From 5ad5c4b44a95a9264a3018c5f73a23639451db9a Mon Sep 17 00:00:00 2001 From: Elijah Rippeth Date: Mon, 18 Nov 2019 06:56:07 -0500 Subject: [PATCH] Add initial Korean support (#4660) * add hangul and jamo char classes. * add initial Korean lexical attributes. * add contributor agreement --- .github/contributors/erip.md | 106 +++++++++++++++++++++++++++++++++++ spacy/lang/char_classes.py | 6 +- spacy/lang/ko/lex_attrs.py | 67 ++++++++++++++++++++++ 3 files changed, 178 insertions(+), 1 deletion(-) create mode 100644 .github/contributors/erip.md create mode 100644 spacy/lang/ko/lex_attrs.py diff --git a/.github/contributors/erip.md b/.github/contributors/erip.md new file mode 100644 index 000000000..56df07338 --- /dev/null +++ b/.github/contributors/erip.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 | Elijah Rippeth | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-11-16 | +| GitHub username | erip | +| Website (optional) | | diff --git a/spacy/lang/char_classes.py b/spacy/lang/char_classes.py index 5ed2a2a8c..b28c43d63 100644 --- a/spacy/lang/char_classes.py +++ b/spacy/lang/char_classes.py @@ -31,6 +31,10 @@ _latin_u_supplement = r"\u00C0-\u00D6\u00D8-\u00DE" _latin_l_supplement = r"\u00DF-\u00F6\u00F8-\u00FF" _latin_supplement = r"\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF" +_hangul_syllables = r"\uAC00-\uD7AF" +_hangul_jamo = r"\u1100-\u11FF" +_hangul = _hangul_syllables + _hangul_jamo + # letters with diacritics - Catalan, Czech, Latin, Latvian, Lithuanian, Polish, Slovak, Turkish, Welsh _latin_u_extendedA = ( r"\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C" @@ -202,7 +206,7 @@ _upper = LATIN_UPPER + _russian_upper + _tatar_upper + _greek_upper + _ukrainian _lower = LATIN_LOWER + _russian_lower + _tatar_lower + _greek_lower + _ukrainian_lower _uncased = ( - _bengali + _hebrew + _persian + _sinhala + _hindi + _kannada + _tamil + _telugu + _bengali + _hebrew + _persian + _sinhala + _hindi + _kannada + _tamil + _telugu + _hangul ) ALPHA = group_chars(LATIN + _russian + _tatar + _greek + _ukrainian + _uncased) diff --git a/spacy/lang/ko/lex_attrs.py b/spacy/lang/ko/lex_attrs.py new file mode 100644 index 000000000..e84a8c7c4 --- /dev/null +++ b/spacy/lang/ko/lex_attrs.py @@ -0,0 +1,67 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + + +_num_words = [ + "영", + "공", + # Native Korean number system + "하나", + "둘", + "셋", + "넷", + "다섯", + "여섯", + "일곱", + "여덟", + "아홉", + "열", + "스물", + "서른", + "마흔", + "쉰", + "예순", + "일흔", + "여든", + "아흔", + # Sino-Korean number system + "일", + "이", + "삼", + "사", + "오", + "육", + "칠", + "팔", + "구", + "십", + "백", + "천", + "만", + "십만", + "백만", + "천만", + "일억", + "십억", + "백억" +] + + +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 any(char.lower() in _num_words for char in text): + return True + return False + + +LEX_ATTRS = {LIKE_NUM: like_num}