server_recording_api_async_backup.py 22.6 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
AIfeng/2025-07-01 16:51:01
服务端录音Web API接口 - aiohttp版本
提供HTTP和WebSocket接口控制服务端录音功能
"""

import asyncio
import json
import time
from typing import Dict, Any, Optional
from aiohttp import web, WSMsgType
import aiohttp_cors
import threading
import weakref

import util
from server_audio_recorder import ServerAudioRecorder, get_global_recorder, create_global_recorder, destroy_global_recorder, PYAUDIO_AVAILABLE
from funasr_asr import FunASRClient
import config_util as cfg
from logger import logger

class ServerRecordingAPI:
    """服务端录音API管理器 - aiohttp版本"""
    
    def __init__(self):
        self.recorder = None
        self.asr_client = None
        self.websocket_clients = weakref.WeakSet()
        
        logger.info("服务端录音API初始化完成")
    
    def register_routes(self, app: web.Application):
        """注册API路由到aiohttp应用"""
        
        # HTTP API路由
        app.router.add_get('/api/server-recording/status', self.get_recording_status)
        app.router.add_get('/api/server-recording/devices', self.list_audio_devices)
        app.router.add_post('/api/server-recording/start', self.start_recording)
        app.router.add_post('/api/server-recording/stop', self.stop_recording)
        app.router.add_get('/api/server-recording/config', self.get_recording_config)
        app.router.add_post('/api/server-recording/config', self.set_recording_config)
        
        # WebSocket路由
        app.router.add_get('/ws/server-recording', self.recording_websocket)
        
        # 测试页面
        app.router.add_get('/server-recording-test', self.test_page)
        
        logger.info("服务端录音API路由注册完成")
    
    async def get_recording_status(self, request):
        """获取录音状态"""
        try:
            if not PYAUDIO_AVAILABLE:
                return web.json_response({
                    'success': False,
                    'error': 'pyaudio未安装,服务端录音功能不可用',
                    'pyaudio_available': False
                })
            
            recorder = get_global_recorder()
            if recorder:
                status = recorder.get_status()
                status['success'] = True
                return web.json_response(status)
            else:
                return web.json_response({
                    'success': True,
                    'is_recording': False,
                    'pyaudio_available': True,
                    'recorder_created': False
                })
        except Exception as e:
            logger.error(f"获取录音状态失败: {e}")
            return web.json_response({
                'success': False,
                'error': str(e)
            })
    
    async def list_audio_devices(self, request):
        """列出音频设备"""
        try:
            if not PYAUDIO_AVAILABLE:
                return web.json_response({
                    'success': False,
                    'error': 'pyaudio未安装',
                    'devices': []
                })
            
            recorder = ServerAudioRecorder()
            devices = recorder.list_audio_devices()
            return web.json_response({
                'success': True,
                'devices': devices
            })
        except Exception as e:
            logger.error(f"列出音频设备失败: {e}")
            return web.json_response({
                'success': False,
                'error': str(e),
                'devices': []
            })
    
    async def start_recording(self, request):
        """开始服务端录音"""
        try:
            if not PYAUDIO_AVAILABLE:
                return web.json_response({
                    'success': False,
                    'error': 'pyaudio未安装,无法启动服务端录音'
                })
            
            # 获取参数
            try:
                data = await request.json()
            except:
                data = {}
            
            sample_rate = data.get('sample_rate', 16000)
            channels = data.get('channels', 1)
            chunk_size = data.get('chunk_size', 1024)
            device_index = data.get('device_index')
            
            # 创建录音器
            recorder = create_global_recorder(
                sample_rate=sample_rate,
                channels=channels,
                chunk_size=chunk_size,
                device_index=device_index
            )
            
            # 设置回调
            recorder.set_callbacks(
                on_speech_start=self._on_speech_start,
                on_speech_end=self._on_speech_end,
                on_audio_data=self._on_audio_data,
                on_recognition_result=self._on_recognition_result
            )
            
            # 创建ASR客户端
            class MockOpt:
                def __init__(self):
                    self.fps = 50
                    self.batch_size = 1
                    self.l = 10
                    self.r = 10
                    self.username = data.get('username', 'server_user')
            
            asr_client = FunASRClient(MockOpt())
            recorder.connect_asr(asr_client)
            
            # 开始录音
            if recorder.start_recording():
                self.recorder = recorder
                self.asr_client = asr_client
                
                return web.json_response({
                    'success': True,
                    'message': '服务端录音已开始',
                    'config': {
                        'sample_rate': sample_rate,
                        'channels': channels,
                        'chunk_size': chunk_size,
                        'device_index': device_index
                    }
                })
            else:
                return web.json_response({
                    'success': False,
                    'error': '启动录音失败'
                })
                
        except Exception as e:
            logger.error(f"启动服务端录音失败: {e}")
            return web.json_response({
                'success': False,
                'error': str(e)
            })
    
    async def stop_recording(self, request):
        """停止服务端录音"""
        try:
            recorder = get_global_recorder()
            if recorder:
                recorder.stop_recording()
                destroy_global_recorder()
                self.recorder = None
                self.asr_client = None
                
                return web.json_response({
                    'success': True,
                    'message': '服务端录音已停止'
                })
            else:
                return web.json_response({
                    'success': True,
                    'message': '录音器未运行'
                })
                
        except Exception as e:
            logger.error(f"停止服务端录音失败: {e}")
            return web.json_response({
                'success': False,
                'error': str(e)
            })
    
    async def get_recording_config(self, request):
        """获取录音配置"""
        return web.json_response({
            'success': True,
            'config': {
                'sample_rate': 16000,
                'channels': 1,
                'chunk_size': 1024,
                'vad_threshold': 0.01,
                'silence_duration': 1.0,
                'speech_duration': 0.3,
                'asr_server': f"{cfg.local_asr_ip}:{cfg.local_asr_port}"
            }
        })
    
    async def set_recording_config(self, request):
        """设置录音配置"""
        try:
            data = await request.json()
            # 这里可以保存配置到文件
            return web.json_response({
                'success': True,
                'message': '配置已更新'
            })
        except Exception as e:
            return web.json_response({
                'success': False,
                'error': str(e)
            })
    
    async def recording_websocket(self, request):
        """录音WebSocket接口"""
        ws = web.WebSocketResponse()
        await ws.prepare(request)
        
        self.websocket_clients.add(ws)
        logger.info(f"WebSocket客户端已连接,当前连接数: {len(self.websocket_clients)}")
        
        try:
            async for msg in ws:
                if msg.type == WSMsgType.TEXT:
                    try:
                        data = json.loads(msg.data)
                        await self._handle_websocket_message(ws, data)
                    except json.JSONDecodeError:
                        await ws.send_str(json.dumps({
                            'type': 'error',
                            'message': '无效的JSON格式'
                        }))
                elif msg.type == WSMsgType.ERROR:
                    logger.error(f"WebSocket错误: {ws.exception()}")
                    break
        except Exception as e:
            logger.error(f"WebSocket连接异常: {e}")
        finally:
            self.websocket_clients.discard(ws)
            logger.info(f"WebSocket客户端已断开,当前连接数: {len(self.websocket_clients)}")
        
        return ws
    
    async def test_page(self, request):
        """测试页面"""
        html_content = '''
        <!DOCTYPE html>
        <html>
        <head>
            <title>服务端录音测试</title>
            <meta charset="utf-8">
            <style>
                body { font-family: Arial, sans-serif; margin: 20px; }
                .button { padding: 10px 20px; margin: 5px; background: #007cba; color: white; border: none; border-radius: 4px; cursor: pointer; }
                .button:hover { background: #005a87; }
                .button:disabled { background: #ccc; cursor: not-allowed; }
                #output { margin-top: 20px; padding: 10px; background: #f5f5f5; border-radius: 4px; max-height: 400px; overflow-y: auto; }
                .status { padding: 10px; margin: 10px 0; border-radius: 4px; }
                .status.success { background: #d4edda; color: #155724; border: 1px solid #c3e6cb; }
                .status.error { background: #f8d7da; color: #721c24; border: 1px solid #f5c6cb; }
                .status.info { background: #d1ecf1; color: #0c5460; border: 1px solid #bee5eb; }
            </style>
        </head>
        <body>
            <h1>🎤 服务端录音API测试</h1>
            <div>
                <button class="button" onclick="getStatus()">📊 获取状态</button>
                <button class="button" onclick="listDevices()">🎧 列出设备</button>
                <button class="button" onclick="startRecording()" id="startBtn">▶️ 开始录音</button>
                <button class="button" onclick="stopRecording()" id="stopBtn" disabled>⏹️ 停止录音</button>
                <button class="button" onclick="connectWebSocket()">🔌 连接WebSocket</button>
                <button class="button" onclick="clearOutput()">🗑️ 清空日志</button>
            </div>
            <div id="output"></div>
            
            <script>
                let ws = null;
                
                function log(message, type = 'info') {
                    const output = document.getElementById('output');
                    const timestamp = new Date().toLocaleTimeString();
                    const div = document.createElement('div');
                    div.className = `status ${type}`;
                    div.innerHTML = `[${timestamp}] ${message}`;
                    output.appendChild(div);
                    output.scrollTop = output.scrollHeight;
                }
                
                function clearOutput() {
                    document.getElementById('output').innerHTML = '';
                }
                
                async function getStatus() {
                    try {
                        const response = await fetch('/api/server-recording/status');
                        const data = await response.json();
                        log('状态: ' + JSON.stringify(data, null, 2), data.success ? 'success' : 'error');
                        
                        // 更新按钮状态
                        if (data.success && data.is_recording) {
                            document.getElementById('startBtn').disabled = true;
                            document.getElementById('stopBtn').disabled = false;
                        } else {
                            document.getElementById('startBtn').disabled = false;
                            document.getElementById('stopBtn').disabled = true;
                        }
                    } catch (e) {
                        log('错误: ' + e.message, 'error');
                    }
                }
                
                async function listDevices() {
                    try {
                        const response = await fetch('/api/server-recording/devices');
                        const data = await response.json();
                        log('设备列表: ' + JSON.stringify(data, null, 2), data.success ? 'success' : 'error');
                    } catch (e) {
                        log('错误: ' + e.message, 'error');
                    }
                }
                
                async function startRecording() {
                    try {
                        const response = await fetch('/api/server-recording/start', {
                            method: 'POST',
                            headers: {'Content-Type': 'application/json'},
                            body: JSON.stringify({
                                sample_rate: 16000,
                                channels: 1,
                                chunk_size: 1024
                            })
                        });
                        const data = await response.json();
                        log('开始录音: ' + JSON.stringify(data, null, 2), data.success ? 'success' : 'error');
                        
                        if (data.success) {
                            document.getElementById('startBtn').disabled = true;
                            document.getElementById('stopBtn').disabled = false;
                        }
                    } catch (e) {
                        log('错误: ' + e.message, 'error');
                    }
                }
                
                async function stopRecording() {
                    try {
                        const response = await fetch('/api/server-recording/stop', {
                            method: 'POST'
                        });
                        const data = await response.json();
                        log('停止录音: ' + JSON.stringify(data, null, 2), data.success ? 'success' : 'error');
                        
                        document.getElementById('startBtn').disabled = false;
                        document.getElementById('stopBtn').disabled = true;
                    } catch (e) {
                        log('错误: ' + e.message, 'error');
                    }
                }
                
                function connectWebSocket() {
                    if (ws && ws.readyState === WebSocket.OPEN) {
                        log('WebSocket已连接', 'info');
                        return;
                    }
                    
                    const protocol = window.location.protocol === 'https:' ? 'wss:' : 'ws:';
                    const wsUrl = `${protocol}//${window.location.host}/ws/server-recording`;
                    
                    ws = new WebSocket(wsUrl);
                    
                    ws.onopen = function() {
                        log('WebSocket连接已建立', 'success');
                    };
                    
                    ws.onmessage = function(event) {
                        try {
                            const data = JSON.parse(event.data);
                            log('WebSocket消息: ' + JSON.stringify(data, null, 2), 'info');
                        } catch (e) {
                            log('WebSocket消息: ' + event.data, 'info');
                        }
                    };
                    
                    ws.onclose = function() {
                        log('WebSocket连接已关闭', 'error');
                    };
                    
                    ws.onerror = function(error) {
                        log('WebSocket错误: ' + error, 'error');
                    };
                }
                
                // 页面加载时获取状态
                window.onload = function() {
                    getStatus();
                };
            </script>
        </body>
        </html>
        '''
        return web.Response(text=html_content, content_type='text/html')
    
    async def _handle_websocket_message(self, ws, data: Dict[str, Any]):
        """处理WebSocket消息"""
        message_type = data.get('type')
        
        if message_type == 'start_recording':
            # 开始录音
            config = data.get('config', {})
            await ws.send_str(json.dumps({
                'type': 'recording_started',
                'timestamp': time.time()
            }))
        
        elif message_type == 'stop_recording':
            # 停止录音
            await ws.send_str(json.dumps({
                'type': 'recording_stopped',
                'timestamp': time.time()
            }))
        
        elif message_type == 'get_status':
            # 获取状态
            recorder = get_global_recorder()
            if recorder:
                status = recorder.get_status()
            else:
                status = {'is_recording': False}
            
            await ws.send_str(json.dumps({
                'type': 'status',
                'data': status,
                'timestamp': time.time()
            }))
        
        else:
            await ws.send_str(json.dumps({
                'type': 'error',
                'message': f'未知消息类型: {message_type}'
            }))
    
    async def _broadcast_to_websockets(self, message: Dict[str, Any]):
        """广播消息到所有WebSocket客户端"""
        if not self.websocket_clients:
            return
        
        message_json = json.dumps(message)
        disconnected_clients = set()
        
        for ws in list(self.websocket_clients):
            try:
                if not ws.closed:
                    await ws.send_str(message_json)
                else:
                    disconnected_clients.add(ws)
            except Exception as e:
                logger.error(f"发送WebSocket消息失败: {e}")
                disconnected_clients.add(ws)
        
        # 清理断开的连接
        for ws in disconnected_clients:
            self.websocket_clients.discard(ws)
    
    def _on_speech_start(self):
        """语音开始回调"""
        logger.info("[MIC] 检测到语音开始")
        # 使用线程安全的方式调度协程到主事件循环
        try:
            loop = asyncio.get_event_loop()
            if loop.is_running():
                asyncio.run_coroutine_threadsafe(self._broadcast_to_websockets({
                    'type': 'speech_start',
                    'timestamp': time.time()
                }), loop)
        except RuntimeError:
            # 如果没有事件循环,忽略广播
            pass
    
    def _on_speech_end(self):
        """语音结束回调"""
        logger.info("[STOP] 检测到语音结束")
        # 使用线程安全的方式调度协程到主事件循环
        try:
            loop = asyncio.get_event_loop()
            if loop.is_running():
                asyncio.run_coroutine_threadsafe(self._broadcast_to_websockets({
                    'type': 'speech_end',
                    'timestamp': time.time()
                }), loop)
        except RuntimeError:
            # 如果没有事件循环,忽略广播
            pass
    
    def _on_audio_data(self, audio_data, vad_result):
        """音频数据回调"""
        # 发送音频状态到WebSocket客户端
        if vad_result['is_speech']:
            # 使用线程安全的方式调度协程到主事件循环
            try:
                loop = asyncio.get_event_loop()
                if loop.is_running():
                    asyncio.run_coroutine_threadsafe(self._broadcast_to_websockets({
                        'type': 'audio_data',
                        'volume': vad_result['volume'],
                        'threshold': vad_result['threshold'],
                        'is_speech': True,
                        'timestamp': time.time()
                    }), loop)
            except RuntimeError:
                # 如果没有事件循环,忽略广播
                pass
    
    def _on_recognition_result(self, result: str):
        """识别结果回调"""
        logger.info(f"🎯 识别结果: {result}")
        # 使用线程安全的方式调度协程到主事件循环
        try:
            loop = asyncio.get_event_loop()
            if loop.is_running():
                asyncio.run_coroutine_threadsafe(self._broadcast_to_websockets({
                    'type': 'recognition_result',
                    'text': result,
                    'timestamp': time.time()
                }), loop)
        except RuntimeError:
            # 如果没有事件循环,忽略广播
            pass

# 全局API实例
server_recording_api = ServerRecordingAPI()

def register_server_recording_api(app: web.Application) -> ServerRecordingAPI:
    """注册服务端录音API到aiohttp应用"""
    server_recording_api.register_routes(app)
    return server_recording_api

if __name__ == "__main__":
    # 测试服务器
    async def init_app():
        app = web.Application()
        register_server_recording_api(app)
        
        # 配置CORS
        cors = aiohttp_cors.setup(app, defaults={
            "*": aiohttp_cors.ResourceOptions(
                allow_credentials=True,
                expose_headers="*",
                allow_headers="*",
            )
        })
        
        for route in list(app.router.routes()):
            cors.add(route)
        
        return app
    
    async def main():
        app = await init_app()
        runner = web.AppRunner(app)
        await runner.setup()
        site = web.TCPSite(runner, '0.0.0.0', 8001)
        await site.start()
        
        print("🎤 服务端录音API测试服务器启动: http://localhost:8001/server-recording-test")
        
        try:
            await asyncio.Future()  # 永远运行
        except KeyboardInterrupt:
            pass
        finally:
            await runner.cleanup()
    
    asyncio.run(main())