""" Smart Park Loader for Hybrid Filtering Strategy This module provides intelligent data loading capabilities for the hybrid filtering approach, optimizing database queries and implementing progressive loading strategies. """ from typing import Dict, Optional, Any from django.db import models from django.core.cache import cache from django.conf import settings from apps.parks.models import Park class SmartParkLoader: """ Intelligent park data loader that optimizes queries based on filtering requirements. Implements progressive loading and smart caching strategies. """ # Cache configuration CACHE_TIMEOUT = getattr(settings, 'HYBRID_FILTER_CACHE_TIMEOUT', 300) # 5 minutes CACHE_KEY_PREFIX = 'hybrid_parks' # Progressive loading thresholds INITIAL_LOAD_SIZE = 50 PROGRESSIVE_LOAD_SIZE = 25 MAX_CLIENT_SIDE_RECORDS = 200 def __init__(self): self.base_queryset = self._get_optimized_queryset() def _get_optimized_queryset(self) -> models.QuerySet: """Get optimized base queryset with all necessary prefetches.""" return Park.objects.select_related( 'operator', 'property_owner', 'banner_image', 'card_image', ).prefetch_related( 'location', # ParkLocation relationship ).filter( # Only include operating and temporarily closed parks by default status__in=['OPERATING', 'CLOSED_TEMP'] ).order_by('name') def get_initial_load(self, filters: Optional[Dict[str, Any]] = None) -> Dict[str, Any]: """ Get initial park data load with smart filtering decisions. Args: filters: Optional filters to apply Returns: Dictionary containing parks data and metadata """ cache_key = self._generate_cache_key('initial', filters) cached_result = cache.get(cache_key) if cached_result: return cached_result # Apply filters if provided queryset = self.base_queryset if filters: queryset = self._apply_filters(queryset, filters) # Get total count for pagination decisions total_count = queryset.count() # Determine loading strategy if total_count <= self.MAX_CLIENT_SIDE_RECORDS: # Load all data for client-side filtering parks = list(queryset.all()) strategy = 'client_side' has_more = False else: # Load initial batch for server-side pagination parks = list(queryset[:self.INITIAL_LOAD_SIZE]) strategy = 'server_side' has_more = total_count > self.INITIAL_LOAD_SIZE result = { 'parks': parks, 'total_count': total_count, 'strategy': strategy, 'has_more': has_more, 'next_offset': len(parks) if has_more else None, 'filter_metadata': self._get_filter_metadata(queryset), } # Cache the result cache.set(cache_key, result, self.CACHE_TIMEOUT) return result def get_progressive_load( self, offset: int, filters: Optional[Dict[str, Any]] = None ) -> Dict[str, Any]: """ Get next batch of parks for progressive loading. Args: offset: Starting offset for the batch filters: Optional filters to apply Returns: Dictionary containing parks data and metadata """ cache_key = self._generate_cache_key(f'progressive_{offset}', filters) cached_result = cache.get(cache_key) if cached_result: return cached_result # Apply filters if provided queryset = self.base_queryset if filters: queryset = self._apply_filters(queryset, filters) # Get the batch end_offset = offset + self.PROGRESSIVE_LOAD_SIZE parks = list(queryset[offset:end_offset]) # Check if there are more records total_count = queryset.count() has_more = end_offset < total_count result = { 'parks': parks, 'total_count': total_count, 'has_more': has_more, 'next_offset': end_offset if has_more else None, } # Cache the result cache.set(cache_key, result, self.CACHE_TIMEOUT) return result def get_filter_metadata(self, filters: Optional[Dict[str, Any]] = None) -> Dict[str, Any]: """ Get metadata about available filter options. Args: filters: Current filters to scope the metadata Returns: Dictionary containing filter metadata """ cache_key = self._generate_cache_key('metadata', filters) cached_result = cache.get(cache_key) if cached_result: return cached_result # Apply filters if provided queryset = self.base_queryset if filters: queryset = self._apply_filters(queryset, filters) result = self._get_filter_metadata(queryset) # Cache the result cache.set(cache_key, result, self.CACHE_TIMEOUT) return result def _apply_filters(self, queryset: models.QuerySet, filters: Dict[str, Any]) -> models.QuerySet: """Apply filters to the queryset.""" # Status filter if 'status' in filters and filters['status']: if isinstance(filters['status'], list): queryset = queryset.filter(status__in=filters['status']) else: queryset = queryset.filter(status=filters['status']) # Park type filter if 'park_type' in filters and filters['park_type']: if isinstance(filters['park_type'], list): queryset = queryset.filter(park_type__in=filters['park_type']) else: queryset = queryset.filter(park_type=filters['park_type']) # Country filter if 'country' in filters and filters['country']: queryset = queryset.filter(location__country__in=filters['country']) # State filter if 'state' in filters and filters['state']: queryset = queryset.filter(location__state__in=filters['state']) # Opening year range if 'opening_year_min' in filters and filters['opening_year_min']: queryset = queryset.filter(opening_year__gte=filters['opening_year_min']) if 'opening_year_max' in filters and filters['opening_year_max']: queryset = queryset.filter(opening_year__lte=filters['opening_year_max']) # Size range if 'size_min' in filters and filters['size_min']: queryset = queryset.filter(size_acres__gte=filters['size_min']) if 'size_max' in filters and filters['size_max']: queryset = queryset.filter(size_acres__lte=filters['size_max']) # Rating range if 'rating_min' in filters and filters['rating_min']: queryset = queryset.filter(average_rating__gte=filters['rating_min']) if 'rating_max' in filters and filters['rating_max']: queryset = queryset.filter(average_rating__lte=filters['rating_max']) # Ride count range if 'ride_count_min' in filters and filters['ride_count_min']: queryset = queryset.filter(ride_count__gte=filters['ride_count_min']) if 'ride_count_max' in filters and filters['ride_count_max']: queryset = queryset.filter(ride_count__lte=filters['ride_count_max']) # Coaster count range if 'coaster_count_min' in filters and filters['coaster_count_min']: queryset = queryset.filter(coaster_count__gte=filters['coaster_count_min']) if 'coaster_count_max' in filters and filters['coaster_count_max']: queryset = queryset.filter(coaster_count__lte=filters['coaster_count_max']) # Operator filter if 'operator' in filters and filters['operator']: if isinstance(filters['operator'], list): queryset = queryset.filter(operator__slug__in=filters['operator']) else: queryset = queryset.filter(operator__slug=filters['operator']) # Search query if 'search' in filters and filters['search']: search_term = filters['search'].lower() queryset = queryset.filter(search_text__icontains=search_term) return queryset def _get_filter_metadata(self, queryset: models.QuerySet) -> Dict[str, Any]: """Generate filter metadata from the current queryset.""" # Get distinct values for categorical filters with counts countries_data = list( queryset.values('location__country') .exclude(location__country__isnull=True) .annotate(count=models.Count('id')) .order_by('location__country') ) states_data = list( queryset.values('location__state') .exclude(location__state__isnull=True) .annotate(count=models.Count('id')) .order_by('location__state') ) park_types_data = list( queryset.values('park_type') .exclude(park_type__isnull=True) .annotate(count=models.Count('id')) .order_by('park_type') ) statuses_data = list( queryset.values('status') .annotate(count=models.Count('id')) .order_by('status') ) operators_data = list( queryset.select_related('operator') .values('operator__id', 'operator__name', 'operator__slug') .exclude(operator__isnull=True) .annotate(count=models.Count('id')) .order_by('operator__name') ) # Convert to frontend-expected format with value/label/count countries = [ { 'value': item['location__country'], 'label': item['location__country'], 'count': item['count'] } for item in countries_data ] states = [ { 'value': item['location__state'], 'label': item['location__state'], 'count': item['count'] } for item in states_data ] park_types = [ { 'value': item['park_type'], 'label': item['park_type'], 'count': item['count'] } for item in park_types_data ] statuses = [ { 'value': item['status'], 'label': self._get_status_label(item['status']), 'count': item['count'] } for item in statuses_data ] operators = [ { 'value': item['operator__slug'], 'label': item['operator__name'], 'count': item['count'] } for item in operators_data ] # Get ranges for numerical filters aggregates = queryset.aggregate( opening_year_min=models.Min('opening_year'), opening_year_max=models.Max('opening_year'), size_min=models.Min('size_acres'), size_max=models.Max('size_acres'), rating_min=models.Min('average_rating'), rating_max=models.Max('average_rating'), ride_count_min=models.Min('ride_count'), ride_count_max=models.Max('ride_count'), coaster_count_min=models.Min('coaster_count'), coaster_count_max=models.Max('coaster_count'), ) return { 'categorical': { 'countries': countries, 'states': states, 'park_types': park_types, 'statuses': statuses, 'operators': operators, }, 'ranges': { 'opening_year': { 'min': aggregates['opening_year_min'], 'max': aggregates['opening_year_max'], 'step': 1, 'unit': 'year' }, 'size_acres': { 'min': float(aggregates['size_min']) if aggregates['size_min'] else None, 'max': float(aggregates['size_max']) if aggregates['size_max'] else None, 'step': 1.0, 'unit': 'acres' }, 'average_rating': { 'min': float(aggregates['rating_min']) if aggregates['rating_min'] else None, 'max': float(aggregates['rating_max']) if aggregates['rating_max'] else None, 'step': 0.1, 'unit': 'stars' }, 'ride_count': { 'min': aggregates['ride_count_min'], 'max': aggregates['ride_count_max'], 'step': 1, 'unit': 'rides' }, 'coaster_count': { 'min': aggregates['coaster_count_min'], 'max': aggregates['coaster_count_max'], 'step': 1, 'unit': 'coasters' }, }, 'total_count': queryset.count(), } def _get_status_label(self, status: str) -> str: """Convert status code to human-readable label.""" status_labels = { 'OPERATING': 'Operating', 'CLOSED_TEMP': 'Temporarily Closed', 'CLOSED_PERM': 'Permanently Closed', 'UNDER_CONSTRUCTION': 'Under Construction', } if status in status_labels: return status_labels[status] else: raise ValueError(f"Unknown park status: {status}") def _generate_cache_key(self, operation: str, filters: Optional[Dict[str, Any]] = None) -> str: """Generate cache key for the given operation and filters.""" key_parts = [self.CACHE_KEY_PREFIX, operation] if filters: # Create a consistent string representation of filters filter_str = '_'.join(f"{k}:{v}" for k, v in sorted(filters.items()) if v) key_parts.append(filter_str) return '_'.join(key_parts) def invalidate_cache(self, filters: Optional[Dict[str, Any]] = None) -> None: """Invalidate cached data for the given filters.""" # This is a simplified implementation # In production, you might want to use cache versioning or tags cache_keys = [ self._generate_cache_key('initial', filters), self._generate_cache_key('metadata', filters), ] # Also invalidate progressive load caches for offset in range(0, 1000, self.PROGRESSIVE_LOAD_SIZE): cache_keys.append(self._generate_cache_key(f'progressive_{offset}', filters)) cache.delete_many(cache_keys) # Singleton instance smart_park_loader = SmartParkLoader()