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.
44 lines
1.2 KiB
Python
44 lines
1.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from spacy.tokens import Doc
|
|
from spacy.compat import path2str
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
def test_serialize_empty_doc(en_vocab):
|
|
doc = Doc(en_vocab)
|
|
data = doc.to_bytes()
|
|
doc2 = Doc(en_vocab)
|
|
doc2.from_bytes(data)
|
|
assert len(doc) == len(doc2)
|
|
for token1, token2 in zip(doc, doc2):
|
|
assert token1.text == token2.text
|
|
|
|
|
|
def test_serialize_doc_roundtrip_bytes(en_vocab):
|
|
doc = Doc(en_vocab, words=['hello', 'world'])
|
|
doc_b = doc.to_bytes()
|
|
new_doc = Doc(en_vocab).from_bytes(doc_b)
|
|
assert new_doc.to_bytes() == doc_b
|
|
|
|
|
|
def test_serialize_doc_roundtrip_disk(en_vocab):
|
|
doc = Doc(en_vocab, words=['hello', 'world'])
|
|
with make_tempdir() as d:
|
|
file_path = d / 'doc'
|
|
doc.to_disk(file_path)
|
|
doc_d = Doc(en_vocab).from_disk(file_path)
|
|
assert doc.to_bytes() == doc_d.to_bytes()
|
|
|
|
|
|
def test_serialize_doc_roundtrip_disk_str_path(en_vocab):
|
|
doc = Doc(en_vocab, words=['hello', 'world'])
|
|
with make_tempdir() as d:
|
|
file_path = d / 'doc'
|
|
file_path = path2str(file_path)
|
|
doc.to_disk(file_path)
|
|
doc_d = Doc(en_vocab).from_disk(file_path)
|
|
assert doc.to_bytes() == doc_d.to_bytes()
|