From 7a2ca00794da43edc9c55e690b647d5b5b962e42 Mon Sep 17 00:00:00 2001 From: Mike Izbicki Date: Mon, 6 Jul 2020 08:03:33 -0700 Subject: [PATCH] fix bug in Korean language, resulting in 100x speedup by reducing overhead of mecab (#5701) * speed up Korean nlp 100x by stopping mecab from reloading on each doc * add contributor agreement * rename variables to improve code readability --- .github/contributors/mikeizbicki.md | 106 ++++++++++++++++++++++++++++ spacy/lang/ko/__init__.py | 27 +++---- 2 files changed, 121 insertions(+), 12 deletions(-) create mode 100644 .github/contributors/mikeizbicki.md diff --git a/.github/contributors/mikeizbicki.md b/.github/contributors/mikeizbicki.md new file mode 100644 index 000000000..6e9d8c098 --- /dev/null +++ b/.github/contributors/mikeizbicki.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 | Mike Izbicki | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 02 Jun 2020 | +| GitHub username | mikeizbicki | +| Website (optional) | https://izbicki.me | diff --git a/spacy/lang/ko/__init__.py b/spacy/lang/ko/__init__.py index ec79a95ab..21a754168 100644 --- a/spacy/lang/ko/__init__.py +++ b/spacy/lang/ko/__init__.py @@ -42,7 +42,11 @@ def check_spaces(text, tokens): class KoreanTokenizer(DummyTokenizer): def __init__(self, cls, nlp=None): self.vocab = nlp.vocab if nlp is not None else cls.create_vocab(nlp) - self.Tokenizer = try_mecab_import() + MeCab = try_mecab_import() + self.mecab_tokenizer = MeCab("-F%f[0],%f[7]") + + def __del__(self): + self.mecab_tokenizer.__del__() def __call__(self, text): dtokens = list(self.detailed_tokens(text)) @@ -58,17 +62,16 @@ class KoreanTokenizer(DummyTokenizer): def detailed_tokens(self, text): # 품사 태그(POS)[0], 의미 부류(semantic class)[1], 종성 유무(jongseong)[2], 읽기(reading)[3], # 타입(type)[4], 첫번째 품사(start pos)[5], 마지막 품사(end pos)[6], 표현(expression)[7], * - with self.Tokenizer("-F%f[0],%f[7]") as tokenizer: - for node in tokenizer.parse(text, as_nodes=True): - if node.is_eos(): - break - surface = node.surface - feature = node.feature - tag, _, expr = feature.partition(",") - lemma, _, remainder = expr.partition("/") - if lemma == "*": - lemma = surface - yield {"surface": surface, "lemma": lemma, "tag": tag} + for node in self.mecab_tokenizer.parse(text, as_nodes=True): + if node.is_eos(): + break + surface = node.surface + feature = node.feature + tag, _, expr = feature.partition(",") + lemma, _, remainder = expr.partition("/") + if lemma == "*": + lemma = surface + yield {"surface": surface, "lemma": lemma, "tag": tag} class KoreanDefaults(Language.Defaults):