From 86eb817b74f13d7561b797120e6984c021ddc411 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Germ=C3=A1n?= <46906587+munozbravo@users.noreply.github.com> Date: Sun, 2 Jun 2019 05:22:57 -0500 Subject: [PATCH] Overwrites default getter for like_num in Spanish by adding _num_words and like_num to lex_attrs.py (#3810) (closes #3803)) * (#3803) Spanish like_num returning false for number-like token * (#3803) Spanish like_num now returning True for number-like token --- .github/contributors/munozbravo.md | 106 +++++++++++++++++++++++ spacy/lang/es/__init__.py | 2 + spacy/lang/es/lex_attrs.py | 59 +++++++++++++ spacy/tests/regression/test_issue3803.py | 15 ++++ 4 files changed, 182 insertions(+) create mode 100644 .github/contributors/munozbravo.md create mode 100644 spacy/lang/es/lex_attrs.py create mode 100644 spacy/tests/regression/test_issue3803.py diff --git a/.github/contributors/munozbravo.md b/.github/contributors/munozbravo.md new file mode 100644 index 000000000..b36133e1e --- /dev/null +++ b/.github/contributors/munozbravo.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 | Germán Muñoz | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-06-01 | +| GitHub username | munozbravo | +| Website (optional) | | diff --git a/spacy/lang/es/__init__.py b/spacy/lang/es/__init__.py index d5d6e4f23..d49948b30 100644 --- a/spacy/lang/es/__init__.py +++ b/spacy/lang/es/__init__.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .tag_map import TAG_MAP from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS from .lemmatizer import LOOKUP from .syntax_iterators import SYNTAX_ITERATORS @@ -16,6 +17,7 @@ from ...util import update_exc, add_lookups class SpanishDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) lex_attr_getters[LANG] = lambda text: "es" lex_attr_getters[NORM] = add_lookups( Language.Defaults.lex_attr_getters[NORM], BASE_NORMS diff --git a/spacy/lang/es/lex_attrs.py b/spacy/lang/es/lex_attrs.py new file mode 100644 index 000000000..03ada1f43 --- /dev/null +++ b/spacy/lang/es/lex_attrs.py @@ -0,0 +1,59 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + + +_num_words = [ + "cero", + "uno", + "dos", + "tres", + "cuatro", + "cinco", + "seis", + "siete", + "ocho", + "nueve", + "diez", + "once", + "doce", + "trece", + "catorce", + "quince", + "dieciséis", + "diecisiete", + "dieciocho", + "diecinueve", + "veinte", + "treinta", + "cuarenta", + "cincuenta", + "sesenta", + "setenta", + "ochenta", + "noventa", + "cien", + "mil", + "millón", + "billón", + "trillón", +] + + +def like_num(text): + if text.startswith(("+", "-", "±", "~")): + text = text[1:] + text = text.replace(",", "").replace(".", "") + if text.isdigit(): + return True + if text.count("/") == 1: + num, denom = text.split("/") + if num.isdigit() and denom.isdigit(): + return True + if text.lower() in _num_words: + return True + return False + + +LEX_ATTRS = {LIKE_NUM: like_num} diff --git a/spacy/tests/regression/test_issue3803.py b/spacy/tests/regression/test_issue3803.py new file mode 100644 index 000000000..4d9b664fa --- /dev/null +++ b/spacy/tests/regression/test_issue3803.py @@ -0,0 +1,15 @@ +# coding: utf8 +from __future__ import unicode_literals + +import pytest + +from spacy.lang.es import Spanish + + +def test_issue3803(): + """Test that spanish num-like tokens have True for like_num attribute.""" + nlp = Spanish() + text = "2 dos 1000 mil 12 doce" + doc = nlp(text) + + assert [t.like_num for t in doc] == [True, True, True, True, True, True]