DuoDuoProject/xiaozhi-esp32-server-0.7.1/main/xiaozhi-server/core/handle/receiveAudioHandle.py

from core.handle.sendAudioHandle import send_stt_message
from core.handle.intentHandler import handle_user_intent
from core.utils.output_counter import check_device_output_limit
from core.handle.abortHandle import handleAbortMessage
import time
import asyncio
import json
from core.handle.sendAudioHandle import SentenceType
from core.utils.util import audio_to_data

TAG = __name__


async def handleAudioMessage(conn, audio):
    # 当前片段是否有人说话
    have_voice = conn.vad.is_vad(conn, audio)
    # 如果设备刚刚被唤醒，短暂忽略VAD检测
    if have_voice and hasattr(conn, "just_woken_up") and conn.just_woken_up:
        have_voice = False
        # 设置一个短暂延迟后恢复VAD检测
        conn.asr_audio.clear()
        if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
            conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
        return

    if have_voice:
        if conn.client_is_speaking:
            await handleAbortMessage(conn)
    # 设备长时间空闲检测，用于say goodbye
    await no_voice_close_connect(conn, have_voice)
    # 接收音频
    await conn.asr.receive_audio(conn, audio, have_voice)


async def resume_vad_detection(conn):
    # 等待2秒后恢复VAD检测
    await asyncio.sleep(1)
    conn.just_woken_up = False


async def startToChat(conn, text):
    # 检查输入是否是JSON格式（包含说话人信息）
    speaker_name = None
    actual_text = text
    
    try:
        # 尝试解析JSON格式的输入
        if text.strip().startswith('{') and text.strip().endswith('}'):
            data = json.loads(text)
            if 'speaker' in data and 'content' in data:
                speaker_name = data['speaker']
                actual_text = data['content']
                conn.logger.bind(tag=TAG).info(f"解析到说话人信息: {speaker_name}")
                
                # 直接使用JSON格式的文本，不解析
                actual_text = text
    except (json.JSONDecodeError, KeyError):
        # 如果解析失败，继续使用原始文本
        pass
    
    # 保存说话人信息到连接对象
    if speaker_name:
        conn.current_speaker = speaker_name
    else:
        conn.current_speaker = None

    if conn.need_bind:
        await check_bind_device(conn)
        return

    # 如果当日的输出字数大于限定的字数
    if conn.max_output_size > 0:
        if check_device_output_limit(
            conn.headers.get("device-id"), conn.max_output_size
        ):
            await max_out_size(conn)
            return
    if conn.client_is_speaking:
        await handleAbortMessage(conn)

    # 首先进行意图分析，使用实际文本内容
    intent_handled = await handle_user_intent(conn, actual_text)

    if intent_handled:
        # 如果意图已被处理，不再进行聊天
        return

    # 意图未被处理，继续常规聊天流程，使用实际文本内容
    await send_stt_message(conn, actual_text)
    conn.executor.submit(conn.chat, actual_text)


async def no_voice_close_connect(conn, have_voice):
    if have_voice:
        conn.last_activity_time = time.time() * 1000
        return
    # 只有在已经初始化过时间戳的情况下才进行超时检查
    if conn.last_activity_time > 0.0:
        no_voice_time = time.time() * 1000 - conn.last_activity_time
        close_connection_no_voice_time = int(
            conn.config.get("close_connection_no_voice_time", 120)
        )
        if (
            not conn.close_after_chat
            and no_voice_time > 1000 * close_connection_no_voice_time
        ):
            conn.close_after_chat = True
            conn.client_abort = False
            end_prompt = conn.config.get("end_prompt", {})
            if end_prompt and end_prompt.get("enable", True) is False:
                conn.logger.bind(tag=TAG).info("结束对话，无需发送结束提示语")
                await conn.close()
                return
            prompt = end_prompt.get("prompt")
            if not prompt:
                prompt = "请你以```时间过得真快```未来头，用富有感情、依依不舍的话来结束这场对话吧。！"
            await startToChat(conn, prompt)


async def max_out_size(conn):
    text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
    await send_stt_message(conn, text)
    file_path = "config/assets/max_output_size.wav"
    opus_packets, _ = audio_to_data(file_path)
    conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))
    conn.close_after_chat = True


async def check_bind_device(conn):
    if conn.bind_code:
        # 确保bind_code是6位数字
        if len(conn.bind_code) != 6:
            conn.logger.bind(tag=TAG).error(f"无效的绑定码格式: {conn.bind_code}")
            text = "绑定码格式错误，请检查配置。"
            await send_stt_message(conn, text)
            return

        text = f"请登录控制面板，输入{conn.bind_code}，绑定设备。"
        await send_stt_message(conn, text)

        # 播放提示音
        music_path = "config/assets/bind_code.wav"
        opus_packets, _ = audio_to_data(music_path)
        conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, text))

        # 逐个播放数字
        for i in range(6):  # 确保只播放6位数字
            try:
                digit = conn.bind_code[i]
                num_path = f"config/assets/bind_code/{digit}.wav"
                num_packets, _ = audio_to_data(num_path)
                conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, num_packets, None))
            except Exception as e:
                conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
                continue
        conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
    else:
        text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
        await send_stt_message(conn, text)
        music_path = "config/assets/bind_not_found.wav"
        opus_packets, _ = audio_to_data(music_path)
        conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text))