daft

[FEAT] Native Parquet Reader into pyarrow directly #4426

Workflow file for this run

.github/workflows/python-package.yml at ea2bd05

	# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
	# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions

	name: daft

	on:
	push:
	branches: [main]
	pull_request:
	branches: [main]

	env:
	DAFT_ANALYTICS_ENABLED: '0'

	jobs:
	unit-tests-with-coverage:
	runs-on: ubuntu-latest
	timeout-minutes: 15
	strategy:
	fail-fast: false
	matrix:
	python-version: ['3.7', '3.10']
	daft-runner: [py, ray]
	new-query-planner: [1, 0]
	pyarrow-version: [6.0.1, 12.0]
	exclude:
	- daft-runner: ray
	pyarrow-version: 6.0.1
	- daft-runner: py
	python-version: '3.10'
	pyarrow-version: 6.0.1

	steps:
	- uses: actions/checkout@v4
	- uses: moonrepo/setup-rust@v0
	with:
	cache: false
	- name: Install cargo-llvm-cov
	uses: taiki-e/install-action@cargo-llvm-cov
	- uses: Swatinem/rust-cache@v2
	with:
	key: ${{ runner.os }}-build
	cache-all-crates: 'true'

	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}

	- name: Setup Virtual Env
	run: \|
	python -m venv venv
	echo "$GITHUB_WORKSPACE/venv/bin" >> $GITHUB_PATH

	- name: Install dependencies
	run: \|
	pip install --upgrade pip
	pip install -r requirements-dev.txt

	- name: Override pyarrow
	if: ${{ matrix.pyarrow-version }}
	run: pip install pyarrow==${{ matrix.pyarrow-version }}

	- name: Build library and Test with pytest
	run: \|
	source activate
	# source <(cargo llvm-cov show-env --export-prefix)
	# export CARGO_TARGET_DIR=$CARGO_LLVM_COV_TARGET_DIR
	# export CARGO_INCREMENTAL=1
	# cargo llvm-cov clean --workspace
	maturin develop
	mkdir -p report-output && pytest --cov=daft --ignore tests/integration --durations=50
	coverage combine -a --data-file='.coverage' \|\| true
	coverage xml -o ./report-output/coverage-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.daft-runner }}-${{ matrix.pyarrow-version }}-${{ matrix.new-query-planner }}.xml
	# cargo llvm-cov --no-run --lcov --output-path report-output/rust-coverage-${{ runner.os }}-${{ matrix.python-version }}-${{ matrix.daft-runner }}-${{ matrix.pyarrow-version }}-${{ matrix.new-query-planner }}.lcov
	env:
	DAFT_RUNNER: ${{ matrix.daft-runner }}
	DAFT_NEW_QUERY_PLANNER: ${{ matrix.new-query-planner }}

	- name: Upload coverage report
	uses: actions/upload-artifact@v3
	with:
	name: coverage-reports
	path: ./report-output

	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] Pytest Unit Tests <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	integration-test-build:
	runs-on: ubuntu-latest
	timeout-minutes: 30
	env:
	package-name: getdaft
	strategy:
	matrix:
	python-version: ['3.7']
	steps:
	- uses: actions/checkout@v4
	with:
	submodules: true
	fetch-depth: 0
	- uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}
	architecture: x64
	- run: pip install -U twine toml maturin
	- run: python tools/patch_package_version.py
	- uses: moonrepo/setup-rust@v0
	with:
	cache: false
	- uses: Swatinem/rust-cache@v2
	with:
	key: ${{ runner.os }}-integration-build
	cache-all-crates: 'true'

	# NOTE: we don't build with all the actual release optimizations to avoid hellish CI times
	- name: Build wheels
	run: maturin build --release --compatibility linux --out dist
	- name: Upload wheels
	uses: actions/upload-artifact@v3
	with:
	name: wheels
	path: dist

	integration-test-tpch:
	runs-on: ubuntu-latest
	timeout-minutes: 30
	needs:
	- integration-test-build
	env:
	package-name: getdaft
	strategy:
	fail-fast: false
	matrix:
	python-version: ['3.7']
	daft-runner: [py, ray]
	new-query-planner: [1, 0]
	steps:
	- uses: actions/checkout@v4
	with:
	submodules: true
	fetch-depth: 0
	- uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}
	architecture: x64
	- name: Download built wheels
	uses: actions/download-artifact@v3
	with:
	name: wheels
	path: dist
	- name: Setup Virtual Env
	run: \|
	python -m venv venv
	echo "$GITHUB_WORKSPACE/venv/bin" >> $GITHUB_PATH
	- name: Install Daft and dev dependencies
	run: \|
	pip install --upgrade pip
	pip install -r requirements-dev.txt dist/${{ env.package-name }}-x86_64.whl --force-reinstall
	rm -rf daft
	- uses: actions/cache@v3
	env:
	cache-name: cache-tpch-data
	with:
	path: data/tpch-dbgen
	key: ${{ runner.os }}-build-${{ env.cache-name }}-${{ hashFiles('tests/integration/test_tpch.py', 'benchmarking/tpch/**') }}
	- name: Run TPCH integration tests
	run: \|
	pytest tests/integration/test_tpch.py --durations=50
	env:
	DAFT_RUNNER: ${{ matrix.daft-runner }}
	DAFT_NEW_QUERY_PLANNER: ${{ matrix.new-query-planner }}
	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] TPCH Integration Tests <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	integration-test-io:
	runs-on: ubuntu-latest
	timeout-minutes: 30
	needs:
	- integration-test-build
	env:
	package-name: getdaft
	strategy:
	fail-fast: false
	matrix:
	python-version: ['3.8'] # can't use 3.7 due to requiring anon mode for adlfs
	daft-runner: [py, ray]
	new-query-planner: [1, 0]
	# These permissions are needed to interact with GitHub's OIDC Token endpoint.
	# This is used in the step "Assume GitHub Actions AWS Credentials"
	permissions:
	id-token: write
	contents: read
	steps:
	- uses: actions/checkout@v4
	with:
	submodules: true
	fetch-depth: 0
	- uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}
	architecture: x64
	- name: Download built wheels
	uses: actions/download-artifact@v3
	with:
	name: wheels
	path: dist
	- name: Setup Virtual Env
	run: \|
	python -m venv venv
	echo "$GITHUB_WORKSPACE/venv/bin" >> $GITHUB_PATH
	- name: Install Daft and dev dependencies
	run: \|
	pip install --upgrade pip
	pip install -r requirements-dev.txt dist/${{ env.package-name }}-x86_64.whl --force-reinstall
	rm -rf daft
	- name: Prepare tmpdirs for IO services
	run: \|
	mkdir -p /tmp/daft-integration-testing/nginx
	chmod +rw /tmp/daft-integration-testing/nginx
	- name: Assume GitHub Actions AWS Credentials
	uses: aws-actions/configure-aws-credentials@v3
	with:
	aws-region: us-west-2
	role-to-assume: ${{ secrets.ACTIONS_AWS_ROLE_ARN }}
	role-session-name: DaftPythonPackageGitHubWorkflow
	- name: Spin up IO services
	uses: isbang/[email protected]
	with:
	compose-file: ./tests/integration/docker-compose/docker-compose.yml
	down-flags: --volumes
	- name: Run IO integration tests
	run: \|
	pytest tests/integration/io -m 'integration' --durations=50
	env:
	DAFT_RUNNER: ${{ matrix.daft-runner }}
	DAFT_NEW_QUERY_PLANNER: ${{ matrix.new-query-planner }}
	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] IO Integration Tests <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	rust-tests:
	runs-on: ubuntu-latest
	timeout-minutes: 15
	strategy:
	fail-fast: false
	steps:
	- uses: actions/checkout@v4
	- uses: moonrepo/setup-rust@v0
	with:
	cache: false
	- uses: Swatinem/rust-cache@v2
	with:
	key: ${{ runner.os }}-rust-build
	cache-all-crates: 'true'

	- name: Install cargo-llvm-cov
	uses: taiki-e/install-action@cargo-llvm-cov
	- name: Generate code coverage
	run: mkdir -p report-output && cargo llvm-cov --no-default-features --workspace --lcov --output-path ./report-output/lcov.info
	- name: Upload coverage report
	uses: actions/upload-artifact@v3
	with:
	name: coverage-reports
	path: ./report-output
	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] Rust Unit Tests <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	publish-coverage-reports:
	name: Publish coverage reports to CodeCov
	runs-on: ubuntu-latest
	needs:
	- unit-tests-with-coverage
	- rust-tests
	steps:
	- uses: actions/checkout@v4
	- uses: actions/download-artifact@v3
	with:
	name: coverage-reports
	path: ./report-output
	- name: Upload coverage reports to Codecov with GitHub Action
	uses: codecov/codecov-action@v3
	env:
	CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
	files: ./report-output/*
	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] Codecov Uploads <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	test-imports:
	runs-on: ubuntu-latest
	timeout-minutes: 15
	strategy:
	fail-fast: false
	matrix:
	python-version: ['3.7']

	steps:
	- uses: actions/checkout@v4
	- uses: moonrepo/setup-rust@v0
	with:
	cache: false
	- uses: Swatinem/rust-cache@v2
	with:
	key: ${{ runner.os }}-build
	cache-all-crates: 'true'

	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}

	- name: Setup Virtual Env
	run: \|
	python -m venv venv
	source venv/bin/activate
	pip install maturin

	- name: Build Rust Library
	run: \|
	venv/bin/maturin build --out dist

	- name: Test Imports in Clean Env
	run: \|
	rm -rf daft
	rm -rf venv
	python -m venv venv
	source venv/bin/activate
	ls -R ./dist
	venv/bin/pip install dist/*.whl
	venv/bin/python -c 'import daft; from daft import *'

	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] Python Import Checks <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

	style:
	runs-on: ubuntu-latest
	timeout-minutes: 15
	strategy:
	fail-fast: false
	matrix:
	python-version: ['3.8']
	steps:
	- uses: actions/checkout@v4
	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}
	- name: Install pre-commit
	run: \|
	pip install --upgrade pip
	pip install pre-commit
	- uses: moonrepo/setup-rust@v0
	with:
	cache: false
	- uses: Swatinem/rust-cache@v2
	with:
	key: ${{ runner.os }}-build
	cache-all-crates: 'true'

	- uses: actions/cache@v3
	id: pre-commit-cache
	with:
	path: ~/.cache/pre-commit/
	key: ${{ runner.os }}-python-${{ steps.setup-python.outputs.python-version }}-pre-commit-${{ hashFiles('.pre-commit-config.yaml') }}
	- name: Python And Rust Style Check
	run: \|
	pre-commit run --all-files

	- name: Send Slack notification on failure
	uses: slackapi/[email protected]
	if: ${{ failure() && (github.ref == 'refs/heads/main') }}
	with:
	payload: \|
	{
	"blocks": [
	{
	"type": "section",
	"text": {
	"type": "mrkdwn",
	"text": ":rotating_light: [CI] Style Checks <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}\|workflow> FAILED on main :rotating_light:"
	}
	}
	]
	}
	env:
	SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
	SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[FEAT] Native Parquet Reader into pyarrow directly #4426

Workflow file

[FEAT] Native Parquet Reader into pyarrow directly #4426

Jobs

Run details

Workflow file for this run