From 6eebfc7bf47214d058b9d1f5dc8a5f382932ceb9 Mon Sep 17 00:00:00 2001 From: Aashish Gangwani Date: Wed, 8 Aug 2018 19:36:11 +0530 Subject: [PATCH] Added numbers to ../lang/hi/lex_attrs.py (#2629) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I have added numbers in hindi lex_attrs.py file according to Indian numbering system(https://en.wikipedia.org/wiki/Indian_numbering_system) and here are there english translations: 'शून्य' => zero 'एक' => one 'दो' => two 'तीन' => three 'चार' => four 'पांच' => five 'छह' => six 'सात'=>seven 'आठ' => eight 'नौ' => nine 'दस' => ten 'ग्यारह' => eleven 'बारह' => twelve 'तेरह' => thirteen 'चौदह' => fourteen 'पंद्रह' => fifteen 'सोलह'=> sixteen 'सत्रह' => seventeen 'अठारह' => eighteen 'उन्नीस' => nineteen 'बीस' => twenty 'तीस' => thirty 'चालीस' => forty 'पचास' => fifty 'साठ' => sixty 'सत्तर' => seventy 'अस्सी' => eighty 'नब्बे' => ninety 'सौ' => hundred 'हज़ार' => thousand 'लाख' => hundred thousand 'करोड़' => ten million 'अरब' => billion 'खरब' => hundred billion ## Description ### Types of change ## Checklist - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. --- .github/contributors/aashishg.md | 106 +++++++++++++++++++++++++++++++ spacy/lang/hi/lex_attrs.py | 22 ++++++- 2 files changed, 127 insertions(+), 1 deletion(-) create mode 100644 .github/contributors/aashishg.md diff --git a/.github/contributors/aashishg.md b/.github/contributors/aashishg.md new file mode 100644 index 000000000..b58cf0c77 --- /dev/null +++ b/.github/contributors/aashishg.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 | Aashish Gangwani | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 7/08/2018 | +| GitHub username | aashishg | +| Website (optional) | | diff --git a/spacy/lang/hi/lex_attrs.py b/spacy/lang/hi/lex_attrs.py index 8886e26c3..bb0b4ba99 100644 --- a/spacy/lang/hi/lex_attrs.py +++ b/spacy/lang/hi/lex_attrs.py @@ -3,9 +3,9 @@ from __future__ import unicode_literals from ..norm_exceptions import BASE_NORMS from ...attrs import NORM +from ...attrs import LIKE_NUM from ...util import add_lookups - _stem_suffixes = [ ["ो","े","ू","ु","ी","ि","ा"], ["कर","ाओ","िए","ाई","ाए","ने","नी","ना","ते","ीं","ती","ता","ाँ","ां","ों","ें"], @@ -14,6 +14,13 @@ _stem_suffixes = [ ["ाएंगी","ाएंगे","ाऊंगी","ाऊंगा","ाइयाँ","ाइयों","ाइयां"] ] +#reference 1:https://en.wikipedia.org/wiki/Indian_numbering_system +#reference 2: https://blogs.transparent.com/hindi/hindi-numbers-1-100/ + +_num_words = ['शून्य', 'एक', 'दो', 'तीन', 'चार', 'पांच', 'छह', 'सात', 'आठ', 'नौ', 'दस', + 'ग्यारह', 'बारह', 'तेरह', 'चौदह', 'पंद्रह', 'सोलह', 'सत्रह', 'अठारह', 'उन्नीस', + 'बीस', 'तीस', 'चालीस', 'पचास', 'साठ', 'सत्तर', 'अस्सी', 'नब्बे', 'सौ', 'हज़ार', + 'लाख', 'करोड़', 'अरब', 'खरब'] def norm(string): # normalise base exceptions, e.g. punctuation or currency symbols @@ -32,7 +39,20 @@ def norm(string): return string[:-length] return string +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 = { NORM: norm + LIKE_NUM: like_num }