# models/suggestions.py

from .model_loader import load_model
from .logging_config import logger

def generate_suggestions(text, data=None):
    try:
        # Ensure text is string
        text = str(text) if text is not None else ""
        
        # Safely convert data values
        if data:
            processed_data = {}
            for key, value in data.items():
                if isinstance(value, (int, float)):
                    processed_data[key] = str(value)
                else:
                    processed_data[key] = str(value) if value is not None else ""
            data = processed_data

        # Initialize suggestions
        suggestions = {
            'improvements': [],
            'warnings': [],
            'recommendations': [],
            'confidence': 0.0,
            'model_used': 'static_fallback'
        }

        # Load model for analysis
        try:
            classifier = load_model("zero-shot-classification")  # Use standard model instead of typeform
        except Exception as e:
            logger.error(f"Error loading model in suggestions: {str(e)}")
            suggestions['warnings'].append({'type': 'error', 'confidence': 0.0, 'details': {'title': 'Model Error', 'message': f'Model loading error: {str(e)}', 'priority': 'high'}})
            return suggestions

        # Define suggestion categories
        categories = [
            "property description improvement",
            "price adjustment needed",
            "documentation required",
            "verification needed",
            "legal compliance issue",
            "location verification needed",
            "property specification update",
            "image quality improvement",
            "market value adjustment",
            "contact information update"
        ]

        # Analyze text with context
        context = f"{text} property_data:{str(data) if data else ''}"
        
        try:
            result = classifier(context[:1000], categories, multi_label=True)
            
            # Process results and generate suggestions
            for label, score in zip(result['labels'], result['scores']):
                if score > 0.3:  # Only include if confidence is above 30%
                    suggestion_details = generate_suggestion_details(label, text, data)
                    if suggestion_details:
                        if 'improvement' in label.lower():
                            suggestions['improvements'].append(suggestion_details)
                        elif 'warning' in label.lower() or 'issue' in label.lower():
                            suggestions['warnings'].append(suggestion_details)
                        else:
                            suggestions['recommendations'].append(suggestion_details)
            
            # Calculate overall confidence
            if result['scores']:
                suggestions['confidence'] = max(result['scores'])
            
            suggestions['model_used'] = getattr(classifier, 'fallback_model', 'primary_model')
            
        except Exception as e:
            logger.error(f"Error in suggestions analysis: {str(e)}")
            suggestions['warnings'].append({'type': 'error', 'confidence': 0.0, 'details': {'title': 'Analysis Error', 'message': f'Analysis error: {str(e)}', 'priority': 'medium'}})

        return suggestions
        
    except Exception as e:
        logger.error(f"Error generating suggestions: {str(e)}")
        return {
            'improvements': [],
            'warnings': [{'type': 'error', 'confidence': 0.0, 'details': {'title': 'System Error', 'message': f'System error: {str(e)}', 'priority': 'high'}}],
            'recommendations': [],
            'confidence': 0.0,
            'model_used': 'static_fallback'
        }

def generate_suggestion_details(suggestion_type, text, data):
    """Generate detailed suggestions based on type"""
    try:
        if 'description improvement' in suggestion_type.lower():
            return {
                'type': 'description_improvement',
                'confidence': 0.8,
                'details': {
                    'title': 'Improve Property Description',
                    'message': 'Add more details about amenities, location benefits, and unique features.',
                    'priority': 'medium',
                    'suggestions': [
                        'Include nearby landmarks and transportation',
                        'Describe interior features and finishes',
                        'Mention parking and security features',
                        'Add information about neighborhood'
                    ]
                }
            }
        elif 'price adjustment' in suggestion_type.lower():
            return {
                'type': 'price_adjustment',
                'confidence': 0.7,
                'details': {
                    'title': 'Review Property Price',
                    'message': 'Consider adjusting the price based on market conditions and property features.',
                    'priority': 'high',
                    'suggestions': [
                        'Compare with similar properties in the area',
                        'Consider current market trends',
                        'Factor in property condition and age',
                        'Include all amenities in pricing'
                    ]
                }
            }
        elif 'documentation required' in suggestion_type.lower():
            return {
                'type': 'documentation_required',
                'confidence': 0.9,
                'details': {
                    'title': 'Additional Documentation Needed',
                    'message': 'Provide more documents to increase property verification.',
                    'priority': 'high',
                    'suggestions': [
                        'Upload property title documents',
                        'Include recent utility bills',
                        'Add property tax receipts',
                        'Provide floor plan or layout'
                    ]
                }
            }
        elif 'verification needed' in suggestion_type.lower():
            return {
                'type': 'verification_needed',
                'confidence': 0.8,
                'details': {
                    'title': 'Property Verification Required',
                    'message': 'Additional verification steps needed for property authenticity.',
                    'priority': 'high',
                    'suggestions': [
                        'Verify property ownership',
                        'Check for any legal disputes',
                        'Confirm property dimensions',
                        'Validate address details'
                    ]
                }
            }
        else:
            return {
                'type': 'general_suggestion',
                'confidence': 0.6,
                'details': {
                    'title': 'General Improvement',
                    'message': 'Consider improving overall property listing quality.',
                    'priority': 'medium',
                    'suggestions': [
                        'Add more high-quality images',
                        'Include detailed specifications',
                        'Provide contact information',
                        'Update property status regularly'
                    ]
                }
            }
    except Exception as e:
        logger.error(f"Error generating suggestion details: {str(e)}")
        return None