"""build_sector_flow_history_progress_v1.py — SECTOR_FLOW_HISTORY_PROGRESS_V1

WBS-2.5 진척도를 실데이터로 요약한다.
sector_flow_history 누적 일수와 Flow_Credit 커버리지를 정직하게 노출한다.
"""
from __future__ import annotations

import argparse
import json
from collections import defaultdict
from pathlib import Path
from typing import Any

ROOT = Path(__file__).resolve().parents[1]
DEFAULT_JSON = ROOT / "GatherTradingData.json"
DEFAULT_OUT = ROOT / "Temp" / "sector_flow_history_progress_v1.json"
FORMULA_ID = "SECTOR_FLOW_HISTORY_PROGRESS_V1"


def _load(path: Path) -> dict[str, Any]:
    if not path.exists():
        return {}
    try:
        obj = json.loads(path.read_text(encoding="utf-8"))
    except Exception:
        return {}
    return obj if isinstance(obj, dict) else {}


def _rows(data: dict[str, Any], key: str) -> list[dict[str, Any]]:
    rows = (data.get("data") or {}).get(key) or []
    return [r for r in rows if isinstance(r, dict)]


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--json", default=str(DEFAULT_JSON))
    ap.add_argument("--out", default=str(DEFAULT_OUT))
    args = ap.parse_args()

    json_path = Path(args.json)
    json_path = json_path if json_path.is_absolute() else ROOT / json_path
    out_path = Path(args.out)
    out_path = out_path if out_path.is_absolute() else ROOT / out_path

    payload = _load(json_path)
    sector_rows = _rows(payload, "sector_flow_history")
    data_feed_rows = _rows(payload, "data_feed")

    by_date: dict[str, int] = defaultdict(int)
    for row in sector_rows:
        snap = row.get("Snapshot_Date") or row.get("snapshot_date") or ""
        day = str(snap)[:10]
        if day:
            by_date[day] += 1

    distinct_dates = len(by_date)
    row_count = len(sector_rows)
    target_dates = 30
    status = "DONE" if distinct_dates >= target_dates else "DATA_GATED"
    coverage = round(min(100.0, distinct_dates / target_dates * 100.0), 2)

    flow_credit_values = [row.get("Flow_Credit") for row in data_feed_rows]
    nonnull_flow_credit = sum(1 for v in flow_credit_values if v is not None)
    flow_credit_coverage = round((nonnull_flow_credit / len(flow_credit_values) * 100.0), 2) if flow_credit_values else 0.0

    result = {
        "formula_id": FORMULA_ID,
        "status": status,
        "current_dates": distinct_dates,
        "target_dates": target_dates,
        "coverage_pct": coverage,
        "row_count": row_count,
        "rows_per_date": sorted(by_date.items()),
        "flow_credit_coverage_pct": flow_credit_coverage,
        "flow_credit_nonnull_count": nonnull_flow_credit,
        "flow_credit_total_count": len(flow_credit_values),
        "source": "GatherTradingData.json:data.sector_flow_history + data.data_feed",
    }

    out_path.parent.mkdir(parents=True, exist_ok=True)
    out_path.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
    print(
        f"[{FORMULA_ID}] status={status} dates={distinct_dates}/{target_dates} "
        f"rows={row_count} flow_credit={nonnull_flow_credit}/{len(flow_credit_values)}"
    )
    return 0


if __name__ == "__main__":
    raise SystemExit(main())