acryldata · hsheth2 · Apr 28, 2023 · Apr 27, 2023 · Apr 28, 2023
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -0,0 +1,27 @@
+name: CI
+on:
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  ci:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    - uses: extractions/setup-just@v1
+
+    - name: Setup
+      run: |
+        just setup
+    - name: Lint
+      run: |
+        just lint
+    - name: Test
+      run: |
+        just test
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,179 @@
+.envrc
+.tool-versions
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-# Acryl dbt action
+# Acryl dbt Impact Analysis Action
 
 This GitHub action will comment on your PRs with a summary of the impact of changes within a dbt project.
 

diff --git a/action.yml b/action.yml
@@ -1,5 +1,5 @@
-name: Acryl dbt Impact Analysis
-description: Comments on PRs with the impact of dbt changes.
+name: Acryl dbt Impact Analysis Action
+description: Comments on PRs with the downstream impact of dbt changes.
 inputs:
   datahub_gms_host:
     description: "DataHub GMS host."
@@ -27,13 +27,6 @@ inputs:
 runs:
   using: "composite"
   steps:
-    # - uses: actions/checkout@v3
-    #   with:
-    #     # We need git history for the git merge-base.
-    #     fetch-depth: 0
-    # TODO: For large repos, use this instead:
-    # - uses: rmacklin/fetch-through-merge-base@v0
-
     # TODO: Add better error checking:
     # - Validate that we have sufficient git history.
     # - Somehow ensure that this is running on a PR.

diff --git a/impact_analysis.py b/impact_analysis.py
@@ -101,7 +101,7 @@ def find_datahub_urns(dbt_node_ids: List[str]) -> List[str]:
         "count": 10000,
         "filter": {"or": [{"and": [filter_cond]} for filter_cond in filter_conditions]},
     }
-    results: Dict = graph._post_generic(graph._get_search_endpoint(), search_body)
+    results: Dict = graph._post_generic(graph._search_endpoint, search_body)
 
     urns = [res["entity"] for res in results["value"]["entities"]]
 

diff --git a/impact_analysis.sh b/impact_analysis.sh
@@ -9,9 +9,8 @@ dbt --version
 # Install dbt deps.
 dbt deps
 
-# Install acryl-datahub package.
-pip install acryl-datahub==0.10.1.2rc8
-# pip cache remove 'acryl*'
+# Install our requirements.
+pip install -r "${GITHUB_ACTION_PATH}/requirements.txt"
 
 # Set DBT_PROFILE_NAME if not provided.
 if [ -z "${DBT_PROFILE_NAME}" ]; then

diff --git a/justfile b/justfile
@@ -0,0 +1,19 @@
+
+test: lint
+	# TODO
+
+setup:
+	# Create venv.
+	python3 -m venv venv
+	venv/bin/pip install --upgrade pip wheel setuptools
+	venv/bin/pip install -r requirements.txt -r requirements-dev.txt
+
+lint:
+	venv/bin/black --check .
+	venv/bin/ruff .
+	venv/bin/mypy .
+
+lint-fix:
+	venv/bin/black .
+	venv/bin/ruff .
+	venv/bin/mypy .
diff --git a/mypy.ini b/mypy.ini
@@ -0,0 +1,3 @@
+[mypy]
+plugins = pydantic.mypy
+exclude = venv
diff --git a/read_dbt_profile_name.py b/read_dbt_profile_name.py
@@ -1,7 +1,7 @@
 import yaml
 import pathlib
 
-with pathlib.Path('dbt_project.yml').open() as f:
+with pathlib.Path("dbt_project.yml").open() as f:
     dbt_project = yaml.safe_load(f)
 
-print(dbt_project['profile'])
+print(dbt_project["profile"])
diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -0,0 +1,6 @@
+dbt-core
+black
+ruff
+pytest
+mypy
+types-PyYAML
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1 @@
+acryl-datahub==0.10.2.2
diff --git a/ruff.toml b/ruff.toml
@@ -0,0 +1,2 @@
+# Never enforce `E501` (line length violations).
+ignore = ["E501"]
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		# Never enforce `E501` (line length violations).
		ignore = ["E501"]