"""10분봉 캐시 갱신 스크립트 — 최신 45일 데이터를 Upbit API로 재수집."""

import os, sys, pickle, time
from pathlib import Path
from datetime import datetime, timedelta

import pyupbit
from dotenv import load_dotenv

load_dotenv(dotenv_path=Path(__file__).parent.parent / ".env")
sys.path.insert(0, str(Path(__file__).parent.parent))

CACHE_FILE = Path(__file__).parent.parent / "data" / "sim10m_cache.pkl"
TOP30_FILE = Path(__file__).parent.parent / "data" / "top30_tickers.pkl"
SIM_DAYS   = 45
TOP_N      = 20


def fetch_10m(ticker: str, days: int) -> "pd.DataFrame | None":
    import pandas as pd
    target_start = datetime.now() - timedelta(days=days)
    all_dfs, to, prev_oldest = [], None, None
    while True:
        kwargs = dict(ticker=ticker, interval="minute10", count=200)
        if to:
            kwargs["to"] = to.strftime("%Y-%m-%d %H:%M:%S")
        try:
            df = pyupbit.get_ohlcv(**kwargs)
        except Exception:
            time.sleep(0.5)
            break
        if df is None or df.empty:
            break
        all_dfs.append(df)
        oldest = df.index[0]
        if prev_oldest is not None and oldest >= prev_oldest:
            break
        prev_oldest = oldest
        if oldest <= target_start:
            break
        to = oldest
        time.sleep(0.12)
    if not all_dfs:
        return None
    combined = pd.concat(all_dfs).sort_index()
    combined = combined[~combined.index.duplicated(keep="last")]
    return combined[combined.index >= target_start]


def main():
    # 현재 Top20 종목 가져오기
    from core.market import get_top_tickers
    print("Top20 종목 조회...")
    tickers = get_top_tickers()[:TOP_N]
    print(f"  {tickers}\n")

    data = {"10m": {}}
    for i, ticker in enumerate(tickers, 1):
        print(f"\r  {i:>2}/{len(tickers)} {ticker}   ", end="", flush=True)
        df = fetch_10m(ticker, SIM_DAYS)
        if df is not None and len(df) > 100:
            data["10m"][ticker] = df
        time.sleep(0.15)

    print(f"\n\n종목: {len(data['10m'])}개")
    if data["10m"]:
        sample = next(iter(data["10m"].values()))
        print(f"기간: {sample.index[0].strftime('%Y-%m-%d')} ~ {sample.index[-1].strftime('%Y-%m-%d')}")
        print(f"레코드: {len(sample)}개")

    # 저장
    pickle.dump(data, open(CACHE_FILE, "wb"))
    print(f"\n캐시 저장: {CACHE_FILE}")

    # top30 갱신
    pickle.dump(tickers, open(TOP30_FILE, "wb"))
    print(f"종목 저장: {TOP30_FILE}")


if __name__ == "__main__":
    main()