From cc8e8046487ecd9d4a3dd7bf1fe3a53f71634ad7 Mon Sep 17 00:00:00 2001 From: "G.Pruvost" Date: Thu, 3 May 2018 18:37:02 +0200 Subject: [PATCH] #2211 - Support for ssl certs config on download command (#2212) * Add support for SSL/Certs customization on download CLI * Add a note on SSL options for the 'download' CLI in the README * Add contributor agreement --- .github/contributors/mn3mos.md | 106 +++++++++++++++++++++++++++++++++ README.rst | 5 ++ spacy/cli/download.py | 36 ++++++++--- 3 files changed, 139 insertions(+), 8 deletions(-) create mode 100644 .github/contributors/mn3mos.md diff --git a/.github/contributors/mn3mos.md b/.github/contributors/mn3mos.md new file mode 100644 index 000000000..e1eae0a09 --- /dev/null +++ b/.github/contributors/mn3mos.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. + + * [ ] 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 | Gaëtan PRUVOST | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 13/04/2018 | +| GitHub username | mn3mos | +| Website (optional) | | diff --git a/README.rst b/README.rst index 139453344..98c880a04 100644 --- a/README.rst +++ b/README.rst @@ -199,6 +199,11 @@ or manually by pointing pip to a path or URL. # pip install .tar.gz archive from path or URL pip install /Users/you/en_core_web_sm-2.0.0.tar.gz +If you have SSL certification problems, SSL customization options are described in the help: + + # help for the download command + python -m spacy download --help + Loading and using models ------------------------ diff --git a/spacy/cli/download.py b/spacy/cli/download.py index 7dc814efa..a68852b00 100644 --- a/spacy/cli/download.py +++ b/spacy/cli/download.py @@ -17,19 +17,39 @@ from .. import about @plac.annotations( model=("model to download, shortcut or name)", "positional", None, str), direct=("force direct download. Needs model name with version and won't " - "perform compatibility check", "flag", "d", bool)) -def download(model, direct=False): + "perform compatibility check", "flag", "d", bool), + unsecure=("unsecure mode - disables the verification of certificates", + "flag", "u", bool), + caFile=("specify a certificate authority file to use for certificates " + "validation. Ignored if --unsecure is used", "option", "c")) +def download(model, direct=False, unsecure=False, caFile=None): """ Download compatible model from default download path using pip. Model can be shortcut, model name or, if --direct flag is set, full model name with version. + The --unsecure optional flag can be used to disable ssl verification + The --caFile option can be used to provide a local CA file + used for certificate verification. """ + + # sslVerify is the argument handled to the 'verify' parameter + # of requests package. It must be either None, a boolean, + # or a String containing the path to CA file + sslVerify = None + if unsecure: + caFile = None + sslVerify = False + else: + if caFile != None: + sslVerify = caFile + + # Download the model if direct: dl = download_model('{m}/{m}.tar.gz'.format(m=model)) else: - shortcuts = get_json(about.__shortcuts__, "available shortcuts") + shortcuts = get_json(about.__shortcuts__, "available shortcuts", sslVerify) model_name = shortcuts.get(model, model) - compatibility = get_compatibility() + compatibility = get_compatibility(sslVerify) version = get_version(model_name, compatibility) dl = download_model('{m}-{v}/{m}-{v}.tar.gz'.format(m=model_name, v=version)) @@ -50,19 +70,19 @@ def download(model, direct=False): prints(Messages.M001.format(name=model_name), title=Messages.M002) -def get_json(url, desc): +def get_json(url, desc, sslVerify): try: - data = url_read(url) + data = url_read(url, verify=sslVerify) except HTTPError as e: prints(Messages.M004.format(desc, about.__version__), title=Messages.M003.format(e.code, e.reason), exits=1) return ujson.loads(data) -def get_compatibility(): +def get_compatibility(sslVerify): version = about.__version__ version = version.rsplit('.dev', 1)[0] - comp_table = get_json(about.__compatibility__, "compatibility table") + comp_table = get_json(about.__compatibility__, "compatibility table", sslVerify) comp = comp_table['spacy'] if version not in comp: prints(Messages.M006.format(version=version), title=Messages.M005,