diff --git a/.github/contributors/tupui.md b/.github/contributors/tupui.md new file mode 100644 index 000000000..5f53a72f8 --- /dev/null +++ b/.github/contributors/tupui.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 | Pamphile Roy | +| Company name (if applicable) | N/A | +| Title or role (if applicable) | N/A | +| Date | January 29th, 2021 | +| GitHub username | tupui | +| Website (optional) | N/A | diff --git a/spacy/cli/download.py b/spacy/cli/download.py index 5fcac63c0..6f9697f32 100644 --- a/spacy/cli/download.py +++ b/spacy/cli/download.py @@ -103,8 +103,6 @@ def download_model( filename: str, user_pip_args: Optional[Sequence[str]] = None ) -> None: download_url = about.__download_url__ + "/" + filename - pip_args = ["--no-cache-dir"] - if user_pip_args: - pip_args.extend(user_pip_args) + pip_args = user_pip_args if user_pip_args is not None else [] cmd = [sys.executable, "-m", "pip", "install"] + pip_args + [download_url] run_command(cmd) diff --git a/spacy/errors.py b/spacy/errors.py index 6874f9a0c..f321b8c5a 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -483,6 +483,7 @@ class Errors: E199 = ("Unable to merge 0-length span at `doc[{start}:{end}]`.") E200 = ("Can't yet set {attr} from Span. Vote for this feature on the " "issue tracker: http://github.com/explosion/spaCy/issues") + E202 = ("Unsupported alignment mode '{mode}'. Supported modes: {modes}.") # TODO: fix numbering after merging develop into master E886 = ("Can't replace {name} -> {tok2vec} listeners: path '{path}' not " diff --git a/spacy/tests/doc/test_span.py b/spacy/tests/doc/test_span.py index 4c7f0c86b..078cc81b1 100644 --- a/spacy/tests/doc/test_span.py +++ b/spacy/tests/doc/test_span.py @@ -195,6 +195,12 @@ def test_spans_by_character(doc): assert span1.end_char == span2.end_char assert span2.label_ == "GPE" + # unsupported alignment mode + with pytest.raises(ValueError): + span2 = doc.char_span( + span1.start_char + 1, span1.end_char, label="GPE", alignment_mode="unk" + ) + def test_span_to_array(doc): span = doc[1:-2] diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index 489de2201..a40931720 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -525,8 +525,9 @@ cdef class Doc: label = self.vocab.strings.add(label) if not isinstance(kb_id, int): kb_id = self.vocab.strings.add(kb_id) - if alignment_mode not in ("strict", "contract", "expand"): - alignment_mode = "strict" + alignment_modes = ("strict", "contract", "expand") + if alignment_mode not in alignment_modes: + raise ValueError(Errors.E202.format(mode=alignment_mode, modes=", ".join(alignment_modes))) cdef int start = token_by_char(self.c, self.length, start_idx) if start < 0 or (alignment_mode == "strict" and start_idx != self[start].idx): return None