publish.yml

name: Publish Spark packages
on:
  release:
    types: [published]
  pull_request:
    paths:
      - .github/workflows/publish.yml
    types:
      - opened
      - synchronize
      - ready_for_review
      - reopened
  workflow_dispatch:
    inputs:
      mode:
        description: 'Release mode'
        required: true
        type: choice
        default: dry_run
        options:
          - dry_run
          - release
      ref:
        description: 'The branch, tag or SHA to checkout'
        required: false
        type: string

jobs:
  release:
    name: Release Spark
    runs-on: ubuntu-24.04
    timeout-minutes: 60
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          # When triggered by a release, use the release tag
          # When triggered manually, use the provided ref
          ref: ${{ github.event.release.tag_name || inputs.ref }}
      - name: Set up Java 17
        uses: actions/setup-java@v4
        with:
          distribution: corretto
          java-version: 17
          cache: "maven"
          server-id: ossrh
          server-username: SONATYPE_USER
          server-password: SONATYPE_TOKEN
          gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }}
          gpg-passphrase: ${{ secrets.GPG_PASSPHRASE }}
      - name: Set github
        run: |
          git config --global user.email "Lance Github Runner"
          git config --global user.name "dev+gha@lancedb.com"
      - name: Dry run
        if: |
          github.event_name == 'pull_request' ||
          inputs.mode == 'dry_run'
        run: |
          mvn --batch-mode -DskipTests package
      - name: Publish to Maven Central
        if: |
          github.event_name == 'release' ||
          inputs.mode == 'release'
        run: |
          echo "use-agent" >> ~/.gnupg/gpg.conf
          echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
          export GPG_TTY=$(tty)
          mvn --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
        env:
          SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
          SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
      
      - name: Get published version
        if: |
          github.event_name == 'release' ||
          inputs.mode == 'release'
        id: get_version
        run: |
          VERSION=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
          echo "version=$VERSION" >> $GITHUB_OUTPUT
          echo "Published version: $VERSION"
      
      - name: Wait for Maven Central availability
        if: |
          github.event_name == 'release' ||
          inputs.mode == 'release'
        run: |
          VERSION="${{ steps.get_version.outputs.version }}"
          GROUP_ID="org.lance"
          
          # List of artifacts to check (a representative subset)
          ARTIFACTS=(
            "lance-spark-base_2.12"
            "lance-spark-3.5_2.12"
            "lance-spark-bundle-3.5_2.12"
          )
          
          echo "Waiting for version $VERSION to be available in Maven Central..."
          echo "This typically takes 10-30 minutes after publishing to OSSRH."
          
          # Maximum wait time: 60 minutes
          MAX_WAIT=3600
          INTERVAL=60
          ELAPSED=0
          
          while [ $ELAPSED -lt $MAX_WAIT ]; do
            ALL_AVAILABLE=true
            
            for ARTIFACT_ID in "${ARTIFACTS[@]}"; do
              URL="https://repo1.maven.org/maven2/org/lance/${ARTIFACT_ID}/${VERSION}/${ARTIFACT_ID}-${VERSION}.pom"
              
              if curl --head --silent --fail "$URL" > /dev/null 2>&1; then
                echo "✓ ${ARTIFACT_ID} is available"
              else
                echo "✗ ${ARTIFACT_ID} is not yet available"
                ALL_AVAILABLE=false
              fi
            done
            
            if [ "$ALL_AVAILABLE" = true ]; then
              echo ""
              echo "🎉 All artifacts are now available in Maven Central!"
              echo ""
              echo "Users can now add the following dependency to their projects:"
              echo ""
              echo "Maven:"
              echo "<dependency>"
              echo "  <groupId>org.lance</groupId>"
              echo "  <artifactId>lance-spark-bundle-3.5_2.12</artifactId>"
              echo "  <version>${VERSION}</version>"
              echo "</dependency>"
              echo ""
              echo "Gradle:"
              echo "implementation 'org.lance:lance-spark-bundle-3.5_2.12:${VERSION}'"
              echo ""
              echo "SBT:"
              echo "libraryDependencies += \"org.lance\" % \"lance-spark-bundle-3.5_2.12\" % \"${VERSION}\""
              exit 0
            fi
            
            ELAPSED=$((ELAPSED + INTERVAL))
            
            if [ $ELAPSED -lt $MAX_WAIT ]; then
              echo ""
              echo "Artifacts not yet available. Waiting ${INTERVAL} seconds... (${ELAPSED}s elapsed)"
              sleep $INTERVAL
            fi
          done
          
          echo ""
          echo "⚠️ WARNING: Artifacts are not yet available in Maven Central after ${MAX_WAIT} seconds."
          echo "This is normal - Maven Central sync can take up to 2 hours."
          echo "The artifacts will appear at: https://central.sonatype.com/artifact/org.lance/lance-spark-bundle-3.5_2.12/${VERSION}"
          echo ""
          echo "You can check the sync status at: https://s01.oss.sonatype.org/"
          exit 0