"""技术验证共用：样本定位、格式识别。样本是不可信输入，只读取，不执行。"""
from __future__ import annotations

import pathlib

ROOT = pathlib.Path(__file__).resolve().parent.parent
SAMPLES = ROOT / "samples" / "tenders"
IDS = [f"S{i:02d}" for i in range(1, 11)]


def sample_file(sid: str) -> pathlib.Path:
    files = [p for p in (SAMPLES / sid).iterdir() if p.suffix.lower() in (".doc", ".docx")]
    assert len(files) == 1, (sid, files)
    return files[0]


def sniff(path: pathlib.Path) -> str:
    """按文件头识别真实格式（FR-M2-01），不看扩展名。"""
    head = path.read_bytes()[:8]
    if head.startswith(b"PK\x03\x04"):
        return "docx"
    if head.startswith(bytes.fromhex("D0CF11E0A1B11AE1")):
        return "doc"
    if head.startswith(b"%PDF"):
        return "pdf"
    return "unknown"