cfy666
da5c727d8c
之前前端 TTSPlayer 攒齐所有音频片段后才播放，导致文字全部显示后才开始语音。 改为后端每句 TTS 发送 is_last: true，前端收到每句即加入播放队列，第一句到达即开始播放。 - 后端 Chunk 结构体新增 Final 字段，区分句子结束和整轮结束 - 前端 TTSPlayer 重写为队列式播放，onended 回调自动衔接下一句 - 同步更新接口文档和测试用例
310 lines
8.1 KiB
Go
310 lines
8.1 KiB
Go
package tts
|
||
|
||
import (
|
||
"context"
|
||
"fmt"
|
||
"io"
|
||
"net/http"
|
||
"net/http/httptest"
|
||
"strings"
|
||
"sync/atomic"
|
||
"testing"
|
||
"time"
|
||
|
||
"go.uber.org/zap"
|
||
)
|
||
|
||
// mockTTSServer 创建模拟 OpenAI TTS API 的 HTTP 服务器。
|
||
func mockTTSServer(t *testing.T, handler http.HandlerFunc) *httptest.Server {
|
||
t.Helper()
|
||
return httptest.NewServer(handler)
|
||
}
|
||
|
||
// sendSentences 向 channel 发送句子并关闭。
|
||
func sendSentences(sentences ...string) <-chan string {
|
||
ch := make(chan string, len(sentences))
|
||
for _, s := range sentences {
|
||
ch <- s
|
||
}
|
||
close(ch)
|
||
return ch
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_Success(t *testing.T) {
|
||
var callCount int32
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
atomic.AddInt32(&callCount, 1)
|
||
|
||
if r.Method != http.MethodPost {
|
||
t.Errorf("method = %s, want POST", r.Method)
|
||
}
|
||
if !strings.Contains(r.URL.Path, "/audio/speech") {
|
||
t.Errorf("path = %s, should contain /audio/speech", r.URL.Path)
|
||
}
|
||
auth := r.Header.Get("Authorization")
|
||
if auth != "Bearer test-key" {
|
||
t.Errorf("Authorization = %q, want %q", auth, "Bearer test-key")
|
||
}
|
||
|
||
// 验证请求体
|
||
body, _ := io.ReadAll(r.Body)
|
||
if !strings.Contains(string(body), "tts-1") {
|
||
t.Errorf("request body should contain model tts-1")
|
||
}
|
||
|
||
// 返回假 MP3 数据
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "fake-mp3-data")
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
textStream := sendSentences("你好", "世界", "！")
|
||
|
||
ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{
|
||
Voice: "alloy", Speed: 1.0, OutputFmt: "mp3", SampleRate: 24000,
|
||
})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
var chunks []Chunk
|
||
for c := range ch {
|
||
chunks = append(chunks, c)
|
||
}
|
||
|
||
// 应该有 3 个音频 chunk + 1 个 Final 标记
|
||
if len(chunks) != 4 {
|
||
t.Fatalf("got %d chunks, want 4", len(chunks))
|
||
}
|
||
|
||
// 验证前 3 个有音频数据，IsLast 为 true（每句结束）
|
||
for i := 0; i < 3; i++ {
|
||
if string(chunks[i].Audio) != "fake-mp3-data" {
|
||
t.Errorf("chunk[%d].Audio = %q, want %q", i, string(chunks[i].Audio), "fake-mp3-data")
|
||
}
|
||
if !chunks[i].IsLast {
|
||
t.Errorf("chunk[%d].IsLast should be true (sentence end)", i)
|
||
}
|
||
if chunks[i].Final {
|
||
t.Errorf("chunk[%d].Final should be false", i)
|
||
}
|
||
}
|
||
|
||
// 验证最后一个是 Final（整轮结束）
|
||
if !chunks[3].Final {
|
||
t.Error("last chunk should be Final")
|
||
}
|
||
if chunks[3].Audio != nil {
|
||
t.Error("last chunk Audio should be nil")
|
||
}
|
||
|
||
// 验证调用了 3 次 API（3 个句子）
|
||
if atomic.LoadInt32(&callCount) != 3 {
|
||
t.Errorf("API called %d times, want 3", callCount)
|
||
}
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_APIError(t *testing.T) {
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
w.WriteHeader(http.StatusInternalServerError)
|
||
fmt.Fprintf(w, "internal error")
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
textStream := sendSentences("你好")
|
||
|
||
ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
// 应该只有一个 Final chunk（音频被跳过）
|
||
var chunks []Chunk
|
||
for c := range ch {
|
||
chunks = append(chunks, c)
|
||
}
|
||
|
||
if len(chunks) != 1 {
|
||
t.Fatalf("got %d chunks, want 1 (Final only)", len(chunks))
|
||
}
|
||
if !chunks[0].Final {
|
||
t.Error("chunk should be Final")
|
||
}
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_Timeout(t *testing.T) {
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
time.Sleep(3 * time.Second)
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "late-mp3")
|
||
})
|
||
defer srv.Close()
|
||
|
||
// 1 秒超时
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 1, 30, zap.NewNop().Sugar())
|
||
|
||
textStream := sendSentences("很长的句子")
|
||
|
||
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
|
||
defer cancel()
|
||
|
||
ch, err := svc.SynthesizeStream(ctx, textStream, Options{})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
var chunks []Chunk
|
||
for c := range ch {
|
||
chunks = append(chunks, c)
|
||
}
|
||
|
||
// 超时后音频被跳过，只有 Final
|
||
if len(chunks) != 1 {
|
||
t.Fatalf("got %d chunks, want 1", len(chunks))
|
||
}
|
||
if !chunks[0].Final {
|
||
t.Error("chunk should be Final")
|
||
}
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_EmptyText(t *testing.T) {
|
||
var callCount int32
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
atomic.AddInt32(&callCount, 1)
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "mp3")
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
// 空句子应该被跳过
|
||
textStream := sendSentences("", "你好", "")
|
||
|
||
ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
var chunks []Chunk
|
||
for c := range ch {
|
||
chunks = append(chunks, c)
|
||
}
|
||
|
||
// 只有 "你好" 应该被合成
|
||
if atomic.LoadInt32(&callCount) != 1 {
|
||
t.Errorf("API called %d times, want 1", callCount)
|
||
}
|
||
|
||
// 1 个音频（IsLast: true）+ 1 个 Final
|
||
if len(chunks) != 2 {
|
||
t.Fatalf("got %d chunks, want 2", len(chunks))
|
||
}
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_ContextCancelled(t *testing.T) {
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "mp3")
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
// 发送多个句子，但在第一个后取消
|
||
textStream := make(chan string, 3)
|
||
textStream <- "第一句"
|
||
textStream <- "第二句"
|
||
textStream <- "第三句"
|
||
close(textStream)
|
||
|
||
ctx, cancel := context.WithCancel(context.Background())
|
||
// 立即取消
|
||
cancel()
|
||
|
||
ch, err := svc.SynthesizeStream(ctx, textStream, Options{})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
// 消费 channel，应该很快结束
|
||
var count int
|
||
for range ch {
|
||
count++
|
||
}
|
||
// 可能收到 0 个或 1 个 chunk，取决于时序
|
||
t.Logf("received %d chunks after context cancel", count)
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_PartialFailure(t *testing.T) {
|
||
var callCount int32
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
n := atomic.AddInt32(&callCount, 1)
|
||
if n == 2 {
|
||
// 第二个句子失败
|
||
w.WriteHeader(http.StatusInternalServerError)
|
||
fmt.Fprintf(w, "error")
|
||
return
|
||
}
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "mp3-%d", n)
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
textStream := sendSentences("第一句", "第二句", "第三句")
|
||
|
||
ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
var chunks []Chunk
|
||
for c := range ch {
|
||
chunks = append(chunks, c)
|
||
}
|
||
|
||
// 2 个成功音频（IsLast: true）+ 1 个 Final（第二句被跳过）
|
||
if len(chunks) != 3 {
|
||
t.Fatalf("got %d chunks, want 3", len(chunks))
|
||
}
|
||
if !chunks[0].IsLast {
|
||
t.Error("first audio chunk should be IsLast")
|
||
}
|
||
if !chunks[1].IsLast {
|
||
t.Error("second audio chunk should be IsLast")
|
||
}
|
||
if !chunks[len(chunks)-1].Final {
|
||
t.Error("last chunk should be Final")
|
||
}
|
||
}
|
||
|
||
func TestOpenAIService_SynthesizeStream_CustomVoice(t *testing.T) {
|
||
srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
|
||
body, _ := io.ReadAll(r.Body)
|
||
if !strings.Contains(string(body), "nova") {
|
||
t.Errorf("request body should contain voice 'nova', got: %s", string(body))
|
||
}
|
||
w.Header().Set("Content-Type", "audio/mpeg")
|
||
fmt.Fprintf(w, "mp3")
|
||
})
|
||
defer srv.Close()
|
||
|
||
svc := NewOpenAIService("test-key", "tts-1", "alloy", srv.URL, 1.0, 5, 30, zap.NewNop().Sugar())
|
||
|
||
textStream := sendSentences("你好")
|
||
|
||
ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{Voice: "nova"})
|
||
if err != nil {
|
||
t.Fatalf("SynthesizeStream() error: %v", err)
|
||
}
|
||
|
||
for range ch {
|
||
}
|
||
}
|