mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
a1b22e90cd
* expand serialization test for custom token attribute * add failing test for issue 4849 * define ENT_ID as attr and use in doc serialization * fix few typos
36 lines
1.0 KiB
Python
36 lines
1.0 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.tokens import Doc, Token
|
|
from spacy.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"
|
|
|
|
Token.set_extension("_test_token", default="t0")
|
|
doc[1]._._test_token = "t1"
|
|
|
|
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")
|
|
|
|
assert doc[0]._._test_token == "t0"
|
|
assert doc[1]._._test_token == "t1"
|
|
assert doc[2]._._test_token == "t0"
|