Merge pull request #5264 from lfiedler/issue-5230

Fix ResourceWarnings during unittest
This commit is contained in:
Matthew Honnibal 2020-05-22 00:31:07 +02:00 committed by GitHub
commit 93c4d13588
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 266 additions and 11 deletions

106
.github/contributors/lfiedler.md vendored Normal file
View File

@ -0,0 +1,106 @@
# spaCy contributor agreement
This spaCy Contributor Agreement (**"SCA"**) is based on the
[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
The SCA applies to any contribution that you make to any product or project
managed by us (the **"project"**), and sets out the intellectual property rights
you grant to us in the contributed materials. The term **"us"** shall mean
[ExplosionAI GmbH](https://explosion.ai/legal). The term
**"you"** shall mean the person or entity identified below.
If you agree to be bound by these terms, fill in the information requested
below and include the filled-in version with your first pull request, under the
folder [`.github/contributors/`](/.github/contributors/). The name of the file
should be your GitHub username, with the extension `.md`. For example, the user
example_user would create the file `.github/contributors/example_user.md`.
Read this agreement carefully before signing. These terms and conditions
constitute a binding legal agreement.
## Contributor Agreement
1. The term "contribution" or "contributed materials" means any source code,
object code, patch, tool, sample, graphic, specification, manual,
documentation, or any other material posted or submitted by you to the project.
2. With respect to any worldwide copyrights, or copyright applications and
registrations, in your contribution:
* you hereby assign to us joint ownership, and to the extent that such
assignment is or becomes invalid, ineffective or unenforceable, you hereby
grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
royalty-free, unrestricted license to exercise all rights under those
copyrights. This includes, at our option, the right to sublicense these same
rights to third parties through multiple levels of sublicensees or other
licensing arrangements;
* you agree that each of us can do all things in relation to your
contribution as if each of us were the sole owners, and if one of us makes
a derivative work of your contribution, the one who makes the derivative
work (or has it made will be the sole owner of that derivative work;
* you agree that you will not assert any moral rights in your contribution
against us, our licensees or transferees;
* you agree that we may register a copyright in your contribution and
exercise all ownership rights associated with it; and
* you agree that neither of us has any duty to consult with, obtain the
consent of, pay or render an accounting to the other for any use or
distribution of your contribution.
3. With respect to any patents you own, or that you can license without payment
to any third party, you hereby grant to us a perpetual, irrevocable,
non-exclusive, worldwide, no-charge, royalty-free license to:
* make, have made, use, sell, offer to sell, import, and otherwise transfer
your contribution in whole or in part, alone or in combination with or
included in any product, work or materials arising out of the project to
which your contribution was submitted, and
* at our option, to sublicense these same rights to third parties through
multiple levels of sublicensees or other licensing arrangements.
4. Except as set out above, you keep all right, title, and interest in your
contribution. The rights that you grant to us under these terms are effective
on the date you first submitted a contribution to us, even if your submission
took place before the date you sign these terms.
5. You covenant, represent, warrant and agree that:
* Each contribution that you submit is and shall be an original work of
authorship and you can legally grant the rights set out in this SCA;
* to the best of your knowledge, each contribution will not violate any
third party's copyrights, trademarks, patents, or other intellectual
property rights; and
* each contribution shall be in compliance with U.S. export control laws and
other applicable export and import laws. You agree to notify us if you
become aware of any circumstance which would make any of the foregoing
representations inaccurate in any respect. We may publicly disclose your
participation in the project, including the fact that you have signed the SCA.
6. This SCA is governed by the laws of the State of California and applicable
U.S. Federal law. Any choice of law rules will not apply.
7. Please place an “x” on one of the applicable statement below. Please do NOT
mark both statements:
* [x] I am signing on behalf of myself as an individual and no other person
or entity, including my employer, has or will have rights with respect to my
contributions.
* [ ] I am signing on behalf of my employer or a legal entity and I have the
actual authority to contractually bind that entity.
## Contributor Details
| Field | Entry |
|------------------------------- | -------------------- |
| Name | Leander Fiedler |
| Company name (if applicable) | |
| Title or role (if applicable) | |
| Date | 06 April 2020 |
| GitHub username | lfiedler |
| Website (optional) | |

View File

@ -445,10 +445,10 @@ cdef class KnowledgeBase:
cdef class Writer: cdef class Writer:
def __init__(self, object loc): def __init__(self, object loc):
if path.exists(loc):
assert not path.isdir(loc), "%s is directory." % loc
if isinstance(loc, Path): if isinstance(loc, Path):
loc = bytes(loc) loc = bytes(loc)
if path.exists(loc):
assert not path.isdir(loc), "%s is directory." % loc
cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc
self._fp = fopen(<char*>bytes_loc, 'wb') self._fp = fopen(<char*>bytes_loc, 'wb')
if not self._fp: if not self._fp:
@ -490,10 +490,10 @@ cdef class Writer:
cdef class Reader: cdef class Reader:
def __init__(self, object loc): def __init__(self, object loc):
assert path.exists(loc)
assert not path.isdir(loc)
if isinstance(loc, Path): if isinstance(loc, Path):
loc = bytes(loc) loc = bytes(loc)
assert path.exists(loc)
assert not path.isdir(loc)
cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc
self._fp = fopen(<char*>bytes_loc, 'rb') self._fp = fopen(<char*>bytes_loc, 'rb')
if not self._fp: if not self._fp:

View File

@ -907,9 +907,8 @@ class Language(object):
serializers["tokenizer"] = lambda p: self.tokenizer.to_disk( serializers["tokenizer"] = lambda p: self.tokenizer.to_disk(
p, exclude=["vocab"] p, exclude=["vocab"]
) )
serializers["meta.json"] = lambda p: p.open("w").write( serializers["meta.json"] = lambda p: srsly.write_json(p, self.meta)
srsly.json_dumps(self.meta)
)
for name, proc in self.pipeline: for name, proc in self.pipeline:
if not hasattr(proc, "name"): if not hasattr(proc, "name"):
continue continue

View File

@ -203,7 +203,7 @@ class Pipe(object):
serialize["cfg"] = lambda p: srsly.write_json(p, self.cfg) serialize["cfg"] = lambda p: srsly.write_json(p, self.cfg)
serialize["vocab"] = lambda p: self.vocab.to_disk(p) serialize["vocab"] = lambda p: self.vocab.to_disk(p)
if self.model not in (None, True, False): if self.model not in (None, True, False):
serialize["model"] = lambda p: p.open("wb").write(self.model.to_bytes()) serialize["model"] = lambda p: self.model.to_disk(p)
exclude = util.get_serialization_exclude(serialize, exclude, kwargs) exclude = util.get_serialization_exclude(serialize, exclude, kwargs)
util.to_disk(path, serialize, exclude) util.to_disk(path, serialize, exclude)
@ -626,7 +626,7 @@ class Tagger(Pipe):
serialize = OrderedDict(( serialize = OrderedDict((
("vocab", lambda p: self.vocab.to_disk(p)), ("vocab", lambda p: self.vocab.to_disk(p)),
("tag_map", lambda p: srsly.write_msgpack(p, tag_map)), ("tag_map", lambda p: srsly.write_msgpack(p, tag_map)),
("model", lambda p: p.open("wb").write(self.model.to_bytes())), ("model", lambda p: self.model.to_disk(p)),
("cfg", lambda p: srsly.write_json(p, self.cfg)) ("cfg", lambda p: srsly.write_json(p, self.cfg))
)) ))
exclude = util.get_serialization_exclude(serialize, exclude, kwargs) exclude = util.get_serialization_exclude(serialize, exclude, kwargs)
@ -1395,7 +1395,7 @@ class EntityLinker(Pipe):
serialize["vocab"] = lambda p: self.vocab.to_disk(p) serialize["vocab"] = lambda p: self.vocab.to_disk(p)
serialize["kb"] = lambda p: self.kb.dump(p) serialize["kb"] = lambda p: self.kb.dump(p)
if self.model not in (None, True, False): if self.model not in (None, True, False):
serialize["model"] = lambda p: p.open("wb").write(self.model.to_bytes()) serialize["model"] = lambda p: self.model.to_disk(p)
exclude = util.get_serialization_exclude(serialize, exclude, kwargs) exclude = util.get_serialization_exclude(serialize, exclude, kwargs)
util.to_disk(path, serialize, exclude) util.to_disk(path, serialize, exclude)

View File

@ -0,0 +1,142 @@
# coding: utf8
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.tests.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(object):
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()
nlp.add_pipe(nlp.create_pipe("tagger"))
tagger = nlp.get_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(pipeline=nlp.pipeline)
return tagger
def entity_linker():
nlp = Language()
nlp.add_pipe(nlp.create_pipe("entity_linker"))
entity_linker = nlp.get_pipe("entity_linker")
# 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
kb = KnowledgeBase(nlp.vocab, entity_vector_length=1)
entity_linker.set_kb(kb)
entity_linker.begin_training(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(nlp.vocab, entity_vector_length=1)
with make_tempdir() as d:
path = d / "kb"
try:
kb.dump(path)
except Exception as e:
pytest.fail(str(e))
try:
kb_loaded = KnowledgeBase(nlp.vocab, entity_vector_length=1)
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)

View File

@ -383,8 +383,16 @@ cdef class Vectors:
save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False) save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False)
else: else:
save_array = lambda arr, file_: xp.save(file_, arr) save_array = lambda arr, file_: xp.save(file_, arr)
def save_vectors(path):
# the source of numpy.save indicates that the file object is closed after use.
# but it seems that somehow this does not happen, as ResourceWarnings are raised here.
# in order to not rely on this, wrap in context manager.
with path.open("wb") as _file:
save_array(self.data, _file)
serializers = OrderedDict(( serializers = OrderedDict((
("vectors", lambda p: save_array(self.data, p.open("wb"))), ("vectors", lambda p: save_vectors(p)),
("key2row", lambda p: srsly.write_msgpack(p, self.key2row)) ("key2row", lambda p: srsly.write_msgpack(p, self.key2row))
)) ))
return util.to_disk(path, serializers, []) return util.to_disk(path, serializers, [])