From 9a016d17c2858812cde4822da859a2f5ee7f36ba Mon Sep 17 00:00:00 2001 From: Keshan Date: Tue, 25 Sep 2018 15:48:25 +0530 Subject: [PATCH] Adding basic support for Sinhala language. (#2788) * adding Sinhala language package, stop words, examples and lex_attrs. * Adding contributor agreement * Updating contributor agreement --- .github/contributors/keshan.md | 106 +++++++++++++++++++++++++++++++++ spacy/lang/char_classes.py | 3 +- spacy/lang/si/__init__.py | 23 +++++++ spacy/lang/si/examples.py | 22 +++++++ spacy/lang/si/lex_attrs.py | 28 +++++++++ spacy/lang/si/stop_words.py | 51 ++++++++++++++++ 6 files changed, 232 insertions(+), 1 deletion(-) create mode 100644 .github/contributors/keshan.md create mode 100644 spacy/lang/si/__init__.py create mode 100644 spacy/lang/si/examples.py create mode 100644 spacy/lang/si/lex_attrs.py create mode 100644 spacy/lang/si/stop_words.py diff --git a/.github/contributors/keshan.md b/.github/contributors/keshan.md new file mode 100644 index 000000000..96b5d89ec --- /dev/null +++ b/.github/contributors/keshan.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 | Keshan Sodimana | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | Sep 21, 2018 | +| GitHub username | keshan | +| Website (optional) | | diff --git a/spacy/lang/char_classes.py b/spacy/lang/char_classes.py index d62eef723..db4624909 100644 --- a/spacy/lang/char_classes.py +++ b/spacy/lang/char_classes.py @@ -16,6 +16,7 @@ _latin = r'[[\p{Ll}||\p{Lu}]&&\p{Latin}]' _persian = r'[\p{L}&&\p{Arabic}]' _russian_lower = r'[ёа-я]' _russian_upper = r'[ЁА-Я]' +_sinhala = r'[\p{L}&&\p{Sinhala}]' _tatar_lower = r'[әөүҗңһ]' _tatar_upper = r'[ӘӨҮҖҢҺ]' _greek_lower = r'[α-ωάέίόώήύ]' @@ -23,7 +24,7 @@ _greek_upper = r'[Α-ΩΆΈΊΌΏΉΎ]' _upper = [_latin_upper, _russian_upper, _tatar_upper, _greek_upper] _lower = [_latin_lower, _russian_lower, _tatar_lower, _greek_lower] -_uncased = [_bengali, _hebrew, _persian] +_uncased = [_bengali, _hebrew, _persian, _sinhala] ALPHA = merge_char_classes(_upper + _lower + _uncased) ALPHA_LOWER = merge_char_classes(_lower + _uncased) diff --git a/spacy/lang/si/__init__.py b/spacy/lang/si/__init__.py new file mode 100644 index 000000000..22d07f5dc --- /dev/null +++ b/spacy/lang/si/__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 SinhalaDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) + lex_attr_getters[LANG] = lambda text: 'si' + stop_words = STOP_WORDS + + +class Sinhala(Language): + lang = 'si' + Defaults = SinhalaDefaults + + +__all__ = ['Sinhala'] diff --git a/spacy/lang/si/examples.py b/spacy/lang/si/examples.py new file mode 100644 index 000000000..68862d3cf --- /dev/null +++ b/spacy/lang/si/examples.py @@ -0,0 +1,22 @@ +# coding: utf8 +from __future__ import unicode_literals + + +""" +Example sentences to test spaCy and its language models. + +>>> from spacy.lang.si.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "ඔබ කවුද?", + "ගූගල් සමාගම ඩොලර් මිලියන 500 කට එම ආයතනය මිලදී ගන්නා ලදී.", + "කොළඹ ශ්‍රී ලංකාවේ ප්‍රධානතම නගරය යි.", + "ප්‍රංශයේ ජනාධිපති කවරෙක් ද?", + "මට බිස්කට් 1 ක් දෙන්න", + "ඔවුන් ලකුණු 59 කින් තරඟය පරාජයට පත් විය.", + "1 ත් 10 ත් අතර සංඛ්‍යාවක් කියන්න", + "ඔහු සහ ඇය නුවර හෝ කොළඹ පදිංචි කරුවන් නොවේ", +] diff --git a/spacy/lang/si/lex_attrs.py b/spacy/lang/si/lex_attrs.py new file mode 100644 index 000000000..4c4e1ef06 --- /dev/null +++ b/spacy/lang/si/lex_attrs.py @@ -0,0 +1,28 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + +_num_words = ['බින්දුව', 'බිංදුව', 'එක', 'දෙක', 'තුන', 'හතර', 'පහ', 'හය', 'හත', + 'අට', 'නවය', 'නමය', 'දහය', 'එකොළහ', 'දොළහ', 'දහතුන', 'දහහතර', + 'දාහතර', 'පහළව', 'පහළොව', 'දහසය', 'දහහත', 'දාහත', 'දහඅට', + 'දහනවය', 'විස්ස', 'තිහ', 'හතළිහ', 'පනහ', 'හැට', 'හැත්තෑව', 'අසූව', + 'අනූව', 'සියය', 'දහස', 'දාහ', 'ලක්ෂය', 'මිලියනය', 'කෝටිය', + 'බිලියනය', 'ට්‍රිලියනය'] + +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/si/stop_words.py b/spacy/lang/si/stop_words.py new file mode 100644 index 000000000..a3473f0a1 --- /dev/null +++ b/spacy/lang/si/stop_words.py @@ -0,0 +1,51 @@ +# coding: utf8 +from __future__ import unicode_literals + + +# Stop words + +STOP_WORDS = set(""" +අතර +එච්චර +එපමණ +එලෙස +එවිට +ඒ +කට +කදී +කින් +ක් +ට +තුර +ත් +ද +නමුත් +නොහොත් +පමණ +පමණි +ම +මෙච්චර +මෙපමණ +මෙලෙස +මෙවිට +මේ +ය +යි +ලදී +ලෙස +වගේ +වන +විට +විටෙක +විතර +විය +වුව +වුවත් +වුවද +වූ +සමඟ +සහ +හා +හෙවත් +හෝ +""".split())