mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +03:00
b6e991440c
* 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
26 lines
790 B
Python
26 lines
790 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
TEST_CASES = [
|
|
(
|
|
"Adresa este str. Principală nr. 5.",
|
|
["Adresa", "este", "str.", "Principală", "nr.", "5", "."],
|
|
),
|
|
("Teste, etc.", ["Teste", ",", "etc."]),
|
|
("Lista, ș.a.m.d.", ["Lista", ",", "ș.a.m.d."]),
|
|
("Și d.p.d.v. al...", ["Și", "d.p.d.v.", "al", "..."]),
|
|
# number tests
|
|
("Clasa a 4-a.", ["Clasa", "a", "4-a", "."]),
|
|
("Al 12-lea ceas.", ["Al", "12-lea", "ceas", "."]),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", TEST_CASES)
|
|
def test_ro_tokenizer_handles_testcases(ro_tokenizer, text, expected_tokens):
|
|
tokens = ro_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|