mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +03:00
75f3234404
## 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.
126 lines
4.3 KiB
Python
126 lines
4.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
PUNCT_OPEN = ['(', '[', '{', '*']
|
|
PUNCT_CLOSE = [')', ']', '}', '*']
|
|
PUNCT_PAIRED = [('(', ')'), ('[', ']'), ('{', '}'), ('*', '*')]
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["(", "((", "<"])
|
|
def test_ru_tokenizer_handles_only_punct(ru_tokenizer, text):
|
|
tokens = ru_tokenizer(text)
|
|
assert len(tokens) == len(text)
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_OPEN)
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_open_punct(ru_tokenizer, punct, text):
|
|
tokens = ru_tokenizer(punct + text)
|
|
assert len(tokens) == 2
|
|
assert tokens[0].text == punct
|
|
assert tokens[1].text == text
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_CLOSE)
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_close_punct(ru_tokenizer, punct, text):
|
|
tokens = ru_tokenizer(text + punct)
|
|
assert len(tokens) == 2
|
|
assert tokens[0].text == text
|
|
assert tokens[1].text == punct
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_OPEN)
|
|
@pytest.mark.parametrize('punct_add', ["`"])
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_two_diff_open_punct(ru_tokenizer, punct, punct_add, text):
|
|
tokens = ru_tokenizer(punct + punct_add + text)
|
|
assert len(tokens) == 3
|
|
assert tokens[0].text == punct
|
|
assert tokens[1].text == punct_add
|
|
assert tokens[2].text == text
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_CLOSE)
|
|
@pytest.mark.parametrize('punct_add', ["'"])
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_two_diff_close_punct(ru_tokenizer, punct, punct_add, text):
|
|
tokens = ru_tokenizer(text + punct + punct_add)
|
|
assert len(tokens) == 3
|
|
assert tokens[0].text == text
|
|
assert tokens[1].text == punct
|
|
assert tokens[2].text == punct_add
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_OPEN)
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_same_open_punct(ru_tokenizer, punct, text):
|
|
tokens = ru_tokenizer(punct + punct + punct + text)
|
|
assert len(tokens) == 4
|
|
assert tokens[0].text == punct
|
|
assert tokens[3].text == text
|
|
|
|
|
|
@pytest.mark.parametrize('punct', PUNCT_CLOSE)
|
|
@pytest.mark.parametrize('text', ["Привет"])
|
|
def test_ru_tokenizer_splits_same_close_punct(ru_tokenizer, punct, text):
|
|
tokens = ru_tokenizer(text + punct + punct + punct)
|
|
assert len(tokens) == 4
|
|
assert tokens[0].text == text
|
|
assert tokens[1].text == punct
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["'Тест"])
|
|
def test_ru_tokenizer_splits_open_appostrophe(ru_tokenizer, text):
|
|
tokens = ru_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
assert tokens[0].text == "'"
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["Тест''"])
|
|
def test_ru_tokenizer_splits_double_end_quote(ru_tokenizer, text):
|
|
tokens = ru_tokenizer(text)
|
|
assert len(tokens) == 2
|
|
tokens_punct = ru_tokenizer("''")
|
|
assert len(tokens_punct) == 1
|
|
|
|
|
|
@pytest.mark.parametrize('punct_open,punct_close', PUNCT_PAIRED)
|
|
@pytest.mark.parametrize('text', ["Тест"])
|
|
def test_ru_tokenizer_splits_open_close_punct(ru_tokenizer, punct_open,
|
|
punct_close, text):
|
|
tokens = ru_tokenizer(punct_open + text + punct_close)
|
|
assert len(tokens) == 3
|
|
assert tokens[0].text == punct_open
|
|
assert tokens[1].text == text
|
|
assert tokens[2].text == punct_close
|
|
|
|
|
|
@pytest.mark.parametrize('punct_open,punct_close', PUNCT_PAIRED)
|
|
@pytest.mark.parametrize('punct_open2,punct_close2', [("`", "'")])
|
|
@pytest.mark.parametrize('text', ["Тест"])
|
|
def test_ru_tokenizer_two_diff_punct(ru_tokenizer, punct_open, punct_close,
|
|
punct_open2, punct_close2, text):
|
|
tokens = ru_tokenizer(punct_open2 + punct_open + text + punct_close + punct_close2)
|
|
assert len(tokens) == 5
|
|
assert tokens[0].text == punct_open2
|
|
assert tokens[1].text == punct_open
|
|
assert tokens[2].text == text
|
|
assert tokens[3].text == punct_close
|
|
assert tokens[4].text == punct_close2
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["Тест."])
|
|
def test_ru_tokenizer_splits_trailing_dot(ru_tokenizer, text):
|
|
tokens = ru_tokenizer(text)
|
|
assert tokens[1].text == "."
|
|
|
|
|
|
def test_ru_tokenizer_splits_bracket_period(ru_tokenizer):
|
|
text = "(Раз, два, три, проверка)."
|
|
tokens = ru_tokenizer(text)
|
|
assert tokens[len(tokens) - 1].text == "."
|