spaCy/spacy/tests/lang/fi/test_tokenizer.py

57 lines
1.7 KiB
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
from __future__ import unicode_literals
import pytest
ABBREVIATION_TESTS = [
(
"Hyvää uutta vuotta t. siht. Niemelä!",
["Hyvää", "uutta", "vuotta", "t.", "siht.", "Niemelä", "!"],
),
("Paino on n. 2.2 kg", ["Paino", "on", "n.", "2.2", "kg"]),
]
HYPHENATED_TESTS = [
(
"1700-luvulle sijoittuva taide-elokuva",
2019-12-21 18:04:17 +00:00
["1700-luvulle", "sijoittuva", "taide-elokuva"],
)
]
ABBREVIATION_INFLECTION_TESTS = [
(
"VTT:ssa ennen v:ta 2010 suoritetut mittaukset",
["VTT:ssa", "ennen", "v:ta", "2010", "suoritetut", "mittaukset"]
),
(
"ALV:n osuus on 24 %.",
["ALV:n", "osuus", "on", "24", "%", "."]
),
(
"Hiihtäjä oli kilpailun 14:s.",
["Hiihtäjä", "oli", "kilpailun", "14:s", "."]
)
]
@pytest.mark.parametrize("text,expected_tokens", ABBREVIATION_TESTS)
def test_fi_tokenizer_abbreviations(fi_tokenizer, text, expected_tokens):
tokens = fi_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list
@pytest.mark.parametrize("text,expected_tokens", HYPHENATED_TESTS)
def test_fi_tokenizer_hyphenated_words(fi_tokenizer, text, expected_tokens):
tokens = fi_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list
@pytest.mark.parametrize("text,expected_tokens", ABBREVIATION_INFLECTION_TESTS)
def test_fi_tokenizer_abbreviation_inflections(fi_tokenizer, text, expected_tokens):
tokens = fi_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list