Full lab documentation and infrastructure as code

- Trino catalogs, Grafana, Spark jobs, LDAP LDIF, NPM compose - Airflow DAG scripts, Proxmox VM inventory, network docs - Ansible playbook, Gitea CI validate workflow - Backup and health-check scripts, cron documentation - Homepage DOCS tab with links to all documentation - Extended collect-fleet-config.sh and populate-repo.py
2026-05-19 23:12:41 +02:00
parent 3c8993a41e
commit df5ec93dc3
46 changed files with 1809 additions and 74 deletions
@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+"""
+Script to generate fake sales order data for PostgreSQL
+Generates approximately 1GB of data
+"""
+
+import psycopg2
+import random
+from datetime import datetime, timedelta
+import uuid
+import sys
+
+# Database connection details
+DB_HOST = "10.0.21.51"
+DB_PORT = "5432"
+DB_NAME = "postgres"
+DB_USER = "mo"
+DB_PASSWORD = "Dell2026!"
+
+# Data generation settings
+TARGET_ROWS = 4000000  # Approximately 1GB of data
+BATCH_SIZE = 10000
+
+# Sample data
+REGIONS = ["EU", "APAC", "LATAM", "NA", "EMEA"]
+SALES_CHANNELS = ["STORE", "ONLINE", "MOBILE", "B2B"]
+CURRENCIES = ["EUR", "USD", "GBP", "JPY", "CNY"]
+ORDER_STATUSES = ["SHIPPED", "PENDING", "CANCELLED", "RETURNED", "DELIVERED"]
+
+def generate_fake_order():
+    """Generate a single fake sales order"""
+    customer_id = random.randint(1, 100000)
+    product_id = random.randint(1, 5000)
+    region = random.choice(REGIONS)
+    sales_channel = random.choice(SALES_CHANNELS)
+    
+    # Random timestamp within the last 2 years
+    days_ago = random.randint(0, 730)
+    order_ts = datetime.now() - timedelta(days=days_ago, hours=random.randint(0, 23), 
+                                          minutes=random.randint(0, 59))
+    
+    amount = round(random.uniform(10.0, 10000.0), 2)
+    currency = random.choice(CURRENCIES)
+    order_status = random.choice(ORDER_STATUSES)
+    
+    # Generate a long notes field (like the existing data)
+    notes = str(uuid.uuid4()) * 10
+    
+    return (customer_id, product_id, region, sales_channel, order_ts, 
+            amount, currency, order_status, notes)
+
+def main():
+    print(f"Connecting to PostgreSQL at {DB_HOST}:{DB_PORT}...")
+    
+    conn = psycopg2.connect(
+        host=DB_HOST,
+        port=DB_PORT,
+        database=DB_NAME,
+        user=DB_USER,
+        password=DB_PASSWORD
+    )
+    cursor = conn.cursor()
+    
+    print(f"Generating {TARGET_ROWS} sales orders...")
+    print(f"Batch size: {BATCH_SIZE}")
+    
+    total_generated = 0
+    batch = []
+    
+    for i in range(TARGET_ROWS):
+        batch.append(generate_fake_order())
+        
+        if len(batch) >= BATCH_SIZE:
+            cursor.executemany(
+                """
+                INSERT INTO sales_orders (customer_id, product_id, region, sales_channel, 
+                                         order_ts, amount, currency, order_status, notes)
+                VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
+                """,
+                batch
+            )
+            conn.commit()
+            total_generated += len(batch)
+            batch = []
+            
+            if total_generated % 100000 == 0:
+                print(f"Generated {total_generated} rows...")
+    
+    # Insert remaining rows
+    if batch:
+        cursor.executemany(
+            """
+            INSERT INTO sales_orders (customer_id, product_id, region, sales_channel, 
+                                     order_ts, amount, currency, order_status, notes)
+            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
+            """,
+            batch
+        )
+        conn.commit()
+        total_generated += len(batch)
+    
+    cursor.close()
+    conn.close()
+    
+    print(f"Completed! Generated {total_generated} sales orders.")
+
+if __name__ == "__main__":
+    main()