beta-release.yml

name: Beta Release (Thursday)

on:
  schedule:
    - cron: '0 2 * * 4' # Thursday at 2 AM UTC
  workflow_dispatch:
    inputs:
      dry_run:
        description: 'Dry run (skip PyPI publish)'
        required: false
        default: 'false'
        type: boolean
      force_build:
        description: 'Force build even if no changes'
        required: false
        default: 'false'
        type: boolean

jobs:
  check-changes:
    runs-on: ubuntu-latest
    outputs:
      has_changes: ${{ steps.changes.outputs.has_changes }}
      commit_count: ${{ steps.changes.outputs.commit_count }}
      last_beta: ${{ steps.changes.outputs.last_beta }}
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: dev

      - name: Check for changes since last beta release
        id: changes
        run: |
          LAST_BETA=$(git tag -l "*b*" --sort=-version:refname | head -n1)

          if [ -z "$LAST_BETA" ]; then
            echo "No previous beta release found"
            COMMIT_COUNT=$(git rev-list --count --since="1 week ago" dev)
          else
            echo "Last beta release: $LAST_BETA"
            COMMIT_COUNT=$(git rev-list --count ${LAST_BETA}..dev)
          fi

          echo "commit_count=$COMMIT_COUNT" >> $GITHUB_OUTPUT
          echo "last_beta=$LAST_BETA" >> $GITHUB_OUTPUT

          if [ "$COMMIT_COUNT" -gt 0 ] || [ "${{ github.event.inputs.force_build }}" = "true" ]; then
            echo "has_changes=true" >> $GITHUB_OUTPUT
          else
            echo "has_changes=false" >> $GITHUB_OUTPUT
          fi

  beta-release:
    needs: check-changes
    if: needs.check-changes.outputs.has_changes == 'true'
    runs-on: ubuntu-latest
    outputs:
      beta_version: ${{ steps.version.outputs.beta_version }}
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: dev
          token: ${{ secrets.GITHUB_TOKEN }}

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install bump2version build twine psutil
          pip install -e ".[all,dev]"
          # Install memory monitoring tools
          pip install memory_profiler

      - name: Configure git
        run: |
          git config --local user.email "action@github.com"
          git config --local user.name "GitHub Action"

      - name: Generate beta version
        id: version
        run: |
          set -e
          CURRENT_VERSION=$(python -c "from datafog.__about__ import __version__; print(__version__)")
          echo "Current version: $CURRENT_VERSION"

          if [[ $CURRENT_VERSION == *"b"* ]]; then
            BASE_VERSION=$(echo $CURRENT_VERSION | cut -d'b' -f1)
            BETA_NUM=$(echo $CURRENT_VERSION | cut -d'b' -f2)
            BETA_VERSION="${BASE_VERSION}b$((BETA_NUM + 1))"
          elif [[ $CURRENT_VERSION == *"a"* ]]; then
            BASE_VERSION=$(echo $CURRENT_VERSION | cut -d'a' -f1)
            BETA_VERSION="${BASE_VERSION}b1"
          else
            BASE_VERSION=$(python3 -c "import sys; version='$CURRENT_VERSION'; parts=version.split('.'); parts[1]=str(int(parts[1])+1); parts[2]='0'; print('.'.join(parts))")
            BETA_VERSION="${BASE_VERSION}b1"
          fi

          echo "beta_version=$BETA_VERSION" >> $GITHUB_OUTPUT
          sed -i "s/__version__ = \".*\"/__version__ = \"$BETA_VERSION\"/" datafog/__about__.py
          sed -i "s/version=\".*\"/version=\"$BETA_VERSION\"/" setup.py

      - name: Generate changelog
        run: |
          python scripts/generate_changelog.py --beta --output BETA_CHANGELOG.md

      - name: Run tests
        env:
          # Control memory usage to prevent segmentation faults
          PYTHONMALLOC: debug
          # Limit the number of threads used by numpy/OpenMP
          OMP_NUM_THREADS: 1
          MKL_NUM_THREADS: 1
          OPENBLAS_NUM_THREADS: 1
          # Limit spaCy's memory usage
          SPACY_MAX_THREADS: 1
        run: |
          # Print system memory info
          free -h || echo "free command not available"
          
          # Split tests into smaller batches to avoid memory issues
          python -m pytest tests/ -v --tb=short -k "not benchmark and not integration" --no-header
          
          # Run integration tests separately
          python -m pytest -m integration -v --no-header
          
          # Run benchmark tests with reduced sample size
          python -c "print('Running memory-intensive benchmark tests with safeguards')"
          python -m pytest tests/benchmark_text_service.py -v --no-header

      - name: Build package
        run: |
          python -m build
          python scripts/check_wheel_size.py

      - name: Create GitHub release
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          BETA_VERSION="${{ steps.version.outputs.beta_version }}"
          git add datafog/__about__.py setup.py
          git commit -m "chore: bump version to $BETA_VERSION for beta release"
          git tag -a "v$BETA_VERSION" -m "Beta release $BETA_VERSION"
          git push origin "v$BETA_VERSION"

          gh release create "v$BETA_VERSION" \
            --title "🚧 Beta Release $BETA_VERSION" \
            --notes-file BETA_CHANGELOG.md \
            --prerelease \
            --target dev \
            dist/*

      - name: Publish to PyPI
        if: github.event.inputs.dry_run != 'true'
        env:
          TWINE_USERNAME: __token__
          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
        run: |
          python -m twine upload dist/* --verbose

      - name: Dry run summary
        if: github.event.inputs.dry_run == 'true'
        run: |
          echo "🏃 DRY RUN COMPLETE"
          echo "Would have published: ${{ steps.version.outputs.beta_version }}"
          ls -la dist/

      - name: Cleanup old betas
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          BETA_RELEASES=$(gh release list --limit 30 | grep b | tail -n +6 | cut -f3)

          for release in $BETA_RELEASES; do
            echo "Deleting $release"
            gh release delete "$release" --yes || true
            git push --delete origin "$release" || true
          done

  notify-beta:
    needs: [check-changes, beta-release]
    if: needs.check-changes.outputs.has_changes == 'true' && success()
    runs-on: ubuntu-latest
    steps:
      - name: Beta release notification
        run: |
          echo "🚧 Beta release completed!"
          echo "Install: pip install datafog==${{ needs.beta-release.outputs.beta_version }}"
          echo "Commits since last beta: ${{ needs.check-changes.outputs.commit_count }}"