mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
bcf2b9b4f5
Tagger is now parametrized and has two sentences with more tag coverage. The tokenizer tests are updated to reflect differences in tokenization between IPAdic and Unidic. -POLM
18 lines
865 B
Python
18 lines
865 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
TOKENIZER_TESTS = [
|
|
("日本語だよ", ['日本', '語', 'だ', 'よ']),
|
|
("東京タワーの近くに住んでいます。", ['東京', 'タワー', 'の', '近く', 'に', '住ん', 'で', 'い', 'ます', '。']),
|
|
("吾輩は猫である。", ['吾輩', 'は', '猫', 'で', 'ある', '。']),
|
|
("月に代わって、お仕置きよ!", ['月', 'に', '代わっ', 'て', '、', 'お', '仕置き', 'よ', '!']),
|
|
("すもももももももものうち", ['すもも', 'も', 'もも', 'も', 'もも', 'の', 'うち'])
|
|
]
|
|
|
|
@pytest.mark.parametrize('text,expected_tokens', TOKENIZER_TESTS)
|
|
def test_japanese_tokenizer(ja_tokenizer, text, expected_tokens):
|
|
tokens = [token.text for token in ja_tokenizer(text)]
|
|
assert tokens == expected_tokens
|