diff --git a/.cruft.json b/.cruft.json new file mode 100644 index 0000000..4f23039 --- /dev/null +++ b/.cruft.json @@ -0,0 +1,20 @@ +{ + "template": "https://github.com/PrefectHQ/prefect-collection-template", + "commit": "e11a3be195f24f60ed3f564dfccb40170ee7c3fa", + "checkout": null, + "context": { + "cookiecutter": { + "full_name": "Arcyl Data", + "email": "shubham.jagtap@gslab.com", + "github_organization": "PrefectHQ", + "collection_name": "prefect-datahub", + "collection_slug": "prefect_datahub", + "collection_short_description": "Metadata emitter for datahub", + "_copy_without_render": [ + ".github/workflows/*.yml" + ], + "_template": "https://github.com/PrefectHQ/prefect-collection-template" + } + }, + "directory": null +} diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc49a45 --- /dev/null +++ b/.gitattributes @@ -0,0 +1 @@ +prefect_datahub/_version.py export-subst diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS new file mode 100644 index 0000000..e69de29 diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md new file mode 100644 index 0000000..f0ac91d --- /dev/null +++ b/.github/ISSUE_TEMPLATE.md @@ -0,0 +1,7 @@ + + +# Expectation / Proposal + +# Traceback / Example + +- [ ] I would like to [help contribute](https://shubhamjagtap639.github.io/prefect-datahub/#contributing) a pull request to resolve this! diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..9230c80 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,28 @@ + + + + +Closes + +### Example + + +### Screenshots + + +### Checklist + + +- [ ] References any related issue by including "Closes #" or "Closes ". + - If no issue exists and your change is not a small fix, please [create an issue](https://github.com/shubhamjagtap639/prefect-datahub/issues/new/choose) first. +- [ ] Includes tests or only affects documentation. +- [ ] Passes `pre-commit` checks. + - Run `pre-commit install && pre-commit run --all` locally for formatting and linting. +- [ ] Includes screenshots of documentation updates. + - Run `mkdocs serve` view documentation locally. +- [ ] Summarizes PR's changes in [CHANGELOG.md](https://github.com/shubhamjagtap639/prefect-datahub/blob/main/CHANGELOG.md) diff --git a/.github/codeql-config.yml b/.github/codeql-config.yml new file mode 100644 index 0000000..d64f1cc --- /dev/null +++ b/.github/codeql-config.yml @@ -0,0 +1,4 @@ +paths-ignore: + - tests/**/test_*.py + - versioneer.py + - prefect_datahub/_version.py \ No newline at end of file diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..653b05d --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,12 @@ +version: 2 +updates: + + - package-ecosystem: "pip" + directory: "/" + schedule: + interval: "daily" + + - package-ecosystem: "github-actions" + directory: "/" + schedule: + interval: "daily" \ No newline at end of file diff --git a/.github/workflows/add-to-project.yml b/.github/workflows/add-to-project.yml new file mode 100644 index 0000000..08c201d --- /dev/null +++ b/.github/workflows/add-to-project.yml @@ -0,0 +1,24 @@ +name: Add issues to integrations board + +on: + issues: + types: + - opened + +jobs: + + add-to-project: + name: Add issue to project + runs-on: ubuntu-latest + steps: + - uses: tibdex/github-app-token@v1 + id: generate-token + name: Generate GitHub token + with: + app_id: ${{ secrets.SYNC_APP_ID }} + private_key: ${{ secrets.SYNC_APP_PRIVATE_KEY }} + + - uses: actions/add-to-project@v0.4.0 + with: + project-url: ${{ secrets.ADD_TO_PROJECT_URL }} + github-token: ${{ steps.generate-token.outputs.token }} diff --git a/.github/workflows/codeql-analysis.yml b/.github/workflows/codeql-analysis.yml new file mode 100644 index 0000000..fde50b6 --- /dev/null +++ b/.github/workflows/codeql-analysis.yml @@ -0,0 +1,35 @@ +name: CodeQL + +on: + push: + branches: + - main + +jobs: + analyze: + name: Analyze + runs-on: ubuntu-latest + permissions: + actions: read + contents: read + security-events: write + + strategy: + fail-fast: false + matrix: + language: + - python + + steps: + - name: Checkout repository + uses: actions/checkout@v3 + + - name: Initialize CodeQL + uses: github/codeql-action/init@v2 + with: + languages: ${{ matrix.language }} + config-file: ./.github/codeql-config.yml + queries: security-and-quality + + - name: Perform CodeQL Analysis + uses: github/codeql-action/analyze@v2 diff --git a/.github/workflows/nightly-dev-tests.yml b/.github/workflows/nightly-dev-tests.yml new file mode 100644 index 0000000..d471925 --- /dev/null +++ b/.github/workflows/nightly-dev-tests.yml @@ -0,0 +1,38 @@ +name: Nightly tests against Prefect's main branch +on: + schedule: + - cron: "0 6 * * *" + workflow_dispatch: + +jobs: + submit-update-pr: + name: Run tests against Prefect's main branch + runs-on: ubuntu-latest + strategy: + matrix: + python-version: + - "3.7" + - "3.8" + - "3.9" + - "3.10" + fail-fast: false + steps: + - uses: actions/checkout@v3 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + cache: pip + cache-dependency-path: requirements*.txt + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + python -m pip install --upgrade --upgrade-strategy eager -e ".[dev]" "prefect @ git+https://github.com/PrefectHQ/prefect.git@main" + + - name: Run tests + env: + PREFECT_API_DATABASE_CONNECTION_URL: "sqlite+aiosqlite:///./collection-tests.db" + run: | + pytest tests -vv \ No newline at end of file diff --git a/.github/workflows/publish-docs.yml b/.github/workflows/publish-docs.yml new file mode 100644 index 0000000..10166bd --- /dev/null +++ b/.github/workflows/publish-docs.yml @@ -0,0 +1,31 @@ +name: Publish docs + +on: + workflow_dispatch + +jobs: + build-and-publish-docs: + name: Build and publish docs + runs-on: ubuntu-latest + + steps: + - uses: actions/checkout@v3 + + - name: Set up Python 3.10 + uses: actions/setup-python@v4 + with: + python-version: "3.10" + cache: pip + cache-dependency-path: requirements*.txt + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + python -m pip install --upgrade --upgrade-strategy eager -e ".[dev]" + mkdocs build + + - name: Publish docs + uses: JamesIves/github-pages-deploy-action@v4.4.1 + with: + branch: docs + folder: site diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml new file mode 100644 index 0000000..4181077 --- /dev/null +++ b/.github/workflows/release.yml @@ -0,0 +1,79 @@ +name: Build & Release + +on: + push: + tags: + - "v*" + +jobs: + build-release: + name: Build Release + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v3 + + - name: Set up Python + uses: actions/setup-python@v4 + with: + python-version: 3.7 + + - name: Install packages + run: | + python -m pip install --upgrade pip build + python -m pip install --upgrade --upgrade-strategy eager -e .[dev] + + - name: Build a binary wheel and a source tarball + run: | + python -m build --sdist --wheel --outdir dist/ + + - name: Publish build artifacts + uses: actions/upload-artifact@v3 + with: + name: built-package + path: "./dist" + + publish-release: + name: Publish release to PyPI + needs: [build-release] + environment: "prod" + runs-on: ubuntu-latest + + steps: + - name: Download build artifacts + uses: actions/download-artifact@v3 + with: + name: built-package + path: "./dist" + + - name: Publish distribution to PyPI + uses: pypa/gh-action-pypi-publish@release/v1 + with: + password: ${{ secrets.PYPI_API_TOKEN }} + verbose: true + + build-and-publish-docs: + name: Build and publish docs + needs: [build-release, publish-release] + runs-on: ubuntu-latest + + steps: + - uses: actions/checkout@v3 + + - name: Set up Python 3.10 + uses: actions/setup-python@v4 + with: + python-version: "3.10" + cache: pip + cache-dependency-path: requirements*.txt + + - name: Build docs + run: | + python -m pip install --upgrade pip + python -m pip install --upgrade --upgrade-strategy eager -e .[dev] + mkdocs build + + - name: Publish docs + uses: JamesIves/github-pages-deploy-action@v4.4.1 + with: + branch: docs + folder: site diff --git a/.github/workflows/static_analysis.yml b/.github/workflows/static_analysis.yml new file mode 100644 index 0000000..58fb933 --- /dev/null +++ b/.github/workflows/static_analysis.yml @@ -0,0 +1,27 @@ +name: Static analysis + +on: [pull_request] + +jobs: + pre-commit-checks: + name: Pre-commit checks + runs-on: ubuntu-latest + + steps: + - uses: actions/checkout@v3 + with: + persist-credentials: false + + - name: Set up Python + uses: actions/setup-python@v4 + with: + python-version: 3.9 + + - name: Install pre-commit + run: | + python -m pip install --upgrade pip + pip install pre-commit + + - name: Run pre-commit + run: | + pre-commit run --show-diff-on-failure --color=always --all-files diff --git a/.github/workflows/template-sync.yml b/.github/workflows/template-sync.yml new file mode 100644 index 0000000..aec8fdb --- /dev/null +++ b/.github/workflows/template-sync.yml @@ -0,0 +1,46 @@ +name: Template Synchronization +on: + schedule: + - cron: "0 6 * * *" + workflow_dispatch: + +jobs: + submit-update-pr: + name: Submit update PR + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v3 + + - name: Set up Python + uses: actions/setup-python@v4 + with: + python-version: 3.9 + + - name: Install cruft + run: pip install "cookiecutter>=1.7.3,<2.0.0" cruft + + - name: Perform updates + run: cruft update -y + + - uses: tibdex/github-app-token@v1 + id: generate-token + name: Generate GitHub token + with: + app_id: ${{ secrets.SYNC_APP_ID }} + private_key: ${{ secrets.SYNC_APP_PRIVATE_KEY }} + + - name: Submit PR + uses: peter-evans/create-pull-request@v4 + with: + commit-message: Updating collection with changes to prefect-collection-template + token: ${{ steps.generate-token.outputs.token }} + branch: sync-with-template + delete-branch: true + title: Sync Collection with changes to prefect-collection-template + body: | + Automated PR created to propagate changes from prefect-collection-template to this collection + + Feel free to make any necessary changes to this PR before merging. + labels: | + template sync + automated pr diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml new file mode 100644 index 0000000..6e7a5d4 --- /dev/null +++ b/.github/workflows/tests.yml @@ -0,0 +1,41 @@ +name: Tests + +on: [pull_request] + +jobs: + run-tests: + name: Run Tests + runs-on: ubuntu-latest + strategy: + matrix: + python-version: + - "3.7" + - "3.8" + - "3.9" + - "3.10" + fail-fast: false + steps: + - uses: actions/checkout@v3 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + cache: pip + cache-dependency-path: requirements*.txt + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + python -m pip install --upgrade --upgrade-strategy eager -e ".[dev]" + + - name: Run tests + env: + PREFECT_SERVER_DATABASE_CONNECTION_URL: "sqlite+aiosqlite:///./collection-tests.db" + run: | + coverage run --branch -m pytest tests -vv + coverage report + + - name: Run mkdocs build + run: | + mkdocs build --verbose --clean diff --git a/.github/workflows/windows-tests.yml b/.github/workflows/windows-tests.yml new file mode 100644 index 0000000..c5d9813 --- /dev/null +++ b/.github/workflows/windows-tests.yml @@ -0,0 +1,34 @@ + +name: Windows Tests + +on: [pull_request] + +jobs: + run-tests: + name: Run Tests + runs-on: windows-latest + strategy: + matrix: + # Prefect only tests 3.9 on Windows + python-version: + - "3.9" + fail-fast: false + steps: + - uses: actions/checkout@v3 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + cache: pip + cache-dependency-path: requirements*.txt + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + python -m pip install --upgrade --upgrade-strategy eager -e ".[dev]" + - name: Run tests + env: + PREFECT_SERVER_DATABASE_CONNECTION_URL: "sqlite+aiosqlite:///./collection-tests.db" + run: | + pytest tests -vv diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b96a3be --- /dev/null +++ b/.gitignore @@ -0,0 +1,138 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$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 + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +.python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# OS files +.DS_Store + +# VS Code +.vscode + +# Jupyter notebook +*.ipynb diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 0000000..2f089e8 --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,29 @@ +repos: + - repo: https://github.com/pycqa/isort + rev: 5.12.0 + hooks: + - id: isort + language_version: python3 + - repo: https://github.com/psf/black + rev: 22.3.0 + hooks: + - id: black + language_version: python3 + - repo: https://github.com/pycqa/flake8 + rev: 4.0.1 + hooks: + - id: flake8 + - repo: https://github.com/econchick/interrogate + rev: 1.5.0 + hooks: + - id: interrogate + args: [-vv] + pass_filenames: false + - repo: https://github.com/fsouza/autoflake8 + rev: v0.3.2 + hooks: + - id: autoflake8 + language_version: python3 + args: [ + '--in-place', + ] diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 0000000..04e9176 --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,28 @@ +# Changelog + +All notable changes to this project will be documented in this file. + +The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), +and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). + +## Unreleased + +### Added + +### Changed + +### Deprecated + +### Removed + +### Fixed + +### Security + +## 0.1.0 + +Released on ????? ?th, 20??. + +### Added + +- `task_name` task - [#1](https://github.com/shubhamjagtap639/prefect-datahub/pull/1) diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..53c2097 --- /dev/null +++ b/LICENSE @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2021 Prefect Technologies, Inc. + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/MAINTAINERS.md b/MAINTAINERS.md new file mode 100644 index 0000000..b58c764 --- /dev/null +++ b/MAINTAINERS.md @@ -0,0 +1,114 @@ +# prefect-datahub + +## Getting Started + +Now that you've bootstrapped a project, follow the steps below to get started developing your Prefect Collection! + +### Python setup + +Requires an installation of Python 3.7+ + +We recommend using a Python virtual environment manager such as pipenv, conda or virtualenv. + +### GitHub setup + +Create a Git respoitory for the newly generated collection and create the first commit: + +```bash +git init +git add . +git commit -m "Initial commit: project generated by prefect-collection-template" +``` + +Then, create a new repo following the prompts at: +https://github.com/organizations/shubhamjagtap639/repositories/new + +Upon creation, push the repository to GitHub: +```bash +git remote add origin https://github.com/shubhamjagtap639/prefect-datahub.git +git branch -M main +git push -u origin main +``` + +It's recommended to setup some protection rules for main at: +https://github.com/shubhamjagtap639/prefect-datahub/settings/branches + +- Require a pull request before merging +- Require approvals + +Lastly, [code owners](https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners) for the repository can be set, like this [example here](https://github.com/PrefectHQ/prefect/blob/master/.github/CODEOWNERS). + +### Project setup + +To setup your project run the following: + +```bash +# Create an editable install of your project +pip install -e ".[dev]" + +# Configure pre-commit hooks +pre-commit install +``` + +To verify the setup was successful you can run the following: + +- Run the tests for tasks and flows in the collection: + ```bash + pytest tests + ``` +- Serve the docs with `mkdocs`: + ```bash + mkdocs serve + ``` + +## Developing tasks and flows + +For information about the use and development of tasks and flow, check out the [flows](https://docs.prefect.io/concepts/flows/) and [tasks](https://docs.prefect.io/concepts/tasks/) concepts docs in the Prefect docs. + +## Writing documentation + +This collection has been setup to with [mkdocs](https://www.mkdocs.org/) for automatically generated documentation. The signatures and docstrings of your tasks and flow will be used to generate documentation for the users of this collection. You can make changes to the structure of the generated documentation by editing the `mkdocs.yml` file in this project. + +To add a new page for a module in your collection, create a new markdown file in the `docs` directory and add that file to the `nav` section of `mkdocs.yml`. If you want to automatically generate documentation based on the docstrings and signatures of the contents of the module with `mkdocstrings`, add a line to the new markdown file in the following format: + +```markdown +::: prefect_datahub.{module_name} +``` + +You can also refer to the `flows.md` and `tasks.md` files included in your generated project as examples. + +Once you have working code, replace the default "Write and run a flow" example in `README.md` to match your collection. + +## Development lifecycle + +### CI Pipeline + +This collection comes with [GitHub Actions](https://docs.github.com/en/actions) for testing and linting. To add additional actions, you can add jobs in the `.github/workflows` folder. Upon a pull request, the pipeline will run linting via [`black`](https://black.readthedocs.io/en/stable/), [`flake8`](https://flake8.pycqa.org/en/latest/), [`interrogate`](https://interrogate.readthedocs.io/en/latest/), and unit tests via `pytest` alongside `coverage`. + +`interrogate` will tell you which methods, functions, classes, and modules have docstrings, and which do not--the job has a fail threshold of 95%, meaning that it will fail if more than 5% of the codebase is undocumented. We recommend following the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for docstring format. + +Simiarly, `coverage` ensures that the codebase includes tests--the job has a fail threshold of 80%, meaning that it will fail if more than 20% of the codebase is missing tests. + +### Track Issues on Project Board + +To automatically add issues to a GitHub Project Board, you'll need a [secret added](https://docs.github.com/en/actions/security-guides/encrypted-secrets#creating-encrypted-secrets-for-an-environment) to the repository. Specifically, a secret named `ADD_TO_PROJECT_URL`, formatted like `https://github.com/orgs//projects/`. + +### Package and Publish + +GitHub actions will handle packaging and publishing of your collection to [PyPI](https://pypi.org/) so other Prefect users can your collection in their flows. + +To publish to PyPI, you'll need a PyPI account and to generate an API token to authenticate with PyPI when publishing new versions of your collection. The [PyPI documentation](https://pypi.org/help/#apitoken) outlines the steps needed to get an API token. + +Once you've obtained a PyPI API token, [create a GitHub secret](https://docs.github.com/en/actions/security-guides/encrypted-secrets#creating-encrypted-secrets-for-a-repository) named `PYPI_API_TOKEN`. + +To publish a new version of your collection, [create a new GitHub release](https://docs.github.com/en/repositories/releasing-projects-on-github/managing-releases-in-a-repository#creating-a-release) and tag it with the version that you want to deploy (e.g. v0.3.2). This will trigger a workflow to publish the new version on PyPI and deploy the updated docs to GitHub pages. + +Upon publishing, a `docs` branch is automatically created. To hook this up to GitHub Pages, simply head over to https://github.com/shubhamjagtap639/prefect-datahub/settings/pages, select `docs` under the dropdown menu, keep the default `/root` folder, `Save`, and upon refresh, you should see a prompt stating "Your site is published at https://shubhamjagtap639.github.io/prefect-datahub". Don't forget to add this link to the repo's "About" section, under "Website" so users can access the docs easily. + +Feel free to [submit your collection](https://docs.prefect.io/collections/overview/#listing-in-the-collections-catalog) to the Prefect [Collections Catalog](https://docs.prefect.io/collections/catalog/)! + +## Further guidance + +If you run into any issues during the bootstrapping process, feel free to open an issue in the [prefect-collection-template](https://github.com/PrefectHQ/prefect-collection-template) repository. + +If you have any questions or issues while developing your collection, you can find help in either the [Prefect Discourse forum](https://discourse.prefect.io/) or the [Prefect Slack community](https://prefect.io/slack). diff --git a/MANIFEST.in b/MANIFEST.in new file mode 100644 index 0000000..9e3fb02 --- /dev/null +++ b/MANIFEST.in @@ -0,0 +1,14 @@ +# Things to always exclude +global-exclude .git* +global-exclude .ipynb_checkpoints +global-exclude *.py[co] +global-exclude __pycache__/** + +# Top-level Config +include versioneer.py +include prefect_datahub/_version.py +include LICENSE +include MANIFEST.in +include setup.cfg +include requirements.txt +include requirements-dev.txt diff --git a/README.md b/README.md index 8245abc..48630d2 100644 --- a/README.md +++ b/README.md @@ -1 +1,148 @@ -# prefect-datahub +# Emit flows & tasks metadata to DataHub rest with `prefect-datahub` + +

+ + + + PyPI + + + + + + +
+ + + + +

+ +## Welcome! + +The `prefect-datahub` collection makes it easy to leverage the capabilities of DataHub emitter in your flows, featuring support for ingesting metadata of flows, tasks & workspace to DataHub gms rest. + + +## Getting Started + +### Setup DataHub UI + +In order to use 'prefect-datahub' collection, you'll first need to deploy the new instance of DataHub. + +You can get the instructions on deploying the open source DataHub by navigating to the [apps page](https://datahubproject.io/docs/quickstart). + +Successful deployment of DataHub will lead creation of DataHub GMS service running on 'http://localhost:8080' if you have deployed it on local system. + +### Saving configurations to a block + + +This is a one-time activity, where you can save the configuration on the [Prefect block document store](https://docs.prefect.io/2.10.13/concepts/blocks/#saving-blocks). +While saving you can provide below configurations. Default value will get set if not provided while saving the configuration to block. + +Config | Type | Default | Description +--- | --- | --- | --- +datahub_rest_url | `str` | *http://localhost:8080* | DataHub GMS REST URL +env | `str` | *PROD* | The environment that all assets produced by this orchestrator belong to. For more detail and possible values refer [here](https://datahubproject.io/docs/graphql/enums/#fabrictype). +platform_instance | `str` | *None* | The instance of the platform that all assets produced by this recipe belong to. For more detail please refer [here](https://datahubproject.io/docs/platform-instances/). + +```python +from prefect_datahub import DatahubEmitter +DatahubEmitter( + datahub_rest_url="http://localhost:8080", + env="PROD", + platform_instance="local_prefect" +).save("BLOCK-NAME-PLACEHOLDER") +``` + +Congrats! You can now load the saved block to use your configurations in your Flow code: + +```python +from prefect_datahub import DatahubEmitter +DatahubEmitter.load("BLOCK-NAME-PLACEHOLDER") +``` + +!!! info "Registering blocks" + + Register blocks in this module to + [view and edit them](https://docs.prefect.io/ui/blocks/) + on Prefect Cloud: + + ```bash + prefect block register -m prefect_datahub + ``` + +### Load the saved block in prefect workflows + +After installing `prefect-datahub` and [saving the configution](#saving-configurations-to-a-block), you can easily use it within your prefect workflows to help you emit metadata event as show below! + +```python +from datahub_provider.entities import Dataset +from prefect import flow, task + +from prefect_datahub import DatahubEmitter + +datahub_emitter = DatahubEmitter.load("MY_BLOCK_NAME") + +@task(name="Transform", description="Transform the data") +def transform(data): + data = data.split(" ") + datahub_emitter.add_task( + inputs=[Dataset("snowflake", "mydb.schema.tableA")], + outputs=[Dataset("snowflake", "mydb.schema.tableC")], + ) + return data + +@flow(name="ETL flow", description="Extract transform load flow") +def etl(): + data = transform("This is data") + datahub_emitter.emit_flow() +``` + +**Note**: To emit the tasks, user compulsory need to emit flow. Otherwise nothing will get emit. + +## Resources + +For more tips on how to use tasks and flows in a Collection, check out [Using Collections](https://docs.prefect.io/collections/usage/)! + +### Installation + +Install `prefect-datahub` with `pip`: + +```bash +pip install prefect-datahub +``` + +Requires an installation of Python 3.7+. + +We recommend using a Python virtual environment manager such as pipenv, conda or virtualenv. + +These tasks are designed to work with Prefect 2.0. For more information about how to use Prefect, please refer to the [Prefect documentation](https://docs.prefect.io/). + +### Feedback + +If you encounter any bugs while using `prefect-datahub`, feel free to open an issue in the [prefect-datahub](https://github.com/shubhamjagtap639/prefect-datahub) repository. + +If you have any questions or issues while using `prefect-datahub`, you can find help in either the [Prefect Discourse forum](https://discourse.prefect.io/) or the [Prefect Slack community](https://prefect.io/slack). + +Feel free to star or watch [`prefect-datahub`](https://github.com/shubhamjagtap639/prefect-datahub) for updates too! + +### Contributing + +If you'd like to help contribute to fix an issue or add a feature to `prefect-datahub`, please [propose changes through a pull request from a fork of the repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork). + +Here are the steps: + +1. [Fork the repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#forking-a-repository) +2. [Clone the forked repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#cloning-your-forked-repository) +3. Install the repository and its dependencies: +``` +pip install -e ".[dev]" +``` +4. Make desired changes +5. Add tests +6. Insert an entry to [CHANGELOG.md](https://github.com/shubhamjagtap639/prefect-datahub/blob/main/CHANGELOG.md) +7. Install `pre-commit` to perform quality checks prior to commit: +``` +pre-commit install +``` +8. `git commit`, `git push`, and create a pull request diff --git a/docs/concept_mapping.md b/docs/concept_mapping.md new file mode 100644 index 0000000..b6d4055 --- /dev/null +++ b/docs/concept_mapping.md @@ -0,0 +1,12 @@ +# Prefect and Datahub concept mapping + + +Prefect concepts are documented [here](https://docs.prefect.io/latest/concepts/), and datahub concepts are documented [here](https://datahubproject.io/docs/what-is-datahub/datahub-concepts). + +Prefect Concept | DataHub Concept +--- | --- +[Flow](https://docs.prefect.io/2.10.13/concepts/flows/#flows) | [DataFlow](https://datahubproject.io/docs/generated/metamodel/entities/dataflow/) +[Flow Run](https://docs.prefect.io/latest/concepts/flows/#flow-runs) | [DataProcessInstance](https://datahubproject.io/docs/generated/metamodel/entities/dataprocessinstance) +[Task](https://docs.prefect.io/2.10.13/concepts/tasks/#tasks) | [DataJob](https://datahubproject.io/docs/generated/metamodel/entities/datajob/) +[Task Run](https://docs.prefect.io/latest/concepts/tasks/#tasks) | [DataProcessInstance](https://datahubproject.io/docs/generated/metamodel/entities/dataprocessinstance) +[Task Tag](https://docs.prefect.io/latest/concepts/tasks/#tags) | [Tag](https://datahubproject.io/docs/generated/metamodel/entities/tag/) diff --git a/docs/datahub_emitter.md b/docs/datahub_emitter.md new file mode 100644 index 0000000..2fcf05c --- /dev/null +++ b/docs/datahub_emitter.md @@ -0,0 +1 @@ +::: prefect_datahub.datahub_emitter diff --git a/docs/gen_blocks_catalog.py b/docs/gen_blocks_catalog.py new file mode 100644 index 0000000..7e40612 --- /dev/null +++ b/docs/gen_blocks_catalog.py @@ -0,0 +1,103 @@ +""" +Discovers all blocks and generates a list of them in the docs +under the Blocks Catalog heading. +""" + +from pathlib import Path +from textwrap import dedent + +import mkdocs_gen_files +from prefect.blocks.core import Block +from prefect.utilities.dispatch import get_registry_for_type +from prefect.utilities.importtools import from_qualified_name, to_qualified_name + +COLLECTION_SLUG = "prefect_datahub" + + +def find_module_blocks(): + blocks = get_registry_for_type(Block) + collection_blocks = [ + block + for block in blocks.values() + if to_qualified_name(block).startswith(COLLECTION_SLUG) + ] + module_blocks = {} + for block in collection_blocks: + block_name = block.__name__ + module_nesting = tuple(to_qualified_name(block).split(".")[1:-1]) + if module_nesting not in module_blocks: + module_blocks[module_nesting] = [] + module_blocks[module_nesting].append(block_name) + return module_blocks + + +def insert_blocks_catalog(generated_file): + module_blocks = find_module_blocks() + if len(module_blocks) == 0: + return + generated_file.write( + dedent( + f""" + Below is a list of Blocks available for registration in + `prefect-datahub`. + + To register blocks in this module to + [view and edit them](https://docs.prefect.io/ui/blocks/) + on Prefect Cloud, first [install the required packages]( + https://shubhamjagtap639.github.io/prefect-datahub/#installation), + then + ```bash + prefect block register -m {COLLECTION_SLUG} + ``` + """ # noqa + ) + ) + generated_file.write( + "Note, to use the `load` method on Blocks, you must already have a block document " # noqa + "[saved through code](https://docs.prefect.io/concepts/blocks/#saving-blocks) " # noqa + "or [saved through the UI](https://docs.prefect.io/ui/blocks/).\n" + ) + for module_nesting, block_names in module_blocks.items(): + module_path = f"{COLLECTION_SLUG}." + " ".join(module_nesting) + module_title = ( + module_path.replace(COLLECTION_SLUG, "") + .lstrip(".") + .replace("_", " ") + .title() + ) + generated_file.write(f"## [{module_title} Module][{module_path}]\n") + for block_name in block_names: + block_obj = from_qualified_name(f"{module_path}.{block_name}") + block_description = block_obj.get_description() + if not block_description.endswith("."): + block_description += "." + generated_file.write( + f"[{block_name}][{module_path}.{block_name}]\n\n{block_description}\n\n" + ) + generated_file.write( + dedent( + f""" + To load the {block_name}: + ```python + from prefect import flow + from {module_path} import {block_name} + + @flow + def my_flow(): + my_block = {block_name}.load("MY_BLOCK_NAME") + + my_flow() + ``` + """ + ) + ) + generated_file.write( + f"For additional examples, check out the [{module_title} Module]" + f"(../examples_catalog/#{module_nesting[-1]}-module) " + f"under Examples Catalog.\n" + ) + + +blocks_catalog_path = Path("blocks_catalog.md") +with mkdocs_gen_files.open(blocks_catalog_path, "w") as generated_file: + insert_blocks_catalog(generated_file) diff --git a/docs/gen_examples_catalog.py b/docs/gen_examples_catalog.py new file mode 100644 index 0000000..c8f8261 --- /dev/null +++ b/docs/gen_examples_catalog.py @@ -0,0 +1,120 @@ +""" +Locates all the examples in the Collection and puts them in a single page. +""" + +import re +from collections import defaultdict +from inspect import getmembers, isclass, isfunction +from pathlib import Path +from pkgutil import iter_modules +from textwrap import dedent +from types import ModuleType +from typing import Callable, Set, Union + +import mkdocs_gen_files +from griffe.dataclasses import Docstring +from griffe.docstrings.dataclasses import DocstringSectionKind +from griffe.docstrings.parsers import Parser, parse +from prefect.logging.loggers import disable_logger +from prefect.utilities.importtools import load_module, to_qualified_name + +import prefect_datahub + +COLLECTION_SLUG = "prefect_datahub" + + +def skip_parsing(name: str, obj: Union[ModuleType, Callable], module_nesting: str): + """ + Skips parsing the object if it's a private object or if it's not in the + module nesting, preventing imports from other libraries from being added to the + examples catalog. + """ + try: + wrong_module = not to_qualified_name(obj).startswith(module_nesting) + except AttributeError: + wrong_module = False + return obj.__doc__ is None or name.startswith("_") or wrong_module + + +def skip_block_load_code_example(code_example: str) -> bool: + """ + Skips the code example if it's just showing how to load a Block. + """ + return re.search(r'\.load\("BLOCK_NAME"\)\s*$', code_example.rstrip("`")) + + +def get_code_examples(obj: Union[ModuleType, Callable]) -> Set[str]: + """ + Gathers all the code examples within an object. + """ + code_examples = set() + with disable_logger("griffe.docstrings.google"): + with disable_logger("griffe.agents.nodes"): + docstring = Docstring(obj.__doc__) + parsed_sections = parse(docstring, Parser.google) + + for section in parsed_sections: + if section.kind == DocstringSectionKind.examples: + code_example = "\n".join( + (part[1] for part in section.as_dict().get("value", [])) + ) + if not skip_block_load_code_example(code_example): + code_examples.add(code_example) + if section.kind == DocstringSectionKind.admonition: + value = section.as_dict().get("value", {}) + if value.get("annotation") == "example": + code_example = value.get("description") + if not skip_block_load_code_example(code_example): + code_examples.add(code_example) + + return code_examples + + +code_examples_grouping = defaultdict(set) +for _, module_name, ispkg in iter_modules(prefect_datahub.__path__): + + module_nesting = f"{COLLECTION_SLUG}.{module_name}" + module_obj = load_module(module_nesting) + + # find all module examples + if skip_parsing(module_name, module_obj, module_nesting): + continue + code_examples_grouping[module_name] |= get_code_examples(module_obj) + + # find all class and method examples + for class_name, class_obj in getmembers(module_obj, isclass): + if skip_parsing(class_name, class_obj, module_nesting): + continue + code_examples_grouping[module_name] |= get_code_examples(class_obj) + for method_name, method_obj in getmembers(class_obj, isfunction): + if skip_parsing(method_name, method_obj, module_nesting): + continue + code_examples_grouping[module_name] |= get_code_examples(method_obj) + + # find all function examples + for function_name, function_obj in getmembers(module_obj, callable): + if skip_parsing(function_name, function_obj, module_nesting): + continue + code_examples_grouping[module_name] |= get_code_examples(function_obj) + + +examples_catalog_path = Path("examples_catalog.md") +with mkdocs_gen_files.open(examples_catalog_path, "w") as generated_file: + generated_file.write( + dedent( + """ + # Examples Catalog + + Below is a list of examples for `prefect-datahub`. + """ + ) + ) + for module_name, code_examples in code_examples_grouping.items(): + if len(code_examples) == 0: + continue + module_title = module_name.replace("_", " ").title() + generated_file.write( + f"## [{module_title} Module][{COLLECTION_SLUG}.{module_name}]\n" + ) + for code_example in code_examples: + generated_file.write(code_example + "\n") diff --git a/docs/gen_home_page.py b/docs/gen_home_page.py new file mode 100644 index 0000000..3341134 --- /dev/null +++ b/docs/gen_home_page.py @@ -0,0 +1,21 @@ +""" +Copies README.md to index.md. +""" + +from pathlib import Path + +import mkdocs_gen_files + +# Home page + +readme_path = Path("README.md") +docs_index_path = Path("index.md") + +with open(readme_path, "r") as readme: + with mkdocs_gen_files.open(docs_index_path, "w") as generated_file: + for line in readme: + if line.startswith("Visit the full docs [here]("): + continue # prevent linking to itself + generated_file.write(line) + + mkdocs_gen_files.set_edit_path(Path(docs_index_path), readme_path) diff --git a/docs/img/favicon.ico b/docs/img/favicon.ico new file mode 100644 index 0000000..c4b4215 Binary files /dev/null and b/docs/img/favicon.ico differ diff --git a/docs/img/prefect-logo-mark-solid-white-500.png b/docs/img/prefect-logo-mark-solid-white-500.png new file mode 100644 index 0000000..f83aa6e Binary files /dev/null and b/docs/img/prefect-logo-mark-solid-white-500.png differ diff --git a/docs/img/prefect-logo-white.png b/docs/img/prefect-logo-white.png new file mode 100644 index 0000000..50ca613 Binary files /dev/null and b/docs/img/prefect-logo-white.png differ diff --git a/docs/overrides/partials/integrations/analytics/custom.html b/docs/overrides/partials/integrations/analytics/custom.html new file mode 100644 index 0000000..96a2301 --- /dev/null +++ b/docs/overrides/partials/integrations/analytics/custom.html @@ -0,0 +1,16 @@ + + + + + diff --git a/docs/stylesheets/extra.css b/docs/stylesheets/extra.css new file mode 100644 index 0000000..11a0209 --- /dev/null +++ b/docs/stylesheets/extra.css @@ -0,0 +1,114 @@ +/* theme */ +:root > * { + /* theme */ + --md-primary-fg-color: #115AF4; + --md-primary-fg-color--light: #115AF4; + --md-primary-fg-color--dark: #115AF4; +} + +/* Table formatting */ +.md-typeset table:not([class]) td { + padding: 0.5em 1.25em; +} +.md-typeset table:not([class]) th { + padding: 0.5em 1.25em; +} + +/* convenience class to keep lines from breaking +useful for wrapping table cell text in a span +to force column width */ +.no-wrap { + white-space: nowrap; +} + +/* badge formatting */ +.badge::before { + background-color: #1860F2; + color: white; + font-size: 0.8rem; + font-weight: normal; + padding: 4px 8px; + margin-left: 0.5rem; + vertical-align: super; + text-align: center; + border-radius: 5px; +} + +.badge-api::before { + background-color: #1860F2; + color: white; + font-size: 0.8rem; + font-weight: normal; + padding: 4px 8px; + text-align: center; + border-radius: 5px; +} + +.experimental::before { + background-color: #FCD14E; + content: "Experimental"; +} + +.cloud::before { + background-color: #799AF7; + content: "Prefect Cloud"; +} + +.deprecated::before { + background-color: #FA1C2F; + content: "Deprecated"; +} + +.new::before { + background-color: #2AC769; + content: "New"; +} + +.expert::before { + background-color: #726576; + content: "Advanced"; +} + +/* dark mode slate theme */ +/* dark mode code overrides */ +[data-md-color-scheme="slate"] { + --md-code-bg-color: #252a33; + --md-code-fg-color: #eee; + --md-code-hl-color: #3b3d54; + --md-code-hl-name-color: #eee; +} + +/* dark mode link overrides */ +[data-md-color-scheme="slate"] .md-typeset a { + color: var(--blue); +} + +[data-md-color-scheme="slate"] .md-typeset a:hover { + font-weight: bold; +} + +/* dark mode nav overrides */ +[data-md-color-scheme="slate"] .md-nav--primary .md-nav__item--active>.md-nav__link { + color: var(--blue); + font-weight: bold; +} + +[data-md-color-scheme="slate"] .md-nav--primary .md-nav__link--active { + color: var(--blue); + font-weight: bold; +} + +/* dark mode collection catalog overrides */ +[data-md-color-scheme="slate"] .collection-item { + background-color: #3b3d54; +} + +/* dark mode recipe collection overrides */ +[data-md-color-scheme="slate"] .recipe-item { + background-color: #3b3d54; +} + +/* dark mode API doc overrides */ +[data-md-color-scheme="slate"] .prefect-table th { + background-color: #3b3d54; +} \ No newline at end of file diff --git a/mkdocs.yml b/mkdocs.yml new file mode 100644 index 0000000..968d6c0 --- /dev/null +++ b/mkdocs.yml @@ -0,0 +1,81 @@ +site_name: prefect-datahub +site_url: https://shubhamjagtap639.github.io/prefect-datahub +repo_url: https://github.com/shubhamjagtap639/prefect-datahub +edit_uri: edit/main/docs/ +theme: + name: material + custom_dir: docs/overrides + favicon: img/favicon.ico + palette: + - media: "(prefers-color-scheme)" + toggle: + icon: material/brightness-auto + name: Switch to light mode + - media: "(prefers-color-scheme: light)" + accent: blue + primary: blue + scheme: default + toggle: + icon: material/weather-sunny + name: Switch to dark mode + - media: "(prefers-color-scheme: dark)" + accent: blue + primary: blue + scheme: slate + toggle: + icon: material/weather-night + name: Switch to light mode + icon: + repo: fontawesome/brands/github + logo: + img/prefect-logo-mark-solid-white-500.png + font: + text: Inter + code: Source Code Pro + features: + - content.code.copy + - content.code.annotate +extra_css: + - stylesheets/extra.css +markdown_extensions: + - admonition + - attr_list + - codehilite + - md_in_html + - meta + - pymdownx.highlight: + use_pygments: true + - pymdownx.superfences + - pymdownx.tabbed + - pymdownx.inlinehilite + - pymdownx.snippets + +plugins: + - search + - gen-files: + scripts: + - docs/gen_home_page.py + - docs/gen_examples_catalog.py + - docs/gen_blocks_catalog.py + - mkdocstrings: + handlers: + python: + options: + show_root_heading: True + show_object_full_path: False + show_category_heading: True + show_bases: True + show_signature: False + heading_level: 1 +watch: + - prefect_datahub/ + - README.md + +nav: + - Home: index.md + - Datahub Emitter: datahub_emitter.md + - Blocks Catalog: blocks_catalog.md + - Examples Catalog: examples_catalog.md + - Concept Mapping: concept_mapping.md + + diff --git a/prefect_datahub/__init__.py b/prefect_datahub/__init__.py new file mode 100644 index 0000000..4d52a61 --- /dev/null +++ b/prefect_datahub/__init__.py @@ -0,0 +1,3 @@ +from . import _version + +__version__ = _version.get_versions()["version"] diff --git a/prefect_datahub/_version.py b/prefect_datahub/_version.py new file mode 100644 index 0000000..04b1004 --- /dev/null +++ b/prefect_datahub/_version.py @@ -0,0 +1,677 @@ +# This file helps to compute a version number in source trees obtained from +# git-archive tarball (such as those provided by githubs download-from-tag +# feature). Distribution tarballs (built by setup.py sdist) and build +# directories (produced by setup.py build) will contain a much shorter file +# that just contains the computed version number. + +# This file is released into the public domain. Generated by +# versioneer-0.21 (https://github.com/python-versioneer/python-versioneer) + +"""Git implementation of _version.py.""" + +import errno +import os +import re +import subprocess +import sys +from typing import Callable, Dict + + +def get_keywords(): + """Get the keywords needed to look up the version information.""" + # these strings will be replaced by git during git-archive. + # setup.py/versioneer.py will grep for the variable names, so they must + # each be defined on a line of their own. _version.py will just call + # get_keywords(). + git_refnames = "$Format:%d$" + git_full = "$Format:%H$" + git_date = "$Format:%ci$" + keywords = {"refnames": git_refnames, "full": git_full, "date": git_date} + return keywords + + +class VersioneerConfig: + """Container for Versioneer configuration parameters.""" + + +def get_config(): + """Create, populate and return the VersioneerConfig() object.""" + # these strings are filled in when 'setup.py versioneer' creates + # _version.py + cfg = VersioneerConfig() + cfg.VCS = "git" + cfg.style = "pep440" + cfg.tag_prefix = "" + cfg.parentdir_prefix = "" + cfg.versionfile_source = "prefect_datahub/_version.py" + cfg.verbose = False + return cfg + + +class NotThisMethod(Exception): + """Exception raised if a method is not valid for the current scenario.""" + + +LONG_VERSION_PY: Dict[str, str] = {} +HANDLERS: Dict[str, Dict[str, Callable]] = {} + + +def register_vcs_handler(vcs, method): # decorator + """Create decorator to mark a method as the handler of a VCS.""" + + def decorate(f): + """Store f in HANDLERS[vcs][method].""" + if vcs not in HANDLERS: + HANDLERS[vcs] = {} + HANDLERS[vcs][method] = f + return f + + return decorate + + +def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=None): + """Call the given command(s).""" + assert isinstance(commands, list) + process = None + for command in commands: + try: + dispcmd = str([command] + args) + # remember shell=False, so use git.cmd on windows, not just git + process = subprocess.Popen( + [command] + args, + cwd=cwd, + env=env, + stdout=subprocess.PIPE, + stderr=(subprocess.PIPE if hide_stderr else None), + ) + break + except OSError: + e = sys.exc_info()[1] + if e.errno == errno.ENOENT: + continue + if verbose: + print("unable to run %s" % dispcmd) + print(e) + return None, None + else: + if verbose: + print("unable to find command, tried %s" % (commands,)) + return None, None + stdout = process.communicate()[0].strip().decode() + if process.returncode != 0: + if verbose: + print("unable to run %s (error)" % dispcmd) + print("stdout was %s" % stdout) + return None, process.returncode + return stdout, process.returncode + + +def versions_from_parentdir(parentdir_prefix, root, verbose): + """Try to determine the version from the parent directory name. + + Source tarballs conventionally unpack into a directory that includes both + the project name and a version string. We will also support searching up + two directory levels for an appropriately named parent directory + """ + rootdirs = [] + + for _ in range(3): + dirname = os.path.basename(root) + if dirname.startswith(parentdir_prefix): + return { + "version": dirname[len(parentdir_prefix) :], + "full-revisionid": None, + "dirty": False, + "error": None, + "date": None, + } + rootdirs.append(root) + root = os.path.dirname(root) # up a level + + if verbose: + print( + "Tried directories %s but none started with prefix %s" + % (str(rootdirs), parentdir_prefix) + ) + raise NotThisMethod("rootdir doesn't start with parentdir_prefix") + + +@register_vcs_handler("git", "get_keywords") +def git_get_keywords(versionfile_abs): + """Extract version information from the given file.""" + # the code embedded in _version.py can just fetch the value of these + # keywords. When used from setup.py, we don't want to import _version.py, + # so we do it with a regexp instead. This function is not used from + # _version.py. + keywords = {} + try: + with open(versionfile_abs, "r") as fobj: + for line in fobj: + if line.strip().startswith("git_refnames ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["refnames"] = mo.group(1) + if line.strip().startswith("git_full ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["full"] = mo.group(1) + if line.strip().startswith("git_date ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["date"] = mo.group(1) + except OSError: + pass + return keywords + + +@register_vcs_handler("git", "keywords") +def git_versions_from_keywords(keywords, tag_prefix, verbose): + """Get version information from git keywords.""" + if "refnames" not in keywords: + raise NotThisMethod("Short version file found") + date = keywords.get("date") + if date is not None: + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + + # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant + # datestamp. However we prefer "%ci" (which expands to an "ISO-8601 + # -like" string, which we must then edit to make compliant), because + # it's been around since git-1.5.3, and it's too difficult to + # discover which version we're using, or to work around using an + # older one. + date = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + refnames = keywords["refnames"].strip() + if refnames.startswith("$Format"): + if verbose: + print("keywords are unexpanded, not using") + raise NotThisMethod("unexpanded keywords, not a git-archive tarball") + refs = {r.strip() for r in refnames.strip("()").split(",")} + # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of + # just "foo-1.0". If we see a "tag: " prefix, prefer those. + TAG = "tag: " + tags = {r[len(TAG) :] for r in refs if r.startswith(TAG)} + if not tags: + # Either we're using git < 1.8.3, or there really are no tags. We use + # a heuristic: assume all version tags have a digit. The old git %d + # expansion behaves like git log --decorate=short and strips out the + # refs/heads/ and refs/tags/ prefixes that would let us distinguish + # between branches and tags. By ignoring refnames without digits, we + # filter out many common branch names like "release" and + # "stabilization", as well as "HEAD" and "master". + tags = {r for r in refs if re.search(r"\d", r)} + if verbose: + print("discarding '%s', no digits" % ",".join(refs - tags)) + if verbose: + print("likely tags: %s" % ",".join(sorted(tags))) + for ref in sorted(tags): + # sorting will prefer e.g. "2.0" over "2.0rc1" + if ref.startswith(tag_prefix): + r = ref[len(tag_prefix) :] + # Filter out refs that exactly match prefix or that don't start + # with a number once the prefix is stripped (mostly a concern + # when prefix is '') + if not re.match(r"\d", r): + continue + if verbose: + print("picking %s" % r) + return { + "version": r, + "full-revisionid": keywords["full"].strip(), + "dirty": False, + "error": None, + "date": date, + } + # no suitable tags, so version is "0+unknown", but full hex is still there + if verbose: + print("no suitable tags, using unknown + full revision id") + return { + "version": "0+unknown", + "full-revisionid": keywords["full"].strip(), + "dirty": False, + "error": "no suitable tags", + "date": None, + } + + +@register_vcs_handler("git", "pieces_from_vcs") +def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command): + """Get version from 'git describe' in the root of the source tree. + + This only gets called if the git-archive 'subst' keywords were *not* + expanded, and _version.py hasn't already been rewritten with a short + version string, meaning we're inside a checked out source tree. + """ + GITS = ["git"] + TAG_PREFIX_REGEX = "*" + if sys.platform == "win32": + GITS = ["git.cmd", "git.exe"] + TAG_PREFIX_REGEX = r"\*" + + _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=True) + if rc != 0: + if verbose: + print("Directory %s not under git control" % root) + raise NotThisMethod("'git rev-parse --git-dir' returned error") + + # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty] + # if there isn't one, this yields HEX[-dirty] (no NUM) + describe_out, rc = runner( + GITS, + [ + "describe", + "--tags", + "--dirty", + "--always", + "--long", + "--match", + "%s%s" % (tag_prefix, TAG_PREFIX_REGEX), + ], + cwd=root, + ) + # --long was added in git-1.5.5 + if describe_out is None: + raise NotThisMethod("'git describe' failed") + describe_out = describe_out.strip() + full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root) + if full_out is None: + raise NotThisMethod("'git rev-parse' failed") + full_out = full_out.strip() + + pieces = {} + pieces["long"] = full_out + pieces["short"] = full_out[:7] # maybe improved later + pieces["error"] = None + + branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], cwd=root) + # --abbrev-ref was added in git-1.6.3 + if rc != 0 or branch_name is None: + raise NotThisMethod("'git rev-parse --abbrev-ref' returned error") + branch_name = branch_name.strip() + + if branch_name == "HEAD": + # If we aren't exactly on a branch, pick a branch which represents + # the current commit. If all else fails, we are on a branchless + # commit. + branches, rc = runner(GITS, ["branch", "--contains"], cwd=root) + # --contains was added in git-1.5.4 + if rc != 0 or branches is None: + raise NotThisMethod("'git branch --contains' returned error") + branches = branches.split("\n") + + # Remove the first line if we're running detached + if "(" in branches[0]: + branches.pop(0) + + # Strip off the leading "* " from the list of branches. + branches = [branch[2:] for branch in branches] + if "master" in branches: + branch_name = "master" + elif not branches: + branch_name = None + else: + # Pick the first branch that is returned. Good or bad. + branch_name = branches[0] + + pieces["branch"] = branch_name + + # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty] + # TAG might have hyphens. + git_describe = describe_out + + # look for -dirty suffix + dirty = git_describe.endswith("-dirty") + pieces["dirty"] = dirty + if dirty: + git_describe = git_describe[: git_describe.rindex("-dirty")] + + # now we have TAG-NUM-gHEX or HEX + + if "-" in git_describe: + # TAG-NUM-gHEX + mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe) + if not mo: + # unparsable. Maybe git-describe is misbehaving? + pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out + return pieces + + # tag + full_tag = mo.group(1) + if not full_tag.startswith(tag_prefix): + if verbose: + fmt = "tag '%s' doesn't start with prefix '%s'" + print(fmt % (full_tag, tag_prefix)) + pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % ( + full_tag, + tag_prefix, + ) + return pieces + pieces["closest-tag"] = full_tag[len(tag_prefix) :] + + # distance: number of commits since tag + pieces["distance"] = int(mo.group(2)) + + # commit: short hex revision ID + pieces["short"] = mo.group(3) + + else: + # HEX: no tags + pieces["closest-tag"] = None + count_out, rc = runner(GITS, ["rev-list", "HEAD", "--count"], cwd=root) + pieces["distance"] = int(count_out) # total number of commits + + # commit date: see ISO-8601 comment in git_versions_from_keywords() + date = runner(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip() + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + + return pieces + + +def plus_or_dot(pieces): + """Return a + if we don't already have one, else return a .""" + if "+" in pieces.get("closest-tag", ""): + return "." + return "+" + + +def render_pep440(pieces): + """Build up version string, with post-release "local version identifier". + + Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you + get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty + + Exceptions: + 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += plus_or_dot(pieces) + rendered += "%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_branch(pieces): + """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] . + + The ".dev0" means not master branch. Note that .dev0 sorts backwards + (a feature branch will appear "older" than the master branch). + + Exceptions: + 1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0" + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+untagged.%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def pep440_split_post(ver): + """Split pep440 version string at the post-release segment. + + Returns the release segments before the post-release and the + post-release version number (or -1 if no post-release segment is present). + """ + vc = str.split(ver, ".post") + return vc[0], int(vc[1] or 0) if len(vc) == 2 else None + + +def render_pep440_pre(pieces): + """TAG[.postN.devDISTANCE] -- No -dirty. + + Exceptions: + 1: no tags. 0.post0.devDISTANCE + """ + if pieces["closest-tag"]: + if pieces["distance"]: + # update the post release segment + tag_version, post_version = pep440_split_post(pieces["closest-tag"]) + rendered = tag_version + if post_version is not None: + rendered += ".post%d.dev%d" % (post_version + 1, pieces["distance"]) + else: + rendered += ".post0.dev%d" % (pieces["distance"]) + else: + # no commits, use the tag as the version + rendered = pieces["closest-tag"] + else: + # exception #1 + rendered = "0.post0.dev%d" % pieces["distance"] + return rendered + + +def render_pep440_post(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX] . + + The ".dev0" means dirty. Note that .dev0 sorts backwards + (a dirty tree will appear "older" than the corresponding clean one), + but you shouldn't be releasing software with -dirty anyways. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%s" % pieces["short"] + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += "+g%s" % pieces["short"] + return rendered + + +def render_pep440_post_branch(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] . + + The ".dev0" means not master branch. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%s" % pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+g%s" % pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_old(pieces): + """TAG[.postDISTANCE[.dev0]] . + + The ".dev0" means dirty. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + return rendered + + +def render_git_describe(pieces): + """TAG[-DISTANCE-gHEX][-dirty]. + + Like 'git describe --tags --dirty --always'. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"]: + rendered += "-%d-g%s" % (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render_git_describe_long(pieces): + """TAG-DISTANCE-gHEX[-dirty]. + + Like 'git describe --tags --dirty --always -long'. + The distance/hash is unconditional. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + rendered += "-%d-g%s" % (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render(pieces, style): + """Render the given version pieces into the requested style.""" + if pieces["error"]: + return { + "version": "unknown", + "full-revisionid": pieces.get("long"), + "dirty": None, + "error": pieces["error"], + "date": None, + } + + if not style or style == "default": + style = "pep440" # the default + + if style == "pep440": + rendered = render_pep440(pieces) + elif style == "pep440-branch": + rendered = render_pep440_branch(pieces) + elif style == "pep440-pre": + rendered = render_pep440_pre(pieces) + elif style == "pep440-post": + rendered = render_pep440_post(pieces) + elif style == "pep440-post-branch": + rendered = render_pep440_post_branch(pieces) + elif style == "pep440-old": + rendered = render_pep440_old(pieces) + elif style == "git-describe": + rendered = render_git_describe(pieces) + elif style == "git-describe-long": + rendered = render_git_describe_long(pieces) + else: + raise ValueError("unknown style '%s'" % style) + + return { + "version": rendered, + "full-revisionid": pieces["long"], + "dirty": pieces["dirty"], + "error": None, + "date": pieces.get("date"), + } + + +def get_versions(): + """Get version information or return default if unable to do so.""" + # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have + # __file__, we can work backwards from there to the root. Some + # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which + # case we can only use expanded keywords. + + cfg = get_config() + verbose = cfg.verbose + + try: + return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, verbose) + except NotThisMethod: + pass + + try: + root = os.path.realpath(__file__) + # versionfile_source is the relative path from the top of the source + # tree (where the .git directory might live) to this file. Invert + # this to find the root from __file__. + for _ in cfg.versionfile_source.split("/"): + root = os.path.dirname(root) + except NameError: + return { + "version": "0+unknown", + "full-revisionid": None, + "dirty": None, + "error": "unable to find root of source tree", + "date": None, + } + + try: + pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose) + return render(pieces, cfg.style) + except NotThisMethod: + pass + + try: + if cfg.parentdir_prefix: + return versions_from_parentdir(cfg.parentdir_prefix, root, verbose) + except NotThisMethod: + pass + + return { + "version": "0+unknown", + "full-revisionid": None, + "dirty": None, + "error": "unable to compute version", + "date": None, + } diff --git a/prefect_datahub/datahub_emitter.py b/prefect_datahub/datahub_emitter.py new file mode 100644 index 0000000..c574c49 --- /dev/null +++ b/prefect_datahub/datahub_emitter.py @@ -0,0 +1,622 @@ +"""Datahub Emitter classes used to emit prefect metadata to Datahub REST.""" + +import asyncio +import traceback +from typing import Dict, List, Optional +from uuid import UUID + +from datahub.api.entities.datajob import DataFlow, DataJob +from datahub.api.entities.dataprocess.dataprocess_instance import ( + DataProcessInstance, + InstanceRunResult, +) +from datahub.emitter.mcp import MetadataChangeProposalWrapper +from datahub.emitter.rest_emitter import DatahubRestEmitter +from datahub.metadata.schema_classes import BrowsePathsClass +from datahub.utilities.urns.data_flow_urn import DataFlowUrn +from datahub.utilities.urns.data_job_urn import DataJobUrn +from datahub.utilities.urns.dataset_urn import DatasetUrn +from datahub_provider.entities import _Entity +from prefect import get_run_logger +from prefect.blocks.core import Block +from prefect.client import cloud, orchestration +from prefect.client.schemas import FlowRun, TaskRun, Workspace +from prefect.client.schemas.objects import Flow +from prefect.context import FlowRunContext, TaskRunContext +from prefect.settings import PREFECT_API_URL +from pydantic import Field + +ORCHESTRATOR = "prefect" + +# Flow and task common constants +VERSION = "version" +RETRIES = "retries" +TIMEOUT_SECONDS = "timeout_seconds" +LOG_PRINTS = "log_prints" +ON_COMPLETION = "on_completion" +ON_FAILURE = "on_failure" + +# Flow constants +FLOW_RUN_NAME = "flow_run_name" +TASK_RUNNER = "task_runner" +PERSIST_RESULT = "persist_result" +ON_CANCELLATION = "on_cancellation" +ON_CRASHED = "on_crashed" + +# Task constants +CACHE_EXPIRATION = "cache_expiration" +TASK_RUN_NAME = "task_run_name" +REFRESH_CACHE = "refresh_cache" +TASK_KEY = "task_key" + +# Flow run and task run common constants +ID = "id" +CREATED = "created" +UPDATED = "updated" +TAGS = "tags" +ESTIMATED_RUN_TIME = "estimated_run_time" +START_TIME = "start_time" +END_TIME = "end_time" +TOTAL_RUN_TIME = "total_run_time" +NEXT_SCHEDULED_START_TIME = "next_scheduled_start_time" + +# Fask run constants +CREATED_BY = "created_by" +AUTO_SCHEDULED = "auto_scheduled" + +# Task run constants +FLOW_RUN_ID = "flow_run_id" +RUN_COUNT = "run_count" +UPSTREAM_DEPENDENCIES = "upstream_dependencies" + +# States constants +COMPLETE = "Completed" +FAILED = "Failed" +CANCELLED = "Cancelled" + + +class DatahubEmitter(Block): + """ + Block used to emit prefect task and flow related metadata to Datahub REST + + Attributes: + datahub_rest_url Optional(str) : Datahub GMS Rest URL. \ + Example: http://localhost:8080. + env Optional(str) : The environment that all assets produced by this \ + orchestrator belong to. For more detail and possible values refer \ + https://datahubproject.io/docs/graphql/enums/#fabrictype. + platform_instance Optional(str) : The instance of the platform that all assets \ + produced by this recipe belong to. For more detail please refer to \ + https://datahubproject.io/docs/platform-instances/. + + Example: + Store value: + ```python + from prefect_datahub import DatahubEmitter + DatahubEmitter( + datahub_rest_url="http://localhost:8080", + env="PROD", + platform_instance="local_prefect" + ).save("BLOCK_NAME") + ``` + Load a stored value: + ```python + from prefect_datahub import DatahubEmitter + block = DatahubEmitter.load("BLOCK_NAME") + ``` + """ + + _block_type_name = "datahub emitter" + # replace this with a relevant logo; defaults to Prefect logo + _logo_url = "https://datahubproject.io/img/datahub-logo-color-mark.svg" # noqa + _documentation_url = "https://shubhamjagtap639.github.io/prefect-datahub/datahub_emitter/#prefect-datahub.datahub_emitter.DatahubEmitter" # noqa + + datahub_rest_url: Optional[str] = Field( + default="http://localhost:8080", + title="Datahub rest url", + description="Datahub GMS Rest URL. Example: http://localhost:8080", + ) + + env: Optional[str] = Field( + default="prod", + title="Environment", + description="The environment that all assets produced by this orchestrator " + "belong to. For more detail and possible values refer " + "https://datahubproject.io/docs/graphql/enums/#fabrictype.", + ) + + platform_instance: Optional[str] = Field( + default=None, + title="Platform instance", + description="The instance of the platform that all assets produced by this " + "recipe belong to. For more detail please refer to " + "https://datahubproject.io/docs/platform-instances/.", + ) + + def __init__(self, *args, **kwargs): + """ + Initialize datahub rest emitter + """ + super().__init__(*args, **kwargs) + self.datajobs_to_emit: Dict[str, DataJob] = {} + self.emitter = DatahubRestEmitter(gms_server=self.datahub_rest_url) + self.emitter.test_connection() + + def _entities_to_urn_list(self, iolets: List[_Entity]) -> List[DatasetUrn]: + """ + Convert list of _entity to list of dataser urn + + Args: + iolets (list[_Entity]): The list of entities. + + Returns: + The list of Dataset URN. + """ + return [DatasetUrn.create_from_string(let.urn) for let in iolets] + + def _get_workspace(self) -> Optional[str]: + """ + Fetch workspace name if present in configured prefect api url. + + Returns: + The workspace name. + """ + try: + asyncio.run(cloud.get_cloud_client().api_healthcheck()) + except Exception: + get_run_logger().debug(traceback.format_exc()) + return None + if "workspaces" not in PREFECT_API_URL.value(): + get_run_logger().debug( + "Cannot fetch workspace name. Please login to prefect cloud using " + "command 'prefect cloud login'." + ) + return None + current_workspace_id = PREFECT_API_URL.value().split("/")[-1] + workspaces: List[Workspace] = asyncio.run( + cloud.get_cloud_client().read_workspaces() + ) + for workspace in workspaces: + if str(workspace.workspace_id) == current_workspace_id: + return workspace.workspace_name + return None + + async def _get_flow_run_graph(self, flow_run_id: str) -> Optional[List[Dict]]: + """ + Fetch the flow run graph for provided flow run id + + Args: + flow_run_id (str): The flow run id. + + Returns: + The flow run graph in json format. + """ + try: + response = await orchestration.get_client()._client.get( + f"/flow_runs/{flow_run_id}/graph" + ) + except Exception: + get_run_logger().debug(traceback.format_exc()) + return None + return response.json() + + def _emit_browsepath(self, urn: str, workspace_name: str) -> None: + """ + Emit browsepath for provided urn. Set path as orchestrator/env/workspace_name. + + Args: + urn (str): The entity URN + workspace_name (str): The prefect cloud workspace name + """ + mcp = MetadataChangeProposalWrapper( + entityUrn=urn, + aspect=BrowsePathsClass( + paths=[f"/{ORCHESTRATOR}/{self.env}/{workspace_name}"] + ), + ) + self.emitter.emit(mcp) + + def _generate_datajob( + self, + flow_run_ctx: FlowRunContext, + task_run_ctx: Optional[TaskRunContext] = None, + task_key: Optional[str] = None, + ) -> Optional[DataJob]: + """ + Create datajob entity using task run ctx and flow run ctx. + Assign description, tags, and properties to created datajob. + + Args: + flow_run_ctx (FlowRunContext): The prefect current running flow run context. + task_run_ctx (Optional[TaskRunContext]): The prefect current running task \ + run context. + task_key (Optional[str]): The task key. + + Returns: + The datajob entity. + """ + dataflow_urn = DataFlowUrn.create_from_ids( + orchestrator=ORCHESTRATOR, + flow_id=flow_run_ctx.flow.name, + env=self.env, + platform_instance=self.platform_instance, + ) + if task_run_ctx is not None: + datajob = DataJob( + id=task_run_ctx.task.task_key, + flow_urn=dataflow_urn, + name=task_run_ctx.task.name, + ) + + datajob.description = task_run_ctx.task.description + datajob.tags = task_run_ctx.task.tags + job_property_bag: Dict[str, str] = {} + + allowed_task_keys = [ + VERSION, + CACHE_EXPIRATION, + TASK_RUN_NAME, + RETRIES, + TIMEOUT_SECONDS, + LOG_PRINTS, + REFRESH_CACHE, + TASK_KEY, + ON_COMPLETION, + ON_FAILURE, + ] + for key in allowed_task_keys: + if ( + hasattr(task_run_ctx.task, key) + and getattr(task_run_ctx.task, key) is not None + ): + job_property_bag[key] = repr(getattr(task_run_ctx.task, key)) + datajob.properties = job_property_bag + return datajob + elif task_key is not None: + datajob = DataJob( + id=task_key, flow_urn=dataflow_urn, name=task_key.split(".")[-1] + ) + return datajob + return None + + def _generate_dataflow(self, flow_run_ctx: FlowRunContext) -> Optional[DataFlow]: + """ + Create dataflow entity using flow run ctx. + Assign description, tags, and properties to created dataflow. + + Args: + flow_run_ctx (FlowRunContext): The prefect current running flow run context. + + Returns: + The dataflow entity. + """ + try: + flow: Flow = asyncio.run( + orchestration.get_client().read_flow( + flow_id=flow_run_ctx.flow_run.flow_id + ) + ) + except Exception: + get_run_logger().debug(traceback.format_exc()) + return None + assert flow + + dataflow = DataFlow( + orchestrator=ORCHESTRATOR, + id=flow_run_ctx.flow.name, + env=self.env, + name=flow_run_ctx.flow.name, + platform_instance=self.platform_instance, + ) + dataflow.description = flow_run_ctx.flow.description + dataflow.tags = flow.tags + flow_property_bag: Dict[str, str] = {} + flow_property_bag[ID] = str(flow.id) + flow_property_bag[CREATED] = str(flow.created) + flow_property_bag[UPDATED] = str(flow.updated) + + allowed_flow_keys = [ + VERSION, + FLOW_RUN_NAME, + RETRIES, + TASK_RUNNER, + TIMEOUT_SECONDS, + PERSIST_RESULT, + LOG_PRINTS, + ON_COMPLETION, + ON_FAILURE, + ON_CANCELLATION, + ON_CRASHED, + ] + for key in allowed_flow_keys: + if ( + hasattr(flow_run_ctx.flow, key) + and getattr(flow_run_ctx.flow, key) is not None + ): + flow_property_bag[key] = repr(getattr(flow_run_ctx.flow, key)) + dataflow.properties = flow_property_bag + + return dataflow + + def _emit_tasks( + self, + flow_run_ctx: FlowRunContext, + dataflow: DataFlow, + workspace_name: Optional[str] = None, + ) -> None: + """ + Emit prefect tasks metadata to datahub rest. Add upstream dependencies if + present for each task. + + Args: + flow_run_ctx (FlowRunContext): The prefect current running flow run context + dataflow (DataFlow): The datahub dataflow entity. + workspace_name Optional(str): The prefect cloud workpace name. + """ + graph_json = asyncio.run( + self._get_flow_run_graph(str(flow_run_ctx.flow_run.id)) + ) + if graph_json is None: + return + + task_run_key_map = { + str(prefect_future.task_run.id): prefect_future.task_run.task_key + for prefect_future in flow_run_ctx.task_run_futures + } + + get_run_logger().info("Emitting tasks to datahub...") + + for node in graph_json: + datajob_urn = DataJobUrn.create_from_ids( + data_flow_urn=str(dataflow.urn), + job_id=task_run_key_map[node[ID]], + ) + if str(datajob_urn) in self.datajobs_to_emit: + datajob = self.datajobs_to_emit[str(datajob_urn)] + else: + datajob = self._generate_datajob( + flow_run_ctx=flow_run_ctx, task_key=task_run_key_map[node[ID]] + ) + for each in node[UPSTREAM_DEPENDENCIES]: + upstream_task_urn = DataJobUrn.create_from_ids( + data_flow_urn=str(dataflow.urn), + job_id=task_run_key_map[each[ID]], + ) + datajob.upstream_urns.extend([upstream_task_urn]) + datajob.emit(self.emitter) + + if workspace_name is not None: + self._emit_browsepath(str(datajob.urn), workspace_name) + + self._emit_task_run( + datajob=datajob, + flow_run_name=flow_run_ctx.flow_run.name, + task_run_id=node[ID], + ) + + def _emit_flow_run(self, dataflow: DataFlow, flow_run_id: UUID) -> None: + """ + Emit prefect flow run to datahub rest. Prefect flow run get mapped with datahub + data process instance entity which get's generate from provided dataflow entity. + Assign flow run properties to data process instance properties. + + Args: + dataflow (DataFlow): The datahub dataflow entity used to create \ + data process instance. + flow_run_id (UUID): The prefect current running flow run id. + """ + try: + flow_run: FlowRun = asyncio.run( + orchestration.get_client().read_flow_run(flow_run_id=flow_run_id) + ) + except Exception: + get_run_logger().debug(traceback.format_exc()) + return + assert flow_run + + if self.platform_instance is not None: + dpi_id = f"{self.platform_instance}.{flow_run.name}" + else: + dpi_id = flow_run.name + dpi = DataProcessInstance.from_dataflow(dataflow=dataflow, id=dpi_id) + + dpi_property_bag: Dict[str, str] = {} + allowed_flow_run_keys = [ + ID, + CREATED, + UPDATED, + CREATED_BY, + AUTO_SCHEDULED, + ESTIMATED_RUN_TIME, + START_TIME, + TOTAL_RUN_TIME, + NEXT_SCHEDULED_START_TIME, + TAGS, + RUN_COUNT, + ] + for key in allowed_flow_run_keys: + if hasattr(flow_run, key) and getattr(flow_run, key) is not None: + dpi_property_bag[key] = str(getattr(flow_run, key)) + dpi.properties.update(dpi_property_bag) + + dpi.emit_process_start( + emitter=self.emitter, + start_timestamp_millis=int(flow_run.start_time.timestamp() * 1000), + ) + + def _emit_task_run( + self, datajob: DataJob, flow_run_name: str, task_run_id: str + ) -> None: + """ + Emit prefect task run to datahub rest. Prefect task run get mapped with datahub + data process instance entity which get's generate from provided datajob entity. + Assign task run properties to data process instance properties. + + Args: + datajob (DataJob): The datahub datajob entity used to create \ + data process instance. + flow_run_name (str): The prefect current running flow run name. + task_run_id (str): The prefect task run id. + """ + try: + task_run: TaskRun = asyncio.run( + orchestration.get_client().read_task_run(task_run_id) + ) + except Exception: + get_run_logger().debug(traceback.format_exc()) + return + assert task_run + + if self.platform_instance is not None: + dpi_id = f"{self.platform_instance}.{flow_run_name}.{task_run.name}" + else: + dpi_id = f"{flow_run_name}.{task_run.name}" + dpi = DataProcessInstance.from_datajob( + datajob=datajob, + id=dpi_id, + clone_inlets=True, + clone_outlets=True, + ) + + dpi_property_bag: Dict[str, str] = {} + allowed_task_run_keys = [ + ID, + FLOW_RUN_ID, + CREATED, + UPDATED, + ESTIMATED_RUN_TIME, + START_TIME, + END_TIME, + TOTAL_RUN_TIME, + NEXT_SCHEDULED_START_TIME, + TAGS, + RUN_COUNT, + ] + for key in allowed_task_run_keys: + if hasattr(task_run, key) and getattr(task_run, key) is not None: + dpi_property_bag[key] = str(getattr(task_run, key)) + dpi.properties.update(dpi_property_bag) + + state_result_map: Dict[str, str] = { + COMPLETE: InstanceRunResult.SUCCESS, + FAILED: InstanceRunResult.FAILURE, + CANCELLED: InstanceRunResult.SKIPPED, + } + + if task_run.state_name not in state_result_map: + raise Exception( + f"State should be either complete, failed or cancelled and it was " + f"{task_run.state_name}" + ) + + result = state_result_map[task_run.state_name] + + dpi.emit_process_start( + emitter=self.emitter, + start_timestamp_millis=int(task_run.start_time.timestamp() * 1000), + emit_template=False, + ) + + dpi.emit_process_end( + emitter=self.emitter, + end_timestamp_millis=int(task_run.end_time.timestamp() * 1000), + result=result, + result_type=ORCHESTRATOR, + ) + + def add_task( + self, + inputs: Optional[List[_Entity]] = None, + outputs: Optional[List[_Entity]] = None, + ) -> None: + """ + Store prefect current running task metadata temporarily which later get emit + to datahub rest only if user calls emit_flow. Prefect task gets mapped with + datahub datajob entity. Assign provided inputs and outputs as datajob inlets + and outlets respectively. + + Args: + inputs (Optional[list]): The list of task inputs. + outputs (Optional[list]): The list of task outputs. + + Example: + Emit the task metadata as show below: + ```python + from datahub_provider.entities import Dataset + from prefect import flow, task + + from prefect_datahub import DatahubEmitter + + datahub_emitter = DatahubEmitter.load("MY_BLOCK_NAME") + + @task(name="Transform", description="Transform the data") + def transform(data): + data = data.split(" ") + datahub_emitter.add_task( + inputs=[Dataset("snowflake", "mydb.schema.tableA")], + outputs=[Dataset("snowflake", "mydb.schema.tableC")], + ) + return data + + @flow(name="ETL flow", description="Extract transform load flow") + def etl(): + data = transform("This is data") + datahub_emitter.emit_flow() + ``` + """ + flow_run_ctx = FlowRunContext.get() + task_run_ctx = TaskRunContext.get() + assert flow_run_ctx + assert task_run_ctx + + datajob = self._generate_datajob( + flow_run_ctx=flow_run_ctx, task_run_ctx=task_run_ctx + ) + if inputs is not None: + datajob.inlets.extend(self._entities_to_urn_list(inputs)) + if outputs is not None: + datajob.outlets.extend(self._entities_to_urn_list(outputs)) + self.datajobs_to_emit[str(datajob.urn)] = datajob + + def emit_flow(self) -> None: + """ + Emit prefect current running flow metadata to datahub rest. Prefect flow gets + mapped with datahub dataflow entity. If the user hasn't called add_task in + the task function still emit_flow will emit a task but without task name, + description,tags and properties. + + + Example: + Emit the flow metadata as show below: + ```python + from prefect import flow, task + + from prefect_datahub import DatahubEmitter + + datahub_emitter = DatahubEmitter.load("MY_BLOCK_NAME") + + @flow(name="ETL flow", description="Extract transform load flow") + def etl(): + data = extract() + data = transform(data) + load(data) + datahub_emitter.emit_flow() + ``` + """ + flow_run_ctx = FlowRunContext.get() + assert flow_run_ctx + + workspace_name = self._get_workspace() + + # Emit flow and flow run + dataflow = self._generate_dataflow(flow_run_ctx=flow_run_ctx) + get_run_logger().info("Emitting flow to datahub...") + + dataflow.emit(self.emitter) + + if workspace_name is not None: + self._emit_browsepath(str(dataflow.urn), workspace_name) + + self._emit_flow_run(dataflow, flow_run_ctx.flow_run.id) + + self._emit_tasks(flow_run_ctx, dataflow, workspace_name) diff --git a/requirements-dev.txt b/requirements-dev.txt new file mode 100644 index 0000000..8f50f4d --- /dev/null +++ b/requirements-dev.txt @@ -0,0 +1,15 @@ +pytest +black +flake8 +mypy +mkdocs +mkdocs-material +mkdocstrings[python] +isort +pre-commit +pytest-asyncio +mock; python_version < '3.8' +mkdocs-gen-files +interrogate +coverage +pillow \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..c4df23d --- /dev/null +++ b/requirements.txt @@ -0,0 +1,2 @@ +prefect==2.10.16 +acryl-datahub[datahub-rest] \ No newline at end of file diff --git a/setup.cfg b/setup.cfg new file mode 100644 index 0000000..17d7e84 --- /dev/null +++ b/setup.cfg @@ -0,0 +1,39 @@ +[flake8] +exclude = .git,__pycache__,build,dist +per-file-ignores = + setup.py:E501 +# Match black line-length +max-line-length = 88 +extend-ignore = + E203, + +[isort] +skip = __init__.py +profile = black +skip_gitignore = True +multi_line_output = 3 + +[versioneer] +VCS = git +style = pep440 +versionfile_source = prefect_datahub/_version.py +versionfile_build = prefect_datahub/_version.py +tag_prefix = v +parentdir_prefix = + +[tool:interrogate] +ignore-init-module = True +ignore_init_method = True +exclude = prefect_datahub/_version.py, tests, setup.py, versioneer.py, docs, site +fail-under = 95 +omit-covered-files = True + +[coverage:run] +omit = tests/*, prefect_datahub/_version.py + +[coverage:report] +fail_under = 80 +show_missing = True + +[tool:pytest] +asyncio_mode = auto diff --git a/setup.py b/setup.py new file mode 100644 index 0000000..64d379b --- /dev/null +++ b/setup.py @@ -0,0 +1,47 @@ +from setuptools import find_packages, setup + +import versioneer + +with open("requirements.txt") as install_requires_file: + install_requires = install_requires_file.read().strip().split("\n") + +with open("requirements-dev.txt") as dev_requires_file: + dev_requires = dev_requires_file.read().strip().split("\n") + +with open("README.md") as readme_file: + readme = readme_file.read() + +setup( + name="prefect-datahub", + description="Metadata emitter for datahub", + license="Apache License 2.0", + author="Acryl Data", + author_email="shubham.jagtap@gslab.com", + keywords="prefect", + url="https://github.com/PrefectHQ/prefect-datahub", + long_description=readme, + long_description_content_type="text/markdown", + version=versioneer.get_version(), + cmdclass=versioneer.get_cmdclass(), + packages=find_packages(exclude=("tests", "docs")), + python_requires=">=3.7", + install_requires=install_requires, + extras_require={"dev": dev_requires}, + entry_points={ + "prefect.collections": [ + "prefect_datahub = prefect_datahub", + ] + }, + classifiers=[ + "Natural Language :: English", + "Intended Audience :: Developers", + "Intended Audience :: System Administrators", + "License :: OSI Approved :: Apache Software License", + "Programming Language :: Python :: 3 :: Only", + "Programming Language :: Python :: 3.7", + "Programming Language :: Python :: 3.8", + "Programming Language :: Python :: 3.9", + "Programming Language :: Python :: 3.10", + "Topic :: Software Development :: Libraries", + ], +) diff --git a/tests/conftest.py b/tests/conftest.py new file mode 100644 index 0000000..75b7f43 --- /dev/null +++ b/tests/conftest.py @@ -0,0 +1,487 @@ +import asyncio +import json +import logging +from unittest.mock import MagicMock, patch +from uuid import UUID + +import pytest +from prefect.client.schemas import FlowRun, TaskRun, Workspace +from prefect.futures import PrefectFuture +from prefect.server.schemas.core import Flow +from requests.models import Response + +mock_transform_task_json = { + "name": "transform", + "description": "Transform the actual data", + "task_key": "__main__.transform", + "tags": ["etl flow task"], +} +mock_extract_task_run_json = { + "id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b", + "created": "2023-06-06T05:51:54.822707+00:00", + "updated": "2023-06-06T05:51:55.126000+00:00", + "name": "Extract-0", + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_key": "__main__.extract", + "dynamic_key": "0", + "cache_key": None, + "cache_expiration": None, + "task_version": None, + "empirical_policy": { + "max_retries": 0, + "retry_delay_seconds": 0.0, + "retries": 0, + "retry_delay": 0, + "retry_jitter_factor": None, + }, + "tags": [], + "state_id": "e280decd-2cc8-4428-a70f-149bcaf95b3c", + "task_inputs": {}, + "state_type": "COMPLETED", + "state_name": "Completed", + "run_count": 1, + "flow_run_run_count": 1, + "expected_start_time": "2023-06-06T05:51:54.822183+00:00", + "next_scheduled_start_time": None, + "start_time": "2023-06-06T05:51:55.016264+00:00", + "end_time": "2023-06-06T05:51:55.096534+00:00", + "total_run_time": 0.08027, + "estimated_run_time": 0.08027, + "estimated_start_time_delta": 0.194081, + "state": { + "id": "e280decd-2cc8-4428-a70f-149bcaf95b3c", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.096534+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": False, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, +} +mock_transform_task_run_json = { + "id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7", + "created": "2023-06-06T05:51:55.160372+00:00", + "updated": "2023-06-06T05:51:55.358000+00:00", + "name": "transform-0", + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_key": "__main__.transform", + "dynamic_key": "0", + "cache_key": None, + "cache_expiration": None, + "task_version": None, + "empirical_policy": { + "max_retries": 0, + "retry_delay_seconds": 0.0, + "retries": 0, + "retry_delay": 0, + "retry_jitter_factor": None, + }, + "tags": [], + "state_id": "971ad82e-6e5f-4691-abab-c900358e96c2", + "task_inputs": { + "actual_data": [ + {"input_type": "task_run", "id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b"} + ] + }, + "state_type": "COMPLETED", + "state_name": "Completed", + "run_count": 1, + "flow_run_run_count": 1, + "expected_start_time": "2023-06-06T05:51:55.159416+00:00", + "next_scheduled_start_time": None, + "start_time": "2023-06-06T05:51:55.243159+00:00", + "end_time": "2023-06-06T05:51:55.332950+00:00", + "total_run_time": 0.089791, + "estimated_run_time": 0.089791, + "estimated_start_time_delta": 0.083743, + "state": { + "id": "971ad82e-6e5f-4691-abab-c900358e96c2", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.332950+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": False, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, +} +mock_load_task_run_json = { + "id": "f19f83ea-316f-4781-8cbe-1d5d8719afc3", + "created": "2023-06-06T05:51:55.389823+00:00", + "updated": "2023-06-06T05:51:55.566000+00:00", + "name": "Load_task-0", + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_key": "__main__.load", + "dynamic_key": "0", + "cache_key": None, + "cache_expiration": None, + "task_version": None, + "empirical_policy": { + "max_retries": 0, + "retry_delay_seconds": 0.0, + "retries": 0, + "retry_delay": 0, + "retry_jitter_factor": None, + }, + "tags": [], + "state_id": "0cad13c8-84e4-4bcf-8616-c5904e10dcb4", + "task_inputs": { + "data": [ + {"input_type": "task_run", "id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7"} + ] + }, + "state_type": "COMPLETED", + "state_name": "Completed", + "run_count": 1, + "flow_run_run_count": 1, + "expected_start_time": "2023-06-06T05:51:55.389075+00:00", + "next_scheduled_start_time": None, + "start_time": "2023-06-06T05:51:55.461812+00:00", + "end_time": "2023-06-06T05:51:55.535954+00:00", + "total_run_time": 0.074142, + "estimated_run_time": 0.074142, + "estimated_start_time_delta": 0.072737, + "state": { + "id": "0cad13c8-84e4-4bcf-8616-c5904e10dcb4", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.535954+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "f19f83ea-316f-4781-8cbe-1d5d8719afc3", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": True, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, +} +mock_flow_json = { + "id": "cc65498f-d950-4114-8cc1-7af9e8fdf91b", + "created": "2023-06-02T12:31:10.988697+00:00", + "updated": "2023-06-02T12:31:10.988710+00:00", + "name": "etl", + "description": "Extract transform load flow", + "tags": [], +} +mock_flow_run_json = { + "id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "created": "2023-06-06T05:51:54.544266+00:00", + "updated": "2023-06-06T05:51:55.622000+00:00", + "name": "olivine-beagle", + "flow_id": "cc65498f-d950-4114-8cc1-7af9e8fdf91b", + "state_id": "ca2db325-d98f-40e7-862e-449cd0cc9a6e", + "deployment_id": None, + "work_queue_name": None, + "flow_version": "3ba54dfa31a7c9af4161aa4cd020a527", + "parameters": {}, + "idempotency_key": None, + "context": {}, + "empirical_policy": { + "max_retries": 0, + "retry_delay_seconds": 0.0, + "retries": 0, + "retry_delay": 0, + "pause_keys": [], + "resuming": False, + }, + "tags": [], + "parent_task_run_id": None, + "state_type": "COMPLETED", + "state_name": "Completed", + "run_count": 1, + "expected_start_time": "2023-06-06T05:51:54.543357+00:00", + "next_scheduled_start_time": None, + "start_time": "2023-06-06T05:51:54.750523+00:00", + "end_time": "2023-06-06T05:51:55.596446+00:00", + "total_run_time": 0.845923, + "estimated_run_time": 0.845923, + "estimated_start_time_delta": 0.207166, + "auto_scheduled": False, + "infrastructure_document_id": None, + "infrastructure_pid": None, + "created_by": None, + "work_pool_name": None, + "state": { + "id": "ca2db325-d98f-40e7-862e-449cd0cc9a6e", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.596446+00:00", + "message": "All states completed.", + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": None, + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": False, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, +} +mock_graph_json = [ + { + "id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b", + "name": "Extract-0", + "upstream_dependencies": [], + "state": { + "id": "e280decd-2cc8-4428-a70f-149bcaf95b3c", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.096534+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": False, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, + "expected_start_time": "2023-06-06T05:51:54.822183+00:00", + "start_time": "2023-06-06T05:51:55.016264+00:00", + "end_time": "2023-06-06T05:51:55.096534+00:00", + "total_run_time": 0.08027, + "estimated_run_time": 0.08027, + "untrackable_result": False, + }, + { + "id": "f19f83ea-316f-4781-8cbe-1d5d8719afc3", + "name": "Load_task-0", + "upstream_dependencies": [ + {"input_type": "task_run", "id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7"} + ], + "state": { + "id": "0cad13c8-84e4-4bcf-8616-c5904e10dcb4", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.535954+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "f19f83ea-316f-4781-8cbe-1d5d8719afc3", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": True, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, + "expected_start_time": "2023-06-06T05:51:55.389075+00:00", + "start_time": "2023-06-06T05:51:55.461812+00:00", + "end_time": "2023-06-06T05:51:55.535954+00:00", + "total_run_time": 0.074142, + "estimated_run_time": 0.074142, + "untrackable_result": True, + }, + { + "id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7", + "name": "transform-0", + "upstream_dependencies": [ + {"input_type": "task_run", "id": "fa14a52b-d271-4c41-99cb-6b42ca7c070b"} + ], + "state": { + "id": "971ad82e-6e5f-4691-abab-c900358e96c2", + "type": "COMPLETED", + "name": "Completed", + "timestamp": "2023-06-06T05:51:55.332950+00:00", + "message": None, + "data": {"type": "unpersisted"}, + "state_details": { + "flow_run_id": "c3b947e5-3fa1-4b46-a2e2-58d50c938f2e", + "task_run_id": "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7", + "child_flow_run_id": None, + "scheduled_time": None, + "cache_key": None, + "cache_expiration": None, + "untrackable_result": False, + "pause_timeout": None, + "pause_reschedule": False, + "pause_key": None, + "refresh_cache": None, + }, + }, + "expected_start_time": "2023-06-06T05:51:55.159416+00:00", + "start_time": "2023-06-06T05:51:55.243159+00:00", + "end_time": "2023-06-06T05:51:55.332950+00:00", + "total_run_time": 0.089791, + "estimated_run_time": 0.089791, + "untrackable_result": False, + }, +] +mock_workspace_json = { + "account_id": "33e98cfe-ad06-4ceb-a500-c11148499f75", + "account_name": "shubhamjagtapgslabcom", + "account_handle": "shubhamjagtapgslabcom", + "workspace_id": "157eb822-1b3b-4338-ae80-98edd5d00cb9", + "workspace_name": "datahub", + "workspace_description": "", + "workspace_handle": "datahub", +} + + +async def mock_task_run_future(): + extract_prefect_future = PrefectFuture( + name=mock_extract_task_run_json["name"], + key=UUID("4552629a-ac04-4590-b286-27642292739f"), + task_runner=None, + ) + extract_prefect_future.task_run = TaskRun.parse_obj(mock_extract_task_run_json) + transform_prefect_future = PrefectFuture( + name=mock_transform_task_run_json["name"], + key=UUID("40fff3e5-5ef4-4b8b-9cc8-786f91bcc656"), + task_runner=None, + ) + transform_prefect_future.task_run = TaskRun.parse_obj(mock_transform_task_run_json) + load_prefect_future = PrefectFuture( + name=mock_load_task_run_json["name"], + key=UUID("7565f596-9eb0-4330-ba34-963e7839883e"), + task_runner=None, + ) + load_prefect_future.task_run = TaskRun.parse_obj(mock_load_task_run_json) + return [extract_prefect_future, transform_prefect_future, load_prefect_future] + + +@pytest.fixture(scope="module") +def mock_run_logger(): + with patch( + "prefect_datahub.datahub_emitter.get_run_logger", + return_value=logging.getLogger(), + ) as mock_logger: + yield mock_logger + + +@pytest.fixture(scope="module") +def mock_run_context(mock_run_logger): + task_run_ctx = MagicMock() + task_run_ctx.task.task_key = mock_transform_task_json["task_key"] + task_run_ctx.task.name = mock_transform_task_json["name"] + task_run_ctx.task.description = mock_transform_task_json["description"] + task_run_ctx.task.tags = mock_transform_task_json["tags"] + + flow_run_ctx = MagicMock() + flow_run_ctx.flow.name = mock_flow_json["name"] + flow_run_ctx.flow.description = mock_flow_json["description"] + flow_run_obj = FlowRun.parse_obj(mock_flow_run_json) + flow_run_ctx.flow_run.id = flow_run_obj.id + flow_run_ctx.flow_run.name = flow_run_obj.name + flow_run_ctx.flow_run.flow_id = flow_run_obj.flow_id + flow_run_ctx.flow_run.start_time = flow_run_obj.start_time + flow_run_ctx.task_run_futures = asyncio.run(mock_task_run_future()) + + with patch( + "prefect_datahub.datahub_emitter.TaskRunContext" + ) as mock_task_run_ctx, patch( + "prefect_datahub.datahub_emitter.FlowRunContext" + ) as mock_flow_run_ctx: + mock_task_run_ctx.get.return_value = task_run_ctx + mock_flow_run_ctx.get.return_value = flow_run_ctx + yield (task_run_ctx, flow_run_ctx) + + +async def mock_task_run(*args, **kwargs): + if args[0] == "fa14a52b-d271-4c41-99cb-6b42ca7c070b": + return TaskRun.parse_obj(mock_extract_task_run_json) + elif args[0] == "dd15ee83-5d28-4bf1-804f-f84eab9f9fb7": + return TaskRun.parse_obj(mock_transform_task_run_json) + elif args[0] == "f19f83ea-316f-4781-8cbe-1d5d8719afc3": + return TaskRun.parse_obj(mock_load_task_run_json) + return None + + +async def mock_flow(*args, **kwargs): + return Flow.parse_obj(mock_flow_json) + + +async def mock_flow_run(*args, **kwargs): + return FlowRun.parse_obj(mock_flow_run_json) + + +async def mock_flow_run_graph(*args, **kwargs): + response = Response() + response.status_code = 200 + response._content = json.dumps(mock_graph_json, separators=(",", ":")).encode( + "utf-8" + ) + return response + + +async def mock_api_healthcheck(*args, **kwargs): + return None + + +async def mock_read_workspaces(*args, **kwargs): + return [Workspace.parse_obj(mock_workspace_json)] + + +@pytest.fixture(scope="module") +def mock_prefect_client(): + prefect_client_mock = MagicMock() + prefect_client_mock.read_flow.side_effect = mock_flow + prefect_client_mock.read_flow_run.side_effect = mock_flow_run + prefect_client_mock.read_task_run.side_effect = mock_task_run + prefect_client_mock._client.get.side_effect = mock_flow_run_graph + with patch("prefect_datahub.datahub_emitter.orchestration") as mock_client: + mock_client.get_client.return_value = prefect_client_mock + yield prefect_client_mock + + +@pytest.fixture(scope="module") +def mock_prefect_cloud_client(): + prefect_cloud_client_mock = MagicMock() + prefect_cloud_client_mock.api_healthcheck.side_effect = mock_api_healthcheck + prefect_cloud_client_mock.read_workspaces.side_effect = mock_read_workspaces + with patch("prefect_datahub.datahub_emitter.cloud") as mock_client, patch( + "prefect_datahub.datahub_emitter.PREFECT_API_URL.value", + return_value="https://api.prefect.cloud/api/accounts/33e98cfe-ad06-4ceb-" + "a500-c11148499f75/workspaces/157eb822-1b3b-4338-ae80-98edd5d00cb9", + ): + mock_client.get_cloud_client.return_value = prefect_cloud_client_mock + yield prefect_cloud_client_mock diff --git a/tests/test_block_standards.py b/tests/test_block_standards.py new file mode 100644 index 0000000..496c128 --- /dev/null +++ b/tests/test_block_standards.py @@ -0,0 +1,22 @@ +import pytest +from prefect.blocks.core import Block +from prefect.testing.standard_test_suites import BlockStandardTestSuite +from prefect.utilities.dispatch import get_registry_for_type +from prefect.utilities.importtools import to_qualified_name + + +def find_module_blocks(): + blocks = get_registry_for_type(Block) + module_blocks = [ + block + for block in blocks.values() + if to_qualified_name(block).startswith("prefect_datahub") + ] + return module_blocks + + +@pytest.mark.parametrize("block", find_module_blocks()) +class TestAllBlocksAdhereToStandards(BlockStandardTestSuite): + @pytest.fixture + def block(self, block): + return block diff --git a/tests/test_datahub_emitter.py b/tests/test_datahub_emitter.py new file mode 100644 index 0000000..e696d15 --- /dev/null +++ b/tests/test_datahub_emitter.py @@ -0,0 +1,292 @@ +import asyncio +from unittest.mock import Mock, patch + +from datahub.api.entities.datajob import DataJob +from datahub.utilities.urns.dataset_urn import DatasetUrn +from datahub_provider.entities import Dataset +from prefect.context import FlowRunContext, TaskRunContext + +from prefect_datahub.datahub_emitter import DatahubEmitter + + +@patch("prefect_datahub.datahub_emitter.DatahubRestEmitter", autospec=True) +def test_entities_to_urn_list(mock_emit): + dataset_urn_list = DatahubEmitter()._entities_to_urn_list( + [Dataset("snowflake", "mydb.schema.tableA")] + ) + for dataset_urn in dataset_urn_list: + assert isinstance(dataset_urn, DatasetUrn) + + +@patch("prefect_datahub.datahub_emitter.DatahubRestEmitter", autospec=True) +def test_get_flow_run_graph(mock_emit, mock_prefect_client): + graph_json = asyncio.run( + DatahubEmitter()._get_flow_run_graph("c3b947e5-3fa1-4b46-a2e2-58d50c938f2e") + ) + assert isinstance(graph_json, list) + + +@patch("prefect_datahub.datahub_emitter.DatahubRestEmitter", autospec=True) +def test__get_workspace(mock_emit, mock_prefect_cloud_client): + workspace_name = DatahubEmitter()._get_workspace() + assert workspace_name == "datahub" + + +@patch("prefect_datahub.datahub_emitter.DatahubRestEmitter", autospec=True) +def test_add_task(mock_emit, mock_run_context): + mock_emitter = Mock() + mock_emit.return_value = mock_emitter + + datahub_emitter = DatahubEmitter() + inputs = [Dataset("snowflake", "mydb.schema.tableA")] + outputs = [Dataset("snowflake", "mydb.schema.tableC")] + datahub_emitter.add_task( + inputs=inputs, + outputs=outputs, + ) + + task_run_ctx: TaskRunContext = mock_run_context[0] + flow_run_ctx: FlowRunContext = mock_run_context[1] + + expected_datajob_urn = ( + f"urn:li:dataJob:(urn:li:dataFlow:" + f"(prefect,{flow_run_ctx.flow.name},prod),{task_run_ctx.task.task_key})" + ) + + assert expected_datajob_urn in datahub_emitter.datajobs_to_emit.keys() + actual_datajob = datahub_emitter.datajobs_to_emit[expected_datajob_urn] + assert isinstance(actual_datajob, DataJob) + assert str(actual_datajob.flow_urn) == "urn:li:dataFlow:(prefect,etl,prod)" + assert actual_datajob.name == task_run_ctx.task.name + assert actual_datajob.description == task_run_ctx.task.description + assert actual_datajob.tags == task_run_ctx.task.tags + assert ( + str(actual_datajob.inlets[0]) + == "urn:li:dataset:(urn:li:dataPlatform:snowflake,mydb.schema.tableA,PROD)" + ) + assert ( + str(actual_datajob.outlets[0]) + == "urn:li:dataset:(urn:li:dataPlatform:snowflake,mydb.schema.tableC,PROD)" + ) + assert mock_emit.emit.call_count == 0 + + +@patch("prefect_datahub.datahub_emitter.DatahubRestEmitter", autospec=True) +def test_emit_flow( + mock_emit, mock_run_context, mock_prefect_client, mock_prefect_cloud_client +): + mock_emitter = Mock() + mock_emit.return_value = mock_emitter + + platform_instance = "datahub_workspace" + + datahub_emitter = DatahubEmitter(platform_instance=platform_instance) + datahub_emitter.add_task() + datahub_emitter.emit_flow() + + task_run_ctx: TaskRunContext = mock_run_context[0] + flow_run_ctx: FlowRunContext = mock_run_context[1] + + expected_dataflow_urn = ( + f"urn:li:dataFlow:(prefect,{platform_instance}.{flow_run_ctx.flow.name},prod)" + ) + + assert mock_emitter.method_calls[1][1][0].aspectName == "dataFlowInfo" + assert mock_emitter.method_calls[1][1][0].entityUrn == expected_dataflow_urn + assert mock_emitter.method_calls[2][1][0].aspectName == "ownership" + assert mock_emitter.method_calls[2][1][0].entityUrn == expected_dataflow_urn + assert mock_emitter.method_calls[3][1][0].aspectName == "globalTags" + assert mock_emitter.method_calls[3][1][0].entityUrn == expected_dataflow_urn + assert mock_emitter.method_calls[4][1][0].aspectName == "browsePaths" + assert mock_emitter.method_calls[4][1][0].entityUrn == expected_dataflow_urn + assert ( + mock_emitter.method_calls[8][1][0].aspectName == "dataProcessInstanceProperties" + ) + assert ( + mock_emitter.method_calls[8][1][0].entityUrn + == "urn:li:dataProcessInstance:a95d24db6abd98384fc1d4c8540098a4" + ) + assert ( + mock_emitter.method_calls[9][1][0].aspectName + == "dataProcessInstanceRelationships" + ) + assert ( + mock_emitter.method_calls[9][1][0].entityUrn + == "urn:li:dataProcessInstance:a95d24db6abd98384fc1d4c8540098a4" + ) + assert ( + mock_emitter.method_calls[10][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[10][1][0].entityUrn + == "urn:li:dataProcessInstance:a95d24db6abd98384fc1d4c8540098a4" + ) + assert mock_emitter.method_calls[11][1][0].aspectName == "dataJobInfo" + assert ( + mock_emitter.method_calls[11][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.extract)" + ) + assert mock_emitter.method_calls[12][1][0].aspectName == "dataJobInputOutput" + assert ( + mock_emitter.method_calls[12][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.extract)" + ) + assert mock_emitter.method_calls[13][1][0].aspectName == "ownership" + assert ( + mock_emitter.method_calls[13][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.extract)" + ) + assert mock_emitter.method_calls[14][1][0].aspectName == "globalTags" + assert ( + mock_emitter.method_calls[14][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.extract)" + ) + assert mock_emitter.method_calls[15][1][0].aspectName == "browsePaths" + assert ( + mock_emitter.method_calls[15][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.extract)" + ) + assert ( + mock_emitter.method_calls[16][1][0].aspectName + == "dataProcessInstanceProperties" + ) + assert ( + mock_emitter.method_calls[16][1][0].entityUrn + == "urn:li:dataProcessInstance:bf5eab177af0097bbff6a41694f39af9" + ) + assert ( + mock_emitter.method_calls[17][1][0].aspectName + == "dataProcessInstanceRelationships" + ) + assert ( + mock_emitter.method_calls[17][1][0].entityUrn + == "urn:li:dataProcessInstance:bf5eab177af0097bbff6a41694f39af9" + ) + assert ( + mock_emitter.method_calls[18][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[18][1][0].entityUrn + == "urn:li:dataProcessInstance:bf5eab177af0097bbff6a41694f39af9" + ) + assert ( + mock_emitter.method_calls[19][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[19][1][0].entityUrn + == "urn:li:dataProcessInstance:bf5eab177af0097bbff6a41694f39af9" + ) + assert mock_emitter.method_calls[20][1][0].aspectName == "dataJobInfo" + assert ( + mock_emitter.method_calls[20][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.load)" + ) + assert mock_emitter.method_calls[21][1][0].aspectName == "dataJobInputOutput" + assert ( + mock_emitter.method_calls[21][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.load)" + ) + assert mock_emitter.method_calls[22][1][0].aspectName == "ownership" + assert ( + mock_emitter.method_calls[22][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.load)" + ) + assert mock_emitter.method_calls[23][1][0].aspectName == "globalTags" + assert ( + mock_emitter.method_calls[23][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.load)" + ) + assert mock_emitter.method_calls[24][1][0].aspectName == "browsePaths" + assert ( + mock_emitter.method_calls[24][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.load)" + ) + assert ( + mock_emitter.method_calls[25][1][0].aspectName + == "dataProcessInstanceProperties" + ) + assert ( + mock_emitter.method_calls[25][1][0].entityUrn + == "urn:li:dataProcessInstance:095673536b61e6f25c7691af0d2cc317" + ) + assert ( + mock_emitter.method_calls[26][1][0].aspectName + == "dataProcessInstanceRelationships" + ) + assert ( + mock_emitter.method_calls[26][1][0].entityUrn + == "urn:li:dataProcessInstance:095673536b61e6f25c7691af0d2cc317" + ) + assert ( + mock_emitter.method_calls[27][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[27][1][0].entityUrn + == "urn:li:dataProcessInstance:095673536b61e6f25c7691af0d2cc317" + ) + assert ( + mock_emitter.method_calls[28][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[28][1][0].entityUrn + == "urn:li:dataProcessInstance:095673536b61e6f25c7691af0d2cc317" + ) + assert mock_emitter.method_calls[29][1][0].aspectName == "dataJobInfo" + assert ( + mock_emitter.method_calls[29][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.transform)" + ) + assert mock_emitter.method_calls[30][1][0].aspectName == "dataJobInputOutput" + assert ( + mock_emitter.method_calls[30][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.transform)" + ) + assert mock_emitter.method_calls[31][1][0].aspectName == "ownership" + assert ( + mock_emitter.method_calls[31][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.transform)" + ) + assert mock_emitter.method_calls[32][1][0].aspectName == "globalTags" + assert ( + mock_emitter.method_calls[32][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.transform)" + ) + assert ( + mock_emitter.method_calls[32][1][0].aspect.tags[0].tag + == f"urn:li:tag:{task_run_ctx.task.tags[0]}" + ) + assert mock_emitter.method_calls[33][1][0].aspectName == "browsePaths" + assert ( + mock_emitter.method_calls[33][1][0].entityUrn + == f"urn:li:dataJob:({expected_dataflow_urn},__main__.transform)" + ) + assert ( + mock_emitter.method_calls[34][1][0].aspectName + == "dataProcessInstanceProperties" + ) + assert ( + mock_emitter.method_calls[34][1][0].entityUrn + == "urn:li:dataProcessInstance:04ba0f8064b2c45f69da571c434f1c69" + ) + assert ( + mock_emitter.method_calls[35][1][0].aspectName + == "dataProcessInstanceRelationships" + ) + assert ( + mock_emitter.method_calls[35][1][0].entityUrn + == "urn:li:dataProcessInstance:04ba0f8064b2c45f69da571c434f1c69" + ) + assert ( + mock_emitter.method_calls[36][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[36][1][0].entityUrn + == "urn:li:dataProcessInstance:04ba0f8064b2c45f69da571c434f1c69" + ) + assert ( + mock_emitter.method_calls[37][1][0].aspectName == "dataProcessInstanceRunEvent" + ) + assert ( + mock_emitter.method_calls[37][1][0].entityUrn + == "urn:li:dataProcessInstance:04ba0f8064b2c45f69da571c434f1c69" + ) diff --git a/versioneer.py b/versioneer.py new file mode 100644 index 0000000..d70f31b --- /dev/null +++ b/versioneer.py @@ -0,0 +1,2163 @@ +# Version: 0.21 + +"""The Versioneer - like a rocketeer, but for versions. + +The Versioneer +============== + +* like a rocketeer, but for versions! +* https://github.com/python-versioneer/python-versioneer +* Brian Warner +* License: Public Domain +* Compatible with: Python 3.6, 3.7, 3.8, 3.9 and pypy3 +* [![Latest Version][pypi-image]][pypi-url] +* [![Build Status][travis-image]][travis-url] + +This is a tool for managing a recorded version number in distutils-based +python projects. The goal is to remove the tedious and error-prone "update +the embedded version string" step from your release process. Making a new +release should be as easy as recording a new tag in your version-control +system, and maybe making new tarballs. + + +## Quick Install + +* `pip install versioneer` to somewhere in your $PATH +* add a `[versioneer]` section to your setup.cfg (see [Install](INSTALL.md)) +* run `versioneer install` in your source tree, commit the results +* Verify version information with `python setup.py version` + +## Version Identifiers + +Source trees come from a variety of places: + +* a version-control system checkout (mostly used by developers) +* a nightly tarball, produced by build automation +* a snapshot tarball, produced by a web-based VCS browser, like github's + "tarball from tag" feature +* a release tarball, produced by "setup.py sdist", distributed through PyPI + +Within each source tree, the version identifier (either a string or a number, +this tool is format-agnostic) can come from a variety of places: + +* ask the VCS tool itself, e.g. "git describe" (for checkouts), which knows + about recent "tags" and an absolute revision-id +* the name of the directory into which the tarball was unpacked +* an expanded VCS keyword ($Id$, etc) +* a `_version.py` created by some earlier build step + +For released software, the version identifier is closely related to a VCS +tag. Some projects use tag names that include more than just the version +string (e.g. "myproject-1.2" instead of just "1.2"), in which case the tool +needs to strip the tag prefix to extract the version identifier. For +unreleased software (between tags), the version identifier should provide +enough information to help developers recreate the same tree, while also +giving them an idea of roughly how old the tree is (after version 1.2, before +version 1.3). Many VCS systems can report a description that captures this, +for example `git describe --tags --dirty --always` reports things like +"0.7-1-g574ab98-dirty" to indicate that the checkout is one revision past the +0.7 tag, has a unique revision id of "574ab98", and is "dirty" (it has +uncommitted changes). + +The version identifier is used for multiple purposes: + +* to allow the module to self-identify its version: `myproject.__version__` +* to choose a name and prefix for a 'setup.py sdist' tarball + +## Theory of Operation + +Versioneer works by adding a special `_version.py` file into your source +tree, where your `__init__.py` can import it. This `_version.py` knows how to +dynamically ask the VCS tool for version information at import time. + +`_version.py` also contains `$Revision$` markers, and the installation +process marks `_version.py` to have this marker rewritten with a tag name +during the `git archive` command. As a result, generated tarballs will +contain enough information to get the proper version. + +To allow `setup.py` to compute a version too, a `versioneer.py` is added to +the top level of your source tree, next to `setup.py` and the `setup.cfg` +that configures it. This overrides several distutils/setuptools commands to +compute the version when invoked, and changes `setup.py build` and `setup.py +sdist` to replace `_version.py` with a small static file that contains just +the generated version data. + +## Installation + +See [INSTALL.md](./INSTALL.md) for detailed installation instructions. + +## Version-String Flavors + +Code which uses Versioneer can learn about its version string at runtime by +importing `_version` from your main `__init__.py` file and running the +`get_versions()` function. From the "outside" (e.g. in `setup.py`), you can +import the top-level `versioneer.py` and run `get_versions()`. + +Both functions return a dictionary with different flavors of version +information: + +* `['version']`: A condensed version string, rendered using the selected + style. This is the most commonly used value for the project's version + string. The default "pep440" style yields strings like `0.11`, + `0.11+2.g1076c97`, or `0.11+2.g1076c97.dirty`. See the "Styles" section + below for alternative styles. + +* `['full-revisionid']`: detailed revision identifier. For Git, this is the + full SHA1 commit id, e.g. "1076c978a8d3cfc70f408fe5974aa6c092c949ac". + +* `['date']`: Date and time of the latest `HEAD` commit. For Git, it is the + commit date in ISO 8601 format. This will be None if the date is not + available. + +* `['dirty']`: a boolean, True if the tree has uncommitted changes. Note that + this is only accurate if run in a VCS checkout, otherwise it is likely to + be False or None + +* `['error']`: if the version string could not be computed, this will be set + to a string describing the problem, otherwise it will be None. It may be + useful to throw an exception in setup.py if this is set, to avoid e.g. + creating tarballs with a version string of "unknown". + +Some variants are more useful than others. Including `full-revisionid` in a +bug report should allow developers to reconstruct the exact code being tested +(or indicate the presence of local changes that should be shared with the +developers). `version` is suitable for display in an "about" box or a CLI +`--version` output: it can be easily compared against release notes and lists +of bugs fixed in various releases. + +The installer adds the following text to your `__init__.py` to place a basic +version in `YOURPROJECT.__version__`: + + from ._version import get_versions + __version__ = get_versions()['version'] + del get_versions + +## Styles + +The setup.cfg `style=` configuration controls how the VCS information is +rendered into a version string. + +The default style, "pep440", produces a PEP440-compliant string, equal to the +un-prefixed tag name for actual releases, and containing an additional "local +version" section with more detail for in-between builds. For Git, this is +TAG[+DISTANCE.gHEX[.dirty]] , using information from `git describe --tags +--dirty --always`. For example "0.11+2.g1076c97.dirty" indicates that the +tree is like the "1076c97" commit but has uncommitted changes (".dirty"), and +that this commit is two revisions ("+2") beyond the "0.11" tag. For released +software (exactly equal to a known tag), the identifier will only contain the +stripped tag, e.g. "0.11". + +Other styles are available. See [details.md](details.md) in the Versioneer +source tree for descriptions. + +## Debugging + +Versioneer tries to avoid fatal errors: if something goes wrong, it will tend +to return a version of "0+unknown". To investigate the problem, run `setup.py +version`, which will run the version-lookup code in a verbose mode, and will +display the full contents of `get_versions()` (including the `error` string, +which may help identify what went wrong). + +## Known Limitations + +Some situations are known to cause problems for Versioneer. This details the +most significant ones. More can be found on Github +[issues page](https://github.com/python-versioneer/python-versioneer/issues). + +### Subprojects + +Versioneer has limited support for source trees in which `setup.py` is not in +the root directory (e.g. `setup.py` and `.git/` are *not* siblings). The are +two common reasons why `setup.py` might not be in the root: + +* Source trees which contain multiple subprojects, such as + [Buildbot](https://github.com/buildbot/buildbot), which contains both + "master" and "slave" subprojects, each with their own `setup.py`, + `setup.cfg`, and `tox.ini`. Projects like these produce multiple PyPI + distributions (and upload multiple independently-installable tarballs). +* Source trees whose main purpose is to contain a C library, but which also + provide bindings to Python (and perhaps other languages) in subdirectories. + +Versioneer will look for `.git` in parent directories, and most operations +should get the right version string. However `pip` and `setuptools` have bugs +and implementation details which frequently cause `pip install .` from a +subproject directory to fail to find a correct version string (so it usually +defaults to `0+unknown`). + +`pip install --editable .` should work correctly. `setup.py install` might +work too. + +Pip-8.1.1 is known to have this problem, but hopefully it will get fixed in +some later version. + +[Bug #38](https://github.com/python-versioneer/python-versioneer/issues/38) is tracking +this issue. The discussion in +[PR #61](https://github.com/python-versioneer/python-versioneer/pull/61) describes the +issue from the Versioneer side in more detail. +[pip PR#3176](https://github.com/pypa/pip/pull/3176) and +[pip PR#3615](https://github.com/pypa/pip/pull/3615) contain work to improve +pip to let Versioneer work correctly. + +Versioneer-0.16 and earlier only looked for a `.git` directory next to the +`setup.cfg`, so subprojects were completely unsupported with those releases. + +### Editable installs with setuptools <= 18.5 + +`setup.py develop` and `pip install --editable .` allow you to install a +project into a virtualenv once, then continue editing the source code (and +test) without re-installing after every change. + +"Entry-point scripts" (`setup(entry_points={"console_scripts": ..})`) are a +convenient way to specify executable scripts that should be installed along +with the python package. + +These both work as expected when using modern setuptools. When using +setuptools-18.5 or earlier, however, certain operations will cause +`pkg_resources.DistributionNotFound` errors when running the entrypoint +script, which must be resolved by re-installing the package. This happens +when the install happens with one version, then the egg_info data is +regenerated while a different version is checked out. Many setup.py commands +cause egg_info to be rebuilt (including `sdist`, `wheel`, and installing into +a different virtualenv), so this can be surprising. + +[Bug #83](https://github.com/python-versioneer/python-versioneer/issues/83) describes +this one, but upgrading to a newer version of setuptools should probably +resolve it. + + +## Updating Versioneer + +To upgrade your project to a new release of Versioneer, do the following: + +* install the new Versioneer (`pip install -U versioneer` or equivalent) +* edit `setup.cfg`, if necessary, to include any new configuration settings + indicated by the release notes. See [UPGRADING](./UPGRADING.md) for details. +* re-run `versioneer install` in your source tree, to replace + `SRC/_version.py` +* commit any changed files + +## Future Directions + +This tool is designed to make it easily extended to other version-control +systems: all VCS-specific components are in separate directories like +src/git/ . The top-level `versioneer.py` script is assembled from these +components by running make-versioneer.py . In the future, make-versioneer.py +will take a VCS name as an argument, and will construct a version of +`versioneer.py` that is specific to the given VCS. It might also take the +configuration arguments that are currently provided manually during +installation by editing setup.py . Alternatively, it might go the other +direction and include code from all supported VCS systems, reducing the +number of intermediate scripts. + +## Similar projects + +* [setuptools_scm](https://github.com/pypa/setuptools_scm/) - a non-vendored build-time + dependency +* [minver](https://github.com/jbweston/miniver) - a lightweight reimplementation of + versioneer +* [versioningit](https://github.com/jwodder/versioningit) - a PEP 518-based setuptools + plugin + +## License + +To make Versioneer easier to embed, all its code is dedicated to the public +domain. The `_version.py` that it creates is also in the public domain. +Specifically, both are released under the Creative Commons "Public Domain +Dedication" license (CC0-1.0), as described in +https://creativecommons.org/publicdomain/zero/1.0/ . + +[pypi-image]: https://img.shields.io/pypi/v/versioneer.svg +[pypi-url]: https://pypi.python.org/pypi/versioneer/ +[travis-image]: +https://img.shields.io/travis/com/python-versioneer/python-versioneer.svg +[travis-url]: https://travis-ci.com/github/python-versioneer/python-versioneer + +""" +# pylint:disable=invalid-name,import-outside-toplevel,missing-function-docstring +# pylint:disable=missing-class-docstring,too-many-branches,too-many-statements +# pylint:disable=raise-missing-from,too-many-lines,too-many-locals,import-error +# pylint:disable=too-few-public-methods,redefined-outer-name,consider-using-with +# pylint:disable=attribute-defined-outside-init,too-many-arguments + +import configparser +import errno +import json +import os +import re +import subprocess +import sys +from typing import Callable, Dict + + +class VersioneerConfig: + """Container for Versioneer configuration parameters.""" + + +def get_root(): + """Get the project root directory. + + We require that all commands are run from the project root, i.e. the + directory that contains setup.py, setup.cfg, and versioneer.py . + """ + root = os.path.realpath(os.path.abspath(os.getcwd())) + setup_py = os.path.join(root, "setup.py") + versioneer_py = os.path.join(root, "versioneer.py") + if not (os.path.exists(setup_py) or os.path.exists(versioneer_py)): + # allow 'python path/to/setup.py COMMAND' + root = os.path.dirname(os.path.realpath(os.path.abspath(sys.argv[0]))) + setup_py = os.path.join(root, "setup.py") + versioneer_py = os.path.join(root, "versioneer.py") + if not (os.path.exists(setup_py) or os.path.exists(versioneer_py)): + err = ( + "Versioneer was unable to run the project root directory. " + "Versioneer requires setup.py to be executed from " + "its immediate directory (like 'python setup.py COMMAND'), " + "or in a way that lets it use sys.argv[0] to find the root " + "(like 'python path/to/setup.py COMMAND')." + ) + raise VersioneerBadRootError(err) + try: + # Certain runtime workflows (setup.py install/develop in a setuptools + # tree) execute all dependencies in a single python process, so + # "versioneer" may be imported multiple times, and python's shared + # module-import table will cache the first one. So we can't use + # os.path.dirname(__file__), as that will find whichever + # versioneer.py was first imported, even in later projects. + my_path = os.path.realpath(os.path.abspath(__file__)) + me_dir = os.path.normcase(os.path.splitext(my_path)[0]) + vsr_dir = os.path.normcase(os.path.splitext(versioneer_py)[0]) + if me_dir != vsr_dir: + print( + "Warning: build in %s is using versioneer.py from %s" + % (os.path.dirname(my_path), versioneer_py) + ) + except NameError: + pass + return root + + +def get_config_from_root(root): + """Read the project setup.cfg file to determine Versioneer config.""" + # This might raise OSError (if setup.cfg is missing), or + # configparser.NoSectionError (if it lacks a [versioneer] section), or + # configparser.NoOptionError (if it lacks "VCS="). See the docstring at + # the top of versioneer.py for instructions on writing your setup.cfg . + setup_cfg = os.path.join(root, "setup.cfg") + parser = configparser.ConfigParser() + with open(setup_cfg, "r") as cfg_file: + parser.read_file(cfg_file) + VCS = parser.get("versioneer", "VCS") # mandatory + + # Dict-like interface for non-mandatory entries + section = parser["versioneer"] + + cfg = VersioneerConfig() + cfg.VCS = VCS + cfg.style = section.get("style", "") + cfg.versionfile_source = section.get("versionfile_source") + cfg.versionfile_build = section.get("versionfile_build") + cfg.tag_prefix = section.get("tag_prefix") + if cfg.tag_prefix in ("''", '""'): + cfg.tag_prefix = "" + cfg.parentdir_prefix = section.get("parentdir_prefix") + cfg.verbose = section.get("verbose") + return cfg + + +class NotThisMethod(Exception): + """Exception raised if a method is not valid for the current scenario.""" + + +# these dictionaries contain VCS-specific tools +LONG_VERSION_PY: Dict[str, str] = {} +HANDLERS: Dict[str, Dict[str, Callable]] = {} + + +def register_vcs_handler(vcs, method): # decorator + """Create decorator to mark a method as the handler of a VCS.""" + + def decorate(f): + """Store f in HANDLERS[vcs][method].""" + HANDLERS.setdefault(vcs, {})[method] = f + return f + + return decorate + + +def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=None): + """Call the given command(s).""" + assert isinstance(commands, list) + process = None + for command in commands: + try: + dispcmd = str([command] + args) + # remember shell=False, so use git.cmd on windows, not just git + process = subprocess.Popen( + [command] + args, + cwd=cwd, + env=env, + stdout=subprocess.PIPE, + stderr=(subprocess.PIPE if hide_stderr else None), + ) + break + except OSError: + e = sys.exc_info()[1] + if e.errno == errno.ENOENT: + continue + if verbose: + print("unable to run %s" % dispcmd) + print(e) + return None, None + else: + if verbose: + print("unable to find command, tried %s" % (commands,)) + return None, None + stdout = process.communicate()[0].strip().decode() + if process.returncode != 0: + if verbose: + print("unable to run %s (error)" % dispcmd) + print("stdout was %s" % stdout) + return None, process.returncode + return stdout, process.returncode + + +LONG_VERSION_PY[ + "git" +] = r''' +# This file helps to compute a version number in source trees obtained from +# git-archive tarball (such as those provided by githubs download-from-tag +# feature). Distribution tarballs (built by setup.py sdist) and build +# directories (produced by setup.py build) will contain a much shorter file +# that just contains the computed version number. + +# This file is released into the public domain. Generated by +# versioneer-0.21 (https://github.com/python-versioneer/python-versioneer) + +"""Git implementation of _version.py.""" + +import errno +import os +import re +import subprocess +import sys +from typing import Callable, Dict + + +def get_keywords(): + """Get the keywords needed to look up the version information.""" + # these strings will be replaced by git during git-archive. + # setup.py/versioneer.py will grep for the variable names, so they must + # each be defined on a line of their own. _version.py will just call + # get_keywords(). + git_refnames = "%(DOLLAR)sFormat:%%d%(DOLLAR)s" + git_full = "%(DOLLAR)sFormat:%%H%(DOLLAR)s" + git_date = "%(DOLLAR)sFormat:%%ci%(DOLLAR)s" + keywords = {"refnames": git_refnames, "full": git_full, "date": git_date} + return keywords + + +class VersioneerConfig: + """Container for Versioneer configuration parameters.""" + + +def get_config(): + """Create, populate and return the VersioneerConfig() object.""" + # these strings are filled in when 'setup.py versioneer' creates + # _version.py + cfg = VersioneerConfig() + cfg.VCS = "git" + cfg.style = "%(STYLE)s" + cfg.tag_prefix = "%(TAG_PREFIX)s" + cfg.parentdir_prefix = "%(PARENTDIR_PREFIX)s" + cfg.versionfile_source = "%(VERSIONFILE_SOURCE)s" + cfg.verbose = False + return cfg + + +class NotThisMethod(Exception): + """Exception raised if a method is not valid for the current scenario.""" + + +LONG_VERSION_PY: Dict[str, str] = {} +HANDLERS: Dict[str, Dict[str, Callable]] = {} + + +def register_vcs_handler(vcs, method): # decorator + """Create decorator to mark a method as the handler of a VCS.""" + def decorate(f): + """Store f in HANDLERS[vcs][method].""" + if vcs not in HANDLERS: + HANDLERS[vcs] = {} + HANDLERS[vcs][method] = f + return f + return decorate + + +def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, + env=None): + """Call the given command(s).""" + assert isinstance(commands, list) + process = None + for command in commands: + try: + dispcmd = str([command] + args) + # remember shell=False, so use git.cmd on windows, not just git + process = subprocess.Popen([command] + args, cwd=cwd, env=env, + stdout=subprocess.PIPE, + stderr=(subprocess.PIPE if hide_stderr + else None)) + break + except OSError: + e = sys.exc_info()[1] + if e.errno == errno.ENOENT: + continue + if verbose: + print("unable to run %%s" %% dispcmd) + print(e) + return None, None + else: + if verbose: + print("unable to find command, tried %%s" %% (commands,)) + return None, None + stdout = process.communicate()[0].strip().decode() + if process.returncode != 0: + if verbose: + print("unable to run %%s (error)" %% dispcmd) + print("stdout was %%s" %% stdout) + return None, process.returncode + return stdout, process.returncode + + +def versions_from_parentdir(parentdir_prefix, root, verbose): + """Try to determine the version from the parent directory name. + + Source tarballs conventionally unpack into a directory that includes both + the project name and a version string. We will also support searching up + two directory levels for an appropriately named parent directory + """ + rootdirs = [] + + for _ in range(3): + dirname = os.path.basename(root) + if dirname.startswith(parentdir_prefix): + return {"version": dirname[len(parentdir_prefix):], + "full-revisionid": None, + "dirty": False, "error": None, "date": None} + rootdirs.append(root) + root = os.path.dirname(root) # up a level + + if verbose: + print("Tried directories %%s but none started with prefix %%s" %% + (str(rootdirs), parentdir_prefix)) + raise NotThisMethod("rootdir doesn't start with parentdir_prefix") + + +@register_vcs_handler("git", "get_keywords") +def git_get_keywords(versionfile_abs): + """Extract version information from the given file.""" + # the code embedded in _version.py can just fetch the value of these + # keywords. When used from setup.py, we don't want to import _version.py, + # so we do it with a regexp instead. This function is not used from + # _version.py. + keywords = {} + try: + with open(versionfile_abs, "r") as fobj: + for line in fobj: + if line.strip().startswith("git_refnames ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["refnames"] = mo.group(1) + if line.strip().startswith("git_full ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["full"] = mo.group(1) + if line.strip().startswith("git_date ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["date"] = mo.group(1) + except OSError: + pass + return keywords + + +@register_vcs_handler("git", "keywords") +def git_versions_from_keywords(keywords, tag_prefix, verbose): + """Get version information from git keywords.""" + if "refnames" not in keywords: + raise NotThisMethod("Short version file found") + date = keywords.get("date") + if date is not None: + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + + # git-2.2.0 added "%%cI", which expands to an ISO-8601 -compliant + # datestamp. However we prefer "%%ci" (which expands to an "ISO-8601 + # -like" string, which we must then edit to make compliant), because + # it's been around since git-1.5.3, and it's too difficult to + # discover which version we're using, or to work around using an + # older one. + date = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + refnames = keywords["refnames"].strip() + if refnames.startswith("$Format"): + if verbose: + print("keywords are unexpanded, not using") + raise NotThisMethod("unexpanded keywords, not a git-archive tarball") + refs = {r.strip() for r in refnames.strip("()").split(",")} + # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of + # just "foo-1.0". If we see a "tag: " prefix, prefer those. + TAG = "tag: " + tags = {r[len(TAG):] for r in refs if r.startswith(TAG)} + if not tags: + # Either we're using git < 1.8.3, or there really are no tags. We use + # a heuristic: assume all version tags have a digit. The old git %%d + # expansion behaves like git log --decorate=short and strips out the + # refs/heads/ and refs/tags/ prefixes that would let us distinguish + # between branches and tags. By ignoring refnames without digits, we + # filter out many common branch names like "release" and + # "stabilization", as well as "HEAD" and "master". + tags = {r for r in refs if re.search(r'\d', r)} + if verbose: + print("discarding '%%s', no digits" %% ",".join(refs - tags)) + if verbose: + print("likely tags: %%s" %% ",".join(sorted(tags))) + for ref in sorted(tags): + # sorting will prefer e.g. "2.0" over "2.0rc1" + if ref.startswith(tag_prefix): + r = ref[len(tag_prefix):] + # Filter out refs that exactly match prefix or that don't start + # with a number once the prefix is stripped (mostly a concern + # when prefix is '') + if not re.match(r'\d', r): + continue + if verbose: + print("picking %%s" %% r) + return {"version": r, + "full-revisionid": keywords["full"].strip(), + "dirty": False, "error": None, + "date": date} + # no suitable tags, so version is "0+unknown", but full hex is still there + if verbose: + print("no suitable tags, using unknown + full revision id") + return {"version": "0+unknown", + "full-revisionid": keywords["full"].strip(), + "dirty": False, "error": "no suitable tags", "date": None} + + +@register_vcs_handler("git", "pieces_from_vcs") +def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command): + """Get version from 'git describe' in the root of the source tree. + + This only gets called if the git-archive 'subst' keywords were *not* + expanded, and _version.py hasn't already been rewritten with a short + version string, meaning we're inside a checked out source tree. + """ + GITS = ["git"] + TAG_PREFIX_REGEX = "*" + if sys.platform == "win32": + GITS = ["git.cmd", "git.exe"] + TAG_PREFIX_REGEX = r"\*" + + _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, + hide_stderr=True) + if rc != 0: + if verbose: + print("Directory %%s not under git control" %% root) + raise NotThisMethod("'git rev-parse --git-dir' returned error") + + # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty] + # if there isn't one, this yields HEX[-dirty] (no NUM) + describe_out, rc = runner(GITS, ["describe", "--tags", "--dirty", + "--always", "--long", + "--match", + "%%s%%s" %% (tag_prefix, TAG_PREFIX_REGEX)], + cwd=root) + # --long was added in git-1.5.5 + if describe_out is None: + raise NotThisMethod("'git describe' failed") + describe_out = describe_out.strip() + full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root) + if full_out is None: + raise NotThisMethod("'git rev-parse' failed") + full_out = full_out.strip() + + pieces = {} + pieces["long"] = full_out + pieces["short"] = full_out[:7] # maybe improved later + pieces["error"] = None + + branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], + cwd=root) + # --abbrev-ref was added in git-1.6.3 + if rc != 0 or branch_name is None: + raise NotThisMethod("'git rev-parse --abbrev-ref' returned error") + branch_name = branch_name.strip() + + if branch_name == "HEAD": + # If we aren't exactly on a branch, pick a branch which represents + # the current commit. If all else fails, we are on a branchless + # commit. + branches, rc = runner(GITS, ["branch", "--contains"], cwd=root) + # --contains was added in git-1.5.4 + if rc != 0 or branches is None: + raise NotThisMethod("'git branch --contains' returned error") + branches = branches.split("\n") + + # Remove the first line if we're running detached + if "(" in branches[0]: + branches.pop(0) + + # Strip off the leading "* " from the list of branches. + branches = [branch[2:] for branch in branches] + if "master" in branches: + branch_name = "master" + elif not branches: + branch_name = None + else: + # Pick the first branch that is returned. Good or bad. + branch_name = branches[0] + + pieces["branch"] = branch_name + + # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty] + # TAG might have hyphens. + git_describe = describe_out + + # look for -dirty suffix + dirty = git_describe.endswith("-dirty") + pieces["dirty"] = dirty + if dirty: + git_describe = git_describe[:git_describe.rindex("-dirty")] + + # now we have TAG-NUM-gHEX or HEX + + if "-" in git_describe: + # TAG-NUM-gHEX + mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe) + if not mo: + # unparsable. Maybe git-describe is misbehaving? + pieces["error"] = ("unable to parse git-describe output: '%%s'" + %% describe_out) + return pieces + + # tag + full_tag = mo.group(1) + if not full_tag.startswith(tag_prefix): + if verbose: + fmt = "tag '%%s' doesn't start with prefix '%%s'" + print(fmt %% (full_tag, tag_prefix)) + pieces["error"] = ("tag '%%s' doesn't start with prefix '%%s'" + %% (full_tag, tag_prefix)) + return pieces + pieces["closest-tag"] = full_tag[len(tag_prefix):] + + # distance: number of commits since tag + pieces["distance"] = int(mo.group(2)) + + # commit: short hex revision ID + pieces["short"] = mo.group(3) + + else: + # HEX: no tags + pieces["closest-tag"] = None + count_out, rc = runner(GITS, ["rev-list", "HEAD", "--count"], cwd=root) + pieces["distance"] = int(count_out) # total number of commits + + # commit date: see ISO-8601 comment in git_versions_from_keywords() + date = runner(GITS, ["show", "-s", "--format=%%ci", "HEAD"], cwd=root)[0].strip() + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + + return pieces + + +def plus_or_dot(pieces): + """Return a + if we don't already have one, else return a .""" + if "+" in pieces.get("closest-tag", ""): + return "." + return "+" + + +def render_pep440(pieces): + """Build up version string, with post-release "local version identifier". + + Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you + get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty + + Exceptions: + 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += plus_or_dot(pieces) + rendered += "%%d.g%%s" %% (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0+untagged.%%d.g%%s" %% (pieces["distance"], + pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_branch(pieces): + """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] . + + The ".dev0" means not master branch. Note that .dev0 sorts backwards + (a feature branch will appear "older" than the master branch). + + Exceptions: + 1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "%%d.g%%s" %% (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0" + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+untagged.%%d.g%%s" %% (pieces["distance"], + pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def pep440_split_post(ver): + """Split pep440 version string at the post-release segment. + + Returns the release segments before the post-release and the + post-release version number (or -1 if no post-release segment is present). + """ + vc = str.split(ver, ".post") + return vc[0], int(vc[1] or 0) if len(vc) == 2 else None + + +def render_pep440_pre(pieces): + """TAG[.postN.devDISTANCE] -- No -dirty. + + Exceptions: + 1: no tags. 0.post0.devDISTANCE + """ + if pieces["closest-tag"]: + if pieces["distance"]: + # update the post release segment + tag_version, post_version = pep440_split_post(pieces["closest-tag"]) + rendered = tag_version + if post_version is not None: + rendered += ".post%%d.dev%%d" %% (post_version+1, pieces["distance"]) + else: + rendered += ".post0.dev%%d" %% (pieces["distance"]) + else: + # no commits, use the tag as the version + rendered = pieces["closest-tag"] + else: + # exception #1 + rendered = "0.post0.dev%%d" %% pieces["distance"] + return rendered + + +def render_pep440_post(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX] . + + The ".dev0" means dirty. Note that .dev0 sorts backwards + (a dirty tree will appear "older" than the corresponding clean one), + but you shouldn't be releasing software with -dirty anyways. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%%d" %% pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%%s" %% pieces["short"] + else: + # exception #1 + rendered = "0.post%%d" %% pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += "+g%%s" %% pieces["short"] + return rendered + + +def render_pep440_post_branch(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] . + + The ".dev0" means not master branch. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%%d" %% pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%%s" %% pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0.post%%d" %% pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+g%%s" %% pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_old(pieces): + """TAG[.postDISTANCE[.dev0]] . + + The ".dev0" means dirty. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%%d" %% pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + else: + # exception #1 + rendered = "0.post%%d" %% pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + return rendered + + +def render_git_describe(pieces): + """TAG[-DISTANCE-gHEX][-dirty]. + + Like 'git describe --tags --dirty --always'. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"]: + rendered += "-%%d-g%%s" %% (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render_git_describe_long(pieces): + """TAG-DISTANCE-gHEX[-dirty]. + + Like 'git describe --tags --dirty --always -long'. + The distance/hash is unconditional. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + rendered += "-%%d-g%%s" %% (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render(pieces, style): + """Render the given version pieces into the requested style.""" + if pieces["error"]: + return {"version": "unknown", + "full-revisionid": pieces.get("long"), + "dirty": None, + "error": pieces["error"], + "date": None} + + if not style or style == "default": + style = "pep440" # the default + + if style == "pep440": + rendered = render_pep440(pieces) + elif style == "pep440-branch": + rendered = render_pep440_branch(pieces) + elif style == "pep440-pre": + rendered = render_pep440_pre(pieces) + elif style == "pep440-post": + rendered = render_pep440_post(pieces) + elif style == "pep440-post-branch": + rendered = render_pep440_post_branch(pieces) + elif style == "pep440-old": + rendered = render_pep440_old(pieces) + elif style == "git-describe": + rendered = render_git_describe(pieces) + elif style == "git-describe-long": + rendered = render_git_describe_long(pieces) + else: + raise ValueError("unknown style '%%s'" %% style) + + return {"version": rendered, "full-revisionid": pieces["long"], + "dirty": pieces["dirty"], "error": None, + "date": pieces.get("date")} + + +def get_versions(): + """Get version information or return default if unable to do so.""" + # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have + # __file__, we can work backwards from there to the root. Some + # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which + # case we can only use expanded keywords. + + cfg = get_config() + verbose = cfg.verbose + + try: + return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, + verbose) + except NotThisMethod: + pass + + try: + root = os.path.realpath(__file__) + # versionfile_source is the relative path from the top of the source + # tree (where the .git directory might live) to this file. Invert + # this to find the root from __file__. + for _ in cfg.versionfile_source.split('/'): + root = os.path.dirname(root) + except NameError: + return {"version": "0+unknown", "full-revisionid": None, + "dirty": None, + "error": "unable to find root of source tree", + "date": None} + + try: + pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose) + return render(pieces, cfg.style) + except NotThisMethod: + pass + + try: + if cfg.parentdir_prefix: + return versions_from_parentdir(cfg.parentdir_prefix, root, verbose) + except NotThisMethod: + pass + + return {"version": "0+unknown", "full-revisionid": None, + "dirty": None, + "error": "unable to compute version", "date": None} +''' + + +@register_vcs_handler("git", "get_keywords") +def git_get_keywords(versionfile_abs): + """Extract version information from the given file.""" + # the code embedded in _version.py can just fetch the value of these + # keywords. When used from setup.py, we don't want to import _version.py, + # so we do it with a regexp instead. This function is not used from + # _version.py. + keywords = {} + try: + with open(versionfile_abs, "r") as fobj: + for line in fobj: + if line.strip().startswith("git_refnames ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["refnames"] = mo.group(1) + if line.strip().startswith("git_full ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["full"] = mo.group(1) + if line.strip().startswith("git_date ="): + mo = re.search(r'=\s*"(.*)"', line) + if mo: + keywords["date"] = mo.group(1) + except OSError: + pass + return keywords + + +@register_vcs_handler("git", "keywords") +def git_versions_from_keywords(keywords, tag_prefix, verbose): + """Get version information from git keywords.""" + if "refnames" not in keywords: + raise NotThisMethod("Short version file found") + date = keywords.get("date") + if date is not None: + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + + # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant + # datestamp. However we prefer "%ci" (which expands to an "ISO-8601 + # -like" string, which we must then edit to make compliant), because + # it's been around since git-1.5.3, and it's too difficult to + # discover which version we're using, or to work around using an + # older one. + date = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + refnames = keywords["refnames"].strip() + if refnames.startswith("$Format"): + if verbose: + print("keywords are unexpanded, not using") + raise NotThisMethod("unexpanded keywords, not a git-archive tarball") + refs = {r.strip() for r in refnames.strip("()").split(",")} + # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of + # just "foo-1.0". If we see a "tag: " prefix, prefer those. + TAG = "tag: " + tags = {r[len(TAG) :] for r in refs if r.startswith(TAG)} + if not tags: + # Either we're using git < 1.8.3, or there really are no tags. We use + # a heuristic: assume all version tags have a digit. The old git %d + # expansion behaves like git log --decorate=short and strips out the + # refs/heads/ and refs/tags/ prefixes that would let us distinguish + # between branches and tags. By ignoring refnames without digits, we + # filter out many common branch names like "release" and + # "stabilization", as well as "HEAD" and "master". + tags = {r for r in refs if re.search(r"\d", r)} + if verbose: + print("discarding '%s', no digits" % ",".join(refs - tags)) + if verbose: + print("likely tags: %s" % ",".join(sorted(tags))) + for ref in sorted(tags): + # sorting will prefer e.g. "2.0" over "2.0rc1" + if ref.startswith(tag_prefix): + r = ref[len(tag_prefix) :] + # Filter out refs that exactly match prefix or that don't start + # with a number once the prefix is stripped (mostly a concern + # when prefix is '') + if not re.match(r"\d", r): + continue + if verbose: + print("picking %s" % r) + return { + "version": r, + "full-revisionid": keywords["full"].strip(), + "dirty": False, + "error": None, + "date": date, + } + # no suitable tags, so version is "0+unknown", but full hex is still there + if verbose: + print("no suitable tags, using unknown + full revision id") + return { + "version": "0+unknown", + "full-revisionid": keywords["full"].strip(), + "dirty": False, + "error": "no suitable tags", + "date": None, + } + + +@register_vcs_handler("git", "pieces_from_vcs") +def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command): + """Get version from 'git describe' in the root of the source tree. + + This only gets called if the git-archive 'subst' keywords were *not* + expanded, and _version.py hasn't already been rewritten with a short + version string, meaning we're inside a checked out source tree. + """ + GITS = ["git"] + TAG_PREFIX_REGEX = "*" + if sys.platform == "win32": + GITS = ["git.cmd", "git.exe"] + TAG_PREFIX_REGEX = r"\*" + + _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=True) + if rc != 0: + if verbose: + print("Directory %s not under git control" % root) + raise NotThisMethod("'git rev-parse --git-dir' returned error") + + # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty] + # if there isn't one, this yields HEX[-dirty] (no NUM) + describe_out, rc = runner( + GITS, + [ + "describe", + "--tags", + "--dirty", + "--always", + "--long", + "--match", + "%s%s" % (tag_prefix, TAG_PREFIX_REGEX), + ], + cwd=root, + ) + # --long was added in git-1.5.5 + if describe_out is None: + raise NotThisMethod("'git describe' failed") + describe_out = describe_out.strip() + full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root) + if full_out is None: + raise NotThisMethod("'git rev-parse' failed") + full_out = full_out.strip() + + pieces = {} + pieces["long"] = full_out + pieces["short"] = full_out[:7] # maybe improved later + pieces["error"] = None + + branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], cwd=root) + # --abbrev-ref was added in git-1.6.3 + if rc != 0 or branch_name is None: + raise NotThisMethod("'git rev-parse --abbrev-ref' returned error") + branch_name = branch_name.strip() + + if branch_name == "HEAD": + # If we aren't exactly on a branch, pick a branch which represents + # the current commit. If all else fails, we are on a branchless + # commit. + branches, rc = runner(GITS, ["branch", "--contains"], cwd=root) + # --contains was added in git-1.5.4 + if rc != 0 or branches is None: + raise NotThisMethod("'git branch --contains' returned error") + branches = branches.split("\n") + + # Remove the first line if we're running detached + if "(" in branches[0]: + branches.pop(0) + + # Strip off the leading "* " from the list of branches. + branches = [branch[2:] for branch in branches] + if "master" in branches: + branch_name = "master" + elif not branches: + branch_name = None + else: + # Pick the first branch that is returned. Good or bad. + branch_name = branches[0] + + pieces["branch"] = branch_name + + # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty] + # TAG might have hyphens. + git_describe = describe_out + + # look for -dirty suffix + dirty = git_describe.endswith("-dirty") + pieces["dirty"] = dirty + if dirty: + git_describe = git_describe[: git_describe.rindex("-dirty")] + + # now we have TAG-NUM-gHEX or HEX + + if "-" in git_describe: + # TAG-NUM-gHEX + mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe) + if not mo: + # unparsable. Maybe git-describe is misbehaving? + pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out + return pieces + + # tag + full_tag = mo.group(1) + if not full_tag.startswith(tag_prefix): + if verbose: + fmt = "tag '%s' doesn't start with prefix '%s'" + print(fmt % (full_tag, tag_prefix)) + pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % ( + full_tag, + tag_prefix, + ) + return pieces + pieces["closest-tag"] = full_tag[len(tag_prefix) :] + + # distance: number of commits since tag + pieces["distance"] = int(mo.group(2)) + + # commit: short hex revision ID + pieces["short"] = mo.group(3) + + else: + # HEX: no tags + pieces["closest-tag"] = None + count_out, rc = runner(GITS, ["rev-list", "HEAD", "--count"], cwd=root) + pieces["distance"] = int(count_out) # total number of commits + + # commit date: see ISO-8601 comment in git_versions_from_keywords() + date = runner(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip() + # Use only the last line. Previous lines may contain GPG signature + # information. + date = date.splitlines()[-1] + pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1) + + return pieces + + +def do_vcs_install(manifest_in, versionfile_source, ipy): + """Git-specific installation logic for Versioneer. + + For Git, this means creating/changing .gitattributes to mark _version.py + for export-subst keyword substitution. + """ + GITS = ["git"] + if sys.platform == "win32": + GITS = ["git.cmd", "git.exe"] + files = [manifest_in, versionfile_source] + if ipy: + files.append(ipy) + try: + my_path = __file__ + if my_path.endswith(".pyc") or my_path.endswith(".pyo"): + my_path = os.path.splitext(my_path)[0] + ".py" + versioneer_file = os.path.relpath(my_path) + except NameError: + versioneer_file = "versioneer.py" + files.append(versioneer_file) + present = False + try: + with open(".gitattributes", "r") as fobj: + for line in fobj: + if line.strip().startswith(versionfile_source): + if "export-subst" in line.strip().split()[1:]: + present = True + break + except OSError: + pass + if not present: + with open(".gitattributes", "a+") as fobj: + fobj.write(f"{versionfile_source} export-subst\n") + files.append(".gitattributes") + run_command(GITS, ["add", "--"] + files) + + +def versions_from_parentdir(parentdir_prefix, root, verbose): + """Try to determine the version from the parent directory name. + + Source tarballs conventionally unpack into a directory that includes both + the project name and a version string. We will also support searching up + two directory levels for an appropriately named parent directory + """ + rootdirs = [] + + for _ in range(3): + dirname = os.path.basename(root) + if dirname.startswith(parentdir_prefix): + return { + "version": dirname[len(parentdir_prefix) :], + "full-revisionid": None, + "dirty": False, + "error": None, + "date": None, + } + rootdirs.append(root) + root = os.path.dirname(root) # up a level + + if verbose: + print( + "Tried directories %s but none started with prefix %s" + % (str(rootdirs), parentdir_prefix) + ) + raise NotThisMethod("rootdir doesn't start with parentdir_prefix") + + +SHORT_VERSION_PY = """ +# This file was generated by 'versioneer.py' (0.21) from +# revision-control system data, or from the parent directory name of an +# unpacked source archive. Distribution tarballs contain a pre-generated copy +# of this file. + +import json + +version_json = ''' +%s +''' # END VERSION_JSON + + +def get_versions(): + return json.loads(version_json) +""" + + +def versions_from_file(filename): + """Try to determine the version from _version.py if present.""" + try: + with open(filename) as f: + contents = f.read() + except OSError: + raise NotThisMethod("unable to read _version.py") + mo = re.search( + r"version_json = '''\n(.*)''' # END VERSION_JSON", contents, re.M | re.S + ) + if not mo: + mo = re.search( + r"version_json = '''\r\n(.*)''' # END VERSION_JSON", contents, re.M | re.S + ) + if not mo: + raise NotThisMethod("no version_json in _version.py") + return json.loads(mo.group(1)) + + +def write_to_version_file(filename, versions): + """Write the given version number to the given _version.py file.""" + os.unlink(filename) + contents = json.dumps(versions, sort_keys=True, indent=1, separators=(",", ": ")) + with open(filename, "w") as f: + f.write(SHORT_VERSION_PY % contents) + + print("set %s to '%s'" % (filename, versions["version"])) + + +def plus_or_dot(pieces): + """Return a + if we don't already have one, else return a .""" + if "+" in pieces.get("closest-tag", ""): + return "." + return "+" + + +def render_pep440(pieces): + """Build up version string, with post-release "local version identifier". + + Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you + get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty + + Exceptions: + 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += plus_or_dot(pieces) + rendered += "%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_branch(pieces): + """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] . + + The ".dev0" means not master branch. Note that .dev0 sorts backwards + (a feature branch will appear "older" than the master branch). + + Exceptions: + 1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0" + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+untagged.%d.g%s" % (pieces["distance"], pieces["short"]) + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def pep440_split_post(ver): + """Split pep440 version string at the post-release segment. + + Returns the release segments before the post-release and the + post-release version number (or -1 if no post-release segment is present). + """ + vc = str.split(ver, ".post") + return vc[0], int(vc[1] or 0) if len(vc) == 2 else None + + +def render_pep440_pre(pieces): + """TAG[.postN.devDISTANCE] -- No -dirty. + + Exceptions: + 1: no tags. 0.post0.devDISTANCE + """ + if pieces["closest-tag"]: + if pieces["distance"]: + # update the post release segment + tag_version, post_version = pep440_split_post(pieces["closest-tag"]) + rendered = tag_version + if post_version is not None: + rendered += ".post%d.dev%d" % (post_version + 1, pieces["distance"]) + else: + rendered += ".post0.dev%d" % (pieces["distance"]) + else: + # no commits, use the tag as the version + rendered = pieces["closest-tag"] + else: + # exception #1 + rendered = "0.post0.dev%d" % pieces["distance"] + return rendered + + +def render_pep440_post(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX] . + + The ".dev0" means dirty. Note that .dev0 sorts backwards + (a dirty tree will appear "older" than the corresponding clean one), + but you shouldn't be releasing software with -dirty anyways. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%s" % pieces["short"] + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + rendered += "+g%s" % pieces["short"] + return rendered + + +def render_pep440_post_branch(pieces): + """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] . + + The ".dev0" means not master branch. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += plus_or_dot(pieces) + rendered += "g%s" % pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["branch"] != "master": + rendered += ".dev0" + rendered += "+g%s" % pieces["short"] + if pieces["dirty"]: + rendered += ".dirty" + return rendered + + +def render_pep440_old(pieces): + """TAG[.postDISTANCE[.dev0]] . + + The ".dev0" means dirty. + + Exceptions: + 1: no tags. 0.postDISTANCE[.dev0] + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"] or pieces["dirty"]: + rendered += ".post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + else: + # exception #1 + rendered = "0.post%d" % pieces["distance"] + if pieces["dirty"]: + rendered += ".dev0" + return rendered + + +def render_git_describe(pieces): + """TAG[-DISTANCE-gHEX][-dirty]. + + Like 'git describe --tags --dirty --always'. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + if pieces["distance"]: + rendered += "-%d-g%s" % (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render_git_describe_long(pieces): + """TAG-DISTANCE-gHEX[-dirty]. + + Like 'git describe --tags --dirty --always -long'. + The distance/hash is unconditional. + + Exceptions: + 1: no tags. HEX[-dirty] (note: no 'g' prefix) + """ + if pieces["closest-tag"]: + rendered = pieces["closest-tag"] + rendered += "-%d-g%s" % (pieces["distance"], pieces["short"]) + else: + # exception #1 + rendered = pieces["short"] + if pieces["dirty"]: + rendered += "-dirty" + return rendered + + +def render(pieces, style): + """Render the given version pieces into the requested style.""" + if pieces["error"]: + return { + "version": "unknown", + "full-revisionid": pieces.get("long"), + "dirty": None, + "error": pieces["error"], + "date": None, + } + + if not style or style == "default": + style = "pep440" # the default + + if style == "pep440": + rendered = render_pep440(pieces) + elif style == "pep440-branch": + rendered = render_pep440_branch(pieces) + elif style == "pep440-pre": + rendered = render_pep440_pre(pieces) + elif style == "pep440-post": + rendered = render_pep440_post(pieces) + elif style == "pep440-post-branch": + rendered = render_pep440_post_branch(pieces) + elif style == "pep440-old": + rendered = render_pep440_old(pieces) + elif style == "git-describe": + rendered = render_git_describe(pieces) + elif style == "git-describe-long": + rendered = render_git_describe_long(pieces) + else: + raise ValueError("unknown style '%s'" % style) + + return { + "version": rendered, + "full-revisionid": pieces["long"], + "dirty": pieces["dirty"], + "error": None, + "date": pieces.get("date"), + } + + +class VersioneerBadRootError(Exception): + """The project root directory is unknown or missing key files.""" + + +def get_versions(verbose=False): + """Get the project version from whatever source is available. + + Returns dict with two keys: 'version' and 'full'. + """ + if "versioneer" in sys.modules: + # see the discussion in cmdclass.py:get_cmdclass() + del sys.modules["versioneer"] + + root = get_root() + cfg = get_config_from_root(root) + + assert cfg.VCS is not None, "please set [versioneer]VCS= in setup.cfg" + handlers = HANDLERS.get(cfg.VCS) + assert handlers, "unrecognized VCS '%s'" % cfg.VCS + verbose = verbose or cfg.verbose + assert ( + cfg.versionfile_source is not None + ), "please set versioneer.versionfile_source" + assert cfg.tag_prefix is not None, "please set versioneer.tag_prefix" + + versionfile_abs = os.path.join(root, cfg.versionfile_source) + + # extract version from first of: _version.py, VCS command (e.g. 'git + # describe'), parentdir. This is meant to work for developers using a + # source checkout, for users of a tarball created by 'setup.py sdist', + # and for users of a tarball/zipball created by 'git archive' or github's + # download-from-tag feature or the equivalent in other VCSes. + + get_keywords_f = handlers.get("get_keywords") + from_keywords_f = handlers.get("keywords") + if get_keywords_f and from_keywords_f: + try: + keywords = get_keywords_f(versionfile_abs) + ver = from_keywords_f(keywords, cfg.tag_prefix, verbose) + if verbose: + print("got version from expanded keyword %s" % ver) + return ver + except NotThisMethod: + pass + + try: + ver = versions_from_file(versionfile_abs) + if verbose: + print("got version from file %s %s" % (versionfile_abs, ver)) + return ver + except NotThisMethod: + pass + + from_vcs_f = handlers.get("pieces_from_vcs") + if from_vcs_f: + try: + pieces = from_vcs_f(cfg.tag_prefix, root, verbose) + ver = render(pieces, cfg.style) + if verbose: + print("got version from VCS %s" % ver) + return ver + except NotThisMethod: + pass + + try: + if cfg.parentdir_prefix: + ver = versions_from_parentdir(cfg.parentdir_prefix, root, verbose) + if verbose: + print("got version from parentdir %s" % ver) + return ver + except NotThisMethod: + pass + + if verbose: + print("unable to compute version") + + return { + "version": "0+unknown", + "full-revisionid": None, + "dirty": None, + "error": "unable to compute version", + "date": None, + } + + +def get_version(): + """Get the short version string for this project.""" + return get_versions()["version"] + + +def get_cmdclass(cmdclass=None): + """Get the custom setuptools/distutils subclasses used by Versioneer. + + If the package uses a different cmdclass (e.g. one from numpy), it + should be provide as an argument. + """ + if "versioneer" in sys.modules: + del sys.modules["versioneer"] + # this fixes the "python setup.py develop" case (also 'install' and + # 'easy_install .'), in which subdependencies of the main project are + # built (using setup.py bdist_egg) in the same python process. Assume + # a main project A and a dependency B, which use different versions + # of Versioneer. A's setup.py imports A's Versioneer, leaving it in + # sys.modules by the time B's setup.py is executed, causing B to run + # with the wrong versioneer. Setuptools wraps the sub-dep builds in a + # sandbox that restores sys.modules to it's pre-build state, so the + # parent is protected against the child's "import versioneer". By + # removing ourselves from sys.modules here, before the child build + # happens, we protect the child from the parent's versioneer too. + # Also see https://github.com/python-versioneer/python-versioneer/issues/52 + + cmds = {} if cmdclass is None else cmdclass.copy() + + # we add "version" to both distutils and setuptools + from distutils.core import Command + + class cmd_version(Command): + description = "report generated version string" + user_options = [] + boolean_options = [] + + def initialize_options(self): + pass + + def finalize_options(self): + pass + + def run(self): + vers = get_versions(verbose=True) + print("Version: %s" % vers["version"]) + print(" full-revisionid: %s" % vers.get("full-revisionid")) + print(" dirty: %s" % vers.get("dirty")) + print(" date: %s" % vers.get("date")) + if vers["error"]: + print(" error: %s" % vers["error"]) + + cmds["version"] = cmd_version + + # we override "build_py" in both distutils and setuptools + # + # most invocation pathways end up running build_py: + # distutils/build -> build_py + # distutils/install -> distutils/build ->.. + # setuptools/bdist_wheel -> distutils/install ->.. + # setuptools/bdist_egg -> distutils/install_lib -> build_py + # setuptools/install -> bdist_egg ->.. + # setuptools/develop -> ? + # pip install: + # copies source tree to a tempdir before running egg_info/etc + # if .git isn't copied too, 'git describe' will fail + # then does setup.py bdist_wheel, or sometimes setup.py install + # setup.py egg_info -> ? + + # we override different "build_py" commands for both environments + if "build_py" in cmds: + _build_py = cmds["build_py"] + elif "setuptools" in sys.modules: + from setuptools.command.build_py import build_py as _build_py + else: + from distutils.command.build_py import build_py as _build_py + + class cmd_build_py(_build_py): + def run(self): + root = get_root() + cfg = get_config_from_root(root) + versions = get_versions() + _build_py.run(self) + # now locate _version.py in the new build/ directory and replace + # it with an updated value + if cfg.versionfile_build: + target_versionfile = os.path.join(self.build_lib, cfg.versionfile_build) + print("UPDATING %s" % target_versionfile) + write_to_version_file(target_versionfile, versions) + + cmds["build_py"] = cmd_build_py + + if "build_ext" in cmds: + _build_ext = cmds["build_ext"] + elif "setuptools" in sys.modules: + from setuptools.command.build_ext import build_ext as _build_ext + else: + from distutils.command.build_ext import build_ext as _build_ext + + class cmd_build_ext(_build_ext): + def run(self): + root = get_root() + cfg = get_config_from_root(root) + versions = get_versions() + _build_ext.run(self) + if self.inplace: + # build_ext --inplace will only build extensions in + # build/lib<..> dir with no _version.py to write to. + # As in place builds will already have a _version.py + # in the module dir, we do not need to write one. + return + # now locate _version.py in the new build/ directory and replace + # it with an updated value + target_versionfile = os.path.join(self.build_lib, cfg.versionfile_build) + print("UPDATING %s" % target_versionfile) + write_to_version_file(target_versionfile, versions) + + cmds["build_ext"] = cmd_build_ext + + if "cx_Freeze" in sys.modules: # cx_freeze enabled? + from cx_Freeze.dist import build_exe as _build_exe + + # nczeczulin reports that py2exe won't like the pep440-style string + # as FILEVERSION, but it can be used for PRODUCTVERSION, e.g. + # setup(console=[{ + # "version": versioneer.get_version().split("+", 1)[0], # FILEVERSION + # "product_version": versioneer.get_version(), + # ... + + class cmd_build_exe(_build_exe): + def run(self): + root = get_root() + cfg = get_config_from_root(root) + versions = get_versions() + target_versionfile = cfg.versionfile_source + print("UPDATING %s" % target_versionfile) + write_to_version_file(target_versionfile, versions) + + _build_exe.run(self) + os.unlink(target_versionfile) + with open(cfg.versionfile_source, "w") as f: + LONG = LONG_VERSION_PY[cfg.VCS] + f.write( + LONG + % { + "DOLLAR": "$", + "STYLE": cfg.style, + "TAG_PREFIX": cfg.tag_prefix, + "PARENTDIR_PREFIX": cfg.parentdir_prefix, + "VERSIONFILE_SOURCE": cfg.versionfile_source, + } + ) + + cmds["build_exe"] = cmd_build_exe + del cmds["build_py"] + + if "py2exe" in sys.modules: # py2exe enabled? + from py2exe.distutils_buildexe import py2exe as _py2exe + + class cmd_py2exe(_py2exe): + def run(self): + root = get_root() + cfg = get_config_from_root(root) + versions = get_versions() + target_versionfile = cfg.versionfile_source + print("UPDATING %s" % target_versionfile) + write_to_version_file(target_versionfile, versions) + + _py2exe.run(self) + os.unlink(target_versionfile) + with open(cfg.versionfile_source, "w") as f: + LONG = LONG_VERSION_PY[cfg.VCS] + f.write( + LONG + % { + "DOLLAR": "$", + "STYLE": cfg.style, + "TAG_PREFIX": cfg.tag_prefix, + "PARENTDIR_PREFIX": cfg.parentdir_prefix, + "VERSIONFILE_SOURCE": cfg.versionfile_source, + } + ) + + cmds["py2exe"] = cmd_py2exe + + # we override different "sdist" commands for both environments + if "sdist" in cmds: + _sdist = cmds["sdist"] + elif "setuptools" in sys.modules: + from setuptools.command.sdist import sdist as _sdist + else: + from distutils.command.sdist import sdist as _sdist + + class cmd_sdist(_sdist): + def run(self): + versions = get_versions() + self._versioneer_generated_versions = versions + # unless we update this, the command will keep using the old + # version + self.distribution.metadata.version = versions["version"] + return _sdist.run(self) + + def make_release_tree(self, base_dir, files): + root = get_root() + cfg = get_config_from_root(root) + _sdist.make_release_tree(self, base_dir, files) + # now locate _version.py in the new base_dir directory + # (remembering that it may be a hardlink) and replace it with an + # updated value + target_versionfile = os.path.join(base_dir, cfg.versionfile_source) + print("UPDATING %s" % target_versionfile) + write_to_version_file( + target_versionfile, self._versioneer_generated_versions + ) + + cmds["sdist"] = cmd_sdist + + return cmds + + +CONFIG_ERROR = """ +setup.cfg is missing the necessary Versioneer configuration. You need +a section like: + + [versioneer] + VCS = git + style = pep440 + versionfile_source = src/myproject/_version.py + versionfile_build = myproject/_version.py + tag_prefix = + parentdir_prefix = myproject- + +You will also need to edit your setup.py to use the results: + + import versioneer + setup(version=versioneer.get_version(), + cmdclass=versioneer.get_cmdclass(), ...) + +Please read the docstring in ./versioneer.py for configuration instructions, +edit setup.cfg, and re-run the installer or 'python versioneer.py setup'. +""" + +SAMPLE_CONFIG = """ +# See the docstring in versioneer.py for instructions. Note that you must +# re-run 'versioneer.py setup' after changing this section, and commit the +# resulting files. + +[versioneer] +#VCS = git +#style = pep440 +#versionfile_source = +#versionfile_build = +#tag_prefix = +#parentdir_prefix = + +""" + +OLD_SNIPPET = """ +from ._version import get_versions +__version__ = get_versions()['version'] +del get_versions +""" + +INIT_PY_SNIPPET = """ +from . import {0} +__version__ = {0}.get_versions()['version'] +""" + + +def do_setup(): + """Do main VCS-independent setup function for installing Versioneer.""" + root = get_root() + try: + cfg = get_config_from_root(root) + except (OSError, configparser.NoSectionError, configparser.NoOptionError) as e: + if isinstance(e, (OSError, configparser.NoSectionError)): + print("Adding sample versioneer config to setup.cfg", file=sys.stderr) + with open(os.path.join(root, "setup.cfg"), "a") as f: + f.write(SAMPLE_CONFIG) + print(CONFIG_ERROR, file=sys.stderr) + return 1 + + print(" creating %s" % cfg.versionfile_source) + with open(cfg.versionfile_source, "w") as f: + LONG = LONG_VERSION_PY[cfg.VCS] + f.write( + LONG + % { + "DOLLAR": "$", + "STYLE": cfg.style, + "TAG_PREFIX": cfg.tag_prefix, + "PARENTDIR_PREFIX": cfg.parentdir_prefix, + "VERSIONFILE_SOURCE": cfg.versionfile_source, + } + ) + + ipy = os.path.join(os.path.dirname(cfg.versionfile_source), "__init__.py") + if os.path.exists(ipy): + try: + with open(ipy, "r") as f: + old = f.read() + except OSError: + old = "" + module = os.path.splitext(os.path.basename(cfg.versionfile_source))[0] + snippet = INIT_PY_SNIPPET.format(module) + if OLD_SNIPPET in old: + print(" replacing boilerplate in %s" % ipy) + with open(ipy, "w") as f: + f.write(old.replace(OLD_SNIPPET, snippet)) + elif snippet not in old: + print(" appending to %s" % ipy) + with open(ipy, "a") as f: + f.write(snippet) + else: + print(" %s unmodified" % ipy) + else: + print(" %s doesn't exist, ok" % ipy) + ipy = None + + # Make sure both the top-level "versioneer.py" and versionfile_source + # (PKG/_version.py, used by runtime code) are in MANIFEST.in, so + # they'll be copied into source distributions. Pip won't be able to + # install the package without this. + manifest_in = os.path.join(root, "MANIFEST.in") + simple_includes = set() + try: + with open(manifest_in, "r") as f: + for line in f: + if line.startswith("include "): + for include in line.split()[1:]: + simple_includes.add(include) + except OSError: + pass + # That doesn't cover everything MANIFEST.in can do + # (http://docs.python.org/2/distutils/sourcedist.html#commands), so + # it might give some false negatives. Appending redundant 'include' + # lines is safe, though. + if "versioneer.py" not in simple_includes: + print(" appending 'versioneer.py' to MANIFEST.in") + with open(manifest_in, "a") as f: + f.write("include versioneer.py\n") + else: + print(" 'versioneer.py' already in MANIFEST.in") + if cfg.versionfile_source not in simple_includes: + print( + " appending versionfile_source ('%s') to MANIFEST.in" + % cfg.versionfile_source + ) + with open(manifest_in, "a") as f: + f.write("include %s\n" % cfg.versionfile_source) + else: + print(" versionfile_source already in MANIFEST.in") + + # Make VCS-specific changes. For git, this means creating/changing + # .gitattributes to mark _version.py for export-subst keyword + # substitution. + do_vcs_install(manifest_in, cfg.versionfile_source, ipy) + return 0 + + +def scan_setup_py(): + """Validate the contents of setup.py against Versioneer's expectations.""" + found = set() + setters = False + errors = 0 + with open("setup.py", "r") as f: + for line in f.readlines(): + if "import versioneer" in line: + found.add("import") + if "versioneer.get_cmdclass()" in line: + found.add("cmdclass") + if "versioneer.get_version()" in line: + found.add("get_version") + if "versioneer.VCS" in line: + setters = True + if "versioneer.versionfile_source" in line: + setters = True + if len(found) != 3: + print("") + print("Your setup.py appears to be missing some important items") + print("(but I might be wrong). Please make sure it has something") + print("roughly like the following:") + print("") + print(" import versioneer") + print(" setup( version=versioneer.get_version(),") + print(" cmdclass=versioneer.get_cmdclass(), ...)") + print("") + errors += 1 + if setters: + print("You should remove lines like 'versioneer.VCS = ' and") + print("'versioneer.versionfile_source = ' . This configuration") + print("now lives in setup.cfg, and should be removed from setup.py") + print("") + errors += 1 + return errors + + +if __name__ == "__main__": + cmd = sys.argv[1] + if cmd == "setup": + errors = do_setup() + errors += scan_setup_py() + if errors: + sys.exit(1)