372 lines
13 KiB
JavaScript
372 lines
13 KiB
JavaScript
import {
|
||
ref,
|
||
onUnmounted,
|
||
onBeforeUnmount,
|
||
onMounted
|
||
} from 'vue'
|
||
import {
|
||
onHide,
|
||
onUnload
|
||
} from '@dcloudio/uni-app'
|
||
import WavDecoder from '@/lib/wav-decoder@1.3.0.js'
|
||
|
||
export function useTTSPlayer(wsUrl) {
|
||
const isSpeaking = ref(false)
|
||
const isPaused = ref(false)
|
||
const isComplete = ref(false)
|
||
|
||
// #ifdef H5
|
||
const audioContext = typeof window !== 'undefined' && (window.AudioContext || window.webkitAudioContext)
|
||
? new(window.AudioContext || window.webkitAudioContext)()
|
||
: null
|
||
// #endif
|
||
|
||
// #ifdef MP-WEIXIN
|
||
const audioContext = null // 微信小程序不支持 AudioContext
|
||
// #endif
|
||
|
||
let playTime = audioContext ? audioContext.currentTime : 0
|
||
let sourceNodes = []
|
||
let socket = null
|
||
let sampleRate = 16000
|
||
let numChannels = 1
|
||
let isHeaderDecoded = false
|
||
let pendingText = null
|
||
|
||
let currentPlayId = 0
|
||
let activePlayId = 0
|
||
|
||
const speak = (text) => {
|
||
if (!audioContext) {
|
||
console.warn('⚠️ TTS not supported in current environment');
|
||
return;
|
||
}
|
||
|
||
console.log('🎤 TTS speak function called');
|
||
console.log('📝 Text to synthesize:', text ? text.substring(0, 100) + '...' : 'No text');
|
||
console.log('🔗 WebSocket URL:', wsUrl);
|
||
|
||
currentPlayId++
|
||
const myPlayId = currentPlayId
|
||
console.log('🆔 Play ID:', myPlayId);
|
||
|
||
reset()
|
||
pendingText = text
|
||
activePlayId = myPlayId
|
||
|
||
console.log('✅ Speak function setup complete');
|
||
}
|
||
|
||
const pause = () => {
|
||
if (!audioContext) {
|
||
console.warn('⚠️ TTS not supported in current environment');
|
||
return;
|
||
}
|
||
|
||
console.log('⏸️ TTS pause called');
|
||
console.log('🔊 AudioContext state:', audioContext.state);
|
||
console.log('🔊 Is speaking before pause:', isSpeaking.value);
|
||
console.log('⏸️ Is paused before pause:', isPaused.value);
|
||
|
||
if (audioContext.state === 'running') {
|
||
audioContext.suspend()
|
||
isPaused.value = true
|
||
// 不要设置 isSpeaking.value = false，保持当前状态
|
||
console.log('✅ Audio paused successfully');
|
||
} else {
|
||
console.log('⚠️ AudioContext is not running, cannot pause');
|
||
}
|
||
|
||
console.log('🔊 Is speaking after pause:', isSpeaking.value);
|
||
console.log('⏸️ Is paused after pause:', isPaused.value);
|
||
}
|
||
|
||
const resume = () => {
|
||
if (!audioContext) {
|
||
console.warn('⚠️ TTS not supported in current environment');
|
||
return;
|
||
}
|
||
|
||
console.log('▶️ TTS resume called');
|
||
console.log('🔊 AudioContext state:', audioContext.state);
|
||
console.log('🔊 Is speaking before resume:', isSpeaking.value);
|
||
console.log('⏸️ Is paused before resume:', isPaused.value);
|
||
|
||
if (audioContext.state === 'suspended') {
|
||
audioContext.resume()
|
||
isPaused.value = false
|
||
isSpeaking.value = true
|
||
console.log('✅ Audio resumed successfully');
|
||
} else {
|
||
console.log('⚠️ AudioContext is not suspended, cannot resume');
|
||
}
|
||
|
||
console.log('🔊 Is speaking after resume:', isSpeaking.value);
|
||
console.log('⏸️ Is paused after resume:', isPaused.value);
|
||
}
|
||
|
||
const cancelAudio = () => {
|
||
stop()
|
||
}
|
||
|
||
const stop = () => {
|
||
isSpeaking.value = false
|
||
isPaused.value = false
|
||
isComplete.value = false
|
||
playTime = audioContext ? audioContext.currentTime : 0
|
||
|
||
sourceNodes.forEach(node => {
|
||
try {
|
||
node.stop()
|
||
node.disconnect()
|
||
} catch (e) {}
|
||
})
|
||
sourceNodes = []
|
||
|
||
if (socket) {
|
||
socket.close()
|
||
socket = null
|
||
}
|
||
|
||
isHeaderDecoded = false
|
||
pendingText = null
|
||
}
|
||
|
||
const reset = () => {
|
||
stop()
|
||
isSpeaking.value = false
|
||
isPaused.value = false
|
||
isComplete.value = false
|
||
playTime = audioContext ? audioContext.currentTime : 0
|
||
initWebSocket()
|
||
}
|
||
|
||
const initWebSocket = () => {
|
||
if (!audioContext) {
|
||
console.warn('⚠️ WebSocket TTS not supported in current environment');
|
||
return;
|
||
}
|
||
|
||
const thisPlayId = currentPlayId
|
||
console.log('🔌 Initializing WebSocket connection');
|
||
console.log('🔗 WebSocket URL:', wsUrl);
|
||
console.log('🆔 This play ID:', thisPlayId);
|
||
|
||
socket = new WebSocket(wsUrl)
|
||
socket.binaryType = 'arraybuffer'
|
||
|
||
// 设置心跳检测，避免超时
|
||
const heartbeatInterval = setInterval(() => {
|
||
if (socket && socket.readyState === WebSocket.OPEN) {
|
||
socket.send(JSON.stringify({ type: 'ping' }));
|
||
}
|
||
}, 30000); // 每30秒发送一次心跳
|
||
|
||
socket.onopen = () => {
|
||
console.log('✅ WebSocket connection opened');
|
||
if (pendingText && thisPlayId === activePlayId) {
|
||
const seepdText = extractSpeechText(pendingText)
|
||
console.log('📤 Sending text to TTS server:', seepdText.substring(0, 100) + '...');
|
||
socket.send(seepdText)
|
||
pendingText = null
|
||
} else {
|
||
console.log('❌ No pending text or play ID mismatch');
|
||
console.log('📝 Pending text exists:', !!pendingText);
|
||
console.log('🆔 Play ID match:', thisPlayId === activePlayId);
|
||
}
|
||
}
|
||
|
||
socket.onerror = (error) => {
|
||
console.error('❌ WebSocket error:', error);
|
||
}
|
||
|
||
socket.onclose = (event) => {
|
||
console.log('🔌 WebSocket connection closed:', event.code, event.reason);
|
||
clearInterval(heartbeatInterval);
|
||
}
|
||
|
||
socket.onmessage = async (e) => {
|
||
if (thisPlayId !== activePlayId) return // 忽略旧播放的消息
|
||
|
||
if (typeof e.data === 'string') {
|
||
try {
|
||
const msg = JSON.parse(e.data)
|
||
console.log('📨 TTS server message:', msg);
|
||
if (msg.status === 'complete') {
|
||
console.log('✅ TTS synthesis completed');
|
||
isComplete.value = true
|
||
// 计算剩余播放时间，确保播放完整
|
||
const remainingTime = audioContext ? Math.max(0, (playTime - audioContext.currentTime) * 1000) : 0;
|
||
console.log('⏱️ Remaining play time:', remainingTime + 'ms');
|
||
setTimeout(() => {
|
||
if (thisPlayId === activePlayId) {
|
||
console.log('🔇 TTS playback finished, setting isSpeaking to false');
|
||
isSpeaking.value = false
|
||
}
|
||
}, remainingTime + 500) // 额外500ms缓冲时间
|
||
}
|
||
} catch (e) {
|
||
console.log('[TTSPlayer] 文本消息:', e.data)
|
||
}
|
||
} else if (e.data instanceof ArrayBuffer) {
|
||
if (!isHeaderDecoded) {
|
||
try {
|
||
const decoded = await WavDecoder.decode(e.data)
|
||
sampleRate = decoded.sampleRate
|
||
numChannels = decoded.channelData.length
|
||
decoded.channelData.forEach((channel, i) => {
|
||
const audioBuffer = audioContext.createBuffer(1, channel.length,
|
||
sampleRate)
|
||
audioBuffer.copyToChannel(channel, 0)
|
||
playBuffer(audioBuffer)
|
||
})
|
||
isHeaderDecoded = true
|
||
} catch (err) {
|
||
console.error('WAV 解码失败:', err)
|
||
}
|
||
} else {
|
||
const pcm = new Int16Array(e.data)
|
||
const audioBuffer = pcmToAudioBuffer(pcm, sampleRate, numChannels)
|
||
playBuffer(audioBuffer)
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
const pcmToAudioBuffer = (pcm, sampleRate, numChannels) => {
|
||
if (!audioContext) return null;
|
||
|
||
const length = pcm.length / numChannels
|
||
const audioBuffer = audioContext.createBuffer(numChannels, length, sampleRate)
|
||
for (let ch = 0; ch < numChannels; ch++) {
|
||
const channelData = audioBuffer.getChannelData(ch)
|
||
for (let i = 0; i < length; i++) {
|
||
const sample = pcm[i * numChannels + ch]
|
||
channelData[i] = sample / 32768
|
||
}
|
||
}
|
||
return audioBuffer
|
||
}
|
||
|
||
const playBuffer = (audioBuffer) => {
|
||
if (!audioContext || !audioBuffer) return;
|
||
|
||
console.log('🎵 playBuffer called, duration:', audioBuffer.duration + 's');
|
||
if (!isSpeaking.value) {
|
||
playTime = audioContext.currentTime
|
||
console.log('🎵 Starting new audio playback at time:', playTime);
|
||
}
|
||
const source = audioContext.createBufferSource()
|
||
source.buffer = audioBuffer
|
||
source.connect(audioContext.destination)
|
||
source.start(playTime)
|
||
sourceNodes.push(source)
|
||
playTime += audioBuffer.duration
|
||
isSpeaking.value = true
|
||
console.log('🎵 Audio scheduled, new playTime:', playTime);
|
||
|
||
// 添加音频播放结束监听
|
||
source.onended = () => {
|
||
console.log('🎵 Audio buffer finished playing');
|
||
}
|
||
}
|
||
|
||
onUnmounted(() => {
|
||
stop()
|
||
})
|
||
|
||
// 页面刷新/关闭时
|
||
onMounted(() => {
|
||
if (typeof window !== 'undefined') {
|
||
window.addEventListener('beforeunload', cancelAudio)
|
||
}
|
||
})
|
||
|
||
onBeforeUnmount(() => {
|
||
cancelAudio()
|
||
if (typeof window !== 'undefined') {
|
||
window.removeEventListener('beforeunload', cancelAudio)
|
||
}
|
||
})
|
||
|
||
onHide(cancelAudio)
|
||
onUnload(cancelAudio)
|
||
|
||
// 只在支持 AudioContext 的环境中初始化 WebSocket
|
||
if (audioContext) {
|
||
initWebSocket()
|
||
}
|
||
|
||
return {
|
||
speak,
|
||
pause,
|
||
resume,
|
||
cancelAudio,
|
||
isSpeaking,
|
||
isPaused,
|
||
isComplete
|
||
}
|
||
}
|
||
|
||
function extractSpeechText(markdown) {
|
||
console.log('🔍 extractSpeechText called');
|
||
console.log('📝 Input markdown length:', markdown ? markdown.length : 0);
|
||
console.log('📝 Input markdown preview:', markdown ? markdown.substring(0, 200) + '...' : 'No markdown');
|
||
|
||
const jobRegex = /``` job-json\s*({[\s\S]*?})\s*```/g;
|
||
const jobs = [];
|
||
let match;
|
||
let lastJobEndIndex = 0;
|
||
let firstJobStartIndex = -1;
|
||
|
||
// 提取岗位 json 数据及前后位置
|
||
while ((match = jobRegex.exec(markdown)) !== null) {
|
||
const jobStr = match[1];
|
||
try {
|
||
const job = JSON.parse(jobStr);
|
||
jobs.push(job);
|
||
if (firstJobStartIndex === -1) {
|
||
firstJobStartIndex = match.index;
|
||
}
|
||
lastJobEndIndex = jobRegex.lastIndex;
|
||
console.log('✅ Found job:', job.jobTitle);
|
||
} catch (e) {
|
||
console.warn('JSON 解析失败', e);
|
||
}
|
||
}
|
||
|
||
console.log('📊 Jobs found:', jobs.length);
|
||
console.log('📍 First job start index:', firstJobStartIndex);
|
||
console.log('📍 Last job end index:', lastJobEndIndex);
|
||
|
||
// 提取引导语（第一个 job-json 之前的文字）
|
||
const guideText = firstJobStartIndex > 0 ?
|
||
markdown.slice(0, firstJobStartIndex).trim() :
|
||
'';
|
||
|
||
// 提取结束语（最后一个 job-json 之后的文字）
|
||
const endingText = lastJobEndIndex < markdown.length ?
|
||
markdown.slice(lastJobEndIndex).trim() :
|
||
'';
|
||
|
||
console.log('📝 Guide text:', guideText);
|
||
console.log('📝 Ending text:', endingText);
|
||
|
||
// 岗位信息格式化为语音文本
|
||
const jobTexts = jobs.map((job, index) => {
|
||
return `第 ${index + 1} 个岗位，岗位名称是：${job.jobTitle}，公司是：${job.companyName}，薪资：${job.salary}，地点：${job.location}，学历要求：${job.education}，经验要求：${job.experience}。`;
|
||
});
|
||
|
||
// 拼接总语音内容
|
||
const finalTextParts = [];
|
||
if (guideText) finalTextParts.push(guideText);
|
||
finalTextParts.push(...jobTexts);
|
||
if (endingText) finalTextParts.push(endingText);
|
||
|
||
const finalText = finalTextParts.join('\n');
|
||
console.log('🎤 Final TTS text length:', finalText.length);
|
||
console.log('🎤 Final TTS text preview:', finalText.substring(0, 200) + '...');
|
||
console.log('🎤 Final TTS text parts count:', finalTextParts.length);
|
||
|
||
return finalText;
|
||
} |