execute_notebooks.yml

# .github/workflows/execute-notebooks.yml
name: Execute Notebooks

on:
  push:
    branches: [ main ]
    paths:
      - 'docs/Data Formatting/*ipynb'
      - 'docs/*ipynb'
      - '.github/workflows/execute_notebooks.yml'
  pull_request:
    branches: [ main ]
    paths:
      - 'docs/Data Formatting/*ipynb'
      - 'docs/*ipynb'
      - '.github/workflows/execute_notebooks.yml'
  workflow_dispatch:  # Allow manual trigger

# Cancel in-progress runs when a new push is made to the same branch/PR
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  execute-notebooks:
    runs-on: ubuntu-latest
    
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          fetch-depth: 0

      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.12'
          cache: 'pip'

      - name: Install dependencies
        run: |
          # Install system dependencies
          sudo apt update
          sudo apt install pandoc
          
          # Install Python dependencies
          python -m pip install --upgrade pip
          pip install jupyter nbconvert nbformat
          pip install -r requirements.txt
          pip install ipykernel rdkit cairosvg pymzml
          pip install .

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

      - name: Find and execute notebooks
        run: |
          # Find all notebooks that need to execute (adjust paths as needed)
          find "docs/Data Formatting/" -name "*.ipynb" > notebooks_to_execute.txt
          echo "docs/Getting Started.ipynb" >> notebooks_to_execute.txt

          echo "Found notebooks:"
          cat notebooks_to_execute.txt
          
          # Execute each notebook
          while IFS= read -r notebook; do
            echo "Executing: $notebook"
            # Clear outputs first (optional)
            jupyter nbconvert --clear-output --inplace "$notebook"
            # Execute notebook
            jupyter nbconvert --execute --to notebook --inplace "$notebook" \
              --ExecutePreprocessor.timeout=300 \
              --ExecutePreprocessor.kernel_name=python3
            
            # Check if execution was successful
            if [ $? -eq 0 ]; then
              echo "✓ Successfully executed: $notebook"
            else
              echo "✗ Failed to execute: $notebook"
              exit 1
            fi
          done < notebooks_to_execute.txt
      - name: Push changes
        if: steps.verify-changed-files.outputs.changed == 'true' && github.event_name != 'pull_request'
        run: |
          git push origin ${{ github.ref_name }}

      - name: Summary
        run: |
          if [ "${{ steps.verify-changed-files.outputs.changed }}" == "true" ]; then
            echo "✅ Notebooks executed successfully and changes committed"
          else
            echo "✅ Notebooks executed successfully, no changes to commit"
          fi