mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +03:00
56eabcb2f2
* Create lex_attrs.py Hello, I am missing a CZECH language in SpaCy. So I would like to help to push it a little. This file is base on others lex_attrs.py files just with translation to Czech. * Update __init__.py Updated for use with new Czech Lex_attrs file * Update stop_words.py * Create test_text.py * add like_num testing for czech Co-authored-by: holubvl3 <47881982+holubvl3@users.noreply.github.com> Co-authored-by: holubvl3 <vilemrousi@gmail.com> Co-authored-by: Vladimír Holubec <vholubec@arcdata.cz>
27 lines
567 B
Python
27 lines
567 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10.000", True),
|
|
("1000", True),
|
|
("999,0", True),
|
|
("devatenáct", True),
|
|
("osmdesát", True),
|
|
("kvadrilion", True),
|
|
("Pes", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(cs_tokenizer, text, match):
|
|
tokens = cs_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|