explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update Japanese tests (#5807)

Browse Source 
* Update POS tests to reflect current behavior (it is not entirely clear
whether the AUX/VERB mapping is indeed the desired behavior?)
* Switch to `from_config` initialization in subtoken test
This commit is contained in:
Adriane Boyd 2020-07-24 12:45:14 +02:00 committed by GitHub
parent fdb8815ef5
commit 656574a01a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tests/lang/ja/test_tokenizer.py
View File

@ -21,9 +21,9 @@ TAG_TESTS = [
] ]
POS_TESTS = [ POS_TESTS = [
('日本語だよ', ['fish', 'NOUN', 'AUX', 'PART']), ('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']), ('東京タワーの近くに住んでいます。', ['PROPN', 'NOUN', 'ADP', 'NOUN', 'ADP', 'VERB', 'SCONJ', 'AUX', 'AUX', 'PUNCT']),
('吾輩は猫である。', ['PRON', 'ADP', 'NOUN', 'AUX', 'VERB', 'PUNCT']), ('吾輩は猫である。', ['PRON', 'ADP', 'NOUN', 'AUX', 'AUX', 'PUNCT']),
('月に代わって、お仕置きよ!', ['NOUN', 'ADP', 'VERB', 'SCONJ', 'PUNCT', 'NOUN', 'NOUN', 'PART', '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']) ('すもももももももものうち', ['NOUN', 'ADP', 'NOUN', 'ADP', 'NOUN', 'ADP', 'NOUN'])
] ]
@ -47,7 +47,6 @@ def test_ja_tokenizer_tags(ja_tokenizer, text, expected_tags):
assert tags == expected_tags assert tags == expected_tags
# XXX This isn't working? Always passes
@pytest.mark.parametrize("text,expected_pos", POS_TESTS) @pytest.mark.parametrize("text,expected_pos", POS_TESTS)
def test_ja_tokenizer_pos(ja_tokenizer, text, expected_pos): def test_ja_tokenizer_pos(ja_tokenizer, text, expected_pos):
pos = [token.pos_ for token in ja_tokenizer(text)] pos = [token.pos_ for token in ja_tokenizer(text)]
@ -120,9 +119,9 @@ def test_ja_tokenizer_split_modes(ja_tokenizer, text, len_a, len_b, len_c):
] ]
) )
def test_ja_tokenizer_sub_tokens(ja_tokenizer, text, sub_tokens_list_a, sub_tokens_list_b, sub_tokens_list_c): def test_ja_tokenizer_sub_tokens(ja_tokenizer, text, sub_tokens_list_a, sub_tokens_list_b, sub_tokens_list_c):
nlp_a = Japanese(meta={"tokenizer": {"config": {"split_mode": "A"}}}) nlp_a = Japanese.from_config({"nlp": {"tokenizer": {"split_mode": "A"}}})
nlp_b = Japanese(meta={"tokenizer": {"config": {"split_mode": "B"}}}) nlp_b = Japanese.from_config({"nlp": {"tokenizer": {"split_mode": "B"}}})
nlp_c = Japanese(meta={"tokenizer": {"config": {"split_mode": "C"}}}) nlp_c = Japanese.from_config({"nlp": {"tokenizer": {"split_mode": "C"}}})
assert ja_tokenizer(text).user_data["sub_tokens"] == sub_tokens_list_a assert ja_tokenizer(text).user_data["sub_tokens"] == sub_tokens_list_a
assert nlp_a(text).user_data["sub_tokens"] == sub_tokens_list_a assert nlp_a(text).user_data["sub_tokens"] == sub_tokens_list_a