diff --git a/.github/contributors/thomasopsomer.md b/.github/contributors/thomasopsomer.md new file mode 100644 index 000000000..240c1d06c --- /dev/null +++ b/.github/contributors/thomasopsomer.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 UG (haftungsbeschränkt)](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: + + * [ ] 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 | thomas opsomer | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 28-01-2018 | +| GitHub username | thomasopsomer | +| Website (optional) | | diff --git a/spacy/tests/regression/test_issue1834.py b/spacy/tests/regression/test_issue1834.py new file mode 100644 index 000000000..00b0c76eb --- /dev/null +++ b/spacy/tests/regression/test_issue1834.py @@ -0,0 +1,27 @@ +from __future__ import unicode_literals +from ...tokens import Doc +from ...vocab import Vocab + + +def test_issue1834(): + """test if sentence boundaries & parse/tag flags are not lost + during serialization + """ + words = "This is a first sentence . And another one".split() + vocab = Vocab() + doc = Doc(vocab, words=words) + vocab = doc.vocab + doc[6].sent_start = True + deser_doc = Doc(vocab).from_bytes(doc.to_bytes()) + assert deser_doc[6].sent_start + assert not deser_doc.is_parsed + assert not deser_doc.is_tagged + doc.is_parsed = True + doc.is_tagged = True + deser_doc = Doc(vocab).from_bytes(doc.to_bytes()) + assert deser_doc.is_parsed + assert deser_doc.is_tagged + + + + diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index b88c02320..daab22434 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -701,9 +701,12 @@ cdef class Doc: for i in range(length): if array[i, col] != 0: self.vocab.morphology.assign_tag(&tokens[i], array[i, col]) - set_children_from_heads(self.c, self.length) + # set flags self.is_parsed = bool(HEAD in attrs or DEP in attrs) self.is_tagged = bool(TAG in attrs or POS in attrs) + # if document is parsed, set children + if self.is_parsed: + set_children_from_heads(self.c, self.length) return self def get_lca_matrix(self): @@ -779,7 +782,16 @@ cdef class Doc: RETURNS (bytes): A losslessly serialized copy of the `Doc`, including all annotations. """ - array_head = [LENGTH, SPACY, TAG, LEMMA, HEAD, DEP, ENT_IOB, ENT_TYPE] + array_head = [LENGTH, SPACY, LEMMA, ENT_IOB, ENT_TYPE] + + if self.is_tagged: + array_head.append(TAG) + # if doc parsed add head and dep attribute + if self.is_parsed: + array_head.extend([HEAD, DEP]) + # otherwise add sent_start + else: + array_head.append(SENT_START) # Msgpack doesn't distinguish between lists and tuples, which is # vexing for user data. As a best guess, we *know* that within # keys, we must have tuples. In values we just have to hope diff --git a/spacy/tokens/token.pxd b/spacy/tokens/token.pxd index b408e04eb..b5879b9ec 100644 --- a/spacy/tokens/token.pxd +++ b/spacy/tokens/token.pxd @@ -48,6 +48,8 @@ cdef class Token: return token.ent_iob elif feat_name == ENT_TYPE: return token.ent_type + elif feat_name == SENT_START: + return token.sent_start else: return Lexeme.get_struct_attr(token.lex, feat_name) @@ -70,3 +72,5 @@ cdef class Token: token.ent_iob = value elif feat_name == ENT_TYPE: token.ent_type = value + elif feat_name == SENT_START: + token.sent_start = value