"""Microsoft Teams 媒体辅助工具。

提供 MIME 类型推断、文件名提取和消息 ID 提取。
"""

from __future__ import annotations

import mimetypes
import re
from pathlib import Path

_MIME_TYPE_MAP = {
    ".jpg": "image/jpeg",
    ".jpeg": "image/jpeg",
    ".png": "image/png",
    ".gif": "image/gif",
    ".bmp": "image/bmp",
    ".webp": "image/webp",
    ".svg": "image/svg+xml",
    ".pdf": "application/pdf",
    ".doc": "application/msword",
    ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    ".xls": "application/vnd.ms-excel",
    ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
    ".ppt": "application/vnd.ms-powerpoint",
    ".pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
    ".txt": "text/plain",
    ".csv": "text/csv",
    ".json": "application/json",
    ".xml": "application/xml",
    ".zip": "application/zip",
    ".mp4": "video/mp4",
    ".mov": "video/quicktime",
    ".avi": "video/x-msvideo",
    ".wmv": "video/x-ms-wmv",
    ".mp3": "audio/mpeg",
    ".wav": "audio/wav",
    ".ogg": "audio/ogg",
    ".flac": "audio/flac",
    ".aac": "audio/aac",
}

_MESSAGE_ID_PATTERN = re.compile(r"^(\d+)@thread\.(skype|tacv2)$")


def get_mime_type(filename: str) -> str:
    ext = Path(filename).suffix.lower()
    if ext in _MIME_TYPE_MAP:
        return _MIME_TYPE_MAP[ext]

    mime_type, _ = mimetypes.guess_type(filename)
    if mime_type:
        return mime_type

    return "application/octet-stream"


def extract_filename(url_or_path: str) -> str:
    if not url_or_path:
        return "unknown"

    cleaned = url_or_path.split("?")[0].split("#")[0]
    name = Path(cleaned).name
    return name or "unknown"


def extract_message_id(raw_id: str) -> str:
    """提取标准化消息 ID，去除 thread/tacv2 前缀格式。"""
    if not raw_id:
        return ""

    m = _MESSAGE_ID_PATTERN.match(raw_id)
    if m:
        return m.group(1)

    return raw_id