mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 07:57:35 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
24 lines
522 B
Python
24 lines
522 B
Python
"""Words like numbers are recognized correctly."""
|
|
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
|