mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +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.
39 lines
1.1 KiB
Python
39 lines
1.1 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.attrs import LEMMA, ORTH, PROB, IS_ALPHA
|
|
from spacy.parts_of_speech import NOUN, VERB
|
|
|
|
|
|
@pytest.mark.parametrize('text1,text2', [
|
|
("Hello", "bye"), ("Hello", "hello"), ("Hello", "Hello,")])
|
|
def test_vocab_api_neq(en_vocab, text1, text2):
|
|
assert en_vocab[text1].orth != en_vocab[text2].orth
|
|
|
|
|
|
@pytest.mark.parametrize('text', "Hello")
|
|
def test_vocab_api_eq(en_vocab, text):
|
|
lex = en_vocab[text]
|
|
assert en_vocab[text].orth == lex.orth
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["example"])
|
|
def test_vocab_api_shape_attr(en_vocab, text):
|
|
lex = en_vocab[text]
|
|
assert lex.orth != lex.shape
|
|
|
|
|
|
@pytest.mark.parametrize('string,symbol', [
|
|
('IS_ALPHA', IS_ALPHA), ('NOUN', NOUN), ('VERB', VERB), ('LEMMA', LEMMA),
|
|
('ORTH', ORTH), ('PROB', PROB)])
|
|
def test_vocab_api_symbols(en_vocab, string, symbol):
|
|
assert en_vocab.strings[string] == symbol
|
|
|
|
|
|
@pytest.mark.parametrize('text', "Hello")
|
|
def test_vocab_api_contains(en_vocab, text):
|
|
_ = en_vocab[text]
|
|
assert text in en_vocab
|
|
assert "LKsdjvlsakdvlaksdvlkasjdvljasdlkfvm" not in en_vocab
|