From 77139bc03cd2405f57b491b24f4ce8be2e8d1077 Mon Sep 17 00:00:00 2001 From: Sainath Adapa Date: Mon, 10 Sep 2018 11:53:18 +0200 Subject: [PATCH] Basic support for Telugu language (#2751) --- .github/contributors/sainathadapa.md | 106 +++++++++++++++++++++++++++ spacy/lang/te/__init__.py | 23 ++++++ spacy/lang/te/examples.py | 24 ++++++ spacy/lang/te/lex_attrs.py | 28 +++++++ spacy/lang/te/stop_words.py | 57 ++++++++++++++ 5 files changed, 238 insertions(+) create mode 100644 .github/contributors/sainathadapa.md create mode 100644 spacy/lang/te/__init__.py create mode 100644 spacy/lang/te/examples.py create mode 100644 spacy/lang/te/lex_attrs.py create mode 100644 spacy/lang/te/stop_words.py diff --git a/.github/contributors/sainathadapa.md b/.github/contributors/sainathadapa.md new file mode 100644 index 000000000..0b40775c6 --- /dev/null +++ b/.github/contributors/sainathadapa.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 | Sainath Adapa | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2018-09-06 | +| GitHub username | sainathadapa | +| Website (optional) | | diff --git a/spacy/lang/te/__init__.py b/spacy/lang/te/__init__.py new file mode 100644 index 000000000..b1526c076 --- /dev/null +++ b/spacy/lang/te/__init__.py @@ -0,0 +1,23 @@ +# coding: utf8 +from __future__ import unicode_literals + +from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS + +from ...language import Language +from ...attrs import LANG + + +class TeluguDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) + lex_attr_getters[LANG] = lambda text: 'te' + stop_words = STOP_WORDS + + +class Telugu(Language): + lang = 'te' + Defaults = TeluguDefaults + + +__all__ = ['Telugu'] diff --git a/spacy/lang/te/examples.py b/spacy/lang/te/examples.py new file mode 100644 index 000000000..f449d681a --- /dev/null +++ b/spacy/lang/te/examples.py @@ -0,0 +1,24 @@ +# coding: utf8 +from __future__ import unicode_literals + + +""" +Example sentences to test spaCy and its language models. + +>>> from spacy.lang.te import Telugu +>>> nlp = Telugu() +>>> from spacy.lang.te.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "ఆపిల్ 1 బిలియన్ డాలర్స్ కి యూ.కె. స్టార్ట్అప్ ని కొనాలని అనుకుంటుంది.", + "ఆటోనోమోస్ కార్లు భీమా బాధ్యతను తయారీదారులపైకి మళ్లిస్తాయి.", + "సాన్ ఫ్రాన్సిస్కో కాలిబాట డెలివరీ రోబోట్లను నిషేధించడానికి ఆలోచిస్తుంది.", + "లండన్ యునైటెడ్ కింగ్డమ్ లో పెద్ద సిటీ.", + "నువ్వు ఎక్కడ ఉన్నావ్?", + "ఫ్రాన్స్ అధ్యక్షుడు ఎవరు?", + "యునైటెడ్ స్టేట్స్ యొక్క రాజధాని ఏంటి?", + "బరాక్ ఒబామా ఎప్పుడు జన్మించారు?" +] diff --git a/spacy/lang/te/lex_attrs.py b/spacy/lang/te/lex_attrs.py new file mode 100644 index 000000000..f9218b70a --- /dev/null +++ b/spacy/lang/te/lex_attrs.py @@ -0,0 +1,28 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + +_num_words = ['సున్నా', 'శూన్యం', 'ఒకటి', 'రెండు', 'మూడు', 'నాలుగు', 'ఐదు', 'ఆరు', + 'ఏడు', 'ఎనిమిది', 'తొమ్మిది', 'పది', 'పదకొండు', 'పన్నెండు', 'పదమూడు', + 'పద్నాలుగు', 'పదిహేను', 'పదహారు', 'పదిహేడు', 'పద్దెనిమిది', 'పందొమ్మిది', 'ఇరవై', + 'ముప్పై', 'నలభై', 'యాభై', 'అరవై', 'డెబ్బై', 'ఎనభై', 'తొంబై', 'వంద', 'నూరు', + 'వెయ్యి', 'లక్ష', 'కోటి'] + + +def like_num(text): + 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/lang/te/stop_words.py b/spacy/lang/te/stop_words.py new file mode 100644 index 000000000..f951a03b4 --- /dev/null +++ b/spacy/lang/te/stop_words.py @@ -0,0 +1,57 @@ +# coding: utf8 +from __future__ import unicode_literals + +# Source: https://github.com/Xangis/extra-stopwords (MIT License) + +STOP_WORDS = set(""" +అందరూ +అందుబాటులో +అడగండి +అడగడం +అడ్డంగా +అనుగుణంగా +అనుమతించు +అనుమతిస్తుంది +అయితే +ఇప్పటికే +ఉన్నారు +ఎక్కడైనా +ఎప్పుడు +ఎవరైనా +ఎవరో ఒకరు +ఏ +ఏదైనా +ఏమైనప్పటికి +ఏమైనప్పటికి +ఒక +ఒక ప్రక్కన +కనిపిస్తాయి +కాదు +కాదు +కూడా +గా +గురించి +చుట్టూ +చేయగలిగింది +తగిన +తర్వాత +తర్వాత +దాదాపు +దూరంగా +నిజంగా +పై +ప్రకారం +మధ్య +మధ్య +మరియు +మరొక +మళ్ళీ +మాత్రమే +మెచ్చుకో +వద్ద +వద్ద +వెంట +వేరుగా +వ్యతిరేకంగా +సంబంధం +""".split())