diff --git a/.gitignore b/.gitignore new file mode 100644 index 00000000..39d60022 --- /dev/null +++ b/.gitignore @@ -0,0 +1,15 @@ +*.pyc +*.sw? +*~ +/.coverage +/.coverage.* +.eggs/ +__pycache__ +build/ +dist/ +*.egg-info +version.txt +.vscode/ +.hypothesis/ +/.tox/ +.mypy_cache/ diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 00000000..7ee9db8a --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,48 @@ +repos: +- repo: https://github.com/pre-commit/pre-commit-hooks + rev: v2.4.0 + hooks: + - id: trailing-whitespace + - id: flake8 + - id: check-json + - id: check-yaml + +- repo: https://github.com/codespell-project/codespell + rev: v1.16.0 + hooks: + - id: codespell + exclude: TODO + args: [-L iff] + +- repo: local + hooks: + - id: mypy + name: mypy + entry: mypy + args: [swh] + pass_filenames: false + language: system + types: [python] + + - id: check-bumped-dbversion + name: check-bumped-dbversion + files: 'sql/upgrades/.*\.sql' + entry: grep + args: ['insert into dbversion'] + language: system + +- repo: https://github.com/python/black + rev: 19.10b0 + hooks: + - id: black + +# unfortunately, we are far from being able to enable this... +#- repo: https://github.com/PyCQA/pydocstyle.git +# rev: 4.0.0 +# hooks: +# - id: pydocstyle +# name: pydocstyle +# description: pydocstyle is a static analysis tool for checking compliance with Python docstring conventions. +# entry: pydocstyle --convention=google +# language: python +# types: [python] diff --git a/AUTHORS b/AUTHORS new file mode 100644 index 00000000..2d0a34af --- /dev/null +++ b/AUTHORS @@ -0,0 +1,3 @@ +Copyright (C) 2015 The Software Heritage developers + +See http://www.softwareheritage.org/ for more information. diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md new file mode 100644 index 00000000..0ad22b51 --- /dev/null +++ b/CODE_OF_CONDUCT.md @@ -0,0 +1,78 @@ +# Software Heritage Code of Conduct + +## Our Pledge + +In the interest of fostering an open and welcoming environment, we as Software +Heritage contributors and maintainers pledge to making participation in our +project and our community a harassment-free experience for everyone, regardless +of age, body size, disability, ethnicity, sex characteristics, gender identity +and expression, level of experience, education, socio-economic status, +nationality, personal appearance, race, religion, or sexual identity and +orientation. + +## Our Standards + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or + advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others' private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Our Responsibilities + +Project maintainers are responsible for clarifying the standards of acceptable +behavior and are expected to take appropriate and fair corrective action in +response to any instances of unacceptable behavior. + +Project maintainers have the right and responsibility to remove, edit, or +reject comments, commits, code, wiki edits, issues, and other contributions +that are not aligned to this Code of Conduct, or to ban temporarily or +permanently any contributor for other behaviors that they deem inappropriate, +threatening, offensive, or harmful. + +## Scope + +This Code of Conduct applies within all project spaces, and it also applies when +an individual is representing the project or its community in public spaces. +Examples of representing a project or community include using an official +project e-mail address, posting via an official social media account, or acting +as an appointed representative at an online or offline event. Representation of +a project may be further defined and clarified by project maintainers. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the project team at `conduct@softwareheritage.org`. All +complaints will be reviewed and investigated and will result in a response that +is deemed necessary and appropriate to the circumstances. The project team is +obligated to maintain confidentiality with regard to the reporter of an +incident. Further details of specific enforcement policies may be posted +separately. + +Project maintainers who do not follow or enforce the Code of Conduct in good +faith may face temporary or permanent repercussions as determined by other +members of the project's leadership. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4, +available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html + +[homepage]: https://www.contributor-covenant.org + +For answers to common questions about this code of conduct, see +https://www.contributor-covenant.org/faq diff --git a/CONTRIBUTORS b/CONTRIBUTORS new file mode 100644 index 00000000..b89f3e04 --- /dev/null +++ b/CONTRIBUTORS @@ -0,0 +1,3 @@ +Daniele Serafini +Ishan Bhanuka +Quentin Campos diff --git a/LICENSE b/LICENSE new file mode 100644 index 00000000..94a9ed02 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/PKG-INFO b/PKG-INFO index d0aedf47..1976d1a4 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,216 +1,216 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.10.0 +Version: 0.10.1 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-storage/ Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects `/usr/sbin/cassandra` to exist. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local args: db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing args: root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/docs/.gitignore b/docs/.gitignore new file mode 100644 index 00000000..58a761ea --- /dev/null +++ b/docs/.gitignore @@ -0,0 +1,3 @@ +_build/ +apidoc/ +*-stamp diff --git a/docs/Makefile b/docs/Makefile new file mode 100644 index 00000000..b97c7532 --- /dev/null +++ b/docs/Makefile @@ -0,0 +1,2 @@ +include ../../swh-docs/Makefile.sphinx +-include Makefile.local diff --git a/docs/Makefile.local b/docs/Makefile.local new file mode 100644 index 00000000..ed0b7b2a --- /dev/null +++ b/docs/Makefile.local @@ -0,0 +1,26 @@ +sphinx/html: sql-autodoc images +sphinx/clean: clean-sql-autodoc clean-images +assets: sql-autodoc images + +sql-autodoc: + make -C ../sql/ doc + +images: + make -C images/ +clean-images: + make -C images/ clean + +clean: clean-sql-autodoc clean-images +clean-sql-autodoc: + make -C ../sql/ clean + +distclean: clean distclean-sql-autodoc +distclean-sql-autodoc: + make -C ../sql/ distclean + +.PHONY: sql-autodoc clean-sql-autodoc images clean-images + + +# Local Variables: +# mode: makefile +# End: diff --git a/docs/_static/.placeholder b/docs/_static/.placeholder new file mode 100644 index 00000000..e69de29b diff --git a/docs/_templates/.placeholder b/docs/_templates/.placeholder new file mode 100644 index 00000000..e69de29b diff --git a/docs/archive-copies.rst b/docs/archive-copies.rst new file mode 100644 index 00000000..09f2ea40 --- /dev/null +++ b/docs/archive-copies.rst @@ -0,0 +1,48 @@ +:orphan: + +.. _archive-copies: + +Archive copies +============== + +.. _swh-storage-copies-layout: +.. figure:: images/swh-archive-copies.svg + :width: 1024px + :align: center + + Layout of Software Heritage archive copies (click to zoom). + +The Software Heritage archive exists in several copies, to minimize the risk of +losing archived source code artifacts. The layout of existing copies, their +relationships, as well as their geographical and administrative domains are +shown in the layout diagram above. + +We recall that the archive is conceptually organized as a graph, and +specifically a Merkle DAG, see :ref:`data model ` for more +information. + +Ingested source code artifacts land directly on the **primary copy**, which is +updated live and also used as reference for deduplication purposes. There, +different parts of the Merkle DAG as stored using different backend +technologies. The leaves of the graph, i.e., *content objects* (or "blobs"), +are stored in a key-value object storage, using their SHA1 identifiers as keys +(see :ref:`persistent identifiers `). SHA1 collision +avoidance is enforced by the :mod:`swh.storage` module. The *rest of the graph* +is stored in a Postgres database (see :ref:`SQL storage `). + +At the time of writing, the primary object storage contains about 5 billion +blobs with a median size of 3 KB---yes, that is *a lot of very small +files*---for a total compressed size of about 200 TB. The Postgres database +takes about 8 TB, half of which required by indexes. In terms of graph metrics, +the Merkle DAG has about 10 B nodes and 100 B edges. + +The **secondary copy** is hosted on Microsoft Azure cloud, using its native +blob storage for the object storage and a large virtual machine to run a +Postgres instance there. The database is kept up-to-date w.r.t. the primary +copy using Postgres WAL replication. The object storage is kept up-to-date +using :mod:`swh.archiver`. + +Archive copies (as opposed to archive mirrors) are operated by the Software +Heritage Team at Inria. The primary archived copy is geographically located at +Rocquencourt, France; the secondary copy hosted in the Europe West region of +the Azure cloud. diff --git a/docs/conf.py b/docs/conf.py new file mode 100644 index 00000000..190deb7e --- /dev/null +++ b/docs/conf.py @@ -0,0 +1 @@ +from swh.docs.sphinx.conf import * # NoQA diff --git a/docs/extrinsic-metadata-specification.rst b/docs/extrinsic-metadata-specification.rst new file mode 100644 index 00000000..d82bb55a --- /dev/null +++ b/docs/extrinsic-metadata-specification.rst @@ -0,0 +1,251 @@ +:orphan: + +.. _extrinsic-metadata-specification: + +Extrinsic metadata specification +================================ + +:term:`Extrinsic metadata` is information about software that is not part +of the source code itself but still closely related to the software. +Typical sources for extrinsic metadata are: the hosting place of a +repository, which can offer metadata via its web view or API; external +registries like collaborative curation initiatives; and out-of-band +information available at source code archival time. + +Since they are not part of the source code, a dedicated mechanism to fetch +and store them is needed. + +This specification assumes the reader is familiar with Software Heritage's +:ref:`architecture` and :ref:`data-model`. + + +Metadata sources +---------------- + +Authorities +^^^^^^^^^^^ + +Metadata authorities are entities that provide metadata about an +:term:`origin`. Metadata authorities include: code hosting places, +:term:`deposit` submitters, and registries (eg. Wikidata). + +An authority is uniquely defined by these properties: + + * its type, representing the kind of authority, which is one of these values: + * `deposit`, for metadata pushed to Software Heritage at the same time + as a software artifact + * `forge`, for metadata pulled from the same source as the one hosting + the software artifacts (which includes package managers) + * `registry`, for metadata pulled from a third-party + * its URL, which unambiguously identifies an instance of the authority type. + +Examples: + +=============== ================================= +type url +=============== ================================= +deposit https://hal.archives-ouvertes.fr/ +deposit https://hal.inria.fr/ +deposit https://software.intel.com/ +forge https://gitlab.com/ +forge https://gitlab.inria.fr/ +forge https://0xacab.org/ +forge https://github.com/ +registry https://www.wikidata.org/ +registry https://swmath.org/ +registry https://ascl.net/ +=============== ================================= + +Metadata fetchers +^^^^^^^^^^^^^^^^^ + +Metadata fetchers are software components used to fetch metadata from +a metadata authority, and ingest them into the Software Heritage archive. + +A metadata fetcher is uniquely defined by these properties: + +* its type +* its version + +Examples: + +* :term:`loaders `, which may either discover metadata as a + side-effect of loading source code, or be dedicated to fetching metadata. + +* :term:`listers `, which may discover metadata as a side-effect + of discovering origins. + +* :term:`deposit` submitters, which push metadata to SWH from a + third-party; usually at the same time as a :term:`software artifact` + +* crawlers, which fetch metadata from an authority in a way that is + none of the above (eg. by querying a specific API of the origin's forge). + + +Storage API +----------- + +Authorities and metadata fetchers +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The :term:`storage` API offers these endpoints to manipulate metadata +authorities and metadata fetchers: + +* ``metadata_authority_add(type, url, metadata)`` + which adds a new metadata authority to the storage. + +* ``metadata_authority_get(type, url)`` + which looks up a known authority (there is at most one) and if it is + known, returns a dictionary with keys ``type``, ``url``, and ``metadata``. + +* ``metadata_fetcher_add(name, version, metadata)`` + which adds a new metadata fetcher to the storage. + +* ``metadata_fetcher_get(name, version)`` + which looks up a known fetcher (there is at most one) and if it is + known, returns a dictionary with keys ``name``, ``version``, and + ``metadata``. + +These `metadata` fields contain JSON-encodable dictionaries +with information about the authority/fetcher, in a format specific to each +authority/fetcher. +With authority, the `metadata` field is reserved for information describing +and qualifying the authority. +With fetchers, the `metadata` field is reserved for configuration metadata +and other technical usage. + +Origin metadata +^^^^^^^^^^^^^^^ + +Extrinsic metadata are stored in SWH's :term:`storage database`. +The storage API offers three endpoints to manipulate origin metadata: + +* Adding metadata:: + + origin_metadata_add(origin_url, discovery_date, + authority, fetcher, + format, metadata) + + which adds a new `metadata` byte string obtained from a given authority + and associated to the origin. + `discovery_date` is a Python datetime. + `authority` must be a dict containing keys `type` and `url`, and + `fetcher` a dict containing keys `name` and `version`. + The authority and fetcher must be known to the storage before using this + endpoint. + `format` is a text field indicating the format of the content of the + `metadata` byte string. + +* Getting latest metadata:: + + origin_metadata_get_latest(origin_url, authority) + + where `authority` must be a dict containing keys `type` and `url`, + which returns a dictionary corresponding to the latest metadata entry + added from this origin, in the format:: + + { + 'origin_url': ..., + 'authority': {'type': ..., 'url': ...}, + 'fetcher': {'name': ..., 'version': ...}, + 'discovery_date': ..., + 'format': '...', + 'metadata': b'...' + } + + +* Getting all metadata:: + + origin_metadata_get(origin_url, + authority, + page_token, limit) + + where `authority` must be a dict containing keys `type` and `url` + which returns a dictionary with keys: + + * `next_page_token`, which is an opaque token to be used as + `page_token` for retrieving the next page. if absent, there is + no more pages to gather. + * `results`: list of dictionaries, one for each metadata item + deposited, corresponding to the given origin and obtained from the + specified authority. + + Each of these dictionaries is in the following format:: + + { + 'authority': {'type': ..., 'url': ...}, + 'fetcher': {'name': ..., 'version': ...}, + 'discovery_date': ..., + 'format': '...', + 'metadata': b'...' + } + +The parameters ``page_token`` and ``limit`` are used for pagination based on +an arbitrary order. An initial query to ``origin_metadata_get`` must set +``page_token`` to ``None``, and further query must use the value from the +previous query's ``next_page_token`` to get the next page of results. + +``metadata`` is a bytes array (eventually encoded using Base64). +Its format is specific to each authority; and is treated as an opaque value +by the storage. +Unifying these various formats into a common language is outside the scope +of this specification. + +Artifact metadata +^^^^^^^^^^^^^^^^^ + +In addition to origin metadata, the storage database stores metadata on +all software artifacts supported by the data model. + +This works similarly to origin metadata, with one major difference: +extrinsic metadata can be given on a specific artifact within a specified +context (for example: a directory in a specific revision from a specific +visit on a specific origin) which will be stored along the metadata itself. + +For example, two origins may develop the same file independently; +the information about authorship, licensing or even description may vary +about the same artifact in a different context. +This is why it is important to qualify the metadata with the complete +context for which it is intended, if any. + +for each artifact type ````, there are two endpoints +to manipulate metadata associated with artifacts of that type: + +* Adding metadata:: + + _metadata_add(id, context, discovery_date, + authority, fetcher, + format, metadata) + + +* Getting all metadata:: + + _metadata_get(id, + authority, + after, + page_token, limit) + + +definited similarly to ``origin_metadata_add`` and ``origin_metadata_get``, +but where ``id`` is a core SWHID (with type matching ````), +and with an extra ``context`` (argument when adding metadata, and dictionary +key when getting them) that is a dictionary with keys +depending on the artifact type ````: + +* for ``snapshot``: ``origin`` (a URL) and ``visit`` (an integer) +* for ``release``: those above, plus ``snapshot`` + (the core SWHID of a snapshot) +* for ``revision``: all those above, plus ``release`` + (the core SWHID of a release) +* for ``directory``: all those above, plus ``revision`` + (the core SWHID of a revision) + and ``path`` (a byte string), representing the path to this directory + from the root of the ``revision`` +* for ``content``: all those above, plus ``directory`` + (the core SWHID of a directory) + +All keys are optional, but should be provided whenever possible. +The dictionary may be empty, if metadata is fully independent from context. + +In all cases, ``visit`` should only be provided if ``origin`` is +(as visit ids are only unique with respect to an origin). diff --git a/docs/images/.gitignore b/docs/images/.gitignore new file mode 100644 index 00000000..542dcd32 --- /dev/null +++ b/docs/images/.gitignore @@ -0,0 +1,2 @@ +swh-archive-copies.pdf +swh-archive-copies.svg diff --git a/docs/images/Makefile b/docs/images/Makefile new file mode 100644 index 00000000..59782050 --- /dev/null +++ b/docs/images/Makefile @@ -0,0 +1,16 @@ + +BUILD_TARGETS = +BUILD_TARGETS += swh-archive-copies.pdf swh-archive-copies.svg + +all: $(BUILD_TARGETS) + + +%.svg: %.dia + inkscape -l $@ $< + +%.pdf: %.dia + inkscape -A $@ $< + + +clean: + -rm -f $(BUILD_TARGETS) diff --git a/docs/images/swh-archive-copies.dia b/docs/images/swh-archive-copies.dia new file mode 100644 index 00000000..bb64fb00 Binary files /dev/null and b/docs/images/swh-archive-copies.dia differ diff --git a/docs/index.rst b/docs/index.rst new file mode 100644 index 00000000..502967a3 --- /dev/null +++ b/docs/index.rst @@ -0,0 +1,45 @@ +.. _swh-storage: + +Software Heritage - Storage +=========================== + +Abstraction layer over the archive, allowing to access all stored source code +artifacts as well as their metadata + + +The Software Heritage storage consist of a high-level storage layer +(:mod:`swh.storage`) that exposes a client/server API +(:mod:`swh.storage.api`). The API is exposed by a server +(:mod:`swh.storage.api.server`) and accessible via a client +(:mod:`swh.storage.api.client`). + +The low-level implementation of the storage is split between an object storage +(:ref:`swh.objstorage `), which stores all "blobs" (i.e., the +leaves of the :ref:`data-model`) and a SQL representation of the rest of the +graph (:mod:`swh.storage.storage`). + + +Database schema +--------------- + +* :ref:`sql-storage` + + +Archive copies +-------------- + +* :ref:`archive-copies` + +Specifications +-------------- + +* :ref:`extrinsic-metadata-specification` + + +Reference Documentation +----------------------- + +.. toctree:: + :maxdepth: 2 + + /apidoc/swh.storage diff --git a/docs/sql-storage.rst b/docs/sql-storage.rst new file mode 100644 index 00000000..01cc2e61 --- /dev/null +++ b/docs/sql-storage.rst @@ -0,0 +1,16 @@ +:orphan: + +.. _sql-storage: + +SQL storage +=========== + +Postgres DB schema +------------------ + +.. _swh-storage-db-schema: +.. figure:: ../sql/doc/sql/db-schema.svg + :width: 1024px + :align: center + + Postgres DB schema of high-level Software Heritage storage (click to zoom). diff --git a/mypy.ini b/mypy.ini new file mode 100644 index 00000000..99c0bcc6 --- /dev/null +++ b/mypy.ini @@ -0,0 +1,60 @@ +[mypy] +namespace_packages = True + +# due to the conditional import logic on swh.journal, in some cases a specific +# type: ignore is needed, in other it isn't... +warn_unused_ignores = False + +# support for sqlalchemy magic: see https://github.com/dropbox/sqlalchemy-stubs +plugins = sqlmypy + + +# 3rd party libraries without stubs (yet) + +[mypy-cassandra.*] +ignore_missing_imports = True + +[mypy-confluent_kafka.*] +ignore_missing_imports = True + +[mypy-deprecated.*] +ignore_missing_imports = True + +# only shipped indirectly via hypothesis +[mypy-django.*] +ignore_missing_imports = True + +[mypy-msgpack.*] +ignore_missing_imports = True + +[mypy-multiprocessing.util] +ignore_missing_imports = True + +[mypy-pkg_resources.*] +ignore_missing_imports = True + +[mypy-psycopg2.*] +ignore_missing_imports = True + +[mypy-pytest.*] +ignore_missing_imports = True + +[mypy-pytest_cov.*] +ignore_missing_imports = True + +[mypy-pytest_kafka.*] +ignore_missing_imports = True + +[mypy-systemd.daemon.*] +ignore_missing_imports = True + +[mypy-tenacity.*] +ignore_missing_imports = True + +# temporary work-around for landing typing support in spite of the current +# journal<->storage dependency loop +[mypy-swh.journal.*] +ignore_missing_imports = True + +[mypy-pytest_postgresql.*] +ignore_missing_imports = True diff --git a/setup.py b/setup.py index 1f37b14f..72480105 100755 --- a/setup.py +++ b/setup.py @@ -1,77 +1,79 @@ #!/usr/bin/env python3 -# Copyright (C) 2015-2018 The Software Heritage developers +# Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from setuptools import setup, find_packages from os import path from io import open here = path.abspath(path.dirname(__file__)) # Get the long description from the README file with open(path.join(here, "README.md"), encoding="utf-8") as f: long_description = f.read() def parse_requirements(name=None): if name: reqf = "requirements-%s.txt" % name else: reqf = "requirements.txt" requirements = [] if not path.exists(reqf): return requirements with open(reqf) as f: for line in f.readlines(): line = line.strip() if not line or line.startswith("#"): continue requirements.append(line) return requirements setup( name="swh.storage", description="Software Heritage storage manager", long_description=long_description, long_description_content_type="text/markdown", python_requires=">=3.7", author="Software Heritage developers", author_email="swh-devel@inria.fr", url="https://forge.softwareheritage.org/diffusion/DSTO/", + setup_requires=["setuptools-scm"], packages=find_packages(), + use_scm_version=True, scripts=["bin/swh-storage-add-dir",], entry_points=""" [console_scripts] swh-storage=swh.storage.cli:main [swh.cli.subcommands] storage=swh.storage.cli:storage + [pytest11] + pytest_swh_storage=swh.storage.pytest_plugin """, - setup_requires=["vcversioner"], install_requires=parse_requirements() + parse_requirements("swh"), extras_require={ "testing": (parse_requirements("test") + parse_requirements("swh-journal")), "schemata": ["SQLAlchemy"], "journal": parse_requirements("swh-journal"), }, - vcversioner={}, include_package_data=True, classifiers=[ "Programming Language :: Python :: 3", "Intended Audience :: Developers", "License :: OSI Approved :: GNU General Public License v3 (GPLv3)", "Operating System :: OS Independent", "Development Status :: 5 - Production/Stable", ], project_urls={ "Bug Reports": "https://forge.softwareheritage.org/maniphest", "Funding": "https://www.softwareheritage.org/donate", "Source": "https://forge.softwareheritage.org/source/swh-storage", "Documentation": "https://docs.softwareheritage.org/devel/swh-storage/", }, ) diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index d0aedf47..1976d1a4 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,216 +1,216 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.10.0 +Version: 0.10.1 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-storage/ Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects `/usr/sbin/cassandra` to exist. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local args: db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing args: root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/swh.storage.egg-info/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt index 623fcdc1..6827b03e 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,266 +1,293 @@ +.gitignore +.pre-commit-config.yaml +AUTHORS +CODE_OF_CONDUCT.md +CONTRIBUTORS +LICENSE MANIFEST.in Makefile Makefile.local README.md +mypy.ini pyproject.toml pytest.ini +requirements-swh-journal.txt +requirements-swh.txt +requirements-test.txt +requirements.txt setup.cfg setup.py tox.ini version.txt ./requirements-swh-journal.txt ./requirements-swh.txt ./requirements-test.txt ./requirements.txt bin/swh-storage-add-dir +docs/.gitignore +docs/Makefile +docs/Makefile.local +docs/archive-copies.rst +docs/conf.py +docs/extrinsic-metadata-specification.rst +docs/index.rst +docs/sql-storage.rst +docs/_static/.placeholder +docs/_templates/.placeholder +docs/images/.gitignore +docs/images/Makefile +docs/images/swh-archive-copies.dia sql/.gitignore sql/Makefile sql/TODO sql/clusters.dot sql/bin/db-upgrade sql/bin/dot_add_content +sql/doc/json sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/entity.lister_metadata.schema.json sql/doc/json/entity.metadata.schema.json sql/doc/json/entity_history.lister_metadata.schema.json sql/doc/json/entity_history.metadata.schema.json sql/doc/json/fetch_history.result.schema.json sql/doc/json/list_history.result.schema.json sql/doc/json/listable_entity.list_params.schema.json sql/doc/json/origin_visit.metadata.json sql/doc/json/tool.tool_configuration.schema.json sql/json/.gitignore sql/json/Makefile sql/json/entity.lister_metadata.schema.json sql/json/entity.metadata.schema.json sql/json/entity_history.lister_metadata.schema.json sql/json/entity_history.metadata.schema.json sql/json/fetch_history.result.schema.json sql/json/list_history.result.schema.json sql/json/listable_entity.list_params.schema.json sql/json/origin_visit.metadata.json sql/json/tool.tool_configuration.schema.json sql/upgrades/015.sql sql/upgrades/016.sql sql/upgrades/017.sql sql/upgrades/018.sql sql/upgrades/019.sql sql/upgrades/020.sql sql/upgrades/021.sql sql/upgrades/022.sql sql/upgrades/023.sql sql/upgrades/024.sql sql/upgrades/025.sql sql/upgrades/026.sql sql/upgrades/027.sql sql/upgrades/028.sql sql/upgrades/029.sql sql/upgrades/030.sql sql/upgrades/032.sql sql/upgrades/033.sql sql/upgrades/034.sql sql/upgrades/035.sql sql/upgrades/036.sql sql/upgrades/037.sql sql/upgrades/038.sql sql/upgrades/039.sql sql/upgrades/040.sql sql/upgrades/041.sql sql/upgrades/042.sql sql/upgrades/043.sql sql/upgrades/044.sql sql/upgrades/045.sql sql/upgrades/046.sql sql/upgrades/047.sql sql/upgrades/048.sql sql/upgrades/049.sql sql/upgrades/050.sql sql/upgrades/051.sql sql/upgrades/052.sql sql/upgrades/053.sql sql/upgrades/054.sql sql/upgrades/055.sql sql/upgrades/056.sql sql/upgrades/057.sql sql/upgrades/058.sql sql/upgrades/059.sql sql/upgrades/060.sql sql/upgrades/061.sql sql/upgrades/062.sql sql/upgrades/063.sql sql/upgrades/064.sql sql/upgrades/065.sql sql/upgrades/066.sql sql/upgrades/067.sql sql/upgrades/068.sql sql/upgrades/069.sql sql/upgrades/070.sql sql/upgrades/071.sql sql/upgrades/072.sql sql/upgrades/073.sql sql/upgrades/074.sql sql/upgrades/075.sql sql/upgrades/076.sql sql/upgrades/077.sql sql/upgrades/078.sql sql/upgrades/079.sql sql/upgrades/080.sql sql/upgrades/081.sql sql/upgrades/082.sql sql/upgrades/083.sql sql/upgrades/084.sql sql/upgrades/085.sql sql/upgrades/086.sql sql/upgrades/087.sql sql/upgrades/088.sql sql/upgrades/089.sql sql/upgrades/090.sql sql/upgrades/091.sql sql/upgrades/092.sql sql/upgrades/093.sql sql/upgrades/094.sql sql/upgrades/095.sql sql/upgrades/096.sql sql/upgrades/097.sql sql/upgrades/098.sql sql/upgrades/099.sql sql/upgrades/100.sql sql/upgrades/101.sql sql/upgrades/102.sql sql/upgrades/103.sql sql/upgrades/104.sql sql/upgrades/105.sql sql/upgrades/106.sql sql/upgrades/107.sql sql/upgrades/108.sql sql/upgrades/109.sql sql/upgrades/110.sql sql/upgrades/111.sql sql/upgrades/112.sql sql/upgrades/113.sql sql/upgrades/114.sql sql/upgrades/115.sql sql/upgrades/116.sql sql/upgrades/117.sql sql/upgrades/118.sql sql/upgrades/119.sql sql/upgrades/120.sql sql/upgrades/121.sql sql/upgrades/122.sql sql/upgrades/123.sql sql/upgrades/124.sql sql/upgrades/125.sql sql/upgrades/126.sql sql/upgrades/127.sql sql/upgrades/128.sql sql/upgrades/129.sql sql/upgrades/130.sql sql/upgrades/131.sql sql/upgrades/132.sql sql/upgrades/133.sql sql/upgrades/134.sql sql/upgrades/135.sql sql/upgrades/136.sql sql/upgrades/137.sql sql/upgrades/138.sql sql/upgrades/139.sql sql/upgrades/140.sql sql/upgrades/141.sql sql/upgrades/142.sql sql/upgrades/143.sql sql/upgrades/144.sql sql/upgrades/145.sql sql/upgrades/146.sql sql/upgrades/147.sql sql/upgrades/148.sql sql/upgrades/149.sql sql/upgrades/150.sql sql/upgrades/151.sql sql/upgrades/152.sql sql/upgrades/153.sql sql/upgrades/154.sql sql/upgrades/155.sql sql/upgrades/156.sql sql/upgrades/157.sql sql/upgrades/158.sql swh/__init__.py swh.storage.egg-info/PKG-INFO swh.storage.egg-info/SOURCES.txt swh.storage.egg-info/dependency_links.txt swh.storage.egg-info/entry_points.txt swh.storage.egg-info/requires.txt swh.storage.egg-info/top_level.txt swh/storage/__init__.py swh/storage/backfill.py swh/storage/buffer.py swh/storage/cli.py swh/storage/common.py swh/storage/converters.py swh/storage/db.py swh/storage/exc.py swh/storage/extrinsic_metadata.py swh/storage/filter.py swh/storage/fixer.py swh/storage/in_memory.py swh/storage/interface.py swh/storage/metrics.py swh/storage/objstorage.py swh/storage/py.typed +swh/storage/pytest_plugin.py swh/storage/replay.py swh/storage/retry.py swh/storage/storage.py swh/storage/utils.py swh/storage/validate.py swh/storage/writer.py swh/storage/algos/__init__.py swh/storage/algos/diff.py swh/storage/algos/dir_iterators.py swh/storage/algos/origin.py swh/storage/algos/revisions_walker.py swh/storage/algos/snapshot.py swh/storage/api/__init__.py swh/storage/api/client.py swh/storage/api/serializers.py swh/storage/api/server.py swh/storage/cassandra/__init__.py swh/storage/cassandra/common.py swh/storage/cassandra/converters.py swh/storage/cassandra/cql.py swh/storage/cassandra/schema.py swh/storage/cassandra/storage.py swh/storage/sql/10-swh-init.sql swh/storage/sql/20-swh-enums.sql swh/storage/sql/30-swh-schema.sql swh/storage/sql/40-swh-func.sql swh/storage/sql/60-swh-indexes.sql swh/storage/tests/__init__.py swh/storage/tests/conftest.py swh/storage/tests/generate_data_test.py swh/storage/tests/storage_data.py swh/storage/tests/test_api_client.py swh/storage/tests/test_backfill.py swh/storage/tests/test_buffer.py swh/storage/tests/test_cassandra.py swh/storage/tests/test_cassandra_converters.py swh/storage/tests/test_cli.py swh/storage/tests/test_converters.py swh/storage/tests/test_db.py swh/storage/tests/test_exception.py swh/storage/tests/test_filter.py swh/storage/tests/test_in_memory.py swh/storage/tests/test_init.py swh/storage/tests/test_kafka_writer.py swh/storage/tests/test_metrics.py swh/storage/tests/test_replay.py swh/storage/tests/test_retry.py swh/storage/tests/test_revision_bw_compat.py swh/storage/tests/test_server.py swh/storage/tests/test_storage.py swh/storage/tests/test_utils.py swh/storage/tests/algos/__init__.py swh/storage/tests/algos/test_diff.py swh/storage/tests/algos/test_dir_iterator.py swh/storage/tests/algos/test_origin.py swh/storage/tests/algos/test_revisions_walker.py -swh/storage/tests/algos/test_snapshot.py \ No newline at end of file +swh/storage/tests/algos/test_snapshot.py +swh/storage/tests/data/storage.yml \ No newline at end of file diff --git a/swh.storage.egg-info/entry_points.txt b/swh.storage.egg-info/entry_points.txt index a3379a55..c1dba848 100644 --- a/swh.storage.egg-info/entry_points.txt +++ b/swh.storage.egg-info/entry_points.txt @@ -1,6 +1,8 @@ [console_scripts] swh-storage=swh.storage.cli:main [swh.cli.subcommands] storage=swh.storage.cli:storage + [pytest11] + pytest_swh_storage=swh.storage.pytest_plugin \ No newline at end of file diff --git a/swh/storage/tests/conftest.py b/swh/storage/pytest_plugin.py similarity index 74% copy from swh/storage/tests/conftest.py copy to swh/storage/pytest_plugin.py index 52d9b4f9..1b010923 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/pytest_plugin.py @@ -1,272 +1,208 @@ -# Copyright (C) 2019 The Software Heritage developers +# Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import glob -import pytest -import multiprocessing.util -from typing import Union from os import path, environ -from hypothesis import settings -from typing import Dict +from typing import Dict, Union -try: - import pytest_cov.embed -except ImportError: - pytest_cov = None +import pytest + +import swh.storage from pytest_postgresql import factories from pytest_postgresql.janitor import DatabaseJanitor, psycopg2, Version -import swh.storage - from swh.core.utils import numfile_sortkey as sortkey -from swh.model.tests.generate_testdata import gen_contents, gen_origins -from swh.model.model import ( - Content, - Directory, - Origin, - OriginVisit, - Release, - Revision, - SkippedContent, - Snapshot, -) - - -OBJECT_FACTORY = { - "content": Content.from_dict, - "directory": Directory.from_dict, - "origin": Origin.from_dict, - "origin_visit": OriginVisit.from_dict, - "release": Release.from_dict, - "revision": Revision.from_dict, - "skipped_content": SkippedContent.from_dict, - "snapshot": Snapshot.from_dict, -} +from swh.storage import get_storage +from swh.storage.tests.storage_data import data + SQL_DIR = path.join(path.dirname(swh.storage.__file__), "sql") environ["LC_ALL"] = "C.UTF-8" DUMP_FILES = path.join(SQL_DIR, "*.sql") -# define tests profile. Full documentation is at: -# https://hypothesis.readthedocs.io/en/latest/settings.html#settings-profiles -settings.register_profile("fast", max_examples=5, deadline=5000) -settings.register_profile("slow", max_examples=20, deadline=5000) - - -if pytest_cov is not None: - # pytest_cov + multiprocessing can cause a segmentation fault when starting - # the child process ; so we're - # removing pytest-coverage's hook that runs when a child process starts. - # This means code run in child processes won't be counted in the coverage - # report, but this is not an issue because the only code that runs only in - # child processes is the RPC server. - for (key, value) in multiprocessing.util._afterfork_registry.items(): - if value is pytest_cov.embed.multiprocessing_start: - del multiprocessing.util._afterfork_registry[key] - break - else: - assert False, "missing pytest_cov.embed.multiprocessing_start?" - @pytest.fixture def swh_storage_backend_config(postgresql_proc, swh_storage_postgresql): yield { "cls": "local", "db": "postgresql://{user}@{host}:{port}/{dbname}".format( host=postgresql_proc.host, port=postgresql_proc.port, user="postgres", dbname="tests", ), "objstorage": {"cls": "memory", "args": {}}, "journal_writer": {"cls": "memory",}, } @pytest.fixture def swh_storage(swh_storage_backend_config): - return swh.storage.get_storage(cls="validate", storage=swh_storage_backend_config) - - -@pytest.fixture -def swh_contents(swh_storage): - contents = gen_contents(n=20) - swh_storage.content_add([c for c in contents if c["status"] != "absent"]) - swh_storage.skipped_content_add([c for c in contents if c["status"] == "absent"]) - return contents - - -@pytest.fixture -def swh_origins(swh_storage): - origins = gen_origins(n=100) - swh_storage.origin_add(origins) - return origins + return get_storage(cls="validate", storage=swh_storage_backend_config) # the postgres_fact factory fixture below is mostly a copy of the code # from pytest-postgresql. We need a custom version here to be able to # specify our version of the DBJanitor we use. def postgresql_fact(process_fixture_name, db_name=None, dump_files=DUMP_FILES): @pytest.fixture def postgresql_factory(request): """ Fixture factory for PostgreSQL. :param FixtureRequest request: fixture request object :rtype: psycopg2.connection :returns: postgresql client """ config = factories.get_config(request) if not psycopg2: raise ImportError("No module named psycopg2. Please install it.") proc_fixture = request.getfixturevalue(process_fixture_name) # _, config = try_import('psycopg2', request) pg_host = proc_fixture.host pg_port = proc_fixture.port pg_user = proc_fixture.user pg_options = proc_fixture.options pg_db = db_name or config["dbname"] with SwhDatabaseJanitor( pg_user, pg_host, pg_port, pg_db, proc_fixture.version, dump_files=dump_files, ): connection = psycopg2.connect( dbname=pg_db, user=pg_user, host=pg_host, port=pg_port, options=pg_options, ) yield connection connection.close() return postgresql_factory swh_storage_postgresql = postgresql_fact("postgresql_proc") # This version of the DatabaseJanitor implement a different setup/teardown # behavior than than the stock one: instead of dropping, creating and # initializing the database for each test, it create and initialize the db only # once, then it truncate the tables. This is needed to have acceptable test # performances. class SwhDatabaseJanitor(DatabaseJanitor): def __init__( self, user: str, host: str, port: str, db_name: str, version: Union[str, float, Version], dump_files: str = DUMP_FILES, ) -> None: super().__init__(user, host, port, db_name, version) self.dump_files = sorted(glob.glob(dump_files), key=sortkey) def db_setup(self): with psycopg2.connect( dbname=self.db_name, user=self.user, host=self.host, port=self.port, ) as cnx: with cnx.cursor() as cur: for fname in self.dump_files: with open(fname) as fobj: sql = fobj.read().replace("concurrently", "").strip() if sql: cur.execute(sql) cnx.commit() def db_reset(self): with psycopg2.connect( dbname=self.db_name, user=self.user, host=self.host, port=self.port, ) as cnx: with cnx.cursor() as cur: cur.execute( "SELECT table_name FROM information_schema.tables " "WHERE table_schema = %s", ("public",), ) tables = set(table for (table,) in cur.fetchall()) for table in tables: cur.execute("truncate table %s cascade" % table) cur.execute( "SELECT sequence_name FROM information_schema.sequences " "WHERE sequence_schema = %s", ("public",), ) seqs = set(seq for (seq,) in cur.fetchall()) for seq in seqs: cur.execute("ALTER SEQUENCE %s RESTART;" % seq) cnx.commit() def init(self): with self.cursor() as cur: cur.execute( "SELECT COUNT(1) FROM pg_database WHERE datname=%s;", (self.db_name,) ) db_exists = cur.fetchone()[0] == 1 if db_exists: cur.execute( "UPDATE pg_database SET datallowconn=true " "WHERE datname = %s;", (self.db_name,), ) if db_exists: self.db_reset() else: with self.cursor() as cur: cur.execute('CREATE DATABASE "{}";'.format(self.db_name)) self.db_setup() def drop(self): pid_column = "pid" with self.cursor() as cur: cur.execute( "UPDATE pg_database SET datallowconn=false " "WHERE datname = %s;", (self.db_name,), ) cur.execute( "SELECT pg_terminate_backend(pg_stat_activity.{})" "FROM pg_stat_activity " "WHERE pg_stat_activity.datname = %s;".format(pid_column), (self.db_name,), ) @pytest.fixture def sample_data() -> Dict: """Pre-defined sample storage object data to manipulate Returns: Dict of data (keys: content, directory, revision, release, person, origin) """ - from .storage_data import data - return { "content": [data.cont, data.cont2], "content_metadata": [data.cont3], "skipped_content": [data.skipped_cont, data.skipped_cont2], "person": [data.person], "directory": [data.dir2, data.dir], "revision": [data.revision, data.revision2, data.revision3], "release": [data.release, data.release2, data.release3], "snapshot": [data.snapshot], "origin": [data.origin, data.origin2], "fetcher": [data.metadata_fetcher], "authority": [data.metadata_authority], "origin_metadata": [data.origin_metadata, data.origin_metadata2], } diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py index 52d9b4f9..7598d9a1 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/tests/conftest.py @@ -1,272 +1,75 @@ -# Copyright (C) 2019 The Software Heritage developers +# Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information -import glob import pytest import multiprocessing.util -from typing import Union -from os import path, environ from hypothesis import settings -from typing import Dict try: import pytest_cov.embed except ImportError: pytest_cov = None -from pytest_postgresql import factories -from pytest_postgresql.janitor import DatabaseJanitor, psycopg2, Version - -import swh.storage - -from swh.core.utils import numfile_sortkey as sortkey from swh.model.tests.generate_testdata import gen_contents, gen_origins from swh.model.model import ( Content, Directory, Origin, OriginVisit, Release, Revision, SkippedContent, Snapshot, ) +from swh.storage.pytest_plugin import * # noqa # for retro compatibility OBJECT_FACTORY = { "content": Content.from_dict, "directory": Directory.from_dict, "origin": Origin.from_dict, "origin_visit": OriginVisit.from_dict, "release": Release.from_dict, "revision": Revision.from_dict, "skipped_content": SkippedContent.from_dict, "snapshot": Snapshot.from_dict, } -SQL_DIR = path.join(path.dirname(swh.storage.__file__), "sql") - -environ["LC_ALL"] = "C.UTF-8" - -DUMP_FILES = path.join(SQL_DIR, "*.sql") # define tests profile. Full documentation is at: # https://hypothesis.readthedocs.io/en/latest/settings.html#settings-profiles settings.register_profile("fast", max_examples=5, deadline=5000) settings.register_profile("slow", max_examples=20, deadline=5000) if pytest_cov is not None: # pytest_cov + multiprocessing can cause a segmentation fault when starting # the child process ; so we're # removing pytest-coverage's hook that runs when a child process starts. # This means code run in child processes won't be counted in the coverage # report, but this is not an issue because the only code that runs only in # child processes is the RPC server. for (key, value) in multiprocessing.util._afterfork_registry.items(): if value is pytest_cov.embed.multiprocessing_start: del multiprocessing.util._afterfork_registry[key] break else: assert False, "missing pytest_cov.embed.multiprocessing_start?" -@pytest.fixture -def swh_storage_backend_config(postgresql_proc, swh_storage_postgresql): - yield { - "cls": "local", - "db": "postgresql://{user}@{host}:{port}/{dbname}".format( - host=postgresql_proc.host, - port=postgresql_proc.port, - user="postgres", - dbname="tests", - ), - "objstorage": {"cls": "memory", "args": {}}, - "journal_writer": {"cls": "memory",}, - } - - -@pytest.fixture -def swh_storage(swh_storage_backend_config): - return swh.storage.get_storage(cls="validate", storage=swh_storage_backend_config) - - @pytest.fixture def swh_contents(swh_storage): contents = gen_contents(n=20) swh_storage.content_add([c for c in contents if c["status"] != "absent"]) swh_storage.skipped_content_add([c for c in contents if c["status"] == "absent"]) return contents @pytest.fixture def swh_origins(swh_storage): origins = gen_origins(n=100) swh_storage.origin_add(origins) return origins - - -# the postgres_fact factory fixture below is mostly a copy of the code -# from pytest-postgresql. We need a custom version here to be able to -# specify our version of the DBJanitor we use. -def postgresql_fact(process_fixture_name, db_name=None, dump_files=DUMP_FILES): - @pytest.fixture - def postgresql_factory(request): - """ - Fixture factory for PostgreSQL. - - :param FixtureRequest request: fixture request object - :rtype: psycopg2.connection - :returns: postgresql client - """ - config = factories.get_config(request) - if not psycopg2: - raise ImportError("No module named psycopg2. Please install it.") - proc_fixture = request.getfixturevalue(process_fixture_name) - - # _, config = try_import('psycopg2', request) - pg_host = proc_fixture.host - pg_port = proc_fixture.port - pg_user = proc_fixture.user - pg_options = proc_fixture.options - pg_db = db_name or config["dbname"] - with SwhDatabaseJanitor( - pg_user, - pg_host, - pg_port, - pg_db, - proc_fixture.version, - dump_files=dump_files, - ): - connection = psycopg2.connect( - dbname=pg_db, - user=pg_user, - host=pg_host, - port=pg_port, - options=pg_options, - ) - yield connection - connection.close() - - return postgresql_factory - - -swh_storage_postgresql = postgresql_fact("postgresql_proc") - - -# This version of the DatabaseJanitor implement a different setup/teardown -# behavior than than the stock one: instead of dropping, creating and -# initializing the database for each test, it create and initialize the db only -# once, then it truncate the tables. This is needed to have acceptable test -# performances. -class SwhDatabaseJanitor(DatabaseJanitor): - def __init__( - self, - user: str, - host: str, - port: str, - db_name: str, - version: Union[str, float, Version], - dump_files: str = DUMP_FILES, - ) -> None: - super().__init__(user, host, port, db_name, version) - self.dump_files = sorted(glob.glob(dump_files), key=sortkey) - - def db_setup(self): - with psycopg2.connect( - dbname=self.db_name, user=self.user, host=self.host, port=self.port, - ) as cnx: - with cnx.cursor() as cur: - for fname in self.dump_files: - with open(fname) as fobj: - sql = fobj.read().replace("concurrently", "").strip() - if sql: - cur.execute(sql) - cnx.commit() - - def db_reset(self): - with psycopg2.connect( - dbname=self.db_name, user=self.user, host=self.host, port=self.port, - ) as cnx: - with cnx.cursor() as cur: - cur.execute( - "SELECT table_name FROM information_schema.tables " - "WHERE table_schema = %s", - ("public",), - ) - tables = set(table for (table,) in cur.fetchall()) - for table in tables: - cur.execute("truncate table %s cascade" % table) - - cur.execute( - "SELECT sequence_name FROM information_schema.sequences " - "WHERE sequence_schema = %s", - ("public",), - ) - seqs = set(seq for (seq,) in cur.fetchall()) - for seq in seqs: - cur.execute("ALTER SEQUENCE %s RESTART;" % seq) - cnx.commit() - - def init(self): - with self.cursor() as cur: - cur.execute( - "SELECT COUNT(1) FROM pg_database WHERE datname=%s;", (self.db_name,) - ) - db_exists = cur.fetchone()[0] == 1 - if db_exists: - cur.execute( - "UPDATE pg_database SET datallowconn=true " "WHERE datname = %s;", - (self.db_name,), - ) - - if db_exists: - self.db_reset() - else: - with self.cursor() as cur: - cur.execute('CREATE DATABASE "{}";'.format(self.db_name)) - self.db_setup() - - def drop(self): - pid_column = "pid" - with self.cursor() as cur: - cur.execute( - "UPDATE pg_database SET datallowconn=false " "WHERE datname = %s;", - (self.db_name,), - ) - cur.execute( - "SELECT pg_terminate_backend(pg_stat_activity.{})" - "FROM pg_stat_activity " - "WHERE pg_stat_activity.datname = %s;".format(pid_column), - (self.db_name,), - ) - - -@pytest.fixture -def sample_data() -> Dict: - """Pre-defined sample storage object data to manipulate - - Returns: - Dict of data (keys: content, directory, revision, release, person, - origin) - - """ - from .storage_data import data - - return { - "content": [data.cont, data.cont2], - "content_metadata": [data.cont3], - "skipped_content": [data.skipped_cont, data.skipped_cont2], - "person": [data.person], - "directory": [data.dir2, data.dir], - "revision": [data.revision, data.revision2, data.revision3], - "release": [data.release, data.release2, data.release3], - "snapshot": [data.snapshot], - "origin": [data.origin, data.origin2], - "fetcher": [data.metadata_fetcher], - "authority": [data.metadata_authority], - "origin_metadata": [data.origin_metadata, data.origin_metadata2], - } diff --git a/swh/storage/tests/data/storage.yml b/swh/storage/tests/data/storage.yml new file mode 100644 index 00000000..97f9f67b --- /dev/null +++ b/swh/storage/tests/data/storage.yml @@ -0,0 +1,13 @@ +storage: + cls: local + args: + db: dbname=%s + + objstorage: + cls: pathslicing + args: + root: TMPDIR + slicing: "0:1/1:5" + + journal_writer: + cls: inmemory