"""审计模板：每个表头字段是否都在「填写说明 → 字段依据」中有来源标注。"""

from __future__ import annotations

import re
import sys
from pathlib import Path

import openpyxl


sys.stdout.reconfigure(encoding="utf-8")
TPL = Path(r"E:\CODE\knowledge_agent\data\templates")


def norm(h: str) -> str:
    s = h.replace("*", "")
    for x in ("（选填）", "（必填）", "（工号）", "（非续签留空）"):
        s = s.replace(x, "")
    return re.sub(r"\s+", "", s)


def main() -> None:
    for f in sorted(TPL.glob("*.xlsx")):
        if f.name.startswith("~$"):
            continue  # Excel 临时锁文件
        wb = openpyxl.load_workbook(f, read_only=True, data_only=True)
        data = wb[wb.sheetnames[0]]
        headers = [c.value for c in data[1] if c.value]
        note = wb["填写说明"]
        start = None
        for r in range(1, 200):
            if note.cell(row=r, column=1).value == "【字段依据】":
                start = r
                break
        entries: list[str] = []
        if start:
            r = start + 2
            while note.cell(row=r, column=1).value:
                entries.append(str(note.cell(row=r, column=1).value))
                r += 1

        missing = []
        for h in headers:
            hn = norm(h)
            if re.fullmatch(r"\d+日", hn):
                continue  # 1日..31日 由「1-31日」条目覆盖
            covered = False
            for e in entries:
                toks = [t for t in re.split(r"[/、，,]", norm(e)) if t]
                for tk in toks:
                    if hn == tk or (len(tk) >= 2 and (tk in hn or hn in tk)):
                        covered = True
                        break
                if covered:
                    break
            if not covered:
                missing.append(h)

        print(f"=== {f.name}: {len(headers)} 列 / 依据 {len(entries)} 条 / 未覆盖 {len(missing)}")
        for m in missing:
            print(f"    ✗ {m}")
        wb.close()


if __name__ == "__main__":
    main()