app/utils/helpers.py

import pandas as pd
from datetime import datetime
from typing import Dict, Any, List

def create_comprehensive_csv_data(data_source: str, company_info: str, accounting_standards: str, 
                                regulatory_frameworks: List[str], result: Dict[str, Any]) -> pd.DataFrame:
    """Create comprehensive CSV data with all analysis information"""
    
    # Extract company information
    company_parts = company_info.split(" in the ")
    company_type = company_parts[0] if len(company_parts) > 0 else "N/A"
    industry_sector = company_parts[1].split(", classified as")[0] if len(company_parts) > 1 else "N/A"
    company_size = company_parts[1].split("classified as ")[1].split(", for")[0] if len(company_parts) > 1 else "N/A"
    financial_year = company_parts[1].split("for ")[-1] if len(company_parts) > 1 else "N/A"
    
    # Create comprehensive data structure
    comprehensive_data = []
    
    # 1. Basic Information
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Analysis Timestamp',
        'Value': datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
        'Details': 'Time when analysis was performed',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Data Source',
        'Value': data_source,
        'Details': 'Source of financial data used for analysis',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Company Type',
        'Value': company_type,
        'Details': 'Legal structure of the company',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Industry Sector',
        'Value': industry_sector,
        'Details': 'Primary business sector',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Company Size',
        'Value': company_size,
        'Details': 'Classification based on turnover and capital',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Financial Year',
        'Value': financial_year,
        'Details': 'Reporting period under analysis',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Accounting Standards',
        'Value': accounting_standards,
        'Details': 'Applicable accounting framework',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    comprehensive_data.append({
        'Category': 'Basic Information',
        'Field': 'Regulatory Frameworks',
        'Value': ', '.join(regulatory_frameworks),
        'Details': 'Applicable regulatory requirements',
        'Priority': '',
        'Timeline': '',
        'Regulation': ''
    })
    
    # 2. AI Analysis Results (if available)
    if isinstance(result, dict) and 'response' in result:
        comprehensive_data.append({
            'Category': 'AI Analysis Results',
            'Field': 'Full Analysis Response',
            'Value': 'AI Generated Compliance Analysis',
            'Details': result['response'][:1000] + '...' if len(result['response']) > 1000 else result['response'],
            'Priority': '',
            'Timeline': '',
            'Regulation': ''
        })
    
    return pd.DataFrame(comprehensive_data)