mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 00:17:44 +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.
50 lines
1.7 KiB
Python
50 lines
1.7 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.en.lex_attrs import like_num
|
|
|
|
|
|
def test_en_tokenizer_handles_long_text(en_tokenizer):
|
|
text = """Tributes pour in for late British Labour Party leader
|
|
|
|
Tributes poured in from around the world Thursday
|
|
to the late Labour Party leader John Smith, who died earlier from a massive
|
|
heart attack aged 55.
|
|
|
|
In Washington, the US State Department issued a statement regretting "the
|
|
untimely death" of the rapier-tongued Scottish barrister and parliamentarian.
|
|
|
|
"Mr. Smith, throughout his distinguished"""
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == 76
|
|
|
|
|
|
@pytest.mark.parametrize('text,length', [
|
|
("The U.S. Army likes Shock and Awe.", 8),
|
|
("U.N. regulations are not a part of their concern.", 10),
|
|
("“Isn't it?”", 6),
|
|
("""Yes! "I'd rather have a walk", Ms. Comble sighed. """, 15),
|
|
("""'Me too!', Mr. P. Delaware cried. """, 11),
|
|
("They ran about 10km.", 6),
|
|
pytest.mark.xfail(("But then the 6,000-year ice age came...", 10))])
|
|
def test_en_tokenizer_handles_cnts(en_tokenizer, text, length):
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize('text,match', [
|
|
('10', True), ('1', True), ('10,000', True), ('10,00', True),
|
|
('999.0', True), ('one', True), ('two', True), ('billion', True),
|
|
('dog', False), (',', False), ('1/2', True)])
|
|
def test_lex_attrs_like_number(en_tokenizer, text, match):
|
|
tokens = en_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|
|
|
|
|
|
@pytest.mark.parametrize('word', ['eleven'])
|
|
def test_en_lex_attrs_capitals(word):
|
|
assert like_num(word)
|
|
assert like_num(word.upper())
|