mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-16 14:47:16 +03:00
8602daba85
* Sign contributor agreement. * Add like_num functionality to Swedish. * Update spacy/tests/lang/sv/test_lex_attrs.py Co-Authored-By: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update contributor agreement Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
34 lines
740 B
Python
34 lines
740 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.sv.lex_attrs import like_num
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10.000", True),
|
|
("10.00", True),
|
|
("999,0", True),
|
|
("en", True),
|
|
("två", True),
|
|
("miljard", True),
|
|
("hund", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(sv_tokenizer, text, match):
|
|
tokens = sv_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|
|
|
|
|
|
@pytest.mark.parametrize("word", ["elva"])
|
|
def test_sv_lex_attrs_capitals(word):
|
|
assert like_num(word)
|
|
assert like_num(word.upper())
|