Migrate Off Circle CI / To Github Actions + dagger.io

.changes/unreleased/Under the Hood-20230929-161218.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Add Github action for integration testing, use dagger-io to run tests. Remove circle ci workflow.
+time: 2023-09-29T16:12:18.968755+02:00
+custom:
+  Author: JCZuurmond, colin-rogers-dbt
+  Issue: "719"

.github/scripts/update_dbt_core_branch.sh

@@ -0,0 +1,17 @@
+#!/bin/bash -e
+set -e
+
+git_branch=$1
+target_req_file="dev-requirements.txt"
+core_req_sed_pattern="s|dbt-core.git.*#egg=dbt-core|dbt-core.git@${git_branch}#egg=dbt-core|g"
+tests_req_sed_pattern="s|dbt-core.git.*#egg=dbt-tests|dbt-core.git@${git_branch}#egg=dbt-tests|g"
+if [[ "$OSTYPE" == darwin* ]]; then
+ # mac ships with a different version of sed that requires a delimiter arg
+ sed -i "" "$core_req_sed_pattern" $target_req_file
+ sed -i "" "$tests_req_sed_pattern" $target_req_file
+else
+ sed -i "$core_req_sed_pattern" $target_req_file
+ sed -i "$tests_req_sed_pattern" $target_req_file
+fi
+core_version=$(curl "https://raw.githubusercontent.com/dbt-labs/dbt-core/${git_branch}/core/dbt/version.py" | grep "__version__ = *"|cut -d'=' -f2)
+bumpversion --allow-dirty --new-version "$core_version" major

.github/workflows/integration.yml

@@ -0,0 +1,160 @@
+# **what?**
+# Runs integration tests.
+
+# **why?**
+# Ensure code runs as expected.
+
+# **when?**
+# This will run for all PRs, when code is pushed to a release
+# branch, and when manually triggered.
+
+name: Adapter Integration Tests
+
+on:
+  push:
+    branches:
+      - "main"
+      - "*.latest"
+      - "releases/*"
+  pull_request_target:
+  workflow_dispatch:
+    inputs:
+      dbt-core-branch:
+        description: "branch of dbt-core to use in dev-requirements.txt"
+        required: false
+        type: string
+
+# explicitly turn off permissions for `GITHUB_TOKEN`
+permissions: read-all
+
+# will cancel previous workflows triggered by the same event and for the same ref for PRs or same SHA otherwise
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ contains(github.event_name, 'pull_request_target') && github.event.pull_request.head.ref || github.sha }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  # generate test metadata about what files changed and the testing matrix to use
+  test-metadata:
+    # run if not a PR from a forked repository or has a label to mark as safe to test
+    if: >-
+      github.event_name != 'pull_request_target' ||
+      github.event.pull_request.head.repo.full_name == github.repository ||
+      contains(github.event.pull_request.labels.*.name, 'ok to test')
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.generate-matrix.outputs.result }}
+
+    steps:
+      - name: Check out the repository (non-PR)
+        if: github.event_name != 'pull_request_target'
+        uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+
+      - name: Check out the repository (PR)
+        if: github.event_name == 'pull_request_target'
+        uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Check if relevant files changed
+        if: github.event_name == 'pull_request_target'
+        # https://github.com/marketplace/actions/paths-changes-filter
+        # For each filter, it sets output variable named by the filter to the text:
+        #  'true' - if any of changed files matches any of filter rules
+        #  'false' - if none of changed files matches any of filter rules
+        # also, returns:
+        #  `changes` - JSON array with names of all filters matching any of the changed files
+        uses: dorny/paths-filter@v2
+        id: get-changes
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          filters: |
+            spark:
+              - 'dbt/**'
+              - 'tests/**'
+              - 'dev-requirements.txt'
+
+  test:
+    name: ${{ matrix.test }} / python ${{ matrix.python-version }} / ubuntu-latest
+
+    # run if not a PR from a forked repository or has a label to mark as safe to test
+    # also checks that the matrix generated is not empty
+    if: >-
+      (
+        github.event_name != 'pull_request_target' ||
+        github.event.pull_request.head.repo.full_name == github.repository ||
+        contains(github.event.pull_request.labels.*.name, 'ok to test')
+      )
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        test:
+          - "apache_spark"
+          - "spark_session"
+          - "databricks_sql_endpoint"
+          - "databricks_cluster"
+          - "databricks_http_cluster"
+
+    env:
+      TOXENV: integration-${{ matrix.test }}
+      PYTEST_ADDOPTS: "-v --color=yes --csv integration_results.csv"
+      DBT_INVOCATION_ENV: github-actions
+      DD_CIVISIBILITY_AGENTLESS_ENABLED: true
+      DD_API_KEY: ${{ secrets.DATADOG_API_KEY }}
+      DD_SITE: datadoghq.com
+      DD_ENV: ci
+      DD_SERVICE: ${{ github.event.repository.name }}
+      DBT_DATABRICKS_CLUSTER_NAME: ${{ secrets.DBT_DATABRICKS_CLUSTER_NAME }}
+      DBT_DATABRICKS_HOST_NAME: ${{ secrets.DBT_DATABRICKS_HOST_NAME }}
+      DBT_DATABRICKS_ENDPOINT: ${{ secrets.DBT_DATABRICKS_ENDPOINT }}
+      DBT_DATABRICKS_TOKEN: ${{ secrets.DBT_DATABRICKS_TOKEN }}
+      DBT_DATABRICKS_USER: ${{ secrets.DBT_DATABRICKS_USERNAME }}
+      DBT_TEST_USER_1: "[email protected]"
+      DBT_TEST_USER_2: "[email protected]"
+      DBT_TEST_USER_3: "[email protected]"
+      ODBC_DRIVER: "Simba"
+
+    steps:
+      - name: Check out the repository
+        if: github.event_name != 'pull_request_target'
+        uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+
+      # explicitly checkout the branch for the PR,
+      # this is necessary for the `pull_request` event
+      - name: Check out the repository (PR)
+        if: github.event_name == 'pull_request_target'
+        uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+
+      - name: Install python dependencies
+        run: |
+          python -m pip install --user --upgrade pip
+          python -m pip --version
+          python -m pip install -r dagger/requirements.txt
+
+      - name: Update dev_requirements.txt
+        if: inputs.dbt-core-branch != ''
+        run: |
+          pip install bumpversion
+          ./.github/scripts/update_dbt_core_branch.sh ${{ inputs.dbt-core-branch }}
+
+
+      - name: Run tests for ${{ matrix.test }}
+        run: python dagger/run_dbt_spark_tests.py --profile ${{ matrix.test }}

.gitignore

@@ -44,3 +44,5 @@ test.env
 .hive-metastore/
 .spark-warehouse/
 dbt-integration-tests
+/.tool-versions
+/.hypothesis/*

README.md

@@ -5,9 +5,6 @@
   <a href="https://github.com/dbt-labs/dbt-spark/actions/workflows/main.yml">
     <img src="https://github.com/dbt-labs/dbt-spark/actions/workflows/main.yml/badge.svg?event=push" alt="Unit Tests Badge"/>
   </a>
-  <a href="https://circleci.com/gh/dbt-labs/dbt-spark/?branch=main">
-    <img src="https://circleci.com/gh/dbt-labs/dbt-spark/tree/main.svg?style=shield" alt="Integration Tests Badge"/>
-  </a>
 </p>
 
 **[dbt](https://www.getdbt.com/)** enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

dagger/requirements.txt

@@ -0,0 +1,2 @@
+dagger-io~=0.8.0
+python-dotenv