mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
29 lines
581 B
Python
29 lines
581 B
Python
# coding: utf-8
|
|
"""Words like numbers are recognized correctly."""
|
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10,000", True),
|
|
("10,00", True),
|
|
("jeden", True),
|
|
("dwa", True),
|
|
("milion", True),
|
|
("pies", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(pl_tokenizer, text, match):
|
|
tokens = pl_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|