From 31c683d87d19dd482e3f702c50aeb60dad957e6e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sean=20L=C3=B6fgren?= Date: Wed, 18 Sep 2019 21:00:33 +0100 Subject: [PATCH] add return_matches and as_tuples back to Matcher.pipe (#4303) * add contributor agreement [ci skip] * add return_matches and as_tuples back to Matcher.pipe --- .github/contributors/seanBE.md | 106 +++++++++++++++++++++++++++++++++ spacy/matcher/matcher.pyx | 27 +++++++-- 2 files changed, 129 insertions(+), 4 deletions(-) create mode 100644 .github/contributors/seanBE.md diff --git a/.github/contributors/seanBE.md b/.github/contributors/seanBE.md new file mode 100644 index 000000000..5e4b4de0a --- /dev/null +++ b/.github/contributors/seanBE.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 | Sean Löfgren | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-09-17 | +| GitHub username | seanBE | +| Website (optional) | http://seanbe.github.io | diff --git a/spacy/matcher/matcher.pyx b/spacy/matcher/matcher.pyx index c698c8024..fe6ccc781 100644 --- a/spacy/matcher/matcher.pyx +++ b/spacy/matcher/matcher.pyx @@ -162,18 +162,37 @@ cdef class Matcher: return default return (self._callbacks[key], self._patterns[key]) - def pipe(self, docs, batch_size=1000, n_threads=-1): + def pipe(self, docs, batch_size=1000, n_threads=-1, return_matches=False, + as_tuples=False): """Match a stream of documents, yielding them in turn. docs (iterable): A stream of documents. batch_size (int): Number of documents to accumulate into a working set. + return_matches (bool): Yield the match lists along with the docs, making + results (doc, matches) tuples. + as_tuples (bool): Interpret the input stream as (doc, context) tuples, + and yield (result, context) tuples out. + If both return_matches and as_tuples are True, the output will + be a sequence of ((doc, matches), context) tuples. YIELDS (Doc): Documents, in order. """ if n_threads != -1: deprecation_warning(Warnings.W016) - for doc in docs: - self(doc) - yield doc + + if as_tuples: + for doc, context in docs: + matches = self(doc) + if return_matches: + yield ((doc, matches), context) + else: + yield (doc, context) + else: + for doc in docs: + matches = self(doc) + if return_matches: + yield (doc, matches) + else: + yield doc def __call__(self, Doc doc): """Find all token sequences matching the supplied pattern.