{
  "pandoc_config": {
    "description": "Pandoc document conversion configuration for AI DevOps Framework",
    "version": "1.1.2",
    "paths": {
      "input_directory": "./documents",
      "output_directory": "./markdown",
      "temp_directory": "./tmp/pandoc",
      "backup_originals": true
    },
    "conversion_settings": {
      "default_output_format": "markdown",
      "wrap_mode": "none",
      "header_style": "atx",
      "include_toc": false,
      "standalone": false,
      "extract_media": true,
      "media_directory": "./media"
    },
    "format_specific": {
      "pdf": {
        "requires": "pdftotext (poppler-utils)",
        "options": "--pdf-engine=xelatex",
        "notes": "PDF conversion quality depends on source document structure"
      },
      "docx": {
        "options": "--extract-media=./media",
        "preserve_formatting": true,
        "notes": "Best conversion quality for Word documents"
      },
      "html": {
        "options": "--from=html --to=markdown",
        "strip_comments": true,
        "preserve_links": true
      },
      "epub": {
        "options": "--extract-media=./media",
        "preserve_structure": true,
        "notes": "Excellent for book-like documents"
      },
      "latex": {
        "options": "--from=latex --to=markdown",
        "math_support": true,
        "notes": "Good for academic papers with equations"
      }
    },
    "batch_processing": {
      "max_concurrent": 4,
      "file_patterns": {
        "documents": "*.{docx,doc,pdf,odt,rtf}",
        "web": "*.{html,htm,epub}",
        "markup": "*.{rst,org,textile,mediawiki}",
        "data": "*.{json,csv,xml}",
        "presentations": "*.{pptx,ppt}"
      },
      "exclude_patterns": [
        "*.tmp",
        "*.bak",
        "*~",
        ".DS_Store"
      ]
    },
    "ai_optimization": {
      "chunk_large_files": true,
      "max_file_size_mb": 10,
      "add_metadata_headers": true,
      "clean_formatting": true,
      "preserve_structure": true,
      "add_source_info": true
    },
    "quality_settings": {
      "validate_output": true,
      "check_encoding": true,
      "fix_line_endings": true,
      "remove_empty_lines": false,
      "normalize_whitespace": true
    },
    "integration": {
      "auto_index": true,
      "create_manifest": true,
      "update_git": false,
      "notify_completion": true
    }
  },
  "usage_examples": {
    "single_file": "bash providers/pandoc-helper.sh convert document.docx",
    "with_options": "bash providers/pandoc-helper.sh convert document.pdf output.md pdf '--extract-media=./images'",
    "batch_conversion": "bash providers/pandoc-helper.sh batch ./documents ./markdown '*.docx'",
    "detect_format": "bash providers/pandoc-helper.sh detect unknown_file.ext",
    "show_formats": "bash providers/pandoc-helper.sh formats"
  },
  "installation": {
    "pandoc_required": true,
    "optional_dependencies": {
      "poppler-utils": "For PDF conversion (pdftotext)",
      "wkhtmltopdf": "For HTML to PDF conversion",
      "librsvg2-bin": "For SVG image support",
      "texlive": "For LaTeX document support"
    },
    "install_commands": {
      "macos": "brew install pandoc poppler",
      "ubuntu": "sudo apt-get install pandoc poppler-utils",
      "centos": "sudo yum install pandoc poppler-utils",
      "windows": "choco install pandoc"
    }
  },
  "ai_assistant_benefits": {
    "markdown_advantages": [
      "Consistent formatting for AI processing",
      "Easy to parse and analyze",
      "Preserves document structure",
      "Lightweight and fast to process",
      "Version control friendly",
      "Cross-platform compatibility"
    ],
    "use_cases": [
      "Convert documentation for AI analysis",
      "Process legacy documents for modernization",
      "Extract content from various formats",
      "Create searchable document archives",
      "Prepare documents for AI training",
      "Standardize document formats across projects"
    ]
  }
}
