From 7918fa4ef9417a04ec65191fac5b16db08c5add8 Mon Sep 17 00:00:00 2001 From: Kevin Humphreys Date: Wed, 3 Jan 2018 12:25:48 -0800 Subject: [PATCH 1/4] handle would've --- spacy/lang/en/tokenizer_exceptions.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/spacy/lang/en/tokenizer_exceptions.py b/spacy/lang/en/tokenizer_exceptions.py index 064b7ea59..df28e1287 100644 --- a/spacy/lang/en/tokenizer_exceptions.py +++ b/spacy/lang/en/tokenizer_exceptions.py @@ -213,7 +213,8 @@ for verb_data in [ {ORTH: "could", NORM: "could", TAG: "MD"}, {ORTH: "might", NORM: "might", TAG: "MD"}, {ORTH: "must", NORM: "must", TAG: "MD"}, - {ORTH: "should", NORM: "should", TAG: "MD"}]: + {ORTH: "should", NORM: "should", TAG: "MD"}, + {ORTH: "would", NORM: "would", TAG: "MD"}]: verb_data_tc = dict(verb_data) verb_data_tc[ORTH] = verb_data_tc[ORTH].title() for data in [verb_data, verb_data_tc]: From 597df5bf83b504f36735182f26cef0f0314eed7a Mon Sep 17 00:00:00 2001 From: Kevin Humphreys Date: Wed, 3 Jan 2018 13:00:05 -0800 Subject: [PATCH 2/4] add test --- spacy/tests/regression/test_issue1758.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 spacy/tests/regression/test_issue1758.py diff --git a/spacy/tests/regression/test_issue1758.py b/spacy/tests/regression/test_issue1758.py new file mode 100644 index 000000000..2c10591e0 --- /dev/null +++ b/spacy/tests/regression/test_issue1758.py @@ -0,0 +1,13 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.parametrize('text', ["would've"]) +def test_issue1758(en_tokenizer, text): + """Test that "would've" is handled by the English tokenizer exceptions.""" + tokens = en_tokenizer(text) + assert len(tokens) == 2 + assert tokens[0].tag_ == "MD" + assert tokens[1].lemma_ == "have" From 6173b697a783d1edac7471ef64d17a78d0a872f4 Mon Sep 17 00:00:00 2001 From: Kevin Humphreys Date: Wed, 3 Jan 2018 13:00:14 -0800 Subject: [PATCH 3/4] add agreement --- .github/contributors/kwhumphreys.md | 107 ++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) create mode 100644 .github/contributors/kwhumphreys.md diff --git a/.github/contributors/kwhumphreys.md b/.github/contributors/kwhumphreys.md new file mode 100644 index 000000000..0df94f407 --- /dev/null +++ b/.github/contributors/kwhumphreys.md @@ -0,0 +1,107 @@ + +# 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: + + * [ ] 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 my + contributions. + + * [x] 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 | Kevin Humphreys | +| Company name (if applicable) | Textio Inc. | +| Title or role (if applicable) | | +| Date | 01-03-2018 | +| GitHub username | kwhumphreys | +| Website (optional) | | From b236e5db97f09b685fc001abbe8131d6211851f0 Mon Sep 17 00:00:00 2001 From: Kevin Humphreys Date: Wed, 3 Jan 2018 13:00:36 -0800 Subject: [PATCH 4/4] add fork to instructions --- CONTRIBUTING.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 63dde7834..0c0ba3144 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -150,7 +150,7 @@ recipes, that does provide some argument for bringing it "in house". ### Getting started -To make changes to spaCy's code base, you need to clone the GitHub repository +To make changes to spaCy's code base, you need to fork then clone the GitHub repository and build spaCy from source. You'll need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, [pip](https://pip.pypa.io/en/latest/installing/),