commit e19eab418abfe3ab8ebb9c517c9021823af06ef4 Author: Lance Edgar Date: Thu Dec 5 07:57:51 2024 -0600 feat: initial release just the basics in place for an ad-hoc CSV -> Wutta import. framework API only at this point, no CLI yet diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..2aef550 --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +*~ +*.pyc +.coverage +docs/_build/ diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 0000000..ad701e5 --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,12 @@ + +# Changelog +All notable changes to WuttaSync will be documented in this file. + +The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) +and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html). + +## v0.1.0 (??) + +### Feat + +- initial release diff --git a/COPYING.txt b/COPYING.txt new file mode 100644 index 0000000..94a9ed0 --- /dev/null +++ b/COPYING.txt @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b4ff38 --- /dev/null +++ b/README.md @@ -0,0 +1,6 @@ + +# WuttaSync + +Wutta framework for data import/export and real-time sync + +See docs at https://rattailproject.org/docs/wuttasync/ diff --git a/docs/Makefile b/docs/Makefile new file mode 100644 index 0000000..d4bb2cb --- /dev/null +++ b/docs/Makefile @@ -0,0 +1,20 @@ +# Minimal makefile for Sphinx documentation +# + +# You can set these variables from the command line, and also +# from the environment for the first two. +SPHINXOPTS ?= +SPHINXBUILD ?= sphinx-build +SOURCEDIR = . +BUILDDIR = _build + +# Put it first so that "make" without argument is like "make help". +help: + @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) + +.PHONY: help Makefile + +# Catch-all target: route all unknown targets to Sphinx using the new +# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). +%: Makefile + @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) diff --git a/docs/api/wuttasync.importing.base.rst b/docs/api/wuttasync.importing.base.rst new file mode 100644 index 0000000..9967f3c --- /dev/null +++ b/docs/api/wuttasync.importing.base.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing.base`` +============================ + +.. automodule:: wuttasync.importing.base + :members: diff --git a/docs/api/wuttasync.importing.csv.rst b/docs/api/wuttasync.importing.csv.rst new file mode 100644 index 0000000..d4656e1 --- /dev/null +++ b/docs/api/wuttasync.importing.csv.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing.csv`` +=========================== + +.. automodule:: wuttasync.importing.csv + :members: diff --git a/docs/api/wuttasync.importing.handlers.rst b/docs/api/wuttasync.importing.handlers.rst new file mode 100644 index 0000000..74a756b --- /dev/null +++ b/docs/api/wuttasync.importing.handlers.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing.handlers`` +================================ + +.. automodule:: wuttasync.importing.handlers + :members: diff --git a/docs/api/wuttasync.importing.model.rst b/docs/api/wuttasync.importing.model.rst new file mode 100644 index 0000000..cad8cad --- /dev/null +++ b/docs/api/wuttasync.importing.model.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing.model`` +============================= + +.. automodule:: wuttasync.importing.model + :members: diff --git a/docs/api/wuttasync.importing.rst b/docs/api/wuttasync.importing.rst new file mode 100644 index 0000000..5699b5c --- /dev/null +++ b/docs/api/wuttasync.importing.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing`` +======================= + +.. automodule:: wuttasync.importing + :members: diff --git a/docs/api/wuttasync.importing.wutta.rst b/docs/api/wuttasync.importing.wutta.rst new file mode 100644 index 0000000..6d3265d --- /dev/null +++ b/docs/api/wuttasync.importing.wutta.rst @@ -0,0 +1,6 @@ + +``wuttasync.importing.wutta`` +============================= + +.. automodule:: wuttasync.importing.wutta + :members: diff --git a/docs/api/wuttasync.rst b/docs/api/wuttasync.rst new file mode 100644 index 0000000..7b21a2d --- /dev/null +++ b/docs/api/wuttasync.rst @@ -0,0 +1,6 @@ + +``wuttasync`` +============= + +.. automodule:: wuttasync + :members: diff --git a/docs/api/wuttasync.util.rst b/docs/api/wuttasync.util.rst new file mode 100644 index 0000000..c15cd92 --- /dev/null +++ b/docs/api/wuttasync.util.rst @@ -0,0 +1,6 @@ + +``wuttasync.util`` +================== + +.. automodule:: wuttasync.util + :members: diff --git a/docs/conf.py b/docs/conf.py new file mode 100644 index 0000000..c5d923c --- /dev/null +++ b/docs/conf.py @@ -0,0 +1,40 @@ +# Configuration file for the Sphinx documentation builder. +# +# For the full list of built-in configuration values, see the documentation: +# https://www.sphinx-doc.org/en/master/usage/configuration.html + +# -- Project information ----------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information + +from importlib.metadata import version as get_version + +project = 'WuttaSync' +copyright = '2024, Lance Edgar' +author = 'Lance Edgar' +release = get_version('WuttaSync') + +# -- General configuration --------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration + +extensions = [ + 'sphinx.ext.autodoc', + 'sphinx.ext.intersphinx', + 'sphinx.ext.viewcode', + 'sphinx.ext.todo', + 'enum_tools.autoenum', +] + +templates_path = ['_templates'] +exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] + +intersphinx_mapping = { + 'python': ('https://docs.python.org/3/', None), + 'wuttjamaican': ('https://rattailproject.org/docs/wuttjamaican/', None), +} + + +# -- Options for HTML output ------------------------------------------------- +# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output + +html_theme = 'furo' +html_static_path = ['_static'] diff --git a/docs/index.rst b/docs/index.rst new file mode 100644 index 0000000..ac6be84 --- /dev/null +++ b/docs/index.rst @@ -0,0 +1,29 @@ + +WuttaSync +========= + +This package adds data import/export and real-time sync utilities for +the `Wutta Framework `_. + +While it of course supports import/export to/from the Wutta :term:`app +database`, it may be used for any "source → target" data flow. + + +.. toctree:: + :maxdepth: 2 + :caption: Documentation + + narr/install + +.. toctree:: + :maxdepth: 1 + :caption: API + + api/wuttasync + api/wuttasync.importing + api/wuttasync.importing.base + api/wuttasync.importing.csv + api/wuttasync.importing.handlers + api/wuttasync.importing.model + api/wuttasync.importing.wutta + api/wuttasync.util diff --git a/docs/make.bat b/docs/make.bat new file mode 100644 index 0000000..32bb245 --- /dev/null +++ b/docs/make.bat @@ -0,0 +1,35 @@ +@ECHO OFF + +pushd %~dp0 + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set SOURCEDIR=. +set BUILDDIR=_build + +%SPHINXBUILD% >NUL 2>NUL +if errorlevel 9009 ( + echo. + echo.The 'sphinx-build' command was not found. Make sure you have Sphinx + echo.installed, then set the SPHINXBUILD environment variable to point + echo.to the full path of the 'sphinx-build' executable. Alternatively you + echo.may add the Sphinx directory to PATH. + echo. + echo.If you don't have Sphinx installed, grab it from + echo.https://www.sphinx-doc.org/ + exit /b 1 +) + +if "%1" == "" goto help + +%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% +goto end + +:help +%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% + +:end +popd diff --git a/docs/narr/install.rst b/docs/narr/install.rst new file mode 100644 index 0000000..4842e2d --- /dev/null +++ b/docs/narr/install.rst @@ -0,0 +1,12 @@ + +Installation +============ + +This assumes you already have a :doc:`WuttJamaican app+database +` setup and working. + +Install the WuttaSync package to your virtual environment: + +.. code-block:: sh + + pip install WuttaSync diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..5f83a0c --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,57 @@ + +[build-system] +requires = ["hatchling"] +build-backend = "hatchling.build" + + +[project] +name = "WuttaSync" +version = "0.1.1" +description = "Wutta framework for data import/export and real-time sync" +readme = "README.md" +authors = [{name = "Lance Edgar", email = "lance@wuttaproject.org"}] +license = {text = "GNU GPL v3+"} +classifiers = [ + "Development Status :: 3 - Alpha", + "Intended Audience :: Developers", + "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)", + "Natural Language :: English", + "Operating System :: OS Independent", + "Programming Language :: Python", + "Programming Language :: Python :: 3", + "Programming Language :: Python :: 3.8", + "Programming Language :: Python :: 3.9", + "Programming Language :: Python :: 3.10", + "Programming Language :: Python :: 3.11", +] +requires-python = ">= 3.8" +dependencies = [ + "SQLAlchemy-Utils", + "WuttJamaican[db]", +] + + +[project.optional-dependencies] +docs = ["Sphinx", "enum-tools[sphinx]", "furo"] +tests = ["pytest-cov", "tox"] + + +[project.urls] +Homepage = "https://wuttaproject.org/" +Repository = "https://forgejo.wuttaproject.org/wutta/wuttasync" +Issues = "https://forgejo.wuttaproject.org/wutta/wuttasync/issues" +Changelog = "https://forgejo.wuttaproject.org/wutta/wuttasync/src/branch/master/CHANGELOG.md" + + +[tool.commitizen] +version_provider = "pep621" +tag_format = "v$version" +update_changelog_on_bump = true + +[tool.hatch.build.targets.sdist] +exclude = [ + "htmlcov/", +] + +[tool.hatch.build.targets.wheel] +packages = ["src/wuttasync"] diff --git a/src/wuttasync/__init__.py b/src/wuttasync/__init__.py new file mode 100644 index 0000000..69a8e83 --- /dev/null +++ b/src/wuttasync/__init__.py @@ -0,0 +1,27 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +WuttaSync -- package root +""" + +from ._version import __version__ diff --git a/src/wuttasync/_version.py b/src/wuttasync/_version.py new file mode 100644 index 0000000..6432bbf --- /dev/null +++ b/src/wuttasync/_version.py @@ -0,0 +1,6 @@ +# -*- coding: utf-8; -*- + +from importlib.metadata import version + + +__version__ = version('WuttaSync') diff --git a/src/wuttasync/importing/__init__.py b/src/wuttasync/importing/__init__.py new file mode 100644 index 0000000..615b2d3 --- /dev/null +++ b/src/wuttasync/importing/__init__.py @@ -0,0 +1,28 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Data Import / Export Framework +""" + +from .handlers import Orientation, ImportHandler, FromFileHandler, ToSqlalchemyHandler +from .base import Importer, FromFile, ToSqlalchemy diff --git a/src/wuttasync/importing/base.py b/src/wuttasync/importing/base.py new file mode 100644 index 0000000..0c83d70 --- /dev/null +++ b/src/wuttasync/importing/base.py @@ -0,0 +1,998 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Data Importer base class +""" + +import os +import logging + +from sqlalchemy import orm +from sqlalchemy_utils.functions import get_primary_keys, get_columns + +from wuttasync.util import data_diffs + + +log = logging.getLogger(__name__) + + +class Importer: + """ + Base class for all data importers / exporters. + + So as with :class:`~wuttasync.importing.handlers.ImportHandler`, + despite the name ``Importer`` this class can be used for export as + well. Occasionally it's helpful to know "which mode" is in + effect, mostly for display to the user. See also + :attr:`orientation` and :attr:`actioning`. + + The role of the "importer/exporter" (instance of this class) is to + process the import/export of data for **one "model"** - which + generally speaking, means one table. Whereas the "import/export + handler" (:class:`~wuttasync.importing.handlers.ImportHandler` + instance) orchestrates the overall DB connections, transactions + and invokes the importer(s)/exporter(s). So multiple + importers/exporters may run in the context of a single handler + job. + + .. attribute:: handler + + Reference to the parent + :class:`~wuttasync.importing.handlers.ImportHandler` instance. + + .. attribute:: model_class + + Reference to the :term:`data model` class representing the + target side, if applicable. + + This normally would be a SQLAlchemy mapped class, e.g. + :class:`~wuttjamaican:wuttjamaican.db.model.base.Person` for + importing to the Wutta People table. + + It is primarily (only?) used when the target side of the + import/export uses SQLAlchemy ORM. + """ + + allow_create = True + """ + Flag indicating whether this importer/exporter should *ever* allow + records to be created on the target side. + + This flag is typically defined in code for each handler. + + See also :attr:`create`. + """ + + allow_update = True + """ + Flag indicating whether this importer/exporter should *ever* allow + records to be updated on the target side. + + This flag is typically defined in code for each handler. + + See also :attr:`update`. + """ + + allow_delete = True + """ + Flag indicating whether this importer/exporter should *ever* allow + records to be deleted on the target side. + + This flag is typically defined in code for each handler. + + See also :attr:`delete`. + """ + + create = None + """ + Flag indicating the current import/export job should create + records on the target side, when applicable. + + This flag is typically set by the caller, e.g. via command line + args. + + See also :attr:`allow_create`. + """ + + update = None + """ + Flag indicating the current import/export job should update + records on the target side, when applicable. + + This flag is typically set by the caller, e.g. via command line + args. + + See also :attr:`allow_update`. + """ + + delete = None + """ + Flag indicating the current import/export job should delete + records on the target side, when applicable. + + This flag is typically set by the caller, e.g. via command line + args. + + See also :attr:`allow_delete`. + """ + + caches_target = False + """ + Flag indicating the importer/exporter should pre-fetch the + existing target data. This is usually what we want, so both + source and target data sets are held in memory and lookups may be + done between them without additional fetching. + + When this flag is false, the importer/exporter must query the + target for every record it gets from the source data, when looking + for a match. + """ + + cached_target = False + """ + This is ``None`` unless :attr:`caches_target` is true, in which + case it may (at times) hold the result from + :meth:`get_target_cache()`. + """ + + def __init__(self, config, **kwargs): + self.config = config + self.app = self.config.get_app() + + self.create = kwargs.pop('create', + kwargs.pop('allow_create', self.allow_create)) + self.update = kwargs.pop('update', + kwargs.pop('allow_update', self.allow_update)) + self.delete = kwargs.pop('delete', + kwargs.pop('allow_delete', self.allow_delete)) + + self.__dict__.update(kwargs) + + self.simple_fields = self.get_simple_fields() + self.supported_fields = self.get_supported_fields() + self.fields = self.get_fields() + + @property + def orientation(self): + """ + Convenience property which returns the value of + :attr:`wuttasync.importing.handlers.ImportHandler.orientation` + from the parent import/export handler. + """ + return self.handler.orientation + + @property + def actioning(self): + """ + Convenience property which returns the value of + :attr:`wuttasync.importing.handlers.ImportHandler.actioning` + from the parent import/export handler. + """ + return self.handler.actioning + + @property + def dry_run(self): + """ + Convenience property which returns the value of + :attr:`wuttasync.importing.handlers.ImportHandler.dry_run` + from the parent import/export handler. + """ + return self.handler.dry_run + + def get_model_title(self): + """ + Returns the display title for the target data model. + """ + if hasattr(self, 'model_title'): + return self.model_title + + # TODO: this will fail if not using a model class, obviously.. + # should raise more helpful error msg? + return self.model_class.__name__ + + def get_simple_fields(self): + """ + This should return a (possibly empty) list of "simple" fields + for the import/export. A "simple" field is one where the + value is a simple scalar, so e.g. can use ``getattr(obj, + field)`` to read and ``setattr(obj, field, value)`` to write. + + See also :meth:`get_supported_fields()` and + :meth:`get_fields()`. + + :returns: Possibly empty list of "simple" field names. + """ + if hasattr(self, 'simple_fields'): + return self.simple_fields + + fields = get_columns(self.model_class) + return list(fields.keys()) + + def get_supported_fields(self): + """ + This should return the full list of fields which are available + for the import/export. + + Note that this field list applies first and foremost to the + target side, i.e. if the target (table etc.) has no "foo" + field defined then it should not be listed here. + + But it also applies to the source side, e.g. if target *does* + define a "foo" field but source does not, then it again should + not be listed here. + + See also :meth:`get_simple_fields()` and :meth:`get_fields()`. + + :returns: List of all "supported" field names. + """ + if hasattr(self, 'supported_fields'): + return self.supported_fields + + return self.get_simple_fields() + + def get_fields(self): + """ + This should return the "effective" list of fields which are to + be used for the import/export. + + All fields in this list should also be found in the output for + :meth:`get_supported_fields()`. + + See also :meth:`get_keys()` and :meth:`get_simple_fields()`. + + :returns: List of "effective" field names. + """ + if hasattr(self, 'fields'): + return self.fields + + return self.get_supported_fields() + + def get_keys(self): + """ + Must return the key field(s) for use with import/export. + + All fields in this list should also be found in the output for + :meth:`get_fields()`. + + :returns: List of "key" field names. + """ + if hasattr(self, 'key'): + keys = self.key + if isinstance(keys, str): + keys = [keys] + return keys + + return list(get_primary_keys(self.model_class)) + + def setup(self): + """ + Perform any setup needed before starting the import/export + job. + + This is called from within :meth:`process_data()`. Default + logic does nothing. + """ + + def teardown(self): + """ + Perform any teardown needed after ending the import/export + job. + + This is called from within :meth:`process_data()`. Default + logic does nothing. + """ + + def process_data(self, source_data=None, progress=None): + """ + Perform the data import/export operations on the target. + + This is the core feature logic and may create, update and/or + delete records on the target side, depending on (subclass) + implementation. It is invoked directly by the parent + :attr:`handler`. + + Note that subclass generally should not override this method, + but instead some of the others. + + :param source_data: Optional sequence of normalized source + data. If not specified, it is obtained from + :meth:`normalize_source_data()`. + + :param progress: Optional progress indicator factory. + + :returns: A 3-tuple of ``(created, updated, deleted)`` as + follows: + + * ``created`` - list of records created on the target + * ``updated`` - list of records updated on the target + * ``deleted`` - list of records deleted on the target + + See also these methods which this one calls: + + * :meth:`setup()` + * :meth:`do_create_update()` + * :meth:`do_delete()` + * :meth:`teardown()` + """ + self.setup() + created = [] + updated = [] + deleted = [] + + # get complete set of normalized source data + if source_data is None: + source_data = self.normalize_source_data(progress=progress) + + # TODO: should exclude duplicate source records + # source_data, unique = self.get_unique_data(source_data) + + # maybe cache existing target data + if self.caches_target: + self.cached_target = self.get_target_cache(source_data, progress=progress) + + # create and/or update target data + if self.create or self.update: + created, updated = self.do_create_update(source_data, progress=progress) + + # delete target data + if self.delete: + deleted = self.do_delete(source_data) + + self.teardown() + return created, updated, deleted + + def do_create_update(self, all_source_data, progress=None): + """ + Import/export the given normalized source data; create and/or + update target records as needed. + + :param all_source_data: Sequence of all normalized source + data, e.g. as obtained from + :meth:`normalize_source_data()`. + + :param progress: Optional progress indicator factory. + + :returns: A 2-tuple of ``(created, updated)`` as follows: + + * ``created`` - list of records created on the target + * ``updated`` - list of records updated on the target + + This loops through all source data records, and for each will + try to find a matching target record. If a match is found it + also checks if any field values differ between them. So, + calls to these methods may also happen from here: + + * :meth:`get_record_key()` + * :meth:`get_target_object()` + * :meth:`create_target_object()` + * :meth:`update_target_object()` + """ + model_title = self.get_model_title() + created = [] + updated = [] + + # cache the set of fields to use for diff checks + fields = set(self.get_fields()) - set(self.get_keys()) + + def create_update(source_data, i): + + # try to fetch target object per source key + key = self.get_record_key(source_data) + target_object = self.get_target_object(key) + if target_object and self.update: + + # target object exists, so compare data + target_data = self.normalize_target_object(target_object) + diffs = self.data_diffs(source_data, target_data, fields=fields) + if diffs: + + # data differs, so update target object + log.debug("fields (%s) differed for target data: %s and source data: %s", + ','.join(diffs), target_data, source_data) + target_object = self.update_target_object(target_object, + source_data, + target_data=target_data) + updated.append((target_object, target_data, source_data)) + + elif not target_object and self.create: + + # target object not yet present, so create it + target_object = self.create_target_object(key, source_data) + if target_object: + log.debug("created new %s %s: %s", model_title, key, target_object) + created.append((target_object, source_data)) + # TODO: update cache if applicable + # if self.caches_target and self.cached_target is not None: + # self.cached_target[key] = { + # 'object': target_object, + # 'data': self.normalize_target_object(target_object), + # } + else: + log.debug("did NOT create new %s for key: %s", model_title, key) + + actioning = self.actioning.capitalize() + target_title = self.handler.get_target_title() + self.app.progress_loop(create_update, all_source_data, progress, + message=f"{actioning} {model_title} data to {target_title}") + + return created, updated + + def do_delete(self, source_data, progress=None): + """ + TODO: not yet implemented + + :returns: List of records deleted on the target. + """ + return [] + + def get_record_key(self, data): + """ + Returns the canonical key value for the given normalized data + record. + + :param data: Normalized data record (dict). + + :returns: A tuple of field values, corresponding to the + import/export key fields. + + Note that this calls :meth:`get_keys()` to determine the + import/export key fields. + + So if an importer has ``key = 'id'`` then :meth:`get_keys()` + would return ``('id',)`` and this method would return just the + ``id`` value e.g. ``(42,)`` for the given data record. + + The return value is always a tuple for consistency and to + allow for composite key fields. + """ + return tuple(data[key] for key in self.get_keys()) + + def data_diffs(self, source_data, target_data, fields=None): + """ + Find all (relevant) fields with differing values between the + two data records, source and target. + + This is a simple wrapper around + :func:`wuttasync.util.data_diffs()` but unless caller + specifies a ``fields`` list, this will use the following by + default: + + It calls :meth:`get_fields()` to get the effective field list, + and from that it *removes* the fields indicated by + :meth:`get_keys()`. + + The thinking here, is that the goal of this function is to + find true diffs, but any "key" fields will already match (or + not) based on the overall processing logic and needn't be + checked further. + """ + + if not fields: + # nb. we do not check for diffs on the key fields, since + # the source/target object matching already handles that + # effectively. also the uuid fields in particular can be + # tricky, if target schema uses UUID proper but source + # data represents them as string etc. + fields = set(self.get_fields()) - set(self.get_keys()) + + return data_diffs(source_data, target_data, fields=fields) + + ############################## + # source methods + ############################## + + def normalize_source_data(self, source_objects=None, progress=None): + """ + This method must return the full list of normalized data + records from the source. + + Default logic here will call :meth:`get_source_objects()` and + then for each object :meth:`normalize_source_object_all()` is + called. + + :param source_objects: Optional sequence of raw objects from + the data source. If not specified, it is obtained from + :meth:`get_source_objects()`. + + :param progress: Optional progress indicator factory. + + :returns: List of normalized source data records. + """ + if source_objects is None: + source_objects = self.get_source_objects() + normalized = [] + + def normalize(obj, i): + data = self.normalize_source_object_all(obj) + if data: + normalized.extend(data) + + model_title = self.get_model_title() + source_title = self.handler.get_source_title() + self.app.progress_loop(normalize, source_objects, progress, + message=f"Reading {model_title} data from {source_title}") + return normalized + + def get_source_objects(self): + """ + This method (if applicable) should return a sequence of "raw" + data objects (i.e. non-normalized records) from the source. + + This method is typically called from + :meth:`normalize_source_data()` which then also handles the + normalization. + """ + return [] + + def normalize_source_object_all(self, obj): + """ + This method should "iterate" over the given object and return + a list of corresponding normalized data records. + + In most cases, the object is "singular" and it doesn't really + make sense to return more than one data record for it. But + this method is here for subclass to override in those rare + cases where you *do* need to "expand" the object into multiple + source data records. + + Default logic for this method simply calls + :meth:`normalize_source_object()` for the given object, and + returns a list with just that one record. + + :param obj: Raw object from data source. + + :returns: List of normalized data records corresponding to the + source object. + """ + data = self.normalize_source_object(obj) + if data: + return [data] + + def normalize_source_object(self, obj): + """ + This should return a single "normalized" data record for the + given source object. + + Subclass will usually need to override this, to "convert" + source data into the shared format required for import/export. + The default logic merely returns the object as-is! + + Note that if this method returns ``None`` then the object is + effectively skipped, treated like it does not exist on the + source side. + + :param obj: Raw object from data source. + + :returns: Dict of normalized data fields, or ``None``. + """ + return obj + + ############################## + # target methods + ############################## + + def get_target_cache(self, source_data=None, progress=None): + """ + Fetch all (existing) raw objects and normalized data from the + target side, and return a cache object with all of that. + + This method will call :meth:`get_target_objects()` first, and + pass along the ``source_data`` param if specified. From there + it will call :meth:`normalize_target_object()` and + :meth:`get_record_key()` for each. + + :param source_data: Sequence of normalized source data for the + import/export job, if known. + + :param progress: Optional progress indicator factory. + + :returns: Dict whose keys are record keys (so one entry for + every normalized target record) and the values are a nested + dict with raw object and normalized record. + + A minimal but complete example of what this return value + looks like:: + + { + (1,): { + 'object': , + 'data': {'id': 1, 'description': 'foo'}, + } + (2,): { + 'object': , + 'data': {'id': 2, 'description': 'bar'}, + } + } + """ + objects = self.get_target_objects(source_data=source_data) + cached = {} + + def cache(obj, i): + data = self.normalize_target_object(obj) + if data: + key = self.get_record_key(data) + cached[key] = {'object': obj, 'data': data} + + model_title = self.get_model_title() + target_title = self.handler.get_target_title() + self.app.progress_loop(cache, objects, progress, + message=f"Reading {model_title} data from {target_title}") + return cached + + def get_target_objects(self, source_data=None, progress=None): + """ + Fetch all existing raw objects from the data target. Or at + least, enough of them to satisfy matching on the given source + data (if applicable). + + :param source_data: Sequence of normalized source data for the + import/export job, if known. + + :param progress: Optional progress indicator factory. + + :returns: Corresponding sequence of raw objects from the + target side. + + Note that the source data is provided only for cases where + that might be useful; it often is not. + + But for instance if the source data contains say an ID field + and the min/max values present in the data set are 1 thru 100, + but the target side has millions of records, you might only + fetch ID <= 100 from target side as an optimization. + """ + raise NotImplementedError + + def get_target_object(self, key): + """ + Should return the object from (existing) target data set which + corresponds to the given record key, if found. + + Note that the default logic is able to find/return the object + from :attr:`cached_target` if applicable. But it is not able + to do a one-off lookup e.g. in the target DB. If you need the + latter then you should override this method. + + :returns: Raw target data object, or ``None``. + """ + if self.caches_target and self.cached_target is not None: + cached = self.cached_target.get(key) + return cached['object'] if cached else None + + def normalize_target_object(self, obj): + """ + This should return a "normalized" data record for the given + raw object from the target side. + + Subclass will often need to override this, to "convert" target + object into the shared format required for import/export. The + default logic is only able to handle "simple" fields; + cf. :meth:`get_simple_fields()`. + + It's possible to optimize this somewhat, by checking + :meth:`get_fields()` and then normalization may be skipped for + any fields which aren't "effective" for the current job. + + Note that if this method returns ``None`` then the object is + ignored, treated like it does not exist on the target side. + + :param obj: Raw object from data target. + + :returns: Dict of normalized data fields, or ``None``. + """ + fields = self.get_fields() + fields = [f for f in self.get_simple_fields() + if f in fields] + data = dict([(field, getattr(obj, field)) + for field in fields]) + return data + + ############################## + # CRUD methods + ############################## + + def create_target_object(self, key, source_data): + """ + Create and return a new target object for the given key, fully + populated from the given source data. This may return + ``None`` if no object is created. + + This method will typically call :meth:`make_empty_object()` + and then :meth:`update_target_object()`. + + :returns: New object for the target side, or ``None``. + """ + if source_data.get('__ignoreme__'): + return + + obj = self.make_empty_object(key) + if obj: + return self.update_target_object(obj, source_data) + + def make_empty_object(self, key): + """ + Return a new empty target object for the given key. + + This method is called from :meth:`create_target_object()`. It + should only populate the object's key, and leave the rest of + the fields to :meth:`update_target_object()`. + + Default logic will call :meth:`make_object()` to get the bare + instance, then populate just the fields from + :meth:`get_keys()`. + """ + obj = self.make_object() + for i, k in enumerate(self.get_keys()): + if hasattr(obj, k): + setattr(obj, k, key[i]) + return obj + + def make_object(self): + """ + Make a bare target object instance. + + This method need not populate the object in any way. See also + :meth:`make_empty_object()`. + + Default logic will make a new instance of :attr:`model_class`. + """ + return self.model_class() + + def update_target_object(self, obj, source_data, target_data=None): + """ + Update the target object with the given source data, and + return the updated object. + + This method may be called from :meth:`do_create_update()` for + a normal update, or :meth:`create_target_object()` when + creating a new record. + + It should update the object for any of :meth:`get_fields()` + which appear to differ. However it need not bother for the + :meth:`get_keys()` fields, since those will already be + accurate. + + :param obj: Raw target object. + + :param source_data: Dict of normalized data for source record. + + :param target_data: Dict of normalized data for existing + target record, if a typical update. Will be missing for a + new object. + + :returns: The final updated object. In most/all cases this + will be the same instance as the original ``obj`` provided + by the caller. + """ + keys = self.get_keys() + fields = self.get_fields() + + # we can automatically handle "simple" fields and update + # target object where needed for those + for field in self.get_simple_fields(): + + if field in keys: + # object key(s) should already be populated + continue + + # elif field not in source_data: + # # no source data for field + # continue + + elif field in fields: + + # field is eligible for update generally, so compare + # values between records + if (not target_data + or field not in target_data + or target_data[field] != source_data[field]): + + # data mismatch; update field for target object + setattr(obj, field, source_data[field]) + + return obj + + +class FromFile(Importer): + """ + Base class for importer/exporter using input file as data source. + + Depending on the subclass, it may be able to "guess" (at least + partially) the path to the input file. If not, and/or to avoid + ambiguity, the caller must specify the file path. + + In most cases caller may specify any of these via kwarg to the + class constructor, or e.g. + :meth:`~wuttasync.importing.handlers.ImportHandler.process_data()`: + + * :attr:`input_file_path` + * :attr:`input_file_dir` + * :attr:`input_file_name` + + The subclass itself can also specify via override of these + methods: + + * :meth:`get_input_file_path()` + * :meth:`get_input_file_dir()` + * :meth:`get_input_file_name()` + + And of course subclass must override these too: + + * :meth:`open_input_file()` + * :meth:`close_input_file()` + * (and see also :attr:`input_file`) + + .. attribute:: input_file_path + + Path to the input file. + + .. attribute:: input_file_dir + + Path to folder containing input file(s). + + .. attribute:: input_file_name + + Name of the input file, sans folder path. + + .. attribute:: input_file + + Handle to the open input file, if applicable. May be set by + :meth:`open_input_file()` for later reference within + :meth:`close_input_file()`. + """ + + def setup(self): + """ + Open the input file. See also :meth:`open_input_file()`. + """ + self.open_input_file() + + def teardown(self): + """ + Close the input file. See also :meth:`close_input_file()`. + """ + self.close_input_file() + + def get_input_file_path(self): + """ + This must return the full path to input file. It tries to + guess it based on various attributes, namely: + + * :attr:`input_file_path` + * :attr:`input_file_dir` + * :attr:`input_file_name` + + :returns: Path to input file. + """ + if hasattr(self, 'input_file_path'): + return self.input_file_path + + folder = self.get_input_file_dir() + filename = self.get_input_file_name() + return os.path.join(folder, filename) + + def get_input_file_dir(self): + """ + This must return the folder with input file(s). It tries to + guess it based on various attributes, namely: + + * :attr:`input_file_dir` + + :returns: Path to folder with input file(s). + """ + if hasattr(self, 'input_file_dir'): + return self.input_file_dir + + raise NotImplementedError("can't guess path to input file(s) folder") + + def get_input_file_name(self): + """ + This must return the input filename, sans folder path. It + tries to guess it based on various attributes, namely: + + * :attr:`input_file_name` + + :returns: Input filename, sans folder path. + """ + if hasattr(self, 'input_file_name'): + return self.input_file_name + + raise NotImplementedError("can't guess input filename") + + def open_input_file(self): + """ + Open the input file for reading source data. + + Subclass must override to specify how this happens; default + logic is not implemented. Remember to set :attr:`input_file` + if applicable for reference when closing. + + See also :attr:`get_input_file_path()` and + :meth:`close_input_file()`. + """ + raise NotImplementedError + + def close_input_file(self): + """ + Close the input file for source data. + + Subclass must override to specify how this happens; default + logic blindly calls the ``close()`` method on whatever + :attr:`input_file` happens to point to. + + See also :attr:`open_input_file()`. + """ + self.input_file.close() + + +class ToSqlalchemy(Importer): + """ + Base class for importer/exporter which uses SQLAlchemy ORM on the + target side. + """ + + caches_target = True + "" # nb. suppress sphinx docs + + def get_target_object(self, key): + """ + Tries to fetch the object from target DB using ORM query. + """ + # first the default logic in case target object is cached + obj = super().get_target_object(key) + if obj: + return obj + + # okay now we must fetch via query + query = self.target_session.query(self.model_class) + for i, k in enumerate(self.get_keys()): + query = query.filter(getattr(self.model_class, k) == key[i]) + try: + return query.one() + except orm.exc.NoResultFound: + pass + + def create_target_object(self, key, source_data): + """ """ + with self.target_session.no_autoflush: + obj = super().create_target_object(key, source_data) + if obj: + # nb. add new object to target db session + self.target_session.add(obj) + return obj + + def get_target_objects(self, source_data=None, progress=None): + """ + Fetches target objects via the ORM query from + :meth:`get_target_query()`. + """ + query = self.get_target_query(source_data=source_data) + return query.all() + + def get_target_query(self, source_data=None): + """ + Returns an ORM query suitable to fetch existing objects from + the target side. This is called from + :meth:`get_target_objects()`. + """ + return self.target_session.query(self.model_class) diff --git a/src/wuttasync/importing/csv.py b/src/wuttasync/importing/csv.py new file mode 100644 index 0000000..7bbc727 --- /dev/null +++ b/src/wuttasync/importing/csv.py @@ -0,0 +1,206 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Importing from CSV +""" + +import csv +from collections import OrderedDict + +from sqlalchemy_utils.functions import get_primary_keys + +from wuttjamaican.db.util import make_topo_sortkey + +from .base import FromFile +from .handlers import FromFileHandler +from .wutta import ToWuttaHandler +from .model import ToWutta + + +class FromCsv(FromFile): + """ + Base class for importer/exporter using CSV file as data source. + + Note that this assumes a particular "format" for the CSV files. + If your needs deviate you should override more methods, e.g. + :meth:`open_input_file()`. + + The default logic assumes CSV file is mostly "standard" - e.g. + comma-delimited, UTF-8-encoded etc. But it also assumes the first + line/row in the file contains column headers, and all subsequent + lines are data rows. + + .. attribute:: input_reader + + While the input file is open, this will reference a + :class:`python:csv.DictReader` instance. + """ + + csv_encoding = 'utf_8' + """ + Encoding used by the CSV input file. + + You can specify an override if needed when calling + :meth:`~wuttasync.importing.handlers.ImportHandler.process_data()`. + """ + + def get_input_file_name(self): + """ + By default this returns the importer/exporter model name plus + CSV file extension, e.g. ``Widget.csv`` + + It calls + :meth:`~wuttasync.importing.base.Importer.get_model_title()` + to obtain the model name. + """ + if hasattr(self, 'input_file_name'): + return self.input_file_name + + model_title = self.get_model_title() + return f'{model_title}.csv' + + def open_input_file(self): + """ + Open the input file for reading, using a CSV parser. + + This tracks the file handle via + :attr:`~wuttasync.importing.base.FromFile.input_file` and the + CSV reader via :attr:`input_reader`. + """ + path = self.get_input_file_path() + self.input_file = open(path, 'rt', encoding=self.csv_encoding) + self.input_reader = csv.DictReader(self.input_file) + + def close_input_file(self): + """ """ + self.input_file.close() + del self.input_reader + del self.input_file + + def get_source_objects(self): + """ + This returns a list of data records "as-is" from the CSV + source file (via :attr:`input_reader`). + + Since this uses :class:`python:csv.DictReader` by default, + each record will be a dict with key/value for each column in + the file. + """ + return list(self.input_reader) + + +class FromCsvToSqlalchemyMixin: + """ + Mixin handler class for CSV → SQLAlchemy ORM import/export. + """ + source_key = 'csv' + generic_source_title = "CSV" + + FromImporterBase = FromCsv + """ + This must be set to a valid base class for the CSV source side. + Default is :class:`FromCsv` which should typically be fine; you + can change if needed. + """ + + # nb. subclass must define this + ToImporterBase = None + """ + For a handler to use this mixin, this must be set to a valid base + class for the ORM target side. The :meth:`define_importers()` + logic will use this as base class when dynamically generating new + importer/exporter classes. + """ + + def get_target_model(self): + """ + This should return the :term:`app model` or a similar module + containing data model classes for the target side. + + The target model is used to dynamically generate a set of + importers (e.g. one per table in the target DB) which can use + CSV file as data source. See also :meth:`define_importers()`. + + Subclass must override this if needed; default behavior is not + implemented. + """ + raise NotImplementedError + + def define_importers(self): + """ + This mixin overrides typical (manual) importer definition, and + instead dynamically generates a set of importers, e.g. one per + table in the target DB. + + It does this based on the target model, as returned by + :meth:`get_target_model()`. It calls + :meth:`make_importer_factory()` for each model class found. + """ + importers = {} + model = self.get_target_model() + + # mostly try to make an importer for every data model + for name in dir(model): + cls = getattr(model, name) + if isinstance(cls, type) and issubclass(cls, model.Base) and cls is not model.Base: + importers[name] = self.make_importer_factory(cls, name) + + # sort importers according to schema topography + topo_sortkey = make_topo_sortkey(model) + importers = OrderedDict([ + (name, importers[name]) + for name in sorted(importers, key=topo_sortkey) + ]) + + return importers + + def make_importer_factory(self, cls, name): + """ + Generate and return a new importer/exporter class, targeting + the given data model class. + + :param cls: A data model class. + + :param name: Optional "model name" override for the + importer/exporter. + + :returns: A new class, meant to process import/export + operations which target the given data model. The new + class will inherit from both :attr:`FromImporterBase` and + :attr:`ToImporterBase`. + """ + return type(f'{name}Importer', (FromCsv, self.ToImporterBase), { + 'model_class': cls, + 'key': list(get_primary_keys(cls)), + }) + + +class FromCsvToWutta(FromCsvToSqlalchemyMixin, ToWuttaHandler): + """ + Handler for CSV → Wutta :term:`app database` import. + """ + ToImporterBase = ToWutta + + def get_target_model(self): + """ """ + return self.app.model diff --git a/src/wuttasync/importing/handlers.py b/src/wuttasync/importing/handlers.py new file mode 100644 index 0000000..87e0ac3 --- /dev/null +++ b/src/wuttasync/importing/handlers.py @@ -0,0 +1,560 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Data Import / Export Handlers +""" + +import logging +from collections import OrderedDict +from enum import Enum + +from wuttjamaican.app import GenericHandler + + +log = logging.getLogger(__name__) + + +class Orientation(Enum): + """ + Enum values for :attr:`ImportHandler.orientation`. + """ + IMPORT = 'import' + EXPORT = 'export' + + +class ImportHandler(GenericHandler): + """ + Base class for all import/export handlers. + + Despite the name ``ImportHandler`` this can be used for export as + well. The logic is no different on a technical level and the + "export" concept is mostly only helpful to the user. The latter + is important of course and to help with that we track the + :attr:`orientation` to distinguish. + + The role of the "import/export handler" (instance of this class) + is to orchestrate the overall DB connections, transactions and + then invoke the importer/exporter instance(s) to do the actual + data assessment/transfer. Each of the latter will be an instance + of (a subclass of) :class:`~wuttasync.importing.base.Importer`. + """ + + source_key = None + """ + Key identifier for the data source. + + This should "uniquely" identify the data source, within the + context of the data target. For instance in the case of CSV → + Wutta, ``csv`` is the source key. + + Among other things, this value is used in :meth:`get_key()`. + """ + + target_key = None + """ + Key identifier for the data target. + + This should "uniquely" identify the data target. For instance in + the case of CSV → Wutta, ``wutta`` is the target key. + + Among other things, this value is used in :meth:`get_key()`. + """ + + orientation = Orientation.IMPORT + """ + Orientation for the data flow. Must be a value from + :enum:`Orientation`: + + * ``Orientation.IMPORT`` (aka. ``'import'``) + * ``Orientation.EXPORT`` (aka. ``'export'``) + + Note that the value may be displayed to the user where helpful:: + + print(handler.orientation.value) + + See also :attr:`actioning`. + + It's important to understand the difference between import/export + and source/target; they are independent concepts. Source and + target indicate where data comes from and where it's going, + whereas import vs. export is mostly cosmetic. + + How a given data flow's orientation is determined, is basically up + to the developer. Most of the time it is straightforward, + e.g. CSV → Wutta would be import, and Wutta → CSV would be + export. But confusing edge cases certainly exist, you'll know + them when you see them. In those cases the developer should try + to choose whichever the end user is likely to find less confusing. + """ + + dry_run = False + """ + Flag indicating whether data import/export should truly happen vs. + dry-run only. + + If true, the data transaction will be rolled back at the end; if + false then it will be committed. + + See also :meth:`rollback_transaction()` and + :meth:`commit_transaction()`. + """ + + importers = None + """ + This should be a dict of all importer/exporter classes available + to the handler. Keys are "model names" and each value is an + importer/exporter class. For instance:: + + { + 'Widget': WidgetImporter, + } + + This dict is defined during the handler constructor; see also + :meth:`define_importers()`. + + Note that in practice, this is usually an ``OrderedDict`` so that + the "sorting" of importer/exporters can be curated. + + If you want an importer/exporter instance you should not use this + directly but instead call :meth:`get_importer()`. + """ + + def __init__(self, config, **kwargs): + """ """ + super().__init__(config, **kwargs) + self.importers = self.define_importers() + + def __str__(self): + """ """ + return self.get_title() + + @property + def actioning(self): + """ + Convenience property which effectively returns the + :attr:`orientation` in progressive verb tense - i.e. one of: + + * ``'importing'`` + * ``'exporting'`` + """ + return f'{self.orientation.value}ing' + + @classmethod + def get_key(cls): + """ + Returns the "full key" for the handler. This is a combination + of :attr:`source_key` and :attr:`target_key` and + :attr:`orientation`. + + For instance in the case of CSV → Wutta, the full handler key + is ``to_wutta.from_csv.import``. + + Note that more than one handler may return the same full key + here; but only one will be configured as the "default" handler + for that key. See also :meth:`get_spec()`. + """ + return f'to_{cls.target_key}.from_{cls.source_key}.{cls.orientation.value}' + + @classmethod + def get_spec(cls): + """ + Returns the "class spec" for the handler. This value is the + same as what might be used to configure the default handler + for a given key. + + For instance in the case of CSV → Wutta, the default handler + spec is ``wuttasync.importing.csv:FromCsvToWutta``. + + See also :meth:`get_key()`. + """ + return f'{cls.__module__}:{cls.__name__}' + + def get_title(self): + """ + Returns the full display title for the handler, e.g. ``"CSV → + Wutta"``. + + Note that the :attr:`orientation` is not included in this title. + + It calls :meth:`get_source_title()` and + :meth:`get_target_title()` to construct the full title. + """ + source = self.get_source_title() + target = self.get_target_title() + return f"{source} → {target}" + + def get_source_title(self): + """ + Returns the display title for the data source. + + See also :meth:`get_title()` and :meth:`get_target_title()`. + """ + if hasattr(self, 'source_title'): + return self.source_title + if hasattr(self, 'generic_source_title'): + return self.generic_source_title + return self.source_key + + def get_target_title(self): + """ + Returns the display title for the data target. + + See also :meth:`get_title()` and :meth:`get_source_title()`. + """ + if hasattr(self, 'target_title'): + return self.target_title + if hasattr(self, 'generic_target_title'): + return self.generic_target_title + return self.target_key + + def process_data(self, *keys, **kwargs): + """ + Run import/export operations for the specified models. + + :param \*keys: One or more importer/exporter (model) keys, as + defined by the handler. + + Each key specified must be present in :attr:`importers` and + thus will correspond to an importer/exporter class. + + A transaction is begun on the source and/or target side as + needed, then for each model key requested, the corresponding + importer/exporter is created and invoked. And finally the + transaction is committed (assuming normal operation). + + See also these methods which may be called from this one: + + * :meth:`consume_kwargs()` + * :meth:`begin_transaction()` + * :meth:`get_importer()` + * :meth:`~wuttasync.importing.base.Importer.process_data()` (on the importer/exporter) + * :meth:`rollback_transaction()` + * :meth:`commit_transaction()` + """ + kwargs = self.consume_kwargs(kwargs) + self.begin_transaction() + + success = False + try: + + # loop thru specified importer keys + for key in keys: + + # invoke importer + importer = self.get_importer(key, **kwargs) + created, updated, deleted = importer.process_data() + + # log what happened + msg = "%s: added %d; updated %d; deleted %d %s records" + if self.dry_run: + msg += " (dry run)" + log.info(msg, self.get_title(), len(created), len(updated), len(deleted), key) + + except: + # TODO: what should happen here? + raise + + else: + success = True + + finally: + if not success: + log.warning("something failed, so transaction was rolled back") + self.rollback_transaction() + elif self.dry_run: + log.info("dry run, so transaction was rolled back") + self.rollback_transaction() + else: + log.info("transaction was committed") + self.commit_transaction() + + def consume_kwargs(self, kwargs): + """ + This method is called by :meth:`process_data()`. + + Its purpose is to give handlers a hook by which they can + update internal handler state from the given kwargs, prior to + running the import/export task(s). + + Any kwargs which pertain only to the handler, should be + removed before they are returned. But any kwargs which (also) + may pertain to the importer/exporter instance, should *not* be + removed, so they are passed along via :meth:`get_importer()`. + + :param kwargs: Dict of kwargs, "pre-consumption." This is the + same kwargs dict originally received by + :meth:`process_data()`. + + :returns: Dict of kwargs, "post-consumption." + """ + if 'dry_run' in kwargs: + self.dry_run = kwargs['dry_run'] + + return kwargs + + def begin_transaction(self): + """ + Begin an import/export transaction, on source and/or target + side as needed. + + This is normally called from :meth:`process_data()`. + + Default logic will call both: + + * :meth:`begin_source_transaction()` + * :meth:`begin_target_transaction()` + """ + self.begin_source_transaction() + self.begin_target_transaction() + + def begin_source_transaction(self): + """ + Begin a transaction on the source side, if applicable. + + This is normally called from :meth:`begin_transaction()`. + """ + + def begin_target_transaction(self): + """ + Begin a transaction on the target side, if applicable. + + This is normally called from :meth:`begin_transaction()`. + """ + + def commit_transaction(self): + """ + Commit the current import/export transaction, on source and/or + target side as needed. + + This is normally called from :meth:`process_data()`. + + Default logic will call both: + + * :meth:`commit_target_transaction()` + * :meth:`commit_source_transaction()` + + .. note:: + + By default the target transaction is committed first; this + is to avoid edge case errors when the source connection + times out. In such cases we want to properly cleanup the + target and then if an error happens when trying to cleanup + the source, it is less disruptive. + """ + # nb. it can sometimes be important to commit the target + # transaction first. in particular when the import takes a + # long time, it may be that no activity occurs on the source + # DB session after the initial data read. then at the end + # committing the source transaction may trigger a connection + # timeout error, which then prevents target transaction from + # committing. so now we just commit target first instead. + # TODO: maybe sequence should be configurable? + self.commit_target_transaction() + self.commit_source_transaction() + + def commit_source_transaction(self): + """ + Commit the transaction on the source side, if applicable. + + This is normally called from :meth:`commit_transaction()`. + """ + + def commit_target_transaction(self): + """ + Commit the transaction on the target side, if applicable. + + This is normally called from :meth:`commit_transaction()`. + """ + + def rollback_transaction(self): + """ + Rollback the current import/export transaction, on source + and/or target side as needed. + + This is normally called from :meth:`process_data()`. It is + "always" called when :attr:`dry_run` is true, but also may be + called if errors are encountered. + + Default logic will call both: + + * :meth:`rollback_target_transaction()` + * :meth:`rollback_source_transaction()` + + .. note:: + + By default the target transaction is rolled back first; + this is to avoid edge case errors when the source + connection times out. In such cases we want to properly + cleanup the target and then if an error happens when trying + to cleanup the source, it is less disruptive. + """ + # nb. it can sometimes be important to rollback the target + # transaction first. in particular when the import takes a + # long time, it may be that no activity occurs on the source + # DB session after the initial data read. then at the end + # rolling back the source transaction may trigger a connection + # timeout error, which then prevents target transaction from + # being rolled back. so now we always rollback target first. + # TODO: maybe sequence should be configurable? + self.rollback_target_transaction() + self.rollback_source_transaction() + + def rollback_source_transaction(self): + """ + Rollback the transaction on the source side, if applicable. + + This is normally called from :meth:`rollback_transaction()`. + """ + + def rollback_target_transaction(self): + """ + Rollback the transaction on the target side, if applicable. + + This is normally called from :meth:`rollback_transaction()`. + """ + + def define_importers(self): + """ + This method must "define" all importer/exporter classes + available to the handler. It is called from the constructor. + + This should return a dict keyed by "model name" and each value + is an importer/exporter class. The end result is then + assigned as :attr:`importers` (in the constoructor). + + For instance:: + + return { + 'Widget': WidgetImporter, + } + + Note that the model name will be displayed in various places + and the caller may invoke a specific importer/exporter by this + name etc. See also :meth:`get_importer()`. + """ + return OrderedDict() + + def get_importer(self, key, **kwargs): + """ + Returns an importer/exporter instance corresponding to the + given key. + + The key will be the "model name" mapped to a particular + importer/exporter class and thus must be present in + :attr:`importers`. + + This method is called from :meth:`process_data()` but may also + be used by ad-hoc callers elsewhere. + + It will call :meth:`get_importer_kwargs()` and then construct + the importer/exporter instance using those kwargs. + + :param key: Model key for desired importer/exporter. + + :returns: Instance of (subclass of) + :class:`~wuttasync.importing.base.Importer`. + """ + if key not in self.importers: + orientation = self.orientation.value + raise KeyError(f"unknown {orientation} key: {key}") + + kwargs = self.get_importer_kwargs(key, **kwargs) + kwargs['handler'] = self + factory = self.importers[key] + return factory(self.config, **kwargs) + + def get_importer_kwargs(self, key, **kwargs): + """ + Returns a dict of kwargs to be used when construcing an + importer/exporter with the given key. This is normally called + from :meth:`get_importer()`. + + :param key: Model key for the desired importer/exporter, + e.g. ``'Widget'`` + + :param \**kwargs: Any kwargs we have so collected far. + + :returns: Final kwargs dict for new importer/exporter. + """ + return kwargs + + +class FromFileHandler(ImportHandler): + """ + Handler for import/export which uses an input file as data source. + """ + + +class ToSqlalchemyHandler(ImportHandler): + """ + Handler for import/export which targets a SQLAlchemy ORM (DB). + """ + + target_session = None + """ + Reference to the SQLAlchemy :term:`db session` for the target side. + + This may often be a session for the :term:`app database` (i.e. for + importing to Wutta DB) but it could also be any other. + + This will be ``None`` unless an import/export transaction is + underway. See also :meth:`begin_target_transaction()`. + """ + + def begin_target_transaction(self): + """ + Establish a new :term:`db session` via + :meth:`make_target_session()` and assign the result to + :attr:`target_session`. + """ + self.target_session = self.make_target_session() + + def rollback_target_transaction(self): + """ + Rollback the :attr:`target_session`. + """ + self.target_session.rollback() + self.target_session.close() + self.target_session = None + + def commit_target_transaction(self): + """ + Commit the :attr:`target_session`. + """ + self.target_session.commit() + self.target_session.close() + self.target_session = None + + def make_target_session(self): + """ + Make and return a new :term:`db session` for the import/export. + + Subclass must override this; default logic is not implemented. + """ + raise NotImplementedError + + def get_importer_kwargs(self, key, **kwargs): + """ """ + kwargs = super().get_importer_kwargs(key, **kwargs) + kwargs.setdefault('target_session', self.target_session) + return kwargs diff --git a/src/wuttasync/importing/model.py b/src/wuttasync/importing/model.py new file mode 100644 index 0000000..7a7c554 --- /dev/null +++ b/src/wuttasync/importing/model.py @@ -0,0 +1,34 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Data import/export to Wutta +""" + +from .base import ToSqlalchemy + + +class ToWutta(ToSqlalchemy): + """ + Base class for data importer/exporter which targets the Wutta ORM + (:term:`app database`). + """ diff --git a/src/wuttasync/importing/wutta.py b/src/wuttasync/importing/wutta.py new file mode 100644 index 0000000..be5786c --- /dev/null +++ b/src/wuttasync/importing/wutta.py @@ -0,0 +1,57 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Wutta ⇄ Wutta import/export +""" + +from .handlers import ToSqlalchemyHandler + + +class ToWuttaHandler(ToSqlalchemyHandler): + """ + Handler for import/export which targets Wutta ORM (:term:`app + database`). + """ + + target_key = 'wutta' + "" # nb. suppress docs + + def get_target_title(self): + """ """ + # nb. we override parent to use app title as default + if hasattr(self, 'target_title'): + return self.target_title + if hasattr(self, 'generic_target_title'): + return self.generic_target_title + return self.app.get_title() + + def make_target_session(self): + """ + Call + :meth:`~wuttjamaican:wuttjamaican.app.AppHandler.make_session()` + and return the result. + + :returns: :class:`~wuttjamaican:wuttjamaican.db.sess.Session` + instance. + """ + return self.app.make_session() diff --git a/src/wuttasync/util.py b/src/wuttasync/util.py new file mode 100644 index 0000000..9f9eccb --- /dev/null +++ b/src/wuttasync/util.py @@ -0,0 +1,60 @@ +# -*- coding: utf-8; -*- +################################################################################ +# +# WuttaSync -- Wutta framework for data import/export and real-time sync +# Copyright © 2024 Lance Edgar +# +# This file is part of Wutta Framework. +# +# Wutta Framework is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation, either version 3 of the License, or (at your option) any +# later version. +# +# Wutta Framework is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# Wutta Framework. If not, see . +# +################################################################################ +""" +Data Utilities +""" + + +def data_diffs(source_data, target_data, fields=None): + """ + Find all (relevant) fields with differing values between the two + data records, source and target. + + :param source_data: Dict of normalized record from source data. + + :param target_data: Dict of normalized record from target data. + + :param fields: Optional list of fields to check. If not + specified, all fields present in ``target_data`` will be + checked. + + :returns: Possibly empty list of field names which were found to + differ between source and target record. + """ + if fields is None: + fields = list(target_data) + + diffs = [] + for field in fields: + + if field not in target_data: + raise KeyError(f"field '{field}' is missing from target_data") + if field not in source_data: + raise KeyError(f"field '{field}' is missing from source_data") + + target_value = target_data[field] + source_value = source_data[field] + if target_value != source_value: + diffs.append(field) + + return diffs diff --git a/tasks.py b/tasks.py new file mode 100644 index 0000000..78a4ece --- /dev/null +++ b/tasks.py @@ -0,0 +1,24 @@ +# -*- coding: utf-8; -*- +""" +Tasks for WuttaSync +""" + +import os +import shutil + +from invoke import task + + +@task +def release(c, skip_tests=False): + """ + Release a new version of WuttaSync + """ + if not skip_tests: + c.run('pytest') + + if os.path.exists('dist'): + shutil.rmtree('dist') + + c.run('python -m build --sdist') + c.run('twine upload dist/*') diff --git a/tests/__init__.py b/tests/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/tests/importing/__init__.py b/tests/importing/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/tests/importing/test_base.py b/tests/importing/test_base.py new file mode 100644 index 0000000..abe121b --- /dev/null +++ b/tests/importing/test_base.py @@ -0,0 +1,437 @@ +#-*- coding: utf-8; -*- + +from unittest.mock import patch + +from wuttjamaican.testing import DataTestCase + +from wuttasync.importing import base as mod, ImportHandler, Orientation + + +class TestImporter(DataTestCase): + + def setUp(self): + self.setup_db() + self.handler = ImportHandler(self.config) + + def make_importer(self, **kwargs): + kwargs.setdefault('handler', self.handler) + return mod.Importer(self.config, **kwargs) + + def test_constructor(self): + model = self.app.model + + # basic importer + imp = self.make_importer(model_class=model.Setting) + + # fields + self.assertEqual(imp.supported_fields, ['name', 'value']) + self.assertEqual(imp.simple_fields, ['name', 'value']) + self.assertEqual(imp.fields, ['name', 'value']) + + # orientation etc. + self.assertEqual(imp.orientation, Orientation.IMPORT) + self.assertEqual(imp.actioning, 'importing') + self.assertTrue(imp.create) + self.assertTrue(imp.update) + self.assertTrue(imp.delete) + self.assertFalse(imp.dry_run) + + def test_get_model_title(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_model_title(), 'Setting') + imp.model_title = "SeTtInG" + self.assertEqual(imp.get_model_title(), 'SeTtInG') + + def test_get_simple_fields(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_simple_fields(), ['name', 'value']) + imp.simple_fields = ['name'] + self.assertEqual(imp.get_simple_fields(), ['name']) + + def test_get_supported_fields(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_supported_fields(), ['name', 'value']) + imp.supported_fields = ['name'] + self.assertEqual(imp.get_supported_fields(), ['name']) + + def test_get_fields(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_fields(), ['name', 'value']) + imp.fields = ['name'] + self.assertEqual(imp.get_fields(), ['name']) + + def test_get_keys(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_keys(), ['name']) + imp.key = 'value' + self.assertEqual(imp.get_keys(), ['value']) + + def test_process_data(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting, caches_target=True) + + # empty data set / just for coverage + with patch.object(imp, 'normalize_source_data') as normalize_source_data: + normalize_source_data.return_value = [] + + with patch.object(imp, 'get_target_cache') as get_target_cache: + get_target_cache.return_value = {} + + result = imp.process_data() + self.assertEqual(result, ([], [], [])) + + def test_do_create_update(self): + model = self.app.model + + # this requires a mock target cache + imp = self.make_importer(model_class=model.Setting, caches_target=True) + setting = model.Setting(name='foo', value='bar') + imp.cached_target = { + ('foo',): { + 'object': setting, + 'data': {'name': 'foo', 'value': 'bar'}, + }, + } + + # will update the one record + result = imp.do_create_update([{'name': 'foo', 'value': 'baz'}]) + self.assertIs(result[1][0][0], setting) + self.assertEqual(result, ([], [(setting, + # nb. target + {'name': 'foo', 'value': 'bar'}, + # nb. source + {'name': 'foo', 'value': 'baz'})])) + self.assertEqual(setting.value, 'baz') + + # will create a new record + result = imp.do_create_update([{'name': 'blah', 'value': 'zay'}]) + self.assertIsNot(result[0][0][0], setting) + setting_new = result[0][0][0] + self.assertEqual(result, ([(setting_new, + # nb. source + {'name': 'blah', 'value': 'zay'})], + [])) + self.assertEqual(setting_new.name, 'blah') + self.assertEqual(setting_new.value, 'zay') + + # but what if new record is *not* created + with patch.object(imp, 'create_target_object', return_value=None): + result = imp.do_create_update([{'name': 'another', 'value': 'one'}]) + self.assertEqual(result, ([], [])) + + # def test_do_delete(self): + # model = self.app.model + # imp = self.make_importer(model_class=model.Setting) + + def test_get_record_key(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + record = {'name': 'foo', 'value': 'bar'} + self.assertEqual(imp.get_record_key(record), ('foo',)) + imp.key = ('name', 'value') + self.assertEqual(imp.get_record_key(record), ('foo', 'bar')) + + def test_data_diffs(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # 2 identical records + rec1 = {'name': 'foo', 'value': 'bar'} + rec2 = {'name': 'foo', 'value': 'bar'} + result = imp.data_diffs(rec1, rec2) + self.assertEqual(result, []) + + # now they're different + rec2['value'] = 'baz' + result = imp.data_diffs(rec1, rec2) + self.assertEqual(result, ['value']) + + def test_normalize_source_data(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # empty source data + data = imp.normalize_source_data() + self.assertEqual(data, []) + + # now with 1 record + setting = model.Setting(name='foo', value='bar') + data = imp.normalize_source_data(source_objects=[setting]) + self.assertEqual(len(data), 1) + # nb. default normalizer returns object as-is + self.assertIs(data[0], setting) + + def test_get_source_objects(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertEqual(imp.get_source_objects(), []) + + def test_normalize_source_object_all(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + setting = model.Setting() + result = imp.normalize_source_object_all(setting) + self.assertEqual(len(result), 1) + self.assertIs(result[0], setting) + + def test_normalize_source_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + setting = model.Setting() + result = imp.normalize_source_object(setting) + self.assertIs(result, setting) + + def test_get_target_cache(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + with patch.object(imp, 'get_target_objects') as get_target_objects: + get_target_objects.return_value = [] + + # empty cache + cache = imp.get_target_cache() + self.assertEqual(cache, {}) + + # cache w/ one record + setting = model.Setting(name='foo', value='bar') + get_target_objects.return_value = [setting] + cache = imp.get_target_cache() + self.assertEqual(len(cache), 1) + self.assertIn(('foo',), cache) + foo = cache[('foo',)] + self.assertEqual(len(foo), 2) + self.assertEqual(set(foo), {'object', 'data'}) + self.assertIs(foo['object'], setting) + self.assertEqual(foo['data'], {'name': 'foo', 'value': 'bar'}) + + def test_get_target_objects(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertRaises(NotImplementedError, imp.get_target_objects) + + def test_get_target_object(self): + model = self.app.model + setting = model.Setting(name='foo', value='bar') + + # nb. must mock up a target cache for this one + imp = self.make_importer(model_class=model.Setting, caches_target=True) + imp.cached_target = { + ('foo',): { + 'object': setting, + 'data': {'name': 'foo', 'value': 'bar'}, + }, + } + + # returns same object + result = imp.get_target_object(('foo',)) + self.assertIs(result, setting) + + # and one more time just for kicks + result = imp.get_target_object(('foo',)) + self.assertIs(result, setting) + + # but then not if cache flag is off + imp.caches_target = False + result = imp.get_target_object(('foo',)) + self.assertIsNone(result) + + def test_normalize_target_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + setting = model.Setting(name='foo', value='bar') + data = imp.normalize_target_object(setting) + self.assertEqual(data, {'name': 'foo', 'value': 'bar'}) + + def test_create_target_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # basic + setting = imp.create_target_object(('foo',), {'name': 'foo', 'value': 'bar'}) + self.assertIsInstance(setting, model.Setting) + self.assertEqual(setting.name, 'foo') + self.assertEqual(setting.value, 'bar') + + # will skip if magic delete flag is set + setting = imp.create_target_object(('foo',), {'name': 'foo', 'value': 'bar', + '__ignoreme__': True}) + self.assertIsNone(setting) + + def test_make_empty_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + obj = imp.make_empty_object(('foo',)) + self.assertIsInstance(obj, model.Setting) + self.assertEqual(obj.name, 'foo') + + def test_make_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + obj = imp.make_object() + self.assertIsInstance(obj, model.Setting) + + def test_update_target_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + setting = model.Setting(name='foo') + + # basic logic for updating *new* object + obj = imp.update_target_object(setting, {'name': 'foo', 'value': 'bar'}) + self.assertIs(obj, setting) + self.assertEqual(setting.value, 'bar') + + +class TestFromFile(DataTestCase): + + def setUp(self): + self.setup_db() + self.handler = ImportHandler(self.config) + + def make_importer(self, **kwargs): + kwargs.setdefault('handler', self.handler) + return mod.FromFile(self.config, **kwargs) + + def test_setup(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + with patch.object(imp, 'open_input_file') as open_input_file: + imp.setup() + open_input_file.assert_called_once_with() + + def test_teardown(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + with patch.object(imp, 'close_input_file') as close_input_file: + imp.teardown() + close_input_file.assert_called_once_with() + + def test_get_input_file_path(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # path is guessed from dir+filename + path = self.write_file('data.txt', '') + imp.input_file_dir = self.tempdir + imp.input_file_name = 'data.txt' + self.assertEqual(imp.get_input_file_path(), path) + + # path can be explicitly set + path2 = self.write_file('data2.txt', '') + imp.input_file_path = path2 + self.assertEqual(imp.get_input_file_path(), path2) + + def test_get_input_file_dir(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # path cannot be guessed + self.assertRaises(NotImplementedError, imp.get_input_file_dir) + + # path can be explicitly set + imp.input_file_dir = self.tempdir + self.assertEqual(imp.get_input_file_dir(), self.tempdir) + + def test_get_input_file_name(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # name cannot be guessed + self.assertRaises(NotImplementedError, imp.get_input_file_name) + + # name can be explicitly set + imp.input_file_name = 'data.txt' + self.assertEqual(imp.get_input_file_name(), 'data.txt') + + def test_open_input_file(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + self.assertRaises(NotImplementedError, imp.open_input_file) + + def test_close_input_file(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + path = self.write_file('data.txt', '') + with open(path, 'rt') as f: + imp.input_file = f + with patch.object(f, 'close') as close: + imp.close_input_file() + close.assert_called_once_with() + + +class TestToSqlalchemy(DataTestCase): + + def setUp(self): + self.setup_db() + self.handler = ImportHandler(self.config) + + def make_importer(self, **kwargs): + kwargs.setdefault('handler', self.handler) + return mod.ToSqlalchemy(self.config, **kwargs) + + def test_get_target_object(self): + model = self.app.model + setting = model.Setting(name='foo', value='bar') + + # nb. must mock up a target cache for this one + imp = self.make_importer(model_class=model.Setting, caches_target=True) + imp.cached_target = { + ('foo',): { + 'object': setting, + 'data': {'name': 'foo', 'value': 'bar'}, + }, + } + + # returns same object + result = imp.get_target_object(('foo',)) + self.assertIs(result, setting) + + # and one more time just for kicks + result = imp.get_target_object(('foo',)) + self.assertIs(result, setting) + + # now let's put a 2nd setting in the db + setting2 = model.Setting(name='foo2', value='bar2') + self.session.add(setting2) + self.session.commit() + + # then we should be able to fetch that via query + imp.target_session = self.session + result = imp.get_target_object(('foo2',)) + self.assertIsInstance(result, model.Setting) + self.assertIs(result, setting2) + + # but sometimes it will not be found + result = imp.get_target_object(('foo3',)) + self.assertIsNone(result) + + def test_create_target_object(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting, target_session=self.session) + setting = model.Setting(name='foo', value='bar') + + # new object is added to session + setting = imp.create_target_object(('foo',), {'name': 'foo', 'value': 'bar'}) + self.assertIsInstance(setting, model.Setting) + self.assertEqual(setting.name, 'foo') + self.assertEqual(setting.value, 'bar') + self.assertIn(setting, self.session) + + def test_get_target_objects(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting, target_session=self.session) + + setting1 = model.Setting(name='foo', value='bar') + self.session.add(setting1) + setting2 = model.Setting(name='foo2', value='bar2') + self.session.add(setting2) + self.session.commit() + + result = imp.get_target_objects() + self.assertEqual(len(result), 2) + self.assertEqual(set(result), {setting1, setting2}) diff --git a/tests/importing/test_csv.py b/tests/importing/test_csv.py new file mode 100644 index 0000000..cf0a302 --- /dev/null +++ b/tests/importing/test_csv.py @@ -0,0 +1,114 @@ +#-*- coding: utf-8; -*- + +import csv +from unittest.mock import patch + +from wuttjamaican.testing import DataTestCase + +from wuttasync.importing import csv as mod, ImportHandler, ToSqlalchemyHandler, ToSqlalchemy + + +class TestFromCsv(DataTestCase): + + def setUp(self): + self.setup_db() + self.handler = ImportHandler(self.config) + + def make_importer(self, **kwargs): + kwargs.setdefault('handler', self.handler) + return mod.FromCsv(self.config, **kwargs) + + def test_get_input_file_name(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + # name can be guessed + self.assertEqual(imp.get_input_file_name(), 'Setting.csv') + + # name can be explicitly set + imp.input_file_name = 'data.txt' + self.assertEqual(imp.get_input_file_name(), 'data.txt') + + def test_open_input_file(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + path = self.write_file('data.txt', '') + imp.input_file_path = path + imp.open_input_file() + self.assertEqual(imp.input_file.name, path) + self.assertIsInstance(imp.input_reader, csv.DictReader) + imp.input_file.close() + + def test_close_input_file(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + path = self.write_file('data.txt', '') + imp.input_file_path = path + imp.open_input_file() + imp.close_input_file() + self.assertFalse(hasattr(imp, 'input_reader')) + self.assertFalse(hasattr(imp, 'input_file')) + + def test_get_source_objects(self): + model = self.app.model + imp = self.make_importer(model_class=model.Setting) + + path = self.write_file('data.csv', """\ +name,value +foo,bar +foo2,bar2 +""") + imp.input_file_path = path + imp.open_input_file() + objects = imp.get_source_objects() + imp.close_input_file() + self.assertEqual(len(objects), 2) + self.assertEqual(objects[0], {'name': 'foo', 'value': 'bar'}) + self.assertEqual(objects[1], {'name': 'foo2', 'value': 'bar2'}) + + +class MockMixinHandler(mod.FromCsvToSqlalchemyMixin, ToSqlalchemyHandler): + ToImporterBase = ToSqlalchemy + + +class TestFromCsvToSqlalchemyMixin(DataTestCase): + + def make_handler(self, **kwargs): + return MockMixinHandler(self.config, **kwargs) + + def test_get_target_model(self): + with patch.object(mod.FromCsvToSqlalchemyMixin, 'define_importers', return_value={}): + handler = self.make_handler() + self.assertRaises(NotImplementedError, handler.get_target_model) + + def test_define_importers(self): + model = self.app.model + with patch.object(mod.FromCsvToSqlalchemyMixin, 'get_target_model', return_value=model): + handler = self.make_handler() + importers = handler.define_importers() + self.assertIn('Setting', importers) + self.assertTrue(issubclass(importers['Setting'], mod.FromCsv)) + self.assertTrue(issubclass(importers['Setting'], ToSqlalchemy)) + self.assertIn('User', importers) + self.assertIn('Person', importers) + self.assertIn('Role', importers) + + def test_make_importer_factory(self): + model = self.app.model + with patch.object(mod.FromCsvToSqlalchemyMixin, 'define_importers', return_value={}): + handler = self.make_handler() + factory = handler.make_importer_factory(model.Setting, 'Setting') + self.assertTrue(issubclass(factory, mod.FromCsv)) + self.assertTrue(issubclass(factory, ToSqlalchemy)) + + +class TestFromCsvToWutta(DataTestCase): + + def make_handler(self, **kwargs): + return mod.FromCsvToWutta(self.config, **kwargs) + + def test_get_target_model(self): + handler = self.make_handler() + self.assertIs(handler.get_target_model(), self.app.model) diff --git a/tests/importing/test_handlers.py b/tests/importing/test_handlers.py new file mode 100644 index 0000000..67d861f --- /dev/null +++ b/tests/importing/test_handlers.py @@ -0,0 +1,218 @@ +#-*- coding: utf-8; -*- + +from collections import OrderedDict +from unittest.mock import patch + +from wuttjamaican.testing import DataTestCase + +from wuttasync.importing import handlers as mod, Importer, ToSqlalchemy + + +class TestImportHandler(DataTestCase): + + def make_handler(self, **kwargs): + return mod.ImportHandler(self.config, **kwargs) + + def test_str(self): + handler = self.make_handler() + self.assertEqual(str(handler), "None → None") + + handler.source_title = 'CSV' + handler.target_title = 'Wutta' + self.assertEqual(str(handler), "CSV → Wutta") + + def test_actioning(self): + handler = self.make_handler() + self.assertEqual(handler.actioning, 'importing') + + handler.orientation = mod.Orientation.EXPORT + self.assertEqual(handler.actioning, 'exporting') + + def test_get_key(self): + handler = self.make_handler() + self.assertEqual(handler.get_key(), 'to_None.from_None.import') + + with patch.multiple(mod.ImportHandler, source_key='csv', target_key='wutta'): + self.assertEqual(handler.get_key(), 'to_wutta.from_csv.import') + + def test_get_spec(self): + handler = self.make_handler() + self.assertEqual(handler.get_spec(), 'wuttasync.importing.handlers:ImportHandler') + + def test_get_title(self): + handler = self.make_handler() + self.assertEqual(handler.get_title(), "None → None") + + handler.source_title = 'CSV' + handler.target_title = 'Wutta' + self.assertEqual(handler.get_title(), "CSV → Wutta") + + def test_get_source_title(self): + handler = self.make_handler() + + # null by default + self.assertIsNone(handler.get_source_title()) + + # which is really using source_key as fallback + handler.source_key = 'csv' + self.assertEqual(handler.get_source_title(), 'csv') + + # can also use (defined) generic fallback + handler.generic_source_title = 'CSV' + self.assertEqual(handler.get_source_title(), 'CSV') + + # or can set explicitly + handler.source_title = 'XXX' + self.assertEqual(handler.get_source_title(), 'XXX') + + def test_get_target_title(self): + handler = self.make_handler() + + # null by default + self.assertIsNone(handler.get_target_title()) + + # which is really using target_key as fallback + handler.target_key = 'wutta' + self.assertEqual(handler.get_target_title(), 'wutta') + + # can also use (defined) generic fallback + handler.generic_target_title = 'Wutta' + self.assertEqual(handler.get_target_title(), 'Wutta') + + # or can set explicitly + handler.target_title = 'XXX' + self.assertEqual(handler.get_target_title(), 'XXX') + + def test_process_data(self): + model = self.app.model + handler = self.make_handler() + + # empy/no-op should commit (not fail) + with patch.object(handler, 'commit_transaction') as commit_transaction: + handler.process_data() + commit_transaction.assert_called_once_with() + + # do that again with no patch, just for kicks + handler.process_data() + + # dry-run should rollback + with patch.object(handler, 'commit_transaction') as commit_transaction: + with patch.object(handler, 'rollback_transaction') as rollback_transaction: + handler.process_data(dry_run=True) + self.assertFalse(commit_transaction.called) + rollback_transaction.assert_called_once_with() + + # and do that with no patch, for kicks + handler.process_data(dry_run=True) + + # outright error should cause rollback + with patch.object(handler, 'commit_transaction') as commit_transaction: + with patch.object(handler, 'rollback_transaction') as rollback_transaction: + with patch.object(handler, 'get_importer', side_effect=RuntimeError): + self.assertRaises(RuntimeError, handler.process_data, 'BlahBlah') + self.assertFalse(commit_transaction.called) + rollback_transaction.assert_called_once_with() + + # fake importer class/data + mock_source_objects = [{'name': 'foo', 'value': 'bar'}] + class SettingImporter(ToSqlalchemy): + model_class = model.Setting + target_session = self.session + def get_source_objects(self): + return mock_source_objects + + # now for a "normal" one + handler.importers['Setting'] = SettingImporter + self.assertEqual(self.session.query(model.Setting).count(), 0) + handler.process_data('Setting') + self.assertEqual(self.session.query(model.Setting).count(), 1) + + # then add another mock record + mock_source_objects.append({'name': 'foo2', 'value': 'bar2'}) + handler.process_data('Setting') + self.assertEqual(self.session.query(model.Setting).count(), 2) + + # nb. even if dry-run, record is added + # (rollback would happen later in that case) + mock_source_objects.append({'name': 'foo3', 'value': 'bar3'}) + handler.process_data('Setting', dry_run=True) + self.assertEqual(self.session.query(model.Setting).count(), 3) + + def test_consume_kwargs(self): + handler = self.make_handler() + + # kwargs are returned as-is + kw = {} + result = handler.consume_kwargs(kw) + self.assertIs(result, kw) + + # captures dry-run flag + self.assertFalse(handler.dry_run) + kw['dry_run'] = True + result = handler.consume_kwargs(kw) + self.assertIs(result, kw) + self.assertTrue(kw['dry_run']) + self.assertTrue(handler.dry_run) + + def test_define_importers(self): + handler = self.make_handler() + importers = handler.define_importers() + self.assertEqual(importers, {}) + self.assertIsInstance(importers, OrderedDict) + + def test_get_importer(self): + model = self.app.model + handler = self.make_handler() + + # normal + handler.importers['Setting'] = Importer + importer = handler.get_importer('Setting', model_class=model.Setting) + self.assertIsInstance(importer, Importer) + + # key not found + self.assertRaises(KeyError, handler.get_importer, 'BunchOfNonsense', model_class=model.Setting) + + +class TestToSqlalchemyHandler(DataTestCase): + + def make_handler(self, **kwargs): + return mod.ToSqlalchemyHandler(self.config, **kwargs) + + def test_begin_target_transaction(self): + handler = self.make_handler() + with patch.object(handler, 'make_target_session') as make_target_session: + make_target_session.return_value = self.session + self.assertIsNone(handler.target_session) + handler.begin_target_transaction() + make_target_session.assert_called_once_with() + + def test_rollback_target_transaction(self): + handler = self.make_handler() + with patch.object(handler, 'make_target_session') as make_target_session: + make_target_session.return_value = self.session + self.assertIsNone(handler.target_session) + handler.begin_target_transaction() + self.assertIs(handler.target_session, self.session) + handler.rollback_target_transaction() + self.assertIsNone(handler.target_session) + + def test_commit_target_transaction(self): + handler = self.make_handler() + with patch.object(handler, 'make_target_session') as make_target_session: + make_target_session.return_value = self.session + self.assertIsNone(handler.target_session) + handler.begin_target_transaction() + self.assertIs(handler.target_session, self.session) + handler.commit_target_transaction() + self.assertIsNone(handler.target_session) + + def test_make_target_session(self): + handler = self.make_handler() + self.assertRaises(NotImplementedError, handler.make_target_session) + + def test_get_importer_kwargs(self): + handler = self.make_handler() + handler.target_session = self.session + kw = handler.get_importer_kwargs('Setting') + self.assertIn('target_session', kw) + self.assertIs(kw['target_session'], self.session) diff --git a/tests/importing/test_model.py b/tests/importing/test_model.py new file mode 100644 index 0000000..ea74a43 --- /dev/null +++ b/tests/importing/test_model.py @@ -0,0 +1,3 @@ +#-*- coding: utf-8; -*- + +from wuttasync.importing import model as mod diff --git a/tests/importing/test_wutta.py b/tests/importing/test_wutta.py new file mode 100644 index 0000000..ec5df50 --- /dev/null +++ b/tests/importing/test_wutta.py @@ -0,0 +1,38 @@ +#-*- coding: utf-8; -*- + +from unittest.mock import patch + +from wuttjamaican.testing import DataTestCase + +from wuttasync.importing import wutta as mod + + +class TestToWuttaHandler(DataTestCase): + + def make_handler(self, **kwargs): + return mod.ToWuttaHandler(self.config, **kwargs) + + def test_get_target_title(self): + handler = self.make_handler() + + # uses app title by default + self.config.setdefault('wutta.app_title', "What About This") + self.assertEqual(handler.get_target_title(), 'What About This') + + # or generic default if present + handler.generic_target_title = "WHATABOUTTHIS" + self.assertEqual(handler.get_target_title(), 'WHATABOUTTHIS') + + # but prefer specific title if present + handler.target_title = "what_about_this" + self.assertEqual(handler.get_target_title(), 'what_about_this') + + def test_make_target_session(self): + handler = self.make_handler() + + # makes "new" (mocked in our case) app session + with patch.object(self.app, 'make_session') as make_session: + make_session.return_value = self.session + session = handler.make_target_session() + make_session.assert_called_once_with() + self.assertIs(session, self.session) diff --git a/tests/test_util.py b/tests/test_util.py new file mode 100644 index 0000000..fc0476c --- /dev/null +++ b/tests/test_util.py @@ -0,0 +1,29 @@ +# -*- coding: utf-8; -*- + +from unittest import TestCase + +from wuttasync import util as mod + + +class TestDataDiffs(TestCase): + + def test_source_missing_field(self): + source = {'foo': 'bar'} + target = {'baz': 'xyz', 'foo': 'bar'} + self.assertRaises(KeyError, mod.data_diffs, source, target) + + def test_target_missing_field(self): + source = {'foo': 'bar', 'baz': 'xyz'} + target = {'baz': 'xyz'} + self.assertRaises(KeyError, mod.data_diffs, source, target, fields=['foo', 'baz']) + + def test_no_diffs(self): + source = {'foo': 'bar', 'baz': 'xyz'} + target = {'baz': 'xyz', 'foo': 'bar'} + self.assertFalse(mod.data_diffs(source, target)) + + def test_with_diffs(self): + source = {'foo': 'bar', 'baz': 'xyz'} + target = {'baz': 'xyz', 'foo': 'BAR'} + result = mod.data_diffs(source, target) + self.assertEqual(result, ['foo']) diff --git a/tox.ini b/tox.ini new file mode 100644 index 0000000..78d41eb --- /dev/null +++ b/tox.ini @@ -0,0 +1,17 @@ + +[tox] +envlist = py38, py39, py310, py311 + +[testenv] +extras = tests +commands = pytest {posargs} + +[testenv:coverage] +basepython = python3.11 +commands = pytest --cov=wuttasync --cov-report=html --cov-fail-under=100 + +[testenv:docs] +basepython = python3.11 +extras = docs +changedir = docs +commands = sphinx-build -b html -d {envtmpdir}/doctrees -W -T . {envtmpdir}/docs