build.yml

name: build

# Controls when the workflow will run
on:
  # Triggers the workflow on push or pull request events but only for the "main" branch
  push:
    branches: [ "main", "branch-*" ]
    paths-ignore:
      - '**/*.md'
      - '**/*.mdx'
      - 'docs/assets/**'
      - 'web-v2/**'
  pull_request:
    branches: [ "main", "branch-*" ]
    paths-ignore:
      - '**/*.md'
      - '**/*.mdx'
      - 'docs/assets/**'
      - 'web-v2/**'

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

# A workflow run is made up of one or more jobs that can run sequentially or in parallel
jobs:
  changes:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36
        id: filter
        with:
          list-files: shell
          filters: |
            source_changes:
              - '.github/**'
              - 'catalogs/**'
              - 'catalogs-contrib/**'
              - 'clients/**'
              - 'conf/**'
              - 'dev/**'
              - 'docs/open-api/**'
              - 'gradle/**'
              - 'gradle.properties'
              - 'meta/**'
              - 'scripts/**'
              - 'web/**'
              - '**/*.java'
              - '**/*.kts'
              - '**/*.py'
              - '**/*.rs'
              - '**/resources/**'
              - '**/src/**'
              - '!**/*.md'
              - '!**/*.mdx'
              - '!docs/**/*.png'
              - '!docs/**/*.svg'
              - '!docs/**/*.jpg'
              - '!docs/**/*.jpeg'
              - '!docs/**/*.gif'
              - '!docs/**/*.webp'
              - 'mcp-server/**'
            spark_connector_changes:
              - spark-connector/**
            mcp_server_changes:
              - mcp-server/**
      - name: Determine maintenance-module-only changes
        id: maintenance_module_only
        env:
          SOURCE_CHANGE_FILES: ${{ steps.filter.outputs.source_changes_files }}
        run: |
          # Route to the maintenance-only build path only when every source
          # change in the PR is under maintenance/. Non-source changes are
          # already filtered out by source_changes_files.
          source_files=()
          if [ -n "${SOURCE_CHANGE_FILES}" ]; then
            eval "source_files=(${SOURCE_CHANGE_FILES})"
          fi

          maintenance_module_only=false
          if [ "${#source_files[@]}" -gt 0 ]; then
            maintenance_module_only=true
            for path in "${source_files[@]}"; do
              case "$path" in
                maintenance/*) ;;
                *)
                  maintenance_module_only=false
                  break
                  ;;
              esac
            done
          fi

          echo "maintenance_module_only_changes=${maintenance_module_only}" >> "${GITHUB_OUTPUT}"
    outputs:
      source_changes: ${{ steps.filter.outputs.source_changes }}
      spark_connector_changes: ${{ steps.filter.outputs.spark_connector_changes }}
      mcp_server_changes: ${{ steps.filter.outputs.mcp_server_changes }}
      maintenance_module_only_changes: ${{ steps.maintenance_module_only.outputs.maintenance_module_only_changes }}

  compile-check:
    runs-on: ubuntu-latest
    needs: changes
    if: needs.changes.outputs.source_changes != 'true'
    steps:
      - uses: actions/checkout@v4

      - uses: ./.github/actions/setup-java-toolchains
        with:
          java-version: 17

      - name: Build with Gradle
        run: |
          ./gradlew assemble -PskipWeb=true

  # To check the spark-connector is compatible with scala2.13
  spark-connector-build:
    runs-on: ubuntu-latest
    timeout-minutes: 30
    needs: changes
    if: needs.changes.outputs.spark_connector_changes == 'true'
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-java@v4
        with:
          java-version: 17
          distribution: 'temurin'
          cache: 'gradle'

      - name: Free up disk space
        run: |
          dev/ci/util_free_space.sh

      - name: Build with Scala2.13
        run: |
          ./gradlew :spark-connector:spark-3.3:build -PscalaVersion=2.13 -PskipITs -PskipDockerTests=false -PskipWeb=true
          ./gradlew :spark-connector:spark-3.4:build -PscalaVersion=2.13 -PskipITs -PskipDockerTests=false -PskipWeb=true
          ./gradlew :spark-connector:spark-3.5:build -PscalaVersion=2.13 -PskipITs -PskipDockerTests=false -PskipWeb=true

      - name: Upload unit tests report
        uses: actions/upload-artifact@v7
        if: failure()
        with:
          name: unit test report
          path: |
            build/reports
            spark-connector/**/*.log

  build:
    # The type of runner that the job will run on
    runs-on: ubuntu-latest
    strategy:
      matrix:
        java-version: [ 17 ]
    timeout-minutes: 90
    needs: changes
    if: needs.changes.outputs.source_changes == 'true'
    # Steps represent a sequence of tasks that will be executed as part of the job
    steps:
      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
      - uses: actions/checkout@v4

      - uses: ./.github/actions/setup-java-toolchains
        with:
          java-version: ${{ matrix.java-version }}

      - name: Test publish to local
        run: ./gradlew publishToMavenLocal -PskipWeb=true -x test

      - name: Free up disk space
        run: |
          dev/ci/util_free_space.sh

      - name: Install dependencies
        run: |
          wget https://nz2.archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb
          sudo dpkg -i libssl1.1_1.1.1f-1ubuntu2_amd64.deb  

      - name: Build with Gradle
        run: |
          if [ "${{ needs.changes.outputs.maintenance_module_only_changes }}" = "true" ]; then
            ./gradlew \
              :maintenance:optimizer-api:build \
              :maintenance:updaters:build \
              :maintenance:optimizer:build \
              :maintenance:jobs:build \
              -PskipWeb=true \
              -PskipITs \
              -PskipDockerTests=false
            exit 0
          fi

          gradle_args=(
            build
            -PskipWeb=true
            -PskipITs
            -PskipDockerTests=false
            -x :clients:client-python:build
          )

          if [ "${{ needs.changes.outputs.mcp_server_changes }}" != "true" ]; then
            gradle_args+=(
              -x :mcp-server:build
              -x :mcp-server:test
              -x :mcp-server:pylint
              -x :web-v2:web:build
            )
          fi

          printf './gradlew'
          printf ' %q' "${gradle_args[@]}"
          printf '\n'

          ./gradlew "${gradle_args[@]}"

      - name: Fetch base branch for coverage diff
        if: github.event_name == 'pull_request'
        run: git fetch origin ${{ github.base_ref }} --depth=1

      - name: Generate Coverage Report
        id: coverage
        if: github.event_name == 'pull_request'
        run: |
          python3 dev/ci/jacoco_report.py \
            --base-ref "${{ github.base_ref }}" \
            --head-sha "${{ github.event.pull_request.head.sha }}" \
            --repo-url "${{ github.event.pull_request.head.repo.html_url }}" \
            --min-overall 40 \
            --min-changed 60 \
            --output coverage-report.md

      - name: Save PR number
        if: github.event_name == 'pull_request' && steps.coverage.outputs.has_reports == 'true'
        run: echo "${{ github.event.pull_request.number }}" > pr-number.txt

      - name: Upload Coverage Report
        if: github.event_name == 'pull_request' && steps.coverage.outputs.has_reports == 'true'
        uses: actions/upload-artifact@v7
        with:
          name: coverage-report
          path: |
            coverage-report.md
            pr-number.txt

      - name: Output Coverage Info
        if: github.event_name == 'pull_request' && steps.coverage.outputs.has_reports == 'true'
        run: |
          echo "Total coverage ${{ steps.coverage.outputs.coverage-overall }}"
          echo "Changed Files coverage ${{ steps.coverage.outputs.coverage-changed-files }}"

      - name: Upload unit tests report
        uses: actions/upload-artifact@v7
        if: failure()
        with:
          name: unit test report
          path: |
            build/reports
            catalogs-contrib/**/*.log
            catalogs-contrib/**/*.tar
            catalogs/**/*.log
            catalogs/**/*.tar