mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +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
811 B
Python
24 lines
811 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.language import Language
|
|
from spacy.lang.punctuation import TOKENIZER_INFIXES
|
|
from spacy.lang.char_classes import ALPHA
|
|
|
|
|
|
@pytest.mark.parametrize('text,expected_tokens', [
|
|
("l'avion", ["l'", "avion"]), ("j'ai", ["j'", "ai"])])
|
|
def test_issue768(text, expected_tokens):
|
|
"""Allow zero-width 'infix' token during the tokenization process."""
|
|
SPLIT_INFIX = r'(?<=[{a}]\')(?=[{a}])'.format(a=ALPHA)
|
|
|
|
class FrenchTest(Language):
|
|
class Defaults(Language.Defaults):
|
|
infixes = TOKENIZER_INFIXES + [SPLIT_INFIX]
|
|
|
|
fr_tokenizer_w_infix = FrenchTest.Defaults.create_tokenizer()
|
|
tokens = fr_tokenizer_w_infix(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|