2017-03-24 15:27:44 +00:00
|
|
|
# encoding: utf8
|
|
|
|
from __future__ import unicode_literals
|
2020-08-24 12:30:05 +00:00
|
|
|
from spacy.lang.he.lex_attrs import like_num
|
2017-03-24 15:27:44 +00:00
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"text,expected_tokens",
|
|
|
|
[("פייתון היא שפת תכנות דינמית", ["פייתון", "היא", "שפת", "תכנות", "דינמית"])],
|
|
|
|
)
|
2018-07-24 21:38:44 +00:00
|
|
|
def test_he_tokenizer_handles_abbreviation(he_tokenizer, text, expected_tokens):
|
2017-04-19 17:28:00 +00:00
|
|
|
tokens = he_tokenizer(text)
|
|
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
|
|
assert expected_tokens == token_list
|
2017-03-24 15:27:44 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"text,expected_tokens",
|
|
|
|
[
|
|
|
|
(
|
|
|
|
"עקבת אחריו בכל רחבי המדינה.",
|
|
|
|
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "."],
|
|
|
|
),
|
|
|
|
(
|
|
|
|
"עקבת אחריו בכל רחבי המדינה?",
|
|
|
|
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "?"],
|
|
|
|
),
|
|
|
|
(
|
|
|
|
"עקבת אחריו בכל רחבי המדינה!",
|
|
|
|
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "!"],
|
|
|
|
),
|
|
|
|
(
|
|
|
|
"עקבת אחריו בכל רחבי המדינה..",
|
|
|
|
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", ".."],
|
|
|
|
),
|
|
|
|
(
|
|
|
|
"עקבת אחריו בכל רחבי המדינה...",
|
|
|
|
["עקבת", "אחריו", "בכל", "רחבי", "המדינה", "..."],
|
|
|
|
),
|
|
|
|
],
|
|
|
|
)
|
2018-07-24 21:38:44 +00:00
|
|
|
def test_he_tokenizer_handles_punct(he_tokenizer, text, expected_tokens):
|
2017-03-24 15:27:44 +00:00
|
|
|
tokens = he_tokenizer(text)
|
2017-04-19 17:28:00 +00:00
|
|
|
assert expected_tokens == [token.text for token in tokens]
|
2020-08-24 12:30:05 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"text,match",
|
|
|
|
[
|
|
|
|
("10", True),
|
|
|
|
("1", True),
|
|
|
|
("10,000", True),
|
|
|
|
("10,00", True),
|
|
|
|
("999.0", True),
|
|
|
|
("אחד", True),
|
|
|
|
("שתיים", True),
|
|
|
|
("מליון", True),
|
|
|
|
("כלב", False),
|
|
|
|
(",", False),
|
|
|
|
("1/2", True),
|
|
|
|
],
|
|
|
|
)
|
|
|
|
def test_lex_attrs_like_number(he_tokenizer, text, match):
|
|
|
|
tokens = he_tokenizer(text)
|
|
|
|
assert len(tokens) == 1
|
|
|
|
assert tokens[0].like_num == match
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"word",
|
|
|
|
[
|
|
|
|
"שלישי",
|
|
|
|
"מליון",
|
|
|
|
"עשירי",
|
|
|
|
"מאה",
|
|
|
|
"עשר",
|
|
|
|
"אחד עשר",
|
|
|
|
]
|
|
|
|
)
|
|
|
|
def test_he_lex_attrs_like_number_for_ordinal(word):
|
|
|
|
assert like_num(word)
|