mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
28 lines
812 B
Python
28 lines
812 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
from ...tokens.doc import Doc
|
|
from ...vocab import Vocab
|
|
|
|
|
|
@pytest.fixture
|
|
def doc_w_attrs(en_tokenizer):
|
|
Doc.set_extension('_test_attr', default=False)
|
|
Doc.set_extension('_test_prop', getter=lambda doc: len(doc.text))
|
|
Doc.set_extension('_test_method', method=lambda doc, arg: "{}{}".format(len(doc.text), arg))
|
|
doc = en_tokenizer("This is a test.")
|
|
doc._._test_attr = 'test'
|
|
return doc
|
|
|
|
|
|
|
|
def test_serialize_ext_attrs_from_bytes(doc_w_attrs):
|
|
doc_b = doc_w_attrs.to_bytes()
|
|
doc = Doc(Vocab()).from_bytes(doc_b)
|
|
assert doc._.has('_test_attr')
|
|
assert doc._._test_attr == 'test'
|
|
assert doc._._test_prop == len(doc.text)
|
|
assert doc._._test_method('test') == '{}{}'.format(len(doc.text), 'test')
|