From 433748e8674f54d0b20b10b49e141d61c4f1e760 Mon Sep 17 00:00:00 2001 From: Christoph Purschke Date: Fri, 15 Nov 2019 16:16:47 +0100 Subject: [PATCH] Fix basic language support for Luxembourgish (by adding punctuation.py) (#4648) * Update __init__.py * Create punctuation.py * Update tokenizer_exceptions.py * Create questoph.md * Update questoph.md * Update test_text.py * Update test_text.py * Update test_text.py * Update test_text.py --- .github/contributors/questoph.md | 106 ++++++++++++++++++++++++++ spacy/lang/lb/__init__.py | 2 + spacy/lang/lb/punctuation.py | 16 ++++ spacy/lang/lb/tokenizer_exceptions.py | 20 +---- spacy/tests/lang/lb/test_text.py | 12 +-- 5 files changed, 127 insertions(+), 29 deletions(-) create mode 100644 .github/contributors/questoph.md create mode 100644 spacy/lang/lb/punctuation.py diff --git a/.github/contributors/questoph.md b/.github/contributors/questoph.md new file mode 100644 index 000000000..24559c098 --- /dev/null +++ b/.github/contributors/questoph.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 | Christoph Purschke | +| Company name (if applicable) | University of Luxembourg | +| Title or role (if applicable) | | +| Date | 14/11/2019 | +| GitHub username | questoph | +| Website (optional) | https://purschke.info | diff --git a/spacy/lang/lb/__init__.py b/spacy/lang/lb/__init__.py index 87058bdea..4fcfaddb4 100644 --- a/spacy/lang/lb/__init__.py +++ b/spacy/lang/lb/__init__.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .norm_exceptions import NORM_EXCEPTIONS +from .punctuation import TOKENIZER_INFIXES from .lex_attrs import LEX_ATTRS from .tag_map import TAG_MAP from .stop_words import STOP_WORDS @@ -24,6 +25,7 @@ class LuxembourgishDefaults(Language.Defaults): tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) stop_words = STOP_WORDS tag_map = TAG_MAP + infixes = TOKENIZER_INFIXES class Luxembourgish(Language): diff --git a/spacy/lang/lb/punctuation.py b/spacy/lang/lb/punctuation.py new file mode 100644 index 000000000..7c155c7e5 --- /dev/null +++ b/spacy/lang/lb/punctuation.py @@ -0,0 +1,16 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ..punctuation import TOKENIZER_INFIXES +from ..char_classes import ALPHA + + +ELISION = " ' ’ ".strip().replace(" ", "").replace("\n", "") +HYPHENS = r"- – — ‐ ‑".strip().replace(" ", "").replace("\n", "") + + +_infixes = TOKENIZER_INFIXES + [ + r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION) +] + +TOKENIZER_INFIXES = _infixes diff --git a/spacy/lang/lb/tokenizer_exceptions.py b/spacy/lang/lb/tokenizer_exceptions.py index adff9da36..18b58f2b1 100644 --- a/spacy/lang/lb/tokenizer_exceptions.py +++ b/spacy/lang/lb/tokenizer_exceptions.py @@ -2,31 +2,15 @@ from __future__ import unicode_literals from ...symbols import ORTH, LEMMA, NORM -from ..punctuation import TOKENIZER_PREFIXES # TODO -# tokenize cliticised definite article "d'" as token of its own: d'Kanner > [d'] [Kanner] # treat other apostrophes within words as part of the word: [op d'mannst], [fir d'éischt] (= exceptions) -# how to write the tokenisation exeption for the articles d' / D' ? This one is not working. -_prefixes = [ - prefix for prefix in TOKENIZER_PREFIXES if prefix not in ["d'", "D'", "d’", "D’"] -] - - _exc = { - "d'mannst": [ - {ORTH: "d'", LEMMA: "d'"}, - {ORTH: "mannst", LEMMA: "mann", NORM: "mann"}, - ], - "d'éischt": [ - {ORTH: "d'", LEMMA: "d'"}, - {ORTH: "éischt", LEMMA: "éischt", NORM: "éischt"}, - ], + } # translate / delete what is not necessary -# what does PRON_LEMMA mean? for exc_data in [ {ORTH: "wgl.", LEMMA: "wann ech gelift", NORM: "wann ech gelieft"}, {ORTH: "M.", LEMMA: "Monsieur", NORM: "Monsieur"}, @@ -64,6 +48,4 @@ for orth in [ ]: _exc[orth] = [{ORTH: orth}] - -TOKENIZER_PREFIXES = _prefixes TOKENIZER_EXCEPTIONS = _exc diff --git a/spacy/tests/lang/lb/test_text.py b/spacy/tests/lang/lb/test_text.py index 10cb16a41..387cf448d 100644 --- a/spacy/tests/lang/lb/test_text.py +++ b/spacy/tests/lang/lb/test_text.py @@ -5,18 +5,10 @@ import pytest def test_lb_tokenizer_handles_long_text(lb_tokenizer): - text = """Den Nordwand an d'Sonn - -An der Zäit hunn sech den Nordwand an d’Sonn gestridden, wie vun hinnen zwee wuel méi staark wier, wéi e Wanderer, deen an ee waarme Mantel agepak war, iwwert de Wee koum. Si goufen sech eens, dass deejéinege fir de Stäerkste gëlle sollt, deen de Wanderer forcéiere géif, säi Mantel auszedoen.", - -Den Nordwand huet mat aller Force geblosen, awer wat e méi geblosen huet, wat de Wanderer sech méi a säi Mantel agewéckelt huet. Um Enn huet den Nordwand säi Kampf opginn. - -Dunn huet d’Sonn d’Loft mat hire frëndleche Strale gewiermt, a schonn no kuerzer Zäit huet de Wanderer säi Mantel ausgedoen. - -Do huet den Nordwand missen zouginn, dass d’Sonn vun hinnen zwee de Stäerkste wier.""" + text = """Den Nordwand an d'Sonn An der Zäit hunn sech den Nordwand an d'Sonn gestridden, wie vun hinnen zwee wuel méi staark wier, wéi e Wanderer, deen an ee waarme Mantel agepak war, iwwert de Wee koum. Si goufen sech eens, dass deejéinege fir de Stäerkste gëlle sollt, deen de Wanderer forcéiere géif, säi Mantel auszedoen. Den Nordwand huet mat aller Force geblosen, awer wat e méi geblosen huet, wat de Wanderer sech méi a säi Mantel agewéckelt huet. Um Enn huet den Nordwand säi Kampf opginn. Dunn huet d'Sonn d'Loft mat hire frëndleche Strale gewiermt, a schonn no kuerzer Zäit huet de Wanderer säi Mantel ausgedoen. Do huet den Nordwand missen zouginn, dass d'Sonn vun hinnen zwee de Stäerkste wier.""" tokens = lb_tokenizer(text) - assert len(tokens) == 143 + assert len(tokens) == 142 @pytest.mark.parametrize(