from __future__ import annotations

import hashlib
import re
from typing import Any, Mapping, Sequence
from urllib.parse import unquote, urlparse

ARCHIVE_ZIP_ATTACH_COL_MAX = 20
ARCHIVE_ZIP_MAX_FILES = 2000
ARCHIVE_ZIP_MAX_BYTES = 500 * 1024 * 1024


def sanitize_zip_segment(raw: str) -> str:
    value = re.sub(r'[\\/:*?"<>|]+', "_", str(raw or "").strip())
    value = re.sub(r"\s+", " ", value).strip()
    return value or "未命名"


def short_hash(text: str, *, n: int = 6) -> str:
    return hashlib.sha1(str(text or "").encode("utf-8")).hexdigest()[:n]


def guess_ext_from_url(url: str) -> str:
    path = unquote(urlparse(str(url or "").split("?", 1)[0]).path)
    name = path.rsplit("/", 1)[-1]
    if "." not in name:
        return "bin"
    ext = name.rsplit(".", 1)[-1].lower()
    if not ext or len(ext) > 8 or "/" in ext:
        return "bin"
    return ext


def build_attachment_filename(row_no: int, label: str, url: str) -> str:
    return (
        f"{int(row_no):02d}_{sanitize_zip_segment(label)}_"
        f"{short_hash(url)}.{guess_ext_from_url(url)}"
    )


def first_row_no_by_plan_id(rows: Sequence[Mapping[str, Any]]) -> dict[str, int]:
    out: dict[str, int] = {}
    for row in rows:
        plan_id = str(row.get("planId") or "").strip()
        if not plan_id or plan_id in out:
            continue
        try:
            out[plan_id] = int(row.get("rowNo") or 0)
        except (TypeError, ValueError):
            out[plan_id] = 0
    return out


def build_hyperlink_formula(rel_path: str, display: str) -> str:
    path = str(rel_path).replace('"', '""')
    text = sanitize_zip_segment(display).replace('"', '""')
    return f'=HYPERLINK("{path}","{text}")'