From 3b53617a69287c45284d0aedc4c7fefcaa631662 Mon Sep 17 00:00:00 2001 From: Baciccin Date: Thu, 19 Mar 2020 21:20:17 -0700 Subject: [PATCH] Add Ligurian language --- .github/contributors/Baciccin.md | 106 +++++++++++++++++++++++++ spacy/lang/lij/__init__.py | 31 ++++++++ spacy/lang/lij/examples.py | 18 +++++ spacy/lang/lij/punctuation.py | 15 ++++ spacy/lang/lij/stop_words.py | 43 ++++++++++ spacy/lang/lij/tokenizer_exceptions.py | 52 ++++++++++++ website/meta/languages.json | 6 ++ 7 files changed, 271 insertions(+) create mode 100644 .github/contributors/Baciccin.md create mode 100644 spacy/lang/lij/__init__.py create mode 100644 spacy/lang/lij/examples.py create mode 100644 spacy/lang/lij/punctuation.py create mode 100644 spacy/lang/lij/stop_words.py create mode 100644 spacy/lang/lij/tokenizer_exceptions.py diff --git a/.github/contributors/Baciccin.md b/.github/contributors/Baciccin.md new file mode 100644 index 000000000..c7a940cb5 --- /dev/null +++ b/.github/contributors/Baciccin.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 | Giovanni Battista Parodi | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2020-03-19 | +| GitHub username | Baciccin | +| Website (optional) | | diff --git a/spacy/lang/lij/__init__.py b/spacy/lang/lij/__init__.py new file mode 100644 index 000000000..9b4b29798 --- /dev/null +++ b/spacy/lang/lij/__init__.py @@ -0,0 +1,31 @@ +# coding: utf8 +from __future__ import unicode_literals + +from .stop_words import STOP_WORDS +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS +from .punctuation import TOKENIZER_INFIXES + +from ..tokenizer_exceptions import BASE_EXCEPTIONS +from ..norm_exceptions import BASE_NORMS +from ...language import Language +from ...attrs import LANG, NORM +from ...util import update_exc, add_lookups + + +class LigurianDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters[LANG] = lambda text: "lij" + lex_attr_getters[NORM] = add_lookups( + Language.Defaults.lex_attr_getters[NORM], BASE_NORMS + ) + tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) + stop_words = STOP_WORDS + infixes = TOKENIZER_INFIXES + + +class Ligurian(Language): + lang = "lij" + Defaults = LigurianDefaults + + +__all__ = ["Ligurian"] diff --git a/spacy/lang/lij/examples.py b/spacy/lang/lij/examples.py new file mode 100644 index 000000000..c4034ae7e --- /dev/null +++ b/spacy/lang/lij/examples.py @@ -0,0 +1,18 @@ +# coding: utf8 +from __future__ import unicode_literals + + +""" +Example sentences to test spaCy and its language models. + +>>> from spacy.lang.lij.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "Sciusciâ e sciorbî no se peu.", + "Graçie di çetroin, che me son arrivæ.", + "Vegnime apreuvo, che ve fasso pescâ di òmmi.", + "Bella pe sempre l'ægua inta conchetta quande unn'agoggia d'ægua a se â trapaña.", +] diff --git a/spacy/lang/lij/punctuation.py b/spacy/lang/lij/punctuation.py new file mode 100644 index 000000000..4439376c8 --- /dev/null +++ b/spacy/lang/lij/punctuation.py @@ -0,0 +1,15 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ..punctuation import TOKENIZER_INFIXES +from ..char_classes import ALPHA + + +ELISION = " ' ’ ".strip().replace(" ", "").replace("\n", "") + + +_infixes = TOKENIZER_INFIXES + [ + r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION) +] + +TOKENIZER_INFIXES = _infixes diff --git a/spacy/lang/lij/stop_words.py b/spacy/lang/lij/stop_words.py new file mode 100644 index 000000000..7ab34adf1 --- /dev/null +++ b/spacy/lang/lij/stop_words.py @@ -0,0 +1,43 @@ +# coding: utf8 +from __future__ import unicode_literals + + +STOP_WORDS = set( + """ +a à â a-a a-e a-i a-o aiva aloa an ancheu ancon apreuvo ascì atra atre atri atro avanti avei + +bella belle belli bello ben + +ch' che chì chi ciù co-a co-e co-i co-o comm' comme con cösa coscì cöse + +d' da da-a da-e da-i da-o dapeu de delongo derê di do doe doî donde dòppo + +é e ê ea ean emmo en ëse + +fin fiña + +gh' ghe guæei + +i î in insemme int' inta inte inti into + +l' lê lì lô + +m' ma manco me megio meno mezo mi + +na n' ne ni ninte nisciun nisciuña no + +o ò ô oua + +parte pe pe-a pe-i pe-e pe-o perché pittin pö primma pròpio + +quæ quand' quande quarche quella quelle quelli quello + +s' sce scê sci sciâ sciô sciù se segge seu sò solo son sott' sta stæta stæte stæti stæto ste sti sto + +tanta tante tanti tanto te ti torna tra tròppo tutta tutte tutti tutto + +un uña unn' unna + +za zu +""".split() +) diff --git a/spacy/lang/lij/tokenizer_exceptions.py b/spacy/lang/lij/tokenizer_exceptions.py new file mode 100644 index 000000000..2aa6f8304 --- /dev/null +++ b/spacy/lang/lij/tokenizer_exceptions.py @@ -0,0 +1,52 @@ +# coding: utf8 +from __future__ import unicode_literals +from ...symbols import ORTH, LEMMA + +_exc = {} + +for raw, lemma in [ + ("a-a", "a-o"), + ("a-e", "a-o"), + ("a-o", "a-o"), + ("a-i", "a-o"), + ("co-a", "co-o"), + ("co-e", "co-o"), + ("co-i", "co-o"), + ("co-o", "co-o"), + ("da-a", "da-o"), + ("da-e", "da-o"), + ("da-i", "da-o"), + ("da-o", "da-o"), + ("pe-a", "pe-o"), + ("pe-e", "pe-o"), + ("pe-i", "pe-o"), + ("pe-o", "pe-o"), +]: + for orth in [raw, raw.capitalize()]: + _exc[orth] = [{ORTH: orth, LEMMA: lemma}] + +# Prefix + prepositions with à (e.g. "sott'a-o") + +for prep, prep_lemma in [ + ("a-a", "a-o"), + ("a-e", "a-o"), + ("a-o", "a-o"), + ("a-i", "a-o"), +]: + for prefix, prefix_lemma in [ + ("sott'", "sotta"), + ("sott’", "sotta"), + ("contr'", "contra"), + ("contr’", "contra"), + ("ch'", "che"), + ("ch’", "che"), + ("s'", "se"), + ("s’", "se"), + ]: + for prefix_orth in [prefix, prefix.capitalize()]: + _exc[prefix_orth+prep] = [ + {ORTH: prefix_orth, LEMMA: prefix_lemma}, + {ORTH: prep, LEMMA: prep_lemma}, + ] + +TOKENIZER_EXCEPTIONS = _exc diff --git a/website/meta/languages.json b/website/meta/languages.json index 8834aaddc..41c1bce7f 100644 --- a/website/meta/languages.json +++ b/website/meta/languages.json @@ -181,6 +181,12 @@ "name": "Vietnamese", "dependencies": [{ "name": "Pyvi", "url": "https://github.com/trungtv/pyvi" }] }, + { + "code": "lij", + "name": "Ligurian", + "example": "Sta chì a l'é unna fraxe.", + "has_examples": true + }, { "code": "xx", "name": "Multi-language",