oedb-backend/create_mock_events.py

#!/usr/bin/env python3
# Script to create mock events in the database
# Events will start slightly before the current date and end far in the future
# Events will be of various types: traffic, nature, weather, sport, conference, party

import os
import sys
import json
import psycopg2
import psycopg2.extras
from datetime import datetime, timedelta
import random

# Function to load environment variables from .env file
def load_env_from_file():
    if os.path.exists('.env'):
        print("Loading environment variables from .env file...")
        with open('.env', 'r') as f:
            for line in f:
                line = line.strip()
                if line and not line.startswith('#'):
                    key, value = line.split('=', 1)
                    os.environ[key] = value

# Load environment variables from .env file
load_env_from_file()

# Database connection parameters
DB_NAME = os.getenv("DB_NAME", "oedb")
DB_HOST = os.getenv("DB_HOST", "localhost")
DB_USER = os.getenv("DB_USER", "postgres")
DB_PASSWORD = os.getenv("POSTGRES_PASSWORD", "")

# Current date (2025-09-15 as specified in the issue)
CURRENT_DATE = datetime(2025, 9, 15, 23, 0)

# Event types
EVENT_TYPES = ["scheduled", "forecast", "unscheduled"]

# Event categories (what)
EVENT_CATEGORIES = ["traffic", "nature", "weather", "sport", "conference", "party", "community", "wildlife"]

# Sample locations (Paris, Lyon, Marseille, Toulouse, Bordeaux, Lille)
SAMPLE_LOCATIONS = [
    {"name": "Paris", "lon": 2.3522, "lat": 48.8566},
    {"name": "Lyon", "lon": 4.8357, "lat": 45.7640},
    {"name": "Marseille", "lon": 5.3698, "lat": 43.2965},
    {"name": "Toulouse", "lon": 1.4442, "lat": 43.6047},
    {"name": "Bordeaux", "lon": -0.5792, "lat": 44.8378},
    {"name": "Lille", "lon": 3.0573, "lat": 50.6292}
]

# Connect to the database
def db_connect():
    return psycopg2.connect(
        dbname=DB_NAME,
        host=DB_HOST,
        user=DB_USER,
        password=DB_PASSWORD
    )

# Create a point geometry
def create_point_geometry(lon, lat):
    return {
        "type": "Point",
        "coordinates": [lon, lat]
    }

# Insert geometry into geo table and return its hash
def insert_geometry(cur, geometry):
    geometry_json = json.dumps(geometry)
    
    # First, calculate the hash
    cur.execute("""
        SELECT md5(st_astext(geom)), st_astext(geom)
        FROM (SELECT st_setsrid(st_geomfromgeojson(%s),4326) as geom) as g;
    """, (geometry_json,))
    
    hash_result = cur.fetchone()
    if not hash_result:
        raise Exception("Failed to calculate geometry hash")
    
    geo_hash = hash_result[0]
    geo_text = hash_result[1]
    
    # Check if this hash already exists in the geo table
    cur.execute("SELECT 1 FROM geo WHERE hash = %s", (geo_hash,))
    exists = cur.fetchone()
    
    if not exists:
        # Insert the geometry if it doesn't exist
        cur.execute("""
            INSERT INTO geo (geom, hash, geom_center)
            VALUES (
                ST_SetSRID(ST_GeomFromText(%s), 4326),
                %s,
                ST_Centroid(ST_SetSRID(ST_GeomFromText(%s), 4326))
            );
        """, (geo_text, geo_hash, geo_text))
    
    return geo_hash

# Create a mock event
def create_mock_event(cur, category, location, event_type):
    # Generate random start date slightly before current date (0-7 days)
    days_before = random.randint(0, 7)
    start_date = CURRENT_DATE - timedelta(days=days_before)
    
    # Generate random end date far in the future (30-365 days from now)
    days_after = random.randint(30, 365)
    end_date = CURRENT_DATE + timedelta(days=days_after)
    
    # Format dates as ISO strings
    start_date_str = start_date.isoformat()
    end_date_str = end_date.isoformat()
    
    # Create geometry
    geometry = create_point_geometry(location["lon"], location["lat"])
    
    # Insert geometry and get hash
    geo_hash = insert_geometry(cur, geometry)
    
    # Create event tags (properties)
    tags = {
        "name": f"{category.capitalize()} event in {location['name']}",
        "description": f"Mock {category} event for testing",
        "location": location["name"],
        "start": start_date_str,
        "stop": end_date_str
    }
    
    # Insert event
    cur.execute("""
        INSERT INTO events (
            events_type, events_what, events_when, events_tags, events_geo
        ) VALUES (
            %s, %s, tstzrange(%s, %s, '[)'), %s, %s
        ) ON CONFLICT DO NOTHING RETURNING events_id;
    """, (
        event_type,
        category,
        start_date_str,
        end_date_str,
        json.dumps(tags),
        geo_hash
    ))
    
    result = cur.fetchone()
    return result[0] if result else None

def main():
    print("Creating mock events...")
    
    try:
        # Connect to the database
        conn = db_connect()
        cur = conn.cursor()
        
        # Create events for each category
        created_events = []
        
        for category in EVENT_CATEGORIES:
            print(f"Creating events for category: {category}")
            
            # Create 3 events for each category (one in each city)
            for i in range(3):
                location = random.choice(SAMPLE_LOCATIONS)
                event_type = random.choice(EVENT_TYPES)
                
                event_id = create_mock_event(cur, category, location, event_type)
                if event_id:
                    created_events.append({
                        "id": event_id,
                        "category": category,
                        "location": location["name"],
                        "type": event_type
                    })
                    print(f"  Created {category} event in {location['name']} with ID: {event_id}")
                else:
                    print(f"  Failed to create {category} event in {location['name']}")
        
        # Commit the transaction
        conn.commit()
        
        print(f"\nSuccessfully created {len(created_events)} mock events:")
        for event in created_events:
            print(f"  - {event['category']} event in {event['location']} (ID: {event['id']})")
        
    except Exception as e:
        print(f"Error: {e}")
        if 'conn' in locals():
            conn.rollback()
        sys.exit(1)
    finally:
        if 'cur' in locals():
            cur.close()
        if 'conn' in locals():
            conn.close()

if __name__ == "__main__":
    main()