#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""ETF 探针 v2: 先 download 再读,对比 dividend_type,确认 ETF 在 sector 中。"""
import sys
from xtquant import xtdata as xd


def main():
    etf = xd.get_stock_list_in_sector("沪深ETF") or []
    fund = xd.get_stock_list_in_sector("沪深基金") or []
    a = xd.get_stock_list_in_sector("沪深A股") or []
    u = list(set(a + etf + fund))
    print(f"A={len(a)} ETF={len(etf)} fund={len(fund)} union={len(u)}")

    # 1) 检查目标 samples 是否在 universe
    for sym in ("510300.SH", "513050.SH", "159919.SZ"):
        print(f"  {sym} in A={sym in a} in ETF={sym in etf} in fund={sym in fund}")

    # 2) 重叠分析: ETF 与 fund 是否相同
    overlap = set(etf) & set(fund)
    only_etf = set(etf) - set(fund)
    only_fund = set(fund) - set(etf)
    print(f"overlap(ETF&fund)={len(overlap)} only_etf={len(only_etf)} only_fund={len(only_fund)}")
    if only_etf:
        print(f"  only_etf sample: {list(only_etf)[:5]}")
    if only_fund:
        print(f"  only_fund sample: {list(only_fund)[:5]}")

    # 3) 先 download 再读
    samples = ["510300.SH", "513050.SH", "159919.SZ"]
    print(f"\n=== download_history_data(1d, 20240101~20260721) ===")
    for sym in samples:
        try:
            n = xd.download_history_data(sym, "1d", "20240101", "20260721")
            print(f"  {sym} download returned: {n}")
        except Exception as e:
            print(f"  {sym} download err: {e}")

    # 4) 读两种 dividend_type
    for dt in ("front", "none"):
        print(f"\n=== get_market_data_ex dividend_type={dt} ===")
        r = xd.get_market_data_ex([], samples, period="1d",
                                  start_time="20240101", end_time="20260721",
                                  dividend_type=dt)
        for sym in samples:
            df = r.get(sym) if r else None
            bars = 0 if df is None else len(df)
            tail_close = None if df is None or not len(df) else float(df["close"].iloc[-1])
            head_date = None if df is None or not len(df) else str(df.index[0])[:8]
            tail_date = None if df is None or not len(df) else str(df.index[-1])[:8]
            print(f"  {sym}: bars={bars} date=[{head_date}~{tail_date}] tail_close={tail_close}")

    sys.stdout.flush()


if __name__ == "__main__":
    main()