From cdd4b3d05c511372d888b04c70d0a985bb307b17 Mon Sep 17 00:00:00 2001 From: Claudiu-Vlad Ursache Date: Sun, 4 Feb 2018 17:48:11 +0100 Subject: [PATCH 1/2] Add contributor agreement for @ursachec --- .github/contributors/ursachec.md | 106 +++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/ursachec.md diff --git a/.github/contributors/ursachec.md b/.github/contributors/ursachec.md new file mode 100644 index 000000000..45a85f166 --- /dev/null +++ b/.github/contributors/ursachec.md @@ -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 UG (haftungsbeschränkt)](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 | Claudiu-Vlad Ursache | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2018-02-04 | +| GitHub username | ursachec | +| Website (optional) | https://www.cvursache.com | From e28de12cbdeb932de0ec4fff901a3bc469bb90c3 Mon Sep 17 00:00:00 2001 From: Claudiu-Vlad Ursache Date: Tue, 13 Feb 2018 20:44:33 +0100 Subject: [PATCH 2/2] Ensure files opened in `from_disk` are closed Fixes [issue 1706](https://github.com/explosion/spaCy/issues/1706). --- spacy/language.py | 2 +- spacy/pipeline.pyx | 6 ++-- spacy/syntax/nn_parser.pyx | 2 +- .../serialize/test_serialize_language.py | 28 +++++++++++++++++++ spacy/vectors.pyx | 3 +- 5 files changed, 36 insertions(+), 5 deletions(-) create mode 100644 spacy/tests/serialize/test_serialize_language.py diff --git a/spacy/language.py b/spacy/language.py index a2b945c49..a61b6b09f 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -624,7 +624,7 @@ class Language(object): deserializers = OrderedDict(( ('vocab', lambda p: self.vocab.from_disk(p)), ('tokenizer', lambda p: self.tokenizer.from_disk(p, vocab=False)), - ('meta.json', lambda p: self.meta.update(ujson.load(p.open('r')))) + ('meta.json', lambda p: self.meta.update(util.read_json(p))) )) for name, proc in self.pipeline: if name in disable: diff --git a/spacy/pipeline.pyx b/spacy/pipeline.pyx index c5f8065de..dae21941e 100644 --- a/spacy/pipeline.pyx +++ b/spacy/pipeline.pyx @@ -214,7 +214,8 @@ class Pipe(object): def _load_cfg(path): if path.exists(): - return ujson.load(path.open()) + with path.open() as file_: + return ujson.load(file_) else: return {} @@ -580,7 +581,8 @@ class Tagger(Pipe): def load_model(p): if self.model is True: self.model = self.Model(self.vocab.morphology.n_tags, **self.cfg) - self.model.from_bytes(p.open('rb').read()) + with p.open('rb') as file_: + self.model.from_bytes(file_.read()) def load_tag_map(p): with p.open('rb') as file_: diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx index fa91c697e..f192e3b96 100644 --- a/spacy/syntax/nn_parser.pyx +++ b/spacy/syntax/nn_parser.pyx @@ -887,7 +887,7 @@ cdef class Parser: deserializers = { 'vocab': lambda p: self.vocab.from_disk(p), 'moves': lambda p: self.moves.from_disk(p, strings=False), - 'cfg': lambda p: self.cfg.update(ujson.load(p.open())), + 'cfg': lambda p: self.cfg.update(util.read_json(p)), 'model': lambda p: None } util.from_disk(path, deserializers, exclude) diff --git a/spacy/tests/serialize/test_serialize_language.py b/spacy/tests/serialize/test_serialize_language.py new file mode 100644 index 000000000..1fcf8ef18 --- /dev/null +++ b/spacy/tests/serialize/test_serialize_language.py @@ -0,0 +1,28 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from ..util import make_tempdir +from ...language import Language + +import pytest + + +@pytest.fixture +def meta_data(): + return { + 'name': 'name-in-fixture', + 'version': 'version-in-fixture', + 'description': 'description-in-fixture', + 'author': 'author-in-fixture', + 'email': 'email-in-fixture', + 'url': 'url-in-fixture', + 'license': 'license-in-fixture', + } + + +def test_serialize_language_meta_disk(meta_data): + language = Language(meta=meta_data) + with make_tempdir() as d: + language.to_disk(d) + new_language = Language().from_disk(d) + assert new_language.meta == language.meta diff --git a/spacy/vectors.pyx b/spacy/vectors.pyx index 079f6fc84..7daebabe6 100644 --- a/spacy/vectors.pyx +++ b/spacy/vectors.pyx @@ -347,7 +347,8 @@ cdef class Vectors: """ def load_key2row(path): if path.exists(): - self.key2row = msgpack.load(path.open('rb')) + with path.open('rb') as file_: + self.key2row = msgpack.load(file_) for key, row in self.key2row.items(): if row in self._unset: self._unset.remove(row)