from __future__ import annotations

from typing import TYPE_CHECKING, Any

from yuxi.channels.models import DeliveryResult
from yuxi.utils.logging_config import logger

if TYPE_CHECKING:
    from nio import AsyncClient

_MSC3245_VOICE_FLAG = "org.matrix.msc3245.voice"
_MSC1767_AUDIO_FLAG = "org.matrix.msc1767.audio"


async def send_voice_note(
    client: AsyncClient,
    room_id: str,
    audio_data: bytes,
    filename: str = "voice.ogg",
    duration_ms: int = 0,
    mime_type: str = "audio/ogg",
    caption: str = "",
    reply_to: str | None = None,
) -> DeliveryResult:
    try:
        upload_resp, _ = await client.upload(audio_data, content_type=mime_type, filename=filename)
    except Exception as e:
        return DeliveryResult(success=False, error=f"Voice upload failed: {e}")

    mxc_url = upload_resp.content_uri
    logger.debug(f"Matrix voice note uploaded: {mxc_url}")

    content: dict[str, Any] = {
        "msgtype": "m.audio",
        "body": caption or filename,
        "url": mxc_url,
        "info": {"mimetype": mime_type, "duration": duration_ms},
    }

    content[_MSC3245_VOICE_FLAG] = {}
    content[_MSC1767_AUDIO_FLAG] = {"duration": duration_ms}

    if reply_to:
        content["m.relates_to"] = {"m.in_reply_to": {"event_id": reply_to}}

    try:
        resp = await client.room_send(
            room_id=room_id,
            message_type="m.room.message",
            content=content,
        )
        return DeliveryResult(success=True, message_id=resp.event_id)
    except Exception as e:
        return DeliveryResult(success=False, error=str(e))


async def send_tts_message(
    client: AsyncClient,
    room_id: str,
    text: str,
    audio_data: bytes,
    filename: str = "tts.ogg",
    duration_ms: int = 0,
    mime_type: str = "audio/ogg",
) -> DeliveryResult:
    tts_caption = f"[TTS] {text[:200]}" + ("..." if len(text) > 200 else "")
    return await send_voice_note(
        client=client,
        room_id=room_id,
        audio_data=audio_data,
        filename=filename,
        duration_ms=duration_ms,
        mime_type=mime_type,
        caption=tts_caption,
    )


def is_voice_message(event_source: dict[str, Any]) -> bool:
    content = event_source.get("content", {})
    if content.get("msgtype") == "m.audio":
        if _MSC3245_VOICE_FLAG in content:
            return True
        if _MSC1767_AUDIO_FLAG in content:
            audio_data = content[_MSC1767_AUDIO_FLAG]
            if isinstance(audio_data, dict) and audio_data.get("duration"):
                return True
    return False


def extract_audio_info(event_source: dict[str, Any]) -> dict[str, Any]:
    content = event_source.get("content", {})
    info = content.get("info", {})
    return {
        "duration_ms": info.get("duration", 0),
        "mime_type": info.get("mimetype", ""),
        "size": info.get("size", 0),
        "is_voice": is_voice_message(event_source),
    }