whisper-local/whisper_local/microphone/_win32.py

# whisper_local/microphone/_win32.py
"""Windows Mikrofon-Monitor via IMMNotificationClient (Core Audio API)."""
import asyncio
import ctypes
import logging
from collections.abc import Awaitable, Callable

import sounddevice as sd

logger = logging.getLogger(__name__)

_CLSID_MMDeviceEnumerator = "{BCDE0395-E52F-467C-8E3D-C4579291692E}"
_IID_IMMDeviceEnumerator = "{A95664D2-9614-4F35-A746-DE8DB63617E6}"
_IID_IMMNotificationClient = "{7991EEC9-7E89-4D85-8390-6C703CEC60C0}"


def _build_com_interfaces():
    """Definiert IMMDeviceEnumerator und IMMNotificationClient via comtypes."""
    import comtypes
    from comtypes import COMMETHOD, GUID, HRESULT, IUnknown, POINTER

    class _IMMNotificationClient(IUnknown):
        _iid_ = GUID(_IID_IMMNotificationClient)
        _methods_ = [
            COMMETHOD([], HRESULT, "OnDeviceStateChanged",
                      (["in"], ctypes.c_wchar_p, "pwstrDeviceId"),
                      (["in"], ctypes.c_uint, "dwNewState")),
            COMMETHOD([], HRESULT, "OnDeviceAdded",
                      (["in"], ctypes.c_wchar_p, "pwstrDeviceId")),
            COMMETHOD([], HRESULT, "OnDeviceRemoved",
                      (["in"], ctypes.c_wchar_p, "pwstrDeviceId")),
            COMMETHOD([], HRESULT, "OnDefaultDeviceChanged",
                      (["in"], ctypes.c_int, "flow"),
                      (["in"], ctypes.c_int, "role"),
                      (["in"], ctypes.c_wchar_p, "pwstrDefaultDeviceId")),
            COMMETHOD([], HRESULT, "OnPropertyValueChanged",
                      (["in"], ctypes.c_wchar_p, "pwstrDeviceId"),
                      (["in"], ctypes.c_void_p, "key")),
        ]

    class _IMMDeviceEnumerator(IUnknown):
        _iid_ = GUID(_IID_IMMDeviceEnumerator)
        _methods_ = [
            COMMETHOD([], HRESULT, "EnumAudioEndpoints",
                      (["in"], ctypes.c_int, "dataFlow"),
                      (["in"], ctypes.c_uint, "dwStateMask"),
                      (["out"], POINTER(IUnknown), "ppDevices")),
            COMMETHOD([], HRESULT, "GetDefaultAudioEndpoint",
                      (["in"], ctypes.c_int, "dataFlow"),
                      (["in"], ctypes.c_int, "role"),
                      (["out"], POINTER(IUnknown), "ppEndpoint")),
            COMMETHOD([], HRESULT, "GetDevice",
                      (["in"], ctypes.c_wchar_p, "pwstrId"),
                      (["out"], POINTER(IUnknown), "ppDevice")),
            COMMETHOD([], HRESULT, "RegisterEndpointNotificationCallback",
                      (["in"], POINTER(_IMMNotificationClient), "pClient")),
            COMMETHOD([], HRESULT, "UnregisterEndpointNotificationCallback",
                      (["in"], POINTER(_IMMNotificationClient), "pClient")),
        ]

    return _IMMNotificationClient, _IMMDeviceEnumerator


def _build_client_class(IMMNotificationClient, callback):
    """Erstellt eine comtypes.COMObject-Implementierung von IMMNotificationClient."""
    import comtypes

    class _NotificationClientImpl(comtypes.COMObject):
        _com_interfaces_ = [IMMNotificationClient]

        def OnDeviceStateChanged(self, pwstrDeviceId, dwNewState):
            callback()
            return 0

        def OnDeviceAdded(self, pwstrDeviceId):
            callback()
            return 0

        def OnDeviceRemoved(self, pwstrDeviceId):
            callback()
            return 0

        def OnDefaultDeviceChanged(self, flow, role, pwstrDefaultDeviceId):
            return 0

        def OnPropertyValueChanged(self, pwstrDeviceId, key):
            return 0

    return _NotificationClientImpl()


class Win32Monitor:
    def __init__(self, configured_device: str | None):
        self.configured_device = configured_device
        self.on_device_added: Callable[[str], Awaitable[None]] | None = None
        self.on_device_removed: Callable[[str], Awaitable[None]] | None = None
        self.on_configured_missing: Callable[[], Awaitable[None]] | None = None
        self._loop: asyncio.AbstractEventLoop | None = None
        self._known_devices: set[str] = set()
        self._enumerator = None
        self._client = None
        self._fallback = None

    def _current_devices(self) -> set[str]:
        try:
            return {
                dev["name"]
                for dev in sd.query_devices()
                if dev["max_input_channels"] > 0
            }
        except Exception:
            logger.exception("Fehler beim Abfragen der Audiogeräte")
            return self._known_devices.copy()

    async def start(self) -> None:
        self._loop = asyncio.get_running_loop()
        self._known_devices = self._current_devices()

        if (
            self.configured_device
            and self.configured_device not in self._known_devices
            and self.on_configured_missing
        ):
            await self.on_configured_missing()

        try:
            self._start_com()
        except Exception:
            logger.warning(
                "IMMNotificationClient nicht verfügbar, Fallback auf Polling",
                exc_info=True,
            )
            from whisper_local.microphone._poll import PollMonitor
            fallback = PollMonitor(self.configured_device)
            fallback.on_device_added = self.on_device_added
            fallback.on_device_removed = self.on_device_removed
            fallback._known_devices = self._known_devices
            self._fallback = fallback
            self._fallback._task = asyncio.create_task(self._fallback._loop())

    def _start_com(self) -> None:
        import comtypes
        import comtypes.client
        from comtypes import GUID

        comtypes.CoInitialize()
        IMMNotificationClient, IMMDeviceEnumerator = _build_com_interfaces()
        self._enumerator = comtypes.client.CreateObject(
            GUID(_CLSID_MMDeviceEnumerator),
            interface=IMMDeviceEnumerator,
        )
        self._client = _build_client_class(IMMNotificationClient, self._on_com_event)
        self._enumerator.RegisterEndpointNotificationCallback(self._client)

    def _on_com_event(self) -> None:
        if self._loop is not None:
            self._loop.call_soon_threadsafe(
                lambda: asyncio.ensure_future(self._handle_change())
            )

    async def _handle_change(self) -> None:
        current = self._current_devices()
        added = current - self._known_devices
        removed = self._known_devices - current
        self._known_devices = current

        for name in added:
            if self.on_device_added:
                await self.on_device_added(name)

        for name in removed:
            if self.on_device_removed:
                await self.on_device_removed(name)

    def stop(self) -> None:
        if self._fallback is not None:
            self._fallback.stop()
            return
        if self._enumerator is not None and self._client is not None:
            try:
                self._enumerator.UnregisterEndpointNotificationCallback(self._client)
            except Exception:
                logger.warning("Fehler beim Deregistrieren des Notification-Clients")
            try:
                import comtypes
                comtypes.CoUninitialize()
            except Exception:
                pass