#!/usr/bin/env python3
"""Remove ALL GPS data that was geocoded from addresses.

Keeps ONLY: the 5 original app check-in entries from gps-backup.json that 
still exist in the current DB. Everything else was derived from an 
address geocoding source (MSFS accounts, Cantaloupe seed data)."""

import json
import sqlite3

DB_PATH = "/home/oplabs/projects/canteen-asset-tracker/assets.db"
GPS_BAK_PATH = "/home/oplabs/projects/canteen-asset-tracker/gps-backup.json"

def main():
    # Load original app check-ins
    with open(GPS_BAK_PATH) as f:
        gps_bak = json.load(f)
    checkin_coords = {}
    for e in gps_bak:
        checkin_coords[e['machine_id']] = (e['lat'], e['lng'])
    print(f"Original app check-in entries: {len(checkin_coords)}")
    
    cur = sqlite3.connect(DB_PATH)
    
    total = cur.execute("SELECT COUNT(*) FROM assets").fetchone()[0]
    before = cur.execute(
        "SELECT COUNT(*) FROM assets WHERE latitude IS NOT NULL AND latitude != 0"
    ).fetchone()[0]
    print(f"Before: {before} / {total} with GPS")
    
    removed = 0
    kept_checkin = 0
    kept_other = 0
    
    for r in cur.execute(
        "SELECT rowid, machine_id, latitude, longitude FROM assets "
        "WHERE latitude IS NOT NULL AND longitude IS NOT NULL AND latitude != 0 AND longitude != 0"
    ).fetchall():
        rowid, mid, lat, lon = r
        
        # KEEP: only app check-in entries where coordinates match exactly
        if mid in checkin_coords:
            expected = checkin_coords[mid]
            if abs(float(lat) - expected[0]) < 0.0001 and abs(float(lon) - expected[1]) < 0.0001:
                kept_checkin += 1
                continue
        
        # Everything else is address-geocoded — remove
        cur.execute("UPDATE assets SET latitude = NULL, longitude = NULL WHERE rowid = ?", (rowid,))
        removed += 1
    
    cur.commit()
    
    after = cur.execute(
        "SELECT COUNT(*) FROM assets WHERE latitude IS NOT NULL AND latitude != 0"
    ).fetchone()[0]
    
    print(f"\nResults:")
    print(f"  Kept (app check-ins): {kept_checkin}")
    print(f"  Removed (address-geocoded): {removed}")
    print(f"  After: {after} / {total} with GPS")
    print(f"  Without GPS: {total - after}")
    
    # Show what's left
    print(f"\n=== Remaining GPS entries ===")
    for r in cur.execute(
        "SELECT machine_id, make, model, category, latitude, longitude FROM assets "
        "WHERE latitude IS NOT NULL AND latitude != 0"
    ).fetchall():
        print(f"  {r[0]}: ({r[4]}, {r[5]}) — {r[1]} {r[2]} ({r[3]})")
    
    cur.close()

if __name__ == "__main__":
    main()