explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 01:04:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Start updating serializer test

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-09 18:12:03 +02:00
parent 1166b0c491
commit f9327343ce
1 changed files with 24 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
spacy/tests/serialize/test_serialization.py
View File

@ -1,8 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ...serialize.packer import Packer
from ..util import get_doc, assert_docs_equal from ..util import get_doc, assert_docs_equal
from ...tokens import Doc
import pytest import pytest
@ -15,26 +15,27 @@ ENTS = [('hi', 'PERSON', 0, 1)]
def test_serialize_empty_doc(en_vocab): def test_serialize_empty_doc(en_vocab):
doc = get_doc(en_vocab) doc = get_doc(en_vocab)
packer = Packer(en_vocab, {}) data = doc.to_bytes()
b = packer.pack(doc) doc2 = Doc(en_vocab)
assert b == b'' doc2.from_bytes(data)
loaded = get_doc(en_vocab).from_bytes(b) assert len(doc) == len(doc2)
assert len(loaded) == 0 for token1, token2 in zip(doc, doc2):
assert token1.text == token2.text
#
@pytest.mark.parametrize('text', [TEXT]) #@pytest.mark.parametrize('text', [TEXT])
def test_serialize_tokens(en_vocab, text): #def test_serialize_tokens(en_vocab, text):
doc1 = get_doc(en_vocab, [t for t in text]) # doc1 = get_doc(en_vocab, [t for t in text])
doc2 = get_doc(en_vocab).from_bytes(doc1.to_bytes()) # doc2 = get_doc(en_vocab).from_bytes(doc1.to_bytes())
assert_docs_equal(doc1, doc2) # assert_docs_equal(doc1, doc2)
#
#
@pytest.mark.models #@pytest.mark.models
@pytest.mark.parametrize('text', [TEXT]) #@pytest.mark.parametrize('text', [TEXT])
@pytest.mark.parametrize('tags', [TAGS, []]) #@pytest.mark.parametrize('tags', [TAGS, []])
@pytest.mark.parametrize('deps', [DEPS, []]) #@pytest.mark.parametrize('deps', [DEPS, []])
@pytest.mark.parametrize('ents', [ENTS, []]) #@pytest.mark.parametrize('ents', [ENTS, []])
def test_serialize_tokens_ner(EN, text, tags, deps, ents): #def test_serialize_tokens_ner(EN, text, tags, deps, ents):
doc1 = get_doc(EN.vocab, [t for t in text], tags=tags, deps=deps, ents=ents) # doc1 = get_doc(EN.vocab, [t for t in text], tags=tags, deps=deps, ents=ents)
doc2 = get_doc(EN.vocab).from_bytes(doc1.to_bytes()) # doc2 = get_doc(EN.vocab).from_bytes(doc1.to_bytes())
assert_docs_equal(doc1, doc2) # assert_docs_equal(doc1, doc2)