Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-29 18:23:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 为多个模块添加类型注解以增强代码可读性

Browse Source 
为 ConnectionHandler 相关的函数参数添加类型注解，使用 TYPE_CHECKING 避免循环导入。主要修改包括：
- 在 abortHandle、textHandle 等处理模块中为 conn 参数添加 ConnectionHandler 类型注解
- 在 websocket_server、connection 等核心模块中为方法参数添加类型注解
- 在 plugins_func 下的多个功能模块中为函数参数添加类型注解
- 在 providers 相关模块中为工具执行器和方法添加类型注解
- 统一代码格式，如将单引号字符串改为双引号

Fixes #2034
This commit is contained in:
huozaimengli
2026-01-25 17:47:52 +08:00
parent 275102f5b7
commit 4b573fb4e2
36 changed files with 338 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/asr/aliyun_stream.py
+7 -3
View File
@@ -13,6 +13,10 @@ from datetime import datetime
from config.logger import setup_logging
from core.providers.asr.base import ASRProviderBase
from core.providers.asr.dto.dto import InterfaceType
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -125,7 +129,7 @@ class ASRProvider(ASRProviderBase):
async def open_audio_channels(self, conn):
await super().open_audio_channels(conn)
async def receive_audio(self, conn, audio, audio_have_voice):
async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
# 初始化音频缓存
if not hasattr(conn, 'asr_audio_for_voiceprint'):
conn.asr_audio_for_voiceprint = []
@@ -154,7 +158,7 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).warning(f"发送音频失败: {str(e)}")
await self._cleanup(conn)
async def _start_recognition(self, conn):
async def _start_recognition(self, conn: "ConnectionHandler"):
"""开始识别会话"""
if self._is_token_expired():
self._refresh_token()
@@ -200,7 +204,7 @@ class ASRProvider(ASRProviderBase):
await self.asr_ws.send(json.dumps(start_request, ensure_ascii=False))
logger.bind(tag=TAG).debug("已发送开始请求，等待服务器准备...")
async def _forward_results(self, conn):
async def _forward_results(self, conn: "ConnectionHandler"):
"""转发识别结果"""
try:
while not conn.stop_event.is_set():
main/xiaozhi-server/core/providers/asr/aliyunbl_stream.py
+8 -4
View File
@@ -3,7 +3,11 @@ import uuid
import asyncio
import websockets
import opuslib_next
from typing import List
from typing import List, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from config.logger import setup_logging
from core.providers.asr.base import ASRProviderBase
from core.providers.asr.dto.dto import InterfaceType
@@ -51,7 +55,7 @@ class ASRProvider(ASRProviderBase):
async def open_audio_channels(self, conn):
await super().open_audio_channels(conn)
async def receive_audio(self, conn, audio, audio_have_voice):
async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
# 初始化音频缓存
if not hasattr(conn, 'asr_audio_for_voiceprint'):
conn.asr_audio_for_voiceprint = []
@@ -82,7 +86,7 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).warning(f"发送音频失败: {str(e)}")
await self._cleanup()
async def _start_recognition(self, conn):
async def _start_recognition(self, conn: "ConnectionHandler"):
"""开始识别会话"""
try:
# 如果为手动模式,设置超时时长为最大值
@@ -162,7 +166,7 @@ class ASRProvider(ASRProviderBase):
return message
async def _forward_results(self, conn):
async def _forward_results(self, conn: "ConnectionHandler"):
"""转发识别结果"""
try:
while not conn.stop_event.is_set():
main/xiaozhi-server/core/providers/asr/base.py
+8 -5
View File
@@ -11,7 +11,10 @@ import threading
import opuslib_next
from abc import ABC, abstractmethod
from config.logger import setup_logging
from typing import Optional, Tuple, List
from typing import Optional, Tuple, List, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from core.handle.receiveAudioHandle import startToChat
from core.handle.reportHandle import enqueue_asr_report
from core.utils.util import remove_punctuation_and_length
@@ -26,14 +29,14 @@ class ASRProviderBase(ABC):
pass
# 打开音频通道
async def open_audio_channels(self, conn):
async def open_audio_channels(self, conn: "ConnectionHandler"):
conn.asr_priority_thread = threading.Thread(
target=self.asr_text_priority_thread, args=(conn,), daemon=True
)
conn.asr_priority_thread.start()
# 有序处理ASR音频
def asr_text_priority_thread(self, conn):
def asr_text_priority_thread(self, conn: "ConnectionHandler"):
while not conn.stop_event.is_set():
try:
message = conn.asr_audio_queue.get(timeout=1)
@@ -51,7 +54,7 @@ class ASRProviderBase(ABC):
continue
# 接收音频
async def receive_audio(self, conn, audio, audio_have_voice):
async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
if conn.client_listen_mode == "manual":
# 手动模式：缓存音频用于ASR识别
conn.asr_audio.append(audio)
@@ -74,7 +77,7 @@ class ASRProviderBase(ABC):
await self.handle_voice_stop(conn, asr_audio_task)
# 处理语音停止
async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]):
async def handle_voice_stop(self, conn: "ConnectionHandler", asr_audio_task: List[bytes]):
"""并行处理ASR和声纹识别"""
try:
total_start_time = time.monotonic()
main/xiaozhi-server/core/providers/asr/doubao_stream.py
+50 -22
View File
@@ -7,6 +7,10 @@ import opuslib_next
from core.providers.asr.base import ASRProviderBase
from config.logger import setup_logging
from core.providers.asr.dto.dto import InterfaceType
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
TAG = __name__
logger = setup_logging()
@@ -34,7 +38,9 @@ class ASRProvider(ASRProviderBase):
# 火山引擎ASR配置
enable_multilingual = config.get("enable_multilingual", False)
self.enable_multilingual = False if str(enable_multilingual).lower() == 'false' else True
self.enable_multilingual = (
False if str(enable_multilingual).lower() == "false" else True
)
if self.enable_multilingual:
self.ws_url = "wss://openspeech.bytedance.com/api/v3/sauc/bigmodel_nostream"
else:
@@ -59,16 +65,20 @@ class ASRProvider(ASRProviderBase):
async def open_audio_channels(self, conn):
await super().open_audio_channels(conn)
async def receive_audio(self, conn, audio, audio_have_voice):
async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
conn.asr_audio.append(audio)
conn.asr_audio = conn.asr_audio[-10:]
# 存储音频数据
if not hasattr(conn, 'asr_audio_for_voiceprint'):
if not hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
conn.asr_audio_for_voiceprint.append(audio)
# 当没有音频数据时处理完整语音片段
if conn.client_listen_mode != "manual" and not audio and len(conn.asr_audio_for_voiceprint) > 0:
if (
conn.client_listen_mode != "manual"
and not audio
and len(conn.asr_audio_for_voiceprint) > 0
):
await self.handle_voice_stop(conn, conn.asr_audio_for_voiceprint)
conn.asr_audio_for_voiceprint = []
@@ -160,11 +170,11 @@ class ASRProvider(ASRProviderBase):
except Exception as e:
logger.bind(tag=TAG).info(f"发送音频数据时发生错误: {e}")
async def _forward_asr_results(self, conn):
async def _forward_asr_results(self, conn: "ConnectionHandler"):
try:
while self.asr_ws and not conn.stop_event.is_set():
# 获取当前连接的音频数据
audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
audio_data = getattr(conn, "asr_audio_for_voiceprint", [])
try:
response = await self.asr_ws.recv()
result = self.parse_response(response)
@@ -181,8 +191,9 @@ class ASRProvider(ASRProviderBase):
utterances = payload["result"].get("utterances", [])
# 检查duration和空文本的情况
if (
not self.enable_multilingual # 注意：多语种模式不返回中间结果，需要等待最终结果
and payload.get("audio_info", {}).get("duration", 0) > 2000
not self.enable_multilingual # 注意：多语种模式不返回中间结果，需要等待最终结果
and payload.get("audio_info", {}).get("duration", 0)
> 2000
and not utterances
and not payload["result"].get("text")
and conn.client_listen_mode != "manual"
@@ -200,8 +211,14 @@ class ASRProvider(ASRProviderBase):
if self.enable_multilingual:
continue
if conn.client_listen_mode == "manual" and conn.client_voice_stop and len(audio_data) > 0:
logger.bind(tag=TAG).debug("消息结束收到停止信号，触发处理")
if (
conn.client_listen_mode == "manual"
and conn.client_voice_stop
and len(audio_data) > 0
):
logger.bind(tag=TAG).debug(
"消息结束收到停止信号，触发处理"
)
await self.handle_voice_stop(conn, audio_data)
# 清理音频缓存
conn.asr_audio.clear()
@@ -223,9 +240,16 @@ class ASRProvider(ASRProviderBase):
self.text = current_text
# 在接收消息中途时收到停止信号
if conn.client_voice_stop and len(audio_data) > 0:
logger.bind(tag=TAG).debug("消息中途收到停止信号，触发处理")
await self.handle_voice_stop(conn, audio_data)
if (
conn.client_voice_stop
and len(audio_data) > 0
):
logger.bind(tag=TAG).debug(
"消息中途收到停止信号，触发处理"
)
await self.handle_voice_stop(
conn, audio_data
)
# 清理音频缓存
conn.asr_audio.clear()
conn.reset_vad_states()
@@ -235,7 +259,9 @@ class ASRProvider(ASRProviderBase):
self.text = current_text
conn.reset_vad_states()
if len(audio_data) > 15: # 确保有足够音频数据
await self.handle_voice_stop(conn, audio_data)
await self.handle_voice_stop(
conn, audio_data
)
break
elif "error" in payload:
error_msg = payload.get("error", "未知错误")
@@ -263,9 +289,9 @@ class ASRProvider(ASRProviderBase):
self.asr_ws = None
self.is_processing = False
if conn:
if hasattr(conn, 'asr_audio_for_voiceprint'):
if hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
if hasattr(conn, 'asr_audio'):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
def stop_ws_connection(self):
@@ -280,7 +306,9 @@ class ASRProvider(ASRProviderBase):
try:
# 发送结束标记的音频帧（gzip压缩的空数据）
empty_payload = gzip.compress(b"")
last_audio_request = bytearray(self.generate_last_audio_default_header())
last_audio_request = bytearray(
self.generate_last_audio_default_header()
)
last_audio_request.extend(len(empty_payload).to_bytes(4, "big"))
last_audio_request.extend(empty_payload)
await self.asr_ws.send(last_audio_request)
@@ -426,9 +454,9 @@ class ASRProvider(ASRProviderBase):
pass
self.forward_task = None
self.is_processing = False
# 显式释放decoder资源
if hasattr(self, 'decoder') and self.decoder is not None:
if hasattr(self, "decoder") and self.decoder is not None:
try:
del self.decoder
self.decoder = None
@@ -437,9 +465,9 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).debug(f"释放Doubao decoder资源时出错: {e}")
# 清理所有连接的音频缓冲区
if hasattr(self, '_connections'):
if hasattr(self, "_connections"):
for conn in self._connections.values():
if hasattr(conn, 'asr_audio_for_voiceprint'):
if hasattr(conn, "asr_audio_for_voiceprint"):
conn.asr_audio_for_voiceprint = []
if hasattr(conn, 'asr_audio'):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
main/xiaozhi-server/core/providers/asr/xunfei_stream.py
+13 -8
View File
@@ -9,7 +9,10 @@ import gc
from time import mktime
from datetime import datetime
from urllib.parse import urlencode
from typing import List
from typing import List, TYPE_CHECKING
if TYPE_CHECKING:
from core.connection import ConnectionHandler
from config.logger import setup_logging
from wsgiref.handlers import format_date_time
from core.providers.asr.base import ASRProviderBase
@@ -94,10 +97,10 @@ class ASRProvider(ASRProviderBase):
url = url + "?" + urlencode(v)
return url
async def open_audio_channels(self, conn):
async def open_audio_channels(self, conn: "ConnectionHandler"):
await super().open_audio_channels(conn)
async def receive_audio(self, conn, audio, audio_have_voice):
async def receive_audio(self, conn: "ConnectionHandler", audio, audio_have_voice):
# 先调用父类方法处理基础逻辑
await super().receive_audio(conn, audio, audio_have_voice)
@@ -124,7 +127,7 @@ class ASRProvider(ASRProviderBase):
logger.bind(tag=TAG).warning(f"发送音频数据时发生错误: {e}")
await self._cleanup()
async def _start_recognition(self, conn):
async def _start_recognition(self, conn: "ConnectionHandler"):
"""开始识别会话"""
try:
self.is_processing = True
@@ -194,7 +197,7 @@ class ASRProvider(ASRProviderBase):
await self.asr_ws.send(json.dumps(frame_data, ensure_ascii=False))
async def _forward_results(self, conn):
async def _forward_results(self, conn: "ConnectionHandler"):
"""转发识别结果"""
try:
while not conn.stop_event.is_set():
@@ -232,7 +235,7 @@ class ASRProvider(ASRProviderBase):
if status == 2:
if conn.client_listen_mode == "manual":
audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
audio_data = getattr(conn, "asr_audio_for_voiceprint", [])
if len(audio_data) > 0:
logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
await self.handle_voice_stop(conn, audio_data)
@@ -270,7 +273,9 @@ class ASRProvider(ASRProviderBase):
if hasattr(conn, "asr_audio"):
conn.asr_audio = []
async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]):
async def handle_voice_stop(
self, conn: "ConnectionHandler", asr_audio_task: List[bytes]
):
"""处理语音停止，发送最后一帧并处理识别结果"""
try:
# 先发送最后一帧表示音频结束
@@ -355,7 +360,7 @@ class ASRProvider(ASRProviderBase):
self.is_processing = False
# 显式释放decoder资源
if hasattr(self, 'decoder') and self.decoder is not None:
if hasattr(self, "decoder") and self.decoder is not None:
try:
del self.decoder
self.decoder = None