diff --git a/.github/contributors/azarezade.md b/.github/contributors/azarezade.md new file mode 100644 index 000000000..4d33fab60 --- /dev/null +++ b/.github/contributors/azarezade.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 | Ali Zarezade | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2018-01-23 | +| GitHub username | azarezade | +| Website (optional) | azarezade.github.io | diff --git a/spacy/lang/char_classes.py b/spacy/lang/char_classes.py index 68d8eecc7..e76ae89d3 100644 --- a/spacy/lang/char_classes.py +++ b/spacy/lang/char_classes.py @@ -15,12 +15,13 @@ _hebrew = r'[\p{L}&&\p{Hebrew}]' _latin_lower = r'[\p{Ll}&&\p{Latin}]' _latin_upper = r'[\p{Lu}&&\p{Latin}]' _latin = r'[[\p{Ll}||\p{Lu}]&&\p{Latin}]' +_persian = r'[\p{L}&&\p{Arabic}]' _russian_lower = r'[ёа-я]' _russian_upper = r'[ЁА-Я]' _upper = [_latin_upper, _russian_upper] _lower = [_latin_lower, _russian_lower] -_uncased = [_bengali, _hebrew] +_uncased = [_bengali, _hebrew, _persian] ALPHA = merge_char_classes(_upper + _lower + _uncased) ALPHA_LOWER = merge_char_classes(_lower + _uncased) @@ -31,12 +32,12 @@ _units = ('km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm 'kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb ' 'TB T G M K % км км² км³ м м² м³ дм дм² дм³ см см² см³ мм мм² мм³ нм ' 'кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тб') -_currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$ ₽' +_currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$ ₽ ﷼' # These expressions contain various unicode variations, including characters # used in Chinese (see #1333, #1340, #1351) – unless there are cross-language # conflicts, spaCy's base tokenizer should handle all of those by default -_punct = r'… …… , : ; \! \? ¿ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ? ! , 、 ; : ~ · ।' +_punct = r'… …… , : ; \! \? ¿ ؟ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ? ! , 、 ; : ~ · । ، ؛ ٪' _quotes = r'\' \'\' " ” “ `` ` ‘ ´ ‘‘ ’’ ‚ , „ » « 「 」 『 』 ( ) 〔 〕 【 】 《 》 〈 〉' _hyphens = '- – — -- --- —— ~'