utils.py

import base64
from io import BytesIO
from PIL import Image
from markitdown import MarkItDown

def encode_image_to_base64(image):
    """Encodes a PIL Image to a base64 string."""
    if isinstance(image, str):
        # If it's a file path
        with open(image, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode('utf-8')
    elif isinstance(image, Image.Image):
        buffered = BytesIO()
        image.save(buffered, format="JPEG")
        return base64.b64encode(buffered.getvalue()).decode('utf-8')
    return None

def convert_doc_to_markdown(file_path):
    """Converts a document (PDF, Docx, etc.) to markdown."""
    if not file_path:
        return ""
    try:
        md = MarkItDown()
        result = md.convert(file_path)
        return result.text_content
    except Exception as e:
        return f"Error converting document: {str(e)}"

def get_mock_claims():
    """Returns a list of mock claims for the dashboard."""
    return [
        {
            "id": "CLM-1001",
            "submitter": "John Doe",
            "date": "2023-10-25",
            "vehicle": "2018 Toyota Camry",
            "status": "New",
            "ai_analysis": {
                "damage_estimate": "£820",
                "fraud_risk": "Low",
                "adjuster_classification": "Junior Adjuster",
                "recommendation": "Auto-approve payment",
                "summary": "Minor rear bumper damage. Policy active. No suspicious indicators."
            }
        },
        {
            "id": "CLM-1002",
            "submitter": "Jane Smith",
            "date": "2023-10-24",
            "vehicle": "2022 Tesla Model 3",
            "status": "Under Review",
            "ai_analysis": {
                "damage_estimate": "£15,000",
                "fraud_risk": "High",
                "adjuster_classification": "Senior Adjuster",
                "recommendation": "Escalate to SIU",
                "summary": "Severe front-end collision. Multiple vehicles involved. Discrepancy in accident location report."
            }
        },
        {
            "id": "CLM-1003",
            "submitter": "Robert Brown",
            "date": "2023-10-26",
            "vehicle": "2015 Ford Focus",
            "status": "New",
            "ai_analysis": {
                "damage_estimate": "£1,200",
                "fraud_risk": "Low",
                "adjuster_classification": "Junior Adjuster",
                "recommendation": "Review Further",
                "summary": "Side panel scratch and dent. consistent with description. Higher than average repair cost for model."
            }
        }
    ]

def extract_claim_data(text):
    """
    Extracts structured data from the AI's markdown response.
    Returns a dictionary with keys: vehicle, damage_estimate, fraud_risk, adjuster_classification, summary, recommendation.
    """
    import re
    data = {
        "submitter": "Anonymous",
        "vehicle": "Unknown",
        "damage_estimate": "N/A",
        "fraud_risk": "Unknown",
        "adjuster_classification": "Junior Adjuster",
        "recommendation": "Review",
        "summary": "Auto-generated summary from intake."
    }
    
    # Simple regex extraction based on the prompt format
    # *   **Submitter Name:** [Name]
    name_match = re.search(r"\*\*Submitter Name:\*\*\s*(.*)", text)
    if name_match:
        data["submitter"] = name_match.group(1).strip()

    # *   **Vehicle:** [Vehicle Make/Model/Year if identifiable, else 'Unknown']
    vehicle_match = re.search(r"\*\*Vehicle:\*\*\s*(.*)", text)
    if vehicle_match:
        data["vehicle"] = vehicle_match.group(1).strip()

    estimate_match = re.search(r"\*\*Estimated Repair Cost:\*\*\s*(.*)", text)
    if estimate_match:
        data["damage_estimate"] = estimate_match.group(1).strip()

    fraud_match = re.search(r"\*\*Fraud Risk:\*\*\s*(.*)", text)
    if fraud_match:
        data["fraud_risk"] = fraud_match.group(1).strip()

    class_match = re.search(r"\*\*Adjuster Classification:\*\*\s*(.*)", text)
    if class_match:
        data["adjuster_classification"] = class_match.group(1).strip()
        
    summary_match = re.search(r"\*\*Summary:\*\*\s*(.*)", text)
    if summary_match:
        data["summary"] = summary_match.group(1).strip()
    else:
        # Fallback: use the first few lines or the whole text if summary not found explicitly
        data["summary"] = text[:200] + "..."

    # Infer recommendation based on classification/risk if not explicitly parsed (or add prompt for it)
    # For now, let's look for "Next Steps" or just default based on risk
    if "High" in data["fraud_risk"]:
        data["recommendation"] = "Escalate to SIU"
    elif "Low" in data["fraud_risk"] and "Junior" in data["adjuster_classification"]:
        data["recommendation"] = "Auto-approve payment"
    
    return data