build.yml

name: Test

on: [push]

jobs:
  build:
    runs-on: ubuntu-latest
    steps:

      # The first step is obviously to check out the repository
      - name: Checkout repo
        uses: actions/checkout@v3

        # The next step is to install a JDK and maven environment
        # A settings.xml file with credentials will be created and stored in that folder
        # See next step for settings.xml creation
      - name: Cache local Maven repository
        uses: actions/cache@v2
        with:
          path: ~/.m2/repository
          key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}
          restore-keys: ${{ runner.os }}-maven-

        # Our library works without Tesseract installed but test will fail on purpose
        # We ensure tesseract C++ library is available on test environment
      - name: Install Tesseract
        run: sudo apt-get install -y -q tesseract-ocr

        # The next step is to install a JDK and maven environment
        # A settings.xml file with credentials will be created and stored in that folder
        # Since we're only testing the stack, no need for a specific configuration with Sonatype credentials
      - name: Set up Maven
        uses: actions/setup-java@v2
        with:
          distribution: "zulu"
          java-version: "11"

        # Pyspark test are integration-tests and requires packaging all dependencies first before
        # invoking a pyspark context. This logic is included in pom.xml and triggered on mvn verify goal
      - name: Run Scala tests and Pyspark compatibility
        run: mvn clean verify -ntp -Dgpg.skip