spaCy/spacy/tests/lang/ja/test_tokenizer.py
Ines Montani 75f3234404
💫 Refactor test suite (#2568)
## Description

Related issues: #2379 (should be fixed by separating model tests)

* **total execution time down from > 300 seconds to under 60 seconds** 🎉
* removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure
* changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version)
* merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways)
* tidied up and rewrote existing tests wherever possible

### Todo

- [ ] move tests to `/tests` and adjust CI commands accordingly
- [x] move model test suite from internal repo to `spacy-models`
- [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~
- [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted
- [ ] update documentation on how to run tests


### Types of change
enhancement, tests

## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-24 23:38:44 +02:00

48 lines
2.8 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
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", ['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'])
]
@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(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(ja_tokenizer, text, expected_pos):
pos = [token.pos_ for token in ja_tokenizer(text)]
assert pos == expected_pos