From 9fa9d7f2cb52ce6a70c264d4e57c7f190d7686bf Mon Sep 17 00:00:00 2001 From: Tyler Couto Date: Mon, 3 Feb 2020 06:01:48 -0600 Subject: [PATCH] Fix for Issue 4665 - conllu2json (#4953) * Fix for Issue 4665 - conllu2json - Allowing HEAD to be an underscore * Added contributor agreement --- .github/contributors/onlyanegg.md | 106 +++++++++++++++++++++++ spacy/cli/converters/conllu2json.py | 2 +- spacy/tests/regression/test_issue4665.py | 31 +++++++ 3 files changed, 138 insertions(+), 1 deletion(-) create mode 100644 .github/contributors/onlyanegg.md create mode 100644 spacy/tests/regression/test_issue4665.py diff --git a/.github/contributors/onlyanegg.md b/.github/contributors/onlyanegg.md new file mode 100644 index 000000000..eb1ac01a6 --- /dev/null +++ b/.github/contributors/onlyanegg.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 | Tyler Couto | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | January 29, 2020 | +| GitHub username | onlyanegg | +| Website (optional) | | diff --git a/spacy/cli/converters/conllu2json.py b/spacy/cli/converters/conllu2json.py index e66a8c50e..3de4dcc30 100644 --- a/spacy/cli/converters/conllu2json.py +++ b/spacy/cli/converters/conllu2json.py @@ -70,7 +70,7 @@ def read_conllx(input_data, use_morphology=False, n=0): continue try: id_ = int(id_) - 1 - head = (int(head) - 1) if head != "0" else id_ + head = (int(head) - 1) if head not in ["0", "_"] else id_ dep = "ROOT" if dep == "root" else dep tag = pos if tag == "_" else tag tag = tag + "__" + morph if use_morphology else tag diff --git a/spacy/tests/regression/test_issue4665.py b/spacy/tests/regression/test_issue4665.py new file mode 100644 index 000000000..721ec0098 --- /dev/null +++ b/spacy/tests/regression/test_issue4665.py @@ -0,0 +1,31 @@ +from spacy.cli.converters.conllu2json import conllu2json + +input_data = """ +1 [ _ PUNCT -LRB- _ _ punct _ _ +2 This _ DET DT _ _ det _ _ +3 killing _ NOUN NN _ _ nsubj _ _ +4 of _ ADP IN _ _ case _ _ +5 a _ DET DT _ _ det _ _ +6 respected _ ADJ JJ _ _ amod _ _ +7 cleric _ NOUN NN _ _ nmod _ _ +8 will _ AUX MD _ _ aux _ _ +9 be _ AUX VB _ _ aux _ _ +10 causing _ VERB VBG _ _ root _ _ +11 us _ PRON PRP _ _ iobj _ _ +12 trouble _ NOUN NN _ _ dobj _ _ +13 for _ ADP IN _ _ case _ _ +14 years _ NOUN NNS _ _ nmod _ _ +15 to _ PART TO _ _ mark _ _ +16 come _ VERB VB _ _ acl _ _ +17 . _ PUNCT . _ _ punct _ _ +18 ] _ PUNCT -RRB- _ _ punct _ _ +""" + + +def test_issue4665(): + """ + conllu2json should not raise an exception if the HEAD column contains an + underscore + """ + + conllu2json(input_data)