spaCy/spacy/tests/lang/zh/test_text.py
2020-05-21 18:39:06 +02:00

22 lines
454 B
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pytest
@pytest.mark.parametrize(
"text,match",
[
("10", True),
("1", True),
("999.0", True),
("", True),
("", True),
("", True),
("十一", True),
("", False),
(",", False),
],
)
def test_lex_attrs_like_number(zh_tokenizer_jieba, text, match):
tokens = zh_tokenizer_jieba(text)
assert len(tokens) == 1
assert tokens[0].like_num == match