spaCy/spacy/tests/lang/th/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

13 lines
374 B
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
@pytest.mark.parametrize(
"text,expected_tokens", [("คุณรักผมไหม", ["คุณ", "รัก", "ผม", "ไหม"])]
)
def test_th_tokenizer(th_tokenizer, text, expected_tokens):
tokens = [token.text for token in th_tokenizer(text)]
assert tokens == expected_tokens