mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
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()
|