diff --git a/.github/contributors/kognate.md b/.github/contributors/kognate.md new file mode 100644 index 000000000..9ff2c75d0 --- /dev/null +++ b/.github/contributors/kognate.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 | Joshua B. Smith | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | July 7, 2019 | +| GitHub username | kognate | +| Website (optional) | | diff --git a/spacy/pipeline/entityruler.py b/spacy/pipeline/entityruler.py index 54fd4a062..edf6b722b 100644 --- a/spacy/pipeline/entityruler.py +++ b/spacy/pipeline/entityruler.py @@ -1,15 +1,17 @@ # coding: utf8 from __future__ import unicode_literals -from collections import defaultdict +from collections import defaultdict, OrderedDict import srsly from ..errors import Errors from ..compat import basestring_ -from ..util import ensure_path +from ..util import ensure_path, to_disk, from_disk from ..tokens import Span from ..matcher import Matcher, PhraseMatcher +DEFAULT_ENT_ID_SEP = '||' + class EntityRuler(object): """The EntityRuler lets you add spans to the `Doc.ents` using token-based @@ -48,7 +50,7 @@ class EntityRuler(object): self.phrase_patterns = defaultdict(list) self.matcher = Matcher(nlp.vocab) self.phrase_matcher = PhraseMatcher(nlp.vocab) - self.ent_id_sep = cfg.get("ent_id_sep", "||") + self.ent_id_sep = cfg.get("ent_id_sep", DEFAULT_ENT_ID_SEP) patterns = cfg.get("patterns") if patterns is not None: self.add_patterns(patterns) @@ -196,7 +198,7 @@ class EntityRuler(object): def _create_label(self, label, ent_id): """Join Entity label with ent_id if the pattern has an `id` attribute - + RETURNS (str): The ent_label joined with configured `ent_id_sep` """ if isinstance(ent_id, basestring_): @@ -212,8 +214,13 @@ class EntityRuler(object): DOCS: https://spacy.io/api/entityruler#from_bytes """ - patterns = srsly.msgpack_loads(patterns_bytes) - self.add_patterns(patterns) + cfg = srsly.msgpack_loads(patterns_bytes) + if isinstance(cfg, dict): + self.add_patterns(cfg.get('patterns', cfg)) + self.overwrite = cfg.get('overwrite', False) + self.ent_id_sep = cfg.get('ent_id_sep', DEFAULT_ENT_ID_SEP) + else: + self.add_patterns(cfg) return self def to_bytes(self, **kwargs): @@ -223,7 +230,12 @@ class EntityRuler(object): DOCS: https://spacy.io/api/entityruler#to_bytes """ - return srsly.msgpack_dumps(self.patterns) + + serial = OrderedDict(( + ('overwrite', self.overwrite), + ('ent_id_sep', self.ent_id_sep), + ('patterns', self.patterns))) + return srsly.msgpack_dumps(serial) def from_disk(self, path, **kwargs): """Load the entity ruler from a file. Expects a file containing @@ -236,9 +248,18 @@ class EntityRuler(object): DOCS: https://spacy.io/api/entityruler#from_disk """ path = ensure_path(path) - path = path.with_suffix(".jsonl") - patterns = srsly.read_jsonl(path) - self.add_patterns(patterns) + if path.is_file(): + patterns = srsly.read_jsonl(path) + self.add_patterns(patterns) + else: + cfg = {} + deserializers = { + 'patterns': lambda p: self.add_patterns(srsly.read_jsonl(p.with_suffix('.jsonl'))), + 'cfg': lambda p: cfg.update(srsly.read_json(p)) + } + from_disk(path, deserializers, {}) + self.overwrite = cfg.get('overwrite', False) + self.ent_id_sep = cfg.get('ent_id_sep', DEFAULT_ENT_ID_SEP) return self def to_disk(self, path, **kwargs): @@ -251,6 +272,12 @@ class EntityRuler(object): DOCS: https://spacy.io/api/entityruler#to_disk """ + cfg = {'overwrite': self.overwrite, + 'ent_id_sep': self.ent_id_sep} + serializers = { + 'patterns': lambda p: srsly.write_jsonl(p.with_suffix('.jsonl'), + self.patterns), + 'cfg': lambda p: srsly.write_json(p, cfg) + } path = ensure_path(path) - path = path.with_suffix(".jsonl") - srsly.write_jsonl(path, self.patterns) + to_disk(path, serializers, {}) diff --git a/spacy/tests/regression/test_issue3526.py b/spacy/tests/regression/test_issue3526.py new file mode 100644 index 000000000..118cb3af5 --- /dev/null +++ b/spacy/tests/regression/test_issue3526.py @@ -0,0 +1,82 @@ +# coding: utf8 +from __future__ import unicode_literals + +import pytest +from spacy.tokens import Span +from spacy.language import Language +from spacy.pipeline import EntityRuler +from spacy import load +import srsly +from ..util import make_tempdir + +@pytest.fixture +def patterns(): + return [ + {"label": "HELLO", "pattern": "hello world"}, + {"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]}, + {"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]}, + {"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]}, + {"label": "TECH_ORG", "pattern": "Apple", "id": "a1"}, + ] + + +@pytest.fixture +def add_ent(): + def add_ent_component(doc): + doc.ents = [Span(doc, 0, 3, label=doc.vocab.strings["ORG"])] + return doc + + return add_ent_component + +def test_entity_ruler_existing_overwrite_serialize_bytes(patterns, en_vocab): + nlp = Language(vocab=en_vocab) + ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True) + ruler_bytes = ruler.to_bytes() + assert len(ruler) == len(patterns) + assert len(ruler.labels) == 4 + assert ruler.overwrite + new_ruler = EntityRuler(nlp) + new_ruler = new_ruler.from_bytes(ruler_bytes) + assert len(new_ruler) == len(ruler) + assert len(new_ruler.labels) == 4 + assert new_ruler.overwrite == ruler.overwrite + assert new_ruler.ent_id_sep == ruler.ent_id_sep + + +def test_entity_ruler_existing_bytes_old_format_safe(patterns, en_vocab): + nlp = Language(vocab=en_vocab) + ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True) + bytes_old_style = srsly.msgpack_dumps(ruler.patterns) + new_ruler = EntityRuler(nlp) + new_ruler = new_ruler.from_bytes(bytes_old_style) + assert len(new_ruler) == len(ruler) + assert new_ruler.patterns == ruler.patterns + assert new_ruler.overwrite is not ruler.overwrite + + +def test_entity_ruler_from_disk_old_format_safe(patterns, en_vocab): + nlp = Language(vocab=en_vocab) + ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True) + with make_tempdir() as tmpdir: + out_file = tmpdir / "entity_ruler.jsonl" + srsly.write_jsonl(out_file, ruler.patterns) + new_ruler = EntityRuler(nlp) + new_ruler = new_ruler.from_disk(out_file) + assert new_ruler.patterns == ruler.patterns + assert len(new_ruler) == len(ruler) + assert new_ruler.overwrite is not ruler.overwrite + + +def test_entity_ruler_in_pipeline_from_issue(patterns, en_vocab): + nlp = Language(vocab=en_vocab) + ruler = EntityRuler(nlp, overwrite_ents=True) + + ruler.add_patterns([{"label": "ORG", "pattern": "Apple"}]) + nlp.add_pipe(ruler) + with make_tempdir() as tmpdir: + nlp.to_disk(tmpdir) + assert nlp.pipeline[-1][-1].patterns == [{"label": "ORG", "pattern": "Apple"}] + assert nlp.pipeline[-1][-1].overwrite is True + nlp2 = load(tmpdir) + assert nlp2.pipeline[-1][-1].patterns == [{"label": "ORG", "pattern": "Apple"}] + assert nlp2.pipeline[-1][-1].overwrite is True