From e626a011cc94d77aa67a09a58f097d60cb1134c0 Mon Sep 17 00:00:00 2001 From: Antti Ajanki Date: Tue, 3 Dec 2019 13:55:28 +0200 Subject: [PATCH] Improvements to the Finnish language data (#4738) * Enable lex_attrs on Finnish * Copy the Danish tokenizer rules to Finnish Specifically, don't break hyphenated compound words * Contributor agreement * A new file for Finnish tokenizer rules instead of including the Danish ones --- .github/contributors/aajanki.md | 106 ++++++++++++++++++++++++++ spacy/lang/fi/__init__.py | 5 ++ spacy/lang/fi/lex_attrs.py | 3 +- spacy/lang/fi/punctuation.py | 33 ++++++++ spacy/tests/lang/fi/test_text.py | 27 +++++++ spacy/tests/lang/fi/test_tokenizer.py | 16 +++- 6 files changed, 188 insertions(+), 2 deletions(-) create mode 100644 .github/contributors/aajanki.md create mode 100644 spacy/lang/fi/punctuation.py create mode 100644 spacy/tests/lang/fi/test_text.py diff --git a/.github/contributors/aajanki.md b/.github/contributors/aajanki.md new file mode 100644 index 000000000..de7dc7fa2 --- /dev/null +++ b/.github/contributors/aajanki.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 | Antti Ajanki | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-11-30 | +| GitHub username | aajanki | +| Website (optional) | | diff --git a/spacy/lang/fi/__init__.py b/spacy/lang/fi/__init__.py index 6debe999c..45d2f886f 100644 --- a/spacy/lang/fi/__init__.py +++ b/spacy/lang/fi/__init__.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS +from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES from ..tokenizer_exceptions import BASE_EXCEPTIONS from ..norm_exceptions import BASE_NORMS @@ -13,10 +15,13 @@ from ...util import update_exc, add_lookups class FinnishDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) lex_attr_getters[LANG] = lambda text: "fi" lex_attr_getters[NORM] = add_lookups( Language.Defaults.lex_attr_getters[NORM], BASE_NORMS ) + infixes = TOKENIZER_INFIXES + suffixes = TOKENIZER_SUFFIXES tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) stop_words = STOP_WORDS diff --git a/spacy/lang/fi/lex_attrs.py b/spacy/lang/fi/lex_attrs.py index 97c876837..e960b55eb 100644 --- a/spacy/lang/fi/lex_attrs.py +++ b/spacy/lang/fi/lex_attrs.py @@ -18,7 +18,8 @@ _num_words = [ "kymmenen", "yksitoista", "kaksitoista", - "kolmetoista" "neljätoista", + "kolmetoista", + "neljätoista", "viisitoista", "kuusitoista", "seitsemäntoista", diff --git a/spacy/lang/fi/punctuation.py b/spacy/lang/fi/punctuation.py new file mode 100644 index 000000000..02eb1b200 --- /dev/null +++ b/spacy/lang/fi/punctuation.py @@ -0,0 +1,33 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ..char_classes import LIST_ELLIPSES, LIST_ICONS +from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER +from ..punctuation import TOKENIZER_SUFFIXES + + +_quotes = CONCAT_QUOTES.replace("'", "") + +_infixes = ( + LIST_ELLIPSES + + LIST_ICONS + + [ + r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER), + r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA), + r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA), + r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes), + r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA), + ] +) + +_suffixes = [ + suffix + for suffix in TOKENIZER_SUFFIXES + if suffix not in ["'s", "'S", "’s", "’S", r"\'"] +] + + +TOKENIZER_INFIXES = _infixes +TOKENIZER_SUFFIXES = _suffixes diff --git a/spacy/tests/lang/fi/test_text.py b/spacy/tests/lang/fi/test_text.py new file mode 100644 index 000000000..2dd92597e --- /dev/null +++ b/spacy/tests/lang/fi/test_text.py @@ -0,0 +1,27 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.parametrize( + "text,match", + [ + ("10", True), + ("1", True), + ("10000", True), + ("10,00", True), + ("-999,0", True), + ("yksi", True), + ("kolmetoista", True), + ("viisikymmentä", True), + ("tuhat", True), + ("1/2", True), + ("hevonen", False), + (",", False), + ], +) +def test_fi_lex_attrs_like_number(fi_tokenizer, text, match): + tokens = fi_tokenizer(text) + assert len(tokens) == 1 + assert tokens[0].like_num == match diff --git a/spacy/tests/lang/fi/test_tokenizer.py b/spacy/tests/lang/fi/test_tokenizer.py index 66be7bd46..cbbebcf28 100644 --- a/spacy/tests/lang/fi/test_tokenizer.py +++ b/spacy/tests/lang/fi/test_tokenizer.py @@ -12,9 +12,23 @@ ABBREVIATION_TESTS = [ ("Paino on n. 2.2 kg", ["Paino", "on", "n.", "2.2", "kg"]), ] +HYPHENATED_TESTS = [ + ( + "1700-luvulle sijoittuva taide-elokuva", + ["1700-luvulle", "sijoittuva", "taide-elokuva"] + ) +] + @pytest.mark.parametrize("text,expected_tokens", ABBREVIATION_TESTS) -def test_fi_tokenizer_handles_testcases(fi_tokenizer, text, expected_tokens): +def test_fi_tokenizer_abbreviations(fi_tokenizer, text, expected_tokens): + tokens = fi_tokenizer(text) + token_list = [token.text for token in tokens if not token.is_space] + assert expected_tokens == token_list + + +@pytest.mark.parametrize("text,expected_tokens", HYPHENATED_TESTS) +def test_fi_tokenizer_hyphenated_words(fi_tokenizer, text, expected_tokens): tokens = fi_tokenizer(text) token_list = [token.text for token in tokens if not token.is_space] assert expected_tokens == token_list