spaCy/spacy/tests/serialize/test_serialize_doc.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

78 lines
2.4 KiB
Python

import spacy
import pytest
from spacy.lang.en import English
from spacy.tokens import Doc, DocBin
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.cats = {"A": 0.5}
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 = str(file_path)
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_exclude(en_vocab):
doc = Doc(en_vocab, words=["hello", "world"])
doc.user_data["foo"] = "bar"
new_doc = Doc(en_vocab).from_bytes(doc.to_bytes())
assert new_doc.user_data["foo"] == "bar"
new_doc = Doc(en_vocab).from_bytes(doc.to_bytes(), exclude=["user_data"])
assert not new_doc.user_data
new_doc = Doc(en_vocab).from_bytes(doc.to_bytes(exclude=["user_data"]))
assert not new_doc.user_data
with pytest.raises(ValueError):
doc.to_bytes(user_data=False)
with pytest.raises(ValueError):
Doc(en_vocab).from_bytes(doc.to_bytes(), tensor=False)
def test_serialize_doc_bin():
doc_bin = DocBin(attrs=["LEMMA", "ENT_IOB", "ENT_TYPE"], store_user_data=True)
texts = ["Some text", "Lots of texts...", "..."]
cats = {"A": 0.5}
nlp = English()
for doc in nlp.pipe(texts):
doc.cats = cats
doc_bin.add(doc)
bytes_data = doc_bin.to_bytes()
# Deserialize later, e.g. in a new process
nlp = spacy.blank("en")
doc_bin = DocBin().from_bytes(bytes_data)
reloaded_docs = list(doc_bin.get_docs(nlp.vocab))
for i, doc in enumerate(reloaded_docs):
assert doc.text == texts[i]
assert doc.cats == cats