#!/usr/bin/env python3
"""
Inspect current data in Supabase database
"""

import psycopg2
import json

def inspect_supabase_data():
    """Inspect all data currently stored in Supabase"""
    print("=" * 70)
    print("SUPABASE DATABASE INSPECTION")
    print("=" * 70)
    
    connection_string = "postgresql://supabase_admin:CzkaYmRvc26Y@localhost:5435/postgres"
    
    try:
        conn = psycopg2.connect(connection_string)
        cursor = conn.cursor()
        
        # Get all tables in vecs schema
        print("📊 All tables in vecs schema:")
        cursor.execute("SELECT table_name FROM information_schema.tables WHERE table_schema = 'vecs';")
        tables = cursor.fetchall()
        table_names = [t[0] for t in tables]
        print(f"   Tables: {table_names}")
        
        for table_name in table_names:
            print(f"\n🔍 Inspecting table: {table_name}")
            try:
                # Get table structure
                cursor.execute(f"""
                    SELECT column_name, data_type, is_nullable
                    FROM information_schema.columns 
                    WHERE table_schema = 'vecs' AND table_name = %s
                    ORDER BY ordinal_position;
                """, (table_name,))
                columns = cursor.fetchall()
                
                print("   Table structure:")
                for col in columns:
                    print(f"      - {col[0]}: {col[1]} (nullable: {col[2]})")
                
                # Get record count
                cursor.execute(f'SELECT COUNT(*) FROM vecs."{table_name}";')
                count = cursor.fetchone()[0]
                print(f"   Record count: {count}")
                
                if count > 0:
                    # Get sample records
                    cursor.execute(f"""
                        SELECT id, metadata, 
                               CASE WHEN vec IS NOT NULL THEN 'Vector present' ELSE 'No vector' END as vec_status
                        FROM vecs."{table_name}" 
                        LIMIT 5;
                    """)
                    records = cursor.fetchall()
                    
                    print("   Sample records:")
                    for i, record in enumerate(records):
                        record_id = record[0]
                        metadata = record[1] if record[1] else {}
                        vec_status = record[2]
                        
                        print(f"      Record {i+1}:")
                        print(f"         ID: {record_id}")
                        print(f"         Vector: {vec_status}")
                        if isinstance(metadata, dict):
                            print(f"         Metadata keys: {list(metadata.keys())}")
                            if 'user_id' in metadata:
                                print(f"         User ID: {metadata['user_id']}")
                            if 'content' in metadata:
                                content = metadata['content'][:100] + "..." if len(str(metadata['content'])) > 100 else metadata['content']
                                print(f"         Content: {content}")
                            if 'created_at' in metadata:
                                print(f"         Created: {metadata['created_at']}")
                        else:
                            print(f"         Metadata: {metadata}")
                        print()
                
            except Exception as e:
                print(f"   ❌ Error inspecting {table_name}: {e}")
        
        # Summary statistics
        print("\n📊 SUMMARY:")
        total_records = 0
        for table_name in table_names:
            try:
                cursor.execute(f'SELECT COUNT(*) FROM vecs."{table_name}";')
                count = cursor.fetchone()[0]
                total_records += count
                print(f"   {table_name}: {count} records")
            except:
                print(f"   {table_name}: Error getting count")
        
        print(f"   Total records across all tables: {total_records}")
        
        # Check for different users
        print("\n👥 USER ANALYSIS:")
        for table_name in table_names:
            try:
                cursor.execute(f"""
                    SELECT metadata->>'user_id' as user_id, COUNT(*) as count
                    FROM vecs."{table_name}" 
                    WHERE metadata->>'user_id' IS NOT NULL
                    GROUP BY metadata->>'user_id'
                    ORDER BY count DESC;
                """)
                users = cursor.fetchall()
                
                if users:
                    print(f"   {table_name} users:")
                    for user, count in users:
                        print(f"      - {user}: {count} memories")
                else:
                    print(f"   {table_name}: No user data found")
            except Exception as e:
                print(f"   Error analyzing users in {table_name}: {e}")
        
        cursor.close()
        conn.close()
        
        print("\n" + "=" * 70)
        print("🎉 DATABASE INSPECTION COMPLETE")
        print("=" * 70)
        
    except Exception as e:
        print(f"❌ Inspection failed: {str(e)}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    inspect_supabase_data()