Document Analysis Framework v2.0.0

A lightweight document analysis framework for text, code, configuration, and other text-based files designed for AI/ML data pipelines. Part of the unified analysis framework suite built on analysis-framework-base.

🎯 When to Use This Framework

This is a fallback framework for text-based files not handled by our specialized frameworks:

Specialized Frameworks (Use These First!)

1. xml-analysis-framework 📑

   • For: XML documents of all types
   • Includes: 29+ specialized XML handlers (SCAP, RSS, Maven POM, Spring configs, etc.)
   • Install: pip install xml-analysis-framework

2. docling-analysis-framework 📄

   • For: PDF, Word, Excel, PowerPoint, and images with text
   • Features: Docling-powered extraction with OCR support
   • Install: pip install docling-analysis-framework

3. data-analysis-framework 📊

   • For: Structured data that needs AI agent interaction
   • Features: Safe query interface for AI agents to analyze data
   • Install: pip install data-analysis-framework

Use This Framework For:

• Code files: Python, JavaScript, TypeScript, Go, Rust, etc.
• Config files: Dockerfile, package.json, .env, INI files, etc.
• Text/Markup: Markdown, plain text, LaTeX, AsciiDoc, etc.
• Data files: CSV, JSON, YAML, TOML, TSV, etc.
• Other text-based formats not covered above

Note: Some file types (like CSV, JSON) can be handled by multiple frameworks. Choose based on your use case:

• Use data-analysis-framework for AI agent querying of structured data
• Use document-analysis-framework for chunking and document analysis

🚀 Quick Start

Document Analysis

from core.analyzer import DocumentAnalyzer

analyzer = DocumentAnalyzer()
result = analyzer.analyze_document("path/to/file.py")

print(f"Document Type: {result['document_type'].type_name}")
print(f"Language: {result['document_type'].language}")
print(f"AI Use Cases: {result['analysis'].ai_use_cases}")

Smart Chunking

from core.analyzer import DocumentAnalyzer
from core.chunking import ChunkingOrchestrator

# Analyze document
analyzer = DocumentAnalyzer()
analysis = analyzer.analyze_document("file.py")

# Convert format for chunking
chunking_analysis = {
    'document_type': {
        'type_name': analysis['document_type'].type_name,
        'confidence': analysis['document_type'].confidence,
        'category': analysis['document_type'].category
    },
    'analysis': analysis['analysis']
}

# Generate AI-optimized chunks
orchestrator = ChunkingOrchestrator()
chunks = orchestrator.chunk_document("file.py", chunking_analysis, strategy='auto')

🔄 Unified Interface Support

This framework now supports the unified interface standard, providing consistent access patterns across all analysis frameworks:

import src as daf  # or from the installed package

# Use the unified interface
result = daf.analyze_unified("config.yaml")

# All access patterns work consistently
doc_type = result['document_type']        # Dict access ✓
doc_type = result.document_type           # Attribute access ✓
doc_type = result.get('document_type')    # get() method ✓
as_dict = result.to_dict()                # Full dict conversion ✓

# Works the same across all frameworks
print(f"Framework: {result.framework}")   # 'document-analysis-framework'
print(f"Type: {result.document_type}")
print(f"Confidence: {result.confidence}")
print(f"AI opportunities: {result.ai_opportunities}")

The unified interface ensures compatibility when switching between frameworks or using multiple frameworks together.

Chunking for RAG

📋 Currently Supported File Types

Coming Soon:

• TypeScript, Go, Rust, Ruby, PHP, Swift, Kotlin
• Shell scripts, PowerShell, R, MATLAB
• INI files, .env files, Apache/Nginx configs
• LaTeX, AsciiDoc, reStructuredText
• Log files, CSS/SCSS, Vue/Svelte components

🎯 Key Features

• 🔍 Intelligent Document Detection - Content-based recognition with confidence scoring
• 🤖 AI-Ready Output - Structured analysis with quality metrics and use case recommendations
• ⚡ Smart Chunking - Document-type-aware segmentation strategies
• 🔒 Security & Reliability - File size limits, safe handling, pure Python stdlib
• 🔄 Extensible - Easy to add new handlers for additional file types

🔧 Installation

pip install document-analysis-framework

Or from source:

git clone https://github.com/rdwj/document-analysis-framework.git
cd document-analysis-framework
pip install -e .

🧪 Framework Ecosystem

This framework is part of the unified analysis framework suite built on analysis-framework-base:

Choosing the Right Framework

graph TD
    A[Have a document to analyze?] --> B{What type?}
    B -->|XML| C[xml-analysis-framework]
    B -->|PDF/Word/Excel/PPT| D[docling-analysis-framework]
    B -->|Need AI to query data| E[data-analysis-framework]
    B -->|Text/Code/Config/Other| F[document-analysis-framework]

📄 License

MIT License - see LICENSE file for details.