adds mkdag

mkdag/.github/workflows/ci.yml

@@ -0,0 +1,30 @@
+name: CI
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel black mypy pytest pytest-cov
+          pip install .
+
+      - name: Run Black
+        run: black --check --verbose mkdag/ tests/
+
+      - name: Run Mypy
+        run: mypy --ignore-missing-imports  mkdag/ tests/
+
+      - name: Run Pytest
+        run: pytest

mkdag/.gitignore

@@ -0,0 +1,164 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+.idea/
+attic/

mkdag/mkdag/__init__.py

@@ -0,0 +1 @@
+

mkdag/mkdag/cli.py

@@ -0,0 +1,70 @@
+import subprocess
+
+import click
+import yaml
+from jinja2 import Environment, FileSystemLoader
+
+
+@click.command(name="render-dag")
+@click.option(
+    "--config",
+    "-c",
+    type=click.Path(exists=True),
+    required=True,
+    help="Path to the YAML configuration file.",
+)
+@click.option(
+    "--template",
+    "-t",
+    type=click.Path(exists=True),
+    required=True,
+    help="Path to the Jinja template file.",
+)
+@click.option(
+    "--output",
+    "-o",
+    type=click.Path(),
+    default="generated_dag.py",
+    help="Path where the generated DAG file should be saved (default: generated_dag.py).",
+)
+def render_dag_cli(config, template, output):
+    """CLI tool to render an Airflow DAG from a YAML configuration file using Jinja."""
+    try:
+        render_dag(config, output, template)
+
+        click.echo(f"✅ DAG file successfully generated: {output}")
+
+    except Exception as e:
+        click.echo(f"❌ Error: {e}", err=True)
+        exit(1)
+
+
+def render_dag(config, output, template):
+    """Render an Airflow DAG from a YAML configuration file using Jinja."""
+    # Load YAML config
+    with open(config, "r") as file:
+        config_data = yaml.safe_load(file)
+    assert 'dag_id' in config_data, 'dag_id not found in config file'
+    # Load Jinja template
+    env = Environment(loader=FileSystemLoader("."), autoescape=True)
+    template_obj = env.get_template(template)
+    # Render template
+    dag_code = template_obj.render(config_data)
+    # Save the rendered DAG
+    with open(output, "w") as dag_file:
+        dag_file.write(dag_code)
+    if output.endswith('.py'):
+        reformat_with_black(output)
+
+
+def reformat_with_black(output_file):
+    """Reformat the output file using black."""
+    black_result = subprocess.run(['black', output_file], capture_output=True, text=True)
+    if black_result.returncode == 0:
+        print(f"Black formatting applied successfully to {output_file}")
+    else:
+        print(f"Black formatting failed: {black_result.stdout} {black_result.stderr}")
+
+
+if __name__ == "__main__":
+    render_dag_cli()

mkdag/mypy.ini

@@ -0,0 +1,2 @@
+[mypy]
+disable_error_code = import-untyped

mkdag/pytest.ini

@@ -0,0 +1,7 @@
+# pytest.ini
+[pytest]
+filterwarnings =
+    ignore::DeprecationWarning:halo.*
+markers =
+    asyncio: asyncio mark
+; addopts = --cov=fhir_query --cov-report=term-missing

mkdag/requirements-dev.txt

@@ -0,0 +1,6 @@
+setuptools
+wheel
+black
+mypy
+pytest
+pytest-cov

mkdag/requirements.txt

@@ -0,0 +1,3 @@
+click
+jinja2
+pyyaml

mkdag/setup.py

@@ -0,0 +1,19 @@
+from setuptools import setup, find_packages
+
+
+def parse_requirements(filename: str) -> list[str]:
+    with open(filename, "r") as file:
+        return [line.strip() for line in file if line.strip() and not line.startswith("#")]
+
+
+setup(
+    name="mkdag",
+    version="0.1.0",
+    packages=find_packages(),
+    install_requires=parse_requirements("requirements.txt"),
+    entry_points={
+        "console_scripts": [
+            "mkdag=mkdag.cli:render_dag_cli",
+        ],
+    },
+)

mkdag/tests/__init__.py

@@ -0,0 +1 @@
+

mkdag/tests/fixtures/pop-etl/config.yaml

@@ -0,0 +1,42 @@
+dag_id: "test2"
+schedule_interval: "@daily"
+start_date: "2025-01-01"
+description: "A POP (plain old python) ETL pipeline"
+
+variables:
+  dag:
+    aws_conn_id: test2_dag
+    bucket_name: EllrottLab
+    etag_variable_name: test_etag
+    s3_prefix: tractor/swapi
+    url: https://swapi.dev/api/
+  etag: INITIAL-VALUE
+
+connections:
+  test2_dag:
+    conn_type: aws
+    description: connection to ceph bucket for test2
+    login: CHANGE_ME-aws_access_key_id
+    password: CHANGE_ME-aws_secret_access_key
+    extra:
+      endpoint_url: https://rgw.ohsu.edu
+
+sensor:
+  description: "Check if the ETag has changed"
+  type: "http-etag"
+  poke_interval: 60
+  timeout: 120
+
+extract:
+  description: "Download from url, save in S3"
+  type: "http-s3"
+
+transform:
+  description: "Transform from json, save in S3 as html"
+  type: "json-html"
+
+load:
+  description: "(mock) list the transformed files"
+  type: "mock"
+
+