spaCy/spacy/tests/lang/ja/test_tokenizer.py
Paul O'Leary McCann bd72fbf09c Port Japanese mecab tokenizer from v1 (#2036)
* Port Japanese mecab tokenizer from v1

This brings the Mecab-based Japanese tokenization introduced in #1246 to
spaCy v2. There isn't a JapaneseTagger implementation yet, but POS tag
information from Mecab is stored in a token extension. A tag map is also
included.

As a reminder, Mecab is required because Universal Dependencies are
based on Unidic tags, and Janome doesn't support Unidic.

Things to check:

1. Is this the right way to use a token extension?

2. What's the right way to implement a JapaneseTagger? The approach in
 #1246 relied on `tag_from_strings` which is just gone now. I guess the
best thing is to just try training spaCy's default Tagger?

-POLM

* Add tagging/make_doc and tests
2018-05-03 18:38:26 +02:00

46 lines
2.9 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_japanese_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_japanese_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_japanese_tokenizer(ja_tokenizer, text, expected_pos):
pos = [token.pos_ for token in ja_tokenizer(text)]
assert pos == expected_pos