From d77361d76c599705ec74c3e0fdd45214676c78e7 Mon Sep 17 00:00:00 2001 From: Bri-Will Date: Mon, 11 Dec 2017 14:13:28 -0800 Subject: [PATCH 1/4] Update lex_attrs.py. Fix like_url from matching on e-mail --- spacy/lang/lex_attrs.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/spacy/lang/lex_attrs.py b/spacy/lang/lex_attrs.py index f0363b05f..8a1bc2b50 100644 --- a/spacy/lang/lex_attrs.py +++ b/spacy/lang/lex_attrs.py @@ -82,6 +82,8 @@ def like_url(text): return True if text[0] == '.' or text[-1] == '.': return False + if '@' in text: #prevent matches on e-mail addresses + return False for i in range(len(text)): if text[i] == '.': break From afd9fc9d3626bbe0ac2dfcb5cdbf8f2c71b23b60 Mon Sep 17 00:00:00 2001 From: Bri-Will Date: Mon, 11 Dec 2017 14:38:37 -0800 Subject: [PATCH 2/4] Adds contributor agreement for Bri-Will --- .github/contributors/Bri-Will.md | 106 +++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/Bri-Will.md diff --git a/.github/contributors/Bri-Will.md b/.github/contributors/Bri-Will.md new file mode 100644 index 000000000..66bcd1e11 --- /dev/null +++ b/.github/contributors/Bri-Will.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 | Brian Williams | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 12/11/2017 | +| GitHub username | Bri-Will | +| Website (optional) | | \ No newline at end of file From 6455b574fc91bbe2605921544f1bbc3a6a5883af Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Tue, 12 Dec 2017 10:25:13 +0100 Subject: [PATCH 3/4] Check for email address first --- spacy/lang/lex_attrs.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/spacy/lang/lex_attrs.py b/spacy/lang/lex_attrs.py index 8a1bc2b50..0a671ab1d 100644 --- a/spacy/lang/lex_attrs.py +++ b/spacy/lang/lex_attrs.py @@ -74,6 +74,8 @@ def like_email(text): def like_url(text): + if '@' in text: # prevent matches on e-mail addresses + return False # We're looking for things that function in text like URLs. So, valid URL # or not, anything they say http:// is going to be good. if text.startswith('http://') or text.startswith('https://'): @@ -82,8 +84,6 @@ def like_url(text): return True if text[0] == '.' or text[-1] == '.': return False - if '@' in text: #prevent matches on e-mail addresses - return False for i in range(len(text)): if text[i] == '.': break From 9c1ee652684fec9dc3b9ed487bfd980e886ec9fc Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Tue, 12 Dec 2017 10:36:11 +0100 Subject: [PATCH 4/4] Add regression test for #1698 --- spacy/tests/regression/test_issue1698.py | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 spacy/tests/regression/test_issue1698.py diff --git a/spacy/tests/regression/test_issue1698.py b/spacy/tests/regression/test_issue1698.py new file mode 100644 index 000000000..fa25cbdd5 --- /dev/null +++ b/spacy/tests/regression/test_issue1698.py @@ -0,0 +1,11 @@ +# coding: utf8 +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.parametrize('text', ['test@example.com', 'john.doe@example.co.uk']) +def test_issue1698(en_tokenizer, text): + doc = en_tokenizer(text) + assert len(doc) == 1 + assert not doc[0].like_url