse", "förseningar"],
),
(
"Anders I. tycker om ord med i i.",
["Anders", "I.", "tycker", "om", "ord", "med", "i", "i", "."],
),
]
@pytest.mark.parametrize("text,expected_tokens", SV_TOKEN_EXCEPTION_TESTS)
def test_sv_tokenizer_handles_exception_cases(sv_tokenizer, text, expected_tokens):
tokens = sv_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list
@pytest.mark.parametrize("text", ["driveru", "hajaru", "Serru", "Fixaru"])
def test_sv_tokenizer_handles_verb_exceptions(sv_tokenizer, text):
tokens = sv_tokenizer(text)
assert len(tokens) == 2
assert tokens[1].text == "u"