"""最终挑选校验：对每个板块的候选做"策略实际窗口（最近 120 根）内是否有价格断层"检查。

接口的 OHLC 不做拆分/份额折算复原（``pre_close`` 已折算、价格未折算），
若断层落在最近 120 根内，MA60/ATR 会被污染，网格锚点会算错 → 必须避开。

用法： py -3.14 -B labs/analysis/etf/verify_picks.py
"""

import json
import sys
import urllib.request
from pathlib import Path

HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE))
try:
    sys.stdout.reconfigure(encoding="utf-8", errors="replace")
except Exception:
    pass

from backtest import CACHE, DAILY_URL, WARMUP  # noqa: E402

# 板块 -> (首选, [替补...])
PLAN = {
    "AI": ("159819.SZ", ["515070.SH", "159363.SZ"]),
    "CPO/通信": ("515880.SH", ["515050.SH", "159994.SZ", "159583.SZ", "159695.SZ"]),
    "PCB": ("159732.SZ", ["562950.SH", "159997.SZ", "561100.SH"]),
    "人形机器人": ("562500.SH", ["159530.SZ", "159770.SZ", "159272.SZ"]),
    "光/光伏": ("515790.SH", ["159755.SZ", "516160.SH", "561910.SH"]),
    "创新药": ("159992.SZ", ["159570.SZ", "515120.SH", "512010.SH"]),
    "半导体": ("588200.SH", ["159516.SZ", "588170.SH", "159995.SZ", "512480.SH"]),
    "存储": ("588750.SH", ["588290.SH", "589130.SH", "588890.SH"]),
    "半导体材料": ("588160.SH", ["588010.SH", "589510.SH", "159761.SZ"]),
    "玻璃基板": ("159745.SZ", ["588010.SH", "159763.SZ"]),
    "电力": ("159326.SZ", ["159611.SZ", "159625.SZ", "561560.SH"]),
    "航空航天": ("159227.SZ", ["512660.SH", "159267.SZ", "512710.SH"]),
    "金属": ("518880.SH", ["512400.SH", "159934.SZ"]),
    "金融": ("512880.SH", ["512070.SH", "512800.SH", "159841.SZ"]),
    "能源": ("515220.SH", ["561360.SH", "159518.SZ"]),
    "宽基(保留)": ("510300.SH", []),
}


def load(code: str) -> list[dict]:
    path = CACHE / f"{code}.json"
    if path.exists():
        rows = json.loads(path.read_text(encoding="utf-8"))
    else:
        request = urllib.request.Request(f"{DAILY_URL}?code={code}",
                                         headers={"User-Agent": "Mozilla/5.0"})
        with urllib.request.urlopen(request, timeout=30) as response:
            rows = json.load(response)
        CACHE.mkdir(parents=True, exist_ok=True)
        path.write_text(json.dumps(rows), encoding="utf-8")
    return sorted(rows, key=lambda r: str(r["trade_date"]))


def report(code: str) -> tuple[bool, str]:
    """返回 (窗口内是否干净, 说明)。窗口 = 最近 120 根（策略指标只用这段）。"""
    rows = load(code)
    window = rows[-120:] if len(rows) >= 120 else rows
    worst, worst_day = 0.0, ""
    for prev, cur in zip(window, window[1:]):
        a, b = float(prev["close"]), float(cur["close"])
        if a > 0:
            change = abs(b / a - 1) * 100
            if change > worst:
                worst, worst_day = change, str(cur["trade_date"])
    clean = worst <= 15
    note = "干净" if clean else f"窗口内{worst_day}跳空 {worst:.1f}%"
    closes = [float(r["close"]) for r in window]
    return clean, f"{note}  最近120根 {min(closes):.3f}~{max(closes):.3f} 最新 {closes[-1]:.3f}"


print(f"{'板块':12} {'首选':11} {'窗口干净':>8}  说明")
picks = {}
for sector, (first, alts) in PLAN.items():
    for code in [first, *alts]:
        clean, note = report(code)
        tag = "★首选" if code == first else " 替补"
        print(f"{sector:12} {code:11} {str(clean):>8} {tag} {note}")
        if code == first:
            picks[sector] = (code, clean)
    print()
print("== 首选中有断层的板块 ==")
for sector, (code, clean) in picks.items():
    if not clean:
        print(f"  {sector}: {code}")