diff --git a/.gitignore b/.gitignore deleted file mode 100644 index d570526..0000000 --- a/.gitignore +++ /dev/null @@ -1,11 +0,0 @@ -*.pyc -*.sw? -*~ -.coverage -.eggs/ -__pycache__ -*.egg-info/ -build/ -dist/ -version.txt -.tox/ diff --git a/AUTHORS b/AUTHORS deleted file mode 100644 index 2d0a34a..0000000 --- a/AUTHORS +++ /dev/null @@ -1,3 +0,0 @@ -Copyright (C) 2015 The Software Heritage developers - -See http://www.softwareheritage.org/ for more information. diff --git a/LICENSE b/LICENSE deleted file mode 100644 index 94a9ed0..0000000 --- a/LICENSE +++ /dev/null @@ -1,674 +0,0 @@ - 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/MANIFEST.in b/MANIFEST.in index e7c46fc..1271b63 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,4 +1,5 @@ include Makefile include requirements.txt include requirements-swh.txt include version.txt +include README.md diff --git a/PKG-INFO b/PKG-INFO index 1a14a8a..f761f9a 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,29 +1,29 @@ Metadata-Version: 2.1 Name: swh.loader.core -Version: 0.0.35 +Version: 0.0.39 Summary: Software Heritage Base Loader Home-page: https://forge.softwareheritage.org/diffusion/DLDBASE 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-loader-core +Project-URL: Funding, https://www.softwareheritage.org/donate +Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Description: SWH-loader-core =============== The Software Heritage Core Loader is a low-level loading utilities and helpers used by other loaders. The main entry points are classes: - :class:`swh.loader.core.loader.SWHLoader` for stateful loaders - :class:`swh.loader.core.loader.SWHStatelessLoader` for stateless loaders 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 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/debian/changelog b/debian/changelog deleted file mode 100644 index f1a89d2..0000000 --- a/debian/changelog +++ /dev/null @@ -1,5 +0,0 @@ -swh-loader-core (0.0.1-1) unstable; urgency=low - - * - - -- Antoine R. Dumont (@ardumont) Wed, 13 Apr 2016 16:49:17 +0200 diff --git a/debian/compat b/debian/compat deleted file mode 100644 index ec63514..0000000 --- a/debian/compat +++ /dev/null @@ -1 +0,0 @@ -9 diff --git a/debian/control b/debian/control deleted file mode 100644 index 4568816..0000000 --- a/debian/control +++ /dev/null @@ -1,33 +0,0 @@ -Source: swh-loader-core -Maintainer: Software Heritage developers -Section: python -Priority: optional -Build-Depends: debhelper (>= 9), - dh-python (>= 2), - python3-all, - python3-pytest, - python3-psutil, - python3-retrying, - python3-setuptools, - python3-swh.core, - python3-swh.model (>= 0.0.18~), - python3-swh.storage (>= 0.0.97~), - python3-vcversioner -Standards-Version: 3.9.6 -Homepage: https://forge.softwareheritage.org/diffusion/60/ - -Package: python3-swh.loader.core -Architecture: all -Depends: python3-swh.core, - python3-swh.model (>= 0.0.18~), - python3-swh.storage (>= 0.0.97~), - ${misc:Depends}, - ${python3:Depends} -Breaks: python3-swh.deposit.loader (<< 0.0.48~), - python3-swh.loader.debian (<< 0.0.9~), - python3-swh.loader.dir (<< 0.0.31~), - python3-swh.loader.git (<< 0.0.36~), - python3-swh.loader.mercurial (<< 0.0.3~), - python3-swh.loader.svn (<< 0.0.35~), - python3-swh.loader.tar (<< 0.0.33~) -Description: Software Heritage Loader Core diff --git a/debian/copyright b/debian/copyright deleted file mode 100644 index 9430897..0000000 --- a/debian/copyright +++ /dev/null @@ -1,22 +0,0 @@ -Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/ - -Files: * -Copyright: 2015-2016 The Software Heritage developers -License: GPL-3+ - -License: GPL-3+ - 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 . - . - On Debian systems, the complete text of the GNU General Public - License version 3 can be found in `/usr/share/common-licenses/GPL-3'. diff --git a/debian/rules b/debian/rules deleted file mode 100755 index ca4338b..0000000 --- a/debian/rules +++ /dev/null @@ -1,11 +0,0 @@ -#!/usr/bin/make -f - -export PYBUILD_NAME=swh.loader.core -export export PYBUILD_TEST_ARGS=-m 'not db' - -%: - dh $@ --with python3 --buildsystem=pybuild - -override_dh_install: - dh_install - rm -v $(CURDIR)/debian/python3-*/usr/lib/python*/dist-packages/swh/__init__.py diff --git a/debian/source/format b/debian/source/format deleted file mode 100644 index 163aaf8..0000000 --- a/debian/source/format +++ /dev/null @@ -1 +0,0 @@ -3.0 (quilt) diff --git a/docs/.gitignore b/docs/.gitignore deleted file mode 100644 index f6b5c55..0000000 --- a/docs/.gitignore +++ /dev/null @@ -1,4 +0,0 @@ -_build/ -apidoc/ -*-stamp -README.md diff --git a/docs/Makefile b/docs/Makefile deleted file mode 100644 index c56b9f1..0000000 --- a/docs/Makefile +++ /dev/null @@ -1,6 +0,0 @@ -include ../../swh-docs/Makefile.sphinx - -html: copy_md - -copy_md: - cp ../README.md ./ diff --git a/docs/_static/.placeholder b/docs/_static/.placeholder deleted file mode 100644 index e69de29..0000000 diff --git a/docs/_templates/.placeholder b/docs/_templates/.placeholder deleted file mode 100644 index e69de29..0000000 diff --git a/docs/conf.py b/docs/conf.py deleted file mode 100644 index 190deb7..0000000 --- a/docs/conf.py +++ /dev/null @@ -1 +0,0 @@ -from swh.docs.sphinx.conf import * # NoQA diff --git a/docs/index.rst b/docs/index.rst deleted file mode 100644 index 4973323..0000000 --- a/docs/index.rst +++ /dev/null @@ -1,21 +0,0 @@ -.. _swh-loader-core: - -Software Heritage - Loader foundations -====================================== - -Low-level loading utilities and helpers used by other loaders. - - -.. toctree:: - :maxdepth: 2 - :caption: Contents: - - README.md - - -Indices and tables -================== - -* :ref:`genindex` -* :ref:`modindex` -* :ref:`search` diff --git a/requirements-test.txt b/requirements-test.txt deleted file mode 100644 index e079f8a..0000000 --- a/requirements-test.txt +++ /dev/null @@ -1 +0,0 @@ -pytest diff --git a/swh.loader.core.egg-info/PKG-INFO b/swh.loader.core.egg-info/PKG-INFO index 1a14a8a..f761f9a 100644 --- a/swh.loader.core.egg-info/PKG-INFO +++ b/swh.loader.core.egg-info/PKG-INFO @@ -1,29 +1,29 @@ Metadata-Version: 2.1 Name: swh.loader.core -Version: 0.0.35 +Version: 0.0.39 Summary: Software Heritage Base Loader Home-page: https://forge.softwareheritage.org/diffusion/DLDBASE 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-loader-core +Project-URL: Funding, https://www.softwareheritage.org/donate +Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Description: SWH-loader-core =============== The Software Heritage Core Loader is a low-level loading utilities and helpers used by other loaders. The main entry points are classes: - :class:`swh.loader.core.loader.SWHLoader` for stateful loaders - :class:`swh.loader.core.loader.SWHStatelessLoader` for stateless loaders 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 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.loader.core.egg-info/SOURCES.txt b/swh.loader.core.egg-info/SOURCES.txt index 99af5be..1a170b0 100644 --- a/swh.loader.core.egg-info/SOURCES.txt +++ b/swh.loader.core.egg-info/SOURCES.txt @@ -1,40 +1,24 @@ -.gitignore -AUTHORS -LICENSE MANIFEST.in Makefile README.md requirements-swh.txt -requirements-test.txt requirements.txt setup.py -tox.ini version.txt -debian/changelog -debian/compat -debian/control -debian/copyright -debian/rules -debian/source/format -docs/.gitignore -docs/Makefile -docs/conf.py -docs/index.rst -docs/_static/.placeholder -docs/_templates/.placeholder swh/__init__.py swh.loader.core.egg-info/PKG-INFO swh.loader.core.egg-info/SOURCES.txt swh.loader.core.egg-info/dependency_links.txt swh.loader.core.egg-info/requires.txt swh.loader.core.egg-info/top_level.txt swh/loader/__init__.py swh/loader/core/__init__.py swh/loader/core/converters.py swh/loader/core/loader.py swh/loader/core/queue.py swh/loader/core/utils.py swh/loader/core/tests/__init__.py swh/loader/core/tests/test_converters.py swh/loader/core/tests/test_loader.py -swh/loader/core/tests/test_queue.py \ No newline at end of file +swh/loader/core/tests/test_queue.py +swh/loader/core/tests/test_tests.py \ No newline at end of file diff --git a/swh.loader.core.egg-info/requires.txt b/swh.loader.core.egg-info/requires.txt index fdc0825..0e04639 100644 --- a/swh.loader.core.egg-info/requires.txt +++ b/swh.loader.core.egg-info/requires.txt @@ -1,9 +1,9 @@ -psutil +vcversioner retrying +psutil swh.core swh.model>=0.0.18 swh.storage>=0.0.97 -vcversioner [testing] pytest diff --git a/swh/loader/core/loader.py b/swh/loader/core/loader.py index 513b978..0065810 100644 --- a/swh/loader/core/loader.py +++ b/swh/loader/core/loader.py @@ -1,1005 +1,1009 @@ # Copyright (C) 2015-2018 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 datetime import logging import os import psycopg2 import requests import traceback import uuid from abc import ABCMeta, abstractmethod from retrying import retry from . import converters from swh.core import config from swh.storage import get_storage from .queue import QueuePerSizeAndNbUniqueElements from .queue import QueuePerNbUniqueElements def send_in_packets(objects, sender, packet_size, packet_size_bytes=None): - """Send `objects`, using the `sender`, in packets of `packet_size` objects (and - of max `packet_size_bytes`). + """Send `objects`, using the `sender`, in packets of `packet_size` objects + (and of max `packet_size_bytes`). """ formatted_objects = [] count = 0 if not packet_size_bytes: packet_size_bytes = 0 for obj in objects: if not obj: continue formatted_objects.append(obj) if packet_size_bytes: count += obj['length'] if len(formatted_objects) >= packet_size or count > packet_size_bytes: sender(formatted_objects) formatted_objects = [] count = 0 if formatted_objects: sender(formatted_objects) def retry_loading(error): """Retry policy when the database raises an integrity error""" exception_classes = [ # raised when two parallel insertions insert the same data. psycopg2.IntegrityError, # raised when uWSGI restarts and hungs up on the worker. requests.exceptions.ConnectionError, ] if not any(isinstance(error, exc) for exc in exception_classes): return False logger = logging.getLogger('swh.loader') error_name = error.__module__ + '.' + error.__class__.__name__ logger.warning('Retry loading a batch', exc_info=False, extra={ 'swh_type': 'storage_retry', 'swh_exception_type': error_name, 'swh_exception': traceback.format_exception( error.__class__, error, error.__traceback__, ), }) return True -class SWHLoader(config.SWHConfig, metaclass=ABCMeta): +class BufferedLoader(config.SWHConfig, metaclass=ABCMeta): """Mixin base class for loader. To use this class, you must: - inherit from this class - and implement the @abstractmethod methods: - :func:`prepare`: First step executed by the loader to prepare some state needed by the `func`:load method. - :func:`get_origin`: Retrieve the origin that is currently being loaded. - :func:`fetch_data`: Fetch the data is actually the method to implement to compute data to inject in swh (through the store_data method) - :func:`store_data`: Store data fetched. - :func:`visit_status`: Explicit status of the visit ('partial' or 'full') - :func:`load_status`: Explicit status of the loading, for use by the scheduler (eventful/uneventful/temporary failure/permanent failure). - :func:`cleanup`: Last step executed by the loader. The entry point for the resulting loader is :func:`load`. You can take a look at some example classes: - :class:`BaseSvnLoader` - :class:`TarLoader` - :class:`DirLoader` - :class:`DebianLoader` """ CONFIG_BASE_FILENAME = None DEFAULT_CONFIG = { 'storage': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5002/', } }), 'send_contents': ('bool', True), 'send_directories': ('bool', True), 'send_revisions': ('bool', True), 'send_releases': ('bool', True), 'send_snapshot': ('bool', True), 'save_data': ('bool', False), 'save_data_path': ('str', ''), # Number of contents 'content_packet_size': ('int', 10000), # packet of 100Mib contents 'content_packet_size_bytes': ('int', 100 * 1024 * 1024), 'directory_packet_size': ('int', 25000), 'revision_packet_size': ('int', 100000), 'release_packet_size': ('int', 100000), 'occurrence_packet_size': ('int', 100000), } ADDITIONAL_CONFIG = {} - def __init__(self, logging_class, config=None): + def __init__(self, logging_class=None, config=None): if config: self.config = config else: self.config = self.parse_config_file( additional_configs=[self.ADDITIONAL_CONFIG]) self.storage = get_storage(**self.config['storage']) + if logging_class is None: + logging_class = '%s.%s' % (self.__class__.__module__, + self.__class__.__name__) self.log = logging.getLogger(logging_class) self.contents = QueuePerSizeAndNbUniqueElements( key='sha1', max_nb_elements=self.config['content_packet_size'], max_size=self.config['content_packet_size_bytes']) self.contents_seen = set() self.directories = QueuePerNbUniqueElements( key='id', max_nb_elements=self.config['directory_packet_size']) self.directories_seen = set() self.revisions = QueuePerNbUniqueElements( key='id', max_nb_elements=self.config['revision_packet_size']) self.revisions_seen = set() self.releases = QueuePerNbUniqueElements( key='id', max_nb_elements=self.config['release_packet_size']) self.releases_seen = set() self.snapshot = None _log = logging.getLogger('requests.packages.urllib3.connectionpool') _log.setLevel(logging.WARN) self.counters = { 'contents': 0, 'directories': 0, 'revisions': 0, 'releases': 0, } # Make sure the config is sane save_data = self.config.get('save_data') if save_data: path = self.config['save_data_path'] os.stat(path) if not os.access(path, os.R_OK | os.W_OK): raise PermissionError("Permission denied: %r" % path) def save_data(self): """Save the data associated to the current load""" raise NotImplementedError def get_save_data_path(self): """The path to which we save the data""" if not hasattr(self, '__save_data_path'): origin_id = self.origin_id year = str(self.visit_date.year) path = os.path.join( self.config['save_data_path'], "%04d" % (origin_id % 10000), "%08d" % origin_id, year, ) os.makedirs(path, exist_ok=True) self.__save_data_path = path return self.__save_data_path @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_origin(self, origin): log_id = str(uuid.uuid4()) self.log.debug('Creating %s origin for %s' % (origin['type'], origin['url']), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'origin', 'swh_num': 1, 'swh_id': log_id }) origin_id = self.storage.origin_add_one(origin) self.log.debug('Done creating %s origin for %s' % (origin['type'], origin['url']), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'origin', 'swh_num': 1, 'swh_id': log_id }) return origin_id @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_origin_visit(self, origin_id, visit_date): log_id = str(uuid.uuid4()) self.log.debug( 'Creating origin_visit for origin %s at time %s' % ( origin_id, visit_date), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'origin_visit', 'swh_num': 1, 'swh_id': log_id }) origin_visit = self.storage.origin_visit_add(origin_id, visit_date) self.log.debug( 'Done Creating origin_visit for origin %s at time %s' % ( origin_id, visit_date), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'origin_visit', 'swh_num': 1, 'swh_id': log_id }) return origin_visit @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_tool(self, tool): log_id = str(uuid.uuid4()) self.log.debug( 'Creating tool with name %s version %s configuration %s' % ( tool['name'], tool['version'], tool['configuration']), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'tool', 'swh_num': 1, 'swh_id': log_id }) - tools = self.storage.tool_add([tool]) + tools = list(self.storage.tool_add([tool])) tool_id = tools[0]['id'] self.log.debug( 'Done creating tool with name %s version %s and configuration %s' % ( # noqa tool['name'], tool['version'], tool['configuration']), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'tool', 'swh_num': 1, 'swh_id': log_id }) return tool_id @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_provider(self, provider): log_id = str(uuid.uuid4()) self.log.debug( 'Creating metadata_provider with name %s type %s url %s' % ( provider['provider_name'], provider['provider_type'], provider['provider_url']), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'metadata_provider', 'swh_num': 1, 'swh_id': log_id }) # FIXME: align metadata_provider_add with indexer_configuration_add _provider = self.storage.metadata_provider_get_by(provider) if _provider and 'id' in _provider: provider_id = _provider['id'] else: provider_id = self.storage.metadata_provider_add( provider['provider_name'], provider['provider_type'], provider['provider_url'], provider['metadata']) self.log.debug( 'Done creating metadata_provider with name %s type %s url %s' % ( provider['provider_name'], provider['provider_type'], provider['provider_url']), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'metadata_provider', 'swh_num': 1, 'swh_id': log_id }) return provider_id @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_origin_metadata(self, origin_id, visit_date, provider_id, tool_id, metadata): log_id = str(uuid.uuid4()) self.log.debug( 'Creating origin_metadata for origin %s at time %s with provider_id %s and tool_id %s' % ( # noqa origin_id, visit_date, provider_id, tool_id), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'origin_metadata', 'swh_num': 1, 'swh_id': log_id }) self.storage.origin_metadata_add(origin_id, visit_date, provider_id, tool_id, metadata) self.log.debug( 'Done Creating origin_metadata for origin %s at time %s with provider %s and tool %s' % ( # noqa origin_id, visit_date, provider_id, tool_id), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'origin_metadata', 'swh_num': 1, 'swh_id': log_id }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def update_origin_visit(self, origin_id, visit, status): log_id = str(uuid.uuid4()) self.log.debug( 'Updating origin_visit for origin %s with status %s' % ( origin_id, status), extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'origin_visit', 'swh_num': 1, 'swh_id': log_id }) self.storage.origin_visit_update(origin_id, visit, status) self.log.debug( 'Done updating origin_visit for origin %s with status %s' % ( origin_id, status), extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'origin_visit', 'swh_num': 1, 'swh_id': log_id }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_contents(self, content_list): """Actually send properly formatted contents to the database. """ num_contents = len(content_list) if num_contents > 0: log_id = str(uuid.uuid4()) self.log.debug("Sending %d contents" % num_contents, extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'content', 'swh_num': num_contents, 'swh_id': log_id, }) self.storage.content_add(content_list) self.counters['contents'] += num_contents self.log.debug("Done sending %d contents" % num_contents, extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'content', 'swh_num': num_contents, 'swh_id': log_id, }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_directories(self, directory_list): """Actually send properly formatted directories to the database. """ num_directories = len(directory_list) if num_directories > 0: log_id = str(uuid.uuid4()) self.log.debug("Sending %d directories" % num_directories, extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'directory', 'swh_num': num_directories, 'swh_id': log_id, }) self.storage.directory_add(directory_list) self.counters['directories'] += num_directories self.log.debug("Done sending %d directories" % num_directories, extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'directory', 'swh_num': num_directories, 'swh_id': log_id, }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_revisions(self, revision_list): """Actually send properly formatted revisions to the database. """ num_revisions = len(revision_list) if num_revisions > 0: log_id = str(uuid.uuid4()) self.log.debug("Sending %d revisions" % num_revisions, extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'revision', 'swh_num': num_revisions, 'swh_id': log_id, }) self.storage.revision_add(revision_list) self.counters['revisions'] += num_revisions self.log.debug("Done sending %d revisions" % num_revisions, extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'revision', 'swh_num': num_revisions, 'swh_id': log_id, }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_releases(self, release_list): """Actually send properly formatted releases to the database. """ num_releases = len(release_list) if num_releases > 0: log_id = str(uuid.uuid4()) self.log.debug("Sending %d releases" % num_releases, extra={ 'swh_type': 'storage_send_start', 'swh_content_type': 'release', 'swh_num': num_releases, 'swh_id': log_id, }) self.storage.release_add(release_list) self.counters['releases'] += num_releases self.log.debug("Done sending %d releases" % num_releases, extra={ 'swh_type': 'storage_send_end', 'swh_content_type': 'release', 'swh_num': num_releases, 'swh_id': log_id, }) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def send_snapshot(self, snapshot): self.storage.snapshot_add(self.origin_id, self.visit, snapshot) @retry(retry_on_exception=retry_loading, stop_max_attempt_number=3) def filter_missing_contents(self, contents): """Return only the contents missing from swh""" max_content_size = self.config['content_size_limit'] contents_per_key = {} content_key = 'blake2s256' for content in contents: if content[content_key] in self.contents_seen: continue key = content[content_key] contents_per_key[key] = content self.contents_seen.add(key) for key in self.storage.content_missing( list(contents_per_key.values()), key_hash=content_key ): yield converters.content_for_storage( contents_per_key[key], max_content_size=max_content_size, origin_id=self.origin_id, ) def bulk_send_contents(self, contents): """Format contents as swh contents and send them to the database. """ threshold_reached = self.contents.add( self.filter_missing_contents(contents)) if threshold_reached: self.send_batch_contents(self.contents.pop()) def filter_missing_directories(self, directories): """Return only directories missing from swh""" directories_per_id = {} search_dirs = [] for directory in directories: dir_id = directory['id'] if dir_id in self.directories_seen: continue search_dirs.append(dir_id) directories_per_id[dir_id] = directory self.directories_seen.add(dir_id) for dir_id in self.storage.directory_missing(search_dirs): yield directories_per_id[dir_id] def bulk_send_directories(self, directories): """Send missing directories to the database""" threshold_reached = self.directories.add( self.filter_missing_directories(directories)) if threshold_reached: self.send_batch_contents(self.contents.pop()) self.send_batch_directories(self.directories.pop()) def filter_missing_revisions(self, revisions): """Return only revisions missing from swh""" revisions_per_id = {} search_revs = [] for revision in revisions: rev_id = revision['id'] if rev_id in self.revisions_seen: continue search_revs.append(rev_id) revisions_per_id[rev_id] = revision self.revisions_seen.add(rev_id) for rev_id in self.storage.revision_missing(search_revs): yield revisions_per_id[rev_id] def bulk_send_revisions(self, revisions): """Send missing revisions to the database""" threshold_reached = self.revisions.add( self.filter_missing_revisions(revisions)) if threshold_reached: self.send_batch_contents(self.contents.pop()) self.send_batch_directories(self.directories.pop()) self.send_batch_revisions(self.revisions.pop()) def filter_missing_releases(self, releases): """Return only releases missing from swh""" releases_per_id = {} search_rels = [] for release in releases: rel_id = release['id'] if rel_id in self.releases_seen: continue search_rels.append(rel_id) releases_per_id[rel_id] = release self.releases_seen.add(rel_id) for rel_id in self.storage.release_missing(search_rels): yield releases_per_id[rel_id] def bulk_send_releases(self, releases): """Send missing releases to the database""" threshold_reached = self.releases.add( self.filter_missing_releases(releases)) if threshold_reached: self.send_batch_contents(self.contents.pop()) self.send_batch_directories(self.directories.pop()) self.send_batch_revisions(self.revisions.pop()) self.send_batch_releases(self.releases.pop()) def bulk_send_snapshot(self, snapshot): """Send missing releases to the database""" self.send_batch_contents(self.contents.pop()) self.send_batch_directories(self.directories.pop()) self.send_batch_revisions(self.revisions.pop()) self.send_batch_releases(self.releases.pop()) self.send_snapshot(snapshot) def maybe_load_contents(self, contents): """Load contents in swh-storage if need be. """ if self.config['send_contents']: self.bulk_send_contents(contents) def maybe_load_directories(self, directories): """Load directories in swh-storage if need be. """ if self.config['send_directories']: self.bulk_send_directories(directories) def maybe_load_revisions(self, revisions): """Load revisions in swh-storage if need be. """ if self.config['send_revisions']: self.bulk_send_revisions(revisions) def maybe_load_releases(self, releases): """Load releases in swh-storage if need be. """ if self.config['send_releases']: self.bulk_send_releases(releases) def maybe_load_snapshot(self, snapshot): """Load the snapshot in swh-storage if need be.""" if self.config['send_snapshot']: self.bulk_send_snapshot(snapshot) def send_batch_contents(self, contents): """Send contents batches to the storage""" packet_size = self.config['content_packet_size'] packet_size_bytes = self.config['content_packet_size_bytes'] send_in_packets(contents, self.send_contents, packet_size, packet_size_bytes=packet_size_bytes) def send_batch_directories(self, directories): """Send directories batches to the storage""" packet_size = self.config['directory_packet_size'] send_in_packets(directories, self.send_directories, packet_size) def send_batch_revisions(self, revisions): """Send revisions batches to the storage""" packet_size = self.config['revision_packet_size'] send_in_packets(revisions, self.send_revisions, packet_size) def send_batch_releases(self, releases): """Send releases batches to the storage """ packet_size = self.config['release_packet_size'] send_in_packets(releases, self.send_releases, packet_size) def open_fetch_history(self): return self.storage.fetch_history_start(self.origin_id) def close_fetch_history_success(self, fetch_history_id): data = { 'status': True, 'result': self.counters, } return self.storage.fetch_history_end(fetch_history_id, data) def close_fetch_history_failure(self, fetch_history_id): import traceback data = { 'status': False, 'stderr': traceback.format_exc(), } if self.counters['contents'] > 0 or \ self.counters['directories'] > 0 or \ self.counters['revisions'] > 0 or \ self.counters['releases'] > 0: data['result'] = self.counters return self.storage.fetch_history_end(fetch_history_id, data) def flush(self): """Flush any potential dangling data not sent to swh-storage. Bypass the maybe_load_* methods which awaits threshold reached signal. We actually want to store those as we are done loading. """ contents = self.contents.pop() directories = self.directories.pop() revisions = self.revisions.pop() releases = self.releases.pop() # and send those to storage if asked if self.config['send_contents']: self.send_batch_contents(contents) if self.config['send_contents']: self.send_batch_directories(directories) if self.config['send_revisions']: self.send_batch_revisions(revisions) if self.config['send_releases']: self.send_batch_releases(releases) if self.config['send_snapshot'] and self.snapshot: self.send_snapshot(self.snapshot) def prepare_metadata(self): """First step for origin_metadata insertion, resolving the - provider_ id and the tool_id by fetching data from the storage + provider_id and the tool_id by fetching data from the storage or creating tool and provider on the fly if the data isn't available """ origin_metadata = self.origin_metadata tool = origin_metadata['tool'] try: tool_id = self.send_tool(tool) self.origin_metadata['tool']['tool_id'] = tool_id except Exception: self.log.exception('Problem when storing new tool') raise provider = origin_metadata['provider'] try: provider_id = self.send_provider(provider) self.origin_metadata['provider']['provider_id'] = provider_id except Exception: self.log.exception('Problem when storing new provider') raise @abstractmethod def cleanup(self): """Last step executed by the loader. """ pass @abstractmethod def prepare_origin_visit(self, *args, **kwargs): """First step executed by the loader to prepare origin and visit references. Set/update self.origin, self.origin_id and optionally self.origin_url, self.visit_date. """ pass def _store_origin_visit(self): """Store origin and visit references. Sets the self.origin_visit and self.visit references. """ origin_id = self.origin.get('id') if origin_id: self.origin_id = origin_id else: self.origin_id = self.send_origin(self.origin) self.origin['id'] = self.origin_id if not self.visit_date: # now as default visit_date if not provided self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) self.origin_visit = self.send_origin_visit( self.origin_id, self.visit_date) self.visit = self.origin_visit['visit'] @abstractmethod def prepare(self, *args, **kwargs): """Second step executed by the loader to prepare some state needed by the loader. """ pass def get_origin(self): """Get the origin that is currently being loaded. self.origin should be set in :func:`prepare_origin` Returns: dict: an origin ready to be sent to storage by :func:`origin_add_one`. """ return self.origin @abstractmethod def fetch_data(self): """Fetch the data from the source the loader is currently loading (ex: git/hg/svn/... repository). Returns: a value that is interpreted as a boolean. If True, fetch_data needs to be called again to complete loading. """ pass @abstractmethod def store_data(self): """Store fetched data in the database. Should call the :func:`maybe_load_xyz` methods, which handle the bundles sent to storage, rather than send directly. """ pass def store_metadata(self): """Store fetched metadata in the database. For more information, see implementation in :class:`DepositLoader`. """ pass def load_status(self): """Detailed loading status. Defaults to logging an eventful load. Returns: a dictionary that is eventually passed back as the task's result to the scheduler, allowing tuning of the task recurrence mechanism. """ return { 'status': 'eventful', } def post_load(self, success=True): """Permit the loader to do some additional actions according to status after the loading is done. The flag success indicates the loading's status. Defaults to doing nothing. This is up to the implementer of this method to make sure this does not break. Args: success (bool): the success status of the loading """ pass def visit_status(self): """Detailed visit status. Defaults to logging a full visit. """ return 'full' def pre_cleanup(self): """As a first step, will try and check for dangling data to cleanup. This should do its best to avoid raising issues. """ pass def load(self, *args, **kwargs): - """Loading logic for the loader to follow: + r"""Loading logic for the loader to follow: + + - 1. Call :meth:`prepare_origin_visit` to prepare the + origin and visit we will associate loading data to + - 2. Store the actual ``origin_visit`` to storage + - 3. Call :meth:`prepare` to prepare any eventual state + - 4. Call :meth:`get_origin` to get the origin we work with and store - - 1. def prepare_origin_visit(\*args, \**kwargs): Prepare the - origin and visit we will associate loading data to - - 2. Store the actual origin_visit to storage - - 3. def prepare(\*args, \**kwargs): Prepare any eventual state - - 4. def get_origin(): Get the origin we work with and store - while True: - - 5. def fetch_data(): Fetch the data to store - - 6. def store_data(): Store the data + - 5. Call :meth:`fetch_data` to fetch the data to store + - 6. Call :meth:`store_data` to store the data - - 7. def cleanup(): Clean up any eventual state put in place in prepare - method. + - 7. Call :meth:`cleanup` to clean up any eventual state put in place + in :meth:`prepare` method. """ try: self.pre_cleanup() except Exception: msg = 'Cleaning up dangling data failed! Continue loading.' - self.log.warn(msg) + self.log.warning(msg) self.prepare_origin_visit(*args, **kwargs) self._store_origin_visit() fetch_history_id = self.open_fetch_history() try: self.prepare(*args, **kwargs) while True: more_data_to_fetch = self.fetch_data() self.store_data() if not more_data_to_fetch: break self.store_metadata() self.close_fetch_history_success(fetch_history_id) self.update_origin_visit( self.origin_id, self.visit, status=self.visit_status()) self.post_load() except Exception: self.log.exception('Loading failure, updating to `partial` status', extra={ 'swh_task_args': args, 'swh_task_kwargs': kwargs, }) self.close_fetch_history_failure(fetch_history_id) self.update_origin_visit( self.origin_id, self.visit, status='partial') self.post_load(success=False) return {'status': 'failed'} finally: self.flush() self.cleanup() return self.load_status() -class SWHStatelessLoader(SWHLoader): - """This base class is a pattern for stateless loaders. +class UnbufferedLoader(BufferedLoader): + """This base class is a pattern for unbuffered loaders. - Stateless loaders are able to load all the data in one go. For + UnbufferedLoader loaders are able to load all the data in one go. For example, the loader defined in swh-loader-git :class:`BulkUpdater`. For other loaders (stateful one, (e.g :class:`SWHSvnLoader`), - inherit directly from :class:`SWHLoader`. + inherit directly from :class:`BufferedLoader`. """ ADDITIONAL_CONFIG = {} def __init__(self, logging_class=None, config=None): - super().__init__(logging_class=logging_class, config=None) + super().__init__(logging_class=logging_class, config=config) self.visit_date = None # possibly overridden in self.prepare method def cleanup(self): """Clean up an eventual state installed for computations.""" pass def has_contents(self): """Checks whether we need to load contents""" return True def get_contents(self): """Get the contents that need to be loaded""" raise NotImplementedError def has_directories(self): """Checks whether we need to load directories""" return True def get_directories(self): """Get the directories that need to be loaded""" raise NotImplementedError def has_revisions(self): """Checks whether we need to load revisions""" return True def get_revisions(self): """Get the revisions that need to be loaded""" raise NotImplementedError def has_releases(self): """Checks whether we need to load releases""" return True def get_releases(self): """Get the releases that need to be loaded""" raise NotImplementedError def get_snapshot(self): """Get the snapshot that needs to be loaded""" raise NotImplementedError def get_fetch_history_result(self): """Return the data to store in fetch_history for the current loader""" raise NotImplementedError def eventful(self): """Whether the load was eventful""" raise NotImplementedError def save_data(self): """Save the data associated to the current load""" raise NotImplementedError def flush(self): - """Stateless loader does not flush since it has no state to flush. + """Unbuffered loader does not flush since it has no state to flush. """ pass def store_data(self): if self.config['save_data']: self.save_data() if self.config['send_contents'] and self.has_contents(): self.send_batch_contents(self.get_contents()) if self.config['send_directories'] and self.has_directories(): self.send_batch_directories(self.get_directories()) if self.config['send_revisions'] and self.has_revisions(): self.send_batch_revisions(self.get_revisions()) if self.config['send_releases'] and self.has_releases(): self.send_batch_releases(self.get_releases()) if self.config['send_snapshot']: self.send_snapshot(self.get_snapshot()) diff --git a/swh/loader/core/tests/__init__.py b/swh/loader/core/tests/__init__.py index b29129a..07d008a 100644 --- a/swh/loader/core/tests/__init__.py +++ b/swh/loader/core/tests/__init__.py @@ -1,285 +1,227 @@ # Copyright (C) 2018 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 os import pytest import shutil import subprocess import tempfile from unittest import TestCase from swh.model import hashutil +from swh.model.hashutil import hash_to_bytes -@pytest.mark.fs -class BaseLoaderTest(TestCase): - """Mixin base loader test class. - - This allows to uncompress archives (mercurial, svn, git, - ... repositories) into a temporary folder so that the loader under - test can work with this. - - When setUp() is done, the following variables are defined: - - self.repo_url: can be used as an origin_url for example - - self.destination_path: can be used as a path to ingest the - repository. - - Args: - archive_name (str): Name of the archive holding the repository - (folder, repository, dump, etc...) - start_path (str): (mandatory) Path from where starting to look - for resources - filename (Optional[str]): Name of the filename/folder once the - archive is uncompressed. When the filename is not - provided, the archive name is used as a derivative. This - is used both for the self.repo_url and - self.destination_path computation (this one only when - provided) - resources_path (str): Folder name to look for archive - prefix_tmp_folder_name (str): Prefix name to name the temporary folder - uncompress_archive (bool): Uncompress the archive passed as - parameters (default to True). It so - happens we could avoid doing - anything to the tarball. - - """ - def setUp(self, archive_name, *, start_path, filename=None, - resources_path='resources', prefix_tmp_folder_name='', - uncompress_archive=True): - repo_path = os.path.join(start_path, resources_path, archive_name) - if not uncompress_archive: - # In that case, simply sets the archive's path - self.destination_path = repo_path - self.tmp_root_path = None - return - tmp_root_path = tempfile.mkdtemp( - prefix=prefix_tmp_folder_name, suffix='-tests') - # uncompress folder/repositories/dump for the loader to ingest - subprocess.check_output(['tar', 'xf', repo_path, '-C', tmp_root_path]) - # build the origin url (or some derivative form) - _fname = filename if filename else os.path.basename(archive_name) - self.repo_url = 'file://' + tmp_root_path + '/' + _fname - # where is the data to ingest? - if filename: - # archive holds one folder with name - self.destination_path = os.path.join(tmp_root_path, filename) - else: - self.destination_path = tmp_root_path - self.tmp_root_path = tmp_root_path - - def tearDown(self): - """Clean up temporary working directory - - """ - if self.tmp_root_path and os.path.exists(self.tmp_root_path): - shutil.rmtree(self.tmp_root_path) - - def state(self, _type): - return self.loader.state(_type) - - def _assertCountOk(self, type, expected_length, msg=None): +class BaseLoaderStorageTest: + def _assertCountEqual(self, type, expected_length, msg=None): """Check typed 'type' state to have the same expected length. """ - self.assertEqual(len(self.state(type)), expected_length, msg=msg) + self.storage.refresh_stat_counters() + self.assertEqual(self.storage.stat_counters()[type], + expected_length, msg=msg) def assertCountContents(self, len_expected_contents, msg=None): - self._assertCountOk('content', len_expected_contents, msg=msg) + self._assertCountEqual('content', len_expected_contents, msg=msg) def assertCountDirectories(self, len_expected_directories, msg=None): - self._assertCountOk('directory', len_expected_directories, msg=msg) + self._assertCountEqual('directory', len_expected_directories, + msg=msg) def assertCountReleases(self, len_expected_releases, msg=None): - self._assertCountOk('release', len_expected_releases, msg=msg) + self._assertCountEqual('release', len_expected_releases, msg=msg) def assertCountRevisions(self, len_expected_revisions, msg=None): - self._assertCountOk('revision', len_expected_revisions, msg=msg) + self._assertCountEqual('revision', len_expected_revisions, msg=msg) def assertCountSnapshots(self, len_expected_snapshot, msg=None): - self._assertCountOk('snapshot', len_expected_snapshot, msg=msg) + self._assertCountEqual('snapshot', len_expected_snapshot, msg=msg) + + def assertContentsContain(self, expected_contents): + """Check the provided content are a subset of the stored ones. + + Args: + expected_contents ([sha1]): List of content ids""" + self._assertCountEqual('content', len(expected_contents)) + missing = list(self.storage.content_missing( + {'sha1': hash_to_bytes(content_hash)} + for content_hash in expected_contents)) + self.assertEqual(missing, []) - def assertContentsOk(self, expected_contents): - self._assertCountOk('content', len(expected_contents)) - for content in self.state('content'): - content_id = hashutil.hash_to_hex(content['sha1']) - self.assertIn(content_id, expected_contents) + def assertDirectoriesContain(self, expected_directories): + """Check the provided directories are a subset of the stored ones. - def assertDirectoriesOk(self, expected_directories): - self._assertCountOk('directory', len(expected_directories)) - for _dir in self.state('directory'): - _dir_id = hashutil.hash_to_hex(_dir['id']) - self.assertIn(_dir_id, expected_directories) + Args: + expected_directories ([sha1]): List of directory ids.""" + self._assertCountEqual('directory', len(expected_directories)) + missing = list(self.storage.directory_missing( + hash_to_bytes(dir_) for dir_ in expected_directories)) + self.assertEqual(missing, []) - def assertReleasesOk(self, expected_releases): - """Check the loader's releases match the expected releases. + def assertReleasesContain(self, expected_releases): + """Check the provided releases are a subset of the stored ones. Args: - releases ([dict]): List of dictionaries representing swh releases. + releases (list): list of swh releases' identifiers. """ - self._assertCountOk('release', len(expected_releases)) - for i, rel in enumerate(self.state('release')): - rel_id = hashutil.hash_to_hex(rel['id']) - self.assertEqual(expected_releases[i], rel_id) + self._assertCountEqual('release', len(expected_releases)) + missing = list(self.storage.release_missing( + hash_to_bytes(rel) for rel in expected_releases)) + self.assertEqual(missing, []) - def assertRevisionsOk(self, expected_revisions): - """Check the loader's revisions match the expected revisions. + def assertRevisionsContain(self, expected_revisions): + """Check the provided revisions are a subset of the stored ones. Expects self.loader to be instantiated and ready to be inspected (meaning the loading took place). Args: expected_revisions (dict): Dict with key revision id, value the targeted directory id. """ - self._assertCountOk('revision', len(expected_revisions)) - for rev in self.state('revision'): - rev_id = hashutil.hash_to_hex(rev['id']) - directory_id = hashutil.hash_to_hex(rev['directory']) + self._assertCountEqual('revision', len(expected_revisions)) - self.assertEqual(expected_revisions[rev_id], directory_id) + revs = list(self.storage.revision_get( + hashutil.hash_to_bytes(rev_id) for rev_id in expected_revisions)) + self.assertNotIn(None, revs) + self.assertEqual( + {rev['id']: rev['directory'] for rev in revs}, + {hash_to_bytes(rev_id): hash_to_bytes(rev_dir) + for (rev_id, rev_dir) in expected_revisions.items()}) - def assertSnapshotOk(self, expected_snapshot, expected_branches=[]): + def assertSnapshotEqual(self, expected_snapshot, expected_branches=[]): """Check for snapshot match. Provide the hashes as hexadecimal, the conversion is done within the method. Args: expected_snapshot (str/dict): Either the snapshot identifier or the full snapshot expected_branches (dict): expected branches or nothing is the full snapshot is provided """ if isinstance(expected_snapshot, dict) and not expected_branches: expected_snapshot_id = expected_snapshot['id'] expected_branches = expected_snapshot['branches'] else: expected_snapshot_id = expected_snapshot - snapshots = self.state('snapshot') - self.assertEqual(len(snapshots), 1) + self._assertCountEqual('snapshot', 1) - snap = snapshots[0] - snap_id = hashutil.hash_to_hex(snap['id']) - self.assertEqual(snap_id, expected_snapshot_id) + snap = self.storage.snapshot_get(hash_to_bytes(expected_snapshot_id)) + self.assertIsNotNone(snap) def decode_target(target): if not target: return target target_type = target['target_type'] if target_type == 'alias': decoded_target = target['target'].decode('utf-8') else: decoded_target = hashutil.hash_to_hex(target['target']) return { 'target': decoded_target, 'target_type': target_type } branches = { branch.decode('utf-8'): decode_target(target) for branch, target in snap['branches'].items() } self.assertEqual(expected_branches, branches) - -class LoaderNoStorage: - """Mixin class to inhibit the persistence and keep in memory the data - sent for storage (for testing purposes). - - This overrides the core loader's behavior to store in a dict the - swh objects. - - cf. :class:`HgLoaderNoStorage`, :class:`SvnLoaderNoStorage`, etc... - - """ - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - self._state = { - 'content': [], - 'directory': [], - 'revision': [], - 'release': [], - 'snapshot': [], - } - - def state(self, type): - return self._state[type] - - def _add(self, type, l): - """Add without duplicates and keeping the insertion order. + def assertOriginMetadataContains(self, origin_type, origin_url, + expected_origin_metadata): + """Check the storage contains this metadata for the given origin. Args: - type (str): Type of objects concerned by the action - l ([object]): List of 'type' object + origin_type (str): type of origin ('deposit', 'git', 'svn', ...) + origin_url (str): URL of the origin + expected_origin_metadata (dict): + Extrinsic metadata of the origin + """ - col = self.state(type) - for o in l: - if o in col: - continue - col.append(o) - - def maybe_load_contents(self, all_contents): - self._add('content', all_contents) - - def maybe_load_directories(self, all_directories): - self._add('directory', all_directories) - - def maybe_load_revisions(self, all_revisions): - self._add('revision', all_revisions) - - def maybe_load_releases(self, all_releases): - self._add('release', all_releases) + origin = self.storage.origin_get( + dict(type=origin_type, url=origin_url)) + results = self.storage.origin_metadata_get_by(origin['id']) + self.assertEqual(len(results), 1, results) + result = results[0] + self.assertEqual(result['metadata'], expected_origin_metadata) - def maybe_load_snapshot(self, snapshot): - self._add('snapshot', [snapshot]) - def send_batch_contents(self, all_contents): - self._add('content', all_contents) - - def send_batch_directories(self, all_directories): - self._add('directory', all_directories) - - def send_batch_revisions(self, all_revisions): - self._add('revision', all_revisions) - - def send_batch_releases(self, all_releases): - self._add('release', all_releases) - - def send_snapshot(self, snapshot): - self._add('snapshot', [snapshot]) - - def _store_origin_visit(self): - pass - - def open_fetch_history(self): - pass +@pytest.mark.fs +class BaseLoaderTest(TestCase, BaseLoaderStorageTest): + """Mixin base loader test class. - def close_fetch_history_success(self, fetch_history_id): - pass + This allows to uncompress archives (mercurial, svn, git, + ... repositories) into a temporary folder so that the loader under + test can work with this. - def close_fetch_history_failure(self, fetch_history_id): - pass + When setUp() is done, the following variables are defined: + - self.repo_url: can be used as an origin_url for example + - self.destination_path: can be used as a path to ingest the + repository. - def update_origin_visit(self, origin_id, visit, status): - pass + Args: + archive_name (str): Name of the archive holding the repository + (folder, repository, dump, etc...) + start_path (str): (mandatory) Path from where starting to look + for resources + filename (Optional[str]): Name of the filename/folder once the + archive is uncompressed. When the filename is not + provided, the archive name is used as a derivative. This + is used both for the self.repo_url and + self.destination_path computation (this one only when + provided) + resources_path (str): Folder name to look for archive + prefix_tmp_folder_name (str): Prefix name to name the temporary folder + uncompress_archive (bool): Uncompress the archive passed as + parameters (default to True). It so + happens we could avoid doing + anything to the tarball. - def close_failure(self): - pass + """ + def setUp(self, archive_name, *, start_path, filename=None, + resources_path='resources', prefix_tmp_folder_name='', + uncompress_archive=True): + super().setUp() + repo_path = os.path.join(start_path, resources_path, archive_name) + if not uncompress_archive: + # In that case, simply sets the archive's path + self.destination_path = repo_path + self.tmp_root_path = None + self.repo_url = 'file://' + repo_path + return + tmp_root_path = tempfile.mkdtemp( + prefix=prefix_tmp_folder_name, suffix='-tests') + # uncompress folder/repositories/dump for the loader to ingest + subprocess.check_output(['tar', 'xf', repo_path, '-C', tmp_root_path]) + # build the origin url (or some derivative form) + _fname = filename if filename else os.path.basename(archive_name) + self.repo_url = 'file://' + tmp_root_path + '/' + _fname + # where is the data to ingest? + if filename: + # archive holds one folder with name + self.destination_path = os.path.join(tmp_root_path, filename) + else: + self.destination_path = tmp_root_path + self.tmp_root_path = tmp_root_path - def close_success(self): - pass + def tearDown(self): + """Clean up temporary working directory - def pre_cleanup(self): - pass + """ + if self.tmp_root_path and os.path.exists(self.tmp_root_path): + shutil.rmtree(self.tmp_root_path) diff --git a/swh/loader/core/tests/test_loader.py b/swh/loader/core/tests/test_loader.py index a27e9be..c6df258 100644 --- a/swh/loader/core/tests/test_loader.py +++ b/swh/loader/core/tests/test_loader.py @@ -1,325 +1,322 @@ # Copyright (C) 2018 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 datetime +import logging from swh.model.hashutil import hash_to_bytes -from . import BaseLoaderTest, LoaderNoStorage +from swh.loader.core.loader import BufferedLoader, UnbufferedLoader +from . import BaseLoaderTest -class DummyBaseLoaderTest(BaseLoaderTest): - def setUp(self): - # do not call voluntarily super().setUp() - self.in_contents = [1, 2, 3] - self.in_directories = [4, 5, 6] - self.in_revisions = [7, 8, 9] - self.in_releases = [10, 11, 12] - self.in_snapshot = 13 - def tearDown(self): - # do not call voluntarily super().tearDown() +class DummyLoader: + def cleanup(self): pass + def prepare(self): + pass -class LoadTest1(DummyBaseLoaderTest): - def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() + def fetch_data(self): + pass - def test_stateful_loader(self): - """Stateful loader accumulates in place the sent data + def store_data(self): + pass - Note: Those behaviors should be somehow merged but that's - another story. + def prepare_origin_visit(self): + origin = self.storage.origin_get( + self._test_prepare_origin_visit_data['origin']) + self.origin = origin + self.origin_id = origin['id'] + self.origin_url = origin['url'] + self.visit_date = datetime.datetime.utcnow() + self.storage.origin_visit_add(origin['id'], self.visit_date) + + def parse_config_file(self, *args, **kwargs): + return { + 'storage': { + 'cls': 'memory', + 'args': { + } + }, - """ - self.loader.maybe_load_directories(self.in_directories) - self.loader.maybe_load_revisions(self.in_revisions) - self.loader.maybe_load_releases(self.in_releases) + 'send_contents': True, + 'send_directories': True, + 'send_revisions': True, + 'send_releases': True, + 'send_snapshot': True, + + 'content_packet_size': 2, + 'content_packet_size_bytes': 8, + 'directory_packet_size': 2, + 'revision_packet_size': 2, + 'release_packet_size': 2, - self.assertEqual(len(self.state('content')), 0) - self.assertEqual( - len(self.state('directory')), len(self.in_directories)) - self.assertEqual( - len(self.state('revision')), len(self.in_revisions)) - self.assertEqual( - len(self.state('release')), len(self.in_releases)) - self.assertEqual(len(self.state('snapshot')), 0) + 'content_size_limit': 10000, + } - def test_stateless_loader(self): - """Stateless loader accumulates in place the sent data as well - Note: Those behaviors should be somehow merged but that's - another story. +class DummyUnbufferedLoader(DummyLoader, UnbufferedLoader): + pass - """ - self.loader.send_batch_contents(self.in_contents) - self.loader.send_snapshot(self.in_snapshot) - self.assertEqual(len(self.state('content')), len(self.in_contents)) - self.assertEqual(len(self.state('directory')), 0) - self.assertEqual(len(self.state('revision')), 0) - self.assertEqual(len(self.state('release')), 0) - self.assertEqual(len(self.state('snapshot')), 1) +class DummyBufferedLoader(DummyLoader, BufferedLoader): + pass -class LoadTestContent(DummyBaseLoaderTest): +class DummyBaseLoaderTest(BaseLoaderTest): def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() - - self.content_id0 = '34973274ccef6ab4dfaaf86599792fa9c3fe4689' - self.content_id1 = '61c2b3a30496d329e21af70dd2d7e097046d07b7' - # trimmed data to the bare necessities - self.in_contents = [{ - 'sha1': hash_to_bytes(self.content_id0), - }, { - 'sha1': hash_to_bytes(self.content_id1), - }] - self.expected_contents = [self.content_id0, self.content_id1] - - def test_maybe_load_contents(self): - """Loading contents should be ok - - """ - self.loader.maybe_load_contents(self.in_contents) - self.assertCountContents(len(self.expected_contents)) - self.assertContentsOk(self.expected_contents) - - def test_send_batch_contents(self): - """Sending contents should be ok 2 - - """ - self.loader.send_batch_contents(self.in_contents) - self.assertCountContents(len(self.expected_contents)) - self.assertContentsOk(self.expected_contents) - - def test_failing(self): - """Comparing wrong snapshot should fail. - - """ - self.loader.send_batch_contents(self.in_contents) - with self.assertRaises(AssertionError): - self.assertContentsOk([]) + self.loader = self.loader_class(logging_class='dummyloader') + # do not call voluntarily super().setUp() + self.storage = self.loader.storage + contents = [ + { + 'id': '34973274ccef6ab4dfaaf86599792fa9c3fe4689', + 'sha1': '34973274ccef6ab4dfaaf86599792fa9c3fe4689', + 'sha1_git': b'bar1', + 'sha256': b'baz1', + 'blake2s256': b'qux1', + 'status': 'visible', + 'data': b'data1', + 'length': 5, + }, + { + 'id': '61c2b3a30496d329e21af70dd2d7e097046d07b7', + 'sha1': '61c2b3a30496d329e21af70dd2d7e097046d07b7', + 'sha1_git': b'bar2', + 'sha256': b'baz2', + 'blake2s256': b'qux2', + 'status': 'visible', + 'data': b'data2', + 'length': 5, + }, + ] + self.expected_contents = [content['id'] for content in contents] + self.in_contents = contents.copy() + for content in self.in_contents: + content['sha1'] = hash_to_bytes(content['sha1']) + self.in_directories = [ + {'id': hash_to_bytes(id_)} + for id_ in [ + '44e45d56f88993aae6a0198013efa80716fd8921', + '54e45d56f88993aae6a0198013efa80716fd8920', + '43e45d56f88993aae6a0198013efa80716fd8920', + ] + ] + person = { + 'name': b'John Doe', + 'email': b'john.doe@institute.org', + 'fullname': b'John Doe ' + } + self.in_revisions = [ + { + 'id': b'rev1', + 'date': None, + 'author': person, + 'committer': person + }, + { + 'id': b'rev2', + 'date': None, + 'author': person, + 'committer': person + }, + ] + self.in_releases = [ + { + 'id': b'rel1', + 'date': None, + 'author': person + }, + { + 'id': b'rel2', + 'date': None, + 'author': person + }, + ] + self.in_origin = { + 'type': 'git', + 'url': 'http://example.com/', + } + self.in_snapshot = { + 'id': b'snap1', + 'branches': {}, + } + self.in_provider = { + 'provider_name': 'Test Provider', + 'provider_type': 'test_provider', + 'provider_url': 'http://example.org/metadata_provider', + 'metadata': {'working': True}, + } + self.in_tool = { + 'name': 'Test Tool', + 'version': 'v1.2.3', + 'configuration': {'in_the_Matrix': 'maybe'}, + } + self.storage.origin_add([self.in_origin]) -class LoadTestDirectory(DummyBaseLoaderTest): - def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() - - self.directory_id0 = '44e45d56f88993aae6a0198013efa80716fd8921' - self.directory_id1 = '54e45d56f88993aae6a0198013efa80716fd8920' - self.directory_id2 = '43e45d56f88993aae6a0198013efa80716fd8920' - # trimmed data to the bare necessities - self.in_directories = [{ - 'id': hash_to_bytes(self.directory_id0), - }, { - 'id': hash_to_bytes(self.directory_id1), - }, { - 'id': hash_to_bytes(self.directory_id2), - }] - self.expected_directories = [ - self.directory_id0, self.directory_id1, self.directory_id2] - - def test_maybe_load_directories(self): - """Loading directories should be ok - - """ - self.loader.maybe_load_directories(self.in_directories) - self.assertCountDirectories(len(self.expected_directories)) - self.assertDirectoriesOk(self.expected_directories) + # used by prepare_origin_visit() when it gets called + self.loader._test_prepare_origin_visit_data = { + 'origin': self.in_origin, + } + + def tearDown(self): + # do not call voluntarily super().tearDown() + pass - def test_send_batch_directories(self): - """Sending directories should be ok 2 - """ - self.loader.send_batch_directories(self.in_directories) - self.assertCountDirectories(len(self.expected_directories)) - self.assertDirectoriesOk(self.expected_directories) +class CoreUnbufferedLoaderTest(DummyBaseLoaderTest): + loader_class = DummyUnbufferedLoader - def test_failing(self): - """Comparing wrong snapshot should fail. + def test_unbuffered_loader(self): + self.loader.load() # initialize the loader - """ - self.loader.send_batch_revisions(self.in_revisions) - with self.assertRaises(AssertionError): - self.assertRevisionsOk([]) + self.loader.send_contents(self.in_contents[0:1]) + self.loader.send_directories(self.in_directories[0:1]) + self.loader.send_revisions(self.in_revisions[0:1]) + self.loader.send_releases(self.in_releases[0:1]) + self.assertCountContents(1) + self.assertCountDirectories(1) + self.assertCountRevisions(1) + self.assertCountReleases(1) -class LoadTestRelease(DummyBaseLoaderTest): - def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() - - self.release_id0 = '44e45d56f88993aae6a0198013efa80716fd8921' - self.release_id1 = '54e45d56f88993aae6a0198013efa80716fd8920' - self.release_id2 = '43e45d56f88993aae6a0198013efa80716fd8920' - # trimmed data to the bare necessities - self.in_releases = [{ - 'id': hash_to_bytes(self.release_id0), - }, { - 'id': hash_to_bytes(self.release_id1), - }, { - 'id': hash_to_bytes(self.release_id2), - }] - self.expected_releases = [ - self.release_id0, self.release_id1, self.release_id2] - - def test_maybe_load_releases(self): - """Loading releases should be ok - - """ - self.loader.maybe_load_releases(self.in_releases) - self.assertCountReleases(len(self.expected_releases)) - self.assertReleasesOk(self.expected_releases) + self.loader.send_contents(self.in_contents[1:]) + self.loader.send_directories(self.in_directories[1:]) + self.loader.send_revisions(self.in_revisions[1:]) + self.loader.send_releases(self.in_releases[1:]) - def test_send_batch_releases(self): - """Sending releases should be ok 2 + self.assertCountContents(len(self.in_contents)) + self.assertCountDirectories(len(self.in_directories)) + self.assertCountRevisions(len(self.in_revisions)) + self.assertCountReleases(len(self.in_releases)) - """ - self.loader.send_batch_releases(self.in_releases) - self.assertCountReleases(len(self.expected_releases)) - self.assertReleasesOk(self.expected_releases) - def test_failing(self): - """Comparing wrong snapshot should fail. +class CoreBufferedLoaderTest(DummyBaseLoaderTest): + loader_class = DummyBufferedLoader - """ - self.loader.send_batch_releases(self.in_releases) - with self.assertRaises(AssertionError): - self.assertReleasesOk([]) + def test_buffered_loader(self): + self.loader.load() # initialize the loader + self.loader.maybe_load_contents(self.in_contents[0:1]) + self.loader.maybe_load_directories(self.in_directories[0:1]) + self.loader.maybe_load_revisions(self.in_revisions[0:1]) + self.loader.maybe_load_releases(self.in_releases[0:1]) -class LoadTestRevision(DummyBaseLoaderTest): - def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() - - rev_id0 = '44e45d56f88993aae6a0198013efa80716fd8921' - dir_id0 = '34973274ccef6ab4dfaaf86599792fa9c3fe4689' - rev_id1 = '54e45d56f88993aae6a0198013efa80716fd8920' - dir_id1 = '61c2b3a30496d329e21af70dd2d7e097046d07b7' - rev_id2 = '43e45d56f88993aae6a0198013efa80716fd8920' - dir_id2 = '33e45d56f88993aae6a0198013efa80716fd8921' - - # data trimmed to bare necessities - self.in_revisions = [{ - 'id': hash_to_bytes(rev_id0), - 'directory': hash_to_bytes(dir_id0), - }, { - 'id': hash_to_bytes(rev_id1), - 'directory': hash_to_bytes(dir_id1), - }, { - 'id': hash_to_bytes(rev_id2), - 'directory': hash_to_bytes(dir_id2), - }] - - self.expected_revisions = { - rev_id0: dir_id0, - rev_id1: dir_id1, - rev_id2: dir_id2, - } + self.assertCountContents(0) + self.assertCountDirectories(0) + self.assertCountRevisions(0) + self.assertCountReleases(0) - def test_maybe_load_revisions(self): - """Loading revisions should be ok + self.loader.maybe_load_contents(self.in_contents[1:]) + self.loader.maybe_load_directories(self.in_directories[1:]) + self.loader.maybe_load_revisions(self.in_revisions[1:]) + self.loader.maybe_load_releases(self.in_releases[1:]) - """ - self.loader.maybe_load_revisions(self.in_revisions) - self.assertCountRevisions(len(self.expected_revisions)) - self.assertRevisionsOk(self.expected_revisions) + self.assertCountContents(len(self.in_contents)) + self.assertCountDirectories(len(self.in_directories)) + self.assertCountRevisions(len(self.in_revisions)) + self.assertCountReleases(len(self.in_releases)) - def test_send_batch_revisions(self): - """Sending revisions should be ok 2 + def test_directory_cascade(self): + """Checks that sending a directory triggers sending contents""" + self.loader.load() # initialize the loader - """ - self.loader.send_batch_revisions(self.in_revisions) - self.assertCountRevisions(len(self.expected_revisions)) - self.assertRevisionsOk(self.expected_revisions) + self.loader.maybe_load_contents(self.in_contents[0:1]) + self.loader.maybe_load_directories(self.in_directories) - def test_failing(self): - """Comparing wrong snapshot should fail. + self.assertCountContents(1) + self.assertCountDirectories(len(self.in_directories)) - """ - self.loader.send_batch_revisions(self.in_revisions) - with self.assertRaises(AssertionError): - self.assertRevisionsOk([]) + def test_revision_cascade(self): + """Checks that sending a revision triggers sending contents and + directories.""" + self.loader.load() # initialize the loader -class LoadTestSnapshot(DummyBaseLoaderTest): - def setUp(self): - super().setUp() - self.loader = LoaderNoStorage() - - snapshot_id = '44e45d56f88993aae6a0198013efa80716fd8921' - revision_id = '54e45d56f88993aae6a0198013efa80716fd8920' - release_id = '43e45d56f88993aae6a0198013efa80716fd8920' - # trimmed data to the bare necessities - self.expected_snapshot = { - 'id': snapshot_id, - 'branches': { - 'default': { - 'target_type': 'revision', - 'target': revision_id, - }, - 'master': { - 'target_type': 'release', - 'target': release_id, - }, - 'HEAD': { - 'target_type': 'alias', - 'target': 'master', - } - } - } + self.loader.maybe_load_contents(self.in_contents[0:1]) + self.loader.maybe_load_directories(self.in_directories[0:1]) + self.loader.maybe_load_revisions(self.in_revisions) - self.in_snapshot = { - 'id': hash_to_bytes(snapshot_id), - 'branches': { - b'default': { - 'target_type': 'revision', - 'target': hash_to_bytes(revision_id), - }, - b'master': { - 'target_type': 'release', - 'target': hash_to_bytes(release_id), - }, - b'HEAD': { - 'target_type': 'alias', - 'target': b'master', - } - } - } + self.assertCountContents(1) + self.assertCountDirectories(1) + self.assertCountRevisions(len(self.in_revisions)) + + def test_release_cascade(self): + """Checks that sending a release triggers sending revisions, + contents, and directories.""" + self.loader.load() # initialize the loader + + self.loader.maybe_load_contents(self.in_contents[0:1]) + self.loader.maybe_load_directories(self.in_directories[0:1]) + self.loader.maybe_load_revisions(self.in_revisions[0:1]) + self.loader.maybe_load_releases(self.in_releases) + + self.assertCountContents(1) + self.assertCountDirectories(1) + self.assertCountRevisions(1) + self.assertCountReleases(len(self.in_releases)) - def test_maybe_load_snapshots(self): - """Loading snapshot should be ok + def test_snapshot_cascade(self): + """Checks that sending a snapshot triggers sending releases, + revisions, contents, and directories.""" + self.loader.load() # initialize the loader - """ + self.loader.maybe_load_contents(self.in_contents[0:1]) + self.loader.maybe_load_directories(self.in_directories[0:1]) + self.loader.maybe_load_revisions(self.in_revisions[0:1]) + self.loader.maybe_load_releases(self.in_releases[0:1]) self.loader.maybe_load_snapshot(self.in_snapshot) + + self.assertCountContents(1) + self.assertCountDirectories(1) + self.assertCountRevisions(1) + self.assertCountReleases(1) self.assertCountSnapshots(1) - self.assertSnapshotOk(self.expected_snapshot) - self.assertSnapshotOk( - self.expected_snapshot['id'], - expected_branches=self.expected_snapshot['branches']) - def test_send_batch_snapshots(self): - """Sending snapshot should be ok 2 + def test_origin_metadata(self): + self.loader.load() - """ - self.loader.send_snapshot(self.in_snapshot) - self.assertCountSnapshots(1) - self.assertSnapshotOk(self.expected_snapshot) - self.assertSnapshotOk( - self.expected_snapshot['id'], - expected_branches=self.expected_snapshot['branches']) + provider_id = self.loader.send_provider(self.in_provider) + tool_id = self.loader.send_tool(self.in_tool) - def test_failing(self): - """Comparing wrong snapshot should fail. + self.loader.send_origin_metadata( + self.loader.origin_id, self.loader.visit_date, provider_id, + tool_id, {'test_metadata': 'foobar'}) + + self.assertOriginMetadataContains( + self.in_origin['type'], self.in_origin['url'], + {'test_metadata': 'foobar'}) - """ - self.loader.send_snapshot(self.in_snapshot) with self.assertRaises(AssertionError): - self.assertSnapshotOk( - 'wrong', expected_branches=self.expected_snapshot['branches']) + self.assertOriginMetadataContains( + self.in_origin['type'], self.in_origin['url'], + {'test_metadata': 'foobarbaz'}) + + with self.assertRaises(Exception): + self.assertOriginMetadataContains( + self.in_origin['type'], self.in_origin['url'] + 'blah', + {'test_metadata': 'foobar'}) + + +def test_loader_logger_default_name(): + loader = DummyBufferedLoader() + assert isinstance(loader.log, logging.Logger) + assert loader.log.name == \ + 'swh.loader.core.tests.test_loader.DummyBufferedLoader' + + loader = DummyUnbufferedLoader() + assert isinstance(loader.log, logging.Logger) + assert loader.log.name == \ + 'swh.loader.core.tests.test_loader.DummyUnbufferedLoader' + + +def test_loader_logger_with_name(): + loader = DummyBufferedLoader('some.logger.name') + assert isinstance(loader.log, logging.Logger) + assert loader.log.name == \ + 'some.logger.name' diff --git a/swh/loader/core/tests/test_tests.py b/swh/loader/core/tests/test_tests.py new file mode 100644 index 0000000..b138b37 --- /dev/null +++ b/swh/loader/core/tests/test_tests.py @@ -0,0 +1,87 @@ +# Copyright (C) 2018 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 os.path +from os.path import join +import pytest +import re +import tarfile +import tempfile +from unittest import TestCase + +from . import BaseLoaderStorageTest + +from swh.loader.core.tests import BaseLoaderTest + + +class TestsTest(BaseLoaderStorageTest, TestCase): + """Test the helpers provided to other loaders' tests.""" + + def _build_archive(self, fd): + with tarfile.open(mode='w', fileobj=fd) as tf: + with tempfile.TemporaryDirectory() as src_dir: + with open(join(src_dir, 'hello.txt'), 'a') as src_file: + src_file.write('world\n') + tf.add(src_dir, arcname='test_dir') + + def _build_workdir(self, workdir): + os.mkdir(join(workdir, 'resources')) + tarball_path = join(workdir, 'resources', 'test_archive.tar') + with open(tarball_path, 'a+b') as tar_fd: + self._build_archive(tar_fd) + + @pytest.mark.fs + def test_uncompress_setup_auto_name(self): + loader_test = BaseLoaderTest() + with tempfile.TemporaryDirectory() as workdir: + self._build_workdir(workdir) + + loader_test.setUp('test_archive.tar', start_path=workdir) + + self.assertTrue(re.match('^file://.*-tests/test_archive.tar$', + loader_test.repo_url), + msg=loader_test.repo_url) + self.assertTrue(os.path.isdir(loader_test.destination_path)) + self.assertTrue(os.path.isdir(join(loader_test.destination_path, + 'test_dir'))) + self.assertTrue(os.path.isfile(join(loader_test.destination_path, + 'test_dir', + 'hello.txt'))) + + loader_test.tearDown() + self.assertFalse(os.path.isdir(loader_test.destination_path)) + + @pytest.mark.fs + def test_uncompress_setup_provided_name(self): + loader_test = BaseLoaderTest() + with tempfile.TemporaryDirectory() as workdir: + self._build_workdir(workdir) + + loader_test.setUp('test_archive.tar', start_path=workdir, + filename='test_dir') + + self.assertTrue(re.match('^file://.*-tests/test_dir$', + loader_test.repo_url), + msg=loader_test.repo_url) + self.assertTrue(os.path.isdir(loader_test.destination_path)) + self.assertTrue(os.path.isfile(join(loader_test.destination_path, + 'hello.txt'))) + + loader_test.tearDown() + self.assertFalse(os.path.isdir(loader_test.destination_path)) + + @pytest.mark.fs + def test_setup_no_uncompress(self): + loader_test = BaseLoaderTest() + with tempfile.TemporaryDirectory() as workdir: + self._build_workdir(workdir) + + loader_test.setUp('test_archive.tar', start_path=workdir, + uncompress_archive=False) + + self.assertEqual('file://' + workdir + '/resources/test_archive.tar', + loader_test.repo_url) + self.assertEqual(workdir + '/resources/test_archive.tar', + loader_test.destination_path) diff --git a/tox.ini b/tox.ini deleted file mode 100644 index 4093c4e..0000000 --- a/tox.ini +++ /dev/null @@ -1,16 +0,0 @@ -[tox] -envlist=flake8,py3 - -[testenv:py3] -deps = - .[testing] - pytest-cov -commands = - pytest --cov=swh --cov-branch {posargs} - -[testenv:flake8] -skip_install = true -deps = - flake8 -commands = - {envpython} -m flake8 diff --git a/version.txt b/version.txt index d32c1c0..6dd2e57 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.35-0-g913eac9 \ No newline at end of file +v0.0.39-0-g8e8ae37 \ No newline at end of file