From 4244e285c25c0c13a1f7f6e172b31ebb8f2bb7b1 Mon Sep 17 00:00:00 2001 From: alldefector Date: Wed, 21 Feb 2018 12:43:21 -0800 Subject: [PATCH 1/5] Fix Spanish noun_chunks failure caused by typo --- spacy/lang/es/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/lang/es/__init__.py b/spacy/lang/es/__init__.py index 661f0bbec..41dd817dd 100644 --- a/spacy/lang/es/__init__.py +++ b/spacy/lang/es/__init__.py @@ -21,7 +21,7 @@ class SpanishDefaults(Language.Defaults): tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) tag_map = TAG_MAP stop_words = STOP_WORDS - sytax_iterators = SYNTAX_ITERATORS + syntax_iterators = SYNTAX_ITERATORS lemma_lookup = LOOKUP From a5981914a6535d46ea67261a01a9c8b7bd765df3 Mon Sep 17 00:00:00 2001 From: Feng Niu Date: Wed, 21 Feb 2018 13:05:57 -0800 Subject: [PATCH 2/5] contributor file --- .github/contributors/alldefector.md | 106 ++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/alldefector.md diff --git a/.github/contributors/alldefector.md b/.github/contributors/alldefector.md new file mode 100644 index 000000000..a32a6dede --- /dev/null +++ b/.github/contributors/alldefector.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: + + * [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. + + * [x] 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 | Feng Niu | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | Feb 21, 2018 | +| GitHub username | alldefector | +| Website (optional) | | From 8df75b229cca93474a8502c7b07ed16e1d575b18 Mon Sep 17 00:00:00 2001 From: Feng Niu Date: Wed, 21 Feb 2018 13:11:17 -0800 Subject: [PATCH 3/5] fix unbound vars in es.syntax_iterators --- spacy/lang/es/syntax_iterators.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/spacy/lang/es/syntax_iterators.py b/spacy/lang/es/syntax_iterators.py index c414897a0..0c199cc6a 100644 --- a/spacy/lang/es/syntax_iterators.py +++ b/spacy/lang/es/syntax_iterators.py @@ -6,17 +6,17 @@ from ...symbols import NOUN, PROPN, PRON, VERB, AUX def noun_chunks(obj): doc = obj.doc - np_label = doc.vocab.strings['NP'] + np_label = doc.vocab.strings.add('NP') left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed'] right_labels = ['flat', 'fixed', 'compound', 'neg'] stop_labels = ['punct'] - np_left_deps = [doc.vocab.strings[label] for label in left_labels] - np_right_deps = [doc.vocab.strings[label] for label in right_labels] - stop_deps = [doc.vocab.strings[label] for label in stop_labels] + np_left_deps = [doc.vocab.strings.add(label) for label in left_labels] + np_right_deps = [doc.vocab.strings.add(label) for label in right_labels] + stop_deps = [doc.vocab.strings.add(label) for label in stop_labels] token = doc[0] while token and token.i < len(doc): if token.pos in [PROPN, NOUN, PRON]: - left, right = noun_bounds(token) + left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps) yield left.i, right.i+1, np_label token = right token = next_token(token) @@ -33,7 +33,7 @@ def next_token(token): return None -def noun_bounds(root): +def noun_bounds(root, np_left_deps, np_right_deps, stop_deps): left_bound = root for token in reversed(list(root.lefts)): if token.dep in np_left_deps: @@ -41,7 +41,7 @@ def noun_bounds(root): right_bound = root for token in root.rights: if (token.dep in np_right_deps): - left, right = noun_bounds(token) + left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps) if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps, doc[left_bound.i: right.i])): break From 7eb1cd100b9e5a9259e5691257ff4fa06aa28ef2 Mon Sep 17 00:00:00 2001 From: Feng Niu Date: Wed, 21 Feb 2018 15:05:37 -0800 Subject: [PATCH 4/5] unbound doc var --- spacy/lang/es/syntax_iterators.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/spacy/lang/es/syntax_iterators.py b/spacy/lang/es/syntax_iterators.py index 0c199cc6a..462d4ccee 100644 --- a/spacy/lang/es/syntax_iterators.py +++ b/spacy/lang/es/syntax_iterators.py @@ -16,7 +16,7 @@ def noun_chunks(obj): token = doc[0] while token and token.i < len(doc): if token.pos in [PROPN, NOUN, PRON]: - left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps) + left, right = noun_bounds(doc, token, np_left_deps, np_right_deps, stop_deps) yield left.i, right.i+1, np_label token = right token = next_token(token) @@ -33,7 +33,7 @@ def next_token(token): return None -def noun_bounds(root, np_left_deps, np_right_deps, stop_deps): +def noun_bounds(doc, root, np_left_deps, np_right_deps, stop_deps): left_bound = root for token in reversed(list(root.lefts)): if token.dep in np_left_deps: @@ -41,7 +41,7 @@ def noun_bounds(root, np_left_deps, np_right_deps, stop_deps): right_bound = root for token in root.rights: if (token.dep in np_right_deps): - left, right = noun_bounds(token, np_left_deps, np_right_deps, stop_deps) + left, right = noun_bounds(doc, token, np_left_deps, np_right_deps, stop_deps) if list(filter(lambda t: is_verb_token(t) or t.dep in stop_deps, doc[left_bound.i: right.i])): break From 1c60384bed3a640e64d79e33c6e33f7574f6bdfd Mon Sep 17 00:00:00 2001 From: Feng Niu Date: Wed, 21 Feb 2018 15:39:04 -0800 Subject: [PATCH 5/5] return on empty doc --- spacy/lang/es/syntax_iterators.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/spacy/lang/es/syntax_iterators.py b/spacy/lang/es/syntax_iterators.py index 462d4ccee..b81d1fab0 100644 --- a/spacy/lang/es/syntax_iterators.py +++ b/spacy/lang/es/syntax_iterators.py @@ -6,6 +6,8 @@ from ...symbols import NOUN, PROPN, PRON, VERB, AUX def noun_chunks(obj): doc = obj.doc + if not len(doc): + return np_label = doc.vocab.strings.add('NP') left_labels = ['det', 'fixed', 'neg'] #['nunmod', 'det', 'appos', 'fixed'] right_labels = ['flat', 'fixed', 'compound', 'neg']