mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
950832f087
* Tidy up pipes * Fix init, defaults and raise custom errors * Update docs * Update docs [ci skip] * Apply suggestions from code review Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com> * Tidy up error handling and validation, fix consistency * Simplify get_examples check * Remove unused import [ci skip] Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
149 lines
4.3 KiB
Python
149 lines
4.3 KiB
Python
import warnings
|
|
from unittest import TestCase
|
|
import pytest
|
|
import srsly
|
|
from numpy import zeros
|
|
from spacy.kb import KnowledgeBase, Writer
|
|
from spacy.vectors import Vectors
|
|
from spacy.language import Language
|
|
from spacy.pipeline import Pipe
|
|
from spacy.util import registry
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
def nlp():
|
|
return Language()
|
|
|
|
|
|
def vectors():
|
|
data = zeros((3, 1), dtype="f")
|
|
keys = ["cat", "dog", "rat"]
|
|
return Vectors(data=data, keys=keys)
|
|
|
|
|
|
def custom_pipe():
|
|
# create dummy pipe partially implementing interface -- only want to test to_disk
|
|
class SerializableDummy:
|
|
def __init__(self, **cfg):
|
|
if cfg:
|
|
self.cfg = cfg
|
|
else:
|
|
self.cfg = None
|
|
super(SerializableDummy, self).__init__()
|
|
|
|
def to_bytes(self, exclude=tuple(), disable=None, **kwargs):
|
|
return srsly.msgpack_dumps({"dummy": srsly.json_dumps(None)})
|
|
|
|
def from_bytes(self, bytes_data, exclude):
|
|
return self
|
|
|
|
def to_disk(self, path, exclude=tuple(), **kwargs):
|
|
pass
|
|
|
|
def from_disk(self, path, exclude=tuple(), **kwargs):
|
|
return self
|
|
|
|
class MyPipe(Pipe):
|
|
def __init__(self, vocab, model=True, **cfg):
|
|
if cfg:
|
|
self.cfg = cfg
|
|
else:
|
|
self.cfg = None
|
|
self.model = SerializableDummy()
|
|
self.vocab = SerializableDummy()
|
|
|
|
return MyPipe(None)
|
|
|
|
|
|
def tagger():
|
|
nlp = Language()
|
|
tagger = nlp.add_pipe("tagger")
|
|
# need to add model for two reasons:
|
|
# 1. no model leads to error in serialization,
|
|
# 2. the affected line is the one for model serialization
|
|
tagger.begin_training(lambda: [], pipeline=nlp.pipeline)
|
|
return tagger
|
|
|
|
|
|
def entity_linker():
|
|
nlp = Language()
|
|
|
|
@registry.assets.register("TestIssue5230KB.v1")
|
|
def dummy_kb() -> KnowledgeBase:
|
|
kb = KnowledgeBase(entity_vector_length=1)
|
|
kb.initialize(nlp.vocab)
|
|
kb.add_entity("test", 0.0, zeros((1, 1), dtype="f"))
|
|
return kb
|
|
|
|
config = {"kb": {"@assets": "TestIssue5230KB.v1"}}
|
|
entity_linker = nlp.add_pipe("entity_linker", config=config)
|
|
# need to add model for two reasons:
|
|
# 1. no model leads to error in serialization,
|
|
# 2. the affected line is the one for model serialization
|
|
entity_linker.begin_training(lambda: [], pipeline=nlp.pipeline)
|
|
return entity_linker
|
|
|
|
|
|
objects_to_test = (
|
|
[nlp(), vectors(), custom_pipe(), tagger(), entity_linker()],
|
|
["nlp", "vectors", "custom_pipe", "tagger", "entity_linker"],
|
|
)
|
|
|
|
|
|
def write_obj_and_catch_warnings(obj):
|
|
with make_tempdir() as d:
|
|
with warnings.catch_warnings(record=True) as warnings_list:
|
|
warnings.filterwarnings("always", category=ResourceWarning)
|
|
obj.to_disk(d)
|
|
# in python3.5 it seems that deprecation warnings are not filtered by filterwarnings
|
|
return list(filter(lambda x: isinstance(x, ResourceWarning), warnings_list))
|
|
|
|
|
|
@pytest.mark.parametrize("obj", objects_to_test[0], ids=objects_to_test[1])
|
|
def test_to_disk_resource_warning(obj):
|
|
warnings_list = write_obj_and_catch_warnings(obj)
|
|
assert len(warnings_list) == 0
|
|
|
|
|
|
def test_writer_with_path_py35():
|
|
writer = None
|
|
with make_tempdir() as d:
|
|
path = d / "test"
|
|
try:
|
|
writer = Writer(path)
|
|
except Exception as e:
|
|
pytest.fail(str(e))
|
|
finally:
|
|
if writer:
|
|
writer.close()
|
|
|
|
|
|
def test_save_and_load_knowledge_base():
|
|
nlp = Language()
|
|
kb = KnowledgeBase(entity_vector_length=1)
|
|
kb.initialize(nlp.vocab)
|
|
with make_tempdir() as d:
|
|
path = d / "kb"
|
|
try:
|
|
kb.dump(path)
|
|
except Exception as e:
|
|
pytest.fail(str(e))
|
|
|
|
try:
|
|
kb_loaded = KnowledgeBase(entity_vector_length=1)
|
|
kb_loaded.initialize(nlp.vocab)
|
|
kb_loaded.load_bulk(path)
|
|
except Exception as e:
|
|
pytest.fail(str(e))
|
|
|
|
|
|
class TestToDiskResourceWarningUnittest(TestCase):
|
|
def test_resource_warning(self):
|
|
scenarios = zip(*objects_to_test)
|
|
|
|
for scenario in scenarios:
|
|
with self.subTest(msg=scenario[1]):
|
|
warnings_list = write_obj_and_catch_warnings(scenario[0])
|
|
self.assertEqual(len(warnings_list), 0)
|