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.
35 lines
1.4 KiB
Python
35 lines
1.4 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
from ...util import get_doc, apply_transition_sequence
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["A test sentence"])
|
|
@pytest.mark.parametrize('punct', ['.', '!', '?', ''])
|
|
def test_en_sbd_single_punct(en_tokenizer, text, punct):
|
|
heads = [2, 1, 0, -1] if punct else [2, 1, 0]
|
|
tokens = en_tokenizer(text + punct)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads)
|
|
assert len(doc) == 4 if punct else 3
|
|
assert len(list(doc.sents)) == 1
|
|
assert sum(len(sent) for sent in doc.sents) == len(doc)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_en_sentence_breaks(en_tokenizer, en_parser):
|
|
text = "This is a sentence . This is another one ."
|
|
heads = [1, 0, 1, -2, -3, 1, 0, 1, -2, -3]
|
|
deps = ['nsubj', 'ROOT', 'det', 'attr', 'punct', 'nsubj', 'ROOT', 'det',
|
|
'attr', 'punct']
|
|
transition = ['L-nsubj', 'S', 'L-det', 'R-attr', 'D', 'R-punct', 'B-ROOT',
|
|
'L-nsubj', 'S', 'L-attr', 'R-attr', 'D', 'R-punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
apply_transition_sequence(en_parser, doc, transition)
|
|
assert len(list(doc.sents)) == 2
|
|
for token in doc:
|
|
assert token.dep != 0 or token.is_space
|
|
assert [token.head.i for token in doc ] == [1, 1, 3, 1, 1, 6, 6, 8, 6, 6]
|