mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-27 01:34:30 +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.
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.language import Language
|
|
from spacy.tokens import Span
|
|
|
|
from ..util import get_doc
|
|
|
|
|
|
@pytest.fixture
|
|
def doc(en_tokenizer):
|
|
text = 'I like New York in Autumn.'
|
|
heads = [1, 0, 1, -2, -3, -1, -5]
|
|
tags = ['PRP', 'IN', 'NNP', 'NNP', 'IN', 'NNP', '.']
|
|
pos = ['PRON', 'VERB', 'PROPN', 'PROPN', 'ADP', 'PROPN', 'PUNCT']
|
|
deps = ['ROOT', 'prep', 'compound', 'pobj', 'prep', 'pobj', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads,
|
|
tags=tags, pos=pos, deps=deps)
|
|
doc.ents = [Span(doc, 2, 4, doc.vocab.strings['GPE'])]
|
|
doc.is_parsed = True
|
|
doc.is_tagged = True
|
|
return doc
|
|
|
|
|
|
def test_factories_merge_noun_chunks(doc):
|
|
assert len(doc) == 7
|
|
nlp = Language()
|
|
merge_noun_chunks = nlp.create_pipe('merge_noun_chunks')
|
|
merge_noun_chunks(doc)
|
|
assert len(doc) == 6
|
|
assert doc[2].text == 'New York'
|
|
|
|
|
|
def test_factories_merge_ents(doc):
|
|
assert len(doc) == 7
|
|
assert len(list(doc.ents)) == 1
|
|
nlp = Language()
|
|
merge_entities = nlp.create_pipe('merge_entities')
|
|
merge_entities(doc)
|
|
assert len(doc) == 6
|
|
assert len(list(doc.ents)) == 1
|
|
assert doc[2].text == 'New York'
|