diff --git a/.github/contributors/ophelielacroix.md b/.github/contributors/ophelielacroix.md new file mode 100644 index 000000000..2abdfdecf --- /dev/null +++ b/.github/contributors/ophelielacroix.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 | Ophélie Lacroix | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | | +| GitHub username | ophelielacroix | +| Website (optional) | | diff --git a/spacy/lang/da/__init__.py b/spacy/lang/da/__init__.py index 0190656e5..88258a8df 100644 --- a/spacy/lang/da/__init__.py +++ b/spacy/lang/da/__init__.py @@ -7,6 +7,7 @@ from .stop_words import STOP_WORDS from .lex_attrs import LEX_ATTRS from .morph_rules import MORPH_RULES from ..tag_map import TAG_MAP +from .syntax_iterators import SYNTAX_ITERATORS from ..tokenizer_exceptions import BASE_EXCEPTIONS from ...language import Language @@ -24,6 +25,7 @@ class DanishDefaults(Language.Defaults): suffixes = TOKENIZER_SUFFIXES tag_map = TAG_MAP stop_words = STOP_WORDS + syntax_iterators = SYNTAX_ITERATORS class Danish(Language): diff --git a/spacy/lang/da/syntax_iterators.py b/spacy/lang/da/syntax_iterators.py new file mode 100644 index 000000000..c6b944193 --- /dev/null +++ b/spacy/lang/da/syntax_iterators.py @@ -0,0 +1,81 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...symbols import NOUN, PROPN, PRON, VERB, AUX +from ...errors import Errors + + +def noun_chunks(doclike): + def is_verb_token(tok): + return tok.pos in [VERB, AUX] + + def next_token(tok): + try: + return tok.nbor() + except IndexError: + return None + + def get_left_bound(doc, root): + left_bound = root + for tok in reversed(list(root.lefts)): + if tok.dep in np_left_deps: + left_bound = tok + return left_bound + + def get_right_bound(doc, root): + right_bound = root + for tok in root.rights: + if tok.dep in np_right_deps: + right = get_right_bound(doc, tok) + if list( + filter( + lambda t: is_verb_token(t) or t.dep in stop_deps, + doc[root.i : right.i], + ) + ): + break + else: + right_bound = right + return right_bound + + def get_bounds(doc, root): + return get_left_bound(doc, root), get_right_bound(doc, root) + + doc = doclike.doc + + if not doc.is_parsed: + raise ValueError(Errors.E029) + + if not len(doc): + return + + left_labels = [ + "det", + "fixed", + "nmod:poss", + "amod", + "flat", + "goeswith", + "nummod", + "appos", + ] + right_labels = ["fixed", "nmod:poss", "amod", "flat", "goeswith", "nummod", "appos"] + stop_labels = ["punct"] + + np_label = doc.vocab.strings.add("NP") + np_left_deps = [doc.vocab.strings.add(label) for label in left_labels] + np_right_deps = [doc.vocab.strings.add(label) for label in right_labels] + stop_deps = [doc.vocab.strings.add(label) for label in stop_labels] + + chunks = [] + prev_right = -1 + for token in doclike: + if token.pos in [PROPN, NOUN, PRON]: + left, right = get_bounds(doc, token) + if left.i <= prev_right: + continue + yield left.i, right.i + 1, np_label + prev_right = right.i + + +SYNTAX_ITERATORS = {"noun_chunks": noun_chunks} diff --git a/spacy/tests/lang/da/test_noun_chunks.py b/spacy/tests/lang/da/test_noun_chunks.py new file mode 100644 index 000000000..01bbbb21c --- /dev/null +++ b/spacy/tests/lang/da/test_noun_chunks.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest + +from ...util import get_doc + + +def test_noun_chunks_is_parsed(da_tokenizer): + """Test that noun_chunks raises Value Error for 'da' language if Doc is not parsed. + To check this test, we're constructing a Doc + with a new Vocab here and forcing is_parsed to 'False' + to make sure the noun chunks don't run. + """ + doc = da_tokenizer("Det er en sætning") + doc.is_parsed = False + with pytest.raises(ValueError): + list(doc.noun_chunks) + + + +DA_NP_TEST_EXAMPLES = [ + ( + "Hun elsker at plukker frugt.", + ['PRON', 'VERB', 'PART', 'VERB', 'NOUN', 'PUNCT'], + ['nsubj', 'ROOT', 'mark', 'obj', 'obj', 'punct'], + [1, 0, 1, -2, -1, -4], + ["Hun", "frugt"], + ), + ( + "Påfugle er de smukkeste fugle.", + ['NOUN', 'AUX', 'DET', 'ADJ', 'NOUN', 'PUNCT'], + ['nsubj', 'cop', 'det', 'amod', 'ROOT', 'punct'], + [4, 3, 2, 1, 0, -1], + ["Påfugle", "de smukkeste fugle"], + ), + ( + "Rikke og Jacob Jensen glæder sig til en hyggelig skovtur", + ['PROPN', 'CCONJ', 'PROPN', 'PROPN', 'VERB', 'PRON', 'ADP', 'DET', 'ADJ', 'NOUN'], + ['nsubj', 'cc', 'conj', 'flat', 'ROOT', 'obj', 'case', 'det', 'amod', 'obl'], + [4, 1, -2, -1, 0, -1, 3, 2, 1, -5], + ["Rikke", "Jacob Jensen", "sig", "en hyggelig skovtur"], + ), +] + + +@pytest.mark.parametrize( + "text,pos,deps,heads,expected_noun_chunks", DA_NP_TEST_EXAMPLES +) +def test_da_noun_chunks(da_tokenizer, text, pos, deps, heads, expected_noun_chunks): + tokens = da_tokenizer(text) + + assert len(heads) == len(pos) + doc = get_doc( + tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps, pos=pos + ) + + noun_chunks = list(doc.noun_chunks) + assert len(noun_chunks) == len(expected_noun_chunks) + for i, np in enumerate(noun_chunks): + assert np.text == expected_noun_chunks[i]