container_integration_tests.yml

name: Container Integration Tests Workflow

on:
  workflow_dispatch:
    inputs:
      force_run:
        description: 'Force run even if ENABLE_DOCKER_TESTS is false'
        required: false
        type: boolean
        default: false
  push:
    branches:
      - develop
    paths-ignore:
      - "doc/**"
      - "**/*.md"
      - "**/*.txt"
      - ".github/ISSUE_TEMPLATE/**"
      - ".github/*.md"
  pull_request:
    branches:
      - develop
    paths-ignore:
      - "doc/**"
      - "**/*.md"
      - "**/*.txt"
      - ".github/ISSUE_TEMPLATE/**"
      - ".github/*.md"

concurrency:
  group: "container-integration-tests-group"
  cancel-in-progress: true

jobs:
  main-integration-tests-workflow:
    runs-on: ubuntu-latest
    timeout-minutes: 120

    defaults:
      run:
        shell: bash

    permissions:
        checks: write
        pull-requests: write

    steps:

      # ---------------------------
      # CHECKOUT
      # ---------------------------
      - name: Checkout repository
        uses: actions/checkout@v6

      # ---------------------------
      # VERIFY DOCKER
      # ---------------------------
      - name: Verify Docker
        run: |
          set -euo pipefail
          docker version
          
      # ---------------------------
      # SETUP JAVA + MAVEN
      # ---------------------------
      - name: Setup Java
        uses: actions/setup-java@v5
        with:
          distribution: "temurin"
          java-version: "21"
          cache: "maven"

      - name: Verify Maven
        run: |
          set -euo pipefail
          mvn -version
          
      # ---------------------------
      # CLEAN PREVIOUS VOLUMES
      # ---------------------------
      - name: Clean docker-dev-volumes
        run: |
          set -euo pipefail
          rm -rf docker-dev-volumes || true
          
      # ---------------------------
      # BUILD IMAGES (Dataverse-native)
      # ---------------------------
      - name: Build Dataverse containers via Maven
        run: |
          set -euo pipefail
          # Force unit tests to run, generate coverage, and ignore failures so the build continues
          mvn clean package -Pct -P all-unit-tests \
            -DskipUnitTests=false \
            -Djacoco.skip=false \
            -Dmaven.test.failure.ignore=true
          
      # ---------------------------
      # START CONTAINERS (BACKGROUND)
      # ---------------------------
      - name: Start Dataverse stack
        run: |
          set -euo pipefail
          mvn -Pct docker:start \
            -Ddataverse.cors.origin=* \
            -Ddataverse.cors.methods=GET,POST,PUT,DELETE,OPTIONS \
            -Ddataverse.cors.headers.allow=range,content-type,x-dataverse-key,accept \
            -Ddataverse.cors.headers.expose=content-encoding,content-range,accept-ranges \
            -Ddataverse.feature.index-harvested-metadata-source=true \
            -Ddataverse.oai.server.maxidentifiers=2 \
            -Ddataverse.oai.server.maxrecords=2 \
          
      # ---------------------------
      # WAIT FOR API READINESS
      # ---------------------------
      - name: Wait for Dataverse API readiness
        run: |
          set -euo pipefail
          URL="http://localhost:8080/api/info/version"
          MAX_ATTEMPTS=10
          SLEEP_TIME=15
          echo "Waiting for Dataverse readiness..."
          for attempt in $(seq 1 $MAX_ATTEMPTS); do
            echo "Attempt $attempt..."
            RESPONSE=$(curl -s --max-time 15 "$URL" || true)
            STATUS=$(echo "$RESPONSE" | jq -r '.status' 2>/dev/null || echo "NOT_READY")
            if [ "$STATUS" = "OK" ]; then
              echo "Dataverse endpoint is READY."
              echo "Dataverse waiting for full readiness. Waiting 30 more seconds."
              sleep 30
              echo "Response: $RESPONSE"
              exit 0
            fi
            echo "Not ready. Sleeping ${SLEEP_TIME}s..."
            sleep $SLEEP_TIME
            if [ $SLEEP_TIME -lt 60 ]; then
              SLEEP_TIME=$((SLEEP_TIME * 2))
              if [ $SLEEP_TIME -gt 60 ]; then
                SLEEP_TIME=60
              fi
            fi
          done
          echo "Dataverse failed to become ready."
          docker ps
          CONTAINERS="$(docker ps -aq)"
          if [ -n "$CONTAINERS" ]; then
            for cid in $CONTAINERS; do
              echo "===== Logs for container $cid ====="
              docker logs "$cid" || true
            done
          else
            echo "No running containers to show logs for."
          fi
          exit 1
          
      # ---------------------------
      # MAP LOCALSTACK TO LOCALHOST
      # ---------------------------
      - name: Map localstack to localhost for Maven tests
        run: echo "127.0.0.1 localstack" | sudo tee -a /etc/hosts

      # ---------------------------
      # CONFIGURE DATAVERSE FOR TESTS
      # ---------------------------
      - name: Configure Dataverse API Settings
        run: |
          set -euo pipefail
          
          echo "Setting API Database Settings via internal container curl..."
          
          # We define the settings in an array
          declare -A settings=(
            [":BuiltinUsersKey"]="burrito"
            [":ProvCollectionEnabled"]="true"
            [":AllowApiTokenLookupViaApi"]="true"
            [":AllowSignUp"]="true"
          )
          # We run curl INSIDE the container so the source IP is 127.0.0.1
          for key in "${!settings[@]}"; do
            echo "Setting $key..."
            docker exec dev_dataverse curl -s -X PUT -d "${settings[$key]}" "http://localhost:8080/api/admin/settings/$key"
            echo ""
          done
        
      # ---------------------------
      # PRE-TEST INJECTIONS (FROM YOUR ALTERNATE WORKFLOWS)
      # ---------------------------
      - name: Put SUSHI config file in place
        run: |
          set -euo pipefail
          # Fixes MakeDataCountApiIT
          docker exec dev_dataverse sh -c 'curl https://raw.githubusercontent.com/IQSS/dataverse/develop/src/test/java/edu/harvard/iq/dataverse/makedatacount/sushi_sample_logs.json > /tmp/sushi_sample_logs.json && head /tmp/sushi_sample_logs.json'
      
      # ---------------------------
      # RUN MAVEN TESTS
      # ---------------------------
      - name: Run Maven Integration Tests
        env:
          DVAPIKEY: "burrito"
          DV_APIKEY: "burrito"
          DV_API_KEY: "burrito"
        run: |
          set -euo pipefail
          TEST_SUITE=$(cat tests/integration-tests.txt)
          
          echo "Running suite: $TEST_SUITE"
          
          # -Dmaven.test.failure.ignore=true forces the JVM to shut down cleanly
          # and write the jacoco.exec file, even when tests fail.
          mvn test \
            -Dtest="$TEST_SUITE" \
            -Dmaven.test.failure.ignore=true \
            -Ddataverse.test.baseurl=http://localhost:8080 \
            -DcompilerArgument=-Xlint:unchecked
        
      # ---------------------------
      # GENERATE REPORTS & DEPOSIT TO COVERALLS
      # ---------------------------
      - name: Deposit to Coveralls
        if: always()
        env:
          COVERALLS_REPO_TOKEN: ${{ secrets.COVERALLS_REPO_TOKEN }}
        continue-on-error: true 
        run: |
          set -euo pipefail
          
          # The pom.xml automatically merged the files and put them here:
          mvn coveralls:report \
            -P all-unit-tests \
            -DrepoToken=$COVERALLS_REPO_TOKEN \
            -DjacocoReports=target/site/jacoco-merged-test-coverage-report/jacoco.xml
        
      # ---------------------------
      # UPLOAD SUREFIRE/FAILSAFE REPORTS
      # ---------------------------
      - name: Upload Test Failure Reports
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: maven-test-reports
          path: |
            target/surefire-reports/
            target/failsafe-reports/
            target/site/jacoco/
          retention-days: 14

      # ---------------------------
      # 2. PUBLISH TEST DASHBOARD IN GITHUB PR (Optional but highly recommended)
      # ---------------------------
      - name: Publish Test Results Dashboard
        uses: EnricoMi/publish-unit-test-result-action@v2
        if: always()
        with:
          files: |
            target/failsafe-reports/TEST-*.xml
            target/surefire-reports/TEST-*.xml
      
      # ---------------------------
      # FAIL WORKFLOW IF TESTS FAILED
      # ---------------------------
      - name: Check for Test Failures
        if: always()
        run: |
          echo "Checking Surefire/Failsafe reports for failures..."
          if grep -q "<failure" target/surefire-reports/*.xml target/failsafe-reports/*.xml 2>/dev/null; then
            echo "Tests failed! Failing the workflow."
            exit 1
          fi
          echo "All tests passed."

      # ---------------------------
      # COLLECT DOCKER LOGS (ALWAYS, WITH MAPPING)
      # ---------------------------
      - name: Collect Docker logs (mapped)
        if: always()
        run: |
          mkdir -p docker-logs
          echo "Gathering container metadata..."
          docker ps -a --format '{{.Names}}|{{.Image}}|{{.Status}}' > docker-logs/container-summary.txt
          while IFS='|' read -r name image status; do
            # Create a readable label
            label="$name"
            case "$name" in
              *dataverse*)
                label="dataverse-app"
                ;;
              *postgres*)
                label="postgres-db"
                ;;
              *solr*)
                label="solr-index"
                ;;
              *localstack*)
                label="localstack-s3"
                ;;
            esac
            echo "Collecting logs for $name ($label)"
            {
              echo "===== CONTAINER: $name ====="
              echo "Label: $label"
              echo "Image: $image"
              echo "Status: $status"
              echo ""
              echo "===== LOGS ====="
              docker logs --timestamps "$name" 2>&1 || true
            } > "docker-logs/${label}__${name}.log"
          done < docker-logs/container-summary.txt
          
      # ---------------------------
      # UPLOAD DOCKER LOGS (ALWAYS)
      # ---------------------------
      - name: Upload Docker logs
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: docker-logs
          path: docker-logs/
          retention-days: 7

      # ---------------------------
      # SHUTDOWN STACK
      # ---------------------------
      - name: Stop Dataverse stack
        if: always()
        run: |
          set -euo pipefail
          mvn -Pct docker:stop || true
          
      - name: Final Docker cleanup
        if: always()
        run: |
          docker system prune -af || true