From cca8651fc8133172ebaa9d9fc438ed1fbf34fb33 Mon Sep 17 00:00:00 2001 From: Boian Tzonev Date: Fri, 19 Feb 2021 20:19:19 +0200 Subject: [PATCH] Bulgarian tokenizer exceptions (#7114) * [Bulgarian] Add tokenizer exceptions and like_num for Bulgarian * [Bulgarian] Add tokenizer exceptions and like_num for Bulgarian --- .github/contributors/dardoria.md | 106 ++++++++++++++++++++++++++ spacy/lang/bg/__init__.py | 12 +++ spacy/lang/bg/lex_attrs.py | 88 +++++++++++++++++++++ spacy/lang/bg/tokenizer_exceptions.py | 68 +++++++++++++++++ spacy/tests/conftest.py | 5 ++ spacy/tests/lang/bg/test_text.py | 30 ++++++++ 6 files changed, 309 insertions(+) create mode 100644 .github/contributors/dardoria.md create mode 100644 spacy/lang/bg/lex_attrs.py create mode 100644 spacy/lang/bg/tokenizer_exceptions.py create mode 100644 spacy/tests/lang/bg/test_text.py diff --git a/.github/contributors/dardoria.md b/.github/contributors/dardoria.md new file mode 100644 index 000000000..0c7202fca --- /dev/null +++ b/.github/contributors/dardoria.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 | Boian Tzonev | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 18.02.2021 | +| GitHub username | dardoria | +| Website (optional) | | diff --git a/spacy/lang/bg/__init__.py b/spacy/lang/bg/__init__.py index a30f49ce7..6fa539a28 100644 --- a/spacy/lang/bg/__init__.py +++ b/spacy/lang/bg/__init__.py @@ -1,9 +1,21 @@ from .stop_words import STOP_WORDS +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS +from .lex_attrs import LEX_ATTRS +from ..tokenizer_exceptions import BASE_EXCEPTIONS + from ...language import Language +from ...attrs import LANG +from ...util import update_exc class BulgarianDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters[LANG] = lambda text: "bg" + + lex_attr_getters.update(LEX_ATTRS) + stop_words = STOP_WORDS + tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) class Bulgarian(Language): diff --git a/spacy/lang/bg/lex_attrs.py b/spacy/lang/bg/lex_attrs.py new file mode 100644 index 000000000..62b69d6cc --- /dev/null +++ b/spacy/lang/bg/lex_attrs.py @@ -0,0 +1,88 @@ +from ...attrs import LIKE_NUM + + +_num_words = [ + "нула", + "едно", + "един", + "една", + "две", + "три", + "четири", + "пет", + "шест", + "седем", + "осем", + "девет", + "десет", + "единадесет", + "единайсет", + "дванадесет", + "дванайсет", + "тринадесет", + "тринайсет", + "четиринадесет", + "четиринайсет" + "петнадесет", + "петнайсет" + "шестнадесет", + "шестнайсет", + "седемнадесет", + "седемнайсет" + "осемнадесет", + "осемнайсет", + "деветнадесет", + "деветнайсет", + "двадесет", + "двайсет", + "тридесет", + "трийсет" + "четиридесет", + "четиресет", + "петдесет", + "шестдесет", + "шейсет", + "седемдесет", + "осемдесет", + "деветдесет", + "сто", + "двеста", + "триста", + "четиристотин", + "петстотин", + "шестстотин", + "седемстотин", + "осемстотин", + "деветстотин", + "хиляда", + "милион", + "милиона", + "милиард", + "милиарда", + "трилион", + "трилионa", + "билион", + "билионa", + "квадрилион", + "квадрилионa", + "квинтилион", + "квинтилионa", +] + + +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 text.lower() in _num_words: + return True + return False + + +LEX_ATTRS = {LIKE_NUM: like_num} diff --git a/spacy/lang/bg/tokenizer_exceptions.py b/spacy/lang/bg/tokenizer_exceptions.py new file mode 100644 index 000000000..defa00ef7 --- /dev/null +++ b/spacy/lang/bg/tokenizer_exceptions.py @@ -0,0 +1,68 @@ +from ...symbols import ORTH, NORM + + +_exc = {} + + +_abbr_exc = [ + {ORTH: "м", NORM: "метър"}, + {ORTH: "мм", NORM: "милиметър"}, + {ORTH: "см", NORM: "сантиметър"}, + {ORTH: "дм", NORM: "дециметър"}, + {ORTH: "км", NORM: "километър"}, + {ORTH: "кг", NORM: "килограм"}, + {ORTH: "мг", NORM: "милиграм"}, + {ORTH: "г", NORM: "грам"}, + {ORTH: "т", NORM: "тон"}, + {ORTH: "хл", NORM: "хектолиър"}, + {ORTH: "дкл", NORM: "декалитър"}, + {ORTH: "л", NORM: "литър"}, +] +for abbr in _abbr_exc: + _exc[abbr[ORTH]] = [abbr] + +_abbr_line_exc = [ + {ORTH: "г-жа", NORM: "госпожа"}, + {ORTH: "г-н", NORM: "господин"}, + {ORTH: "г-ца", NORM: "госпожица"}, + {ORTH: "д-р", NORM: "доктор"}, + {ORTH: "о-в", NORM: "остров"}, + {ORTH: "п-в", NORM: "полуостров"}, +] + +for abbr in _abbr_line_exc: + _exc[abbr[ORTH]] = [abbr] + +_abbr_dot_exc = [ + {ORTH: "акад.", NORM: "академик"}, + {ORTH: "ал.", NORM: "алинея"}, + {ORTH: "арх.", NORM: "архитект"}, + {ORTH: "бл.", NORM: "блок"}, + {ORTH: "бр.", NORM: "брой"}, + {ORTH: "бул.", NORM: "булевард"}, + {ORTH: "в.", NORM: "век"}, + {ORTH: "г.", NORM: "година"}, + {ORTH: "гр.", NORM: "град"}, + {ORTH: "ж.р.", NORM: "женски род"}, + {ORTH: "инж.", NORM: "инженер"}, + {ORTH: "лв.", NORM: "лев"}, + {ORTH: "м.р.", NORM: "мъжки род"}, + {ORTH: "мат.", NORM: "математика"}, + {ORTH: "мед.", NORM: "медицина"}, + {ORTH: "пл.", NORM: "площад"}, + {ORTH: "проф.", NORM: "професор"}, + {ORTH: "с.", NORM: "село"}, + {ORTH: "с.р.", NORM: "среден род"}, + {ORTH: "св.", NORM: "свети"}, + {ORTH: "сп.", NORM: "списание"}, + {ORTH: "стр.", NORM: "страница"}, + {ORTH: "ул.", NORM: "улица"}, + {ORTH: "чл.", NORM: "член"}, + +] + +for abbr in _abbr_dot_exc: + _exc[abbr[ORTH]] = [abbr] + + +TOKENIZER_EXCEPTIONS = _exc diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 9209a840c..04e254c50 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -39,6 +39,11 @@ def ar_tokenizer(): return get_lang_class("ar")().tokenizer +@pytest.fixture(scope="session") +def bg_tokenizer(): + return get_lang_class("bg")().tokenizer + + @pytest.fixture(scope="session") def bn_tokenizer(): return get_lang_class("bn")().tokenizer diff --git a/spacy/tests/lang/bg/test_text.py b/spacy/tests/lang/bg/test_text.py new file mode 100644 index 000000000..3d35ba997 --- /dev/null +++ b/spacy/tests/lang/bg/test_text.py @@ -0,0 +1,30 @@ +import pytest +from spacy.lang.bg.lex_attrs import like_num + +@pytest.mark.parametrize( + "word,match", + [ + ("10", True), + ("1", True), + ("10000", True), + ("1.000", True), + ("бројка", False), + ("999,23", True), + ("едно", True), + ("две", True), + ("цифра", False), + ("единайсет", True), + ("десет", True), + ("сто", True), + ("брой", False), + ("хиляда", True), + ("милион", True), + (",", False), + ("милиарда", True), + ("билион", True), + ], +) +def test_bg_lex_attrs_like_number(bg_tokenizer, word, match): + tokens = bg_tokenizer(word) + assert len(tokens) == 1 + assert tokens[0].like_num == match