test-python-examples.yml

name: Test Python Examples

on:
  # Run on push to bindings/python/ directory
  push:
    paths:
      - 'bindings/python/**'
      - '.github/workflows/test-python-examples.yml'

  # Run on pull request affecting bindings/python/
  pull_request:
    paths:
      - 'bindings/python/**'
      - '.github/workflows/test-python-examples.yml'

  # Run after release workflow completes
  workflow_run:
    workflows: ["Release"]
    types: [completed]

  # Allow being called by other workflows (e.g., release workflow)
  workflow_call:
    inputs:
      examples:
        description: "Glob pattern(s) for examples to run (space-separated, relative to bindings/python/examples)."
        required: false
        type: string
        default: "01_*.py"

  # Allow manual trigger
  workflow_dispatch:
    inputs:
      examples:
        description: "Glob pattern(s) for examples to run (space-separated, relative to bindings/python/examples)."
        required: false
        default: "01_*.py"

env:
  EXAMPLES: ${{ inputs.examples || '01_*.py' }}

permissions:
  contents: read

jobs:
  # First job: Download ArcadeDB JARs (platform-agnostic)
  download-jars:
    name: Download ArcadeDB JARs
    runs-on: ubuntu-24.04
    steps:
      - name: Checkout code
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12.0

      - name: Download JARs from ArcadeDB Docker image
        shell: bash
        run: |
          cd bindings/python

          # Detect ArcadeDB version from pom.xml (Docker format: X.Y.Z-SNAPSHOT)
          ARCADEDB_TAG=$(python3 extract_version.py --format=docker)
          echo "📌 ArcadeDB version: $ARCADEDB_TAG"

          # Download JARs from official Docker image
          echo "📦 Downloading JARs from arcadedata/arcadedb:$ARCADEDB_TAG..."

          # Create output directory
          mkdir -p src/arcadedb_embedded/jars

          # Create a temporary container and copy JARs from it
          CONTAINER_ID=$(docker create arcadedata/arcadedb:$ARCADEDB_TAG)
          docker cp $CONTAINER_ID:/home/arcadedb/lib/. src/arcadedb_embedded/jars/
          docker rm $CONTAINER_ID

          echo "✅ Downloaded $(ls -1 src/arcadedb_embedded/jars/*.jar | wc -l) JARs"

      - name: Remove excluded JARs
        shell: bash
        run: |
          cd bindings/python

          JARS_DIR="src/arcadedb_embedded/jars"
          EXCLUSIONS_FILE="jar_exclusions.txt"

          if [[ -f "$EXCLUSIONS_FILE" ]]; then
            echo "🗑️  Removing excluded JARs from jar_exclusions.txt..."
            EXCLUSION_COUNT=0

            while IFS= read -r pattern || [[ -n "$pattern" ]]; do
              # Skip empty lines and comments
              if [[ -n "$pattern" ]] && [[ ! "$pattern" =~ ^# ]]; then
                echo "   Processing pattern: $pattern"

                # Remove matching JARs
                for jar in "$JARS_DIR"/$pattern; do
                  if [[ -f "$jar" ]]; then
                    rm -f "$jar"
                    echo "   - Removed: $(basename "$jar")"
                    EXCLUSION_COUNT=$((EXCLUSION_COUNT + 1))
                  fi
                done
              fi
            done < "$EXCLUSIONS_FILE"

            JAR_COUNT_AFTER=$(ls -1 "$JARS_DIR"/*.jar 2>/dev/null | wc -l)
            echo "✅ Removed $EXCLUSION_COUNT JAR(s), $JAR_COUNT_AFTER remaining"
          else
            echo "⚠️  No jar_exclusions.txt found, skipping exclusions"
          fi

      - name: Upload filtered JARs as artifact
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: arcadedb-jars-examples
          path: bindings/python/src/arcadedb_embedded/jars/*.jar
          retention-days: 1

  # Second job: Test examples on each platform
  test-examples:
    name: Test Python Examples (${{ matrix.platform }}, Python ${{ matrix.python-version }})
    runs-on: ${{ matrix.runs-on }}
    needs: download-jars
    strategy:
      fail-fast: false
      matrix:
        python-version: ['3.10', '3.11', '3.12', '3.13', '3.14']
        # Temporarily limit to three platforms (skip macOS x86_64, all Windows)
        # platform: ['linux/amd64', 'linux/arm64', 'darwin/amd64', 'darwin/arm64', 'windows/amd64', 'windows/arm64']
        platform: ['linux/amd64', 'linux/arm64', 'darwin/arm64']
        include:
          - platform: linux/amd64
            runs-on: ubuntu-24.04
          - platform: linux/arm64
            runs-on: ubuntu-24.04-arm
          - platform: darwin/arm64
            runs-on: macos-15
          # - platform: darwin/amd64
          #   runs-on: macos-15-intel
          # - platform: windows/amd64
          #   runs-on: windows-2025
          # - platform: windows/arm64
          #   runs-on: windows-11-arm
          # macOS x86_64 and all Windows temporarily disabled

    steps:
      - name: Checkout code
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1

      - name: Download JARs artifact
        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
        with:
          name: arcadedb-jars-examples
          path: bindings/python/src/arcadedb_embedded/jars

      - name: Set up Java (for native builds on macOS/Windows)
        if: matrix.platform != 'linux/amd64' && matrix.platform != 'linux/arm64'
        uses: actions/setup-java@f2beeb24e141e01a676f977032f5a29d81c9e27e # v5.1.0
        with:
          distribution: 'temurin'
          java-version: '25'

      - name: Set up Docker Buildx (Linux only)
        if: matrix.platform == 'linux/amd64' || matrix.platform == 'linux/arm64'
        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12.0

      - name: Set up Python
        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
        with:
          python-version: ${{ matrix.python-version }}

      - name: Setup UV package manager
        shell: bash
        run: |
          curl -LsSf https://astral.sh/uv/install.sh | sh
          uv --version

      - name: Install Python build dependencies
        shell: bash
        run: |
          uv pip install --system build wheel setuptools

      # Windows currently disabled, no symlink needed
      # - name: Create python3 symlink (Windows only)
      #   if: matrix.platform == 'windows/amd64' || matrix.platform == 'windows/arm64'
      #   shell: bash
      #   run: |
      #     PYTHON_DIR=$(dirname "$(which python)")
      #     ln -s "$PYTHON_DIR/python.exe" "$PYTHON_DIR/python3.exe" || true
      #     python3 --version

      - name: Build arcadedb-embedded (${{ matrix.platform }})
        shell: bash
        run: |
          cd bindings/python
          echo "🔨 Building arcadedb-embedded for ${{ matrix.platform }} with Python ${{ matrix.python-version }}..."
          ./build.sh ${{ matrix.platform }} ${{ matrix.python-version }}

      # Note: Java is NOT required - arcadedb-embedded has bundled JRE!

      - name: Install ArcadeDB Python bindings
        shell: bash
        run: |
          cd bindings/python
          uv pip install --system dist/*embed*.whl

      - name: Install example dependencies
        shell: bash
        run: |
          # Install dependencies needed by examples
          # PyTorch is required by sentence-transformers, even on macOS
          # For Python 3.13+, wheels might only be on PyTorch official index
          if [[ "$OSTYPE" == "darwin"* ]]; then
            # macOS: Install CPU-only PyTorch (supports MPS acceleration)
            uv pip install --system torch --index-url https://download.pytorch.org/whl/cpu
            uv pip install --system "numpy<2.0" requests sentence-transformers
          else
            # Linux & Windows: Install CPU-only PyTorch to save space (avoid CUDA)
            uv pip install --system torch --index-url https://download.pytorch.org/whl/cpu
            uv pip install --system numpy requests sentence-transformers
          fi

      - name: Download datasets
        shell: bash
        run: |
          uv pip install --system tqdm py7zr lxml
          cd bindings/python/examples
          echo "📥 Downloading MovieLens Small dataset..."
          python3 download_data.py movielens-small
          echo "📥 Downloading Stack Overflow Small dataset..."
          python3 download_data.py stackoverflow-small

      - name: Install timeout command (macOS only)
        if: matrix.platform == 'darwin/amd64' || matrix.platform == 'darwin/arm64'
        shell: bash
        run: |
          # macOS doesn't have timeout command by default, use coreutils
          brew install coreutils

      # Windows currently disabled, no env override needed
      # - name: Set UTF-8 encoding (Windows only)
      #   if: matrix.platform == 'windows/amd64' || matrix.platform == 'windows/arm64'
      #   shell: bash
      #   run: |
      #     echo "PYTHONIOENCODING=utf-8" >> $GITHUB_ENV

      - name: Run all examples
        id: run_examples
        shell: bash
        env:
          # Increase JVM heap for large CSV imports (example 04)
          ARCADEDB_JVM_ARGS: "-Xmx8g -Xms8g"
        run: |
          cd bindings/python/examples

          echo "🚀 Running Python Examples..."
          echo ""

          # Initialize counters
          total=0
          passed=0
          failed=0
          skipped=0

          # Create results file
          results_file="example-results.txt"
          > $results_file

          # Select example files by pattern(s) in EXAMPLES (space-separated globs)
          examples=$(ls $EXAMPLES 2>/dev/null | sort)

          if [ -z "$examples" ]; then
            echo "❌ No example files found!"
            exit 1
          fi

          # Detect timeout command (macOS uses gtimeout, Linux uses timeout)
          if command -v gtimeout &> /dev/null; then
            TIMEOUT_CMD="gtimeout"
          else
            TIMEOUT_CMD="timeout"
          fi

          # Run each example
          for example in $examples; do
            total=$((total + 1))

            # Set example-specific parameters and timeout
            case "$example" in
              "04_csv_import_documents.py")
                example_args="--dataset movielens-small --export"
                example_name="$example (movielens-small dataset with export)"
                timeout_duration=900  # 15 minutes
                ;;
              "05_csv_import_graph.py")
                example_args="--dataset movielens-small --method java --import-jsonl ./exports/movielens_small_db.jsonl.tgz --export"
                example_name="$example (movielens-small dataset, embedded java method, import/export)"
                timeout_duration=900  # 15 minutes
                ;;
              "06_vector_search_recommendations.py")
                example_args="--import-jsonl ./exports/movielens_graph_small_db.jsonl.tgz"
                example_name="$example (vector search, import from JSONL)"
                timeout_duration=900  # 15 minutes
                ;;
              "07_stackoverflow_multimodel.py")
                example_args="--dataset stackoverflow-small"
                example_name="$example (stackoverflow-small dataset)"
                timeout_duration=1800  # 30 minutes
                ;;
              *)
                example_args=""
                example_name="$example"
                timeout_duration=900  # 15 minutes default
                ;;
            esac

            log_file="${example%.py}.log"

            echo "----------------------------------------"
            echo "📝 Running: $example_name"
            echo "----------------------------------------"

            # Run the example with appropriate parameters
            if $TIMEOUT_CMD $timeout_duration python "$example" $example_args > "$log_file" 2>&1; then
              echo "✅ PASSED: $example_name" | tee -a $results_file
              passed=$((passed + 1))
            else
              exit_code=$?
              if [ $exit_code -eq 124 ]; then
                echo "⏱️  TIMEOUT: $example_name (exceeded $((timeout_duration/60)) minutes)" | tee -a $results_file
                failed=$((failed + 1))
              else
                echo "❌ FAILED: $example_name (exit code: $exit_code)" | tee -a $results_file
                failed=$((failed + 1))
              fi
              # Show last 20 lines of error log
              echo "Last 20 lines of output:"
              tail -n 20 "$log_file"
            fi
            echo ""
          done

          # Print summary
          echo "========================================"
          echo "📊 EXAMPLE TEST SUMMARY"
          echo "========================================"
          echo "Total:   $total"
          echo "Passed:  $passed ✅"
          echo "Failed:  $failed ❌"
          echo "Skipped: $skipped ⏭️"
          echo "========================================"
          echo ""

          echo "Examples pattern(s): $EXAMPLES"

          # Output to GitHub Actions
          echo "total=$total" >> $GITHUB_OUTPUT
          echo "passed=$passed" >> $GITHUB_OUTPUT
          echo "failed=$failed" >> $GITHUB_OUTPUT
          echo "skipped=$skipped" >> $GITHUB_OUTPUT

          # Show detailed results
          echo "Detailed Results:"
          cat $results_file

          # Exit with error if any failed
          if [ $failed -gt 0 ]; then
            echo "❌ Some examples failed!"
            exit 1
          else
            echo "✅ All examples passed!"
          fi

          # Save list of examples for summary
          echo "$examples" > examples-ran.txt

      - name: Generate test summary
        if: always()
        shell: bash
        run: |
          cd bindings/python/examples

          echo "## 🎮 Python Examples Test Results (${{ matrix.platform }})" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY

          total="${{ steps.run_examples.outputs.total || '0' }}"
          passed="${{ steps.run_examples.outputs.passed || '0' }}"
          failed="${{ steps.run_examples.outputs.failed || '0' }}"

          if [ "${{ steps.run_examples.outcome }}" = "success" ]; then
            echo "✅ **Status**: ALL EXAMPLES PASSED ($passed/$total)" >> $GITHUB_STEP_SUMMARY
          else
            echo "❌ **Status**: SOME EXAMPLES FAILED ($passed/$total passed)" >> $GITHUB_STEP_SUMMARY
          fi

          echo "" >> $GITHUB_STEP_SUMMARY
          echo "### Summary" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "| Metric | Count |" >> $GITHUB_STEP_SUMMARY
          echo "|--------|------:|" >> $GITHUB_STEP_SUMMARY
          echo "| 📝 Total | $total |" >> $GITHUB_STEP_SUMMARY
          echo "| ✅ Passed | $passed |" >> $GITHUB_STEP_SUMMARY
          echo "| ❌ Failed | $failed |" >> $GITHUB_STEP_SUMMARY
          echo "| ⏭️ Skipped | ${{ steps.run_examples.outputs.skipped || '0' }} |" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY

          # Add detailed results if available
          if [ -f example-results.txt ]; then
            echo "### Detailed Results" >> $GITHUB_STEP_SUMMARY
            echo "" >> $GITHUB_STEP_SUMMARY
            echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
            cat example-results.txt >> $GITHUB_STEP_SUMMARY
            echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
          fi

          echo "" >> $GITHUB_STEP_SUMMARY
          echo "### Examples Tested" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          echo "**Pattern(s)**: $EXAMPLES" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY
          if [ -f examples-ran.txt ]; then
            while IFS= read -r example; do
              [ -n "$example" ] && echo "- **$example**" >> $GITHUB_STEP_SUMMARY
            done < examples-ran.txt
          fi
          echo "" >> $GITHUB_STEP_SUMMARY

      - name: Upload example logs
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: example-logs-${{ matrix.platform == 'linux/amd64' && 'linux-amd64' || matrix.platform == 'linux/arm64' && 'linux-arm64' || matrix.platform == 'darwin/amd64' && 'darwin-amd64' || matrix.platform == 'darwin/arm64' && 'darwin-arm64' || matrix.platform == 'windows/amd64' && 'windows-amd64' || 'windows-arm64' }}-py${{ matrix.python-version }}
          path: |
            bindings/python/examples/*.log
            bindings/python/examples/example-results.txt
          retention-days: 7

      - name: Upload example databases
        if: failure()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
        with:
          name: example-databases-${{ matrix.platform == 'linux/amd64' && 'linux-amd64' || matrix.platform == 'linux/arm64' && 'linux-arm64' || matrix.platform == 'darwin/amd64' && 'darwin-amd64' || matrix.platform == 'darwin/arm64' && 'darwin-arm64' || matrix.platform == 'windows/amd64' && 'windows-amd64' || 'windows-arm64' }}-py${{ matrix.python-version }}
          path: bindings/python/examples/my_test_databases/
          retention-days: 3

  # Summary job that checks all platforms
  test-examples-summary:
    name: Examples Test Summary
    needs: test-examples
    runs-on: ubuntu-latest
    if: always()
    steps:
      - name: Check test results
        shell: bash
        run: |
          echo "## 🎯 Overall Examples Test Summary" >> $GITHUB_STEP_SUMMARY
          echo "" >> $GITHUB_STEP_SUMMARY

          if [ "${{ needs.test-examples.result }}" = "success" ]; then
            echo "✅ **All platforms passed example testing!**" >> $GITHUB_STEP_SUMMARY
            echo "" >> $GITHUB_STEP_SUMMARY
            echo "All examples ran successfully across all enabled platforms." >> $GITHUB_STEP_SUMMARY
            echo "" >> $GITHUB_STEP_SUMMARY
            echo "**Platforms tested**: linux/amd64, linux/arm64, darwin/arm64" >> $GITHUB_STEP_SUMMARY
          else
            echo "❌ **Some platforms failed example testing**" >> $GITHUB_STEP_SUMMARY
            echo "" >> $GITHUB_STEP_SUMMARY
            echo "Please check the individual platform jobs for details." >> $GITHUB_STEP_SUMMARY
            exit 1
          fi