from __future__ import annotations

import re
import unicodedata


def normalize_open_id(open_id: str) -> str:
    return open_id.strip().lower() if open_id else ""


def normalize_chat_id(chat_id: str) -> str:
    return chat_id.strip() if chat_id else ""


def safe_filename(name: str) -> str:
    name = re.sub(r"[\x00-\x1f\x7f-\x9f]", "", name)
    name = name.replace('"', "'").replace("\\", "_")
    return name.strip() or "file"


def recover_latin1_filename(value: str) -> str:
    try:
        return value.encode("latin-1").decode("utf-8")
    except (UnicodeEncodeError, UnicodeDecodeError):
        return value


def build_sequential_key(chat_id: str, account_id: str) -> str:
    return f"{account_id}:{chat_id}"


def parse_feishu_allow_entry(entry: str) -> tuple[str, str]:
    entry = entry.strip()
    if entry == "*":
        return ("wildcard", "*")
    if ":" in entry:
        prefix, value = entry.split(":", 1)
        return (prefix.strip().lower(), value.strip())
    if entry.startswith("oc_"):
        return ("chat", entry)
    if entry.startswith("ou_"):
        return ("user", entry)
    return ("unknown", entry)


def is_broadcast_mention(mention_key: str) -> bool:
    return mention_key in ("@all", "@_all", "@everyone")


def extract_image_keys(text: str) -> list[str]:
    return re.findall(r"img_v2_[a-zA-Z0-9]+", text)


def sanitize_markdown_escape(text: str) -> str:
    special_chars = r"\*_{}[]()#+-!|>~"
    result = []
    for ch in text:
        if ch in special_chars:
            result.append("\\" + ch)
        else:
            result.append(ch)
    return "".join(result)


def ellipsize(text: str, max_len: int = 100) -> str:
    if len(text) <= max_len:
        return text
    return text[: max_len - 1] + "…"


def strip_control_chars(text: str) -> str:
    return "".join(ch for ch in text if unicodedata.category(ch)[0] != "C" or ch in ("\n", "\r", "\t"))