397 lines
14 KiB
Python
397 lines
14 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Demo Retail Customer Seeding Script for Orders Service
|
|
Creates walk-in customers for child retail outlets
|
|
|
|
This script runs as a Kubernetes init job inside the orders-service container.
|
|
It populates child retail tenants with realistic customer profiles.
|
|
|
|
Usage:
|
|
python /app/scripts/demo/seed_demo_customers_retail.py
|
|
|
|
Environment Variables Required:
|
|
ORDERS_DATABASE_URL - PostgreSQL connection string for orders database
|
|
DEMO_MODE - Set to 'production' for production seeding
|
|
LOG_LEVEL - Logging level (default: INFO)
|
|
"""
|
|
|
|
import asyncio
|
|
import uuid
|
|
import sys
|
|
import os
|
|
import random
|
|
from datetime import datetime, timezone, timedelta
|
|
from pathlib import Path
|
|
|
|
# Add app to path
|
|
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
|
# Add shared to path for demo utilities
|
|
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent.parent))
|
|
|
|
from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine
|
|
from sqlalchemy.orm import sessionmaker
|
|
from sqlalchemy import select
|
|
import structlog
|
|
|
|
from shared.utils.demo_dates import BASE_REFERENCE_DATE
|
|
|
|
from app.models.customer import Customer
|
|
|
|
# Configure logging
|
|
structlog.configure(
|
|
processors=[
|
|
structlog.stdlib.add_log_level,
|
|
structlog.processors.TimeStamper(fmt="iso"),
|
|
structlog.dev.ConsoleRenderer()
|
|
]
|
|
)
|
|
|
|
logger = structlog.get_logger()
|
|
|
|
# Fixed Demo Tenant IDs (must match tenant service)
|
|
DEMO_TENANT_CHILD_1 = uuid.UUID("d4e5f6a7-b8c9-40d1-e2f3-a4b5c6d7e8f9") # Madrid Centro
|
|
DEMO_TENANT_CHILD_2 = uuid.UUID("e5f6a7b8-c9d0-41e2-f3a4-b5c6d7e8f9a0") # Barcelona Gràcia
|
|
DEMO_TENANT_CHILD_3 = uuid.UUID("f6a7b8c9-d0e1-42f3-a4b5-c6d7e8f9a0b1") # Valencia Ruzafa
|
|
|
|
# Spanish first names and surnames for realistic customer generation
|
|
FIRST_NAMES = [
|
|
"Carmen", "María", "José", "Antonio", "Ana", "Manuel", "Francisca", "David",
|
|
"Laura", "Daniel", "Marta", "Carlos", "Isabel", "Javier", "Lucía", "Miguel",
|
|
"Sofía", "Francisco", "Elena", "Rafael", "Paula", "Pedro", "Cristina", "Luis",
|
|
"Sara", "Fernando", "Raquel", "Alberto", "Beatriz", "Alejandro", "Natalia",
|
|
"Pablo", "Silvia", "Jorge", "Mónica", "Sergio", "Andrea", "Rubén", "Virginia",
|
|
"Diego", "Pilar", "Iván", "Teresa", "Adrián", "Nuria", "Óscar", "Patricia"
|
|
]
|
|
|
|
SURNAMES = [
|
|
"García", "Rodríguez", "González", "Fernández", "López", "Martínez", "Sánchez",
|
|
"Pérez", "Gómez", "Martín", "Jiménez", "Ruiz", "Hernández", "Díaz", "Moreno",
|
|
"Muñoz", "Álvarez", "Romero", "Alonso", "Gutiérrez", "Navarro", "Torres",
|
|
"Domínguez", "Vázquez", "Ramos", "Gil", "Ramírez", "Serrano", "Blanco", "Suárez",
|
|
"Molina", "Castro", "Ortega", "Delgado", "Ortiz", "Morales", "Jiménez", "Núñez",
|
|
"Medina", "Aguilar"
|
|
]
|
|
|
|
# Customer segment distribution for retail
|
|
CUSTOMER_SEGMENTS = [
|
|
("regular", 0.60), # 60% regular customers
|
|
("loyal", 0.25), # 25% loyal customers
|
|
("occasional", 0.15) # 15% occasional customers
|
|
]
|
|
|
|
|
|
def generate_spanish_name():
|
|
"""Generate a realistic Spanish name"""
|
|
first_name = random.choice(FIRST_NAMES)
|
|
surname1 = random.choice(SURNAMES)
|
|
surname2 = random.choice(SURNAMES)
|
|
return f"{first_name} {surname1} {surname2}"
|
|
|
|
|
|
def generate_customer_email(name: str, customer_code: str):
|
|
"""Generate a realistic email address"""
|
|
# Create email-safe version of name
|
|
parts = name.lower().split()
|
|
if len(parts) >= 2:
|
|
email_name = f"{parts[0]}.{parts[1]}"
|
|
else:
|
|
email_name = parts[0]
|
|
|
|
# Remove accents
|
|
email_name = email_name.replace('á', 'a').replace('é', 'e').replace('í', 'i')
|
|
email_name = email_name.replace('ó', 'o').replace('ú', 'u').replace('ñ', 'n')
|
|
|
|
domains = ["gmail.com", "hotmail.es", "yahoo.es", "outlook.es", "protonmail.com"]
|
|
domain = random.choice(domains)
|
|
|
|
return f"{email_name}{random.randint(1, 99)}@{domain}"
|
|
|
|
|
|
def generate_spanish_phone():
|
|
"""Generate a realistic Spanish mobile phone number"""
|
|
# Spanish mobile numbers start with 6 or 7
|
|
prefix = random.choice(['6', '7'])
|
|
number = ''.join([str(random.randint(0, 9)) for _ in range(8)])
|
|
return f"+34 {prefix}{number[0:2]} {number[2:5]} {number[5:8]}"
|
|
|
|
|
|
def select_customer_segment():
|
|
"""Select customer segment based on distribution"""
|
|
rand = random.random()
|
|
cumulative = 0.0
|
|
for segment, probability in CUSTOMER_SEGMENTS:
|
|
cumulative += probability
|
|
if rand <= cumulative:
|
|
return segment
|
|
return "regular"
|
|
|
|
|
|
async def seed_retail_customers_for_tenant(
|
|
db: AsyncSession,
|
|
tenant_id: uuid.UUID,
|
|
tenant_name: str,
|
|
num_customers: int,
|
|
city: str
|
|
) -> dict:
|
|
"""
|
|
Seed walk-in customers for a retail outlet
|
|
|
|
Args:
|
|
db: Database session
|
|
tenant_id: UUID of the child tenant
|
|
tenant_name: Name of the tenant (for logging)
|
|
num_customers: Number of customers to generate
|
|
city: City name for address generation
|
|
|
|
Returns:
|
|
Dict with seeding statistics
|
|
"""
|
|
logger.info("─" * 80)
|
|
logger.info(f"Seeding retail customers for: {tenant_name}")
|
|
logger.info(f"Tenant ID: {tenant_id}")
|
|
logger.info(f"Number of customers: {num_customers}")
|
|
logger.info("─" * 80)
|
|
|
|
# Check if customers already exist
|
|
result = await db.execute(
|
|
select(Customer).where(Customer.tenant_id == tenant_id).limit(1)
|
|
)
|
|
existing = result.scalar_one_or_none()
|
|
|
|
if existing:
|
|
logger.info(f"Customers already exist for {tenant_name}, skipping seed")
|
|
return {"tenant_id": str(tenant_id), "customers_created": 0, "skipped": True}
|
|
|
|
created_count = 0
|
|
|
|
for i in range(num_customers):
|
|
# Generate customer details
|
|
name = generate_spanish_name()
|
|
customer_code = f"RET-{str(tenant_id).split('-')[0].upper()[:4]}-{i+1:04d}"
|
|
email = generate_customer_email(name, customer_code) if random.random() > 0.2 else None # 80% have email
|
|
phone = generate_spanish_phone() if random.random() > 0.1 else None # 90% have phone
|
|
|
|
# Customer segment determines behavior
|
|
segment = select_customer_segment()
|
|
|
|
# Determine order history based on segment
|
|
if segment == "loyal":
|
|
total_orders = random.randint(15, 40)
|
|
avg_order_value = random.uniform(15.0, 35.0)
|
|
days_since_last_order = random.randint(1, 7)
|
|
elif segment == "regular":
|
|
total_orders = random.randint(5, 15)
|
|
avg_order_value = random.uniform(8.0, 20.0)
|
|
days_since_last_order = random.randint(3, 14)
|
|
else: # occasional
|
|
total_orders = random.randint(1, 5)
|
|
avg_order_value = random.uniform(5.0, 15.0)
|
|
days_since_last_order = random.randint(14, 60)
|
|
|
|
total_spent = total_orders * avg_order_value
|
|
last_order_date = BASE_REFERENCE_DATE - timedelta(days=days_since_last_order)
|
|
first_order_date = BASE_REFERENCE_DATE - timedelta(days=random.randint(30, 365))
|
|
|
|
# Most retail customers are individuals (not businesses)
|
|
is_business = random.random() < 0.05 # 5% are small businesses (cafes, hotels, etc.)
|
|
|
|
if is_business:
|
|
business_name = f"{name.split()[0]} {random.choice(['Cafetería', 'Restaurante', 'Hotel', 'Catering'])}"
|
|
customer_type = "business"
|
|
tax_id = f"B{random.randint(10000000, 99999999)}" # Spanish NIF for businesses
|
|
else:
|
|
business_name = None
|
|
customer_type = "individual"
|
|
tax_id = None
|
|
|
|
# Create customer
|
|
customer = Customer(
|
|
id=uuid.uuid4(),
|
|
tenant_id=tenant_id,
|
|
customer_code=customer_code,
|
|
name=name,
|
|
business_name=business_name,
|
|
customer_type=customer_type,
|
|
tax_id=tax_id,
|
|
email=email,
|
|
phone=phone,
|
|
address_line1=None, # Walk-in customers don't always provide full address
|
|
city=city if random.random() > 0.3 else None, # 70% have city info
|
|
state=None,
|
|
postal_code=None,
|
|
country="España",
|
|
is_active=True,
|
|
preferred_delivery_method="pickup", # Retail customers typically pick up
|
|
payment_terms="immediate", # Retail is always immediate payment
|
|
credit_limit=None, # No credit for retail
|
|
discount_percentage=5.0 if segment == "loyal" else 0.0, # Loyal customers get 5% discount
|
|
customer_segment=segment,
|
|
priority_level="normal",
|
|
special_instructions=None,
|
|
total_orders=total_orders,
|
|
total_spent=total_spent,
|
|
average_order_value=avg_order_value,
|
|
last_order_date=last_order_date,
|
|
created_at=first_order_date,
|
|
updated_at=BASE_REFERENCE_DATE
|
|
)
|
|
|
|
db.add(customer)
|
|
created_count += 1
|
|
|
|
if created_count % 20 == 0:
|
|
logger.debug(f" Created {created_count}/{num_customers} customers...")
|
|
|
|
# Commit all changes
|
|
await db.commit()
|
|
|
|
logger.info(f" 📊 Customers created: {created_count}")
|
|
logger.info("")
|
|
|
|
return {
|
|
"tenant_id": str(tenant_id),
|
|
"tenant_name": tenant_name,
|
|
"customers_created": created_count,
|
|
"skipped": False
|
|
}
|
|
|
|
|
|
async def seed_retail_customers(db: AsyncSession):
|
|
"""
|
|
Seed retail customers for all child tenant templates
|
|
|
|
Args:
|
|
db: Database session
|
|
|
|
Returns:
|
|
Dict with overall seeding statistics
|
|
"""
|
|
logger.info("=" * 80)
|
|
logger.info("👥 Starting Demo Retail Customers Seeding")
|
|
logger.info("=" * 80)
|
|
logger.info("Creating walk-in customer profiles for retail outlets")
|
|
logger.info("")
|
|
|
|
results = []
|
|
|
|
# Seed customers for each retail outlet
|
|
# Larger stores have more customers
|
|
retail_configs = [
|
|
(DEMO_TENANT_CHILD_1, "Madrid Centro", 100, "Madrid"), # Large urban store
|
|
(DEMO_TENANT_CHILD_2, "Barcelona Gràcia", 75, "Barcelona"), # Medium store
|
|
(DEMO_TENANT_CHILD_3, "Valencia Ruzafa", 60, "Valencia") # Smaller boutique store
|
|
]
|
|
|
|
for tenant_id, tenant_name, num_customers, city in retail_configs:
|
|
logger.info("")
|
|
result = await seed_retail_customers_for_tenant(
|
|
db,
|
|
tenant_id,
|
|
f"{tenant_name} (Retail Outlet)",
|
|
num_customers,
|
|
city
|
|
)
|
|
results.append(result)
|
|
|
|
# Calculate totals
|
|
total_customers = sum(r["customers_created"] for r in results)
|
|
|
|
logger.info("=" * 80)
|
|
logger.info("✅ Demo Retail Customers Seeding Completed")
|
|
logger.info("=" * 80)
|
|
|
|
return {
|
|
"service": "customers_retail",
|
|
"tenants_seeded": len(results),
|
|
"total_customers_created": total_customers,
|
|
"results": results
|
|
}
|
|
|
|
|
|
async def main():
|
|
"""Main execution function"""
|
|
|
|
logger.info("Demo Retail Customers Seeding Script Starting")
|
|
logger.info("Mode: %s", os.getenv("DEMO_MODE", "development"))
|
|
logger.info("Log Level: %s", os.getenv("LOG_LEVEL", "INFO"))
|
|
|
|
# Get database URL from environment
|
|
database_url = os.getenv("ORDERS_DATABASE_URL") or os.getenv("DATABASE_URL")
|
|
if not database_url:
|
|
logger.error("❌ ORDERS_DATABASE_URL or DATABASE_URL environment variable must be set")
|
|
return 1
|
|
|
|
# Convert to async URL if needed
|
|
if database_url.startswith("postgresql://"):
|
|
database_url = database_url.replace("postgresql://", "postgresql+asyncpg://", 1)
|
|
|
|
logger.info("Connecting to orders database")
|
|
|
|
# Create engine and session
|
|
engine = create_async_engine(
|
|
database_url,
|
|
echo=False,
|
|
pool_pre_ping=True,
|
|
pool_size=5,
|
|
max_overflow=10
|
|
)
|
|
|
|
async_session = sessionmaker(
|
|
engine,
|
|
class_=AsyncSession,
|
|
expire_on_commit=False
|
|
)
|
|
|
|
try:
|
|
async with async_session() as session:
|
|
result = await seed_retail_customers(session)
|
|
|
|
logger.info("")
|
|
logger.info("📊 Retail Customers Seeding Summary:")
|
|
logger.info(f" ✅ Retail outlets seeded: {result['tenants_seeded']}")
|
|
logger.info(f" ✅ Total customers created: {result['total_customers_created']}")
|
|
logger.info("")
|
|
|
|
# Print per-tenant details
|
|
for tenant_result in result['results']:
|
|
if not tenant_result['skipped']:
|
|
logger.info(
|
|
f" {tenant_result['tenant_name']}: "
|
|
f"{tenant_result['customers_created']} customers"
|
|
)
|
|
|
|
logger.info("")
|
|
logger.info("🎉 Success! Retail customer base is ready for cloning.")
|
|
logger.info("")
|
|
logger.info("Customer characteristics:")
|
|
logger.info(" ✓ Realistic Spanish names and contact info")
|
|
logger.info(" ✓ Segmentation: 60% regular, 25% loyal, 15% occasional")
|
|
logger.info(" ✓ 95% individual customers, 5% small businesses")
|
|
logger.info(" ✓ Order history and spending patterns")
|
|
logger.info(" ✓ Loyal customers receive 5% discount")
|
|
logger.info("")
|
|
logger.info("Next steps:")
|
|
logger.info(" 1. Seed retail orders (internal transfers from parent)")
|
|
logger.info(" 2. Seed POS configurations")
|
|
logger.info(" 3. Test customer analytics and segmentation")
|
|
logger.info("")
|
|
|
|
return 0
|
|
|
|
except Exception as e:
|
|
logger.error("=" * 80)
|
|
logger.error("❌ Demo Retail Customers Seeding Failed")
|
|
logger.error("=" * 80)
|
|
logger.error("Error: %s", str(e))
|
|
logger.error("", exc_info=True)
|
|
return 1
|
|
|
|
finally:
|
|
await engine.dispose()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
exit_code = asyncio.run(main())
|
|
sys.exit(exit_code)
|