From 3834f4146d85b35ccc5d6d6e705d62f746900f37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Emil=20Stenstr=C3=B6m?= Date: Tue, 7 Aug 2018 13:53:17 +0200 Subject: [PATCH] Add abbreviations from UD_Swedish-Talbanken (#2613) * Add abbreviations from UD_Swedish-Talbanken * Add contributor agreement. --- .github/contributors/EmilStenstrom.md | 106 ++++++++++++++++++++++++++ spacy/lang/sv/tokenizer_exceptions.py | 21 +++-- 2 files changed, 119 insertions(+), 8 deletions(-) create mode 100644 .github/contributors/EmilStenstrom.md diff --git a/.github/contributors/EmilStenstrom.md b/.github/contributors/EmilStenstrom.md new file mode 100644 index 000000000..473639445 --- /dev/null +++ b/.github/contributors/EmilStenstrom.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 | Emil Stenström | +| Company name (if applicable) | - | +| Title or role (if applicable) | - | +| Date | 2018-07-28 | +| GitHub username | EmilStenstrom | +| Website (optional) | https://friendlybit.com | diff --git a/spacy/lang/sv/tokenizer_exceptions.py b/spacy/lang/sv/tokenizer_exceptions.py index aa03e61cb..444a04c4a 100644 --- a/spacy/lang/sv/tokenizer_exceptions.py +++ b/spacy/lang/sv/tokenizer_exceptions.py @@ -1,8 +1,7 @@ # coding: utf8 from __future__ import unicode_literals -from ...symbols import ORTH, LEMMA, TAG, NORM, PRON_LEMMA, PUNCT - +from ...symbols import LEMMA, NORM, ORTH, PRON_LEMMA, PUNCT, TAG _exc = {} @@ -70,12 +69,18 @@ for exc_data in [ _exc[exc_data[ORTH]] = [exc_data] -for orth in [ - "ang.", "anm.", "bil.", "bl.a.", "dvs.", "e.Kr.", "el.", "e.d.", "eng.", - "etc.", "exkl.", "f.d.", "fid.", "f.Kr.", "forts.", "fr.o.m.", "f.ö.", - "förf.", "inkl.", "jur.", "kl.", "kr.", "lat.", "m.a.o.", "max.", "m.fl.", - "min.", "m.m.", "obs.", "o.d.", "osv.", "p.g.a.", "ref.", "resp.", "s.a.s.", - "s.k.", "st.", "s:t", "t.ex.", "t.o.m.", "ung.", "äv.", "övers."]: +ABBREVIATIONS = [ + "ang", "anm", "bil", "bl.a", "d.v.s", "doc", "dvs", "e.d", "e.kr", "el", + "eng", "etc", "exkl", "f", "f.d", "f.kr", "f.n", "f.ö", "fid", "fig", + "forts", "fr.o.m", "förf", "inkl", "jur", "kap", "kl", "kor", "kr", + "kungl", "lat", "m.a.o", "m.fl", "m.m", "max", "milj", "min", "mos", + "mt", "o.d", "o.s.v", "obs", "osv", "p.g.a", "proc", "prof", "ref", + "resp", "s.a.s", "s.k", "s.t", "sid", "s:t", "t.ex", "t.h", "t.o.m", "t.v", + "tel", "ung", "vol", "äv", "övers" +] +ABBREVIATIONS = [abbr + "." for abbr in ABBREVIATIONS] + ABBREVIATIONS + +for orth in ABBREVIATIONS: _exc[orth] = [{ORTH: orth}] # Sentences ending in "i." (as in "... peka i."), "m." (as in "...än 2000 m."),