From 49aed683cce4d58baca10e7cb4fe89fbfc209a36 Mon Sep 17 00:00:00 2001 From: Sevdimali Date: Wed, 28 Apr 2021 16:42:02 +0400 Subject: [PATCH] Azerbaijani language added (#7911) --- .github/contributors/sevdimali.md | 106 ++++++++++++++++++++++ spacy/lang/az/__init__.py | 21 +++++ spacy/lang/az/examples.py | 18 ++++ spacy/lang/az/lex_attrs.py | 89 ++++++++++++++++++ spacy/lang/az/stop_words.py | 145 ++++++++++++++++++++++++++++++ 5 files changed, 379 insertions(+) create mode 100644 .github/contributors/sevdimali.md create mode 100644 spacy/lang/az/__init__.py create mode 100644 spacy/lang/az/examples.py create mode 100644 spacy/lang/az/lex_attrs.py create mode 100644 spacy/lang/az/stop_words.py diff --git a/.github/contributors/sevdimali.md b/.github/contributors/sevdimali.md new file mode 100644 index 000000000..6b96abdf8 --- /dev/null +++ b/.github/contributors/sevdimali.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 | Sevdimali | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 10/4/2021 | +| GitHub username | sevdimali | +| Website (optional) | https://sevdimali.me | diff --git a/spacy/lang/az/__init__.py b/spacy/lang/az/__init__.py new file mode 100644 index 000000000..6a4288d1e --- /dev/null +++ b/spacy/lang/az/__init__.py @@ -0,0 +1,21 @@ +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH +from .stop_words import STOP_WORDS +from .syntax_iterators import SYNTAX_ITERATORS +from .lex_attrs import LEX_ATTRS +from ...language import Language + + +class AzerbaijaniDefaults(Language.Defaults): + tokenizer_exceptions = TOKENIZER_EXCEPTIONS + lex_attr_getters = LEX_ATTRS + stop_words = STOP_WORDS + token_match = TOKEN_MATCH + syntax_iterators = SYNTAX_ITERATORS + + +class Azerbaijani(Language): + lang = "az" + Defaults = AzerbaijaniDefaults + + +__all__ = ["Azerbaijani"] diff --git a/spacy/lang/az/examples.py b/spacy/lang/az/examples.py new file mode 100644 index 000000000..f3331a8cb --- /dev/null +++ b/spacy/lang/az/examples.py @@ -0,0 +1,18 @@ +""" +Example sentences to test spaCy and its language models. +>>> from spacy.lang.az.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "Bu bir cümlədir.", + "Necəsən?", + "Qarabağ ordeni vətən müharibəsində qələbə münasibəti ilə təsis edilmişdir.", + "Məktəbimizə Bakıdan bir tarix müəllimi gəlmişdi.", + "Atılan növbəti mərmilər lap yaxınlıqda partladı.", + "Sinqapur koronavirus baxımından ən təhlükəsiz ölkələr sırasındadır.", + "Marsda ilk sınaq uçuşu həyata keçirilib.", + "SSRİ dağılandan bəri 5 sahil dövləti Xəzərin statusunu müəyyən edə bilməyiblər.", + "Videoda beyninə xüsusi çip yerləşdirilmiş meymun əks olunub.", +] diff --git a/spacy/lang/az/lex_attrs.py b/spacy/lang/az/lex_attrs.py new file mode 100644 index 000000000..73a5e2762 --- /dev/null +++ b/spacy/lang/az/lex_attrs.py @@ -0,0 +1,89 @@ +from ...attrs import LIKE_NUM + + +# Eleven, twelve etc. are written separate: on bir, on iki + +_num_words = [ + "bir", + "iki", + "üç", + "dörd", + "beş", + "altı", + "yeddi", + "səkkiz", + "doqquz", + "on", + "iyirmi", + "otuz", + "qırx", + "əlli", + "altmış", + "yetmiş", + "səksən", + "doxsan", + "yüz", + "min", + "milyon", + "milyard", + "trilyon", + "kvadrilyon", + "kentilyon", +] + + +_ordinal_words = [ + "birinci", + "ikinci", + "üçüncü", + "dördüncü", + "beşinci", + "altıncı", + "yedinci", + "səkkizinci", + "doqquzuncu", + "onuncu", + "iyirminci", + "otuzuncu", + "qırxıncı", + "əllinci", + "altmışıncı", + "yetmişinci", + "səksəninci", + "doxsanıncı", + "yüzüncü", + "mininci", + "milyonuncu", + "milyardıncı", + "trilyonuncu", + "kvadrilyonuncu", + "kentilyonuncu", +] + +_ordinal_endings = ("inci", "ıncı", "nci", "ncı", "uncu", "üncü") + + +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 + text_lower = text.lower() + # Check cardinal number + if text_lower in _num_words: + return True + # Check ordinal number + if text_lower in _ordinal_words: + return True + if text_lower.endswith(_ordinal_endings): + if text_lower[:-3].isdigit() or text_lower[:-4].isdigit(): + return True + return False + + +LEX_ATTRS = {LIKE_NUM: like_num} diff --git a/spacy/lang/az/stop_words.py b/spacy/lang/az/stop_words.py new file mode 100644 index 000000000..2114939ba --- /dev/null +++ b/spacy/lang/az/stop_words.py @@ -0,0 +1,145 @@ +# Source: https://github.com/eliasdabbas/advertools/blob/master/advertools/stopwords.py +STOP_WORDS = set( + """ +amma +arasında +artıq +ay +az +bax +belə +beş +bilər +bir +biraz +biri +birşey +biz +bizim +bizlər +bu +buna +bundan +bunların +bunu +bunun +buradan +bütün +bəli +bəlkə +bəy +bəzi +bəzən +daha +dedi +deyil +dir +düz +də +dək +dən +dəqiqə +edir +edən +elə +et +etdi +etmə +etmək +faiz +gilə +görə +ha +haqqında +harada +heç +hə +həm +həmin +həmişə +hər +idi +il +ildə +ilk +ilə +in +indi +istifadə +isə +ki +kim +kimi +kimə +lakin +lap +mirşey +məhz +mən +mənə +niyə +nə +nəhayət +o +obirisi +of +olan +olar +olaraq +oldu +olduğu +olmadı +olmaz +olmuşdur +olsun +olur +on +ona +ondan +onlar +onlardan +onların +onsuzda +onu +onun +oradan +qarşı +qədər +saat +sadəcə +saniyə +siz +sizin +sizlər +sonra +səhv +sən +sənin +sənə +təəssüf +var +və +xan +xanım +xeyr +ya +yalnız +yaxşı +yeddi +yenə +yox +yoxdur +yoxsa +yəni +zaman +çox +çünki +öz +özü +üçün +əgər +əlbəttə +ən +əslində +""".split() +)