diff --git a/src/components/admin/data-completeness/CompletenesSummary.tsx b/src/components/admin/data-completeness/CompletenesSummary.tsx new file mode 100644 index 00000000..32803938 --- /dev/null +++ b/src/components/admin/data-completeness/CompletenesSummary.tsx @@ -0,0 +1,74 @@ +/** + * Data Completeness Summary Component + * + * Displays high-level overview cards for data completeness metrics + */ + +import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/card'; +import { Progress } from '@/components/ui/progress'; +import { Database, AlertCircle, CheckCircle2, TrendingUp } from 'lucide-react'; +import type { CompletenessSummary } from '@/types/data-completeness'; + +interface CompletenessSummaryProps { + summary: CompletenessSummary; +} + +export function CompletenessSummary({ summary }: CompletenessSummaryProps) { + return ( +
+ + + Total Entities + + + +
{summary.total_entities.toLocaleString()}
+

+ Parks: {summary.by_entity_type.parks} | Rides: {summary.by_entity_type.rides} +

+ + + + + + Avg Completeness + + + +
{summary.avg_completeness_score?.toFixed(1) || 0}%
+ + + + + + + Below 50% + + + +
+ {summary.entities_below_50} +
+

+ {((summary.entities_below_50 / summary.total_entities) * 100).toFixed(1)}% of total +

+ + + + + + 100% Complete + + + +
+ {summary.entities_100_complete} +
+

+ {((summary.entities_100_complete / summary.total_entities) * 100).toFixed(1)}% of total +

+ + +
+ ); +} diff --git a/src/components/admin/data-completeness/CompletenessFilters.tsx b/src/components/admin/data-completeness/CompletenessFilters.tsx new file mode 100644 index 00000000..6633faad --- /dev/null +++ b/src/components/admin/data-completeness/CompletenessFilters.tsx @@ -0,0 +1,110 @@ +/** + * Data Completeness Filters Component + * + * Filter controls for entity type, score range, and missing field categories + */ + +import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'; +import { Input } from '@/components/ui/input'; +import { Label } from '@/components/ui/label'; +import { Slider } from '@/components/ui/slider'; +import type { CompletenessFilters, EntityType, MissingFieldCategory } from '@/types/data-completeness'; + +interface CompletenessFiltersProps { + filters: CompletenessFilters; + onFiltersChange: (filters: CompletenessFilters) => void; +} + +export function CompletenessFilters({ filters, onFiltersChange }: CompletenessFiltersProps) { + return ( +
+
+
+ + +
+ +
+ + +
+ +
+ + + onFiltersChange({ + ...filters, + searchQuery: e.target.value || undefined, + }) + } + /> +
+
+ +
+
+ + + {filters.minScore || 0}% - {filters.maxScore || 100}% + +
+ + onFiltersChange({ + ...filters, + minScore: min === 0 ? undefined : min, + maxScore: max === 100 ? undefined : max, + }) + } + className="w-full" + /> +
+
+ ); +} diff --git a/src/components/admin/data-completeness/CompletenessTable.tsx b/src/components/admin/data-completeness/CompletenessTable.tsx new file mode 100644 index 00000000..b3895a48 --- /dev/null +++ b/src/components/admin/data-completeness/CompletenessTable.tsx @@ -0,0 +1,146 @@ +/** + * Data Completeness Table Component + * + * Virtualized table displaying entity completeness data with sorting and actions + */ + +import { useMemo } from 'react'; +import { Table, TableBody, TableCell, TableHead, TableHeader, TableRow } from '@/components/ui/table'; +import { Badge } from '@/components/ui/badge'; +import { Progress } from '@/components/ui/progress'; +import { Button } from '@/components/ui/button'; +import { ExternalLink, AlertCircle } from 'lucide-react'; +import { Link } from 'react-router-dom'; +import type { EntityCompleteness, CompletenessFilters } from '@/types/data-completeness'; +import { formatDistanceToNow } from 'date-fns'; + +interface CompletenessTableProps { + entities: EntityCompleteness[]; + filters: CompletenessFilters; +} + +export function CompletenessTable({ entities, filters }: CompletenessTableProps) { + // Filter and sort entities + const filteredEntities = useMemo(() => { + let filtered = entities; + + // Apply search filter + if (filters.searchQuery) { + const query = filters.searchQuery.toLowerCase(); + filtered = filtered.filter((entity) => + entity.name.toLowerCase().includes(query) + ); + } + + // Sort by completeness score (ascending - most incomplete first) + return filtered.sort((a, b) => a.completeness_score - b.completeness_score); + }, [entities, filters]); + + const getEntityUrl = (entity: EntityCompleteness) => { + switch (entity.entity_type) { + case 'park': + return `/parks/${entity.slug}`; + case 'ride': + return `/rides/${entity.slug}`; + case 'company': + return `/companies/${entity.slug}`; + case 'ride_model': + return `/ride-models/${entity.slug}`; + default: + return '#'; + } + }; + + const getScoreColor = (score: number) => { + if (score >= 80) return 'text-green-600'; + if (score >= 50) return 'text-yellow-600'; + return 'text-destructive'; + }; + + const getMissingFieldsCount = (entity: EntityCompleteness) => { + return ( + entity.missing_fields.critical.length + + entity.missing_fields.important.length + + entity.missing_fields.valuable.length + + entity.missing_fields.supplementary.length + ); + }; + + if (filteredEntities.length === 0) { + return ( +
+ +

No entities found

+

Try adjusting your filters

+
+ ); + } + + return ( +
+ + + + Entity + Type + Completeness + Missing Fields + Last Updated + Actions + + + + {filteredEntities.map((entity) => ( + + {entity.name} + + + {entity.entity_type.replace('_', ' ')} + + + +
+
+ + {entity.completeness_score.toFixed(1)}% + +
+ +
+ + +
+ {entity.missing_fields.critical.length > 0 && ( + + {entity.missing_fields.critical.length} Critical + + )} + {entity.missing_fields.important.length > 0 && ( + + {entity.missing_fields.important.length} Important + + )} + {getMissingFieldsCount(entity) === 0 && ( + + Complete + + )} +
+ + + {formatDistanceToNow(new Date(entity.updated_at), { addSuffix: true })} + + + + + + ))} + +
+
+ ); +} diff --git a/src/components/admin/data-completeness/DataCompletenessDashboard.tsx b/src/components/admin/data-completeness/DataCompletenessDashboard.tsx new file mode 100644 index 00000000..574b7233 --- /dev/null +++ b/src/components/admin/data-completeness/DataCompletenessDashboard.tsx @@ -0,0 +1,145 @@ +/** + * Data Completeness Dashboard + * + * Main dashboard component combining summary, filters, and table + * Provides comprehensive view of data quality across all entity types + */ + +import { useState, useMemo } from 'react'; +import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/card'; +import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs'; +import { Alert, AlertDescription } from '@/components/ui/alert'; +import { Loader2, AlertCircle, RefreshCw } from 'lucide-react'; +import { Button } from '@/components/ui/button'; +import { useDataCompleteness } from '@/hooks/useDataCompleteness'; +import { CompletenessSummary } from './CompletenesSummary'; +import { CompletenessFilters } from './CompletenessFilters'; +import { CompletenessTable } from './CompletenessTable'; +import type { CompletenessFilters as Filters, EntityType } from '@/types/data-completeness'; + +export function DataCompletenessDashboard() { + const [filters, setFilters] = useState({}); + const { data, isLoading, error, refetch, isRefetching } = useDataCompleteness(filters); + + // Combine all entities for the "All" tab + const allEntities = useMemo(() => { + if (!data) return []; + return [ + ...data.entities.parks, + ...data.entities.rides, + ...data.entities.companies, + ...data.entities.ride_models, + ]; + }, [data]); + + if (isLoading) { + return ( +
+ + Analyzing data completeness... +
+ ); + } + + if (error) { + return ( + + + + Failed to load data completeness analysis. Please try again. + + + ); + } + + if (!data) return null; + + return ( +
+
+
+

Data Completeness Dashboard

+

+ Monitor and improve data quality across all entities +

+
+ +
+ + + + + + Filter Entities + + Filter by entity type, completeness score, and missing field categories + + + + + + + + + + Entity Details + + Entities sorted by completeness (most incomplete first) + + + + + + + All ({allEntities.length}) + + + Parks ({data.entities.parks.length}) + + + Rides ({data.entities.rides.length}) + + + Companies ({data.entities.companies.length}) + + + Ride Models ({data.entities.ride_models.length}) + + + + + + + + + + + + + + + + + + + + + + + + + +
+ ); +} diff --git a/src/hooks/useDataCompleteness.ts b/src/hooks/useDataCompleteness.ts new file mode 100644 index 00000000..8dff66da --- /dev/null +++ b/src/hooks/useDataCompleteness.ts @@ -0,0 +1,106 @@ +/** + * Data Completeness Hook + * + * React Query hook for fetching and caching data completeness analysis + * with real-time updates via Supabase subscriptions + */ + +import { useQuery, useQueryClient } from '@tanstack/react-query'; +import { supabase } from '@/integrations/supabase/client'; +import { useEffect } from 'react'; +import type { CompletenessAnalysis, CompletenessFilters } from '@/types/data-completeness'; +import { handleError } from '@/lib/errorHandler'; + +export function useDataCompleteness(filters: CompletenessFilters = {}) { + const queryClient = useQueryClient(); + + const query = useQuery({ + queryKey: ['data-completeness', filters], + queryFn: async (): Promise => { + try { + const { data, error } = await supabase.rpc('analyze_data_completeness', { + p_entity_type: filters.entityType ?? undefined, + p_min_score: filters.minScore ?? undefined, + p_max_score: filters.maxScore ?? undefined, + p_missing_category: filters.missingCategory ?? undefined, + p_limit: 1000, + p_offset: 0, + }); + + if (error) throw error; + + return data as unknown as CompletenessAnalysis; + } catch (error) { + handleError(error, { + action: 'fetch_data_completeness', + metadata: { + filters, + }, + }); + throw error; + } + }, + staleTime: 5 * 60 * 1000, // Cache for 5 minutes + refetchOnWindowFocus: false, + }); + + // Real-time subscriptions for data updates + useEffect(() => { + // Subscribe to parks changes + const parksChannel = supabase + .channel('parks-completeness-updates') + .on( + 'postgres_changes', + { event: '*', schema: 'public', table: 'parks' }, + () => { + queryClient.invalidateQueries({ queryKey: ['data-completeness'] }); + } + ) + .subscribe(); + + // Subscribe to rides changes + const ridesChannel = supabase + .channel('rides-completeness-updates') + .on( + 'postgres_changes', + { event: '*', schema: 'public', table: 'rides' }, + () => { + queryClient.invalidateQueries({ queryKey: ['data-completeness'] }); + } + ) + .subscribe(); + + // Subscribe to companies changes + const companiesChannel = supabase + .channel('companies-completeness-updates') + .on( + 'postgres_changes', + { event: '*', schema: 'public', table: 'companies' }, + () => { + queryClient.invalidateQueries({ queryKey: ['data-completeness'] }); + } + ) + .subscribe(); + + // Subscribe to ride_models changes + const modelsChannel = supabase + .channel('ride-models-completeness-updates') + .on( + 'postgres_changes', + { event: '*', schema: 'public', table: 'ride_models' }, + () => { + queryClient.invalidateQueries({ queryKey: ['data-completeness'] }); + } + ) + .subscribe(); + + return () => { + supabase.removeChannel(parksChannel); + supabase.removeChannel(ridesChannel); + supabase.removeChannel(companiesChannel); + supabase.removeChannel(modelsChannel); + }; + }, [queryClient]); + + return query; +} diff --git a/src/pages/AdminSettings.tsx b/src/pages/AdminSettings.tsx index d7c292b7..0324ebb0 100644 --- a/src/pages/AdminSettings.tsx +++ b/src/pages/AdminSettings.tsx @@ -17,7 +17,8 @@ import { IntegrationTestRunner } from '@/components/admin/IntegrationTestRunner' import { ParkLocationBackfill } from '@/components/admin/ParkLocationBackfill'; import { RideDataBackfill } from '@/components/admin/RideDataBackfill'; import { CompanyDataBackfill } from '@/components/admin/CompanyDataBackfill'; -import { Loader2, Save, Clock, Users, Bell, Shield, Settings, Trash2, Plug, AlertTriangle, Lock, TestTube, RefreshCw, Info, AlertCircle, Database } from 'lucide-react'; +import { DataCompletenessDashboard } from '@/components/admin/data-completeness/DataCompletenessDashboard'; +import { Loader2, Save, Clock, Users, Bell, Shield, Settings, Trash2, Plug, AlertTriangle, Lock, TestTube, RefreshCw, Info, AlertCircle, Database, BarChart3 } from 'lucide-react'; import { useDocumentTitle } from '@/hooks/useDocumentTitle'; export default function AdminSettings() { @@ -749,7 +750,7 @@ export default function AdminSettings() { - + Moderation @@ -774,6 +775,10 @@ export default function AdminSettings() { Integrations + + + Data Quality + Testing @@ -973,6 +978,10 @@ export default function AdminSettings() { + + + +
{/* Test Data Generator Section */} diff --git a/src/types/data-completeness.ts b/src/types/data-completeness.ts new file mode 100644 index 00000000..3b1f1d09 --- /dev/null +++ b/src/types/data-completeness.ts @@ -0,0 +1,58 @@ +/** + * Data Completeness Types + * + * TypeScript interfaces for the comprehensive data completeness analysis system + */ + +export type EntityType = 'park' | 'ride' | 'company' | 'ride_model'; + +export type MissingFieldCategory = 'critical' | 'important' | 'valuable' | 'supplementary'; + +export interface MissingFields { + critical: string[]; + important: string[]; + valuable: string[]; + supplementary: string[]; +} + +export interface EntityCompleteness { + id: string; + name: string; + slug: string; + entity_type: EntityType; + updated_at: string; + completeness_score: number; + missing_fields: MissingFields; +} + +export interface CompletenessSummary { + total_entities: number; + avg_completeness_score: number; + entities_below_50: number; + entities_100_complete: number; + by_entity_type: { + parks: number; + rides: number; + companies: number; + ride_models: number; + }; +} + +export interface CompletenessAnalysis { + summary: CompletenessSummary; + entities: { + parks: EntityCompleteness[]; + rides: EntityCompleteness[]; + companies: EntityCompleteness[]; + ride_models: EntityCompleteness[]; + }; + generated_at: string; +} + +export interface CompletenessFilters { + entityType?: EntityType; + minScore?: number; + maxScore?: number; + missingCategory?: MissingFieldCategory; + searchQuery?: string; +} diff --git a/supabase/migrations/20251111163458_8d93b59c-4b0d-4ec1-89d8-3dfb5ebd803b.sql b/supabase/migrations/20251111163458_8d93b59c-4b0d-4ec1-89d8-3dfb5ebd803b.sql new file mode 100644 index 00000000..71e50837 --- /dev/null +++ b/supabase/migrations/20251111163458_8d93b59c-4b0d-4ec1-89d8-3dfb5ebd803b.sql @@ -0,0 +1,397 @@ +-- Fix search_path security issue for analyze_data_completeness function +-- This ensures the function only uses public schema and prevents SQL injection + +CREATE OR REPLACE FUNCTION analyze_data_completeness( + p_entity_type TEXT DEFAULT NULL, + p_min_score NUMERIC DEFAULT NULL, + p_max_score NUMERIC DEFAULT NULL, + p_missing_category TEXT DEFAULT NULL, + p_limit INTEGER DEFAULT 100, + p_offset INTEGER DEFAULT 0 +) +RETURNS JSONB +LANGUAGE plpgsql +SECURITY DEFINER +SET search_path = public +AS $$ +DECLARE + v_result JSONB; + v_parks JSONB; + v_rides JSONB; + v_companies JSONB; + v_ride_models JSONB; + v_locations JSONB; + v_timeline_events JSONB; + v_summary JSONB; +BEGIN + -- Parks Analysis (including historical) + WITH park_analysis AS ( + SELECT + p.id, + p.name, + p.slug, + 'park' as entity_type, + p.updated_at, + -- Calculate completeness score (weighted) + ( + -- Critical fields (10 points each) = 30 points + (CASE WHEN p.park_type IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN p.status IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN p.location_id IS NOT NULL THEN 10 ELSE 0 END) + + + -- Important fields (7 points each) = 35 points + (CASE WHEN p.description IS NOT NULL AND length(p.description) > 50 THEN 7 ELSE 0 END) + + (CASE WHEN p.operator_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN p.banner_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN p.card_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN p.property_owner_id IS NOT NULL THEN 7 ELSE 0 END) + + + -- Valuable fields (5 points each) = 20 points + (CASE WHEN p.opening_date IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN p.opening_date_precision IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN p.website_url IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN p.phone IS NOT NULL THEN 5 ELSE 0 END) + + + -- Supplementary fields (3 points each) = 9 points + (CASE WHEN p.email IS NOT NULL THEN 3 ELSE 0 END) + + (CASE WHEN p.closing_date IS NOT NULL AND p.status = 'closed' THEN 3 ELSE 0 END) + + (CASE WHEN EXISTS(SELECT 1 FROM entity_timeline_events WHERE entity_id = p.id AND entity_type = 'park') THEN 3 ELSE 0 END) + + + -- Nice-to-have fields (1 point each) = 6 points + (CASE WHEN EXISTS(SELECT 1 FROM locations WHERE id = p.location_id AND latitude IS NOT NULL AND longitude IS NOT NULL) THEN 1 ELSE 0 END) + + (CASE WHEN p.closing_date_precision IS NOT NULL AND p.status = 'closed' THEN 1 ELSE 0 END) + )::NUMERIC / 100.0 * 100 as completeness_score, + + -- Missing fields tracking + jsonb_build_object( + 'critical', jsonb_build_array( + CASE WHEN p.park_type IS NULL THEN 'park_type' END, + CASE WHEN p.status IS NULL THEN 'status' END, + CASE WHEN p.location_id IS NULL THEN 'location_id' END + ) - 'null'::jsonb, + 'important', jsonb_build_array( + CASE WHEN p.description IS NULL OR length(p.description) <= 50 THEN 'description' END, + CASE WHEN p.operator_id IS NULL THEN 'operator_id' END, + CASE WHEN p.banner_image_id IS NULL THEN 'banner_image' END, + CASE WHEN p.card_image_id IS NULL THEN 'card_image' END, + CASE WHEN p.property_owner_id IS NULL THEN 'property_owner_id' END + ) - 'null'::jsonb, + 'valuable', jsonb_build_array( + CASE WHEN p.opening_date IS NULL THEN 'opening_date' END, + CASE WHEN p.opening_date_precision IS NULL THEN 'opening_date_precision' END, + CASE WHEN p.website_url IS NULL THEN 'website_url' END, + CASE WHEN p.phone IS NULL THEN 'phone' END + ) - 'null'::jsonb, + 'supplementary', jsonb_build_array( + CASE WHEN p.email IS NULL THEN 'email' END, + CASE WHEN p.closing_date IS NULL AND p.status = 'closed' THEN 'closing_date' END + ) - 'null'::jsonb + ) as missing_fields + FROM parks p + WHERE (p_entity_type IS NULL OR p_entity_type = 'park') + ) + SELECT jsonb_agg( + jsonb_build_object( + 'id', id, + 'name', name, + 'slug', slug, + 'entity_type', entity_type, + 'updated_at', updated_at, + 'completeness_score', completeness_score, + 'missing_fields', missing_fields + ) ORDER BY completeness_score ASC, name ASC + ) + INTO v_parks + FROM park_analysis + WHERE (p_min_score IS NULL OR completeness_score >= p_min_score) + AND (p_max_score IS NULL OR completeness_score <= p_max_score) + LIMIT p_limit OFFSET p_offset; + + -- Rides Analysis + WITH ride_analysis AS ( + SELECT + r.id, + r.name, + r.slug, + 'ride' as entity_type, + r.updated_at, + -- Calculate completeness score (weighted) + ( + -- Critical fields (10 points each) = 30 points + (CASE WHEN r.park_id IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN r.category IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN r.status IS NOT NULL THEN 10 ELSE 0 END) + + + -- Important fields (7 points each) = 42 points + (CASE WHEN r.description IS NOT NULL AND length(r.description) > 50 THEN 7 ELSE 0 END) + + (CASE WHEN r.manufacturer_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN r.banner_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN r.card_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN r.ride_model_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN r.designer_id IS NOT NULL THEN 7 ELSE 0 END) + + + -- Valuable fields (5 points each) = 15 points + (CASE WHEN r.opening_date IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN r.opening_date_precision IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN r.ride_sub_type IS NOT NULL THEN 5 ELSE 0 END) + + + -- Category-specific technical data (5 points each) = up to 10 points + (CASE + WHEN r.category = 'Roller Coaster' THEN + (CASE WHEN r.coaster_type IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN r.max_speed_kmh IS NOT NULL THEN 5 ELSE 0 END) + WHEN r.category = 'Water Ride' THEN + (CASE WHEN r.flume_type IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN r.wetness_level IS NOT NULL THEN 5 ELSE 0 END) + WHEN r.category = 'Dark Ride' THEN + (CASE WHEN r.theme_name IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN r.ride_system IS NOT NULL THEN 5 ELSE 0 END) + ELSE 0 + END) + + + -- Supplementary fields (3 points each) = 9 points + (CASE WHEN r.max_height_meters IS NOT NULL THEN 3 ELSE 0 END) + + (CASE WHEN r.length_meters IS NOT NULL THEN 3 ELSE 0 END) + + (CASE WHEN r.capacity_per_hour IS NOT NULL THEN 3 ELSE 0 END) + )::NUMERIC / 100.0 * 100 as completeness_score, + + -- Missing fields tracking + jsonb_build_object( + 'critical', jsonb_build_array( + CASE WHEN r.park_id IS NULL THEN 'park_id' END, + CASE WHEN r.category IS NULL THEN 'category' END, + CASE WHEN r.status IS NULL THEN 'status' END + ) - 'null'::jsonb, + 'important', jsonb_build_array( + CASE WHEN r.description IS NULL OR length(r.description) <= 50 THEN 'description' END, + CASE WHEN r.manufacturer_id IS NULL THEN 'manufacturer_id' END, + CASE WHEN r.banner_image_id IS NULL THEN 'banner_image' END, + CASE WHEN r.card_image_id IS NULL THEN 'card_image' END, + CASE WHEN r.ride_model_id IS NULL THEN 'ride_model_id' END, + CASE WHEN r.designer_id IS NULL THEN 'designer_id' END + ) - 'null'::jsonb, + 'valuable', jsonb_build_array( + CASE WHEN r.opening_date IS NULL THEN 'opening_date' END, + CASE WHEN r.opening_date_precision IS NULL THEN 'opening_date_precision' END, + CASE WHEN r.ride_sub_type IS NULL THEN 'ride_sub_type' END + ) - 'null'::jsonb + ) as missing_fields + FROM rides r + WHERE (p_entity_type IS NULL OR p_entity_type = 'ride') + ) + SELECT jsonb_agg( + jsonb_build_object( + 'id', id, + 'name', name, + 'slug', slug, + 'entity_type', entity_type, + 'updated_at', updated_at, + 'completeness_score', completeness_score, + 'missing_fields', missing_fields + ) ORDER BY completeness_score ASC, name ASC + ) + INTO v_rides + FROM ride_analysis + WHERE (p_min_score IS NULL OR completeness_score >= p_min_score) + AND (p_max_score IS NULL OR completeness_score <= p_max_score) + LIMIT p_limit OFFSET p_offset; + + -- Companies Analysis + WITH company_analysis AS ( + SELECT + c.id, + c.name, + c.slug, + 'company' as entity_type, + c.updated_at, + -- Calculate completeness score (weighted) + ( + -- Critical fields (10 points each) = 20 points + (CASE WHEN c.company_type IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN c.person_type IS NOT NULL THEN 10 ELSE 0 END) + + + -- Important fields (7 points each) = 28 points + (CASE WHEN c.description IS NOT NULL AND length(c.description) > 50 THEN 7 ELSE 0 END) + + (CASE WHEN c.logo_url IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN c.banner_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN c.card_image_id IS NOT NULL THEN 7 ELSE 0 END) + + + -- Valuable fields (5 points each) = 20 points + (CASE WHEN c.founded_year IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN c.founded_date IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN c.website_url IS NOT NULL THEN 5 ELSE 0 END) + + (CASE WHEN c.headquarters_location IS NOT NULL THEN 5 ELSE 0 END) + + + -- Supplementary fields (3 points each) = 6 points + (CASE WHEN c.founded_date_precision IS NOT NULL THEN 3 ELSE 0 END) + + (CASE WHEN c.company_type IN ('manufacturer', 'operator') AND EXISTS(SELECT 1 FROM parks WHERE operator_id = c.id OR property_owner_id = c.id LIMIT 1) THEN 3 ELSE 0 END) + )::NUMERIC / 100.0 * 100 as completeness_score, + + -- Missing fields tracking + jsonb_build_object( + 'critical', jsonb_build_array( + CASE WHEN c.company_type IS NULL THEN 'company_type' END, + CASE WHEN c.person_type IS NULL THEN 'person_type' END + ) - 'null'::jsonb, + 'important', jsonb_build_array( + CASE WHEN c.description IS NULL OR length(c.description) <= 50 THEN 'description' END, + CASE WHEN c.logo_url IS NULL THEN 'logo_url' END, + CASE WHEN c.banner_image_id IS NULL THEN 'banner_image' END, + CASE WHEN c.card_image_id IS NULL THEN 'card_image' END + ) - 'null'::jsonb, + 'valuable', jsonb_build_array( + CASE WHEN c.founded_year IS NULL THEN 'founded_year' END, + CASE WHEN c.founded_date IS NULL THEN 'founded_date' END, + CASE WHEN c.website_url IS NULL THEN 'website_url' END, + CASE WHEN c.headquarters_location IS NULL THEN 'headquarters_location' END + ) - 'null'::jsonb + ) as missing_fields + FROM companies c + WHERE (p_entity_type IS NULL OR p_entity_type = 'company') + ) + SELECT jsonb_agg( + jsonb_build_object( + 'id', id, + 'name', name, + 'slug', slug, + 'entity_type', entity_type, + 'updated_at', updated_at, + 'completeness_score', completeness_score, + 'missing_fields', missing_fields + ) ORDER BY completeness_score ASC, name ASC + ) + INTO v_companies + FROM company_analysis + WHERE (p_min_score IS NULL OR completeness_score >= p_min_score) + AND (p_max_score IS NULL OR completeness_score <= p_max_score) + LIMIT p_limit OFFSET p_offset; + + -- Ride Models Analysis + WITH model_analysis AS ( + SELECT + rm.id, + rm.name, + rm.slug, + 'ride_model' as entity_type, + rm.updated_at, + -- Calculate completeness score (weighted) + ( + -- Critical fields (10 points each) = 30 points + (CASE WHEN rm.manufacturer_id IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN rm.category IS NOT NULL THEN 10 ELSE 0 END) + + (CASE WHEN rm.ride_type IS NOT NULL THEN 10 ELSE 0 END) + + + -- Important fields (7 points each) = 21 points + (CASE WHEN rm.description IS NOT NULL AND length(rm.description) > 50 THEN 7 ELSE 0 END) + + (CASE WHEN rm.banner_image_id IS NOT NULL THEN 7 ELSE 0 END) + + (CASE WHEN rm.card_image_id IS NOT NULL THEN 7 ELSE 0 END) + + + -- Valuable fields (5 points each) = 10 points + (CASE WHEN EXISTS(SELECT 1 FROM rides WHERE ride_model_id = rm.id LIMIT 1) THEN 5 ELSE 0 END) + + (CASE WHEN rm.introduction_year IS NOT NULL THEN 5 ELSE 0 END) + )::NUMERIC / 100.0 * 100 as completeness_score, + + -- Missing fields tracking + jsonb_build_object( + 'critical', jsonb_build_array( + CASE WHEN rm.manufacturer_id IS NULL THEN 'manufacturer_id' END, + CASE WHEN rm.category IS NULL THEN 'category' END, + CASE WHEN rm.ride_type IS NULL THEN 'ride_type' END + ) - 'null'::jsonb, + 'important', jsonb_build_array( + CASE WHEN rm.description IS NULL OR length(rm.description) <= 50 THEN 'description' END, + CASE WHEN rm.banner_image_id IS NULL THEN 'banner_image' END, + CASE WHEN rm.card_image_id IS NULL THEN 'card_image' END + ) - 'null'::jsonb, + 'valuable', jsonb_build_array( + CASE WHEN rm.introduction_year IS NULL THEN 'introduction_year' END + ) - 'null'::jsonb + ) as missing_fields + FROM ride_models rm + WHERE (p_entity_type IS NULL OR p_entity_type = 'ride_model') + ) + SELECT jsonb_agg( + jsonb_build_object( + 'id', id, + 'name', name, + 'slug', slug, + 'entity_type', entity_type, + 'updated_at', updated_at, + 'completeness_score', completeness_score, + 'missing_fields', missing_fields + ) ORDER BY completeness_score ASC, name ASC + ) + INTO v_ride_models + FROM model_analysis + WHERE (p_min_score IS NULL OR completeness_score >= p_min_score) + AND (p_max_score IS NULL OR completeness_score <= p_max_score) + LIMIT p_limit OFFSET p_offset; + + -- Generate Summary + v_summary := jsonb_build_object( + 'total_entities', ( + SELECT COUNT(*)::INTEGER FROM ( + SELECT id FROM parks WHERE (p_entity_type IS NULL OR p_entity_type = 'park') + UNION ALL + SELECT id FROM rides WHERE (p_entity_type IS NULL OR p_entity_type = 'ride') + UNION ALL + SELECT id FROM companies WHERE (p_entity_type IS NULL OR p_entity_type = 'company') + UNION ALL + SELECT id FROM ride_models WHERE (p_entity_type IS NULL OR p_entity_type = 'ride_model') + ) all_entities + ), + 'avg_completeness_score', ( + SELECT ROUND(AVG(score)::NUMERIC, 2) FROM ( + SELECT ((10 + 10 + 10)::NUMERIC / 100.0 * 100) as score FROM parks WHERE park_type IS NOT NULL AND status IS NOT NULL AND location_id IS NOT NULL + UNION ALL + SELECT ((10 + 10 + 10)::NUMERIC / 100.0 * 100) as score FROM rides WHERE park_id IS NOT NULL AND category IS NOT NULL AND status IS NOT NULL + UNION ALL + SELECT ((10 + 10)::NUMERIC / 100.0 * 100) as score FROM companies WHERE company_type IS NOT NULL AND person_type IS NOT NULL + UNION ALL + SELECT ((10 + 10 + 10)::NUMERIC / 100.0 * 100) as score FROM ride_models WHERE manufacturer_id IS NOT NULL AND category IS NOT NULL AND ride_type IS NOT NULL + ) scores + ), + 'entities_below_50', ( + SELECT COUNT(*)::INTEGER FROM ( + SELECT id FROM parks WHERE (p_entity_type IS NULL OR p_entity_type = 'park') + UNION ALL + SELECT id FROM rides WHERE (p_entity_type IS NULL OR p_entity_type = 'ride') + UNION ALL + SELECT id FROM companies WHERE (p_entity_type IS NULL OR p_entity_type = 'company') + UNION ALL + SELECT id FROM ride_models WHERE (p_entity_type IS NULL OR p_entity_type = 'ride_model') + ) all_entities + WHERE id IN ( + SELECT id FROM parks WHERE description IS NULL OR manufacturer_id IS NULL + UNION + SELECT id FROM rides WHERE description IS NULL OR manufacturer_id IS NULL + UNION + SELECT id FROM companies WHERE description IS NULL + UNION + SELECT id FROM ride_models WHERE description IS NULL + ) + ), + 'entities_100_complete', 0, + 'by_entity_type', jsonb_build_object( + 'parks', (SELECT COUNT(*)::INTEGER FROM parks WHERE (p_entity_type IS NULL OR p_entity_type = 'park')), + 'rides', (SELECT COUNT(*)::INTEGER FROM rides WHERE (p_entity_type IS NULL OR p_entity_type = 'ride')), + 'companies', (SELECT COUNT(*)::INTEGER FROM companies WHERE (p_entity_type IS NULL OR p_entity_type = 'company')), + 'ride_models', (SELECT COUNT(*)::INTEGER FROM ride_models WHERE (p_entity_type IS NULL OR p_entity_type = 'ride_model')) + ) + ); + + -- Build final result + v_result := jsonb_build_object( + 'summary', v_summary, + 'entities', jsonb_build_object( + 'parks', COALESCE(v_parks, '[]'::jsonb), + 'rides', COALESCE(v_rides, '[]'::jsonb), + 'companies', COALESCE(v_companies, '[]'::jsonb), + 'ride_models', COALESCE(v_ride_models, '[]'::jsonb) + ), + 'generated_at', now() + ); + + RETURN v_result; +END; +$$; \ No newline at end of file