PDF Document Analysis System

Analyzes PDF documents, extracts structured information, groups similar documents, and identifies the most recent version.

Installation

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Usage

# Analyze PDFs in current directory
python main.py

# Analyze PDFs in specific directory
python main.py /path/to/pdfs

# Specify output file
python main.py /path/to/pdfs -o output.json

# Verbose mode
python main.py /path/to/pdfs -v

What It Does

-> Extracts revision dates, numbers, paragraphs, and images from PDFs -> Groups similar documents together -> Identifies the most recent/authoritative version -> Outputs structured JSON with all findings

Output Format

{
  "groups": [
    {
      "groupId": "A",
      "documents": [
        {
          "fileName": "Document1.pdf",
          "revisionDate": "12/15/2024",
          "revisionNumber": "2.1",
          "paragraphs": [
            {"title": "Paragraph 1", "text": "..."}
          ],
          "images": [
            {"exists": true}
          ]
        }
      ],
      "isIdentical": false
    }
  ]
}

Running Tests

pytest