Skip to content

Add OAuth support in Databricks Loader #1417

Add OAuth support in Databricks Loader

Add OAuth support in Databricks Loader #1417

Workflow file for this run

name: CI
on:
push:
tags:
- '*'
branches:
- master
- develop
pull_request:
jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up JDK 11
uses: actions/setup-java@v1
with:
java-version: 11
- name: Check Scala formatting
if: ${{ always() }}
run: sbt scalafmtCheckAll scalafmtSbtCheck
- name: Run tests
run: sbt coverage test coverageReport
- name: Aggregate coverage data
if: ${{ always() }}
run: sbt coverageAggregate
- name: Submit coveralls data
if: ${{ always() }}
run: sbt coveralls
env:
COVERALLS_REPO_TOKEN: ${{ secrets.COVERALLS_REPO_TOKEN }}
publish_docker:
needs: test
if: startsWith(github.ref, 'refs/tags/')
runs-on: ubuntu-latest
strategy:
matrix:
app:
- redshiftLoader
- snowflakeLoader
- databricksLoader
- transformerKinesis
- transformerPubsub
- transformerKafka
steps:
- name: Checkout Github
uses: actions/checkout@v2
- uses: coursier/cache-action@v6
- name: Set up JDK 11 for loader and streaming transformer
uses: actions/setup-java@v1
with:
java-version: 11
- name: Get the latest Databricks JDBC driver
run: |
curl https://databricks-bi-artifacts.s3.us-east-2.amazonaws.com/simbaspark-drivers/jdbc/2.6.40/DatabricksJDBC42-2.6.40.1070.zip --output DatabricksJDBC42.jar.zip
unzip DatabricksJDBC42.jar.zip
cp ./*/DatabricksJDBC42.jar . # 2.6.34 download changes directory structure - grab the jar from nested directory (which has entropy in its name)
- name: Docker login
uses: docker/login-action@v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Get current version
id: ver
run: echo "::set-output name=tag::${GITHUB_REF#refs/tags/}"
- name: Get app package name
id: packageName
run: |
export PACKAGE_NAME=$(sbt "project ${{ matrix.app }}" dockerAlias -Dsbt.log.noformat=true | sed -n '/\[info\]/ s/\[info\] //p' | tail -1 | tr -d '\n' | cut -d":" -f1)
echo "::set-output name=package_name::$PACKAGE_NAME"
- name: Get app base directory
id: baseDirectory
run: |
export BASE_DIRECTORY=$(sbt "project ${{ matrix.app }}" baseDirectory -Dsbt.log.noformat=true | sed -n '/\[info\]/ s/\[info\] //p' | tail -1 | tr -d '\n')
echo "::set-output name=directory::$BASE_DIRECTORY"
- name: Get app base directory (distroless)
id: baseDirectoryDistroless
run: |
export BASE_DIRECTORY_DISTROLESS=$(sbt "project ${{ matrix.app }}Distroless" baseDirectory -Dsbt.log.noformat=true | sed -n '/\[info\]/ s/\[info\] //p' | tail -1 | tr -d '\n')
echo "::set-output name=directory::$BASE_DIRECTORY_DISTROLESS"
- name: Stage the Docker build
run: sbt "project ${{ matrix.app}}" docker:stage
- name: Stage the Docker distroless build
run: sbt "project ${{ matrix.app }}Distroless" docker:stage
- name: Docker metadata
id: meta
uses: docker/metadata-action@v3
with:
images: ${{ steps.packageName.outputs.package_name }}
tags: |
type=raw,value=latest,enable=${{ !contains(steps.ver.outputs.tag, 'rc') }}
type=raw,value=latest-focal,enable=${{ !contains(steps.ver.outputs.tag, 'rc') }}
type=raw,value=${{ steps.ver.outputs.tag }}
type=raw,value=${{ steps.ver.outputs.tag }}-focal
flavor: |
latest=false
- name: Docker metadata distroless
id: distroless-meta
uses: docker/metadata-action@v3
with:
images: ${{ steps.packageName.outputs.package_name }}
tags: |
type=raw,value=latest-distroless,enable=${{ !contains(steps.ver.outputs.tag, 'rc') }}
type=raw,value=${{ steps.ver.outputs.tag }}-distroless
flavor: |
latest=false
- name: Set up QEMU
uses: docker/setup-qemu-action@v1
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v1
- name: Push image
uses: docker/build-push-action@v2
with:
context: ${{ steps.baseDirectory.outputs.directory }}/target/docker/stage
file: ${{ steps.baseDirectory.outputs.directory }}/target/docker/stage/Dockerfile
platforms: linux/amd64,linux/arm64/v8
tags: ${{ steps.meta.outputs.tags }}
push: true
- name: Push distroless image
uses: docker/build-push-action@v2
with:
context: ${{ steps.baseDirectoryDistroless.outputs.directory }}/target/docker/stage
file: ${{ steps.baseDirectoryDistroless.outputs.directory }}/target/docker/stage/Dockerfile
platforms: linux/amd64,linux/arm64/v8
tags: ${{ steps.distroless-meta.outputs.tags }}
push: true
- name: Build local distroless image, which is needed to run Snyk
if: ${{ !contains(github.ref_name, 'rc') }}
run: sbt "project ${{ matrix.app }}Distroless" docker:publishLocal
- name: Run Snyk to check for vulnerabilities
uses: snyk/actions/docker@master
if: ${{ !contains(github.ref_name, 'rc') }}
with:
image: "${{ steps.packageName.outputs.package_name }}:${{ github.ref_name }}-distroless"
args: "--app-vulns --org=data-processing-new"
command: monitor
env:
SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
create_release:
needs: test
if: startsWith(github.ref, 'refs/tags/')
runs-on: ubuntu-latest
steps:
- name: Checkout Github
uses: actions/checkout@v2
- uses: coursier/cache-action@v6
- name: Set up JDK 11 for loader and streaming transformer
uses: actions/setup-java@v1
with:
java-version: 11
- name: Get the latest Databricks JDBC driver
run: |
curl https://databricks-bi-artifacts.s3.us-east-2.amazonaws.com/simbaspark-drivers/jdbc/2.6.33/DatabricksJDBC42-2.6.33.1055.zip --output DatabricksJDBC42.jar.zip
unzip DatabricksJDBC42.jar.zip
- name: Build jar files
env:
SKIP_TEST: true
run: |
sbt \
'project redshiftLoader; assembly' \
'project snowflakeLoader; assembly' \
'project databricksLoader; assembly' \
'project transformerBatch; assembly' \
'project transformerKinesis; assembly' \
'project transformerPubsub; assembly' \
'project transformerKafka; assembly'
- name: Get current version
id: ver
run: echo "::set-output name=project_version::${GITHUB_REF#refs/tags/}"
- name: Create GitHub release and attach jars
uses: softprops/action-gh-release@v1
with:
draft: true
prerelease: true
name: ${{ steps.ver.outputs.project_version }}
tag_name: ${{ steps.ver.outputs.project_version }}
files: |
modules/redshift-loader/target/scala-2.12/snowplow-redshift-loader-${{ steps.ver.outputs.project_version }}.jar
modules/snowflake-loader/target/scala-2.12/snowplow-snowflake-loader-${{ steps.ver.outputs.project_version }}.jar
modules/databricks-loader/target/scala-2.12/snowplow-databricks-loader-${{ steps.ver.outputs.project_version }}.jar
modules/transformer-batch/target/scala-2.12/snowplow-transformer-batch-${{ steps.ver.outputs.project_version }}.jar
modules/transformer-kinesis/target/scala-2.12/snowplow-transformer-kinesis-${{ steps.ver.outputs.project_version }}.jar
modules/transformer-pubsub/target/scala-2.12/snowplow-transformer-pubsub-${{ steps.ver.outputs.project_version }}.jar
modules/transformer-kafka/target/scala-2.12/snowplow-transformer-kafka-${{ steps.ver.outputs.project_version }}.jar
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}