pax_global_header00006660000000000000000000000064147235430410014515gustar00rootroot0000000000000052 comment=c4a8a5197b0825ba3ce4b814de269cec23382e46 trollsift-0.5.3/000077500000000000000000000000001472354304100135445ustar00rootroot00000000000000trollsift-0.5.3/.gitattributes000066400000000000000000000000421472354304100164330ustar00rootroot00000000000000trollsift/version.py export-subst trollsift-0.5.3/.github/000077500000000000000000000000001472354304100151045ustar00rootroot00000000000000trollsift-0.5.3/.github/dependabot.yml000066400000000000000000000010011472354304100177240ustar00rootroot00000000000000# To get started with Dependabot version updates, you'll need to specify which # package ecosystems to update and where the package manifests are located. # Please see the documentation for all configuration options: # https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates version: 2 updates: - package-ecosystem: "github-actions" # See documentation for possible values directory: "/" # Location of package manifests schedule: interval: "weekly" trollsift-0.5.3/.github/workflows/000077500000000000000000000000001472354304100171415ustar00rootroot00000000000000trollsift-0.5.3/.github/workflows/ci.yaml000066400000000000000000000021341472354304100204200ustar00rootroot00000000000000name: CI on: [push, pull_request] jobs: test: runs-on: ${{ matrix.os }} strategy: fail-fast: true matrix: os: ["windows-latest", "ubuntu-latest", "macos-latest"] python-version: ["3.10", "3.11", "3.12"] env: PYTHON_VERSION: ${{ matrix.python-version }} OS: ${{ matrix.os }} ACTIONS_ALLOW_UNSECURE_COMMANDS: true steps: - name: Checkout source uses: actions/checkout@v4 - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v5 with: python-version: ${{ matrix.python-version }} - name: Install dependencies run: | pip install -U codecov pytest pytest-cov - name: Install trollsift run: | pip install --no-deps -e . - name: Run unit tests run: | pytest --cov=trollsift trollsift/tests --cov-report=xml - name: Upload unittest coverage to Codecov uses: codecov/codecov-action@v5 with: flags: unittests file: ./coverage.xml env_vars: OS,PYTHON_VERSION trollsift-0.5.3/.github/workflows/deploy-sdist.yaml000066400000000000000000000010371472354304100224460ustar00rootroot00000000000000name: Deploy sdist on: release: types: - published jobs: test: runs-on: ubuntu-latest steps: - name: Checkout source uses: actions/checkout@v4 - name: Create sdist shell: bash -l {0} run: | python -m pip install -q build python -m build - name: Publish package to PyPI if: github.event.action == 'published' uses: pypa/gh-action-pypi-publish@v1.12.2 with: user: __token__ password: ${{ secrets.pypi_password }}trollsift-0.5.3/.gitignore000066400000000000000000000006031472354304100155330ustar00rootroot00000000000000# Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ wheels/ pip-wheel-metadata/ share/python-wheels/ *.egg-info/ .installed.cfg *.egg MANIFEST trollsift/version.py # Jupyter Notebook .ipynb_checkpoints doc/build/* .coverage trollsift-0.5.3/.readthedocs.yaml000066400000000000000000000007011472354304100167710ustar00rootroot00000000000000# Read the Docs configuration file # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details version: 2 # Build documentation in the docs/ directory with Sphinx sphinx: configuration: doc/source/conf.py fail_on_warning: true # Optionally build your docs in additional formats such as PDF and ePub formats: all build: os: "ubuntu-20.04" tools: python: "mambaforge-4.10" conda: environment: doc/rtd_environment.yaml trollsift-0.5.3/AUTHORS.md000066400000000000000000000013321472354304100152120ustar00rootroot00000000000000# Project Contributors The following people have made contributions to this project: - [David Hoese (djhoese)](https://github.com/djhoese) - [Panu Lahtinen (pnuu)](https://github.com/pnuu) - [Martin Raspaud (mraspaud)](https://github.com/mraspaud) - [Hrobjartur Thorsteinsson (thorsteinssonh)](https://github.com/thorsteinssonh) - [Stephan Finkensieper (sfinkens)](https://github.com/sfinkens) - [Paulo Medeiros (paulovcmedeiros)](https://github.com/paulovcmedeiros) - [Regan Koopmans (Regan-Koopmans)](https://github.com/Regan-Koopmans)trollsift-0.5.3/CHANGELOG.md000066400000000000000000000153351472354304100153640ustar00rootroot00000000000000## Version 0.5.3 (2024/12/03) ### Pull Requests Merged #### Bugs fixed * [PR 76](https://github.com/pytroll/trollsift/pull/76) - Drop support for Python 3.8 and below In this release 1 pull request was closed. ## Version 0.5.2 (2024/12/02) ### Pull Requests Merged #### Features added * [PR 75](https://github.com/pytroll/trollsift/pull/75) - Switch to pyproject.toml In this release 1 pull request was closed. ## Version 0.5.1 (2023/10/09) ### Pull Requests Merged #### Bugs fixed * [PR 49](https://github.com/pytroll/trollsift/pull/49) - Update versioneer to stop using deprecated distutils module. #### Features added * [PR 56](https://github.com/pytroll/trollsift/pull/56) - Add readthedocs configuration file In this release 2 pull requests were closed. ## Version 0.5.0 (2022/11/21) ### Issues Closed * [Issue 45](https://github.com/pytroll/trollsift/issues/45) - Provide simple access to defined keys of a parser instance ([PR 46](https://github.com/pytroll/trollsift/pull/46) by [@carloshorn](https://github.com/carloshorn)) * [Issue 37](https://github.com/pytroll/trollsift/issues/37) - Global instances of formatters ([PR 38](https://github.com/pytroll/trollsift/pull/38) by [@Regan-Koopmans](https://github.com/Regan-Koopmans)) * [Issue 36](https://github.com/pytroll/trollsift/issues/36) - Alignment marker is not optional for numbers when it should * [Issue 34](https://github.com/pytroll/trollsift/issues/34) - Trollsift doesn't parse hex numbers ([PR 35](https://github.com/pytroll/trollsift/pull/35) by [@mraspaud](https://github.com/mraspaud)) In this release 4 issues were closed. ### Pull Requests Merged #### Bugs fixed * [PR 38](https://github.com/pytroll/trollsift/pull/38) - Replace global RegexFormatter with memoized function ([37](https://github.com/pytroll/trollsift/issues/37)) * [PR 35](https://github.com/pytroll/trollsift/pull/35) - Add hex, octal, and binary parsing ([34](https://github.com/pytroll/trollsift/issues/34)) #### Features added * [PR 46](https://github.com/pytroll/trollsift/pull/46) - Add keys method to Parser class ([45](https://github.com/pytroll/trollsift/issues/45)) In this release 3 pull requests were closed. ## Version 0.4.0 (2022/02/03) ### Issues Closed * [Issue 30](https://github.com/pytroll/trollsift/issues/30) - Problems with padding syntax ([PR 33](https://github.com/pytroll/trollsift/pull/33) by [@paulovcmedeiros](https://github.com/paulovcmedeiros)) In this release 1 issue was closed. ### Pull Requests Merged #### Bugs fixed * [PR 33](https://github.com/pytroll/trollsift/pull/33) - Fix problems with type='' in string padding syntax ([30](https://github.com/pytroll/trollsift/issues/30)) #### Features added * [PR 32](https://github.com/pytroll/trollsift/pull/32) - Add 'allow_partial' keyword to compose * [PR 31](https://github.com/pytroll/trollsift/pull/31) - Change tested Python versions to 3.8, 3.9 and 3.10 * [PR 24](https://github.com/pytroll/trollsift/pull/24) - Skip Python2 support and require python 3.6 or higher ## Version 0.3.5 (2021/02/15) ### Issues Closed * [Issue 27](https://github.com/pytroll/trollsift/issues/27) - Parsing zero padded floats * [Issue 26](https://github.com/pytroll/trollsift/issues/26) - MNT: Stop using ci-helpers in appveyor.yml * [Issue 23](https://github.com/pytroll/trollsift/issues/23) - Bug when parsing leap day when you dont have year * [Issue 20](https://github.com/pytroll/trollsift/issues/20) - Special conversion specifiers do not work ([PR 21](https://github.com/pytroll/trollsift/pull/21)) In this release 4 issues were closed. ### Pull Requests Merged #### Bugs fixed * [PR 21](https://github.com/pytroll/trollsift/pull/21) - Fix typo in string formatting usage example and drop Python 2.7 tests ([20](https://github.com/pytroll/trollsift/issues/20)) #### Features added * [PR 29](https://github.com/pytroll/trollsift/pull/29) - GitHub actions * [PR 25](https://github.com/pytroll/trollsift/pull/25) - Add lru_cache to parsing for improved performance In this release 3 pull requests were closed. ## Version 0.3.4 (2019/12/18) ### Issues Closed * [Issue 18](https://github.com/pytroll/trollsift/issues/18) - Different parsing allignment behaviour between 0.2.* and 0.3.* ([PR 19](https://github.com/pytroll/trollsift/pull/19)) In this release 1 issue was closed. ### Pull Requests Merged #### Bugs fixed * [PR 19](https://github.com/pytroll/trollsift/pull/19) - Fix regex parser being too greedy with partial string patterns ([18](https://github.com/pytroll/trollsift/issues/18)) In this release 1 pull request was closed. ## Version 0.3.3 (2019/10/09) ### Pull Requests Merged #### Bugs fixed * [PR 15](https://github.com/pytroll/trollsift/pull/15) - Fix parse accepting strings with trailing characters #### Features added * [PR 14](https://github.com/pytroll/trollsift/pull/14) - Adding .stickler.yml configuration file In this release 2 pull requests were closed. ## Version 0.3.2 (2019/01/14) ### Pull Requests Merged #### Bugs fixed * [PR 13](https://github.com/pytroll/trollsift/pull/13) - Fix backslashes in regex patterns on Windows In this release 1 pull request was closed. ## Version 0.3.1 (2018/11/02) ### Issues Closed * [Issue 11](https://github.com/pytroll/trollsift/issues/11) - Using the same information in two places in the template is fails with 0.3.0 ([PR 12](https://github.com/pytroll/trollsift/pull/12)) In this release 1 issue was closed. ### Pull Requests Merged #### Bugs fixed * [PR 12](https://github.com/pytroll/trollsift/pull/12) - Fix fields being specified multiple times in one pattern ([11](https://github.com/pytroll/trollsift/issues/11)) In this release 1 pull request was closed. ## Version 0.3.0 (2018/09/29) ### Issues Closed * [Issue 5](https://github.com/pytroll/trollsift/issues/5) - Add custom string formatter for lower/upper support In this release 1 issue was closed. ### Pull Requests Merged #### Features added * [PR 6](https://github.com/pytroll/trollsift/pull/6) - Add additional string formatting conversion options In this release 1 pull request was closed. ## Version 0.2.1 (2018/05/22) ### Issues Closed * [Issue 3](https://github.com/pytroll/trollsift/issues/3) - Packaging license file ([PR 4](https://github.com/pytroll/trollsift/pull/4)) In this release 1 issues were closed. ### Pull Requests Merged #### Features added * [PR 4](https://github.com/pytroll/trollsift/pull/4) - Update travis tests and add appveyor tests ([3](https://github.com/pytroll/trollsift/issues/3)) In this release 1 pull request was closed. ## Version 0.2.0 (2017/12/08) ### Issues Closed * [Issue 2](https://github.com/pytroll/trollsift/issues/2) - Another timestring issue * [Issue 1](https://github.com/pytroll/trollsift/issues/1) - problem when parsing time strings In this release 2 issues were closed. trollsift-0.5.3/LICENSE.txt000066400000000000000000001044601472354304100153740ustar00rootroot00000000000000GNU 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. {one line to give the program's name and a brief idea of what it does.} Copyright (C) {year} {name of author} 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: {project} Copyright (C) {year} {fullname} 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 .trollsift-0.5.3/MANIFEST.in000066400000000000000000000002041472354304100152760ustar00rootroot00000000000000include doc/Makefile include doc/source/* include LICENSE.txt include README.rst include versioneer.py include trollsift/version.py trollsift-0.5.3/README.rst000066400000000000000000000003051472354304100152310ustar00rootroot00000000000000Trollsift ========= Trollsift is a collection of modules that assist with formatting, parsing and filtering satellite granule file names. For documentation, see http://trollsift.readthedocs.org/ trollsift-0.5.3/RELEASING.md000066400000000000000000000023541472354304100154030ustar00rootroot00000000000000# Releasing trollsift 1. checkout main branch 2. pull from repo 3. run the unittests 4. run `loghub` and update the `CHANGELOG.md` file: ``` loghub pytroll/trollsift --token $LOGHUB_GITHUB_TOKEN -st $(git tag --sort=-version:refname --list 'v*' | head -n 1) -plg bug "Bugs fixed" -plg enhancement "Features added" -plg documentation "Documentation changes" -plg backwards-incompatibility "Backwards incompatible changes" ``` Don't forget to commit! 5. Create a tag with the new version number, starting with a 'v', eg: ``` git tag -a v0.22.45 -m "Version 0.22.45" ``` See [semver.org](http://semver.org/) on how to write a version number. 6. push changes to github `git push --follow-tags` 7. Verify tests pass on GitHub Actions 8. Create a "Release" on GitHub by going to https://github.com/pytroll/pyresample/releases and clicking "Draft a new release". On the next page enter the newly created tag in the "Tag version" field, "Version X.Y.Z" in the "Release title" field, and paste the markdown from the changelog (the portion under the version section header) in the "Describe this release" box. Finally click "Publish release". 9. Verify the GitHub actions for deployment succeed and the release is on PyPI. trollsift-0.5.3/doc/000077500000000000000000000000001472354304100143115ustar00rootroot00000000000000trollsift-0.5.3/doc/Makefile000066400000000000000000000127251472354304100157600ustar00rootroot00000000000000# Makefile for Sphinx documentation # # You can set these variables from the command line. SPHINXOPTS = SPHINXBUILD = sphinx-build PAPER = BUILDDIR = build # Internal variables. PAPEROPT_a4 = -D latex_paper_size=a4 PAPEROPT_letter = -D latex_paper_size=letter ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source # the i18n builder cannot share the environment and doctrees with the others I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source .PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext help: @echo "Please use \`make ' where is one of" @echo " html to make standalone HTML files" @echo " dirhtml to make HTML files named index.html in directories" @echo " singlehtml to make a single large HTML file" @echo " pickle to make pickle files" @echo " json to make JSON files" @echo " htmlhelp to make HTML files and a HTML help project" @echo " qthelp to make HTML files and a qthelp project" @echo " devhelp to make HTML files and a Devhelp project" @echo " epub to make an epub" @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" @echo " latexpdf to make LaTeX files and run them through pdflatex" @echo " text to make text files" @echo " man to make manual pages" @echo " texinfo to make Texinfo files" @echo " info to make Texinfo files and run them through makeinfo" @echo " gettext to make PO message catalogs" @echo " changes to make an overview of all changed/added/deprecated items" @echo " linkcheck to check all external links for integrity" @echo " doctest to run all doctests embedded in the documentation (if enabled)" clean: -rm -rf $(BUILDDIR)/* html: $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html @echo @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." dirhtml: $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml @echo @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." singlehtml: $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml @echo @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." pickle: $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle @echo @echo "Build finished; now you can process the pickle files." json: $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json @echo @echo "Build finished; now you can process the JSON files." htmlhelp: $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp @echo @echo "Build finished; now you can run HTML Help Workshop with the" \ ".hhp project file in $(BUILDDIR)/htmlhelp." qthelp: $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp @echo @echo "Build finished; now you can run "qcollectiongenerator" with the" \ ".qhcp project file in $(BUILDDIR)/qthelp, like this:" @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/Pydecorate.qhcp" @echo "To view the help file:" @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/Pydecorate.qhc" devhelp: $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp @echo @echo "Build finished." @echo "To view the help file:" @echo "# mkdir -p $$HOME/.local/share/devhelp/Pydecorate" @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/Pydecorate" @echo "# devhelp" epub: $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub @echo @echo "Build finished. The epub file is in $(BUILDDIR)/epub." latex: $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex @echo @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." @echo "Run \`make' in that directory to run these through (pdf)latex" \ "(use \`make latexpdf' here to do that automatically)." latexpdf: $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex @echo "Running LaTeX files through pdflatex..." $(MAKE) -C $(BUILDDIR)/latex all-pdf @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." text: $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text @echo @echo "Build finished. The text files are in $(BUILDDIR)/text." man: $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man @echo @echo "Build finished. The manual pages are in $(BUILDDIR)/man." texinfo: $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo @echo @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." @echo "Run \`make' in that directory to run these through makeinfo" \ "(use \`make info' here to do that automatically)." info: $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo @echo "Running Texinfo files through makeinfo..." make -C $(BUILDDIR)/texinfo info @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." gettext: $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale @echo @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." changes: $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes @echo @echo "The overview file is in $(BUILDDIR)/changes." linkcheck: $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck @echo @echo "Link check complete; look for any errors in the above output " \ "or in $(BUILDDIR)/linkcheck/output.txt." doctest: $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest @echo "Testing of doctests in the sources finished, look at the " \ "results in $(BUILDDIR)/doctest/output.txt." trollsift-0.5.3/doc/rtd_environment.yaml000066400000000000000000000003351472354304100204130ustar00rootroot00000000000000name: readthedocs channels: - conda-forge dependencies: - python=3.11 - pip - pytest - sphinx - sphinx_rtd_theme - sphinxcontrib-apidoc - pip: - graphviz - .. # relative path to the satpy project trollsift-0.5.3/doc/source/000077500000000000000000000000001472354304100156115ustar00rootroot00000000000000trollsift-0.5.3/doc/source/_static/000077500000000000000000000000001472354304100172375ustar00rootroot00000000000000trollsift-0.5.3/doc/source/_static/.gitkeep000066400000000000000000000000001472354304100206560ustar00rootroot00000000000000trollsift-0.5.3/doc/source/api.rst000066400000000000000000000002531472354304100171140ustar00rootroot00000000000000The :mod:`trollsift` API =============================== trollsift parser --------------------------- .. automodule:: trollsift.parser :members: :undoc-members: trollsift-0.5.3/doc/source/conf.py000066400000000000000000000177771472354304100171330ustar00rootroot00000000000000# -*- coding: utf-8 -*- # # trollsift documentation build configuration file, created by # sphinx-quickstart on Wed Nov 27 13:05:45 2013. # # This file is execfile()d with the current directory set to its containing dir. # # Note that not all possible configuration values are present in this # autogenerated file. # # All configuration values have a default; values that are commented out # serve to show the default. import sys, os # If extensions (or modules to document with autodoc) are in another directory, # add these directories to sys.path here. If the directory is relative to the # documentation root, use os.path.abspath to make it absolute, like shown here. sys.path.insert(0, os.path.abspath('../../')) # -- General configuration ----------------------------------------------------- # If your documentation needs a minimal Sphinx version, state it here. # needs_sphinx = '1.0' # Add any Sphinx extension module names here, as strings. They can be extensions # coming with Sphinx (named 'sphinx.ext.*') or your custom ones. extensions = ['sphinx.ext.autodoc', 'sphinx.ext.doctest', 'sphinx.ext.intersphinx', 'sphinx.ext.napoleon', 'sphinx.ext.viewcode'] # Add any paths that contain templates here, relative to this directory. templates_path = ['_templates'] # The suffix of source filenames. source_suffix = '.rst' # The encoding of source files. # source_encoding = 'utf-8-sig' # The master toctree document. master_doc = 'index' # General information about the project. project = u'trollsift' copyright = u'2014, Panu Lahtinen, Hrobjartur Thorsteinsson' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the # built documents. # # The short X.Y version. version = '0.1' # The full version, including alpha/beta/rc tags. release = '0.1.0' # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. # language = None # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: # today = '' # Else, today_fmt is used as the format for a strftime call. # today_fmt = '%B %d, %Y' # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files. exclude_patterns = [] # The reST default role (used for this markup: `text`) to use for all documents. # default_role = None # If true, '()' will be appended to :func: etc. cross-reference text. # add_function_parentheses = True # If true, the current module name will be prepended to all description # unit titles (such as .. function::). # add_module_names = True # If true, sectionauthor and moduleauthor directives will be shown in the # output. They are ignored by default. # show_authors = False # The name of the Pygments (syntax highlighting) style to use. pygments_style = 'sphinx' # A list of ignored prefixes for module index sorting. # modindex_common_prefix = [] # -- Options for HTML output --------------------------------------------------- # The theme to use for HTML and HTML Help pages. See the documentation for # a list of builtin themes. html_theme = 'default' # Theme options are theme-specific and customize the look and feel of a theme # further. For a list of options available for each theme, see the # documentation. # html_theme_options = {} # Add any paths that contain custom themes here, relative to this directory. # html_theme_path = [] # The name for this set of Sphinx documents. If None, it defaults to # " v documentation". # html_title = None # A shorter title for the navigation bar. Default is the same as html_title. # html_short_title = None # The name of an image file (relative to this directory) to place at the top # of the sidebar. # html_logo = None # The name of an image file (within the static path) to use as favicon of the # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 # pixels large. # html_favicon = None # Add any paths that contain custom static files (such as style sheets) here, # relative to this directory. They are copied after the builtin static files, # so a file named "default.css" will overwrite the builtin "default.css". html_static_path = ['_static'] # If not '', a 'Last updated on:' timestamp is inserted at every page bottom, # using the given strftime format. # html_last_updated_fmt = '%b %d, %Y' # If true, SmartyPants will be used to convert quotes and dashes to # typographically correct entities. # html_use_smartypants = True # Custom sidebar templates, maps document names to template names. # html_sidebars = {} # Additional templates that should be rendered to pages, maps page names to # template names. # html_additional_pages = {} # If false, no module index is generated. # html_domain_indices = True # If false, no index is generated. # html_use_index = True # If true, the index is split into individual pages for each letter. # html_split_index = False # If true, links to the reST sources are added to the pages. # html_show_sourcelink = True # If true, "Created using Sphinx" is shown in the HTML footer. Default is True. # html_show_sphinx = True # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. # html_show_copyright = True # If true, an OpenSearch description file will be output, and all pages will # contain a tag referring to it. The value of this option must be the # base URL from which the finished HTML is served. # html_use_opensearch = '' # This is the file name suffix for HTML files (e.g. ".xhtml"). # html_file_suffix = None # Output file base name for HTML help builder. htmlhelp_basename = 'trollsiftdoc' # -- Options for LaTeX output -------------------------------------------------- latex_elements = { # The paper size ('letterpaper' or 'a4paper'). # 'papersize': 'letterpaper', # The font size ('10pt', '11pt' or '12pt'). # 'pointsize': '10pt', # Additional stuff for the LaTeX preamble. # 'preamble': '', } # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, author, documentclass [howto/manual]). latex_documents = [ ('index', 'trollsift.tex', u'Trollsift Documentation', u'Hrobjartur Thorsteinsson', 'manual'), ] # The name of an image file (relative to this directory) to place at the top of # the title page. # latex_logo = None # For "manual" documents, if this is true, then toplevel headings are parts, # not chapters. # latex_use_parts = False # If true, show page references after internal links. # latex_show_pagerefs = False # If true, show URL addresses after external links. # latex_show_urls = False # Documents to append as an appendix to all manuals. # latex_appendices = [] # If false, no module index is generated. # latex_domain_indices = True # -- Options for manual page output -------------------------------------------- # One entry per manual page. List of tuples # (source start file, name, description, authors, manual section). man_pages = [ ('index', 'trollsift', u'Trollsift Documentation', [u'Panu Lahtinen', u'Hrobjartur Thorsteinsson'], 1) ] # If true, show URL addresses after external links. # man_show_urls = False # -- Options for Texinfo output ------------------------------------------------ # Grouping the document tree into Texinfo files. List of tuples # (source start file, target name, title, author, # dir menu entry, description, category) texinfo_documents = [ ('index', 'trollsift', u'Trollsift Documentation', u'Panu Lahtinen', u'Hrobjartur Thorsteinsson', 'trollsift', 'One line description of project.', 'Miscellaneous'), ] # Documents to append as an appendix to all manuals. # texinfo_appendices = [] # If false, no module index is generated. # texinfo_domain_indices = True # How to display URL addresses: 'footnote', 'no', or 'inline'. # texinfo_show_urls = 'footnote' # How intersphinx should find links to other packages intersphinx_mapping = { 'python': ('https://docs.python.org/3', None), } trollsift-0.5.3/doc/source/index.rst000066400000000000000000000017671472354304100174650ustar00rootroot00000000000000.. Trollsift documentation master file, created by sphinx-quickstart on Wed Nov 27 13:05:45 2013. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. .. meta:: :description: Trollsift project, modules for formatting, parsing and filtering satellite granule file names :keywords: Python, pytroll, format, parse, filter, string Welcome to the trollsift documentation! ========================================= Trollsift is a collection of modules that assist with formatting, parsing and filtering satellite granule file names. These modules are useful and necessary for writing higher level applications and api's for satellite batch processing. The source code of the package can be found at github, github_ .. _github: https://github.com/pytroll/trollsift Contents +++++++++ .. toctree:: :maxdepth: 3 installation usage api Indices and tables +++++++++++++++++++ * :ref:`genindex` * :ref:`modindex` * :ref:`search` trollsift-0.5.3/doc/source/installation.rst000066400000000000000000000013741472354304100210510ustar00rootroot00000000000000 .. .. sectnum:: .. :depth: 4 .. :start: 1 .. :suffix: . Installation ------------ Trollsift is available from PyPI:: $ pip install trollsift Alternatively, you can install it into a conda environment by using the conda-forge channel:: $ conda install -c conda-forge trollsift Or you can install it directly from the GitHub repository:: $ pip install git+https://github.com/pytroll/trollsift.git Developer Installation ++++++++++++++++++++++ You can download the trollsift source code from github:: $ git clone https://github.com/pytroll/trollsift.git and then run:: $ pip install -e . Testing ++++++++ To check if your python setup is compatible with trollsift, you can run the test suite using pytest:: $ pytest trollsift/tests trollsift-0.5.3/doc/source/usage.rst000066400000000000000000000076411472354304100174570ustar00rootroot00000000000000Usage ===== Trollsift include collection of modules that assist with formatting, parsing and filtering satellite granule file names. These modules are useful and necessary for writing higher level applications and api’s for satellite batch processing. Currently we are implementing the string parsing and composing functionality. Watch this space for further modules to do with various types of filtering of satellite data granules. Parser ------ The trollsift string parser module is useful for composing (formatting) and parsing strings compatible with the Python :ref:`python:formatstrings`. In satellite data file name filtering, the library is useful for extracting typical information from granule filenames, such as observation time, platform and instrument names. The trollsift Parser can also verify that the string formatting is invertible, i.e. specific enough to ensure that parsing and composing of strings are bijective mappings ( aka one-to-one correspondence ) which may be essential for some applications, such as predicting granule parsing ^^^^^^^ The Parser object holds a format string, allowing us to parse and compose strings: >>> from trollsift import Parser >>> >>> p = Parser("/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b") >>> data = p.parse("/somedir/otherdir/hrpt_noaa16_20140210_1004_69022.l1b") >>> print(data) # doctest: +NORMALIZE_WHITESPACE {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': datetime.datetime(2014, 2, 10, 10, 4), 'orbit': 69022} Parsing in trollsift is not "greedy". This means that in the case of ambiguous patterns it will match the shortest portion of the string possible. For example: >>> from trollsift import Parser >>> >>> p = Parser("{field_one}_{field_two}") >>> data = p.parse("abc_def_ghi") >>> print(data) {'field_one': 'abc', 'field_two': 'def_ghi'} So even though the first field could have matched to "abc_def", the non-greedy parsing chose the shorter possible match of "abc". composing ^^^^^^^^^ The reverse operation is called 'compose', and is equivalent to the Python string class format method. Here we take the filename pattern from earlier, change the time stamp of the data, and write out a new file name, >>> from datetime import datetime >>> >>> p = Parser("/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b") >>> data = {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': datetime(2012, 1, 1, 1, 1), 'orbit': 69022} >>> p.compose(data) '/somedir/otherdir/hrpt_noaa16_20120101_0101_69022.l1b' It is also possible to compose only partially, i.e., compose by specifying values for only a subset of the parameters in the format string. Example: >>> p = Parser("/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b") >>> data = {'directory':'my_dir'} >>> p.compose(data, allow_partial=True) '/somedir/my_dir/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b' In addition to python's builtin string formatting functionality trollsift also provides extra conversion options such as making all characters lowercase: >>> my_parser = Parser("{platform_name!l}") >>> my_parser.compose({'platform_name': 'NPP'}) 'npp' For all of the options see :class:`~trollsift.parser.StringFormatter`. standalone parse and compose ---------------------------- The parse and compose methods also exist as standalone functions, depending on your requirements you can call, >>> from trollsift import parse, compose >>> fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b" >>> data = parse( fmt, "/somedir/otherdir/hrpt_noaa16_20140210_1004_69022.l1b" ) >>> data['time'] = datetime(2012, 1, 1, 1, 1) >>> compose(fmt, data) '/somedir/otherdir/hrpt_noaa16_20120101_0101_69022.l1b' And achieve the exact same result as in the Parse object example above. trollsift-0.5.3/pyproject.toml000066400000000000000000000017471472354304100164710ustar00rootroot00000000000000[project] name = "trollsift" description = "String parser/formatter" readme = "README.rst" authors = [ { name = "The Pytroll Team", email = "pytroll@googlegroups.com" } ] classifiers = [ "Development Status :: 5 - Production/Stable", "Intended Audience :: Science/Research", "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)", "Operating System :: OS Independent", "Programming Language :: Python", "Topic :: Scientific/Engineering" ] keywords = ["string parsing", "string formatting", "pytroll"] requires-python = ">=3.9" dependencies = [] dynamic = ["version"] [build-system] requires = ["hatchling", "hatch-vcs"] build-backend = "hatchling.build" [tool.hatch.metadata] allow-direct-references = true [tool.hatch.build.targets.wheel] packages = ["trollsift"] [tool.hatch.version] source = "vcs" [tool.hatch.build.hooks.vcs] version-file = "trollsift/version.py" [tool.coverage.run] relative_files = true omit = ["trollsift/version.py"] trollsift-0.5.3/setup.cfg000066400000000000000000000004601472354304100153650ustar00rootroot00000000000000[metadata] description-file = README.md [bdist_rpm] release=1 [bdist_wheel] universal=1 [flake8] max-line-length = 120 [versioneer] VCS = git style = pep440 versionfile_source = trollsift/version.py versionfile_build = tag_prefix = v [coverage:run] omit = trollsift/version.py versioneer.py trollsift-0.5.3/trollsift/000077500000000000000000000000001472354304100155665ustar00rootroot00000000000000trollsift-0.5.3/trollsift/__init__.py000066400000000000000000000005141472354304100176770ustar00rootroot00000000000000 from .parser import * try: from trollsift.version import version as __version__ # noqa except ModuleNotFoundError: # pragma: no cover raise ModuleNotFoundError( "No module named trollsift.version. This could mean " "you didn't install 'trollsift' properly. Try reinstalling ('pip " "install').") trollsift-0.5.3/trollsift/parser.py000066400000000000000000000632101472354304100174360ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2022 Trollsift Developers # # 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 . """Main parsing and formatting functionality.""" import re import datetime as dt import random import string from functools import lru_cache class Parser(object): """Class-based interface to parsing and formatting functionality.""" def __init__(self, fmt): self.fmt = fmt def __str__(self): return self.fmt def keys(self): """Get parameter names defined in the format string.""" convert_dict = get_convert_dict(self.fmt) return convert_dict.keys() def parse(self, stri, full_match=True): '''Parse keys and corresponding values from *stri* using format described in *fmt* string. ''' return parse(self.fmt, stri, full_match=full_match) def compose(self, keyvals, allow_partial=False): """Compose format string *self.fmt* with parameters given in the *keyvals* dict. Args: keyvals (dict): "Parameter --> parameter value" map allow_partial (bool): If True, then partial composition is allowed, i.e., not all parameters present in `fmt` need to be specified in `keyvals`. Unspecified parameters will, in this case, be left unchanged. (Default value = False). Returns: str: Result of formatting the *self.fmt* string with parameter values extracted from the corresponding items in the *keyvals* dictionary. """ return compose(fmt=self.fmt, keyvals=keyvals, allow_partial=allow_partial) format = compose def globify(self, keyvals=None): '''Generate a string useable with glob.glob() from format string *fmt* and *keyvals* dictionary. ''' return globify(self.fmt, keyvals) def validate(self, stri): """ Validates that string *stri* is parsable and therefore complies with this string format definition. Useful for filtering strings, or to check if a string if compatible before passing it to the parser function. """ return validate(self.fmt, stri) def is_one2one(self): """ Runs a check to evaluate if this format string has a one to one correspondence. I.e. that successive composing and parsing opperations will result in the original data. In other words, that input data maps to a string, which then maps back to the original data without any change or loss in information. Note: This test only applies to sensible usage of the format string. If string or numeric data is causes overflow, e.g. if composing "abcd" into {3s}, one to one correspondence will always be broken in such cases. This off course also applies to precision losses when using datetime data. """ return is_one2one(self.fmt) class StringFormatter(string.Formatter): """Custom string formatter class for basic strings. This formatter adds a few special conversions for assisting with common trollsift situations like making a parameter lowercase or removing hyphens. The added conversions are listed below and can be used in a format string by prefixing them with an `!` like so: >>> fstr = "{!u}_{!l}" >>> formatter = StringFormatter() >>> formatter.format(fstr, "to_upper", "To_LowerCase") "TO_UPPER_to_lowercase" - c: Make capitalized version of string (first character upper case, all lowercase after that) by executing the parameter's `.capitalize()` method. - l: Make all characters lowercase by executing the parameter's `.lower()` method. - R: Remove all separators from the parameter including '-', '_', ' ', and ':'. - t: Title case the string by executing the parameter's `.title()` method. - u: Make all characters uppercase by executing the parameter's `.upper()` method. - h: A combination of 'R' and 'l'. - H: A combination of 'R' and 'u'. """ CONV_FUNCS = { 'c': 'capitalize', 'h': 'lower', 'H': 'upper', 'l': 'lower', 't': 'title', 'u': 'upper' } def convert_field(self, value, conversion): """Apply conversions mentioned above.""" func = self.CONV_FUNCS.get(conversion) if func is not None: value = getattr(value, func)() elif conversion not in ['R']: # default conversion ('r', 's') return super(StringFormatter, self).convert_field(value, conversion) if conversion in ['h', 'H', 'R']: value = value.replace('-', '').replace('_', '').replace(':', '').replace(' ', '') return value formatter = StringFormatter() # taken from https://docs.python.org/3/library/re.html#simulating-scanf spec_regexes = { 'b': r'[-+]?[0-1]', 'c': r'.', 'd': r'[-+]?\d', 'f': { # Naive fixed point format specifier (e.g. {foo:f}) 'naive': r'[-+]?(\d+(\.\d*)?|\.\d+)([eE][-+]?\d+)?', # Fixed point format specifier including width and precision # (e.g. {foo:4.2f}). The lookahead (?=.{width}) makes sure that the # subsequent pattern is only matched if the string has the required # (minimum) width. 'precision': r'(?=.{{{width}}})([-+]?([\d ]+(\.\d{{{decimals}}})+|\.\d{{{decimals}}})([eE][-+]?\d+)?)' }, 'i': r'[-+]?(0[xX][\dA-Fa-f]+|0[0-7]*|\d+)', 'o': r'[-+]?[0-7]', 's': r'\S', 'x': r'[-+]?(0[xX])?[\dA-Fa-f]', } spec_regexes['e'] = spec_regexes['f'] spec_regexes['E'] = spec_regexes['f'] spec_regexes['g'] = spec_regexes['f'] spec_regexes['X'] = spec_regexes['x'] spec_regexes[''] = spec_regexes['s'] allow_multiple = ['b', 'c', 'd', 'o', 's', '', 'x', 'X'] fixed_point_types = ['f', 'e', 'E', 'g'] # format_spec ::= [[fill]align][sign][#][0][width][,][.precision][type] # https://docs.python.org/3.4/library/string.html#format-specification-mini-language fmt_spec_regex = re.compile( r'(?P(?P.)?[<>=^])?(?P[\+\-\s])?(?P#)?(?P0)?(?P\d+)?' r'(?P,)?(?P.\d+)?(?P[bcdeEfFgGnosxX%]?)') def _get_fixed_point_regex(regex_dict, width, precision): """Get regular expression for fixed point numbers. Args: width: Total width of the string representation. precision: Number of decimals. """ if width or precision: if precision is None: precision = '0,' else: precision = precision.strip('.') if width is None: width = '1,' return regex_dict['precision'].format( width=width, decimals=precision) else: return regex_dict['naive'] class RegexFormatter(string.Formatter): """String formatter that converts a format string to a regular expression. >>> regex_formatter = RegexFormatter() >>> regex_str = regex_formatter.format('{field_one:5d}_{field_two}') Can also be used to extract values from a string given the format spec for that string: >>> regex_formatter.extract_values('{field_one:5d}_{field_two}', '12345_sometext') {'field_one': '12345', 'field_two': 'sometext'} Note that the regular expressions generated by this class are specially generated to reduce "greediness" of the matches found. For ambiguous patterns where a single field could match shorter or longer portions of the provided string, this class will prefer the shorter version of the string in order to make the rest of the pattern match. For example: >>> regex_formatter.extract_values('{field_one}_{field_two}', 'abc_def_ghi') {'field_one': 'abc', 'field_two': 'def_ghi'} Note how `field_one` could have matched "abc_def", but the lower greediness of this parser caused it to only match against "abc". """ # special string to mark a parameter not being specified UNPROVIDED_VALUE = '' ESCAPE_CHARACTERS = ['\\'] + [x for x in string.punctuation if x not in '\\%'] ESCAPE_SETS = [(c, '\\' + c) for c in ESCAPE_CHARACTERS] def __init__(self): # hold on to fields we've seen already so we can reuse their # definitions in the regex self._cached_fields = {} super(RegexFormatter, self).__init__() @lru_cache() def format(*args, **kwargs): try: # super() doesn't seem to work here ret_val = string.Formatter.format(*args, **kwargs) finally: self = args[0] # just matching the parent class self._cached_fields.clear() return ret_val def _escape(self, s): """Escape bad characters for regular expressions. Similar to `re.escape` but allows '%' to pass through. """ for ch, r_ch in self.ESCAPE_SETS: s = s.replace(ch, r_ch) return s def parse(self, format_string): parse_ret = super(RegexFormatter, self).parse(format_string) for literal_text, field_name, format_spec, conversion in parse_ret: # the parent class will call parse multiple times moving # 'format_spec' to 'literal_text'. We only escape 'literal_text' # so we don't escape things twice. literal_text = self._escape(literal_text) yield literal_text, field_name, format_spec, conversion def get_value(self, key, args, kwargs): try: return super(RegexFormatter, self).get_value(key, args, kwargs) except (IndexError, KeyError): return key, self.UNPROVIDED_VALUE def _regex_datetime(self, format_spec): replace_str = format_spec for fmt_key, fmt_val in DT_FMT.items(): if fmt_key == '%%': # special case replace_str.replace('%%', '%') continue count = fmt_val.count('?') # either a series of numbers or letters/numbers regex = r'\d{{{:d}}}'.format(count) if count else r'[^ \t\n\r\f\v\-_:]+' replace_str = replace_str.replace(fmt_key, regex) return replace_str @staticmethod def format_spec_to_regex(field_name, format_spec): """Make an attempt at converting a format spec to a regular expression.""" # NOTE: remove escaped backslashes so regex matches regex_match = fmt_spec_regex.match(format_spec.replace('\\', '')) if regex_match is None: raise ValueError("Invalid format specification: '{}'".format(format_spec)) regex_dict = regex_match.groupdict() fill = regex_dict['fill'] ftype = regex_dict['type'] width = regex_dict['width'] align = regex_dict['align'] precision = regex_dict['precision'] # NOTE: does not properly handle `=` alignment if fill is None: if width is not None and width[0] == '0': fill = '0' elif ftype in ['s', '', 'd', 'x', 'X', 'o', 'b']: fill = ' ' char_type = spec_regexes[ftype] if ftype in fixed_point_types: char_type = _get_fixed_point_regex( char_type, width=width, precision=precision ) if ftype in ('s', '') and align and align.endswith('='): raise ValueError("Invalid format specification: '{}'".format(format_spec)) final_regex = char_type if ftype in allow_multiple and (not width or width == '0'): final_regex += r'*?' elif width and width != '0': if not fill and ftype not in fixed_point_types: # we know we have exactly this many characters final_regex += r'{{{}}}'.format(int(width)) elif fill: # we don't know how many fill characters we have compared to # field characters so just match all characters and sort it out # later during type conversion. final_regex = r'.{{{}}}'.format(int(width)) elif ftype in allow_multiple: final_regex += r'*?' return r'(?P<{}>{})'.format(field_name, final_regex) def regex_field(self, field_name, value, format_spec): if value != self.UNPROVIDED_VALUE: return super(RegexFormatter, self).format_field(value, format_spec) if self._cached_fields.get(field_name, format_spec) != format_spec: raise ValueError("Can't specify the same field_name with " "different formats: {}".format(field_name)) elif field_name in self._cached_fields: return r'(?P={})'.format(field_name) else: self._cached_fields[field_name] = format_spec # Replace format spec with glob patterns (*, ?, etc) if not format_spec: return r'(?P<{}>.*?)'.format(field_name) if '%' in format_spec: return r'(?P<{}>{})'.format(field_name, self._regex_datetime(format_spec)) return self.format_spec_to_regex(field_name, format_spec) def format_field(self, value, format_spec): if not isinstance(value, tuple) or value[1] != self.UNPROVIDED_VALUE: return super(RegexFormatter, self).format_field(value, format_spec) field_name, value = value return self.regex_field(field_name, value, format_spec) @lru_cache() def regex_format(fmt): # We create a new instance of RegexFormatter here to prevent concurrent calls to # format interfering with one another. return RegexFormatter().format(fmt) def extract_values(fmt, stri, full_match=True): """Extract information from string matching format. Args: fmt (str): Python format string to match against stri (str): String to extract information from full_match (bool): Force the match of the whole string. Default to ``True``. """ regex = regex_format(fmt) if full_match: regex = '^' + regex + '$' match = re.match(regex, stri) if match is None: raise ValueError("String does not match pattern.") return match.groupdict() def _get_number_from_fmt(fmt): """Helper function for extract_values. Figures out string length from format string. """ if '%' in fmt: # its datetime return len(("{0:" + fmt + "}").format(dt.datetime.now())) else: # its something else fmt = fmt.lstrip('0') return int(re.search('[0-9]+', fmt).group(0)) def _convert(convdef, stri): """Convert the string *stri* to the given conversion definition *convdef*.""" if '%' in convdef: result = dt.datetime.strptime(stri, convdef) else: result = _strip_padding(convdef, stri) if 'd' in convdef: result = int(result) elif 'x' in convdef or 'X' in convdef: result = int(result, 16) elif 'o' in convdef: result = int(result, 8) elif 'b' in convdef: result = int(result, 2) elif any(float_type_marker in convdef for float_type_marker in fixed_point_types): result = float(result) return result def _strip_padding(convdef, stri): """Strip padding from the given string. Args: convdef: Conversion definition (indicates the padding) stri: String to be modified """ regex_match = fmt_spec_regex.match(convdef) match_dict = regex_match.groupdict() if regex_match else {} align = match_dict.get('align') pad = match_dict.get('fill') if align: # align character is the last one align = align[-1] if align and align in '<>^' and not pad: pad = ' ' if align == '>': stri = stri.lstrip(pad) elif align == '<': stri = stri.rstrip(pad) elif align == '^': stri = stri.strip(pad) return stri @lru_cache() def get_convert_dict(fmt): """Retrieve parse definition from the format string `fmt`.""" convdef = {} for literal_text, field_name, format_spec, conversion in formatter.parse(fmt): if field_name is None: continue # XXX: Do I need to include 'conversion'? convdef[field_name] = format_spec return convdef def parse(fmt, stri, full_match=True): """Parse keys and corresponding values from *stri* using format described in *fmt* string. Args: fmt (str): Python format string to match against stri (str): String to extract information from full_match (bool): Force the match of the whole string. Default True. """ convdef = get_convert_dict(fmt) keyvals = extract_values(fmt, stri, full_match=full_match) for key in convdef.keys(): keyvals[key] = _convert(convdef[key], keyvals[key]) return keyvals def compose(fmt, keyvals, allow_partial=False): """Compose format string *self.fmt* with parameters given in the *keyvals* dict. Args: fmt (str): Python format string to match against keyvals (dict): "Parameter --> parameter value" map allow_partial (bool): If True, then partial composition is allowed, i.e., not all parameters present in `fmt` need to be specified in `keyvals`. Unspecified parameters will, in this case, be left unchanged. (Default value = False). Returns: str: Result of formatting the *self.fmt* string with parameter values extracted from the corresponding items in the *keyvals* dictionary. """ if allow_partial: return _partial_compose(fmt=fmt, keyvals=keyvals) return _strict_compose(fmt=fmt, keyvals=keyvals) DT_FMT = { "%a": "*", "%A": "*", "%w": "?", "%d": "??", "%b": "*", "%B": "*", "%m": "??", "%y": "??", "%Y": "????", "%H": "??", "%I": "??", "%p": "*", "%M": "??", "%S": "??", "%f": "*", "%z": "*", "%Z": "*", "%j": "???", "%U": "??", "%W": "??", "%c": "*", "%x": "*", "%X": "*", "%%": "?" } class GlobifyFormatter(string.Formatter): # special string to mark a parameter not being specified UNPROVIDED_VALUE = '' def get_value(self, key, args, kwargs): try: return super(GlobifyFormatter, self).get_value(key, args, kwargs) except (IndexError, KeyError): # assumes that return self.UNPROVIDED_VALUE def format_field(self, value, format_spec): if not isinstance(value, (list, tuple)) and value != self.UNPROVIDED_VALUE: return super(GlobifyFormatter, self).format_field(value, format_spec) elif value != self.UNPROVIDED_VALUE: # partial provided date/time fields # specified with a tuple/list of 2 elements # (value, partial format string) value, dt_fmt = value for fmt_letter in dt_fmt: fmt = '%' + fmt_letter format_spec = format_spec.replace(fmt, value.strftime(fmt)) # Replace format spec with glob patterns (*, ?, etc) if not format_spec: return '*' if '%' in format_spec: replace_str = format_spec for fmt_key, fmt_val in DT_FMT.items(): replace_str = replace_str.replace(fmt_key, fmt_val) return replace_str if not re.search('[0-9]+', format_spec): # non-integer type return '*' return '?' * _get_number_from_fmt(format_spec) globify_formatter = GlobifyFormatter() def globify(fmt, keyvals=None): """Generate a string usable with glob.glob() from format string *fmt* and *keyvals* dictionary. """ if keyvals is None: keyvals = {} return globify_formatter.format(fmt, **keyvals) def validate(fmt, stri): """ Validates that string *stri* is parsable and therefore complies with the format string, *fmt*. Useful for filtering string, or to check if string if compatible before passing the string to the parser function. """ try: parse(fmt, stri) return True except ValueError: return False def _generate_data_for_format(fmt): """Generate a fake data dictionary to fill in the provided format string.""" # finally try some data, create some random data for the fmt. data = {} # keep track of how many "free_size" (wildcard) parameters we have # if we get two in a row then we know the pattern is invalid, meaning # we'll never be able to match the second wildcard field free_size_start = False for literal_text, field_name, format_spec, conversion in formatter.parse(fmt): if literal_text: free_size_start = False if not field_name: free_size_start = False continue # encapsulating free size keys, # e.g. {:s}{:s} or {:s}{:4s}{:d} if not format_spec or format_spec == "s" or format_spec == "d": if free_size_start: return None else: free_size_start = True # make some data for this key and format if format_spec and '%' in format_spec: # some datetime t = dt.datetime.now() # run once through format to limit precision t = parse( "{t:" + format_spec + "}", compose("{t:" + format_spec + "}", {'t': t}))['t'] data[field_name] = t elif format_spec and 'd' in format_spec: # random number (with n sign. figures) if not format_spec.isalpha(): n = _get_number_from_fmt(format_spec) else: # clearly bad return None data[field_name] = random.randint(0, 99999999999999999) % (10 ** n) else: # string type if format_spec is None: n = 4 elif format_spec.isalnum(): n = _get_number_from_fmt(format_spec) else: n = 4 randstri = '' for x in range(n): randstri += random.choice(string.ascii_letters) data[field_name] = randstri return data def is_one2one(fmt): """ Runs a check to evaluate if the format string has a one to one correspondence. I.e. that successive composing and parsing opperations will result in the original data. In other words, that input data maps to a string, which then maps back to the original data without any change or loss in information. Note: This test only applies to sensible usage of the format string. If string or numeric data is causes overflow, e.g. if composing "abcd" into {3s}, one to one correspondence will always be broken in such cases. This of course also applies to precision losses when using datetime data. """ data = _generate_data_for_format(fmt) if data is None: return False # run data forward once and back to data stri = compose(fmt, data) data2 = parse(fmt, stri) # check if data2 equal to original data if len(data) != len(data2): return False for key in data: if key not in data2: return False if data2[key] != data[key]: return False # all checks passed, so just return True return True def purge(): """Clear internal caches. Not needed normally, but can be used to force cache clear when memory is very limited. """ regex_format.cache_clear() get_convert_dict.cache_clear() def _strict_compose(fmt, keyvals): """Convert parameters in `keyvals` to a string based on `fmt` string.""" return formatter.format(fmt, **keyvals) def _partial_compose(fmt, keyvals): """Convert parameters in `keyvals` to a string based on `fmt` string. Similar to _strict_compose, but accepts partial composing, i.e., not all parameters in `fmt` need to be specified in `keyvals`. Unspecified parameters are left unchanged. Args: fmt (str): Python format string to match against keyvals (dict): "Parameter --> parameter value" map """ fmt, undefined_vars = _replace_undefined_params_with_placeholders(fmt, keyvals) composed_string = _strict_compose(fmt=fmt, keyvals=keyvals) for fmt_placeholder, fmt_specification in undefined_vars.items(): composed_string = composed_string.replace(fmt_placeholder, fmt_specification) return composed_string def _replace_undefined_params_with_placeholders(fmt, keyvals=None): """Replace with placeholders params in `fmt` not specified in `keyvals`.""" vars_left_undefined = get_convert_dict(fmt).keys() if keyvals is not None: vars_left_undefined -= keyvals.keys() undefined_vars_placeholders_dict = {} new_fmt = fmt for var in sorted(vars_left_undefined): matches = set( match.group() for match in re.finditer(rf"{{{re.escape(var)}([^\w{{}}].*?)*}}", new_fmt) ) if len(matches) == 0: raise ValueError(f"Could not capture definitions for {var} from {fmt}") for var_specification in matches: fmt_placeholder = f"({hex(hash(var_specification))})" undefined_vars_placeholders_dict[fmt_placeholder] = var_specification new_fmt = new_fmt.replace(var_specification, fmt_placeholder) return new_fmt, undefined_vars_placeholders_dict trollsift-0.5.3/trollsift/tests/000077500000000000000000000000001472354304100167305ustar00rootroot00000000000000trollsift-0.5.3/trollsift/tests/__init__.py000066400000000000000000000000561472354304100210420ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- trollsift-0.5.3/trollsift/tests/integrationtests/000077500000000000000000000000001472354304100223365ustar00rootroot00000000000000trollsift-0.5.3/trollsift/tests/integrationtests/__init__.py000066400000000000000000000014051472354304100244470ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2020 Panu Lahtinen # # 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 . """Integration tests for the trollsift package.""" trollsift-0.5.3/trollsift/tests/integrationtests/test_parser.py000066400000000000000000000140501472354304100252430ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2020 Martin Raspaud # # 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 . """Parser integration tests.""" import os import unittest import datetime as dt from trollsift.parser import Parser class TestParser(unittest.TestCase): def setUp(self): self.fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}" +\ "_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b" self.string = "/somedir/otherdir/hrpt_noaa16_20140210_1004_69022.l1b" self.data = {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': dt.datetime(2014, 2, 10, 10, 4), 'orbit': 69022} self.p = Parser(self.fmt) def test_parse(self): # Run result = self.p.parse(self.string) # Assert self.assertDictEqual(result, self.data) def test_cache_clear(self): """Test we can clear the internal cache properly""" from trollsift.parser import purge, regex_format # Run result = self.p.parse(self.string) # Assert self.assertDictEqual(result, self.data) assert regex_format.cache_info()[-1] != 0 purge() assert regex_format.cache_info()[-1] == 0 def test_compose(self): # Run result = self.p.compose(self.data) # Assert self.assertEqual(result, self.string) def test_validate(self): # These cases are True self.assertTrue( self.p.validate("/somedir/avhrr/2014/hrpt_noaa19_20140212_1412_12345.l1b")) # These cases are False self.assertFalse( self.p.validate("/somedir/bla/bla/hrpt_noaa19_20140212__1412_00000.l1b")) def assertDictEqual(self, a, b): for key in a: self.assertTrue(key in b) self.assertEqual(a[key], b[key]) self.assertEqual(len(a), len(b)) def assertItemsEqual(self, a, b): for i in range(len(a)): if isinstance(a[i], dict): self.assertDictEqual(a[i], b[i]) else: self.assertEqual(a[i], b[i]) self.assertEqual(len(a), len(b)) class TestParserVariousFormats(unittest.TestCase): def test_parse_viirs_sdr(self): fmt = 'SVI01_{platform_shortname}_d{start_time:%Y%m%d_t%H%M%S%f}_e{end_time:%H%M%S%f}_b{orbit:5d}_c{creation_time:%Y%m%d%H%M%S%f}_{source}.h5' filename = 'SVI01_npp_d20120225_t1801245_e1802487_b01708_c20120226002130255476_noaa_ops.h5' data = {'platform_shortname': 'npp', 'start_time': dt.datetime(2012, 2, 25, 18, 1, 24, 500000), 'orbit': 1708, 'end_time': dt.datetime(1900, 1, 1, 18, 2, 48, 700000), 'source': 'noaa_ops', 'creation_time': dt.datetime(2012, 2, 26, 0, 21, 30, 255476)} p = Parser(fmt) result = p.parse(filename) self.assertDictEqual(result, data) def test_parse_iasi_l2(self): fmt = "W_XX-EUMETSAT-{reception_location},{instrument},{long_platform_id}+{processing_location}_C_EUMS_{processing_time:%Y%m%d%H%M%S}_IASI_PW3_02_{platform_id}_{start_time:%Y%m%d-%H%M%S}Z_{end_time:%Y%m%d.%H%M%S}Z.hdf" filename = "W_XX-EUMETSAT-kan,iasi,metopb+kan_C_EUMS_20170920103559_IASI_PW3_02_M01_20170920-102217Z_20170920.102912Z.hdf" data = {'reception_location': 'kan', 'instrument': 'iasi', 'long_platform_id': 'metopb', 'processing_location': 'kan', 'processing_time': dt.datetime(2017, 9, 20, 10, 35, 59), 'platform_id': 'M01', 'start_time': dt.datetime(2017, 9, 20, 10, 22, 17), 'end_time': dt.datetime(2017, 9, 20, 10, 29, 12)} p = Parser(fmt) result = p.parse(filename) self.assertDictEqual(result, data) def test_parse_olci_l1b(self): fmt = os.path.join( "{mission_id:3s}_OL_1_{datatype_id:_<6s}_{start_time:%Y%m%dT%H%M%S}_" "{end_time:%Y%m%dT%H%M%S}_{creation_time:%Y%m%dT%H%M%S}_{duration:4d}_" "{cycle:3d}_{relative_orbit:3d}_{frame:4d}_{centre:3s}_{platform_mode:1s}_" "{timeliness:2s}_{collection:3s}.SEN3", "{dataset_name}_radiance.nc") # made up: filename = os.path.join( "S3A_OL_1_EFR____20180916T090539_" "20180916T090839_20180916T090539_0001_" "001_001_0001_CEN_M_" "AA_AAA.SEN3", "Oa21_radiance.nc") data = {'mission_id': 'S3A', 'datatype_id': 'EFR', 'start_time': dt.datetime(2018, 9, 16, 9, 5, 39), 'end_time': dt.datetime(2018, 9, 16, 9, 8, 39), 'creation_time': dt.datetime(2018, 9, 16, 9, 5, 39), 'duration': 1, 'cycle': 1, 'relative_orbit': 1, 'frame': 1, 'centre': 'CEN', 'platform_mode': 'M', 'timeliness': 'AA', 'collection': 'AAA', 'dataset_name': 'Oa21', } p = Parser(fmt) result = p.parse(filename) self.assertDictEqual(result, data) def test_parse_duplicate_fields(self): """Test parsing a pattern that has duplicate fields.""" fmt = '{version_number:1s}/filename_with_version_number_{version_number:1s}.tif' filename = '1/filename_with_version_number_1.tif' p = Parser(fmt) result = p.parse(filename) self.assertEqual(result['version_number'], '1') trollsift-0.5.3/trollsift/tests/regressiontests/000077500000000000000000000000001472354304100221735ustar00rootroot00000000000000trollsift-0.5.3/trollsift/tests/regressiontests/__init__.py000066400000000000000000000014071472354304100243060ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2020 Martin Raspaud # # 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 . """Regression tests for the trollsift package.""" trollsift-0.5.3/trollsift/tests/regressiontests/test_parser.py000066400000000000000000000023441472354304100251030ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2020 Martin Raspaud # # 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 . """Parser regression tests.""" import unittest import datetime as dt from trollsift.parser import parse class TestParser(unittest.TestCase): def test_002(self): res = parse('hrpt16_{satellite:7s}_{start_time:%d-%b-%Y_%H:%M:%S.000}_{orbit_number:5d}', "hrpt16_NOAA-19_26-NOV-2014_10:12:00.000_29889") self.assertEqual(res, {'orbit_number': 29889, 'satellite': 'NOAA-19', 'start_time': dt.datetime(2014, 11, 26, 10, 12)}) trollsift-0.5.3/trollsift/tests/unittests/000077500000000000000000000000001472354304100207725ustar00rootroot00000000000000trollsift-0.5.3/trollsift/tests/unittests/__init__.py000066400000000000000000000013761472354304100231120ustar00rootroot00000000000000#!/usr/bin/env python # -*- coding: utf-8 -*- # # Copyright (c) 2014-2020 Panu Lahtinen # # 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 . """Unit tests for the trollsift package.""" trollsift-0.5.3/trollsift/tests/unittests/test_parser.py000066400000000000000000000525151472354304100237070ustar00rootroot00000000000000import unittest import datetime as dt import pytest from trollsift.parser import get_convert_dict, extract_values from trollsift.parser import _convert from trollsift.parser import parse, globify, validate, is_one2one, compose, Parser class TestParser(unittest.TestCase): def setUp(self): self.fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}" +\ "_{time:%Y%m%d_%H%M}_{orbit:05d}.l1b" self.string = "/somedir/otherdir/hrpt_noaa16_20140210_1004_69022.l1b" self.string2 = "/somedir/otherdir/hrpt_noaa16_20140210_1004_00022.l1b" self.string3 = "/somedir/otherdir/hrpt_noaa16_20140210_1004_69022" self.string4 = "/somedir/otherdir/hrpt_noaa16_20140210_1004_69022" def test_parser_keys(self): parser = Parser(self.fmt) keys = {"directory", "platform", "platnum", "time", "orbit"} self.assertTrue(keys.issubset(parser.keys()) and keys.issuperset(parser.keys())) def test_get_convert_dict(self): # Run result = get_convert_dict(self.fmt) # Assert self.assertDictEqual(result, { 'directory': '', 'platform': '4s', 'platnum': '2s', 'time': '%Y%m%d_%H%M', 'orbit': '05d', }) def test_extract_values(self): fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:d}.l1b" result = extract_values(fmt, self.string) self.assertDictEqual(result, {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '69022'}) def test_extract_values_end(self): fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:d}" result = extract_values(fmt, self.string3) self.assertDictEqual(result, {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '69022'}) def test_extract_values_beginning(self): fmt = "{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:d}" result = extract_values(fmt, self.string4) self.assertDictEqual(result, {'directory': '/somedir/otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '69022'}) def test_extract_values_s4spair(self): fmt = "{directory}/hrpt_{platform:4s}{platnum:s}_{time:%Y%m%d_%H%M}_{orbit:d}" result = extract_values(fmt, self.string4) self.assertDictEqual(result, {'directory': '/somedir/otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '69022'}) def test_extract_values_ss2pair(self): fmt = "{directory}/hrpt_{platform:s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:d}" result = extract_values(fmt, self.string4) self.assertDictEqual(result, {'directory': '/somedir/otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '69022'}) def test_extract_values_ss2pair_end(self): fmt = "{directory}/hrpt_{platform:s}{platnum:2s}" result = extract_values(fmt, "/somedir/otherdir/hrpt_noaa16") self.assertDictEqual(result, {'directory': '/somedir/otherdir', 'platform': 'noaa', 'platnum': '16'}) def test_extract_values_sdatetimepair_end(self): fmt = "{directory}/hrpt_{platform:s}{date:%Y%m%d}" result = extract_values(fmt, "/somedir/otherdir/hrpt_noaa20140212") self.assertDictEqual(result, {'directory': '/somedir/otherdir', 'platform': 'noaa', 'date': '20140212'}) def test_extract_values_everything(self): fmt = "{everything}" result = extract_values(fmt, self.string) self.assertDictEqual( result, {'everything': '/somedir/otherdir/hrpt_noaa16_20140210_1004_69022.l1b'}) def test_extract_values_padding2(self): fmt = "/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:0>5d}.l1b" # parsedef = ['/somedir/', {'directory': None}, '/hrpt_', # {'platform': '4s'}, {'platnum': '2s'}, # '_', {'time': '%Y%m%d_%H%M'}, '_', # {'orbit': '0>5d'}, '.l1b'] result = extract_values(fmt, self.string2) # Assert self.assertDictEqual(result, {'directory': 'otherdir', 'platform': 'noaa', 'platnum': '16', 'time': '20140210_1004', 'orbit': '00022'}) def test_extract_values_fails(self): fmt = '/somedir/{directory}/hrpt_{platform:4s}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:4d}.l1b' self.assertRaises(ValueError, extract_values, fmt, self.string) def test_extract_values_full_match(self): """Test that a string must completely match.""" fmt = '{orbit:05d}' val = extract_values(fmt, '12345') self.assertEqual(val, {'orbit': '12345'}) self.assertRaises(ValueError, extract_values, fmt, '12345abc') val = extract_values(fmt, '12345abc', full_match=False) self.assertEqual(val, {'orbit': '12345'}) def test_convert_digits(self): self.assertEqual(_convert('d', '69022'), 69022) self.assertRaises(ValueError, _convert, 'd', '69dsf') self.assertEqual(_convert('d', '00022'), 22) self.assertEqual(_convert('4d', '69022'), 69022) self.assertEqual(_convert('_>10d', '_____69022'), 69022) self.assertEqual(_convert('%Y%m%d_%H%M', '20140210_1004'), dt.datetime(2014, 2, 10, 10, 4)) def test_parse(self): # Run result = parse( self.fmt, "/somedir/avhrr/2014/hrpt_noaa19_20140212_1412_12345.l1b") # Assert self.assertDictEqual(result, {'directory': 'avhrr/2014', 'platform': 'noaa', 'platnum': '19', 'time': dt.datetime(2014, 2, 12, 14, 12), 'orbit': 12345}) def test_parse_string_padding_syntax_with_and_without_s(self): """Test that, in string padding syntax, '' is equivalent to 's'. From : * Type 's': String format. This is the default type for strings and may be omitted. * Type None: The same as 's'. """ result = parse('{foo}/{bar:_<8}', 'baz/qux_____') expected_result = parse('{foo}/{bar:_<8s}', 'baz/qux_____') self.assertEqual(expected_result["foo"], "baz") self.assertEqual(expected_result["bar"], "qux") self.assertEqual(result, expected_result) def test_parse_wildcards(self): # Run result = parse( "hrpt_{platform}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}{ext}", "hrpt_noaa19_20140212_1412_12345.l1b") # Assert self.assertDictEqual(result, {'platform': 'noaa', 'platnum': '19', 'time': dt.datetime(2014, 2, 12, 14, 12), 'orbit': 12345, 'ext': '.l1b'}) def test_parse_align(self): filepattern="H-000-{hrit_format:4s}__-{platform_name:4s}________-{channel_name:_<9s}-{segment:_<9s}-{start_time:%Y%m%d%H%M}-__" result = parse(filepattern, "H-000-MSG3__-MSG3________-IR_039___-000007___-201506051700-__") self.assertDictEqual(result, {'channel_name': 'IR_039', 'hrit_format': 'MSG3', 'platform_name': 'MSG3', 'segment': '000007', 'start_time': dt.datetime(2015, 6, 5, 17, 0)}) def test_parse_digits(self): """Test when a digit field is shorter than the format spec.""" result = parse( "hrpt_{platform}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:05d}{ext}", "hrpt_noaa19_20140212_1412_02345.l1b") self.assertDictEqual(result, {'platform': 'noaa', 'platnum': '19', 'time': dt.datetime(2014, 2, 12, 14, 12), 'orbit': 2345, 'ext': '.l1b'}) result = parse( "hrpt_{platform}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:5d}{ext}", "hrpt_noaa19_20140212_1412_ 2345.l1b") self.assertDictEqual(result, {'platform': 'noaa', 'platnum': '19', 'time': dt.datetime(2014, 2, 12, 14, 12), 'orbit': 2345, 'ext': '.l1b'}) result = parse( "hrpt_{platform}{platnum:2s}_{time:%Y%m%d_%H%M}_{orbit:_>5d}{ext}", "hrpt_noaa19_20140212_1412___345.l1b") self.assertDictEqual(result, {'platform': 'noaa', 'platnum': '19', 'time': dt.datetime(2014, 2, 12, 14, 12), 'orbit': 345, 'ext': '.l1b'}) def test_parse_bad_pattern(self): """Test when a digit field is shorter than the format spec.""" self.assertRaises(ValueError, parse, "hrpt_{platform}{platnum:-=2s}_{time:%Y%m%d_%H%M}_{orbit:05d}{ext}", "hrpt_noaa19_20140212_1412_02345.l1b") def test_globify_simple(self): # Run result = globify('{a}_{b}.end', {'a': 'a', 'b': 'b'}) # Assert self.assertEqual(result, 'a_b.end') def test_globify_empty(self): # Run result = globify('{a}_{b:4d}.end', {}) # Assert self.assertEqual(result, '*_????.end') def test_globify_noarg(self): # Run result = globify('{a}_{b:4d}.end') # Assert self.assertEqual(result, '*_????.end') def test_globify_known_lengths(self): # Run result = globify('{directory}/{platform:4s}{satnum:2d}/{orbit:05d}', {'directory': 'otherdir', 'platform': 'noaa'}) # Assert self.assertEqual(result, 'otherdir/noaa??/?????') def test_globify_unknown_lengths(self): # Run result = globify('hrpt_{platform_and_num}_' + '{date}_{time}_{orbit}.l1b', {'platform_and_num': 'noaa16'}) # Assert self.assertEqual(result, 'hrpt_noaa16_*_*_*.l1b') def test_globify_datetime(self): # Run result = globify('hrpt_{platform}{satnum}_' + '{time:%Y%m%d_%H%M}_{orbit}.l1b', {'platform': 'noaa', 'time': dt.datetime(2014, 2, 10, 12, 12)}) # Assert self.assertEqual(result, 'hrpt_noaa*_20140210_1212_*.l1b') def test_globify_partial_datetime(self): # Run result = globify('hrpt_{platform:4s}{satnum:2d}_' + '{time:%Y%m%d_%H%M}_{orbit}.l1b', {'platform': 'noaa', 'time': (dt.datetime(2014, 2, 10, 12, 12), 'Ymd')}) # Assert self.assertEqual(result, 'hrpt_noaa??_20140210_????_*.l1b') def test_globify_datetime_nosub(self): # Run result = globify('hrpt_{platform:4s}{satnum:2d}_' + '{time:%Y%m%d_%H%M}_{orbit}.l1b', {'platform': 'noaa'}) # Assert self.assertEqual(result, 'hrpt_noaa??_????????_????_*.l1b') def test_validate(self): # These cases are True self.assertTrue( validate(self.fmt, "/somedir/avhrr/2014/hrpt_noaa19_20140212_1412_12345.l1b")) self.assertTrue( validate(self.fmt, "/somedir/avhrr/2014/hrpt_noaa01_19790530_0705_00000.l1b")) self.assertTrue(validate( self.fmt, "/somedir/funny-char$dir/hrpt_noaa19_20140212_1412_12345.l1b")) self.assertTrue( validate(self.fmt, "/somedir//hrpt_noaa19_20140212_1412_12345.l1b")) # These cases are False self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_20140212_1412_1A345.l1b")) self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_2014021_1412_00000.l1b")) self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_20140212__412_00000.l1b")) self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_20140212__1412_00000.l1b")) self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_20140212_1412_00000.l1")) self.assertFalse( validate(self.fmt, "/somedir/bla/bla/hrpt_noaa19_20140212_1412_00000")) self.assertFalse( validate(self.fmt, "{}/somedir/bla/bla/hrpt_noaa19_20140212_1412_00000.l1b")) def test_is_one2one(self): # These cases are True self.assertTrue(is_one2one( "/somedir/{directory}/somedata_{platform:4s}_{time:%Y%d%m-%H%M}_{orbit:5d}.l1b")) # These cases are False self.assertFalse(is_one2one( "/somedir/{directory}/somedata_{platform:4s}_{time:%Y%d%m-%H%M}_{orbit:d}.l1b")) def test_greediness(self): """Test that the minimum match is parsed out. See GH #18. """ from trollsift import parse template = '{band_type}_{polarization_extracted}_{unit}_{s1_fname}' fname = 'Amplitude_VH_db_S1A_IW_GRDH_1SDV_20160528T171628_20160528T171653_011462_011752_0EED.tif' res_dict = parse(template, fname) exp = { 'band_type': 'Amplitude', 'polarization_extracted': 'VH', 'unit': 'db', 's1_fname': 'S1A_IW_GRDH_1SDV_20160528T171628_20160528T171653_011462_011752_0EED.tif', } self.assertEqual(exp, res_dict) template = '{band_type:s}_{polarization_extracted}_{unit}_{s1_fname}' res_dict = parse(template, fname) self.assertEqual(exp, res_dict) class TestCompose: """Test routines related to `compose` methods.""" @pytest.mark.parametrize('allow_partial', [False, True]) def test_compose(self, allow_partial): """Test the compose method's custom conversion options.""" key_vals = {"a": "this Is A-Test b_test c test"} new_str = compose("{a!c}", key_vals, allow_partial=allow_partial) assert new_str == "This is a-test b_test c test" new_str = compose("{a!h}", key_vals, allow_partial=allow_partial) assert new_str == "thisisatestbtestctest" new_str = compose("{a!H}", key_vals, allow_partial=allow_partial) assert new_str == "THISISATESTBTESTCTEST" new_str = compose("{a!l}", key_vals, allow_partial=allow_partial) assert new_str == "this is a-test b_test c test" new_str = compose("{a!R}", key_vals, allow_partial=allow_partial) assert new_str == "thisIsATestbtestctest" new_str = compose("{a!t}", key_vals, allow_partial=allow_partial) assert new_str == "This Is A-Test B_Test C Test" new_str = compose("{a!u}", key_vals, allow_partial=allow_partial) assert new_str == "THIS IS A-TEST B_TEST C TEST" # builtin repr new_str = compose("{a!r}", key_vals, allow_partial=allow_partial) assert new_str == "'this Is A-Test b_test c test'" # no formatting new_str = compose("{a}", key_vals, allow_partial=allow_partial) assert new_str == "this Is A-Test b_test c test" # bad formatter with pytest.raises(ValueError): new_str = compose("{a!X}", key_vals, allow_partial=allow_partial) assert new_str == "this Is A-Test b_test c test" def test_default_compose_is_strict(self): """Make sure the default compose call does not accept partial composition.""" fmt = "{foo}_{bar}.qux" with pytest.raises(KeyError): _ = compose(fmt, {"foo": "foo"}) def test_partial_compose_simple(self): """Test partial compose with a simple use case.""" fmt = "{variant:s}/{platform_name}_{start_time:%Y%m%d_%H%M}_{product}.{format}" composed = compose( fmt=fmt, keyvals={"platform_name": "foo", "format": "bar"}, allow_partial=True ) assert composed == "{variant:s}/foo_{start_time:%Y%m%d_%H%M}_{product}.bar" def test_partial_compose_with_similarly_named_params(self): """Test that partial compose handles well vars with common substrings in name.""" original_fmt = "{foo}{afooo}{fooo}.{bar}/{baz:%Y}/{baz:%Y%m%d_%H}/{baz:%Y}/{bar:d}" composed = compose(fmt=original_fmt, keyvals={"afooo": "qux"}, allow_partial=True) assert composed == "{foo}qux{fooo}.{bar}/{baz:%Y}/{baz:%Y%m%d_%H}/{baz:%Y}/{bar:d}" def test_partial_compose_repeated_vars_with_different_formatting(self): """Test partial compose with a fmt with repeated vars with different formatting.""" fmt = "/foo/{start_time:%Y%m}/bar/{baz}_{start_time:%Y%m%d_%H%M}.{format}" composed = compose(fmt=fmt, keyvals={"format": "qux"}, allow_partial=True) assert composed == "/foo/{start_time:%Y%m}/bar/{baz}_{start_time:%Y%m%d_%H%M}.qux" @pytest.mark.parametrize( 'original_fmt', ["{}_{}", "{foo}{afooo}{fooo}.{bar}/{baz:%Y}/{baz:%Y%m%d_%H}/{baz:%Y}/{bar:d}"] ) def test_partial_compose_is_identity_with_empty_keyvals(self, original_fmt): """Test that partial compose leaves the input untouched if no keyvals at all.""" assert compose(fmt=original_fmt, keyvals={}, allow_partial=True) == original_fmt def test_that_some_invalid_fmt_can_confuse_partial_compose(self): """Test that a fmt with a weird char can confuse partial compose.""" fmt = "{foo?}_{bar}_{foo}.qux" with pytest.raises(ValueError): _ = compose(fmt=fmt, keyvals={}, allow_partial=True) class TestParserFixedPoint: """Test parsing of fixed point numbers.""" @pytest.mark.parametrize('allow_partial_compose', [False, True]) @pytest.mark.parametrize( ('fmt', 'string', 'expected'), [ # Naive ('{foo:f}', '12.34', 12.34), # Including width and precision ('{foo:5.2f}', '12.34', 12.34), ('{foo:5.2f}', '-1.23', -1.23), ('{foo:5.2f}', '12.34', 12.34), ('{foo:5.2f}', '123.45', 123.45), # Whitespace padded ('{foo:5.2f}', ' 1.23', 1.23), ('{foo:5.2f}', ' 12.34', 12.34), # Zero padded ('{foo:05.2f}', '01.23', 1.23), ('{foo:05.2f}', '012.34', 12.34), # Only precision, no width ('{foo:.2f}', '12.34', 12.34), # Only width, no precision ('{foo:16f}', ' 1.12', 1.12), # No digits before decimal point ('{foo:3.2f}', '.12', 0.12), ('{foo:4.2f}', '-.12', -0.12), ('{foo:4.2f}', ' .12', 0.12), ('{foo:4.2f}', ' .12', 0.12), ('{foo:16f}', ' .12', 0.12), # Exponential format ('{foo:7.2e}', '-1.23e4', -1.23e4) ] ) def test_match(self, allow_partial_compose, fmt, string, expected): """Test cases expected to be matched.""" # Test parsed value parsed = parse(fmt, string) assert parsed['foo'] == expected # Test round trip composed = compose(fmt, {'foo': expected}, allow_partial=allow_partial_compose) parsed = parse(fmt, composed) assert parsed['foo'] == expected @pytest.mark.parametrize( ('fmt', 'string'), [ # Decimals incorrect ('{foo:5.2f}', '12345'), ('{foo:5.2f}', '1234.'), ('{foo:5.2f}', '1.234'), ('{foo:5.2f}', '123.4'), ('{foo:.2f}', '12.345'), # Decimals correct, but width too short ('{foo:5.2f}', '1.23'), ('{foo:5.2f}', '.23'), ('{foo:10.2e}', '1.23e4'), # Invalid ('{foo:5.2f}', '12_34'), ('{foo:5.2f}', 'aBcD'), ] ) def test_no_match(self, fmt, string): """Test cases expected to not be matched.""" with pytest.raises(ValueError): parse(fmt, string) @pytest.mark.parametrize( ('fmt', 'string', 'expected'), [ # Decimal ("{foo:d}", "123", 123), # Hex with small letter ("{foo:x}", "7b", 123), # Hex with big letter ("{foo:X}", "7B", 123), # Fixed length hex ("{foo:03x}", "07b", 123), ("{foo:3x}", " 7b", 123), ("{foo:3X}", " 7B", 123), # Octal ("{foo:o}", "173", 123), # Free size with octal ("{bar:s}{foo:o}", "something173", 123), # Fixed length with octal ("{foo:_>4o}", "_173", 123), ("{foo:4o}", " 173", 123), # Binary ("{foo:b}", "1111011", 123), # Fixed length with binary ("{foo:8b}", " 1111011", 123), ("{foo:_>8b}", "_1111011", 123), ] ) def test_parse_integers(fmt, string, expected): assert parse(fmt, string)["foo"] == expected