feat(engine): 优化字幕引擎通信和控制逻辑，优化窗口信息展示

- 优化错误处理和引擎重启逻辑
- 添加字幕引擎强制终止功能
- 调整通知和错误提示的显示位置
- 优化日志记录精度到毫秒级

docs/CHANGELOG.md

@@ -123,9 +123,13 @@
 
 - 新增字幕记录排序功能，可选择字幕记录正序或倒叙显示
 
+### 优化体验
+
+- 交换窗口界面信息和错误提示弹窗的位置，防止提示信息挡住操作
+
 ### 项目优化
 
 - 重构字幕引擎，提示字幕引擎代码的可扩展性和可读性
-- 合并 Gummy 和 Vosk 引擎为单个可执行文件
+- 合并 Gummy 和 Vosk 引擎为单个可执行文件，减小软件体积
 - 字幕引擎和主程序添加 WebScoket 通信，完全避免字幕引擎成为孤儿进程
 

docs/api-docs/caption-engine.md

@@ -1,17 +1,63 @@
 # caption engine api-doc
 
-本文档主要 Electron 主进程和字幕引擎进程的通信约定。
+本文档主要介绍字幕引擎和 Electron 主进程进程的通信约定。
 
 ## 原理说明
 
-本项目的 Python 进程通过标准输出向 Electron 主进程发送数据。
+本项目的 Python 进程通过标准输出向 Electron 主进程发送数据。Python 进程标准输出 (`sys.stdout`) 的内容一定为一行一行的字符串。且每行字符串均可以解释为一个 JSON 对象。每个 JSON 对象一定有 `command` 参数。
 
-Python 进程标准输出 (`sys.stdout`) 的内容一定为一行一行的字符串。且每行字符串均可以解释为一个 JSON 对象。每个 JSON 对象一定有 `command` 参数。
+Electron 主进程通过 WebSocket 向 Python 进程发送数据。发送的数据均是转化为字符串的对象，对象格式一定为：
 
-## 输出约定
+```js
+{
+  command: string,
+  content: string
+}
+```
+
+## 标准输出约定
+
+> 数据传递方向：字幕引擎进程 => Electron 主进程
 
 当 JSON 对象的 `command` 参数为下列值时，表示的对应的含义：
 
+### `connect`
+
+```js
+{
+  command: "connect",
+  content: ""
+}
+```
+
+字幕引擎 WebSocket 服务已经准备好，命令 Electron 主进程连接字幕引擎 WebSocket 服务
+
+### `kill`
+
+```js
+{
+  command: "connect",
+  content: ""
+}
+```
+
+命令 Electron 主进程强制结束字幕引擎进程。
+
+### `caption`
+
+```js
+{
+  command: "caption",
+  index: number,
+  time_s: string,
+  time_t: string,
+  text: string,
+  translation: string
+}
+```
+
+Python 端监听到的音频流转换为的字幕数据。
+
 ### `print`
 
 ```js
@@ -45,18 +91,12 @@ Python 端打印的提示信息，比起 `print`，该信息更希望 Electron
 
 Gummy 字幕引擎结束时打印计费消耗信息。
 
+## WebSocket
 
-### `caption`
+> 数据传递方向：Electron 主进程 => 字幕引擎进程
 
-```js
-{
-  command: "caption",
-  index: number,
-  time_s: string,
-  time_t: string,
-  text: string,
-  translation: string
-}
-```
+当 JSON 对象的 `command` 参数为下列值时，表示的对应的含义：
 
-Python 端监听到的音频流转换为的字幕数据。
+### `stop`
+
+命令当前字幕引擎停止监听并结束任务。

engine/audio2text/gummy.py

@@ -6,7 +6,7 @@ from dashscope.audio.asr import (
 )
 import dashscope
 from datetime import datetime
-from utils import stdout_cmd, stdout_obj
+from utils import stdout_cmd, stdout_obj, stderr
 
 
 class Callback(TranslationRecognizerCallback):
@@ -96,4 +96,7 @@ class GummyRecognizer:
 
     def stop(self):
         """停止 Gummy 引擎"""
-        self.translator.stop()
+        try:
+            self.translator.stop()
+        except Exception:
+            return

engine/main.py

@@ -1,5 +1,5 @@
 import argparse
-from utils import stdout_cmd
+from utils import stdout_cmd, stderr
 from utils import thread_data, start_server
 from utils import merge_chunk_channels, resample_chunk_mono
 from audio2text import InvalidParameter, GummyRecognizer
@@ -8,6 +8,7 @@ from sysaudio import AudioStream
 
 
 def main_gummy(s: str, t: str, a: int, c: int, k: str):
+    global thread_data
     stream = AudioStream(a, c)
     if t == 'none':
         engine = GummyRecognizer(stream.RATE, s, None, k)
@@ -17,6 +18,7 @@ def main_gummy(s: str, t: str, a: int, c: int, k: str):
     stream.open_stream()
     engine.start()
 
+    restart_count = 0
     while thread_data.status == "running":
         try:
             chunk = stream.read_chunk()
@@ -24,18 +26,22 @@ def main_gummy(s: str, t: str, a: int, c: int, k: str):
             chunk_mono = merge_chunk_channels(chunk, stream.CHANNELS)
             try:
                 engine.send_audio_frame(chunk_mono)
-            except InvalidParameter:
-                stdout_cmd('info', 'Gummy engine stopped, restart engine')
-                engine.start()
-                engine.send_audio_frame(chunk_mono)
+            except InvalidParameter as e:
+                restart_count += 1
+                if restart_count > 8:
+                    stderr(str(e))
+                    thread_data.status = "kill"
+                    break
+                else:
+                    stdout_cmd('info', f'Gummy engine stopped, trying to restart #{restart_count}')
         except KeyboardInterrupt:
             break
 
     stream.close_stream()
     engine.stop()
 
-
 def main_vosk(a: int, c: int, m: str):
+    global thread_data
     stream = AudioStream(a, c)
     engine = VoskRecognizer(m)
 
@@ -68,9 +74,8 @@ if __name__ == "__main__":
     parser.add_argument('-k', '--api_key', default='', help='API KEY for Gummy model')
     # vosk
     parser.add_argument('-m', '--model_path', default='', help='The path to the vosk model.')
-    # for test
-    args = parser.parse_args()
-    
+
+    args = parser.parse_args()    
     if int(args.port) == 0:
         thread_data.status = "running"
     else:
@@ -91,4 +96,7 @@ if __name__ == "__main__":
             args.model_path
         )
     else:
-        raise ValueError('Invalid caption engine specified.')
+        raise ValueError('Invalid caption engine specified.')
+    
+    if thread_data.status == "kill":
+        stdout_cmd('kill')

engine/utils/audioprcs.py

@@ -1,6 +1,6 @@
 import samplerate
 import numpy as np
-import numpy.core.multiarray
+import numpy.core.multiarray # do not remove
 
 def merge_chunk_channels(chunk: bytes, channels: int) -> bytes:
     """

engine/utils/server.py

@@ -6,7 +6,7 @@ from utils import thread_data, stdout_cmd, stderr
 
 def handle_client(client_socket):
     global thread_data
-    while True:
+    while thread_data.status == 'running':
         try:
             data = client_socket.recv(4096).decode('utf-8')
             if not data:
@@ -14,9 +14,8 @@ def handle_client(client_socket):
             data = json.loads(data)
 
             if data['command'] == 'stop':
-                if thread_data.status == 'running':
-                    thread_data.status = 'stop'
-                    break
+                thread_data.status = 'stop'
+                break
         except Exception as e:
             stderr(f'Communication error: {e}')
             break
@@ -29,7 +28,7 @@ def start_server(port: int):
     server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
     server.bind(('localhost', port))
     server.listen(1)
-    stdout_cmd('ready')
+    stdout_cmd('connect')
 
     client, addr = server.accept()
     client_handler = threading.Thread(target=handle_client, args=(client,))

src/main/utils/CaptionEngine.ts

@@ -1,4 +1,4 @@
-import { spawn } from 'child_process'
+import { exec, spawn } from 'child_process'
 import { app } from 'electron'
 import { is } from '@electron-toolkit/utils'
 import path from 'path'
@@ -13,11 +13,11 @@ export class CaptionEngine {
   command: string[] = []
   process: any | undefined
   client: net.Socket | undefined
-  status: 'running' | 'stopping' | 'stopped' = 'stopped'
+  status: 'running' | 'starting' | 'stopping' | 'stopped' = 'stopped'
 
   private getApp(): boolean {
     if (allConfig.controls.customized) {
-      Log.info('Using customized engine')
+      Log.info('Using customized caption engine')
       this.appPath = allConfig.controls.customizedApp
       this.command = allConfig.controls.customizedCommand.split(' ')
     }
@@ -30,14 +30,14 @@ export class CaptionEngine {
       }
       this.command = []
       if (is.dev) {
-        // this.appPath = path.join(
-        //   app.getAppPath(), 'engine',
-        //   'subenv', 'Scripts', 'python.exe'
-        // )
-        // this.command.push(path.join(
-        //   app.getAppPath(), 'engine', 'main.py'
-        // ))
-        this.appPath = path.join(app.getAppPath(), 'engine', 'dist', 'main.exe')
+        this.appPath = path.join(
+          app.getAppPath(), 'engine',
+          'subenv', 'Scripts', 'python.exe'
+        )
+        this.command.push(path.join(
+          app.getAppPath(), 'engine', 'main.py'
+        ))
+        // this.appPath = path.join(app.getAppPath(), 'engine', 'dist', 'main.exe')
       }
       else {
         this.appPath = path.join(process.resourcesPath, 'engine', 'main.exe')
@@ -73,6 +73,14 @@ export class CaptionEngine {
       Log.info('Connected to caption engine server');
     });
     this.status = 'running'
+    allConfig.controls.engineEnabled = true
+    if(controlWindow.window){
+      allConfig.sendControls(controlWindow.window)
+      controlWindow.window.webContents.send(
+        'control.engine.started',
+        this.process.pid
+      )
+    }
   }
 
   public sendCommand(command: string, content: string = "") {
@@ -93,19 +101,11 @@ export class CaptionEngine {
     if(!this.getApp()){ return }
 
     this.process = spawn(this.appPath, this.command)
-    Log.info('Caption Engine Started, PID:', this.process.pid)
-
-    allConfig.controls.engineEnabled = true
-    if(controlWindow.window){
-      allConfig.sendControls(controlWindow.window)
-      controlWindow.window.webContents.send(
-        'control.engine.started',
-        this.process.pid
-      )
-    }
-
+    this.status = 'starting'
+    Log.info('Caption Engine Starting, PID:', this.process.pid)
+    
     this.process.stdout.on('data', (data: any) => {
-      const lines = data.toString().split('\n');
+      const lines = data.toString().split('\n')
       lines.forEach((line: string) => {
         if (line.trim()) {
           try {
@@ -120,13 +120,18 @@ export class CaptionEngine {
     });
 
     this.process.stderr.on('data', (data: any) => {
-      if(this.status === 'stopping') return
-      controlWindow.sendErrorMessage(i18n('engine.error') + data)
-      Log.error(`Engine Error: ${data}`);
+      const lines = data.toString().split('\n')
+      lines.forEach((line: string) => {
+        if(line.trim()){
+          controlWindow.sendErrorMessage(/*i18n('engine.error') +*/ line)
+          console.error(line)          
+        }
+      })
     });
 
     this.process.on('close', (code: any) => {
       this.process = undefined;
+      this.client = undefined
       allConfig.controls.engineEnabled = false
       if(controlWindow.window){
         allConfig.sendControls(controlWindow.window)
@@ -150,25 +155,52 @@ export class CaptionEngine {
     this.status = 'stopping'
     Log.info('Caption engine process stopping...')
   }
+
+  public kill(){
+    if(this.status !== 'running'){
+      Log.warn('Engine is not running, current status:', this.status)
+      return
+    }
+    if (this.process.pid) {
+      Log.warn('Trying to kill engine process, PID:', this.process.pid)
+      if(this.client){
+        this.client.destroy()
+        this.client = undefined
+      }
+      let cmd = `kill ${this.process.pid}`;
+      if (process.platform === "win32") {
+        cmd = `taskkill /pid ${this.process.pid} /t /f`
+      }
+      exec(cmd)
+    }
+    this.status = 'stopping'
+  }
 }
 
 function handleEngineData(data: any) {
-  if(data.command === 'ready'){
+  if(data.command === 'connect'){
     captionEngine.connect()
   }
+  else if(data.command === 'kill') {
+    if(captionEngine.status !== 'stopped') {
+      Log.warn('Error occurred, trying to kill Gummy engine...')
+      captionEngine.kill()
+    }
+  }
   else if(data.command === 'caption') {
     allConfig.updateCaptionLog(data);
   }
   else if(data.command === 'print') {
-    console.log(data.content)
-    // Log.info('Engine Print:', data.content)
+    Log.info('Engine Print:', data.content)
   }
   else if(data.command === 'info') {
     Log.info('Engine Info:', data.content)
   }
   else if(data.command === 'usage') {
-    console.error(data.content)
-    // Log.info('Gummy Engine Usage: ', data.content)
+    Log.info('Gummy Engine Usage: ', data.content)
+  }
+  else {
+    Log.warn('Unknown command:', data)
   }
 }
 

src/main/utils/Log.ts

@@ -3,7 +3,8 @@ function getTimeString() {
   const HH = String(now.getHours()).padStart(2, '0')
   const MM = String(now.getMinutes()).padStart(2, '0')
   const SS = String(now.getSeconds()).padStart(2, '0')
-  return `${HH}:${MM}:${SS}`
+  const MS = String(now.getMilliseconds()).padStart(3, '0')
+  return `${HH}:${MM}:${SS}.${MS}`
 }
 
 export class Log {

src/renderer/src/components/CaptionStyle.vue

@@ -282,7 +282,8 @@ function applyStyle(){
 
   captionStyle.sendStylesChange();
 
-    notification.open({
+  notification.open({
+    placement: 'topLeft',
     message: t('noti.styleChange'),
     description: t('noti.styleInfo')
   });

src/renderer/src/components/EngineControl.vue

@@ -164,6 +164,7 @@ function applyChange(){
   engineControl.sendControlsChange()
 
   notification.open({
+    placement: 'topLeft',
     message: t('noti.engineChange'),
     description: t('noti.changeInfo')
   });

src/renderer/src/components/EngineStatus.vue

@@ -61,12 +61,14 @@
     >{{ $t('status.openCaption') }}</a-button>
     <a-button
       class="control-button"
-      :disabled="engineEnabled"
+      :loading="pending && !engineEnabled"
+      :disabled="pending || engineEnabled"
       @click="startEngine"
     >{{ $t('status.startEngine') }}</a-button>
     <a-button
      danger class="control-button"
-     :disabled="!engineEnabled"
+     :loading="pending && engineEnabled"
+     :disabled="pending || !engineEnabled"
      @click="stopEngine"
     >{{ $t('status.stopEngine') }}</a-button>
   </div>
@@ -119,13 +121,14 @@
 
 <script setup lang="ts">
 import { EngineInfo } from '@renderer/types'
-import { ref } from 'vue'
+import { ref, watch } from 'vue'
 import { storeToRefs } from 'pinia'
 import { useCaptionLogStore } from '@renderer/stores/captionLog'
 import { useEngineControlStore } from '@renderer/stores/engineControl'
 import { GithubOutlined, InfoCircleOutlined } from '@ant-design/icons-vue';
 
 const showAbout = ref(false)
+const pending = ref(false)
 
 const captionLog = useCaptionLogStore()
 const { captionData } = storeToRefs(captionLog)
@@ -143,6 +146,7 @@ function openCaptionWindow() {
 }
 
 function startEngine() {
+  pending.value = true
   if(engineControl.engine === 'vosk' && engineControl.modelPath.trim() === '') {
     engineControl.emptyModelPathErr()
     return
@@ -151,6 +155,7 @@ function startEngine() {
 }
 
 function stopEngine() {
+  pending.value = true
   window.electron.ipcRenderer.send('control.engine.stop')
 }
 
@@ -164,6 +169,9 @@ function getEngineInfo() {
   })
 }
 
+watch(engineEnabled, () => {
+  pending.value = false
+})
 </script>
 
 <style scoped>

src/renderer/src/stores/engineControl.ts

@@ -64,6 +64,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
 
   function emptyModelPathErr() {
     notification.open({
+      placement: 'topLeft',
       message: t('noti.empty'),
       description: t('noti.emptyInfo')
     });
@@ -80,6 +81,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
       (translation.value ? `${t('noti.tLang')}${targetLang.value}` : '');
     const str1 = `${t('noti.custom')}${customizedApp.value}${t('noti.args')}${customizedCommand.value}`;
     notification.open({
+      placement: 'topLeft',
       message: t('noti.started'),
       description:
         (customized.value ? str1 : str0) +
@@ -89,6 +91,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
 
   window.electron.ipcRenderer.on('control.engine.stopped', () => {
     notification.open({
+      placement: 'topLeft',
       message: t('noti.stopped'),
       description: t('noti.stoppedInfo')
     });
@@ -99,7 +102,6 @@ export const useEngineControlStore = defineStore('engineControl', () => {
       message: t('noti.error'),
       description: message,
       duration: null,
-      placement: 'topLeft',
       icon: () => h(ExclamationCircleOutlined, { style: 'color: #ff4d4f' })
     });
   })