Initial commit

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/deploy_recipe.yaml

@@ -0,0 +1,54 @@
+name: Deploy Recipes to Google Dataflow
+
+env:
+  JOB_NAME: ${{ github.event.inputs.recipe_id }}-${{ github.run_id }}-${{ github.run_attempt }}
+  # Can we sanitize the job name here to remove special characters?
+
+on:
+  workflow_dispatch:
+    inputs:
+      recipe_id:
+        description: 'The id of a single recipe to submit to Dataflow'
+        required: true
+        default: 'all'
+
+jobs:
+  deploy-recipes:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: "Authenticate to Google Cloud"
+        id: "auth"
+        uses: "google-github-actions/auth@v2"
+        with:
+          credentials_json: "${{ secrets.LEAP_BAKERY_SERVICE_ACCOUNT }}"
+      - name: "Install dependencies"
+        run: |
+          python -m pip install --upgrade pip
+          pip install pangeo-forge-runner
+      - name: "Deploy recipes"
+        run: |
+          pangeo-forge-runner bake \
+            --repo=${{ github.server_url }}/${{ github.repository }}.git \
+            --ref=${{ github.sha }} \
+            --feedstock-subdir='feedstock' \
+            --Bake.job_name=${{ env.JOB_NAME }} \
+            --Bake.recipe_id=${{ github.event.inputs.recipe_id }} \
+            -f configs/config_dataflow.py
+        env:
+          GOOGLE_APPLICATION_CREDENTIALS: "${{ steps.auth.outputs.credentials_file_path }}"
+      - name: Wait for Dataflow jobs to finish
+        # I tried to make this reusable but the fucking thing would not accept env.JOB_NAME as input.
+        # AT that point, screw it, not worth it.
+        run: |
+          jobname="${{ env.JOB_NAME }}"
+          while true; do
+            count=$(gcloud dataflow jobs list --status=active --filter="name:${jobname}" --format="value(id)" | wc -l)
+            echo "Active Dataflow jobs: $count"
+            if [ "$count" -eq "0" ]; then
+              echo "No active Dataflow jobs found."
+              break
+            fi
+            echo "Waiting for Dataflow jobs to finish..."
+            sleep 20
+          done

.github/workflows/validate-catalog.yaml

@@ -0,0 +1,27 @@
+name: Catalog
+
+on:
+  pull_request:
+    branches:
+  push:
+    branches:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+    validate:
+        runs-on: ubuntu-latest
+        defaults:
+            run:
+                shell: bash -l {0}
+        steps:
+            - uses: actions/checkout@v4
+            - uses: actions/setup-python@v5
+              with:
+                  python-version: '3.10'
+            - name: validate feedstock entry
+              uses: leap-stc/data-catalog-actions/leap-catalog@main
+              with:
+                single-feedstock: "./feedstock/catalog.yaml"

.gitignore

@@ -0,0 +1,163 @@
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+proto_feedstock/

.pre-commit-config.yaml

@@ -0,0 +1,22 @@
+ci:
+  autoupdate_schedule: quarterly
+  autofix_prs: true
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-toml
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: debug-statements
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.3.5
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [ --fix ]
+      # Run the formatter.
+      - id: ruff-format