diff --git a/.flake8 b/.flake8 new file mode 100644 index 000000000..cc285f26f --- /dev/null +++ b/.flake8 @@ -0,0 +1,8 @@ +[flake8] +max-line-length = 125 + +# Style issues are handled by yapf formatting +ignore = + E126, # continuation line over-indented for hanging indent + W503, # line break before binary operator + E251, # unexpected spaces around keyword / parameter equals diff --git a/.gitignore b/.gitignore new file mode 100644 index 000000000..957757d66 --- /dev/null +++ b/.gitignore @@ -0,0 +1,16 @@ +*.pyc +*.pyo +*~ +/.cache +/.coverage +/.project +/.pydevproject +/.pytest_cache/ +__pycache__/ +/build/ +/dist/ +/karapace.egg-info/ +/karapace-rpm-src.tar +/rpm/ +/kafka_*.tgz +/kafka_*/ diff --git a/.pylintrc b/.pylintrc new file mode 100644 index 000000000..b3062fb4e --- /dev/null +++ b/.pylintrc @@ -0,0 +1,27 @@ +[MASTER] +jobs=4 + +[MESSAGES CONTROL] +disable= + bad-continuation, + fixme, + invalid-name, + missing-docstring, + too-few-public-methods, + too-many-arguments, + too-many-branches, + too-many-instance-attributes, + too-many-locals, + too-many-nested-blocks, + too-many-public-methods, + too-many-statements, + too-public-methods, + wrong-import-order, + +[FORMAT] +max-line-length=125 + +[REPORTS] +output-format=text +reports=no +score=no diff --git a/.style.yapf b/.style.yapf new file mode 100644 index 000000000..0805f8f4d --- /dev/null +++ b/.style.yapf @@ -0,0 +1,55 @@ +[style] +# For docs, see https://github.com/google/yapf/blob/master/README.rst + +based_on_style = pep8 +# Disallow splitting between dict key and dict value in multiline {"key": "value"} lines +ALLOW_SPLIT_BEFORE_DICT_VALUE = false + +# Avoid adding unnecessary blank lines when nesting +BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = false + +# Always add two blank lines for top-level classes and methods +BLANK_LINES_AROUND_TOP_LEVEL_DEFINITION = 2 + +# These two combine consecutive ({ and }) to same line to reduce clutter +COALESCE_BRACKETS = true +DEDENT_CLOSING_BRACKETS = true + +# Line length +COLUMN_LIMIT = 125 + +# Try to avoid having overly long lines by having excessively large penalty for that. +SPLIT_PENALTY_EXCESS_CHARACTER = 1000000000 + +# Always split dict entries to one entry per line +# EACH_DICT_ENTRY_ON_SEPARATE_LINE = true + +# Never split this comment to a separate line. Workaround for certain flake8 & email template lines +I18N_COMMENT = # noqa + +# Allow automatically joining lines, for example, multiline if that would fit to a single line +JOIN_MULTIPLE_LINES = true + +# "3 * 5", instead of "3*5" +SPACES_AROUND_POWER_OPERATOR = true + +# Follow normal comment style by adding two spaces between code and comment +SPACES_BEFORE_COMMENT = 2 + +# If list of items is comma terminated, always split to one per line. +SPLIT_ARGUMENTS_WHEN_COMMA_TERMINATED = true + +# Related to previous one, if list of items (args or dict/list/...) needs to be split, split to one per line. +# SPLIT_ALL_COMMA_SEPARATED_VALUES = true + +# Split dict generators for clarity (add line breaks between { and key: val etc. +SPLIT_BEFORE_DICT_SET_GENERATOR = true + +# Split method(k1=v1, k2=v2...) to separate lines +SPLIT_BEFORE_NAMED_ASSIGNS = true + +# For complex (for some definition of complex) comprehensions, put output, for and if to separate lines +SPLIT_COMPLEX_COMPREHENSION = true + +# When splitting something to multiple lines ('method(\n val...'), intend by 4 +CONTINUATION_INDENT_WIDTH = 4 diff --git a/.travis.yml b/.travis.yml new file mode 100644 index 000000000..a7216af43 --- /dev/null +++ b/.travis.yml @@ -0,0 +1,20 @@ +language: python + +python: + - "3.5" + - "3.6" + +# TODO: remove these overrides once default dist supports python 3.7 +matrix: + include: + - python: 3.7 + dist: xenial + sudo: true + +install: + - "pip install astroid==2.0.0 flake8 pylint pytest isort yapf requests kafka-python aiohttp avro-python3 aiosocksy" + +script: + - "make pylint" + - "make flake8" + - "make unittest" diff --git a/LICENSE b/LICENSE new file mode 100644 index 000000000..be3f7b28e --- /dev/null +++ b/LICENSE @@ -0,0 +1,661 @@ + GNU AFFERO GENERAL PUBLIC LICENSE + Version 3, 19 November 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 Affero General Public License is a free, copyleft license for +software and other kinds of works, specifically designed to ensure +cooperation with the community in the case of network server software. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +our General Public Licenses are 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. + + 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. + + Developers that use our General Public Licenses protect your rights +with two steps: (1) assert copyright on the software, and (2) offer +you this License which gives you legal permission to copy, distribute +and/or modify the software. + + A secondary benefit of defending all users' freedom is that +improvements made in alternate versions of the program, if they +receive widespread use, become available for other developers to +incorporate. Many developers of free software are heartened and +encouraged by the resulting cooperation. However, in the case of +software used on network servers, this result may fail to come about. +The GNU General Public License permits making a modified version and +letting the public access it on a server without ever releasing its +source code to the public. + + The GNU Affero General Public License is designed specifically to +ensure that, in such cases, the modified source code becomes available +to the community. It requires the operator of a network server to +provide the source code of the modified version running there to the +users of that server. Therefore, public use of a modified version, on +a publicly accessible server, gives the public access to the source +code of the modified version. + + An older license, called the Affero General Public License and +published by Affero, was designed to accomplish similar goals. This is +a different license, not a version of the Affero GPL, but Affero has +released a new version of the Affero GPL which permits relicensing under +this license. + + 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 Affero 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. Remote Network Interaction; Use with the GNU General Public License. + + Notwithstanding any other provision of this License, if you modify the +Program, your modified version must prominently offer all users +interacting with it remotely through a computer network (if your version +supports such interaction) an opportunity to receive the Corresponding +Source of your version by providing access to the Corresponding Source +from a network server at no charge, through some standard or customary +means of facilitating copying of software. This Corresponding Source +shall include the Corresponding Source for any work covered by version 3 +of the GNU General Public License that is incorporated pursuant to the +following paragraph. + + 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 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 work with which it is combined will remain governed by version +3 of the GNU General Public License. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU Affero 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 Affero 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 Affero 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 Affero 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 Affero 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 Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If your software can interact with users remotely through a computer +network, you should also make sure that it provides a way for users to +get its source. For example, if your program is a web application, its +interface could display a "Source" link that leads users to an archive +of the code. There are many ways you could offer source, and different +solutions will be better for different programs; see section 13 for the +specific requirements. + + 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 AGPL, see +. diff --git a/MANIFEST.in b/MANIFEST.in new file mode 100644 index 000000000..fa15133f4 --- /dev/null +++ b/MANIFEST.in @@ -0,0 +1,13 @@ +include karapace/*.py +include karapace.json +include karapace.unit +include tests/*.py +include scripts/* +include README.rst +include version.py +include setup.py +include setup.cfg +include LICENSE +include MANIFEST.in + +recursive-exclude examples *~ *.pyc \.* diff --git a/Makefile b/Makefile new file mode 100644 index 000000000..a6a45bcc5 --- /dev/null +++ b/Makefile @@ -0,0 +1,74 @@ +SHORT_VER = 0.1.0 +LONG_VER = $(shell git describe --long 2>/dev/null || echo $(SHORT_VER)-0-unknown-g`git describe --always`) +KAFKA_PATH = kafka_2.12-2.1.0 +KAFKA_TAR = $(KAFKA_PATH).tgz +PYTHON_SOURCE_DIRS = karapace/ +PYTHON_TEST_DIRS = tests/ +ALL_PYTHON_DIRS = $(PYTHON_SOURCE_DIRS) $(PYTHON_TEST_DIRS) +GENERATED = karapace/version.py +PYTHON = python3 + +default: $(GENERATED) + +clean: + rm -rf rpm/ + +.PHONY: build-dep-fedora +build-dep-fedora: + sudo dnf builddep karapace.spec + +karapace/version.py: version.py + $(PYTHON) $^ $@ + +$(KAFKA_TAR): + wget "http://www.nic.funet.fi/pub/mirrors/apache.org/kafka/2.1.0/$(KAFKA_PATH).tgz" + +$(KAFKA_PATH): $(KAFKA_TAR) + gtar zxf "$(KAFKA_TAR)" + +.PHONY: kafka +kafka: $(KAFKA_PATH) + "$(KAFKA_PATH)/bin/zookeeper-server-start.sh" "$(KAFKA_PATH)/config/zookeeper.properties" & + "$(KAFKA_PATH)/bin/kafka-server-start.sh" "$(KAFKA_PATH)/config/server.properties" & + +.PHONY: pylint +pylint: + python3 -m pylint --rcfile .pylintrc $(ALL_PYTHON_DIRS) + +.PHONY: flake8 +flake8: + python3 -m flake8 --config .flake8 $(ALL_PYTHON_DIRS) + +.PHONY: copyright +copyright: + grep -EL "Copyright \(c\) 20.* Aiven" $(shell git ls-files "*.py" | grep -v __init__.py) + +.PHONY: unittest +unittest: + python3 -m pytest -s -vvv tests/ + +.PHONY: test +test: flake8 pylint copyright unittest + +.PHONY: isort +isort: + time isort --recursive $(ALL_PYTHON_DIRS) + +.PHONY: yapf +yapf: + time yapf --parallel --recursive --in-place $(ALL_PYTHON_DIRS) + +.PHONY: reformat +reformat: isort yapf + +.PHONY: rpm +rpm: $(GENERATED) + git archive --output=karapace-rpm-src.tar --prefix=karapace/ HEAD + # add generated files to the tar, they're not in git repository + tar -r -f karapace-rpm-src.tar --transform=s,karapace/,karapace/karapace/, $(GENERATED) + rpmbuild -bb karapace.spec \ + --define '_topdir $(PWD)/rpm' \ + --define '_sourcedir $(CURDIR)' \ + --define 'major_version $(SHORT_VER)' \ + --define 'minor_version $(subst -,.,$(subst $(SHORT_VER)-,,$(LONG_VER)))' + $(RM) karapace-rpm-src.tar diff --git a/NEWS b/NEWS new file mode 100644 index 000000000..5c8766f6c --- /dev/null +++ b/NEWS @@ -0,0 +1,6 @@ +Karapace 0.1.0 (2019-01-16) +=========================== + +* Initial release with schema storing, retrieving and compatibility testing functionality +* Unittests for the functionality +* aiohttp based architecture diff --git a/README.rst b/README.rst new file mode 100644 index 000000000..6afe76397 --- /dev/null +++ b/README.rst @@ -0,0 +1,334 @@ +Karapace |BuildStatus|_ +======================= + +.. |BuildStatus| image:: https://travis-ci.org/aiven/karapace.png?branch=master +.. _BuildStatus: https://travis-ci.org/aiven/karapace + +``karapace`` Your Kafka essentials in one tool + + +Features +======== + +* Schema Registry that is 1:1 Compatible with the pre-existing proprietary + Confluent Schema Registry +* Drop in replacement both on pre-existing Schema Registry client and + server-sides +* Moderate memory consumption +* Asynchronous architecture based on aiohttp + + +Overview +======== + +Karapace supports the storing of schemas in a central repository, which +clients can access to serialize and deserialize messages. The schemas also +maintain their own version histories and can be checked for compatibility +between their different respective versions. + + +Requirements +============ + +Karapace requires Python 3.6 or later and some additional components in +order to operate: + +* aiohttp_ for serving schemas over HTTP in an asynchronous fashion +* avro-python3_ for Avro serialization +* kafka-python_ to read, write and coordinate Karapace's persistence in Kafka + +.. _`aiohttp`: https://github.com/aio-libs/aiohttp +.. _`avro-python3`: https://github.com/apache/avro +.. _`kafka-python`: https://github.com/dpkp/kafka-python + +Developing and testing Karapace also requires the following utilities: +requests_, flake8_, pylint_ and pytest_. + +.. _`flake8`: https://flake8.readthedocs.io/ +.. _`requests`: http://www.python-requests.org/en/latest/ +.. _`pylint`: https://www.pylint.org/ +.. _`pytest`: http://pytest.org/ + +Karapace has been developed and tested on modern Linux x86-64 systems, but +should work on other platforms that provide the required modules. + + +Building +======== + +To build an installation package for your distribution, go to the root +directory of a Karapace Git checkout and run: + +Fedora:: + + make rpm + +This will produce a ``.rpm`` package usually into ``rpm/RPMS/noarch/``. + +Python/Other:: + + python3 setup.py bdist_egg + +This will produce an egg file into a dist directory within the same folder. + + +Installation +============ + +To install it run as root: + +Fedora:: + + dnf install rpm/RPMS/noarch/* + +On Linux systems it is recommended to simply run ``karapace`` under +``systemd``:: + + systemctl enable karapace.service + +and eventually after the setup section, you can just run:: + + systemctl start karapace.service + +Python/Other:: + + easy_install dist/karapace-0.1.0-py3.6.egg + + +Setup +===== + +After this you need to create a suitable JSON configuration file for your +installation. Keys to take special care are the ones needed to configure +Kafka and advertised_hostname. + +To see descriptions of configuration keys see section ``config``. Here's an +example configuration file to give you an idea what you need to change:: + + { + "advertised_hostname": "localhost", + "bootstrap_uri": "127.0.0.1:9092", + "client_id": "sr-1", + "compatibility": "FULL", + "group_id": "schema-registry", + "host": "127.0.0.1", + "log_level": "DEBUG", + "port": 8081, + "master_eligibility": true, + "replication_factor": 1, + "security_protocol": "PLAINTEXT", + "ssl_cafile": null, + "ssl_certfile": null, + "ssl_keyfile": null, + "topic_name": "_schemas" + } + + +Quickstart +========== + +To Register the first version of a schema under the subject "test":: + + $ curl -X POST -H "Content-Type: application/vnd.schemaregistry.v1+json" \ + --data '{"schema": "{\"type\": \"record\", \"name\": \"Obj\", \"fields\":[{\"name\": \"age\", \"type\": \"int\"}]}"}' \ + http://localhost:8081/subjects/test-key/versions + {"id":1} + + +To list all subjects (including the one created just above):: + + $ curl -X GET http://localhost:8081/subjects + ["test-key"] + +To list all the versions of a given schema (including the one just created above):: + + $ curl -X GET http://localhost:8081/subjects/test-key/versions + [1] + +To fetch back the schema whose global id is 1 (i.e. the one registered above):: + + $ curl -X GET http://localhost:8081/schemas/ids/1 + {"schema":"{\"fields\":[{\"name\":\"age\",\"type\":\"int\"}],\"name\":\"Obj\",\"type\":\"record\"}"} + +To get the specific version 1 of the schema just registered run:: + + $ curl -X GET http://localhost:8081/subjects/test-key/versions/1 + {"subject":"test-key","version":1,"id":1,"schema":"{\"fields\":[{\"name\":\"age\",\"type\":\"int\"}],\"name\":\"Obj\",\"type\":\"record\"}"} + +To get the latest version of the schema under subject test-key run:: + + $ curl -X GET http://localhost:8081/subjects/Kafka-value/versions/latest + {"subject":"test-key","version":1,"id":1,"schema":"{\"fields\":[{\"name\":\"age\",\"type\":\"int\"}],\"name\":\"Obj\",\"type\":\"record\"}"} + +In order to delete version 10 of the schema registered under subject "test-key" (if it exists):: + + $ curl -X DELETE http://localhost:8081/subjects/test-key/versions/10 + 10 + +To Delete all versions of the schema registered under subject "test-key":: + + $ curl -X DELETE http://localhost:8081/subjects/test-key + [1] + +Test the compatibility of a schema with the latest schema under subject "test-key":: + + $ curl -X POST -H "Content-Type: application/vnd.schemaregistry.v1+json" \ + --data '{"schema": "{\"type\": \"int\"}"}' \ + http://localhost:8081/compatibility/subjects/test-key/versions/latest + {"is_compatible":true} + +Get current global backwards compatibility setting value:: + + $ curl -X GET http://localhost:8081/config + {"compatibilityLevel":"BACKWARD"} + +Change compatibility requirements for all subjects where it's not +specifically defined otherwise:: + + $ curl -X PUT -H "Content-Type: application/vnd.schemaregistry.v1+json" \ + --data '{"compatibility": "NONE"}' http://localhost:8081/config + {"compatibility":"NONE"} + +Change compatibility requirement to FULL for the test-key subject:: + + $ curl -X PUT -H "Content-Type: application/vnd.schemaregistry.v1+json" \ + --data '{"compatibility": "FULL"}' http://localhost:8081/config/test-key + {"compatibility":"FULL"} + + +Backing up your Karapace +======================== + +Karapace natively stores its data in a Kafka topic the name of which you can +configure freely but which by default is called _schemas. + +To easily back up the data in the topic you can run Kafka's Java console +consumer:: + + ./kafka-console-consumer.sh --bootstrap-server brokerhostname:9092 --topic _schemas --from-beginning --property print.key=true --timeout-ms 1000 1> schemas.log + + +Restoring Karapace from backup +============================== + +Kafka's Java console producer can then in turn be used to restore the data +to a new Kafka cluster. + +You can restore the data from the previous step by running:: + + ./kafka-console-producer.sh --broker-list brokerhostname:9092 --topic _schemas --property parse.key=true < schemas.log + + +Commands +======== + +Once installed, the ``karapace`` program should be in your path. It is the +main daemon process that should be run under a service manager such as +``systemd`` to serve clients. + + +Configuration keys +================== + +``advertised_hostname`` (default ``socket.gethostname()``) + +The hostname being advertised to other instances of Karapace that are +attached to the same Kafka group. All nodes within the cluster need to have +their advertised_hostname's set so that they can all reach each other. + +``bootstrap_uri`` (default ``localhost:9092``) + +The URI to the Kafka service where to store the schemas and to run +coordination among the Karapace instances. + +``client_id`` (default ``sr-1``) + +The client_id name by which the Karapace will use when coordinating with +other Karapaces who is master. The one with the name that sorts as the +first alphabetically is chosen as master from among the services with +master_eligibility set to true. + +``group_id`` (default ``schema-registry``) + +The Kafka group name used for selecting a master service to coordinate the +storing of Schemas. + +``master_eligibility`` (``true``) + +Should the service instance be considered for promotion to be the master +service. Reason to turn this off would be to have an instances of Karapace +running somewhere else for HA purposes but which you wouldn't want to +automatically promote to master if the primary instances were to become +unavailable. + +``security_protocol`` (default ``PLAINTEXT``) + +Default Kafka security protocol needed to communicate with the Kafka +cluster. Other options is to use SSL for SSL client certificate +authentication. + +``ssl_cafile`` (default ``Path to CA certificate``) + +Used when security_protocol is set to SSL, the path to the SSL CA certificate. + +``ssl_certfile`` (default ``/path/to/certfile``) + +Used when security_protocol is set to SSL, the path to the SSL certfile. + +``ssl_keyfile`` (default ``/path/to/keyfile``) + +Used when security_protocol is set to SSL, the path to the SSL keyfile. + +``topic_name`` (default ``_schemas``) + +The name of the Kafka topic where to store the schemas. + +``replication_factor`` (default ``1``) + +The replication factor to be used with the schema topic. + +``host`` (default ``"127.0.0.1"``) + +Address to bind the Karapace HTTP server to. Set to an empty string to +listen to all available addresses. + +``port`` (default ``8081``) + +HTTP webserver port to bind the Karapace to. + + +License +======= + +Karapace is licensed under the AGPL, version 3. Full license text is +available in the ``LICENSE`` file. + +Please note that the project explicitly does not require a CLA (Contributor +License Agreement) from its contributors. + + +Contact +======= + +Bug reports and patches are very welcome, please post them as GitHub issues +and pull requests at https://github.com/aiven/karapace . Any possible +vulnerabilities or other serious issues should be reported directly to the +maintainers . + + +Credits +======= + +Karapace was created by, and is maintained by, Aiven_ cloud data hub +developers. + +The schema storing part of Karapace loans heavily from the ideas of the +earlier Schema Registry implementation by Confluent and thanks are in order +to them for pioneering the concept. + +.. _`Aiven`: https://aiven.io/ + +Recent contributors are listed on the GitHub project page, +https://github.com/aiven/karapace/graphs/contributors + +Copyright ⓒ 2019 Aiven Ltd. diff --git a/karapace.config.json b/karapace.config.json new file mode 100644 index 000000000..46556b664 --- /dev/null +++ b/karapace.config.json @@ -0,0 +1,17 @@ +{ + "advertised_hostname": "localhost", + "bootstrap_uri": "127.0.0.1:9092", + "client_id": "sr-1", + "compatibility": "FULL", + "group_id": "schema-registry", + "host": "127.0.0.1", + "log_level": "DEBUG", + "port": 8081, + "master_eligibility": true, + "replication_factor": 1, + "security_protocol": "PLAINTEXT", + "ssl_cafile": null, + "ssl_certfile": null, + "ssl_keyfile": null, + "topic_name": "_schemas" +} diff --git a/karapace.spec b/karapace.spec new file mode 100644 index 000000000..b325e9b92 --- /dev/null +++ b/karapace.spec @@ -0,0 +1,57 @@ +Name: karapace +Version: %{major_version} +Release: %{minor_version}%{?dist} +Url: http://github.com/aiven/karapace +Summary: Your Kafka essentials in one tool +License: AGPL 3 +Source0: karapace-rpm-src.tar +BuildRequires: python3-aiohttp +BuildRequires: python3-aiosocksy +BuildRequires: python3-avro +BuildRequires: python3-devel +BuildRequires: python3-flake8 +BuildRequires: python3-isort +BuildRequires: python3-kafka +BuildRequires: python3-pylint +BuildRequires: python3-pytest +BuildRequires: python3-requests +BuildRequires: python3-yapf +Requires: python3-aiohttp +Requires: python3-aiosocksy +Requires: python3-avro +Requires: python3-kafka +Requires: python3-requests +Requires: systemd + +%undefine _missing_build_ids_terminate_build + +%description +Your Kafka essentials in one tool + + +%prep +%setup -q -n karapace + + +%install +python3 setup.py install --prefix=%{_prefix} --root=%{buildroot} +sed -e "s@#!/bin/python@#!%{_bindir}/python@" -i %{buildroot}%{_bindir}/* +rm -rf %{buildroot}%{python3_sitelib}/tests/ +%{__install} -Dm0644 karapace.unit %{buildroot}%{_unitdir}/karapace.service +%{__mkdir_p} %{buildroot}%{_localstatedir}/lib/karapace + + +%check +make -j flake8 pylint + +%files +%defattr(-,root,root,-) +%doc LICENSE README.rst karapace.config.json +%{_bindir}/karapace* +%{_unitdir}/karapace.service +%{python3_sitelib}/* + + +%changelog +* Mon Jan 14 2019 Hannu Valtonen - 0.0.1 +- Initial RPM package diff --git a/karapace.unit b/karapace.unit new file mode 100644 index 000000000..1d05210a4 --- /dev/null +++ b/karapace.unit @@ -0,0 +1,14 @@ +[Unit] +Description=Your Kafka essentials in one tool + +[Service] +User=karapace +Group=karapace +Type=notify +Restart=always +ExecStart=/usr/bin/karapace /etc/karapace/karapace.config.json +ExecReload=/bin/kill -HUP $MAINPID +WorkingDirectory=/var/lib + +[Install] +WantedBy=multi-user.target diff --git a/karapace/__init__.py b/karapace/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/karapace/compatibility.py b/karapace/compatibility.py new file mode 100644 index 000000000..99179079f --- /dev/null +++ b/karapace/compatibility.py @@ -0,0 +1,120 @@ +""" +karapace - schema compatibility checking + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import avro.schema +import logging + + +class IncompatibleSchema(Exception): + pass + + +class Compatibility: + def __init__(self, source, target, compatibility): + self.source = source + self.target = target + self.log = logging.getLogger("Compatibility") + self.compatibility = compatibility + self.log.info("Compatibility initialized with level: %r", self.compatibility) + + def check(self): + if self.compatibility == "NONE": + self.log.info("Compatibility level set to NONE, no schema compatibility checks performed") + return True + return self.check_compatibility(self.source, self.target) + + def contains(self, field, target): # pylint: disable=no-self-use + return bool(field in target.fields) + + def check_same_name(self, source, target): # pylint: disable=no-self-use + return source.name == target.name + + def check_same_type(self, source, target): # pylint: disable=no-self-use, too-many-return-statements + """Returns info on if the types are the same and whether it's a basetype or not""" + self.log.error("source: %s, target: %s", type(source.type), type(target.type)) + self.log.error("source: %s, target: %s", source, target) + + if isinstance(source.type, str): + return source.type == target.type, True + if isinstance(source.type, avro.schema.PrimitiveSchema): + if isinstance(target.type, avro.schema.PrimitiveSchema): + # Follow promotion rules in schema resolution section of: + # https://avro.apache.org/docs/current/spec.html#schemas + if source.type.type == "int" and target.type.type in {"int", "long", "float", "double"}: + return True, True + if source.type.type == "long" and target.type.type in {"long", "float", "double"}: + return True, True + if source.type.type == "float" and target.type.type in {"float", "double"}: + return True, True + if source.type.type == "string" and target.type.type in {"string", "bytes"}: + return True, True + return source.type.type == target.type.type, True + return False, True + if isinstance(source.type, avro.schema.RecordSchema): + return isinstance(target.type, avro.schema.RecordSchema), False + if isinstance(source.type, avro.schema.EnumSchema): + return isinstance(target.type, avro.schema.EnumSchema), True + raise IncompatibleSchema("Unhandled schema type: {}".format(type(source.type))) + + def check_source_field(self, source, target): + for source_field in source.fields: + if self.contains(source_field, target): # this is an optimization to check for identical fields + self.log.info("source_field: identical %s in both source and target: %s", source_field.name, target) + continue + # The fields aren't identical in both but could be similar enough (i.e. changed default) + found = False + for target_field in target.fields: + if self.check_same_name(source_field, target_field): + # Ok we found the same named fields + same_type, base_type = self.check_same_type(source_field, target_field) + if not same_type: # different types + raise IncompatibleSchema( + "source_field.type: {} != target_field.type: {}".format(source_field.type, target_field.type) + ) + if not base_type: # same type but nested structure + self.log.info("Recursing source with: source: %s target: %s", source_field, target_field) + self.check_compatibility(source_field.type, target_field.type) + else: + found = True + break + if not found: + self.log.info("source_field: %s removed from: %s", source_field.name, target) + if not found and self.compatibility in {"FORWARD", "FULL"} and not source_field.has_default: + raise IncompatibleSchema("Source field: {} removed".format(source_field.name)) + + def check_target_field(self, source, target): + for target_field in target.fields: + if self.contains(target_field, source): + self.log.info("target_field: %r in both source and target: %r", target_field.name, source) + continue + # The fields aren't identical in both but could be similar enough (i.e. changed default) + found = False + for source_field in source.fields: + if self.check_same_name(source_field, target_field): + same_type, base_type = self.check_same_type(source_field, target_field) + if not same_type: + raise IncompatibleSchema( + "source_field.type: {} != target_field.type: {}".format(source_field.type, target_field.type) + ) + if not base_type: + self.log.info("Recursing target with: source: %s target: %s", source_field, target_field) + self.check_compatibility(source_field.type, target_field.type) + else: + found = True + self.log.info("source_field is: %s, target_field: %s added", source_field, target_field) + break + + if not found and self.compatibility in {"BACKWARD", "FULL"} and not target_field.has_default: + raise IncompatibleSchema("Target field: {} added".format(target_field.name)) + + def check_compatibility(self, source, target): + same_type, _ = self.check_same_type(source, target) + if not same_type: + raise IncompatibleSchema("source {} and target {} different types".format(source, target)) + + if source.type == "record": + self.check_source_field(source, target) + self.check_target_field(source, target) diff --git a/karapace/config.py b/karapace/config.py new file mode 100644 index 000000000..f62f2026d --- /dev/null +++ b/karapace/config.py @@ -0,0 +1,26 @@ +""" +karapace - configuration validation + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import socket + + +def set_config_defaults(config): + config.setdefault("advertised_hostname", socket.gethostname()) + config.setdefault("bootstrap_uri", "127.0.0.1:9092") + config.setdefault("client_id", "sr-1") + config.setdefault("compatibility", "BACKWARD") + config.setdefault("group_id", "schema-registry") + config.setdefault("host", "127.0.0.1") + config.setdefault("log_level", "DEBUG") + config.setdefault("port", 8081) + config.setdefault("master_eligibility", True) + config.setdefault("replication_factor", 1) + config.setdefault("security_protocol", "PLAINTEXT") + config.setdefault("ssl_cafile", None) + config.setdefault("ssl_certfile", None) + config.setdefault("ssl_keyfile", None) + config.setdefault("topic_name", "_schemas") + return config diff --git a/karapace/karapace.py b/karapace/karapace.py new file mode 100644 index 000000000..53b9de6e7 --- /dev/null +++ b/karapace/karapace.py @@ -0,0 +1,421 @@ +""" +karapace - main + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import asyncio +import avro.schema +import json +import logging +import os +import sys +import time + +from kafka import KafkaProducer +from karapace.compatibility import Compatibility, IncompatibleSchema +from karapace.config import set_config_defaults +from karapace.master_coordinator import MasterCoordinator +from karapace.rapu import HTTPResponse, RestApp +from karapace.schema_reader import KafkaSchemaReader +from karapace.utils import json_encode + +LOG_FORMAT_JOURNAL = "%(name)-20s\t%(threadName)s\t%(levelname)-8s\t%(message)s" +logging.basicConfig(level=logging.INFO, format=LOG_FORMAT_JOURNAL) + +COMPATIBILITY_MODES = {"NONE", "FULL", "FORWARD", "BACKWARD"} + + +class InvalidConfiguration(Exception): + pass + + +class Karapace(RestApp): + def __init__(self, config_path): + super().__init__(app_name="Karapace") + self.config = {} + self.config_path = config_path + self.log = logging.getLogger("Karapace") + self.kafka_timeout = 10 + + self.route( + "/compatibility/subjects//versions/", + callback=self.compatibility_check, + method="POST" + ) + + self.route("/config/", callback=self.config_subject_get, method="GET") + self.route("/config/", callback=self.config_subject_set, method="PUT") + self.route("/config", callback=self.config_get, method="GET") + self.route("/config", callback=self.config_set, method="PUT") + + self.route("/schemas/ids/", callback=self.schemas_get, method="GET") + + self.route("/subjects", callback=self.subjects_list, method="GET") + self.route("/subjects//versions", callback=self.subject_post, method="POST") + self.route("/subjects//versions", callback=self.subject_versions_list, method="GET") + self.route("/subjects//versions/", callback=self.subject_version_get, method="GET") + self.route("/subjects//versions/", callback=self.subject_version_delete, method="DELETE") + self.route("/subjects/", callback=self.subject_delete, method="DELETE") + + self.ksr = None + self.read_config() + self._create_producer() + self._create_schema_reader() + self._create_master_coordinator() + self.app.on_startup.append(self.create_http_client) + + self.master_lock = asyncio.Lock() + + self.log.info("Karapace initialized") + + def close(self): + self.log.info("Shutting down all auxiliary threads") + if self.mc: + self.mc.close() + if self.ksr: + self.ksr.close() + if self.producer: + self.producer.close() + + def read_config(self): + if os.path.exists(self.config_path): + try: + config = json.loads(open(self.config_path, "r").read()) + self.config = set_config_defaults(config) + try: + logging.getLogger().setLevel(config["log_level"]) + except ValueError: + self.log.excption("Problem with log_level: %r", config["log_level"]) + except Exception as ex: + raise InvalidConfiguration(ex) + else: + raise InvalidConfiguration() + + def _create_schema_reader(self): + self.ksr = KafkaSchemaReader(config=self.config, ) + self.ksr.start() + + def _create_master_coordinator(self): + self.mc = MasterCoordinator(config=self.config) + self.mc.start() + + def _create_producer(self): + self.producer = KafkaProducer( + bootstrap_servers=self.config["bootstrap_uri"], + security_protocol=self.config["security_protocol"], + ssl_cafile=self.config["ssl_cafile"], + ssl_certfile=self.config["ssl_certfile"], + ssl_keyfile=self.config["ssl_keyfile"], + api_version=(1, 0, 0), + ) + + @staticmethod + def r(body, status=200): + raise HTTPResponse( + body=body, + status=status, + content_type="application/vnd.schemaregistry.v1+json", + headers={}, + ) + + def get_offset_from_queue(self, sent_offset): + start_time = time.monotonic() + while True: + self.log.info("Starting to wait for offset: %r from ksr queue", sent_offset) + offset = self.ksr.queue.get() + if offset == sent_offset: + self.log.info( + "We've consumed back produced offset: %r message back, everything is in sync, took: %.4f", offset, + time.monotonic() - start_time + ) + break + elif offset != sent_offset: + self.log.error("Put the offset: %r back to queue, someone else is waiting for this?", offset) + self.ksr.queue.put(offset) + + def send_kafka_message(self, key, value): + if isinstance(key, str): + key = key.encode("utf8") + if isinstance(value, str): + value = value.encode("utf8") + + future = self.producer.send(self.config["topic_name"], key=key, value=value) + self.producer.flush(timeout=self.kafka_timeout) + msg = future.get(self.kafka_timeout) + self.log.warning("Sent kafka msg key: %r, value: %r, offset: %r", key, value, msg.offset) + self.get_offset_from_queue(msg.offset) + return future + + def send_schema_message(self, subject, parsed_schema_json, schema_id, version, deleted): + key = f'{{"subject":"{subject}","version":{version},"magic":1,"keytype":"SCHEMA"}}' + value = { + "subject": subject, + "version": version, + "id": schema_id, + "schema": json_encode(parsed_schema_json, compact=True), + "deleted": deleted + } + return self.send_kafka_message(key, json_encode(value, compact=True)) + + def send_config_message(self, compatibility_level, subject=None): + if subject is not None: + key = '{{"subject":"{}","magic":0,"keytype":"CONFIG"}}'.format(subject) + else: + key = '{"subject":null,"magic":0,"keytype":"CONFIG"}' + value = f'{{"compatibilityLevel":"{compatibility_level}"}}' + return self.send_kafka_message(key, value) + + def send_delete_subject_message(self, subject): + key = f'{{"subject":"{subject}","magic":0,"keytype":"DELETE_SUBJECT"}}' + value = f'{{"subject":"{subject}","version":2}}' + return self.send_kafka_message(key, value) + + async def compatibility_check(self, *, subject, version, request): + """Check for schema compatibility""" + body = request.json + self.log.info("Got request to check subject: %r, version_id: %r compatibility", subject, version) + old = await self.subject_version_get(subject=subject, version=version, return_dict=True) + self.log.info("Existing schema: %r, new_schema: %r", old["schema"], body["schema"]) + try: + new = avro.schema.Parse(body["schema"]) + except avro.schema.SchemaParseException: + self.log.warning("Invalid schema: %r", body["schema"]) + self.r(body={"error_code": 44201, "message": "Invalid Avro schema"}, status=422) + try: + old_schema = avro.schema.Parse(json.loads(old["schema"])) + except avro.schema.SchemaParseException: + self.log.warning("Invalid existing schema: %r", old["schema"]) + self.r(body={"error_code": 44201, "message": "Invalid Avro schema"}, status=422) + + compat = Compatibility( + source=old_schema, + target=new, + compatibility=old.get("compatibility", self.ksr.config["compatibility"]) + ) + try: + compat.check() + except IncompatibleSchema as ex: + self.log.warning("Invalid schema %s found by compatibility check: old: %s new: %s", ex, old_schema, new) + self.r({"is_compatible": False}) + self.r({"is_compatible": True}) + + async def schemas_get(self, *, schema_id): + schema = self.ksr.schemas.get(int(schema_id)) + if not schema: + self.log.warning("Schema: %r that was requested, not found", int(schema_id)) + self.r(body={"error_code": 40403, "message": "Schema not found"}, status=404) + self.r({"schema": schema}) + + async def config_get(self): + self.r({"compatibilityLevel": self.ksr.config["compatibility"]}) + + async def config_set(self, *, request): + if "compatibility" in request.json and request.json["compatibility"] in COMPATIBILITY_MODES: + compatibility_level = request.json["compatibility"] + self.send_config_message(compatibility_level=compatibility_level, subject=None) + else: + self.r( + body={ + "error_code": 42203, + "message": "Invalid compatibility level. Valid values are none, backward, forward and full" + }, + status=422 + ) + self.r({"compatibility": self.ksr.config["compatibility"]}) + + async def config_subject_get(self, *, subject): + subject_data = self.ksr.subjects.get(subject) + if not subject_data: + self.r({"error_code": 40401, "message": "no subject"}, status=404) + + if "compatibility" in subject_data: + self.r({"compatibilityLevel": subject_data["compatibility"]}) + + self.r({"error_code": 40401, "message": "Subject not found."}, status=404) + + async def config_subject_set(self, *, request, subject): + subject_data = self.ksr.subjects.get(subject) + if not subject_data: + self.r({"error_code": 40401, "message": "no subject"}, status=404) + + if "compatibility" in request.json and request.json["compatibility"] in COMPATIBILITY_MODES: + self.send_config_message(compatibility_level=request.json["compatibility"], subject=subject) + else: + self.r(body={"error_code": 42203, "message": "Invalid compatibility level"}, status=422) + + self.r({"compatibility": request.json["compatibility"]}) + + async def subjects_list(self): + self.r(list(self.ksr.subjects.keys())) + + async def subject_delete(self, *, subject): + subject_data = self.ksr.subjects.get(subject, {}) + if not subject_data: + self.r({"error_code": 40401, "message": "subject does not exist"}, status=404) + + self.send_delete_subject_message(subject) + self.r(list(subject_data["schemas"]), status=200) + + async def subject_version_get(self, *, subject, version, return_dict=False): + if version != "latest" and int(version) < 1: + self.r({ + "error_code": 42202, + "message": 'The specified version is not a valid version id. ' + 'Allowed values are between [1, 2^31-1] and the string "latest"' + }, + status=422) + + subject_data = self.ksr.subjects.get(subject) + if not subject_data: + self.r({"error_code": 40401, "message": "no subject"}, status=404) + + max_version = max(subject_data["schemas"]) + if version == "latest": + schema = subject_data["schemas"][max(subject_data["schemas"])] + version = max(subject_data["schemas"]) + elif int(version) <= max_version: + schema = subject_data["schemas"].get(int(version)) + else: + self.r({"error_code": 40402, "message": "Version not found."}, status=404) + + schema_string = schema["schema"] + schema_id = schema["id"] + ret = { + "subject": subject, + "version": int(version), + "id": schema_id, + "schema": json_encode(schema_string, compact=True) + } + if return_dict: + # Return also compatibility information to compatibility check + if subject_data.get("compatibility"): + ret["compatibility"] = subject_data.get("compatibility") + return ret + self.r(ret) + + async def subject_version_delete(self, *, subject, version): + version = int(version) + subject_data = self.ksr.subjects.get(subject) + if not subject_data: + self.r({"error_code": 40401, "message": "subject not found"}, status=404) + + schema = subject_data["schemas"].get(version, None) + if not schema: + self.r({"error_code": 40402, "message": "Version not found."}, status=404) + schema_id = schema["id"] + self.send_schema_message(subject, schema, schema_id, version, deleted=True) + self.r(str(version), status=200) + + async def subject_versions_list(self, *, subject): + subject_data = self.ksr.subjects.get(subject) + if not subject_data: + self.r({"error_code": 40401, "message": "subject not found"}, status=404) + + self.r(list(subject_data["schemas"]), status=200) + + async def get_master(self): + async with self.master_lock: + while True: + master, master_url = self.mc.get_master_info() + if master is None: + self.log.info("No master set: %r, url: %r", master, master_url) + elif self.ksr.ready is False: + self.log.info("Schema reader isn't ready yet: %r", self.ksr.ready) + else: + return master, master_url + await asyncio.sleep(1.0) + + async def subject_post(self, *, subject, request): + body = request.json + self.log.debug("POST with subject: %r, request: %r", subject, body) + are_we_master, master_url = await self.get_master() + if are_we_master: + self.write_new_schema_local(subject, body) + elif are_we_master is None: + self.r({"error_code": 50003, "message": "Error while forwarding the request to the master."}, status=500) + else: + await self.write_new_schema_remote(subject, body, master_url) + + def write_new_schema_local(self, subject, body): + """Since we're the master we get to write the new schema""" + self.log.info("Writing new schema locally since we're the master") + try: + new_schema = avro.schema.Parse(body["schema"]) + except avro.schema.SchemaParseException: + self.log.warning("Invalid schema: %r", body["schema"]) + self.r(body={"error_code": 44201, "message": "Invalid Avro schema"}, status=422) + + if subject not in self.ksr.subjects: + schema_id = self.ksr.get_new_schema_id() + version = 1 + self.log.info( + "Registering new subject: %r with version: %r to schema %r, schema_id: %r", subject, version, + new_schema.to_json(), schema_id + ) + else: + # First check if any of the existing schemas for the subject match + subject_data = self.ksr.subjects[subject] + schema_versions = sorted(list(subject_data["schemas"])) + # Go through these in version order + for version in schema_versions: + schema = subject_data["schemas"][version] + parsed_version_schema = avro.schema.Parse(schema["schema"]) + if parsed_version_schema == new_schema: + self.r({"id": schema["id"]}) + else: + self.log.debug("schema: %s did not match with: %s", schema["schema"], new_schema.to_json()) + + # Run a compatibility check between the newest on file schema and the one being submitted now + latest_schema = subject_data["schemas"][schema_versions[-1]] + old_schema = avro.schema.Parse(latest_schema["schema"]) + compat = Compatibility( + old_schema, + new_schema, + compatibility=subject_data.get("compatibility", self.ksr.config["compatibility"]) + ) + try: + compat.check() + except IncompatibleSchema as ex: + self.log.warning("Incompatible schema: %s", ex) + self.r( + body={ + "error_code": 409, + "message": "Schema being registered is incompatible with an earlier schema" + }, + status=409 + ) + + # We didn't find an existing schema, so go and create one + schema_id = self.ksr.get_new_schema_id() + version = max(self.ksr.subjects[subject]["schemas"]) + 1 + self.log.info( + "Registering subject: %r, id: %r new version: %r with schema %r, schema_id: %r", subject, schema_id, version, + new_schema.to_json(), schema_id + ) + self.send_schema_message(subject, new_schema.to_json(), schema_id, version, deleted=False) + self.r({"id": schema_id}) + + async def write_new_schema_remote(self, subject, body, master_url): + self.log.info("Writing new schema to remote url: %r since we're not the master", master_url) + response = await self.http_request( + url="{}/subjects/{}/versions".format(master_url, subject), method="POST", json=body, timeout=60.0 + ) + self.r(body=response.body, status=response.status) + + +def main(): + if len(sys.argv) != 2: + print("Not enough arguments, given - usage schema config.json") + return 1 + + config_path = sys.argv[1] + if not os.path.exists(config_path): + print("Config file: {} does not exist, exiting".format(config_path)) + return 1 + kc = Karapace(config_path) + return kc.run(host=kc.config["host"], port=kc.config["port"]) + + +if __name__ == "__main__": + sys.exit(main()) diff --git a/karapace/master_coordinator.py b/karapace/master_coordinator.py new file mode 100644 index 000000000..0f3b5bfa4 --- /dev/null +++ b/karapace/master_coordinator.py @@ -0,0 +1,177 @@ +""" +karapace - master coordinator + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import json +import logging +import time +from threading import Lock, Thread + +from kafka.client_async import KafkaClient +from kafka.coordinator.base import BaseCoordinator +from kafka.errors import NoBrokersAvailable, NodeNotReadyError +from kafka.metrics import MetricConfig, Metrics + +# SR group errors +NO_ERROR = 0 +DUPLICATE_URLS = 1 + + +def get_identity_url(scheme, host, port): + return f"{scheme}://{host}:{port}" + + +class SchemaCoordinator(BaseCoordinator): + hostname = None + port = None + scheme = None + master = None + master_url = None + log = logging.getLogger("SchemaCoordinator") + + def protocol_type(self): + return "sr" + + @staticmethod + def get_identity(*, host, port, scheme, json_encode=True): + res = {"version": 1, "host": host, "port": port, "scheme": scheme, "master_eligibility": True} + if json_encode: + return json.dumps(res) + return res + + def group_protocols(self): + return [("v0", self.get_identity(host=self.hostname, port=self.port, scheme=self.scheme))] + + def _perform_assignment(self, leader_id, protocol, members): + self.log.info("Creating assignment: %r, protocol: %r, members: %r", leader_id, protocol, members) + self.master = None + error = NO_ERROR + urls = {} + for member_id, member_data in members: + member_identity = json.loads(member_data.decode("utf8")) + if member_identity["master_eligibility"] is True: + urls[get_identity_url(member_identity["scheme"], member_identity["host"], + member_identity["port"])] = (member_id, member_data) + + lowest_url = sorted(urls)[0] + schema_master_id, member_data = urls[lowest_url] + member_identity = json.loads(member_data.decode("utf8")) + identity = self.get_identity( + host=member_identity["host"], + port=member_identity["port"], + scheme=member_identity["scheme"], + json_encode=False, + ) + self.log.info("Chose: %r with url: %r as the master", schema_master_id, lowest_url) + self.master_url = lowest_url + + assignments = {} + for member_id, member_data in members: + assignments[member_id] = json.dumps({"master": schema_master_id, "master_identity": identity, "error": error}) + return assignments + + def _on_join_prepare(self, generation, member_id): + """Invoked prior to each group join or rejoin.""" + # needs to be implemented in our class for pylint to be satisfied + + def _on_join_complete(self, generation, member_id, protocol, member_assignment_bytes): + self.log.info( + "Join complete, generation %r, member_id: %r, protocol: %r, member_assignment_bytes: %r", generation, member_id, + protocol, member_assignment_bytes + ) + member_assignment = json.loads(member_assignment_bytes.decode("utf8")) + member_identity = member_assignment["master_identity"] + + master_url = get_identity_url( + scheme=member_identity["scheme"], + host=member_identity["host"], + port=member_identity["port"], + ) + if member_assignment["master"] == member_id: + self.master_url = master_url + self.master = True + else: + self.master_url = master_url + self.master = False + return super(SchemaCoordinator, self)._on_join_complete(generation, member_id, protocol, member_assignment_bytes) + + def _on_join_follower(self): + self.log.info("We are a follower, not a master") + return super(SchemaCoordinator, self)._on_join_follower() + + +class MasterCoordinator(Thread): + """Handles schema topic creation and master election""" + + def __init__(self, config): + Thread.__init__(self) + self.config = config + self.api_version_auto_timeout_ms = 30000 + self.timeout_ms = 10000 + self.kafka_client = None + self.running = True + self.sc = None + metrics_tags = {"client-id": self.config["client_id"]} + metric_config = MetricConfig(samples=2, time_window_ms=30000, tags=metrics_tags) + self._metrics = Metrics(metric_config, reporters=[]) + self.lock = Lock() + self.lock.acquire() + self.log = logging.getLogger("MasterCoordinator") + + def init_kafka_client(self): + try: + self.kafka_client = KafkaClient( + api_version_auto_timeout_ms=self.api_version_auto_timeout_ms, + bootstrap_servers=self.config["bootstrap_uri"], + client_id=self.config["client_id"], + security_protocol=self.config["security_protocol"], + ssl_cafile=self.config["ssl_cafile"], + ssl_certfile=self.config["ssl_certfile"], + ssl_keyfile=self.config["ssl_keyfile"], + ) + return True + except (NodeNotReadyError, NoBrokersAvailable): + self.log.warning("No Brokers available yet, retrying init_kafka_client()") + time.sleep(2.0) + return False + + def init_schema_coordinator(self): + self.sc = SchemaCoordinator( + client=self.kafka_client, + metrics=self._metrics, + group_id=self.config["group_id"], + ) + self.sc.hostname = self.config["advertised_hostname"] + self.sc.port = self.config["port"] + self.sc.scheme = "http" + self.lock.release() # self.sc now exists, we get to release the lock + + def get_master_info(self): + """Return whether we're the master, and the actual master url that can be used if we're not""" + with self.lock: + return self.sc.master, self.sc.master_url + + def close(self): + self.log.info("Closing master_coordinator") + self.running = False + if self.kafka_client: + self.kafka_client.close() + + def run(self): + while self.running: + try: + if not self.kafka_client: + if self.init_kafka_client() is False: + continue + if not self.sc: + self.init_schema_coordinator() + + self.sc.ensure_active_group() + self.log.info("We're master: %r: master_uri: %r", self.sc.master, self.sc.master_url) + time.sleep(5.0) + except: # pylint: disable=bare-except + self.log.exception("Exception in master_coordinator") + time.sleep(1.0) + self.close() diff --git a/karapace/rapu.py b/karapace/rapu.py new file mode 100644 index 000000000..21e5e05d3 --- /dev/null +++ b/karapace/rapu.py @@ -0,0 +1,306 @@ +""" +karapace - +Custom middleware system on top of `aiohttp` implementing HTTP server and +client components for use in Aiven's REST applications. + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import asyncio +import hashlib +import json as jsonlib +import logging +import re +import ssl +import time + +import aiohttp +import aiohttp.web +import aiosocksy +import aiosocksy.connector +import async_timeout +from karapace.statsd import statsd_client +from karapace.utils import json_encode +from karapace.version import __version__ + + +SERVER_NAME = f"Karapace/{__version__}" + + +class HTTPRequest: + def __init__(self, *, url, query, headers, path_for_stats, method): + self.url = url + self.headers = headers + self.query = query + self.path_for_stats = path_for_stats + self.method = method + self.json = None + + +class HTTPResponse(Exception): + """A custom Response object derived from Exception so it can be raised + in response handler callbacks.""" + + def __init__(self, body, *, status=200, content_type=None, headers=None): + self.body = body + self.status = status + self.headers = dict(headers) if headers else {} + if isinstance(body, (dict, list)): + self.headers["Content-Type"] = "application/json" + self.json = body + else: + self.json = None + if content_type: + self.headers["Content-Type"] = content_type + super().__init__("HTTPResponse {}".format(status)) + + def ok(self): + if self.status < 200 or self.status >= 300: + return False + return True + + +class RestApp: + def __init__(self, *, app_name): + self.app_name = app_name + self.app_request_metric = "{}_request".format(app_name) + self.app = aiohttp.web.Application() + self.app.on_startup.append(self.create_http_client) + self.app.on_cleanup.append(self.cleanup_http_client) + self.http_client_v = None + self.http_client_no_v = None + self.log = logging.getLogger(self.app_name) + self.stats = self._get_stats_client() + self.app.on_cleanup.append(self.cleanup_stats_client) + + def _get_stats_client(self): + return statsd_client(app=self.app_name) + + async def cleanup_stats_client(self, app): # pylint: disable=unused-argument + self.stats.close() + + async def create_http_client(self, app): # pylint: disable=unused-argument + no_v_conn = aiohttp.TCPConnector(verify_ssl=False) + self.http_client_no_v = aiohttp.ClientSession(connector=no_v_conn, headers={"User-Agent": SERVER_NAME}) + self.http_client_v = aiohttp.ClientSession(headers={"User-Agent": SERVER_NAME}) + + async def cleanup_http_client(self, app): # pylint: disable=unused-argument + if self.http_client_no_v: + await self.http_client_no_v.close() + if self.http_client_v: + await self.http_client_v.close() + + @staticmethod + def cors_and_server_headers_for_request(*, request, origin="*"): # pylint: disable=unused-argument + return { + "Access-Control-Allow-Origin": origin, + "Access-Control-Allow-Methods": "DELETE, GET, OPTIONS, POST, PUT", + "Access-Control-Allow-Headers": "Authorization, Content-Type", + "Server": SERVER_NAME, + } + + async def _handle_request(self, *, request, path_for_stats, callback, callback_with_request=False, json_request=False): + start_time = time.monotonic() + resp = None + rapu_request = HTTPRequest( + headers=request.headers, + query=request.query, + method=request.method, + url=request.url, + path_for_stats=path_for_stats, + ) + try: + if request.method == "OPTIONS": + origin = request.headers.get("Origin") + if not origin: + raise HTTPResponse(body="OPTIONS missing Origin", status=400) + headers = self.cors_and_server_headers_for_request(request=rapu_request, origin=origin) + raise HTTPResponse(body=b"", status=200, headers=headers) + + body = await request.read() + if json_request: + if not body: + raise HTTPResponse(body="Missing request JSON body", status=400) + if request.charset and request.charset.lower() != "utf-8" and request.charset.lower() != "utf8": + raise HTTPResponse(body="Request character set must be UTF-8", status=400) + try: + body_string = body.decode("utf-8") + rapu_request.json = jsonlib.loads(body_string) + except jsonlib.decoder.JSONDecodeError: + raise HTTPResponse(body="Invalid request JSON body", status=400) + except UnicodeDecodeError: + raise HTTPResponse(body="Request body is not valid UTF-8", status=400) + else: + if body not in {b"", b"{}"}: + raise HTTPResponse(body="No request body allowed for this operation", status=400) + + callback_kwargs = dict(request.match_info) + if callback_with_request: + callback_kwargs["request"] = rapu_request + + try: + data = await callback(**callback_kwargs) + status = 200 + headers = {} + except HTTPResponse as ex: + data = ex.body + status = ex.status + headers = ex.headers + headers.update(self.cors_and_server_headers_for_request(request=rapu_request)) + + if isinstance(data, (dict, list)): + resp_bytes = json_encode(data, binary=True, sort_keys=True, compact=True) + elif isinstance(data, str): + if "Content-Type" not in headers: + headers["Content-Type"] = "text/plain; charset=utf-8" + resp_bytes = data.encode("utf-8") + else: + resp_bytes = data + + # On 204 - NO CONTENT there is no point of calculating cache headers + if 200 >= status <= 299: + if resp_bytes: + etag = '"{}"'.format(hashlib.md5(resp_bytes).hexdigest()) + else: + etag = '""' + if_none_match = request.headers.get("if-none-match") + if if_none_match and if_none_match.replace("W/", "") == etag: + status = 304 + resp_bytes = b"" + + headers["access-control-expose-headers"] = "etag" + headers["etag"] = etag + + resp = aiohttp.web.Response(body=resp_bytes, status=status, headers=headers) + except HTTPResponse as ex: + if isinstance(ex.body, str): + resp = aiohttp.web.Response(text=ex.body, status=ex.status, headers=ex.headers) + else: + resp = aiohttp.web.Response(body=ex.body, status=ex.status, headers=ex.headers) + except asyncio.CancelledError: + self.log.debug("Client closed connection") + raise + except Exception as ex: # pylint: disable=broad-except + self.stats.unexpected_exception(ex=ex, where="rapu_wrapped_callback") + self.log.exception("Unexpected error handling user request: %s %s", request.method, request.url) + resp = aiohttp.web.Response(text="Internal Server Error", status=500) + finally: + self.stats.timing( + self.app_request_metric, + time.monotonic() - start_time, + tags={ + "path": path_for_stats, + # no `resp` means that we had a failure in exception handler + "result": resp.status if resp else 0, + "method": request.method, + } + ) + + return resp + + def route(self, path, *, callback, method, with_request=None, json_body=None): + # pretty path for statsd reporting + path_for_stats = re.sub(r"<[\w:]+>", "x", path) + + # bottle compatible routing + aio_route = path + aio_route = re.sub(r"<(\w+):path>", r"{\1:.+}", aio_route) + aio_route = re.sub(r"<(\w+)>", r"{\1}", aio_route) + + if (method in {"POST", "PUT"}) and with_request is None: + with_request = True + + if with_request and json_body is None: + json_body = True + + async def wrapped_callback(request): + return await self._handle_request( + request=request, + path_for_stats=path_for_stats, + callback=callback, + callback_with_request=with_request, + json_request=json_body, + ) + + async def wrapped_cors(request): + return await self._handle_request( + request=request, + path_for_stats=path_for_stats, + callback=None, + ) + + self.app.router.add_route(method, aio_route, wrapped_callback) + try: + self.app.router.add_route("OPTIONS", aio_route, wrapped_cors) + except RuntimeError as ex: + if "Added route will never be executed, method OPTIONS is already registered" not in str(ex): + raise + + async def http_request( + self, + url, + *, + method="GET", + json=None, + timeout=10.0, + verify=True, + proxy=None, + ): + close_session = False + proxy_auth = None + proxy_url = None + + if isinstance(verify, str): + sslcontext = ssl.create_default_context(cadata=verify) + else: + sslcontext = None + + if proxy: + proxy_auth = aiosocksy.Socks5Auth(proxy["username"], proxy["password"]) + connector = aiosocksy.connector.ProxyConnector( + remote_resolve=False, + verify_ssl=verify, + ssl_context=sslcontext, + ) + session = aiohttp.ClientSession( + connector=connector, + request_class=aiosocksy.connector.ProxyClientRequest, + ) + proxy_url = "socks5://{host}:{port}".format_map(proxy) + close_session = True + elif sslcontext: + conn = aiohttp.TCPConnector(ssl_context=sslcontext) + session = aiohttp.ClientSession(connector=conn) + close_session = True + elif verify is True: + session = self.http_client_v + elif verify is False: + session = self.http_client_no_v + else: + raise ValueError("invalid arguments to http_request") + + func = getattr(session, method.lower()) + try: + with async_timeout.timeout(timeout): + async with func(url, json=json, proxy=proxy_url, proxy_auth=proxy_auth) as response: + if response.headers.get("content-type", "").startswith("application/json"): + resp_content = await response.json() + else: + resp_content = await response.text() + result = HTTPResponse(body=resp_content, status=response.status) + finally: + if close_session: + await session.close() + + return result + + def run(self, *, host, port): + aiohttp.web.run_app( + app=self.app, + host=host, + port=port, + access_log_format='%Tfs %{x-client-ip}i "%r" %s "%{user-agent}i" response=%bb request_body=%{content-length}ib', + ) + + def add_routes(self): + pass # Override in sub-classes diff --git a/karapace/schema_reader.py b/karapace/schema_reader.py new file mode 100644 index 000000000..aa4e0d44d --- /dev/null +++ b/karapace/schema_reader.py @@ -0,0 +1,201 @@ +""" +karapace - Kafka schema reader + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import json +import logging +import time +from queue import Queue +from threading import Thread + +from kafka import KafkaConsumer +from kafka.admin import KafkaAdminClient, NewTopic +from kafka.errors import (NoBrokersAvailable, NodeNotReadyError, TopicAlreadyExistsError) + + +class KafkaSchemaReader(Thread): + def __init__(self, config): + Thread.__init__(self) + self.log = logging.getLogger("KafkaSchemaReader") + self.api_version_auto_timeout_ms = 30000 + self.topic_creation_timeout_ms = 20000 + self.timeout_ms = 200 + self.config = config + self.subjects = {} + self.schemas = {} + self.global_schema_id = 0 + self.offset = 0 + self.admin_client = None + self.topic_num_partitions = 1 + self.topic_replication_factor = self.config["replication_factor"] + self.consumer = None + self.queue = Queue() + self.ready = False + self.running = True + + def init_consumer(self): + # Group not set on purpose, all consumers read the same data + self.consumer = KafkaConsumer( + self.config["topic_name"], + enable_auto_commit=False, + api_version=(1, 0, 0), + bootstrap_servers=self.config["bootstrap_uri"], + client_id=self.config["client_id"], + security_protocol=self.config["security_protocol"], + ssl_cafile=self.config["ssl_cafile"], + ssl_certfile=self.config["ssl_certfile"], + ssl_keyfile=self.config["ssl_keyfile"], + auto_offset_reset="earliest", + ) + + def init_admin_client(self): + try: + self.admin_client = KafkaAdminClient( + api_version_auto_timeout_ms=self.api_version_auto_timeout_ms, + bootstrap_servers=self.config["bootstrap_uri"], + client_id=self.config["client_id"], + security_protocol=self.config["security_protocol"], + ssl_cafile=self.config["ssl_cafile"], + ssl_certfile=self.config["ssl_certfile"], + ssl_keyfile=self.config["ssl_keyfile"], + ) + return True + except (NodeNotReadyError, NoBrokersAvailable): + self.log.warning("No Brokers available yet, retrying init_admin_client()") + time.sleep(2.0) + return False + + def create_schema_topic(self): + schema_topic = NewTopic( + name=self.config["topic_name"], + num_partitions=self.topic_num_partitions, + replication_factor=self.config["replication_factor"], + topic_configs={"cleanup.policy": "compact"} + ) + try: + self.log.info("Creating topic: %r", schema_topic) + self.admin_client.create_topics([schema_topic], timeout_ms=self.topic_creation_timeout_ms) + self.log.info("Topic: %r created successfully", self.config["topic_name"]) + return True + except TopicAlreadyExistsError: + self.log.warning("Topic: %r already exists", self.config["topic_name"]) + return True + return False + + def get_new_schema_id(self): + self.global_schema_id += 1 + return self.global_schema_id + + def close(self): + self.log.info("Closing schema_reader") + self.running = False + if self.admin_client: + self.admin_client.close() + if self.consumer: + self.consumer.close() + + def run(self): + while self.running: + if not self.admin_client: + if self.init_admin_client() is False: + continue + self.create_schema_topic() + if not self.consumer: + self.init_consumer() + self.handle_messages() + + def handle_messages(self): + raw_msgs = self.consumer.poll(timeout_ms=self.timeout_ms) + if self.ready is False and raw_msgs == {}: + self.ready = True + + for _, msgs in raw_msgs.items(): + for msg in msgs: + try: + key = json.loads(msg.key.decode("utf8")) + except json.JSONDecodeError: + self.log.exception("Invalid JSON in msg.key: %r, value: %r", msg.key, msg.value) + continue + + value = None + if msg.value: + try: + value = json.loads(msg.value.decode("utf8")) + except json.JSONDecodeError: + self.log.exception("Invalid JSON in msg.value: %r, key: %r", msg.value, msg.key) + continue + + self.log.info("Read new record: key: %r, value: %r, offset: %r", key, value, msg.offset) + self.handle_msg(key, value) + self.offset = msg.offset + self.log.info("Handled message, current offset: %r", self.offset) + if self.ready: + self.queue.put(self.offset) + + def handle_msg(self, key, value): + if key["keytype"] == "CONFIG": + if "subject" in key and key["subject"] is not None: + self.log.info( + "Setting subject: %r config to: %r, value: %r", key["subject"], value["compatibilityLevel"], value + ) + subject_data = self.subjects.get(key["subject"]) + subject_data["compatibility"] = value["compatibilityLevel"] + else: + self.log.info("Setting global config to: %r, value: %r", value["compatibilityLevel"], value) + self.config["compatibility"] = value["compatibilityLevel"] + elif key["keytype"] == "SCHEMA": + subject = value["subject"] + if subject not in self.subjects: + self.log.info("Adding first version of subject: %r, value: %r", subject, value) + self.subjects[subject] = { + "schemas": { + value["version"]: { + "schema": value["schema"], + "version": value["version"], + "id": value["id"], + } + } + } + self.log.info("Setting schema_id: %r with schema: %r", value["id"], value["schema"]) + self.schemas[value["id"]] = value["schema"] + self.global_schema_id = value["id"] + elif value["deleted"] is True: + self.log.info("Deleting subject: %r, version: %r", subject, value["version"]) + entry = self.subjects[subject]["schemas"].pop(value["version"], None) + if not entry: + self.log.error( + "Subject: %r, version: %r, value: %r did not exist, should have.", subject, value["version"], value + ) + else: + self.log.info("Deleting schema_id: %r, schema: %r", value["id"], self.schemas.get(value["id"])) + entry = self.schemas.pop(value["id"], None) + if not entry: + self.log.error("Schema: %r did not exist, should have", value["id"]) + elif value["deleted"] is False: + self.log.info("Adding new version of subject: %r, value: %r", subject, value) + self.subjects[subject]["schemas"][value["version"]] = { + "schema": value["schema"], + "version": value["version"], + "id": value["id"] + } + self.log.info("Setting schema_id: %r with schema: %r", value["id"], value["schema"]) + self.schemas[value["id"]] = value["schema"] + self.global_schema_id = value["id"] + elif key["keytype"] == "DELETE_SUBJECT": + self.log.info("Deleting subject: %r, value: %r", value["subject"], value) + subject = self.subjects.pop(value["subject"], None) + if not subject: + self.log.error("Subject: %r did not exist, should have", value["subject"]) + else: + for schema in subject["schemas"].values(): + self.log.info( + "Deleting subject: %r, schema_id: %r, schema: %r", subject, schema["id"], + self.schemas.get(schema["id"]) + ) + entry = self.schemas.pop(schema["id"], None) + if not entry: + self.log.error("Schema: %r did not exist, should have", schema["id"]) + elif key["keytype"] == "NOOP": # for spec completeness + pass diff --git a/karapace/statsd.py b/karapace/statsd.py new file mode 100644 index 000000000..2b0199a46 --- /dev/null +++ b/karapace/statsd.py @@ -0,0 +1,125 @@ +""" +karapace - statsd + +Supports telegraf's statsd protocol extension for 'key=value' tags: + + https://github.com/influxdata/telegraf/tree/master/plugins/inputs/statsd + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import datetime +import logging +import os +import socket +import time +from contextlib import contextmanager + +STATSD_HOST = "127.0.0.1" +STATSD_PORT = 8125 + + +class StatsClient: + def __init__(self, host="127.0.0.1", port=8125, tags=None): + self.log = logging.getLogger("StatsClient") + self.sentry_config = {} + self.update_sentry_config({ + "dsn": os.environ.get("SENTRY_DSN") or None, + "tags": tags, + "ignore_exceptions": [ + "ClientConnectorError", # influxdb, aiohttp + "ClientPayloadError", # infludb (aiohttp) + "ConnectionLoss", # kazoo, zkwrap + "ConnectionRefusedError", # mostly kafka (asyncio) + "ConnectionResetError", # paramiko, kafka, requests + "IncompleteReadError", # kafka (asyncio) + "ServerDisconnectedError", # influxdb (aiohttp) + "ServerTimeoutError", # influxdb (aiohttp) + "TimeoutError", # kafka, redis + ] + }) + self._dest_addr = (host, port) + self._socket = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + self._tags = tags or {} + + @contextmanager + def timing_manager(self, metric, tags=None): + start_time = time.monotonic() + yield + self.timing(metric, time.monotonic() - start_time, tags) + + def update_sentry_config(self, config): + new_config = self.sentry_config.copy() + new_config.update(config) + if new_config == self.sentry_config: + return + + self.sentry_config = new_config + if self.sentry_config.get("dsn"): + try: + # Lazy-load raven as this file is loaded by a lot of tools + import raven + self.raven_client = raven.Client(**self.sentry_config) + except ImportError: + self.raven_client = None + self.log.warning("Cannot enable Sentry.io sending: importing 'raven' failed") + else: + self.raven_client = None + + def gauge(self, metric, value, tags=None): + self._send(metric, b"g", value, tags) + + def increase(self, metric, inc_value=1, tags=None): + self._send(metric, b"c", inc_value, tags) + + def timing(self, metric, value, tags=None): + self._send(metric, b"ms", value, tags) + + def unexpected_exception(self, ex, where, tags=None, *, elapsed=None): + all_tags = { + "exception": ex.__class__.__name__, + "where": where, + } + all_tags.update(tags or {}) + self.increase("exception", tags=all_tags) + if self.raven_client: + raven_tags = {**(tags or {}), "where": where} + self.raven_client.captureException(tags=raven_tags, time_spent=elapsed) + + def _send(self, metric, metric_type, value, tags): + if None in self._dest_addr: + # stats sending is disabled + return + + try: + # format: "user.logins,service=payroll,region=us-west:1|c" + parts = [metric.encode("utf-8"), b":", str(value).encode("utf-8"), b"|", metric_type] + send_tags = self._tags.copy() + send_tags.update(tags or {}) + for tag, tag_value in sorted(send_tags.items()): + if tag_value is None: + tag_value = "" + elif isinstance(tag_value, datetime.datetime): + if tag_value.tzinfo: + tag_value = tag_value.astimezone(datetime.timezone.utc).replace(tzinfo=None) + tag_value = tag_value.isoformat()[:19].replace("-", "").replace(":", "") + "Z" + elif isinstance(tag_value, datetime.timedelta): + tag_value = "{}s".format(int(tag_value.total_seconds())) + elif not isinstance(tag_value, str): + tag_value = str(tag_value) + if " " in tag_value or ":" in tag_value or "|" in tag_value or "=" in tag_value: + tag_value = "INVALID" + parts.insert(1, ",{}={}".format(tag, tag_value).encode("utf-8")) + + self._socket.sendto(b"".join(parts), self._dest_addr) + except Exception as ex: # pylint: disable=broad-except + self.log.error("Unexpected exception in statsd send: %s: %s", ex.__class__.__name__, ex) + + def close(self): + self._socket.close() + + +def statsd_client(*, app, tags=None): + tags = (tags or {}).copy() + tags["app"] = app + return StatsClient(host=STATSD_HOST, port=STATSD_PORT, tags=tags) diff --git a/karapace/utils.py b/karapace/utils.py new file mode 100644 index 000000000..d5edcb45c --- /dev/null +++ b/karapace/utils.py @@ -0,0 +1,50 @@ +""" +karapace - utils + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import datetime +import decimal +import json as jsonlib +import types + + +def isoformat(datetime_obj=None, *, preserve_subsecond=False, compact=False): + """Return datetime to ISO 8601 variant suitable for users. + Assume UTC for datetime objects without a timezone, always use + the Z timezone designator.""" + if datetime_obj is None: + datetime_obj = datetime.datetime.utcnow() + elif datetime_obj.tzinfo: + datetime_obj = datetime_obj.astimezone(datetime.timezone.utc).replace(tzinfo=None) + isof = datetime_obj.isoformat() + if not preserve_subsecond: + isof = isof[:19] + if compact: + isof = isof.replace("-", "").replace(":", "").replace(".", "") + return isof + "Z" + + +def default_json_serialization(obj): + if isinstance(obj, datetime.datetime): + return isoformat(obj, preserve_subsecond=True) + if isinstance(obj, datetime.timedelta): + return obj.total_seconds() + if isinstance(obj, decimal.Decimal): + return str(obj) + if isinstance(obj, types.MappingProxyType): + return dict(obj) + + raise TypeError("Object of type {!r} is not JSON serializable".format(obj.__class__.__name__)) + + +def json_encode(obj, *, compact=True, sort_keys=True, binary=False): + res = jsonlib.dumps( + obj, + sort_keys=sort_keys if sort_keys is not None else not compact, + indent=None if compact else 4, + separators=(",", ":") if compact else None, + default=default_json_serialization + ) + return res.encode("utf-8") if binary else res diff --git a/karapace/version.py b/karapace/version.py new file mode 100644 index 000000000..b09440f15 --- /dev/null +++ b/karapace/version.py @@ -0,0 +1,7 @@ +""" +karapace - version + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +__version__ = "0.0.1-0-unknown-10a2904" diff --git a/pytest.ini b/pytest.ini new file mode 100644 index 000000000..1c3dd6f6f --- /dev/null +++ b/pytest.ini @@ -0,0 +1,2 @@ +[pytest] +addopts = -ra -q --tb=short --showlocals diff --git a/setup.py b/setup.py new file mode 100644 index 000000000..6a2b380a4 --- /dev/null +++ b/setup.py @@ -0,0 +1,58 @@ +""" +karapace - setup + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +from setuptools import setup, find_packages +import os +import version + + +readme_path = os.path.join(os.path.dirname(__file__), "README.rst") +with open(readme_path, "r") as fp: + readme_text = fp.read() + + +version_for_setup_py = version.get_project_version("karapace/version.py") +version_for_setup_py = ".dev".join(version_for_setup_py.split("-", 2)[:2]) + + +setup( + name="karapace", + version=version_for_setup_py, + zip_safe=False, + packages=find_packages(exclude=["test"]), + install_requires=[ + "aiohttp", + ], + extras_require={}, + dependency_links=[], + package_data={}, + entry_points={ + "console_scripts": [ + "karapace = karapace.karapace:main", + ], + }, + author="Hannu Valtonen", + author_email="hannu.valtonen@aiven.io", + license="AGPL 3", + platforms=["POSIX", "MacOS"], + description="Karapace", + long_description=readme_text, + url="https://github.com/aiven/karapace/", + classifiers=[ + "Development Status :: 5 - Production/Stable", + "Intended Audience :: Developers", + "Intended Audience :: Information Technology", + "Intended Audience :: System Administrators", + "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)", + "Programming Language :: Python :: 3.3", + "Programming Language :: Python :: 3.4", + "Programming Language :: Python :: 3.5", + "Programming Language :: Python :: 3.6", + "Programming Language :: Python :: 3.7", + "Topic :: Database :: Database Engines/Servers", + "Topic :: Software Development :: Libraries", + ], +) diff --git a/tests/__init__.py b/tests/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/tests/conftest.py b/tests/conftest.py new file mode 100644 index 000000000..5eb673254 --- /dev/null +++ b/tests/conftest.py @@ -0,0 +1,267 @@ +""" +karapace - conftest + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import contextlib +import os +import random +import signal +import socket +import subprocess +import time + +import pytest + +KAFKA_CURRENT_VERSION = "2.1" +BASEDIR = "kafka_2.12-2.1.0" + + +class Timeout(Exception): + pass + + +def port_is_listening(hostname, port, ipv6): + if ipv6: + s = socket.socket(socket.AF_INET6, socket.SOCK_STREAM, 0) + else: + s = socket.socket() + s.settimeout(0.5) + try: + s.connect((hostname, port)) + return True + except socket.error: + return False + + +def wait_for_port(port, *, hostname="127.0.0.1", wait_time=20.0, ipv6=False): + start_time = time.monotonic() + while True: + if port_is_listening(hostname, port, ipv6): + break + elif time.monotonic() - start_time > wait_time: + raise Timeout("Timeout waiting for port {} on host {}".format(port, hostname)) + time.sleep(2.0) + print("Port {} on host {} started listening in {} seconds".format(port, hostname, time.monotonic() - start_time)) + + +def get_random_port(*, start=3000, stop=30000, blacklist=None): + if isinstance(blacklist, int): + blacklist = [blacklist] + + while True: + value = random.randrange(start, stop) + if not blacklist or value not in blacklist: + return value + + +@pytest.fixture(scope="session", name="session_tmpdir") +def fixture_session_tmpdir(tmpdir_factory): + """Create a temporary directory object that's usable in the session scope. The returned value is a + function which creates a new temporary directory which will be automatically cleaned up upon exit.""" + tmpdir_obj = tmpdir_factory.mktemp("karapace.sssion.tmpdr.") + + def subdir(): + return tmpdir_obj.mkdtemp(rootdir=tmpdir_obj) + + try: + yield subdir + finally: + with contextlib.suppress(Exception): + tmpdir_obj.remove(rec=1) + + +@pytest.fixture(scope="session", name="zkserver") +def fixture_zkserver(session_tmpdir): + config, proc = zkserver_base(session_tmpdir) + try: + yield config + finally: + os.kill(proc.pid, signal.SIGKILL) + proc.wait(timeout=10.0) + + +@pytest.fixture(scope="session", name="kafka_server") +def fixture_kafka_server(session_tmpdir, zkserver): + config, proc = kafka_server_base(session_tmpdir, zkserver) + try: + yield config + finally: + os.kill(proc.pid, signal.SIGKILL) + proc.wait(timeout=10.0) + + +def kafka_java_args(heap_mb, kafka_config_path, logs_dir, log4j_properties_path): + java_args = [ + "-Xmx{}M".format(heap_mb), + "-Xms{}M".format(heap_mb), + "-Dkafka.logs.dir={}/logs".format(logs_dir), + "-Dlog4j.configuration=file:{}".format(log4j_properties_path), + "-cp", + ":".join([ + os.path.join(BASEDIR, "libs", "*"), + ]), + "kafka.Kafka", + kafka_config_path, + ] + return java_args + + +def get_java_process_configuration(java_args): + command = [ + "/usr/bin/java", + "-server", + "-XX:+UseG1GC", + "-XX:MaxGCPauseMillis=20", + "-XX:InitiatingHeapOccupancyPercent=35", + "-XX:+DisableExplicitGC", + "-XX:+ExitOnOutOfMemoryError", + "-Djava.awt.headless=true", + "-Dcom.sun.management.jmxremote", + "-Dcom.sun.management.jmxremote.authenticate=false", + "-Dcom.sun.management.jmxremote.ssl=false", + ] + command.extend(java_args) + return command + + +def kafka_server_base(session_tmpdir, zk): + datadir = session_tmpdir() + blacklist = [zk["admin_port"], zk["client_port"]] + plaintext_port = get_random_port(start=15000, blacklist=blacklist) + + config = { + "datadir": datadir.join("data").strpath, + "kafka_keystore_password": "secret", + "kafka_port": plaintext_port, + "zookeeper_port": zk["client_port"], + } + + os.makedirs(config["datadir"]) + advertised_listeners = ",".join([ + f"PLAINTEXT://127.0.0.1:{plaintext_port}", + ]) + listeners = ",".join([ + f"PLAINTEXT://:{plaintext_port}", + ]) + + kafka_config = { + "broker.id": 1, + "broker.rack": "local", + "advertised.listeners": advertised_listeners, + "auto.create.topics.enable": True, + "default.replication.factor": 1, + "delete.topic.enable": "true", + "inter.broker.listener.name": "PLAINTEXT", + "inter.broker.protocol.version": KAFKA_CURRENT_VERSION, + "listeners": listeners, + "log.cleaner.enable": "true", + "log.dirs": config["datadir"], + "log.message.format.version": KAFKA_CURRENT_VERSION, + "log.retention.check.interval.ms": 300000, + "log.segment.bytes": 200 * 1024 * 1024, # 200 MiB + "num.io.threads": 8, + "num.network.threads": 112, + "num.partitions": 1, + "num.replica.fetchers": 4, + "num.recovery.threads.per.data.dir": 1, + "offsets.topic.replication.factor": 1, + "socket.receive.buffer.bytes": 100 * 1024, + "socket.request.max.bytes": 100 * 1024 * 1024, + "socket.send.buffer.bytes": 100 * 1024, + "transaction.state.log.min.isr": 1, + "transaction.state.log.num.partitions": 16, + "transaction.state.log.replication.factor": 1, + "zookeeper.connection.timeout.ms": 6000, + "zookeeper.connect": "{}:{}".format("127.0.0.1", zk["client_port"]) + } + kafka_config_path = os.path.join(datadir.strpath, "kafka", "config") + os.makedirs(kafka_config_path) + + kafka_config_path = os.path.join(kafka_config_path, "server.properties") + with open(kafka_config_path, "w") as fp: + for key, value in kafka_config.items(): + fp.write(f"{key}={value}\n") + + log4j_properties_path = os.path.join(BASEDIR, "config/log4j.properties") + + kafka_cmd = get_java_process_configuration( + java_args=kafka_java_args( + heap_mb=256, + logs_dir=os.path.join(datadir.strpath, "kafka"), + log4j_properties_path=log4j_properties_path, + kafka_config_path=kafka_config_path, + ), + ) + proc = subprocess.Popen(kafka_cmd, env={}) + wait_for_port(config["kafka_port"], wait_time=60) + return config, proc + + +def zkserver_base(session_tmpdir, subdir="base"): + datadir = session_tmpdir() + path = os.path.join(datadir.strpath, subdir) + os.makedirs(path) + client_port = get_random_port(start=15000) + admin_port = get_random_port(start=15000, blacklist=client_port) + config = { + "client_port": client_port, + "admin_port": admin_port, + "path": path, + } + zoo_cfg = """ +# The number of milliseconds of each tick +tickTime=2000 +# The number of ticks that the initial +# synchronization phase can take +initLimit=10 +# The number of ticks that can pass between +# sending a request and getting an acknowledgement +syncLimit=5 +# the directory where the snapshot is stored. +# do not use /tmp for storage, /tmp here is just +# example sakes. +dataDir={path} +# the port at which the clients will connect +clientPort={client_port} +#clientPortAddress=127.0.0.1 +# the maximum number of client connections. +# increase this if you need to handle more clients +#maxClientCnxns=60 +# +# Be sure to read the maintenance section of the +# administrator guide before turning on autopurge. +# +# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance +# +# The number of snapshots to retain in dataDir +#autopurge.snapRetainCount=3 +# Purge task interval in hours +# Set to "0" to disable auto purge feature +#autopurge.purgeInterval=1 +# admin server +admin.serverPort={admin_port} +admin.enableServer=false +# Allow reconfig calls to be made to add/remove nodes to the cluster on the fly +reconfigEnabled=true +# Don't require authentication for reconfig +skipACL=yes +""".format_map(config) + zoo_cfg_path = os.path.join(path, "zoo.cfg") + with open(zoo_cfg_path, "w") as fp: + fp.write(zoo_cfg) + env = { + "CLASSPATH": "/usr/share/java/slf4j/slf4j-simple.jar", + "ZOO_LOG_DIR": datadir.join("logs").strpath, + } + java_args = get_java_process_configuration( + java_args=[ + "-cp", ":".join([ + os.path.join(BASEDIR, "libs", "*"), + ]), "org.apache.zookeeper.server.quorum.QuorumPeerMain", zoo_cfg_path + ] + ) + proc = subprocess.Popen(java_args, env=env) + wait_for_port(config["client_port"]) + return config, proc diff --git a/tests/test_master_coordinator.py b/tests/test_master_coordinator.py new file mode 100644 index 000000000..e5c3aeb56 --- /dev/null +++ b/tests/test_master_coordinator.py @@ -0,0 +1,52 @@ +""" +karapace - master coordination test + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import time + +from karapace.config import set_config_defaults +from karapace.master_coordinator import MasterCoordinator + + +class Timeout(Exception): + pass + + +def init_admin(config): + mc = MasterCoordinator(config=config) + mc.start() + return mc + + +def test_master_selection(kafka_server): + config_aa = set_config_defaults({}) + config_aa["advertised_hostname"] = "127.0.0.1" + config_aa["bootstrap_uri"] = "127.0.0.1:{}".format(kafka_server["kafka_port"]) + config_aa["client_id"] = "aa" + config_aa["port"] = 1234 + + mc_aa = init_admin(config_aa) + + config_bb = set_config_defaults({}) + config_bb["advertised_hostname"] = "127.0.0.1" + config_bb["bootstrap_uri"] = "127.0.0.1:{}".format(kafka_server["kafka_port"]) + config_bb["client_id"] = "bb" + config_bb["port"] = 5678 + mc_bb = init_admin(config_bb) + while True: + if not (mc_aa.sc or mc_bb.sc): + time.sleep(1.0) + continue + if not (mc_aa.sc.master or mc_bb.sc.master or mc_aa.sc.master_url or mc_bb.sc.master_url): + time.sleep(1.0) + continue + assert mc_aa.sc.master is True + assert mc_bb.sc.master is False + master_url = "http://{}:{}".format(config_aa["host"], config_aa["port"]) + assert mc_aa.sc.master_url == master_url + assert mc_bb.sc.master_url == master_url + break + mc_aa.close() + mc_bb.close() diff --git a/tests/test_schema.py b/tests/test_schema.py new file mode 100644 index 000000000..7476d6b02 --- /dev/null +++ b/tests/test_schema.py @@ -0,0 +1,489 @@ +""" +karapace - schema tests + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import json as jsonlib +import os + +import pytest + +from karapace.karapace import Karapace +from .utils import Client + +pytest_plugins = "aiohttp.pytest_plugin" +baseurl = "http://localhost:8081" + + +def create_service(datadir, kafka_server): + config_path = os.path.join(datadir, "karapace_config.json") + with open(config_path, "w") as fp: + karapace_config = {"log_level": "INFO", "bootstrap_uri": "127.0.0.1:{}".format(kafka_server["kafka_port"])} + fp.write(jsonlib.dumps(karapace_config)) + kc = Karapace(config_path) + return kc + + +async def enum_schema_compatibility_checks(c, compatibility): + subject = os.urandom(16).hex() + + res = await c.put("config", json={"compatibility": compatibility}) + assert res.status == 200 + schema = { + "type": "record", + "name": "myenumtest", + "fields": [{ + "type": { + "type": "enum", + "name": "enumtest", + "symbols": ["first", "second"], + }, + "name": "faa", + }] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id = res.json()["id"] + schema = { + "type": "record", + "name": "myenumtest", + "fields": [{ + "type": { + "type": "enum", + "name": "enumtest", + "symbols": ["first", "second", "third"], + }, + "name": "faa", + }] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id2 = res.json()["id"] + assert schema_id != schema_id2 + + schema = { + "type": "record", + "name": "myenumtest", + "fields": [{ + "type": { + "type": "enum", + "name": "enumtest", + "symbols": ["second"], + }, + "name": "faa", + }] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id3 = res.json()["id"] + assert schema_id3 != schema_id2 + + res = await c.get("schemas/ids/{}".format(schema_id3)) + assert res.status_code == 200 + res = jsonlib.loads(res.json()["schema"]) + assert res["type"] == "record" + assert res["name"] == "myenumtest" + assert res["fields"][0]["name"] == "faa" + assert res["fields"][0]["type"]["type"] == "enum" + assert res["fields"][0]["type"]["name"] == "enumtest" + assert res["fields"][0]["type"]["symbols"] == ["second"] + + +async def record_nested_schema_compatibility_checks(c): + subject = os.urandom(16).hex() + + res = await c.put("config", json={"compatibility": "BACKWARD"}) + assert res.status == 200 + schema = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "first_name", + "type": "string", + }, + { + "name": "nested_record_name", + "type": { + "name": "first_name_record", + "type": "record", + "fields": [ + { + "name": "first_name", + "type": "string", + }, + ], + } + }, + ] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert "id" in res.json() + + # change string to integer in the nested record, should fail + schema["fields"][1]["type"]["fields"][0]["type"] = "int" + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 409 + + +async def compatibility_endpoint_checks(c): + subject = os.urandom(16).hex() + schema = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "age", + "type": "int", + }, + ] + } + + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + + res = await c.get("schemas/ids/{}".format(res.json()["id"])) + schema_gotten_back = jsonlib.loads(res.json()["schema"]) + assert schema_gotten_back == schema + + # replace int with long + schema["fields"] = [{"type": "long", "name": "age"}] + res = await c.post( + "compatibility/subjects/{}/versions/latest".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert res.json() == {"is_compatible": True} + + schema["fields"] = [{"type": "string", "name": "age"}] + res = await c.post( + "compatibility/subjects/{}/versions/latest".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert res.json() == {"is_compatible": False} + + +async def record_schema_compatibility_checks(c): + subject = os.urandom(16).hex() + + res = await c.put("config", json={"compatibility": "FORWARD"}) + assert res.status == 200 + schema = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "first_name", + "type": "string", + }, + ] + } + + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema)}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id = res.json()["id"] + + schema2 = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "first_name", + "type": "string" + }, + { + "name": "last_name", + "type": "string" + }, + ] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema2)}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id2 = res.json()["id"] + assert schema_id != schema_id2 + + schema3 = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "last_name", + "type": "string" + }, + { + "name": "third_name", + "type": "string", + "default": "foodefaultvalue" + }, + ] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema3)}, + ) + # Fails because field removed + assert res.status == 409 + assert res.json() == {"error_code": 409, "message": "Schema being registered is incompatible with an earlier schema"} + + schema4 = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "first_name", + "type": "string" + }, + { + "name": "last_name", + "type": "string" + }, + { + "name": "third_name", + "type": "string", + "default": "foodefaultvalue" + }, + ] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema4)}, + ) + assert res.status == 200 + + res = await c.put("config", json={"compatibility": "BACKWARD"}) + schema5 = { + "type": "record", + "name": "Objct", + "fields": [ + { + "name": "first_name", + "type": "string" + }, + { + "name": "last_name", + "type": "string" + }, + { + "name": "third_name", + "type": "string", + "default": "foodefaultvalue" + }, + { + "name": "fourth_name", + "type": "string" + }, + ] + } + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema5)}, + ) + assert res.status == 409 + + # Add a default value for the field + schema5["fields"][3] = {"name": "fourth_name", "type": "string", "default": "foof"} + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema5)}, + ) + assert res.status == 200 + assert "id" in res.json() + + # Try to submit schema with a different definition + schema5["fields"][3] = {"name": "fourth_name", "type": "int", "default": 2} + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": jsonlib.dumps(schema5)}, + ) + assert res.status == 409 + + +async def schema_checks(c): + subject = os.urandom(16).hex() + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": '{"type": "string"}'}, + ) + assert res.status == 200 + assert "id" in res.json() + schema_id = res.json()["id"] + + res = await c.get("schemas/ids/{}".format(res.json()["id"])) + assert res.status_code == 200 + assert res.json()["schema"] == '"string"' + + # repost same schema again to see that a new id is not generated but an old one is given back + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": '{"type": "string"}'}, + ) + assert res.status == 200 + assert "id" in res.json() + assert schema_id == res.json()["id"] + + # nonexistent schema id + result = await c.get(os.path.join("schemas/ids/{}".format(123456789))) + assert result.json()["error_code"] == 40403 + + res = await c.post( + "subjects/{}/versions".format(subject), json={"schema": "{\"type\": \"string\", \"foo\": \"string\"}"} + ) + assert res.status_code == 200 + assert "id" in res.json() + assert schema_id != res.json()["id"] + + # Fetch the schema back to see how it was mangled + result = await c.get(os.path.join("schemas/ids/{}".format(res.json()["id"]))) + schema = jsonlib.loads(result.json()["schema"]) + assert schema["type"] == "string" + assert schema["foo"] == "string" + + res = await c.get("subjects") + assert res.status_code == 200 + assert subject in res.json() + + res = await c.get("subjects/{}/versions".format(subject)) + assert res.status_code == 200 + assert res.json() == [1, 2] + + res = await c.get("subjects/{}/versions/1".format(subject)) + assert res.status_code == 200 + assert res.json()["subject"] == subject + + # Find an invalid version 0 + res = await c.get("subjects/{}/versions/0".format(subject)) + assert res.status_code == 422 + assert res.json()["error_code"] == 42202 + assert res.json()["message"] == \ + 'The specified version is not a valid version id. Allowed values are between [1, 2^31-1] and the string "latest"' + + # Find an invalid version (too large) + res = await c.get("subjects/{}/versions/15".format(subject)) + assert res.status_code == 404 + assert res.json()["error_code"] == 40402 + assert res.json()["message"] == "Version not found." + + # Delete an actual version + res = await c.delete("subjects/{}/versions/1".format(subject)) + assert res.status_code == 200 + assert res.json() == 1 + + # Delete a whole subject + res = await c.delete("subjects/{}".format(subject)) + assert res.status_code == 200 + assert res.json() == [2] + + # List all subjects, our subject shouldn't be in the list + res = await c.get("subjects") + assert res.status_code == 200 + assert subject not in res.json() + + +async def config_checks(c): + # Tests /config endpoint + res = await c.put("config", json={"compatibility": "FULL"}) + assert res.status_code == 200 + assert res.json()["compatibility"] == "FULL" + assert res.headers["Content-Type"] == "application/vnd.schemaregistry.v1+json" + + res = await c.get("config") + assert res.status_code == 200 + assert res.json()["compatibilityLevel"] == "FULL" + assert res.headers["Content-Type"] == "application/vnd.schemaregistry.v1+json" + + res = await c.put("config", json={"compatibility": "NONE"}) + assert res.status_code == 200 + assert res.json()["compatibility"] == "NONE" + assert res.headers["Content-Type"] == "application/vnd.schemaregistry.v1+json" + + res = await c.put("config", json={"compatibility": "nonexistentmode"}) + assert res.status_code == 422 + assert res.json()["error_code"] == 42203 + assert res.json()["message"] == "Invalid compatibility level. Valid values are none, backward, forward and full" + assert res.headers["Content-Type"] == "application/vnd.schemaregistry.v1+json" + + # Create a new subject so we can try setting its config + subject = os.urandom(16).hex() + res = await c.post( + "subjects/{}/versions".format(subject), + json={"schema": '{"type": "string"}'}, + ) + assert res.status_code == 200 + assert "id" in res.json() + + res = await c.get("config/{}".format(subject)) + assert res.status_code == 404 + assert res.json()["error_code"] == 40401 + assert res.json()["message"] == "Subject not found." + + res = await c.put("config/{}".format(subject), json={"compatibility": "FULL"}) + assert res.status_code == 200 + assert res.json()["compatibility"] == "FULL" + assert res.headers["Content-Type"] == "application/vnd.schemaregistry.v1+json" + + res = await c.get("config/{}".format(subject)) + assert res.status_code == 200 + assert res.json()["compatibilityLevel"] == "FULL" + + +async def test_local(session_tmpdir, kafka_server, aiohttp_client): + datadir = session_tmpdir() + + kc = create_service(datadir, kafka_server) + client = await aiohttp_client(kc.app) + c = Client(client=client) + + await schema_checks(c) + await compatibility_endpoint_checks(c) + await record_schema_compatibility_checks(c) + await record_nested_schema_compatibility_checks(c) + for compatibility in {"FORWARD", "BACKWARD", "FULL"}: + await enum_schema_compatibility_checks(c, compatibility) + await config_checks(c) + kc.close() + + +async def test_remote(): + server_uri = os.environ.get("SERVER_URI") + if not server_uri: + pytest.skip("SERVER_URI env variable not set") + c = Client(server_uri=os.environ.get("SERVER_URI")) + await schema_checks(c) + await compatibility_endpoint_checks(c) + await record_schema_compatibility_checks(c) + await record_nested_schema_compatibility_checks(c) + for compatibility in {"FORWARD", "BACKWARD", "FULL"}: + await enum_schema_compatibility_checks(c, compatibility) + await config_checks(c) diff --git a/tests/utils.py b/tests/utils.py new file mode 100644 index 000000000..c63f4ffc8 --- /dev/null +++ b/tests/utils.py @@ -0,0 +1,87 @@ +""" +karapace - test utils + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import requests +import os + + +class Result: + def __init__(self, status, json_result, headers=None): + # We create both status and status_code so people can be agnostic on whichever to use + self.status_code = status + self.status = status + self.json_result = json_result + self.headers = headers if headers else {} + + def json(self): + return self.json_result + + +class Client: + def __init__(self, server_uri=None, client=None): + self.server_uri = server_uri + self.session = requests.Session() + self.client = client + + async def get(self, path, headers=None): + if not headers: + headers = {} + if self.client: + async with self.client.get( + path, + headers=headers, + ) as res: + json_result = await res.json() + return Result(res.status, json_result, headers=res.headers) + elif self.server_uri: + res = requests.get(os.path.join(self.server_uri, path)) + return Result(status=res.status_code, json_result=res.json(), headers=res.headers) + + async def delete(self, path, headers=None): + if not headers: + headers = {} + if self.client: + async with self.client.delete( + path, + headers=headers, + ) as res: + json_result = await res.json() + return Result(res.status, json_result, headers=res.headers) + elif self.server_uri: + res = requests.delete(os.path.join(self.server_uri, path)) + return Result(status=res.status_code, json_result=res.json(), headers=res.headers) + + async def post(self, path, json, headers=None): + if not headers: + headers = {"Content-Type": "application/vnd.schemaregistry.v1+json"} + + if self.client: + async with self.client.post( + path, + headers=headers, + json=json, + ) as res: + json_result = await res.json() + return Result(res.status, json_result, headers=res.headers) + elif self.server_uri: + res = self.session.post(os.path.join(self.server_uri, path), headers=headers, json=json) + return Result(status=res.status_code, json_result=res.json(), headers=res.headers) + + async def put(self, path, json, headers=None): + if not headers: + headers = {"Content-Type": "application/vnd.schemaregistry.v1+json"} + + if self.client: + async with self.client.put( + path, + headers=headers, + json=json, + ) as res: + json_result = await res.json() + return Result(res.status, json_result, headers=res.headers) + elif self.server_uri: + res = self.session.put(os.path.join(self.server_uri, path), headers=headers, json=json) + return Result(status=res.status_code, json_result=res.json(), headers=res.headers) diff --git a/version.py b/version.py new file mode 100644 index 000000000..1c0e17cdf --- /dev/null +++ b/version.py @@ -0,0 +1,58 @@ +""" +karapace - version + +Copyright (c) 2019 Aiven Ltd +See LICENSE for details +""" +import imp +import os +import subprocess + + +def save_version(new_ver, old_ver, version_file): + if not new_ver: + return False + version_file = os.path.join(os.path.dirname(__file__), version_file) + if not old_ver or new_ver != old_ver: + with open(version_file, "w") as fp: + fp.write('"""{}"""\n__version__ = "{}"\n'.format(__doc__, new_ver)) + return True + + +def get_project_version(version_file): + version_file = os.path.join(os.path.dirname(os.path.realpath(__file__)), version_file) + try: + module = imp.load_source("verfile", version_file) + file_ver = module.__version__ + except IOError: + file_ver = None + + os.chdir(os.path.dirname(__file__) or ".") + try: + git_out = subprocess.check_output(["git", "describe", "--always"], + stderr=getattr(subprocess, "DEVNULL", None)) + except (OSError, subprocess.CalledProcessError): + pass + else: + git_ver = git_out.splitlines()[0].strip().decode("utf-8") + if "." not in git_ver: + git_ver = "0.0.1-0-unknown-{}".format(git_ver) + if save_version(git_ver, file_ver, version_file): + return git_ver + + makefile = os.path.join(os.path.dirname(__file__), "Makefile") + if os.path.exists(makefile): + with open(makefile, "r") as fp: + lines = fp.readlines() + short_ver = [line.split("=", 1)[1].strip() for line in lines if line.startswith("short_ver")][0] + if save_version(short_ver, file_ver, version_file): + return short_ver + + if not file_ver: + raise Exception("version not available from git or from file {!r}".format(version_file)) + + return file_ver + +if __name__ == "__main__": + import sys + get_project_version(sys.argv[1])