#!/usr/bin/env python3
"""Warm Redis cache for vehicle info (part_vehicle_preview alternative).

Runs in batches over all parts in the catalog, populating
nexus:vehicle:{part_id} keys in Redis. This eliminates the
DISTINCT ON + 4 JOINs query on vehicle_parts (2B rows) for
cached parts.

Usage:
    export MASTER_DB_URL="postgresql://..."
    export REDIS_URL="redis://localhost:6379/0"
    python3 warm_vehicle_cache.py
"""

import os, sys, json, time
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'pos'))

import psycopg2
import redis

def _fix_dsn(dsn):
    if dsn and 'host=' not in dsn and '@/' in dsn:
        dsn = dsn.replace('@/', '@localhost/')
    return dsn


MASTER_DB_URL = _fix_dsn(os.environ.get('MASTER_DB_URL', 'postgresql://postgres@localhost/nexus_autoparts'))
REDIS_URL = os.environ.get('REDIS_URL', 'redis://localhost:6379/0')
BATCH_SIZE = 5000
TTL_SECONDS = 3600


def main():
    print("Connecting to master DB and Redis...")
    conn = psycopg2.connect(MASTER_DB_URL)
    cur = conn.cursor()
    r = redis.from_url(REDIS_URL, decode_responses=True)
    r.ping()

    # Get all part_ids
    cur.execute("SELECT id_part FROM parts WHERE oem_part_number IS NOT NULL ORDER BY id_part")
    all_ids = [r[0] for r in cur.fetchall()]
    total = len(all_ids)
    print(f"Total parts to warm: {total}")

    processed = 0
    cached = 0
    start = time.time()

    for i in range(0, total, BATCH_SIZE):
        batch = all_ids[i:i + BATCH_SIZE]
        cur.execute("""
            SELECT DISTINCT ON (vp.part_id)
                   vp.part_id, b.name_brand, m.name_model, y.year_car
            FROM vehicle_parts vp
            JOIN model_year_engine mye ON mye.id_mye = vp.model_year_engine_id
            JOIN models m ON m.id_model = mye.model_id
            JOIN brands b ON b.id_brand = m.brand_id
            JOIN years y ON y.id_year = mye.year_id
            WHERE vp.part_id = ANY(%s)
            ORDER BY vp.part_id, y.year_car DESC
        """, (batch,))

        pipe = r.pipeline()
        batch_cached = 0
        for row in cur.fetchall():
            info = f"{row[1]} {row[2]} {row[3]}"
            pipe.setex(f'nexus:vehicle:{row[0]}', TTL_SECONDS, info)
            batch_cached += 1
        pipe.execute()

        processed += len(batch)
        cached += batch_cached
        elapsed = time.time() - start
        rate = processed / elapsed if elapsed > 0 else 0
        print(f"  [{processed}/{total}] cached={batch_cached} ({rate:.0f}/s)")

    cur.close()
    conn.close()
    print(f"\nDone. Cached {cached} vehicle entries in {elapsed:.0f}s")


if __name__ == '__main__':
    main()