spaCy/spacy/tests/lang/ja/test_tokenizer.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

54 lines
3.1 KiB
Python

import pytest
# fmt: off
TOKENIZER_TESTS = [
("日本語だよ", ['日本', '', '', '']),
("東京タワーの近くに住んでいます。", ['東京', 'タワー', '', '近く', '', '住ん', '', '', 'ます', '']),
("吾輩は猫である。", ['吾輩', '', '', '', 'ある', '']),
("月に代わって、お仕置きよ!", ['', '', '代わっ', '', '', '', '仕置き', '', '!']),
("すもももももももものうち", ['すもも', '', 'もも', '', 'もも', '', 'うち'])
]
TAG_TESTS = [
("日本語だよ", ['名詞,固有名詞,地名,国', '名詞,普通名詞,一般,*', '助動詞,*,*,*', '助詞,終助詞,*,*']),
("東京タワーの近くに住んでいます。", ['名詞,固有名詞,地名,一般', '名詞,普通名詞,一般,*', '助詞,格助詞,*,*', '名詞,普通名詞,副詞可能,*', '助詞,格助詞,*,*', '動詞,一般,*,*', '助詞,接続助詞,*,*', '動詞,非自立可能,*,*', '助動詞,*,*,*', '補助記号,句点,*,*']),
("吾輩は猫である。", ['代名詞,*,*,*', '助詞,係助詞,*,*', '名詞,普通名詞,一般,*', '助動詞,*,*,*', '動詞,非自立可能,*,*', '補助記号,句点,*,*']),
("月に代わって、お仕置きよ!", ['名詞,普通名詞,助数詞可能,*', '助詞,格助詞,*,*', '動詞,一般,*,*', '助詞,接続助詞,*,*', '補助記号,読点,*,*', '接頭辞,*,*,*', '名詞,普通名詞,一般,*', '助詞,終助詞,*,*', '補助記号,句点,*,*']),
("すもももももももものうち", ['名詞,普通名詞,一般,*', '助詞,係助詞,*,*', '名詞,普通名詞,一般,*', '助詞,係助詞,*,*', '名詞,普通名詞,一般,*', '助詞,格助詞,*,*', '名詞,普通名詞,副詞可能,*'])
]
POS_TESTS = [
('日本語だよ', ['PROPN', 'NOUN', 'AUX', 'PART']),
('東京タワーの近くに住んでいます。', ['PROPN', 'NOUN', 'ADP', 'NOUN', 'ADP', 'VERB', 'SCONJ', 'VERB', 'AUX', 'PUNCT']),
('吾輩は猫である。', ['PRON', 'ADP', 'NOUN', 'AUX', 'VERB', 'PUNCT']),
('月に代わって、お仕置きよ!', ['NOUN', 'ADP', 'VERB', 'SCONJ', 'PUNCT', 'NOUN', 'NOUN', 'PART', 'PUNCT']),
('すもももももももものうち', ['NOUN', 'ADP', 'NOUN', 'ADP', 'NOUN', 'ADP', 'NOUN'])
]
# fmt: on
@pytest.mark.parametrize("text,expected_tokens", TOKENIZER_TESTS)
def test_ja_tokenizer(ja_tokenizer, text, expected_tokens):
tokens = [token.text for token in ja_tokenizer(text)]
assert tokens == expected_tokens
@pytest.mark.parametrize("text,expected_tags", TAG_TESTS)
def test_ja_tokenizer_tags(ja_tokenizer, text, expected_tags):
tags = [token.tag_ for token in ja_tokenizer(text)]
assert tags == expected_tags
@pytest.mark.parametrize("text,expected_pos", POS_TESTS)
def test_ja_tokenizer_pos(ja_tokenizer, text, expected_pos):
pos = [token.pos_ for token in ja_tokenizer(text)]
assert pos == expected_pos
def test_extra_spaces(ja_tokenizer):
# note: three spaces after "I"
tokens = ja_tokenizer("I like cheese.")
assert tokens[1].orth_ == " "
assert tokens[2].orth_ == " "