From b818afaa0e7c5e661c0db6275885cba4da9fbb81 Mon Sep 17 00:00:00 2001 From: Motoki Wu Date: Fri, 17 Nov 2017 17:04:27 -0800 Subject: [PATCH 1/3] Added failing test for Issue #1207. The noun chunk iterator should work for `Doc` but not for `Span`. --- spacy/tests/regression/test_issue1207.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 spacy/tests/regression/test_issue1207.py diff --git a/spacy/tests/regression/test_issue1207.py b/spacy/tests/regression/test_issue1207.py new file mode 100644 index 000000000..f8a53e05c --- /dev/null +++ b/spacy/tests/regression/test_issue1207.py @@ -0,0 +1,13 @@ +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.models('en') +def test_issue1207(EN): + text = 'Employees are recruiting talented staffers from overseas.' + doc = EN(text) + + assert [i.text for i in doc.noun_chunks] == ['Employees', 'talented staffers'] + sent = list(doc.sents)[0] + assert [i.text for i in sent.noun_chunks] == ['Employees', 'talented staffers'] From a52e195a0ac7061966893906451a822947dbcea7 Mon Sep 17 00:00:00 2001 From: Motoki Wu Date: Fri, 17 Nov 2017 17:13:13 -0800 Subject: [PATCH 2/3] Fixes Issue #1207 where `noun_chunks` of `Span` gives an error. Make sure to reference `self.doc` when getting the noun chunks. Same fix as 9750a0128cf211dac80217eee38e41c38f2c761c --- spacy/tokens/span.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx index 4056ef615..9759c10a9 100644 --- a/spacy/tokens/span.pyx +++ b/spacy/tokens/span.pyx @@ -370,7 +370,7 @@ cdef class Span: spans = [] cdef attr_t label for start, end, label in self.doc.noun_chunks_iterator(self): - spans.append(Span(self, start, end, label=label)) + spans.append(Span(self.doc, start, end, label=label)) for span in spans: yield span From 7b5b49eef03c86dfc40bc3c53681895252890ce2 Mon Sep 17 00:00:00 2001 From: Motoki Wu Date: Fri, 17 Nov 2017 17:27:20 -0800 Subject: [PATCH 3/3] added contributor agreement --- .github/contributors/tokestermw.md | 106 +++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/tokestermw.md diff --git a/.github/contributors/tokestermw.md b/.github/contributors/tokestermw.md new file mode 100644 index 000000000..2d69d7736 --- /dev/null +++ b/.github/contributors/tokestermw.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 | Motoki Wu | +| Company name (if applicable) | WriteLab | +| Title or role (if applicable) | NLP / Deep Learning Engineer | +| Date | 17 November 2017 | +| GitHub username | tokestermw | +| Website (optional) | https://twitter.com/plusepsilon |