sync-content.yml

name: Auto-sync Jekyll Content

on:
  push:
    paths:
      - 'demos/**/README.md'
      - 'experiments/**/README.md'
      - 'snippets/**/README.md'
      - 'snippets/**/*.md'
      - 'snippets/**/*.py'
  workflow_dispatch:

jobs:
  sync-content:
    runs-on: ubuntu-latest
    permissions:
      contents: write
    
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
      
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.x'
      
      - name: Create sync script
        run: |
          cat > sync_content.py << 'SCRIPT_END'
          import os
          import re
          from datetime import datetime
          from pathlib import Path
          
          # Create directories if they don't exist
          Path("_demos").mkdir(exist_ok=True)
          Path("_experiments").mkdir(exist_ok=True)
          Path("_snippets").mkdir(exist_ok=True)
          
          # Sync demos
          if Path("demos").exists():
              for demo_dir in Path("demos").iterdir():
                  if demo_dir.is_dir() and (demo_dir / "README.md").exists():
                      readme_path = demo_dir / "README.md"
                      content = readme_path.read_text()
                      
                      # Extract title from first # heading
                      title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
                      title = title_match.group(1) if title_match else demo_dir.name
                      
                      # Extract metadata from content
                      tags = []
                      if "## Tags" in content:
                          tags_section = content.split("## Tags")[1].split("##")[0]
                          tags = [tag.strip("- \n") for tag in tags_section.strip().split("\n") if tag.strip()]
                      
                      technologies = []
                      if "## Technologies" in content:
                          tech_section = content.split("## Technologies")[1].split("##")[0]
                          technologies = [tech.strip("- \n") for tech in tech_section.strip().split("\n") if tech.strip()]
                      
                      difficulty = "medium"
                      if "## Difficulty" in content:
                          diff_section = content.split("## Difficulty")[1].split("##")[0]
                          difficulty = diff_section.strip().lower()
                      
                      # Get description (first paragraph after title, stop at next heading)
                      desc_match = re.search(r'^# .+\n\n([^#]+?)(?:\n#|\n\n#|\Z)', content, re.MULTILINE | re.DOTALL)
                      description = desc_match.group(1).strip() if desc_match else "Demo showcasing AI capabilities"
                      
                      # Format tags and technologies as YAML lists
                      tags_yaml = "\n".join([f"  - {tag}" for tag in tags]) if tags else ""
                      tech_yaml = "\n".join([f"  - {tech}" for tech in technologies]) if technologies else ""
                      
                      # Create Jekyll file with proper front matter
                      jekyll_content = f"""---
          title: "{title}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          description: "{description}"
          layout: demo
          difficulty: {difficulty}
          source_folder: "demos/{demo_dir.name}"
          """
                      
                      if tags_yaml:
                          jekyll_content += f"\ntags:\n{tags_yaml}"
                      
                      if tech_yaml:
                          jekyll_content += f"\ntechnologies:\n{tech_yaml}"
                      
                      jekyll_content += f"""
          ---
          
          {content}
          
          <div class='source-links'>
            <h3>Full Source Code</h3>
            <a href='https://github.com/aws-samples/sample-ai-possibilities/tree/main/demos/{demo_dir.name}' class='btn btn-primary'>
              View on GitHub
            </a>
          </div>
          """
                      
                      # Clean up extra indentation
                      jekyll_content = jekyll_content.replace("\n          ", "\n")
                      
                      # Write to _demos
                      output_path = Path("_demos") / f"{demo_dir.name}.md"
                      output_path.write_text(jekyll_content)
                      print(f"Synced demo: {demo_dir.name}")
          
          # Sync experiments
          if Path("experiments").exists():
              for exp_dir in Path("experiments").iterdir():
                  if exp_dir.is_dir() and (exp_dir / "README.md").exists():
                      readme_path = exp_dir / "README.md"
                      content = readme_path.read_text()
                      
                      title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
                      title = title_match.group(1) if title_match else exp_dir.name
                      
                      # Extract metadata from content
                      tags = []
                      if "## Tags" in content:
                          tags_section = content.split("## Tags")[1].split("##")[0]
                          tags = [tag.strip("- \n") for tag in tags_section.strip().split("\n") if tag.strip()]
                      
                      technologies = []
                      if "## Technologies" in content:
                          tech_section = content.split("## Technologies")[1].split("##")[0]
                          technologies = [tech.strip("- \n") for tech in tech_section.strip().split("\n") if tech.strip()]
                      
                      difficulty = "medium"
                      if "## Difficulty" in content:
                          diff_section = content.split("## Difficulty")[1].split("##")[0]
                          difficulty = diff_section.strip().lower()
                      
                      # Get description - try to get content under Overview section first
                      description = "Experimental AI implementation"
                      if "## Overview" in content:
                          overview_match = re.search(r'## Overview\s*\n\n([^#]+?)(?:\n#|\n\n#|\Z)', content, re.MULTILINE | re.DOTALL)
                          if overview_match:
                              description = overview_match.group(1).strip()
                      else:
                          # Fallback to first paragraph after title
                          desc_match = re.search(r'^# .+\n\n([^#]+?)(?:\n#|\n\n#|\Z)', content, re.MULTILINE | re.DOTALL)
                          if desc_match:
                              description = desc_match.group(1).strip()
                      
                      # Format tags and technologies as YAML lists
                      tags_yaml = "\n".join([f"  - {tag}" for tag in tags]) if tags else ""
                      tech_yaml = "\n".join([f"  - {tech}" for tech in technologies]) if technologies else ""
                      
                      jekyll_content = f"""---
          title: "{title}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          description: "{description}"
          layout: experiment
          difficulty: {difficulty}
          source_folder: "experiments/{exp_dir.name}"
          """
                      
                      if tags_yaml:
                          jekyll_content += f"\ntags:\n{tags_yaml}"
                      
                      if tech_yaml:
                          jekyll_content += f"\ntechnologies:\n{tech_yaml}"
                      
                      jekyll_content += f"""
          ---
          
          {content}
          
          <div class='source-links'>
            <h3>View Source</h3>
            <a href='https://github.com/aws-samples/sample-ai-possibilities/tree/main/experiments/{exp_dir.name}' class='btn btn-primary'>
              View on GitHub
            </a>
          </div>
          """
                      
                      # Clean up indentation
                      jekyll_content = jekyll_content.replace("\n          ", "\n")
                      
                      output_path = Path("_experiments") / f"{exp_dir.name}.md"
                      output_path.write_text(jekyll_content)
                      print(f"Synced experiment: {exp_dir.name}")
          
          # Sync snippets
          if Path("snippets").exists():
              # First check for files directly in snippets folder
              for snippet_file in Path("snippets").iterdir():
                  if snippet_file.is_file() and snippet_file.suffix in ['.py', '.md']:
                      content = snippet_file.read_text()
                      
                      if snippet_file.suffix == '.py':
                          # Extract docstring
                          docstring_match = re.search(r'"""(.+?)"""', content, re.DOTALL)
                          description = docstring_match.group(1).strip() if docstring_match else "Code snippet"
                          
                          jekyll_content = f"""---
          title: "{snippet_file.stem.replace('-', ' ').replace('_', ' ').title()}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          layout: snippet
          language: python
          description: "{description}"
          source_file: "snippets/{snippet_file.name}"
          ---
          
          # {snippet_file.stem.replace('-', ' ').replace('_', ' ').title()}
          
          {description}
          
          ```python
          {content}
          ```
          
          <div class='source-links'>
            <a href='https://github.com/aws-samples/sample-ai-possibilities/blob/main/snippets/{snippet_file.name}' class='btn btn-primary'>
              View Raw File
            </a>
          </div>
          """
                      else:
                          jekyll_content = f"""---
          title: "{snippet_file.stem.replace('-', ' ').replace('_', ' ').title()}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          layout: snippet
          source_file: "snippets/{snippet_file.name}"
          ---
          
          {content}
          """
                      
                      # Clean up indentation
                      jekyll_content = jekyll_content.replace("\n          ", "\n")
                      
                      output_path = Path("_snippets") / f"{snippet_file.stem}.md"
                      output_path.write_text(jekyll_content)
                      print(f"Synced snippet: {snippet_file.name}")
              
              # Now check for README files in subdirectories (like demos and experiments)
              for snippet_dir in Path("snippets").iterdir():
                  if snippet_dir.is_dir():
                      # Look for README.md in subdirectory
                      readme_path = snippet_dir / "README.md"
                      if readme_path.exists():
                          content = readme_path.read_text()
                          
                          # Extract title from first # heading
                          title_match = re.search(r'^# (.+)$', content, re.MULTILINE)
                          title = title_match.group(1) if title_match else snippet_dir.name
                          
                          # Extract metadata from content
                          tags = []
                          if "## Tags" in content:
                              tags_section = content.split("## Tags")[1].split("##")[0]
                              tags = [tag.strip("- \n") for tag in tags_section.strip().split("\n") if tag.strip()]
                          
                          technologies = []
                          if "## Technologies" in content:
                              tech_section = content.split("## Technologies")[1].split("##")[0]
                              technologies = [tech.strip("- \n") for tech in tech_section.strip().split("\n") if tech.strip()]
                          
                          difficulty = "medium"
                          if "## Difficulty" in content:
                              diff_section = content.split("## Difficulty")[1].split("##")[0]
                              difficulty = diff_section.strip().lower()
                          
                          # Get description (first paragraph after title, stop at next heading)
                          desc_match = re.search(r'^# .+\n\n([^#]+?)(?:\n#|\n\n#|\Z)', content, re.MULTILINE | re.DOTALL)
                          description = desc_match.group(1).strip() if desc_match else "Code snippet"
                          
                          # Format tags and technologies as YAML lists
                          tags_yaml = "\n".join([f"  - {tag}" for tag in tags]) if tags else ""
                          tech_yaml = "\n".join([f"  - {tech}" for tech in technologies]) if technologies else ""
                          
                          jekyll_content = f"""---
          title: "{title}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          description: "{description}"
          layout: snippet
          difficulty: {difficulty}
          source_folder: "snippets/{snippet_dir.name}"
          """
                          
                          if tags_yaml:
                              jekyll_content += f"\ntags:\n{tags_yaml}"
                          
                          if tech_yaml:
                              jekyll_content += f"\ntechnologies:\n{tech_yaml}"
                          
                          jekyll_content += f"""
          ---
          
          {content}
          
          <div class='source-links'>
            <h3>View Source</h3>
            <a href='https://github.com/aws-samples/sample-ai-possibilities/tree/main/snippets/{snippet_dir.name}' class='btn btn-primary'>
              View on GitHub
            </a>
          </div>
          """
                          
                          # Clean up indentation
                          jekyll_content = jekyll_content.replace("\n          ", "\n")
                          
                          output_path = Path("_snippets") / f"{snippet_dir.name}.md"
                          output_path.write_text(jekyll_content)
                          print(f"Synced snippet: {snippet_dir.name}")
                      
                      # Also look for individual .py files in subdirectories
                      for py_file in snippet_dir.glob("*.py"):
                          if py_file.name != "__init__.py":  # Skip __init__.py files
                              content = py_file.read_text()
                              
                              # Extract docstring
                              docstring_match = re.search(r'"""(.+?)"""', content, re.DOTALL)
                              description = docstring_match.group(1).strip() if docstring_match else "Code snippet"
                              
                              jekyll_content = f"""---
          title: "{py_file.stem.replace('-', ' ').replace('_', ' ').title()}"
          date: {datetime.now().strftime('%Y-%m-%d')}
          layout: snippet
          language: python
          description: "{description}"
          source_file: "snippets/{snippet_dir.name}/{py_file.name}"
          ---
          
          # {py_file.stem.replace('-', ' ').replace('_', ' ').title()}
          
          {description}
          
          ```python
          {content}
          ```
          
          <div class='source-links'>
            <a href='https://github.com/aws-samples/sample-ai-possibilities/blob/main/snippets/{snippet_dir.name}/{py_file.name}' class='btn btn-primary'>
              View Raw File
            </a>
          </div>
          """
                              
                              # Clean up indentation
                              jekyll_content = jekyll_content.replace("\n          ", "\n")
                              
                              output_path = Path("_snippets") / f"{snippet_dir.name}-{py_file.stem}.md"
                              output_path.write_text(jekyll_content)
                              print(f"Synced snippet: {snippet_dir.name}/{py_file.name}")
          
          print("\nContent sync complete!")
          SCRIPT_END
      
      - name: Run sync script
        run: python sync_content.py
      
      - name: Commit and push changes
        run: |
          git config --local user.email "github-actions[bot]@users.noreply.github.com"
          git config --local user.name "github-actions[bot]"
          git add _demos/ _experiments/ _snippets/
          if git diff --staged --quiet; then
            echo "No changes to commit"
          else
            git commit -m "Auto-sync content from source folders [skip ci]"
            git push
          fi