mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +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.
24 lines
1.3 KiB
Python
24 lines
1.3 KiB
Python
# encoding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize('text,expected_tokens',
|
|
[('פייתון היא שפת תכנות דינמית', ['פייתון', 'היא', 'שפת', 'תכנות', 'דינמית'])])
|
|
def test_he_tokenizer_handles_abbreviation(he_tokenizer, text, expected_tokens):
|
|
tokens = he_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|
|
|
|
|
|
@pytest.mark.parametrize('text,expected_tokens', [
|
|
('עקבת אחריו בכל רחבי המדינה.', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '.']),
|
|
('עקבת אחריו בכל רחבי המדינה?', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '?']),
|
|
('עקבת אחריו בכל רחבי המדינה!', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '!']),
|
|
('עקבת אחריו בכל רחבי המדינה..', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '..']),
|
|
('עקבת אחריו בכל רחבי המדינה...', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '...'])])
|
|
def test_he_tokenizer_handles_punct(he_tokenizer, text, expected_tokens):
|
|
tokens = he_tokenizer(text)
|
|
assert expected_tokens == [token.text for token in tokens]
|