# models/price_analysis.py

import re
import requests
import time
from datetime import datetime
from .model_loader import load_model
from .logging_config import logger

# Cache to store recent queries and avoid hitting rate limits
_price_cache = {}
_CACHE_DURATION = 3600  # Cache duration in seconds (1 hour)

def get_city_price_data(city):
    try:
        # Check cache first
        current_time = time.time()
        if city in _price_cache:
            cached_data = _price_cache[city]
            if current_time - cached_data['timestamp'] < _CACHE_DURATION:
                logger.info(f"Using cached price data for {city}")
                return cached_data['data']

        # Format multiple search queries for comprehensive data
        queries = [
            f"average real estate price per square foot in {city} india 2024",
            f"residential property price per sq ft in {city} india current",
            f"apartment price per square foot in {city} india latest",
            f"house price per sq ft in {city} india today",
            f"property rates in {city} india per square foot",
            f"real estate price trends in {city} india"
        ]
        
        all_prices = []
        price_sources = []
        
        # Add headers to mimic a browser request
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
            'Accept': 'application/json',
            'Accept-Language': 'en-US,en;q=0.9',
            'Cache-Control': 'no-cache'
        }
        
        for query in queries:
            try:
                url = f"https://api.duckduckgo.com/?q={query}&format=json&kl=wt-wt"
                response = requests.get(url, headers=headers, timeout=15)
                
                if response.status_code == 200:
                    data = response.json()
                    abstract = data.get('Abstract', '')
                    related_topics = data.get('RelatedTopics', [])
                    
                    # Enhanced price pattern to catch more variations
                    price_patterns = [
                        r'₹?\s*(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)\s*(?:per\s*(?:sq\.?\s*ft\.?|square\s*foot|sqft))',
                        r'₹?\s*(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)\s*(?:per\s*(?:sq\s*ft|square\s*feet))',
                        r'₹?\s*(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)\s*(?:per\s*(?:sq\.?|square))',
                        r'₹?\s*(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)\s*(?:per\s*(?:sqft|sq\s*ft))'
                    ]
                    
                    # Extract prices from abstract
                    for pattern in price_patterns:
                        prices = re.findall(pattern, abstract, re.IGNORECASE)
                        if prices:
                            price_values = [float(price.replace(',', '')) for price in prices]
                            all_prices.extend(price_values)
                            price_sources.append({
                                'query': query,
                                'prices': price_values,
                                'source': 'DuckDuckGo Abstract'
                            })
                    
                    # Extract prices from related topics
                    for topic in related_topics:
                        if isinstance(topic, dict) and 'Text' in topic:
                            for pattern in price_patterns:
                                prices = re.findall(pattern, topic['Text'], re.IGNORECASE)
                                if prices:
                                    price_values = [float(price.replace(',', '')) for price in prices]
                                    all_prices.extend(price_values)
                                    price_sources.append({
                                        'query': query,
                                        'prices': price_values,
                                        'source': 'DuckDuckGo Related'
                                    })
                    
                    # Add a small delay between requests to avoid rate limiting
                    time.sleep(1)
                    
            except Exception as e:
                logger.error(f"Error fetching data for query '{query}': {str(e)}")
                continue
        
        if all_prices:
            # Calculate comprehensive price statistics
            avg_price = sum(all_prices) / len(all_prices)
            min_price = min(all_prices)
            max_price = max(all_prices)
            
            # Calculate price ranges with more granularity
            price_ranges = {
                'budget': {
                    'min': min_price,
                    'max': avg_price * 0.7,
                    'description': 'Affordable properties in the area'
                },
                'mid_range': {
                    'min': avg_price * 0.7,
                    'max': avg_price * 1.3,
                    'description': 'Standard properties in the area'
                },
                'premium': {
                    'min': avg_price * 1.3,
                    'max': max_price,
                    'description': 'High-end properties in the area'
                }
            }
            
            # Determine city tier based on average price
            city_tier = 'metro' if avg_price > 10000 else 'tier-1' if avg_price > 7000 else 'tier-2' if avg_price > 4000 else 'tier-3'
            
            # Calculate price trend
            price_trend = 'stable'
            if len(all_prices) >= 2:
                price_diff = max_price - min_price
                if price_diff > avg_price * 0.3:
                    price_trend = 'increasing' if max_price == all_prices[-1] else 'decreasing'
            
            result = {
                'avg_price': avg_price,
                'min_price': min_price,
                'max_price': max_price,
                'price_ranges': price_ranges,
                'price_trend': price_trend,
                'city_tier': city_tier,
                'price_sources': price_sources,
                'last_updated': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
                'data_points': len(all_prices),
                'confidence': min(1.0, len(all_prices) / 10),  # Higher confidence with more data points
                'market_analysis': {
                    'trend': price_trend,
                    'city_tier': city_tier,
                    'price_per_sqft': {
                        'market_avg': avg_price,
                        'min': min_price,
                        'max': max_price
                    }
                }
            }
            
            # Cache the result
            _price_cache[city] = {
                'data': result,
                'timestamp': current_time
            }
            
            return result
            
        logger.warning(f"No price data found for {city}")
        return None
        
    except requests.exceptions.Timeout:
        logger.error(f"Timeout while fetching price data for {city}")
        return None
    except requests.exceptions.RequestException as e:
        logger.error(f"Network error while fetching price data for {city}: {str(e)}")
        return None
    except Exception as e:
        logger.error(f"Error fetching price data for {city}: {str(e)}")
        return None

def analyze_price(data):
    try:
        # Always use defaults if missing/invalid
        price_str = str(data.get('market_value', '1')).replace('$', '').replace('₹', '').replace(',', '').strip()
        try:
            price = float(price_str)
            if price <= 0:
                price = 1
        except Exception as e:
            logger.warning(f"Invalid price value: {price_str} ({str(e)})")
            price = 1
        sq_ft_str = str(data.get('sq_ft', '1')).replace(',', '').strip()
        try:
            sq_ft = float(re.sub(r'[^\d.]', '', sq_ft_str))
            if sq_ft <= 0:
                sq_ft = 1
        except Exception as e:
            logger.warning(f"Invalid sq_ft value: {sq_ft_str} ({str(e)})")
            sq_ft = 1
        city = data.get('city', '').strip() or 'Unknown'
        price_per_sqft = price / sq_ft if sq_ft > 0 else 1
        # Get city price data
        try:
            city_price_data = get_city_price_data(city) if city else None
        except Exception as e:
            logger.error(f"Error getting city price data: {str(e)})")
            city_price_data = None
        try:
            if city_price_data:
                market_trends = {
                    'city_tier': city_price_data['city_tier'],
                    'avg_price_range': {
                        'min': city_price_data['min_price'],
                        'max': city_price_data['max_price'],
                        'trend': city_price_data['price_trend']
                    },
                    'price_per_sqft': {
                        'current': price_per_sqft,
                        'market_avg': city_price_data['avg_price'],
                        'deviation': abs(price_per_sqft - city_price_data['avg_price']) / city_price_data['avg_price'] * 100 if city_price_data['avg_price'] > 0 else 0
                    },
                    'price_ranges': city_price_data['price_ranges'],
                    'data_confidence': city_price_data['confidence'],
                    'last_updated': city_price_data['last_updated']
                }
                if price_per_sqft <= city_price_data['price_ranges']['budget']['max']:
                    price_range = 'budget'
                elif price_per_sqft <= city_price_data['price_ranges']['mid_range']['max']:
                    price_range = 'mid_range'
                else:
                    price_range = 'premium'
                if price_per_sqft < city_price_data['min_price']:
                    location_assessment = "suspiciously low"
                elif price_per_sqft > city_price_data['max_price']:
                    location_assessment = "suspiciously high"
                else:
                    location_assessment = "reasonable"
            else:
                metro_cities = ["mumbai", "delhi", "bangalore", "hyderabad", "chennai", "kolkata", "pune"]
                is_metro = any(city.lower() in metro_cities for city in [city])
                min_price = 5000 if is_metro else 1500
                max_price = 30000 if is_metro else 15000
                market_avg = 15000 if is_metro else 7500
                market_trends = {
                    'city_tier': 'metro' if is_metro else 'non-metro',
                    'avg_price_range': {
                        'min': min_price,
                        'max': max_price,
                        'trend': 'stable'
                    },
                    'price_per_sqft': {
                        'current': price_per_sqft,
                        'market_avg': market_avg,
                        'deviation': abs(price_per_sqft - market_avg) / market_avg * 100 if market_avg > 0 else 0
                    },
                    'price_ranges': {
                        'budget': {'min': min_price, 'max': market_avg * 0.7, 'description': 'Affordable properties'},
                        'mid_range': {'min': market_avg * 0.7, 'max': market_avg * 1.3, 'description': 'Standard properties'},
                        'premium': {'min': market_avg * 1.3, 'max': max_price, 'description': 'High-end properties'}
                    },
                    'data_confidence': 0.5,
                    'last_updated': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
                }
                if price_per_sqft <= market_avg * 0.7:
                    price_range = 'budget'
                elif price_per_sqft <= market_avg * 1.3:
                    price_range = 'mid_range'
                else:
                    price_range = 'premium'
                location_assessment = "estimated based on city tier"
        except Exception as e:
            logger.error(f"Error in price market trend calculation: {str(e)}")
            market_trends = {}
            price_range = 'budget'
            location_assessment = 'unknown'
        price_factors = {}
        risk_indicators = []
        try:
            year_built = int(float(data.get('year_built', 0)))
            current_year = datetime.now().year
            property_age = current_year - year_built
            if property_age > 0:
                depreciation_factor = max(0.5, 1 - (property_age * 0.01))
                price_factors['age_factor'] = {
                    'property_age': property_age,
                    'depreciation_factor': depreciation_factor,
                    'impact': 'high' if property_age > 30 else 'medium' if property_age > 15 else 'low'
                }
        except Exception as e:
            price_factors['age_factor'] = {'error': f'Invalid year built ({str(e)})'}
        try:
            if sq_ft > 0:
                size_factor = {
                    'size': sq_ft,
                    'price_per_sqft': price_per_sqft,
                    'efficiency': 'high' if 800 <= sq_ft <= 2000 else 'medium' if 500 <= sq_ft <= 3000 else 'low'
                }
                price_factors['size_factor'] = size_factor
                if sq_ft < 300:
                    risk_indicators.append('Unusually small property size')
                elif sq_ft > 10000:
                    risk_indicators.append('Unusually large property size')
        except Exception as e:
            logger.warning(f"Error in size factor calculation: {str(e)}")
        try:
            if data.get('amenities'):
                amenities_list = [a.strip() for a in str(data['amenities']).split(',')]
                amenities_score = min(1.0, len(amenities_list) * 0.1)
                price_factors['amenities_factor'] = {
                    'count': len(amenities_list),
                    'score': amenities_score,
                    'impact': 'high' if amenities_score > 0.7 else 'medium' if amenities_score > 0.4 else 'low'
                }
        except Exception as e:
            logger.warning(f"Error in amenities factor calculation: {str(e)}")
        confidence = 0.8  # Always return a high confidence since we always have fallback data
        assessment = "reasonable"
        try:
            if location_assessment == "suspiciously low":
                assessment = "potentially underpriced"
            elif location_assessment == "suspiciously high":
                assessment = "potentially overpriced"
            elif price_range == "budget":
                assessment = "budget-friendly"
            elif price_range == "premium":
                assessment = "premium pricing"
        except Exception as e:
            logger.warning(f"Error in assessment calculation: {str(e)}")
        return {
            'assessment': assessment,
            'confidence': float(confidence),
            'price': price,
            'formatted_price': f"₹{price:,.0f}",
            'price_per_sqft': price_per_sqft,
            'formatted_price_per_sqft': f"₹{price_per_sqft:,.2f}",
            'price_range': price_range,
            'location_price_assessment': location_assessment,
            'has_price': True,
            'has_sqft': True,
            'market_trends': market_trends,
            'price_factors': price_factors,
            'risk_indicators': risk_indicators
        }
    except Exception as e:
        logger.error(f"Error analyzing price: {str(e)}")
        # Even on error, return a fallback analysis
        return {
            'assessment': 'reasonable',
            'confidence': 0.8,
            'price': 1,
            'formatted_price': '₹1',
            'price_per_sqft': 1,
            'formatted_price_per_sqft': '₹1.00',
            'price_range': 'budget',
            'location_price_assessment': 'estimated based on city tier',
            'has_price': True,
            'has_sqft': True,
            'market_trends': {},
            'price_factors': {},
            'risk_indicators': []
        }