From 6b7971408066a6c29dbda5323e0c66183c984e46 Mon Sep 17 00:00:00 2001 From: Narayan Acharya Date: Mon, 31 May 2021 04:36:52 -0400 Subject: [PATCH] Address missing config overrides post load of models (#8208) --- .github/contributors/narayanacharya6.md | 106 +++++++++++++++++++++++ spacy/language.py | 5 +- spacy/tests/regression/test_issue8190.py | 28 ++++++ spacy/util.py | 5 +- 4 files changed, 140 insertions(+), 4 deletions(-) create mode 100644 .github/contributors/narayanacharya6.md create mode 100644 spacy/tests/regression/test_issue8190.py diff --git a/.github/contributors/narayanacharya6.md b/.github/contributors/narayanacharya6.md new file mode 100644 index 000000000..e4bf7703f --- /dev/null +++ b/.github/contributors/narayanacharya6.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 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 | Narayan Acharya | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 29 APR 2021 | +| GitHub username | narayanacharya6 | +| Website (optional) | narayanacharya.com | \ No newline at end of file diff --git a/spacy/language.py b/spacy/language.py index 2696d3655..d148df573 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -1846,7 +1846,8 @@ class Language: util.to_disk(path, serializers, exclude) def from_disk( - self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList() + self, path: Union[str, Path], *, exclude: Iterable[str] = SimpleFrozenList(), + overrides: Dict[str, Any] = SimpleFrozenDict(), ) -> "Language": """Loads state from a directory. Modifies the object in place and returns it. If the saved `Language` object contains a model, the @@ -1875,7 +1876,7 @@ class Language: deserializers = {} if Path(path / "config.cfg").exists(): deserializers["config.cfg"] = lambda p: self.config.from_disk( - p, interpolate=False + p, interpolate=False, overrides=overrides ) deserializers["meta.json"] = deserialize_meta deserializers["vocab"] = deserialize_vocab diff --git a/spacy/tests/regression/test_issue8190.py b/spacy/tests/regression/test_issue8190.py new file mode 100644 index 000000000..800a1638d --- /dev/null +++ b/spacy/tests/regression/test_issue8190.py @@ -0,0 +1,28 @@ +import spacy +from spacy.lang.en import English +from ..util import make_tempdir + + +def test_issue8190(): + """Test that config overrides are not lost after load is complete.""" + source_cfg = { + "nlp": { + "lang": "en", + }, + "custom": { + "key": "value" + } + + } + source_nlp = English.from_config(source_cfg) + with make_tempdir() as dir_path: + # We need to create a loadable source pipeline + source_path = dir_path / "test_model" + source_nlp.to_disk(source_path) + nlp = spacy.load(source_path, config={ + "custom": { + "key": "updated_value" + } + }) + + assert nlp.config["custom"]["key"] == "updated_value" diff --git a/spacy/util.py b/spacy/util.py index 84142d5d8..928106dbb 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -387,9 +387,10 @@ def load_model_from_path( if not meta: meta = get_model_meta(model_path) config_path = model_path / "config.cfg" - config = load_config(config_path, overrides=dict_to_dot(config)) + overrides = dict_to_dot(config) + config = load_config(config_path, overrides=overrides) nlp = load_model_from_config(config, vocab=vocab, disable=disable, exclude=exclude) - return nlp.from_disk(model_path, exclude=exclude) + return nlp.from_disk(model_path, exclude=exclude, overrides=overrides) def load_model_from_config(