import sqlite3
import random
from datetime import datetime, timedelta

conn = sqlite3.connect('rivp.db')
c = conn.cursor()

# Hämta alla vägar - kolla kolumnnamn först
c.execute("PRAGMA table_info(roads)")
columns = c.fetchall()
print("Columns:", [col[1] for col in columns])

c.execute("SELECT id, name, length_km, bbox, type, county FROM roads")
roads = c.fetchall()

print(f"Generating observations for {len(roads)} roads...")

observation_types = ['pothole', 'surface_damage', 'crack', 'construction', 'vegetation', 'flooding', 'ice_damage']
severities = ['low', 'medium', 'high', 'critical']
sources = ['satellite', 'quixzoom', 'manual', 'sensor']

observation_count = 0

for road in roads:
    road_id, name, length_km, bbox, road_type, county = road
    
    # Antal observationer baserat på väglängd och typ
    if road_type == 'motorway':
        num_obs = int(length_km / 10) + random.randint(0, 3)
    else:
        num_obs = int(length_km / 15) + random.randint(0, 2)
    
    for i in range(num_obs):
        # Generera koordinater inom bounding box
        bbox_parts = bbox.split(',')
        min_lon, min_lat, max_lon, max_lat = map(float, bbox_parts)
        
        lat = random.uniform(min_lat, max_lat)
        lon = random.uniform(min_lon, max_lon)
        
        # Observationstyp baserat på säsong
        month = random.randint(1, 12)
        if month in [11, 12, 1, 2, 3]:
            obs_type = random.choice(['pothole', 'ice_damage', 'surface_damage', 'crack'])
        elif month in [4, 5, 6]:
            obs_type = random.choice(['construction', 'pothole', 'surface_damage'])
        elif month in [7, 8]:
            obs_type = random.choice(['vegetation', 'construction', 'surface_damage'])
        else:
            obs_type = random.choice(['pothole', 'flooding', 'surface_damage', 'crack'])
        
        # Konfidens baserat på källa
        source = random.choice(sources)
        if source == 'satellite':
            confidence = random.uniform(0.6, 0.9)
        elif source == 'quixzoom':
            confidence = random.uniform(0.75, 0.95)
        elif source == 'manual':
            confidence = random.uniform(0.85, 0.99)
        else:
            confidence = random.uniform(0.5, 0.8)
        
        # Severity
        if obs_type in ['construction']:
            severity = random.choice(['medium', 'high'])
        elif obs_type in ['pothole', 'crack']:
            severity = random.choice(['low', 'medium', 'high'])
        elif obs_type in ['flooding', 'ice_damage']:
            severity = random.choice(['medium', 'high', 'critical'])
        else:
            severity = random.choice(['low', 'medium'])
        
        # Storlek
        if obs_type == 'construction':
            size_m2 = random.uniform(500, 5000)
        elif obs_type == 'pothole':
            size_m2 = random.uniform(1, 20)
        elif obs_type == 'vegetation':
            size_m2 = random.uniform(50, 500)
        else:
            size_m2 = random.uniform(10, 200)
        
        # Datum
        day = random.randint(1, 28)
        detected_date = f"2026-{month:02d}-{day:02d}"
        
        # Verifierad?
        verified = 1 if confidence > 0.8 else 0
        
        c.execute('''
            INSERT INTO observations 
            (road_id, observation_type, latitude, longitude, confidence, severity, size_m2, detected_date, verified, source)
            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
        ''', (road_id, obs_type, lat, lon, confidence, severity, size_m2, detected_date, verified, source))
        
        observation_count += 1

conn.commit()

# Räkna totala
conn = sqlite3.connect('rivp.db')
c = conn.cursor()
c.execute("SELECT COUNT(*) FROM observations")
total = c.fetchone()[0]
print(f"Total observations in database: {total}")

# Visa fördelning
c.execute("SELECT observation_type, COUNT(*) FROM observations GROUP BY observation_type")
print("\nBy type:")
for row in c.fetchall():
    print(f"  {row[0]}: {row[1]}")

c.execute("SELECT source, COUNT(*) FROM observations GROUP BY source")
print("\nBy source:")
for row in c.fetchall():
    print(f"  {row[0]}: {row[1]}")

c.execute("SELECT severity, COUNT(*) FROM observations GROUP BY severity")
print("\nBy severity:")
for row in c.fetchall():
    print(f"  {row[0]}: {row[1]}")

conn.close()

print(f"\nGenerated {observation_count} new observations")