spaCy/spacy/tests/lang/test_attrs.py
Ines Montani 75f3234404
💫 Refactor test suite (#2568)
## 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.
2018-07-24 23:38:44 +02:00

59 lines
2.1 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.attrs import intify_attrs, ORTH, NORM, LEMMA, IS_ALPHA
from spacy.lang.lex_attrs import is_punct, is_ascii, is_currency, like_url, word_shape
@pytest.mark.parametrize('text', ["dog"])
def test_attrs_key(text):
assert intify_attrs({"ORTH": text}) == {ORTH: text}
assert intify_attrs({"NORM": text}) == {NORM: text}
assert intify_attrs({"lemma": text}, strings_map={text: 10}) == {LEMMA: 10}
@pytest.mark.parametrize('text', ["dog"])
def test_attrs_idempotence(text):
int_attrs = intify_attrs({"lemma": text, 'is_alpha': True}, strings_map={text: 10})
assert intify_attrs(int_attrs) == {LEMMA: 10, IS_ALPHA: True}
@pytest.mark.parametrize('text', ["dog"])
def test_attrs_do_deprecated(text):
int_attrs = intify_attrs({"F": text, 'is_alpha': True}, strings_map={text: 10},
_do_deprecated=True)
assert int_attrs == {ORTH: 10, IS_ALPHA: True}
@pytest.mark.parametrize('text,match', [(',', True), (' ', False), ('a', False)])
def test_lex_attrs_is_punct(text, match):
assert is_punct(text) == match
@pytest.mark.parametrize('text,match', [(',', True), ('£', False), ('', False)])
def test_lex_attrs_is_ascii(text, match):
assert is_ascii(text) == match
@pytest.mark.parametrize('text,match', [('$', True), ('£', True), ('', False),
('', True), ('¥', True), ('¢', True),
('a', False), ('www.google.com', False), ('dog', False)])
def test_lex_attrs_is_currency(text, match):
assert is_currency(text) == match
@pytest.mark.parametrize('text,match', [
('www.google.com', True), ('google.com', True), ('sydney.com', True),
('2girls1cup.org', True), ('http://stupid', True), ('www.hi', True),
('dog', False), ('1.2', False), ('1.a', False), ('hello.There', False)])
def test_lex_attrs_like_url(text, match):
assert like_url(text) == match
@pytest.mark.parametrize('text,shape', [
('Nasa', 'Xxxx'), ('capitalized', 'xxxx'), ('999999999', 'dddd'),
('C3P0', 'XdXd'), (',', ','), ('\n', '\n'), ('``,-', '``,-')])
def test_lex_attrs_word_shape(text, shape):
assert word_shape(text) == shape