Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
3129d45b25 | ||
|
|
e226224119 |
17
.gitignore
vendored
17
.gitignore
vendored
@@ -20,11 +20,14 @@ node_modules/
|
||||
out/
|
||||
.turbo/
|
||||
|
||||
# ============ IDE ============
|
||||
# ============ IDE / AI 工具 ============
|
||||
.vscode/
|
||||
.idea/
|
||||
*.swp
|
||||
*.swo
|
||||
.agents/
|
||||
.opencode/
|
||||
.claude/
|
||||
|
||||
# ============ 系统文件 ============
|
||||
.DS_Store
|
||||
@@ -35,11 +38,21 @@ desktop.ini
|
||||
backend/outputs/
|
||||
backend/uploads/
|
||||
backend/cookies/
|
||||
backend/user_data/
|
||||
backend/debug_screenshots/
|
||||
*_cookies.json
|
||||
|
||||
# ============ MuseTalk ============
|
||||
# ============ 模型权重 ============
|
||||
models/*/checkpoints/
|
||||
models/MuseTalk/models/
|
||||
models/MuseTalk/results/
|
||||
models/LatentSync/temp/
|
||||
|
||||
# ============ Remotion 构建 ============
|
||||
remotion/dist/
|
||||
|
||||
# ============ 临时文件 ============
|
||||
Temp/
|
||||
|
||||
# ============ 日志 ============
|
||||
*.log
|
||||
|
||||
@@ -29,15 +29,15 @@ backend/
|
||||
├── app/
|
||||
│ ├── core/ # config、deps、security、response
|
||||
│ ├── modules/ # 业务模块（路由 + 逻辑）
|
||||
│ │ ├── videos/ # 视频生成任务
|
||||
│ │ ├── materials/ # 素材管理
|
||||
│ │ ├── videos/ # 视频生成任务（router/schemas/service/workflow）
|
||||
│ │ ├── materials/ # 素材管理（router/schemas/service）
|
||||
│ │ ├── publish/ # 多平台发布
|
||||
│ │ ├── auth/ # 认证与会话
|
||||
│ │ ├── ai/ # AI 功能（标题标签生成等）
|
||||
│ │ ├── assets/ # 静态资源（字体/样式/BGM）
|
||||
│ │ ├── ref_audios/ # 声音克隆参考音频
|
||||
│ │ ├── ref_audios/ # 声音克隆参考音频（router/schemas/service）
|
||||
│ │ ├── login_helper/ # 扫码登录辅助
|
||||
│ │ ├── tools/ # 工具接口
|
||||
│ │ ├── tools/ # 工具接口（router/schemas/service）
|
||||
│ │ └── admin/ # 管理员功能
|
||||
│ ├── repositories/ # Supabase 数据访问
|
||||
│ ├── services/ # 外部服务集成
|
||||
@@ -124,10 +124,13 @@ backend/user_data/{user_uuid}/cookies/
|
||||
|
||||
## 8. 开发流程建议
|
||||
|
||||
- **新增功能**：先建模块，再写 router/service/workflow。
|
||||
- **修复 Bug**：顺手把涉及的逻辑抽到对应 service/workflow。
|
||||
- **新增功能**：先建模块，**必须**包含 `router.py + schemas.py + service.py`，不允许 router-only。
|
||||
- **修复 Bug**：顺手把涉及的逻辑抽到对应 service/workflow（渐进式改造）。
|
||||
- **改旧模块**：改动哪部分就拆哪部分，不要求一次重构整个文件。
|
||||
- **核心流程变更**：必跑冒烟（登录/生成/发布）。
|
||||
|
||||
> **渐进原则**：新代码高标准，旧代码逐步改。不做大规模一次性重构，避免引入回归风险。
|
||||
|
||||
---
|
||||
|
||||
## 9. 常用环境变量
|
||||
|
||||
@@ -15,15 +15,15 @@ backend/
|
||||
├── app/
|
||||
│ ├── core/ # 核心配置 (config.py, security.py, response.py)
|
||||
│ ├── modules/ # 业务模块 (router/service/workflow/schemas)
|
||||
│ │ ├── videos/ # 视频生成任务
|
||||
│ │ ├── materials/ # 素材管理
|
||||
│ │ ├── videos/ # 视频生成任务（router/schemas/service/workflow）
|
||||
│ │ ├── materials/ # 素材管理（router/schemas/service）
|
||||
│ │ ├── publish/ # 多平台发布
|
||||
│ │ ├── auth/ # 认证与会话
|
||||
│ │ ├── ai/ # AI 功能（标题标签生成）
|
||||
│ │ ├── assets/ # 静态资源（字体/样式/BGM）
|
||||
│ │ ├── ref_audios/ # 声音克隆参考音频
|
||||
│ │ ├── ref_audios/ # 声音克隆参考音频（router/schemas/service）
|
||||
│ │ ├── login_helper/ # 扫码登录辅助
|
||||
│ │ ├── tools/ # 工具接口（文案提取等）
|
||||
│ │ ├── tools/ # 工具接口（router/schemas/service）
|
||||
│ │ └── admin/ # 管理员功能
|
||||
│ ├── repositories/ # Supabase 数据访问
|
||||
│ ├── services/ # 外部服务集成 (TTS/Remotion/Storage/Uploader 等)
|
||||
@@ -108,6 +108,8 @@ backend/
|
||||
|
||||
`POST /api/videos/generate` 支持以下可选字段：
|
||||
|
||||
- `material_path`: 视频素材路径（单素材模式）
|
||||
- `material_paths`: 多素材路径数组（多机位模式，≥2 个素材时按句子自动切换）
|
||||
- `tts_mode`: TTS 模式 (`edgetts` / `voiceclone`)
|
||||
- `voice`: EdgeTTS 音色 ID（edgetts 模式）
|
||||
- `ref_audio_id` / `ref_text`: 参考音频 ID 与文本（voiceclone 模式）
|
||||
|
||||
@@ -342,6 +342,6 @@ models/Qwen3-TTS/
|
||||
|
||||
## 🔗 相关文档
|
||||
|
||||
- [task_complete.md](../task_complete.md) - 任务总览
|
||||
- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
|
||||
- [Day11.md](./Day11.md) - 上传架构重构
|
||||
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 部署指南
|
||||
|
||||
@@ -273,7 +273,7 @@ pm2 logs vigent2-qwen-tts --lines 50
|
||||
|
||||
## 🔗 相关文档
|
||||
|
||||
- [task_complete.md](../task_complete.md) - 任务总览
|
||||
- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
|
||||
- [Day12.md](./Day12.md) - iOS 兼容与 Qwen3-TTS 部署
|
||||
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 部署指南
|
||||
- [SUBTITLE_DEPLOY.md](../SUBTITLE_DEPLOY.md) - 字幕功能部署指南
|
||||
|
||||
@@ -397,6 +397,6 @@ if ((status === 401 || status === 403) && !isRedirecting && !isPublicPath) {
|
||||
|
||||
## 🔗 相关文档
|
||||
|
||||
- [task_complete.md](../task_complete.md) - 任务总览
|
||||
- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
|
||||
- [Day13.md](./Day13.md) - 声音克隆功能集成 + 字幕功能
|
||||
- [QWEN3_TTS_DEPLOY.md](../QWEN3_TTS_DEPLOY.md) - Qwen3-TTS 1.7B 部署指南
|
||||
|
||||
@@ -342,7 +342,7 @@ pm2 restart vigent2-backend vigent2-frontend
|
||||
|
||||
## 🔗 相关文档
|
||||
|
||||
- [task_complete.md](../task_complete.md) - 任务总览
|
||||
- [TASK_COMPLETE.md](../TASK_COMPLETE.md) - 任务总览
|
||||
- [Day14.md](./Day14.md) - 模型升级 + AI 标题标签
|
||||
- [AUTH_DEPLOY.md](../AUTH_DEPLOY.md) - 认证系统部署指南
|
||||
|
||||
|
||||
@@ -136,4 +136,4 @@ if service["failures"] >= service['threshold']:
|
||||
|
||||
- [x] `Docs/QWEN3_TTS_DEPLOY.md`: 添加 Flash Attention 安装指南
|
||||
- [x] `Docs/DEPLOY_MANUAL.md`: 添加 Watchdog 部署说明
|
||||
- [x] `Docs/task_complete.md`: 更新进度至 100% (Day 16)
|
||||
- [x] `Docs/TASK_COMPLETE.md`: 更新进度至 100% (Day 16)
|
||||
|
||||
@@ -246,3 +246,204 @@ PLATFORM_CONFIGS = {
|
||||
pm2 restart vigent2-backend # 发布服务 + QR登录
|
||||
npm run build && pm2 restart vigent2-frontend # 刷脸验证UI
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ 架构优化：前端结构微调 + 后端模块分层 (Day 21)
|
||||
|
||||
### 概述
|
||||
根据架构审计结果，完成前端目录规范化和后端核心模块的分层补全。
|
||||
|
||||
### 一、前端结构微调
|
||||
|
||||
#### 1. ScriptExtractionModal 迁移
|
||||
- `components/ScriptExtractionModal.tsx` → `features/home/ui/ScriptExtractionModal.tsx`
|
||||
- 连带 `components/script-extraction/` 目录一并迁移到 `features/home/ui/script-extraction/`
|
||||
- 更新 `HomePage.tsx` 的 import 路径
|
||||
|
||||
#### 2. contexts/ 目录归并
|
||||
- `src/contexts/AuthContext.tsx` → `src/shared/contexts/AuthContext.tsx`
|
||||
- `src/contexts/TaskContext.tsx` → `src/shared/contexts/TaskContext.tsx`
|
||||
- 更新 6 处 import（layout.tsx, useHomeController.ts, usePublishController.ts, AccountSettingsDropdown.tsx, GlobalTaskIndicator.tsx）
|
||||
- 删除空的 `src/contexts/` 目录
|
||||
|
||||
#### 3. 清理重构遗留空目录
|
||||
- 删除 `src/lib/`、`src/components/home/`、`src/hooks/`
|
||||
|
||||
### 二、后端模块分层补全
|
||||
|
||||
将 3 个 400+ 行的 router-only 模块拆分为 `router.py + schemas.py + service.py`：
|
||||
|
||||
| 模块 | 改造前 | 改造后 router |
|
||||
|------|--------|--------------|
|
||||
| `materials/` | 416 行 | 63 行 |
|
||||
| `tools/` | 417 行 | 33 行 |
|
||||
| `ref_audios/` | 421 行 | 71 行 |
|
||||
|
||||
业务逻辑全部提取到 `service.py`，数据模型定义在 `schemas.py`，router 只做参数校验 + 调用 service + 返回响应。
|
||||
|
||||
### 三、开发规范更新
|
||||
|
||||
`BACKEND_DEV.md` 第 8 节新增渐进原则：
|
||||
- 新模块**必须**包含 `router.py + schemas.py + service.py`
|
||||
- 改旧模块时顺手拆涉及的部分
|
||||
- 新代码高标准，旧代码逐步改
|
||||
|
||||
### 涉及文件汇总
|
||||
|
||||
| 文件 | 变更 |
|
||||
|------|------|
|
||||
| `frontend/src/features/home/ui/ScriptExtractionModal.tsx` | 从 components/ 迁入 |
|
||||
| `frontend/src/features/home/ui/script-extraction/` | 从 components/ 迁入 |
|
||||
| `frontend/src/shared/contexts/AuthContext.tsx` | 从 contexts/ 迁入 |
|
||||
| `frontend/src/shared/contexts/TaskContext.tsx` | 从 contexts/ 迁入 |
|
||||
| `backend/app/modules/materials/schemas.py` | **新建** |
|
||||
| `backend/app/modules/materials/service.py` | **新建** |
|
||||
| `backend/app/modules/materials/router.py` | 精简为薄路由 |
|
||||
| `backend/app/modules/tools/schemas.py` | **新建** |
|
||||
| `backend/app/modules/tools/service.py` | **新建** |
|
||||
| `backend/app/modules/tools/router.py` | 精简为薄路由 |
|
||||
| `backend/app/modules/ref_audios/schemas.py` | **新建** |
|
||||
| `backend/app/modules/ref_audios/service.py` | **新建** |
|
||||
| `backend/app/modules/ref_audios/router.py` | 精简为薄路由 |
|
||||
| `Docs/BACKEND_DEV.md` | 目录结构标注分层、新增渐进原则 |
|
||||
| `Docs/BACKEND_README.md` | 目录结构标注分层 |
|
||||
| `Docs/FRONTEND_DEV.md` | 更新目录结构（contexts 迁移、ScriptExtractionModal 迁移） |
|
||||
|
||||
### 重启要求
|
||||
```bash
|
||||
pm2 restart vigent2-backend
|
||||
npm run build && pm2 restart vigent2-frontend
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🎬 多素材视频生成（多机位效果）
|
||||
|
||||
### 概述
|
||||
支持用户上传多个不同角度的自拍视频，生成视频时按句子自动切换素材，最终效果类似多机位拍摄。单素材时走原有流程，无额外开销。
|
||||
|
||||
### 核心架构
|
||||
|
||||
#### 流水线变更
|
||||
```
|
||||
【单素材（不变）】
|
||||
text → TTS → audio → LatentSync(1个素材+完整audio) → Whisper字幕 → Remotion → 成片
|
||||
|
||||
【多素材（新增）】
|
||||
text → TTS → audio → Whisper字幕(提前) → 按素材数量均分时长(对齐字边界)
|
||||
→ 对每段: 切分audio + LatentSync(素材[i]+音频片段[i])
|
||||
→ FFmpeg拼接所有片段 → Remotion(完整字幕时间戳) → 成片
|
||||
```
|
||||
|
||||
#### 素材切换逻辑（均分方案）
|
||||
1. Whisper 对完整音频转录，得到字级别时间戳
|
||||
2. 按素材数量**均分音频总时长**（`total_duration / N`）
|
||||
3. 每个分割点对齐到最近的 Whisper 字边界，避免在字中间切分
|
||||
4. 首段 start 扩展为 0.0，末段 end 扩展为音频结尾，确保完整覆盖
|
||||
|
||||
> **设计决策**：最初方案基于原始文案标点分句，但用户文案往往不含句号（只有逗号），导致只产生 1 段。改为均分方案后不依赖文案标点，对任何输入都能正确切分。
|
||||
|
||||
---
|
||||
|
||||
### 一、后端改动
|
||||
|
||||
#### 1. `backend/app/modules/videos/schemas.py`
|
||||
- 新增 `material_paths: Optional[List[str]]` 字段
|
||||
- 保留 `material_path: str` 向后兼容
|
||||
|
||||
#### 2. `backend/app/modules/videos/workflow.py`（核心改动）
|
||||
|
||||
**新增函数**：
|
||||
- `_split_equal(segments, material_paths)`: 按素材数量均分音频时长，对齐到最近的 Whisper 字边界
|
||||
|
||||
**修改 `process_video_generation()`**：
|
||||
- `is_multi = len(material_paths) > 1` 判断走多素材/单素材分支
|
||||
- 多素材分支：Whisper 提前 → 均分切分 → 音频切分 → 逐段 LatentSync → FFmpeg 拼接
|
||||
|
||||
#### 3. `backend/app/services/video_service.py`
|
||||
- 新增 `concat_videos()`: FFmpeg concat demuxer (`-c copy`) 拼接视频片段
|
||||
- 新增 `split_audio()`: FFmpeg 按时间范围切分音频 (`-ss` + `-t` + `-c copy`)
|
||||
|
||||
#### 4. `backend/scripts/watchdog.py`
|
||||
- 健康检查阈值从 3 次提高到 5 次（容忍期 2.5 分钟）
|
||||
- 新增重启后 120 秒冷却期，避免模型加载期间被误判为故障
|
||||
- 启动时给所有服务 60 秒初始冷却期
|
||||
|
||||
---
|
||||
|
||||
### 二、前端改动
|
||||
|
||||
#### 1. 新增依赖
|
||||
```bash
|
||||
npm install @dnd-kit/core @dnd-kit/sortable @dnd-kit/utilities
|
||||
```
|
||||
|
||||
#### 2. `frontend/src/features/home/model/useMaterials.ts`
|
||||
- `selectedMaterial: string` → `selectedMaterials: string[]`（多选）
|
||||
- 新增 `toggleMaterial(id)`: 切换选中/取消（至少保留1个）
|
||||
- 新增 `reorderMaterials(activeId, overId)`: 拖拽排序
|
||||
- 上传格式扩展：新增 `.mkv/.webm/.flv/.wmv/.m4v/.ts/.mts`
|
||||
|
||||
#### 3. `frontend/src/features/home/ui/MaterialSelector.tsx`（重写）
|
||||
- 素材列表每行增加复选框 + 序号徽标（①②③）
|
||||
- 选中 ≥2 个时显示拖拽排序区（@dnd-kit `SortableContext`）
|
||||
- 每个排序项：拖拽把手 + 序号 + 素材名 + 移除按钮
|
||||
- HTML input accept 改为 `video/*`
|
||||
|
||||
#### 4. `frontend/src/features/home/model/useHomeController.ts`
|
||||
- 多素材 payload：`material_paths` 数组 + `material_path` 向后兼容
|
||||
- `enable_subtitles` 硬编码为 `true`（移除开关）
|
||||
- 验证：至少选中 1 个素材
|
||||
|
||||
#### 5. `frontend/src/features/home/model/useHomePersistence.ts`
|
||||
- 素材持久化改为 JSON 数组，向后兼容旧格式（单字符串）
|
||||
- 移除 `enableSubtitles` 持久化
|
||||
|
||||
#### 6. `frontend/src/features/home/ui/TitleSubtitlePanel.tsx`
|
||||
- 移除"逐字高亮字幕"开关，字幕样式区始终显示
|
||||
|
||||
#### 7. `frontend/src/features/home/ui/HomePage.tsx`
|
||||
- 更新 props 传递（`selectedMaterials`, `toggleMaterial`, `reorderMaterials`）
|
||||
|
||||
---
|
||||
|
||||
### 三、Bug 修复记录
|
||||
|
||||
#### BUG-1: 多素材只使用第一个视频（基于标点的分句方案失败）
|
||||
- **现象**: 选了 2 个素材但生成的视频只使用第 1 个，日志显示 `Multi-material: 1 segments, 2 materials`。
|
||||
- **根因 v1**: 最初通过正则 `[。！？!?]` 在 Whisper 输出中分句，但 Whisper 不输出标点。
|
||||
- **修复 v1**: 改为用原始文案标点分句——但用户文案往往只含逗号（，），无句末标点（。！？），仍退化为 1 段。
|
||||
- **最终修复**: 彻底放弃基于标点的分句方案，改为 `_split_equal()` **按素材数量均分音频时长**，对齐到最近的 Whisper 字边界。不依赖任何标点符号，对所有文案均有效。
|
||||
|
||||
#### BUG-2: 口型对不上（音频时间偏移）
|
||||
- **根因**: `split_audio` 用 Whisper 的 start/end 时间（如 0.11~7.21）切分音频，但 `compose()` 用完整原始音频（0.0~结尾）合成，导致时间偏移。
|
||||
- **修复**: 强制首段 start=0.0，末段 end=音频实际时长，确保切分音频完整覆盖。
|
||||
|
||||
#### BUG-3: min_segment_sec 过度合并导致退化（已随方案切换移除）
|
||||
- **根因**: 旧方案中 2 个句子第 2 句不足 3 秒时，最短时长检查合并为 1 段，多素材退化为单素材。
|
||||
- **状态**: 均分方案不存在此问题，相关代码已移除。
|
||||
|
||||
---
|
||||
|
||||
### 涉及文件汇总
|
||||
|
||||
| 文件 | 变更类型 | 说明 |
|
||||
|------|----------|------|
|
||||
| `backend/app/modules/videos/schemas.py` | 修改 | 新增 material_paths 字段 |
|
||||
| `backend/app/modules/videos/workflow.py` | 修改 | 多素材流水线核心逻辑 + 3个 Bug 修复 |
|
||||
| `backend/app/services/video_service.py` | 修改 | 新增 concat_videos / split_audio |
|
||||
| `backend/scripts/watchdog.py` | 修改 | 阈值优化 + 冷却期机制 |
|
||||
| `frontend/package.json` | 修改 | 新增 @dnd-kit 依赖 |
|
||||
| `frontend/src/features/home/model/useMaterials.ts` | 修改 | 多选 + 排序状态管理 |
|
||||
| `frontend/src/features/home/ui/MaterialSelector.tsx` | 重写 | 多选复选框 + 拖拽排序 UI |
|
||||
| `frontend/src/features/home/model/useHomeController.ts` | 修改 | 多素材 payload + 移除字幕开关 |
|
||||
| `frontend/src/features/home/model/useHomePersistence.ts` | 修改 | JSON 数组持久化 |
|
||||
| `frontend/src/features/home/ui/TitleSubtitlePanel.tsx` | 修改 | 移除字幕开关 |
|
||||
| `frontend/src/features/home/ui/HomePage.tsx` | 修改 | 更新 props 传递 |
|
||||
|
||||
### 重启要求
|
||||
```bash
|
||||
pm2 restart vigent2-backend
|
||||
npm run build && pm2 restart vigent2-frontend
|
||||
```
|
||||
|
||||
221
Docs/DevLogs/Day22.md
Normal file
221
Docs/DevLogs/Day22.md
Normal file
@@ -0,0 +1,221 @@
|
||||
## 🔧 多素材生成优化与健壮性加固 (Day 22)
|
||||
|
||||
### 概述
|
||||
对 Day 21 实现的多素材视频生成（多机位）功能进行全面审查，修复 6 个高优先级 Bug、完成 8 项体验优化，并将多素材流水线从"逐段 LatentSync"重构为"先拼接再推理"架构，推理次数从 N 次降为 1 次。
|
||||
|
||||
---
|
||||
|
||||
### 一、后端高优 Bug 修复
|
||||
|
||||
#### 1. `_split_equal()` 素材数 > 字符数边界溢出
|
||||
- **问题**: 5 个素材但只有 2 个 Whisper 字符时，边界索引重复，部分素材被跳过
|
||||
- **修复**: 加入 `n = min(n, len(all_chars))` 上限保护
|
||||
- **文件**: `backend/app/modules/videos/workflow.py`
|
||||
|
||||
#### 2. 多素材 LatentSync 单段失败无 fallback
|
||||
- **问题**: 单素材模式下 LatentSync 失败会 fallback 到原始素材，但多素材模式直接抛异常，整个任务失败
|
||||
- **修复**: 多素材循环中加 try-except，失败时 fallback 到原始素材片段
|
||||
- **文件**: `backend/app/modules/videos/workflow.py`
|
||||
|
||||
#### 3. `num_segments == 0` 时 ZeroDivisionError
|
||||
- **问题**: 所有 assignments 被跳过后 `i / num_segments` 触发除零
|
||||
- **修复**: 循环前加 `if num_segments == 0` 检查并抛出明确错误
|
||||
- **文件**: `backend/app/modules/videos/workflow.py`
|
||||
|
||||
#### 4. `split_audio` 未校验 duration > 0
|
||||
- **问题**: `end <= start` 时 FFmpeg 行为异常
|
||||
- **修复**: 加入 `if duration <= 0: raise ValueError(...)`
|
||||
- **文件**: `backend/app/services/video_service.py`
|
||||
|
||||
#### 5. Whisper 失败时按时长均分兜底
|
||||
- **问题**: Whisper 失败后直接退化为单素材，其他素材被浪费
|
||||
- **修复**: 按 `audio_duration / len(material_paths)` 均分，不依赖字符对齐
|
||||
- **文件**: `backend/app/modules/videos/workflow.py`
|
||||
|
||||
#### 6. `concat_videos` 空列表未检查
|
||||
- **问题**: 传入空 `video_paths` 时 FFmpeg 报错
|
||||
- **修复**: 加入 `if not video_paths: raise ValueError(...)`
|
||||
- **文件**: `backend/app/services/video_service.py`
|
||||
|
||||
---
|
||||
|
||||
### 二、前端优化
|
||||
|
||||
#### 1. payload 构建非空断言修复
|
||||
- `m!.path` → `m?.path` + `.filter(Boolean)`，防止素材被删后 crash
|
||||
- **文件**: `frontend/src/features/home/model/useHomeController.ts`
|
||||
|
||||
#### 2. 生成按钮展示后端进度消息
|
||||
- 新增 `message` prop，生成中显示如"(正在处理片段 2/3...)"
|
||||
- **文件**: `frontend/src/features/home/ui/GenerateActionBar.tsx`, `HomePage.tsx`
|
||||
|
||||
#### 3. 新上传素材自动选中
|
||||
- 上传成功后对比前后素材列表，新增的 ID 自动追加到 `selectedMaterials`
|
||||
- **文件**: `frontend/src/features/home/model/useMaterials.ts`
|
||||
|
||||
#### 4. Material 接口统一
|
||||
- 三处 `interface Material` 重复定义提取到 `shared/types/material.ts`
|
||||
- **文件**: `frontend/src/shared/types/material.ts` (新建), `useMaterials.ts`, `useHomeController.ts`, `MaterialSelector.tsx`
|
||||
|
||||
#### 5. 拖拽排序修复
|
||||
- 移除 `DragOverlay`（`backdrop-blur` 创建新 containing block 导致定位错乱）
|
||||
- 改为 `useSortable` 原生拖拽 + `CSS.Translate`，拖拽中元素高亮加阴影
|
||||
- **文件**: `frontend/src/features/home/ui/MaterialSelector.tsx`
|
||||
|
||||
#### 6. 素材选择上限 4 个
|
||||
- `toggleMaterial` 新增 `MAX_MATERIALS = 4` 限制
|
||||
- UI 选满后未选中项变半透明禁用，提示文字改为"可多选，最多4个"
|
||||
- **文件**: `useMaterials.ts`, `MaterialSelector.tsx`
|
||||
|
||||
#### 7. 移动端排序区域响应式
|
||||
- 素材列表 `max-h-64` → `max-h-48 sm:max-h-64`
|
||||
- **文件**: `MaterialSelector.tsx`
|
||||
|
||||
#### 8. 多素材耗时提示
|
||||
- 选中 ≥2 素材时生成按钮下方显示"多素材模式 (N 个机位)，生成耗时较长"
|
||||
- **文件**: `GenerateActionBar.tsx`, `HomePage.tsx`
|
||||
|
||||
---
|
||||
|
||||
### 三、核心架构重构：先拼接再推理
|
||||
|
||||
#### V1 (Day 21): 逐段 LatentSync
|
||||
```
|
||||
素材A → LatentSync(素材A, 音频片段1) → lipsync_A
|
||||
素材B → LatentSync(素材B, 音频片段2) → lipsync_B
|
||||
FFmpeg concat(lipsync_A, lipsync_B) → 最终视频
|
||||
```
|
||||
- 缺点：N 个素材 = N 次 LatentSync 推理（每次 ~30s）
|
||||
|
||||
#### V2 (Day 22): 先拼接再推理
|
||||
```
|
||||
素材A → prepare_segment(裁剪到3.67s) → prepared_A
|
||||
素材B → prepare_segment(裁剪到4.00s) → prepared_B
|
||||
FFmpeg concat(prepared_A, prepared_B) → concat_video (7.67s)
|
||||
LatentSync(concat_video, 完整音频) → 最终视频
|
||||
```
|
||||
- 优点：只需 **1 次** LatentSync 推理，时间从 N×30s 降为 1×30s
|
||||
|
||||
#### 新增 `prepare_segment()` 方法
|
||||
```python
|
||||
def prepare_segment(self, video_path, target_duration, output_path, target_resolution=None):
|
||||
# 素材时长 > 目标: 裁剪 (-t)
|
||||
# 素材时长 < 目标: 循环 (-stream_loop) + 裁剪
|
||||
# 分辨率一致: -c copy 无损 (不重编码)
|
||||
# 分辨率不一致: scale + pad 统一到第一个素材分辨率
|
||||
```
|
||||
|
||||
#### 分辨率处理策略
|
||||
- 新增 `get_resolution()` 方法检测各素材分辨率
|
||||
- 所有素材分辨率相同时：`-c copy` 无损裁剪（保持原画质）
|
||||
- 分辨率不一致时：统一到第一个素材的分辨率，`force_original_aspect_ratio=decrease` + `pad` 居中
|
||||
- LatentSync 只处理嘴部 512×512 区域，输出保持原分辨率
|
||||
|
||||
#### 时间对齐验证
|
||||
|
||||
| 环节 | 时间基准 | 对齐关系 |
|
||||
|------|---------|---------|
|
||||
| TTS 音频 | 原始时长 (7.67s) | 基准 |
|
||||
| Whisper 字幕 | 基于 TTS 音频 | 时间戳对齐音频 |
|
||||
| 均分切分 | assignments 总时长 = 音频时长 | 首段 start=0, 末段 end=audio_duration |
|
||||
| prepare 各段 | `-t seg_dur` 精确截断 | 总和 ≈ 音频时长 |
|
||||
| LatentSync | concat_video + 完整音频 | 内部 0.5s 容差 |
|
||||
| compose | lipsync_video + 音频/BGM | `-shortest` 保证同步 |
|
||||
| Remotion | 基于 captions_path 渲染字幕 | 时间戳对齐音频 |
|
||||
|
||||
---
|
||||
|
||||
### 涉及文件汇总
|
||||
|
||||
| 文件 | 变更类型 | 说明 |
|
||||
|------|----------|------|
|
||||
| `backend/app/modules/videos/workflow.py` | 修改 | 6 个 Bug 修复 + 流水线重构（先拼接再推理）|
|
||||
| `backend/app/services/video_service.py` | 修改 | 新增 `prepare_segment()`、`get_resolution()`，`split_audio` 校验，`concat_videos` 空列表检查 |
|
||||
| `frontend/src/shared/types/material.ts` | 新建 | 统一 Material 接口 |
|
||||
| `frontend/src/features/home/model/useMaterials.ts` | 修改 | 上传自动选中、素材上限 4 个 |
|
||||
| `frontend/src/features/home/model/useHomeController.ts` | 修改 | payload 非空断言修复、Material 接口引用 |
|
||||
| `frontend/src/features/home/ui/MaterialSelector.tsx` | 修改 | 拖拽修复、上限 4 个 UI、移动端响应式 |
|
||||
| `frontend/src/features/home/ui/GenerateActionBar.tsx` | 修改 | 进度消息展示、多素材耗时提示 |
|
||||
| `frontend/src/features/home/ui/HomePage.tsx` | 修改 | 传递 message、materialCount prop |
|
||||
|
||||
---
|
||||
|
||||
### 四、AI 多语言翻译
|
||||
|
||||
#### 功能
|
||||
在文案编辑区新增「AI多语言」按钮，支持将中文口播文案一键翻译为 9 种语言，并可随时还原原文。
|
||||
|
||||
#### 支持语言
|
||||
英语 English、日语 日本語、韩语 한국어、法语 Français、德语 Deutsch、西班牙语 Español、俄语 Русский、意大利语 Italiano、葡萄牙语 Português
|
||||
|
||||
#### 实现
|
||||
|
||||
##### 后端
|
||||
- **`backend/app/services/glm_service.py`** — 新增 `translate_text()` 方法，调用智谱 GLM API（temperature=0.3），prompt 要求只返回译文、保持语气风格
|
||||
- **`backend/app/modules/ai/router.py`** — 新增 `POST /api/ai/translate` 接口，接收 `{text, target_lang}`，返回 `{translated_text}`
|
||||
|
||||
##### 前端
|
||||
- **`frontend/src/features/home/ui/ScriptEditor.tsx`** — 新增 `LANGUAGES` 列表（9 种语言）、语言下拉菜单（点击外部自动关闭）、翻译中 loading 状态、「还原原文」按钮（翻译过后出现在菜单顶部）
|
||||
- **`frontend/src/features/home/model/useHomeController.ts`** — 新增 `handleTranslate`（调用翻译 API、首次翻译保存原文）、`originalText` 状态、`handleRestoreOriginal`（恢复原文）
|
||||
|
||||
#### 涉及文件
|
||||
|
||||
| 文件 | 变更 | 说明 |
|
||||
|------|------|------|
|
||||
| `backend/app/services/glm_service.py` | 修改 | 新增 `translate_text()` 方法 |
|
||||
| `backend/app/modules/ai/router.py` | 修改 | 新增 `/api/ai/translate` 接口 |
|
||||
| `frontend/src/features/home/ui/ScriptEditor.tsx` | 修改 | 语言菜单 UI、翻译 loading、还原原文按钮 |
|
||||
| `frontend/src/features/home/model/useHomeController.ts` | 修改 | `handleTranslate`、`originalText`、`handleRestoreOriginal` |
|
||||
|
||||
---
|
||||
|
||||
### 五、TTS 多语言支持
|
||||
|
||||
#### 背景
|
||||
翻译功能实现后，用户可将中文文案翻译为其他语言。但翻译后生成视频时 TTS 仍只支持中文：
|
||||
- **EdgeTTS**：声音列表只有 5 个 `zh-CN-*` 中文声音
|
||||
- **声音克隆 (Qwen3-TTS)**：`language` 参数硬编码为 `"Chinese"`
|
||||
|
||||
#### 实现方案
|
||||
|
||||
##### 1. 前端：语言感知的声音列表
|
||||
- `VOICES` 从扁平数组扩展为 `Record<string, VoiceOption[]>`，覆盖 10 种语言（zh-CN / en-US / ja-JP / ko-KR / fr-FR / de-DE / es-ES / ru-RU / it-IT / pt-BR），每种语言 2 个声音（男/女）
|
||||
- 新增 `LANG_TO_LOCALE` 映射：翻译目标语言名 → EdgeTTS locale（如 `"English" → "en-US"`）
|
||||
- 新增 `textLang` 状态，跟踪当前文案语言，默认 `"zh-CN"`
|
||||
|
||||
##### 2. 翻译时自动切换声音
|
||||
- `handleTranslate` 成功后：根据目标语言设置 `textLang`，EdgeTTS 模式下自动切换 `voice` 为目标语言的默认声音
|
||||
- `handleRestoreOriginal` 还原时：重置 `textLang` 为 `"zh-CN"`，恢复中文默认声音
|
||||
- `VoiceSelector` 根据 `textLang` 动态显示对应语言的声音列表
|
||||
|
||||
##### 3. 声音克隆语言透传
|
||||
- 前端：新增 `LOCALE_TO_QWEN_LANG` 映射（`zh-CN→"Chinese"`, `en-US→"English"`, 其他→`"Auto"`）
|
||||
- 生成请求 payload 加入 `language` 字段（仅声音克隆模式）
|
||||
- 后端 `GenerateRequest` schema 新增 `language: str = "Chinese"` 字段
|
||||
- `workflow.py`：`language="Chinese"` 硬编码改为 `language=req.language`
|
||||
|
||||
##### 4. Bug 修复：textLang 持久化
|
||||
- **问题**: `voice` 已持久化但 `textLang` 未持久化，刷新页面后 `voice` 恢复为英文声音但 `textLang` 默认回中文，导致 VoiceSelector 显示中文声音列表却选中英文声音，无高亮按钮
|
||||
- **修复**: 在 `useHomePersistence` 中加入 `textLang` 的 localStorage 读写
|
||||
|
||||
#### 数据流
|
||||
|
||||
```
|
||||
用户翻译 "English"
|
||||
→ ScriptEditor.onTranslate("English")
|
||||
→ LANG_TO_LOCALE["English"] = "en-US"
|
||||
→ setTextLang("en-US"), setVoice("en-US-GuyNeural")
|
||||
→ VoiceSelector 显示 VOICES["en-US"] = [Guy, Jenny]
|
||||
→ 生成时:
|
||||
EdgeTTS: payload.voice = "en-US-GuyNeural"
|
||||
声音克隆: payload.language = "English" (via getQwenLanguage)
|
||||
```
|
||||
|
||||
#### 涉及文件
|
||||
|
||||
| 文件 | 变更 | 说明 |
|
||||
|------|------|------|
|
||||
| `frontend/src/features/home/model/useHomeController.ts` | 修改 | VOICES 多语言 Record、textLang 状态、LANG_TO_LOCALE / LOCALE_TO_QWEN_LANG 映射、翻译自动切换 voice |
|
||||
| `frontend/src/features/home/model/useHomePersistence.ts` | 修改 | textLang 持久化读写 |
|
||||
| `backend/app/modules/videos/schemas.py` | 修改 | GenerateRequest 加 `language` 字段 |
|
||||
| `backend/app/modules/videos/workflow.py` | 修改 | 声音克隆调用处用 `req.language` 替代硬编码 |
|
||||
@@ -389,7 +389,7 @@ if not qr_element:
|
||||
|
||||
## 📋 文档规则优化 (16:42 - 17:10)
|
||||
|
||||
**问题**：Doc_Rules需要优化，避免误删历史内容、规范工具使用、防止任务清单遗漏
|
||||
**问题**：DOC_RULES需要优化，避免误删历史内容、规范工具使用、防止任务清单遗漏
|
||||
|
||||
**优化内容（最终版）**：
|
||||
|
||||
@@ -411,7 +411,7 @@ if not qr_element:
|
||||
- 移除无关项目组件
|
||||
|
||||
**修改文件**：
|
||||
- `Docs/Doc_Rules.md` - 包含检查清单的最终完善版
|
||||
- `Docs/DOC_RULES.md` - 包含检查清单的最终完善版
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -8,8 +8,8 @@
|
||||
|
||||
| 规则 | 说明 |
|
||||
|------|------|
|
||||
| **默认更新** | 只更新 `DayN.md` |
|
||||
| **按需更新** | `task_complete.md` 仅在用户**明确要求**时更新 |
|
||||
| **默认更新** | 更新 `DayN.md` 和 `TASK_COMPLETE.md` |
|
||||
| **按需更新** | 其他文档仅在内容变化涉及时更新 |
|
||||
| **智能修改** | 错误→替换，改进→追加（见下方详细规则） |
|
||||
| **先读后写** | 更新前先查看文件当前内容 |
|
||||
| **日内合并** | 同一天的多次小修改合并为最终版本 |
|
||||
@@ -23,7 +23,7 @@
|
||||
| 优先级 | 文件路径 | 检查重点 |
|
||||
| :---: | :--- | :--- |
|
||||
| 🔥 **High** | `Docs/DevLogs/DayN.md` | **(最新日志)** 详细记录变更、修复、代码片段 |
|
||||
| 🔥 **High** | `Docs/task_complete.md` | **(任务总览)** 更新 `[x]`、进度条、时间线 |
|
||||
| 🔥 **High** | `Docs/TASK_COMPLETE.md` | **(任务总览)** 更新 `[x]`、进度条、时间线 |
|
||||
| ⚡ **Med** | `README.md` | **(项目主页)** 功能特性、技术栈、最新截图 |
|
||||
| ⚡ **Med** | `Docs/DEPLOY_MANUAL.md` | **(部署手册)** 环境变量、依赖包、启动命令变更 |
|
||||
| ⚡ **Med** | `Docs/BACKEND_DEV.md` | **(后端规范)** 接口契约、模块划分、环境变量 |
|
||||
@@ -186,15 +186,15 @@ new_string: "**状态**：✅ 已修复"
|
||||
|
||||
```
|
||||
ViGent2/Docs/
|
||||
├── task_complete.md # 任务总览（仅按需更新）
|
||||
├── Doc_Rules.md # 本文件
|
||||
├── TASK_COMPLETE.md # 任务总览（仅按需更新）
|
||||
├── DOC_RULES.md # 本文件
|
||||
├── BACKEND_DEV.md # 后端开发规范
|
||||
├── BACKEND_README.md # 后端功能文档
|
||||
├── FRONTEND_DEV.md # 前端开发规范
|
||||
├── FRONTEND_README.md # 前端功能文档
|
||||
├── DEPLOY_MANUAL.md # 部署手册
|
||||
├── SUPABASE_DEPLOY.md # Supabase 部署文档
|
||||
├── LatentSync_DEPLOY.md # LatentSync 部署文档
|
||||
├── LATENTSYNC_DEPLOY.md # LatentSync 部署文档
|
||||
├── QWEN3_TTS_DEPLOY.md # 声音克隆部署文档
|
||||
├── SUBTITLE_DEPLOY.md # 字幕系统部署文档
|
||||
└── DevLogs/
|
||||
@@ -206,8 +206,16 @@ ViGent2/Docs/
|
||||
|
||||
## 📅 DayN.md 更新规则（日常更新）
|
||||
|
||||
### 更新时机
|
||||
|
||||
> **边开发边记录，不要等到最后才写。**
|
||||
|
||||
- 每完成一个功能/修复后，**立即**追加到 DayN.md
|
||||
- 避免积攒到对话末尾一次性补写，容易遗漏变更
|
||||
- `TASK_COMPLETE.md` 同理，重要变更完成后及时同步
|
||||
|
||||
### 新建判断 (对话开始前)
|
||||
1. **回顾进度**：查看 `task_complete.md` 了解当前状态
|
||||
1. **回顾进度**：查看 `TASK_COMPLETE.md` 了解当前状态
|
||||
2. **检查日期**：查看最新 `DayN.md`
|
||||
- **今天 (与当前日期相同)** → 🚨 **绝对禁止创建新文件**，必须**追加**到现有 `DayN.md` 末尾！即使是完全不同的功能模块。
|
||||
- **之前 (昨天或更早)** → 创建 `Day{N+1}.md`
|
||||
@@ -263,17 +271,17 @@ ViGent2/Docs/
|
||||
|
||||
---
|
||||
|
||||
## 📝 task_complete.md 更新规则（仅按需）
|
||||
## 📝 TASK_COMPLETE.md 更新规则
|
||||
|
||||
> ⚠️ **仅当用户明确要求更新 `task_complete.md` 时才更新**
|
||||
> 与 DayN.md 同步更新，记录重要变更时更新任务总览。
|
||||
|
||||
### 更新原则
|
||||
- **格式一致性**：直接参考 `task_complete.md` 现有格式追加内容。
|
||||
- **格式一致性**：直接参考 `TASK_COMPLETE.md` 现有格式追加内容。
|
||||
- **进度更新**：仅在阶段性里程碑时更新进度百分比。
|
||||
|
||||
### 🔍 完整性检查清单 (必做)
|
||||
|
||||
每次更新 `task_complete.md` 时，必须**逐一检查**以下所有板块：
|
||||
每次更新 `TASK_COMPLETE.md` 时，必须**逐一检查**以下所有板块：
|
||||
|
||||
1. **文件头部 & 导航**
|
||||
- [ ] `更新时间`：必须是当天日期
|
||||
|
||||
@@ -28,6 +28,9 @@ frontend/src/
|
||||
│ │ ├── HomeHeader.tsx
|
||||
│ │ ├── MaterialSelector.tsx
|
||||
│ │ ├── ScriptEditor.tsx
|
||||
│ │ ├── ScriptExtractionModal.tsx
|
||||
│ │ ├── script-extraction/
|
||||
│ │ │ └── useScriptExtraction.ts
|
||||
│ │ ├── TitleSubtitlePanel.tsx
|
||||
│ │ ├── FloatingStylePreview.tsx
|
||||
│ │ ├── VoiceSelector.tsx
|
||||
@@ -55,11 +58,11 @@ frontend/src/
|
||||
│ ├── types/
|
||||
│ │ ├── user.ts # User 类型定义
|
||||
│ │ └── publish.ts # 发布相关类型
|
||||
│ └── contexts/ # 已迁移的 Context
|
||||
├── contexts/ # 全局 Context（Auth、Task）
|
||||
│ └── contexts/ # 全局 Context（Auth、Task）
|
||||
│ ├── AuthContext.tsx
|
||||
│ └── TaskContext.tsx
|
||||
├── components/ # 遗留通用组件
|
||||
│ ├── VideoPreviewModal.tsx
|
||||
│ └── ScriptExtractionModal.tsx
|
||||
│ └── VideoPreviewModal.tsx
|
||||
└── proxy.ts # Next.js middleware（路由保护）
|
||||
```
|
||||
|
||||
@@ -278,8 +281,8 @@ import { formatDate } from '@/shared/lib/media';
|
||||
- `shared/lib`：通用工具函数（media.ts / auth.ts / title.ts）
|
||||
- `shared/hooks`：跨功能通用 hooks
|
||||
- `shared/types`：跨功能实体类型（User / PublishVideo 等）
|
||||
- `contexts/`：全局 Context（AuthContext / TaskContext）
|
||||
- `components/`：遗留通用组件（VideoPreviewModal 等）
|
||||
- `shared/contexts`：全局 Context（AuthContext / TaskContext）
|
||||
- `components/`：遗留通用组件（VideoPreviewModal）
|
||||
|
||||
## 类型定义规范
|
||||
|
||||
|
||||
@@ -10,18 +10,30 @@
|
||||
|
||||
> 这里记录了每一天的核心开发内容与 milestone。
|
||||
|
||||
### Day 21: 缺陷修复与持久化回归治理 (Current)
|
||||
### Day 21: 缺陷修复 + 浮动预览 + 发布重构 + 架构优化 + 多素材生成 (Current)
|
||||
- [x] **Remotion 崩溃容错**: 渲染进程 SIGABRT 退出时检查输出文件，避免误判失败导致标题/字幕丢失。
|
||||
- [x] **首页作品选择持久化**: 修复 `fetchGeneratedVideos` 无条件覆盖恢复值的问题，新增 `preferVideoId` 参数控制选中逻辑。
|
||||
- [x] **发布页作品选择持久化**: 根因为签名 URL 不稳定，全面改用 `video.id` 替代 `path` 进行选择/持久化/比较。
|
||||
- [x] **预取缓存补全**: 首页预取发布页数据时加入 `id` 字段，确保缓存数据可用于持久化匹配。
|
||||
- [x] **浮动样式预览窗口**: 标题字幕预览改为 `position: fixed` 浮动窗口，固定左上角，滚动时始终可见。
|
||||
- [x] **移动端适配**: ScriptEditor 按钮换行、预览默认比例改为 9:16 竖屏。
|
||||
- [x] **多平台发布重构**: 平台配置独立化（DOUYIN_*/WEIXIN_*）、用户隔离 Cookie 管理、抖音刷脸验证二维码、微信发布流程优化。
|
||||
- [x] **前端结构微调**: ScriptExtractionModal 迁移到 features/、contexts 迁移到 shared/contexts/、清理空目录。
|
||||
- [x] **后端模块分层**: materials/tools/ref_audios 三个模块补全 router+schemas+service 分层。
|
||||
- [x] **开发规范更新**: BACKEND_DEV.md 新增渐进原则、DOC_RULES.md 取消 TASK_COMPLETE.md 手动触发约束。
|
||||
- [x] **文档全面更新**: BACKEND_DEV/README、FRONTEND_DEV、DEPLOY_MANUAL、README.md 同步更新。
|
||||
- [x] **多素材视频生成（多机位效果）**: 支持多选素材 + 拖拽排序，按素材数量均分音频时长（对齐 Whisper 字边界）自动切换机位。逐段 LatentSync + FFmpeg 拼接。前端 @dnd-kit 拖拽排序 UI。
|
||||
- [x] **字幕开关移除**: 默认启用逐字高亮字幕，移除开关及相关死代码。
|
||||
- [x] **视频格式扩展**: 上传支持 mkv/webm/flv/wmv/m4v/ts/mts 等常见格式。
|
||||
- [x] **Watchdog 优化**: 健康检查阈值提高到 5 次，新增重启冷却期 120 秒，避免误重启。
|
||||
- [x] **多素材 Bug 修复**: 修复标点分句方案对无句末标点文案无效（改为均分方案）、音频时间偏移导致口型不对齐等缺陷。
|
||||
|
||||
### Day 20: 代码质量与安全优化
|
||||
- [x] **功能性修复**: LatentSync 回退逻辑、任务状态接口认证、User 类型统一。
|
||||
- [x] **性能优化**: N+1 查询修复、视频上传流式处理、httpx 异步替换、GLM 异步包装。
|
||||
- [x] **安全修复**: 硬编码 Cookie 配置化、日志敏感信息脱敏、ffprobe 安全调用、CORS 配置化。
|
||||
- [x] **配置优化**: 存储路径环境变量化、Remotion 预编译加速、LatentSync 绝对路径。
|
||||
- [x] **文档更新**: 更新 Doc_Rules.md 清单，补齐后端与部署文档；更新 SUBTITLE_DEPLOY.md, FRONTEND_DEV.md, implementation_plan.md。
|
||||
- [x] **文档更新**: 更新 DOC_RULES.md 清单，补齐后端与部署文档；更新 SUBTITLE_DEPLOY.md, FRONTEND_DEV.md, implementation_plan.md。
|
||||
- [x] **缺陷修复**: 修复 Remotion 路径解析、发布页持久化竞态、首页选中回归、素材闭包陷阱。
|
||||
|
||||
### Day 19: 自动发布稳定性与发布体验优化 🚀
|
||||
|
||||
@@ -24,6 +24,33 @@ class GenerateMetaResponse(BaseModel):
|
||||
tags: list[str]
|
||||
|
||||
|
||||
class TranslateRequest(BaseModel):
|
||||
"""翻译请求"""
|
||||
text: str
|
||||
target_lang: str
|
||||
|
||||
|
||||
@router.post("/translate")
|
||||
async def translate_text(req: TranslateRequest):
|
||||
"""
|
||||
AI 翻译文案
|
||||
|
||||
将文案翻译为指定目标语言
|
||||
"""
|
||||
if not req.text or not req.text.strip():
|
||||
raise HTTPException(status_code=400, detail="文案不能为空")
|
||||
if not req.target_lang or not req.target_lang.strip():
|
||||
raise HTTPException(status_code=400, detail="目标语言不能为空")
|
||||
|
||||
try:
|
||||
logger.info(f"Translating text to {req.target_lang}: {req.text[:50]}...")
|
||||
translated = await glm_service.translate_text(req.text.strip(), req.target_lang.strip())
|
||||
return success_response({"translated_text": translated})
|
||||
except Exception as e:
|
||||
logger.error(f"Translate failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.post("/generate-meta")
|
||||
async def generate_meta(req: GenerateMetaRequest):
|
||||
"""
|
||||
|
||||
@@ -1,416 +1,62 @@
|
||||
from fastapi import APIRouter, UploadFile, File, HTTPException, Request, BackgroundTasks, Depends
|
||||
from app.core.config import settings
|
||||
from app.core.deps import get_current_user
|
||||
from app.core.response import success_response
|
||||
from app.services.storage import storage_service
|
||||
import re
|
||||
import time
|
||||
import traceback
|
||||
import os
|
||||
import aiofiles
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
import asyncio
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException, Request, Depends
|
||||
from loguru import logger
|
||||
|
||||
from app.core.deps import get_current_user
|
||||
from app.core.response import success_response
|
||||
from app.modules.materials.schemas import RenameMaterialRequest
|
||||
from app.modules.materials import service
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
class RenameMaterialRequest(BaseModel):
|
||||
new_name: str
|
||||
|
||||
def sanitize_filename(filename: str) -> str:
|
||||
safe_name = re.sub(r'[<>:"/\\|?*]', '_', filename)
|
||||
if len(safe_name) > 100:
|
||||
ext = Path(safe_name).suffix
|
||||
safe_name = safe_name[:100 - len(ext)] + ext
|
||||
return safe_name
|
||||
|
||||
async def process_and_upload(temp_file_path: str, original_filename: str, content_type: str, user_id: str):
|
||||
"""Background task to strip multipart headers and upload to Supabase"""
|
||||
try:
|
||||
logger.info(f"Processing raw upload: {temp_file_path} for user {user_id}")
|
||||
|
||||
# 1. Analyze file to find actual video content (strip multipart boundaries)
|
||||
# This is a simplified manual parser for a SINGLE file upload.
|
||||
# Structure:
|
||||
# --boundary
|
||||
# Content-Disposition: form-data; name="file"; filename="..."
|
||||
# Content-Type: video/mp4
|
||||
# \r\n\r\n
|
||||
# [DATA]
|
||||
# \r\n--boundary--
|
||||
|
||||
# We need to read the first few KB to find the header end
|
||||
start_offset = 0
|
||||
end_offset = 0
|
||||
boundary = b""
|
||||
|
||||
file_size = os.path.getsize(temp_file_path)
|
||||
|
||||
with open(temp_file_path, 'rb') as f:
|
||||
# Read first 4KB to find header
|
||||
head = f.read(4096)
|
||||
|
||||
# Find boundary
|
||||
first_line_end = head.find(b'\r\n')
|
||||
if first_line_end == -1:
|
||||
raise Exception("Could not find boundary in multipart body")
|
||||
|
||||
boundary = head[:first_line_end] # e.g. --boundary123
|
||||
logger.info(f"Detected boundary: {boundary}")
|
||||
|
||||
# Find end of headers (\r\n\r\n)
|
||||
header_end = head.find(b'\r\n\r\n')
|
||||
if header_end == -1:
|
||||
raise Exception("Could not find end of multipart headers")
|
||||
|
||||
start_offset = header_end + 4
|
||||
logger.info(f"Video data starts at offset: {start_offset}")
|
||||
|
||||
# Find end boundary (read from end of file)
|
||||
# It should be \r\n + boundary + -- + \r\n
|
||||
# We seek to end-200 bytes
|
||||
f.seek(max(0, file_size - 200))
|
||||
tail = f.read()
|
||||
|
||||
# The closing boundary is usually --boundary--
|
||||
# We look for the last occurrence of the boundary
|
||||
last_boundary_pos = tail.rfind(boundary)
|
||||
if last_boundary_pos != -1:
|
||||
# The data ends before \r\n + boundary
|
||||
# The tail buffer relative position needs to be converted to absolute
|
||||
end_pos_in_tail = last_boundary_pos
|
||||
# We also need to check for the preceding \r\n
|
||||
if end_pos_in_tail >= 2 and tail[end_pos_in_tail-2:end_pos_in_tail] == b'\r\n':
|
||||
end_pos_in_tail -= 2
|
||||
|
||||
# Absolute end offset
|
||||
end_offset = (file_size - 200) + last_boundary_pos
|
||||
# Correction for CRLF before boundary
|
||||
# Actually, simply: read until (file_size - len(tail) + last_boundary_pos) - 2
|
||||
end_offset = (max(0, file_size - 200) + last_boundary_pos) - 2
|
||||
else:
|
||||
logger.warning("Could not find closing boundary, assuming EOF")
|
||||
end_offset = file_size
|
||||
|
||||
logger.info(f"Video data ends at offset: {end_offset}. Total video size: {end_offset - start_offset}")
|
||||
|
||||
# 2. Extract and Upload to Supabase
|
||||
# Since we have the file on disk, we can just pass the file object (seeked) to upload_file?
|
||||
# Or if upload_file expects bytes/path, checking storage.py...
|
||||
# It takes `file_data` (bytes) or file-like?
|
||||
# supabase-py's `upload` method handles parsing if we pass a file object.
|
||||
# But we need to pass ONLY the video slice.
|
||||
# So we create a generator or a sliced file object?
|
||||
# Simpler: Read the slice into memory if < 1GB? Or copy to new temp file?
|
||||
# Copying to new temp file is safer for memory.
|
||||
|
||||
video_path = temp_file_path + "_video.mp4"
|
||||
with open(temp_file_path, 'rb') as src, open(video_path, 'wb') as dst:
|
||||
src.seek(start_offset)
|
||||
# Copy in chunks
|
||||
bytes_to_copy = end_offset - start_offset
|
||||
copied = 0
|
||||
while copied < bytes_to_copy:
|
||||
chunk_size = min(1024*1024*10, bytes_to_copy - copied) # 10MB chunks
|
||||
chunk = src.read(chunk_size)
|
||||
if not chunk:
|
||||
break
|
||||
dst.write(chunk)
|
||||
copied += len(chunk)
|
||||
|
||||
logger.info(f"Extracted video content to {video_path}")
|
||||
|
||||
# 3. Upload to Supabase with user isolation
|
||||
timestamp = int(time.time())
|
||||
safe_name = re.sub(r'[^a-zA-Z0-9._-]', '', original_filename)
|
||||
# 使用 user_id 作为目录前缀实现隔离
|
||||
storage_path = f"{user_id}/{timestamp}_{safe_name}"
|
||||
|
||||
# Use storage service (this calls Supabase which might do its own http request)
|
||||
# We read the cleaned video file
|
||||
with open(video_path, 'rb') as f:
|
||||
file_content = f.read() # Still reading into memory for simple upload call, but server has 32GB RAM so ok for 500MB
|
||||
await storage_service.upload_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=storage_path,
|
||||
file_data=file_content,
|
||||
content_type=content_type
|
||||
)
|
||||
|
||||
logger.info(f"Upload to Supabase complete: {storage_path}")
|
||||
|
||||
# Cleanup
|
||||
os.remove(temp_file_path)
|
||||
os.remove(video_path)
|
||||
|
||||
return storage_path
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Background upload processing failed: {e}\n{traceback.format_exc()}")
|
||||
raise
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("")
|
||||
async def upload_material(
|
||||
request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
user_id = current_user["id"]
|
||||
logger.info(f"ENTERED upload_material (Streaming Mode) for user {user_id}. Headers: {request.headers}")
|
||||
|
||||
filename = "unknown_video.mp4" # Fallback
|
||||
content_type = "video/mp4"
|
||||
|
||||
# Try to parse filename from header if possible (unreliable in raw stream)
|
||||
# We will rely on post-processing or client hint
|
||||
# Frontend sends standard multipart.
|
||||
|
||||
# Create temp file
|
||||
timestamp = int(time.time())
|
||||
temp_filename = f"upload_{timestamp}.raw"
|
||||
temp_path = os.path.join("/tmp", temp_filename) # Use /tmp on Linux
|
||||
# Ensure /tmp exists (it does) but verify paths
|
||||
if os.name == 'nt': # Local dev
|
||||
temp_path = f"d:/tmp/{temp_filename}"
|
||||
os.makedirs("d:/tmp", exist_ok=True)
|
||||
|
||||
logger.info(f"Upload material request from user {user_id}")
|
||||
try:
|
||||
total_size = 0
|
||||
last_log = 0
|
||||
|
||||
async with aiofiles.open(temp_path, 'wb') as f:
|
||||
async for chunk in request.stream():
|
||||
await f.write(chunk)
|
||||
total_size += len(chunk)
|
||||
|
||||
# Log progress every 20MB
|
||||
if total_size - last_log > 20 * 1024 * 1024:
|
||||
logger.info(f"Receiving stream... Processed {total_size / (1024*1024):.2f} MB")
|
||||
last_log = total_size
|
||||
|
||||
logger.info(f"Stream reception complete. Total size: {total_size} bytes. Saved to {temp_path}")
|
||||
|
||||
if total_size == 0:
|
||||
raise HTTPException(400, "Received empty body")
|
||||
|
||||
# Attempt to extract filename from the saved file's first bytes?
|
||||
# Or just accept it as "uploaded_video.mp4" for now to prove it works.
|
||||
# We can try to regex the header in the file content we just wrote.
|
||||
# Implemented in background task to return success immediately.
|
||||
|
||||
# Wait, if we return immediately, the user's UI might not show the file yet?
|
||||
# The prompt says "Wait for upload".
|
||||
# But to avoid User Waiting Timeout, maybe returning early is better?
|
||||
# NO, user expects the file to be in the list.
|
||||
# So we Must await the processing.
|
||||
# But "Processing" (Strip + Upload to Supabase) takes time.
|
||||
# Receiving took time.
|
||||
# If we await Supabase upload, does it timeout?
|
||||
# Supabase upload is outgoing. Usually faster/stable.
|
||||
|
||||
# Let's await the processing to ensure "List Materials" shows it.
|
||||
# We need to extract the filename for the list.
|
||||
|
||||
# Quick extract filename from first 4kb
|
||||
with open(temp_path, 'rb') as f:
|
||||
head = f.read(4096).decode('utf-8', errors='ignore')
|
||||
match = re.search(r'filename="([^"]+)"', head)
|
||||
if match:
|
||||
filename = match.group(1)
|
||||
logger.info(f"Extracted filename from body: {filename}")
|
||||
|
||||
# Run processing sync (in await)
|
||||
storage_path = await process_and_upload(temp_path, filename, content_type, user_id)
|
||||
|
||||
# Get signed URL (it exists now)
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=storage_path
|
||||
)
|
||||
|
||||
size_mb = total_size / (1024 * 1024) # Approximate (includes headers)
|
||||
|
||||
# 从 storage_path 提取显示名
|
||||
display_name = storage_path.split('/')[-1] # 去掉 user_id 前缀
|
||||
if '_' in display_name:
|
||||
parts = display_name.split('_', 1)
|
||||
if parts[0].isdigit():
|
||||
display_name = parts[1]
|
||||
|
||||
return success_response({
|
||||
"id": storage_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
"size_mb": size_mb,
|
||||
"type": "video"
|
||||
})
|
||||
|
||||
result = await service.upload_material(request, user_id)
|
||||
return success_response(result)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
except Exception as e:
|
||||
error_msg = f"Streaming upload failed: {str(e)}"
|
||||
detail_msg = f"Exception: {repr(e)}\nArgs: {e.args}\n{traceback.format_exc()}"
|
||||
logger.error(error_msg + "\n" + detail_msg)
|
||||
|
||||
# Write to debug file
|
||||
try:
|
||||
with open("debug_upload.log", "a") as logf:
|
||||
logf.write(f"\n--- Error at {time.ctime()} ---\n")
|
||||
logf.write(detail_msg)
|
||||
logf.write("\n-----------------------------\n")
|
||||
except:
|
||||
pass
|
||||
|
||||
if os.path.exists(temp_path):
|
||||
try:
|
||||
os.remove(temp_path)
|
||||
except:
|
||||
pass
|
||||
raise HTTPException(500, f"Upload failed. Check server logs. Error: {str(e)}")
|
||||
raise HTTPException(500, f"Upload failed. Error: {str(e)}")
|
||||
|
||||
|
||||
@router.get("")
|
||||
async def list_materials(current_user: dict = Depends(get_current_user)):
|
||||
user_id = current_user["id"]
|
||||
try:
|
||||
# 只列出当前用户目录下的文件
|
||||
files_obj = await storage_service.list_files(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=user_id
|
||||
)
|
||||
semaphore = asyncio.Semaphore(8)
|
||||
|
||||
async def build_item(f):
|
||||
name = f.get('name')
|
||||
if not name or name == '.emptyFolderPlaceholder':
|
||||
return None
|
||||
display_name = name
|
||||
if '_' in name:
|
||||
parts = name.split('_', 1)
|
||||
if parts[0].isdigit():
|
||||
display_name = parts[1]
|
||||
full_path = f"{user_id}/{name}"
|
||||
async with semaphore:
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=full_path
|
||||
)
|
||||
metadata = f.get('metadata', {})
|
||||
size = metadata.get('size', 0)
|
||||
created_at_str = f.get('created_at', '')
|
||||
created_at = 0
|
||||
if created_at_str:
|
||||
from datetime import datetime
|
||||
try:
|
||||
dt = datetime.fromisoformat(created_at_str.replace('Z', '+00:00'))
|
||||
created_at = int(dt.timestamp())
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
"id": full_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
"size_mb": size / (1024 * 1024),
|
||||
"type": "video",
|
||||
"created_at": created_at
|
||||
}
|
||||
|
||||
tasks = [build_item(f) for f in files_obj]
|
||||
results = await asyncio.gather(*tasks, return_exceptions=True)
|
||||
|
||||
materials = []
|
||||
for item in results:
|
||||
if not item:
|
||||
continue
|
||||
if isinstance(item, Exception):
|
||||
logger.warning(f"Material signed url build failed: {item}")
|
||||
continue
|
||||
materials.append(item)
|
||||
materials.sort(key=lambda x: x['id'], reverse=True)
|
||||
return success_response({"materials": materials})
|
||||
except Exception as e:
|
||||
logger.error(f"List materials failed: {e}")
|
||||
return success_response({"materials": []}, message="获取素材失败")
|
||||
materials = await service.list_materials(user_id)
|
||||
return success_response({"materials": materials})
|
||||
|
||||
|
||||
@router.delete("/{material_id:path}")
|
||||
async def delete_material(material_id: str, current_user: dict = Depends(get_current_user)):
|
||||
@router.delete("/{material_id:path}")
|
||||
async def delete_material(material_id: str, current_user: dict = Depends(get_current_user)):
|
||||
user_id = current_user["id"]
|
||||
# 验证 material_id 属于当前用户
|
||||
if not material_id.startswith(f"{user_id}/"):
|
||||
raise HTTPException(403, "无权删除此素材")
|
||||
try:
|
||||
await storage_service.delete_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=material_id
|
||||
)
|
||||
return success_response(message="素材已删除")
|
||||
except Exception as e:
|
||||
raise HTTPException(500, f"删除失败: {str(e)}")
|
||||
|
||||
|
||||
@router.put("/{material_id:path}")
|
||||
async def rename_material(
|
||||
material_id: str,
|
||||
payload: RenameMaterialRequest,
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
user_id = current_user["id"]
|
||||
if not material_id.startswith(f"{user_id}/"):
|
||||
raise HTTPException(403, "无权重命名此素材")
|
||||
|
||||
new_name_raw = payload.new_name.strip() if payload.new_name else ""
|
||||
if not new_name_raw:
|
||||
raise HTTPException(400, "新名称不能为空")
|
||||
|
||||
old_name = material_id.split("/", 1)[1]
|
||||
old_ext = Path(old_name).suffix
|
||||
base_name = Path(new_name_raw).stem if Path(new_name_raw).suffix else new_name_raw
|
||||
safe_base = sanitize_filename(base_name).strip()
|
||||
if not safe_base:
|
||||
raise HTTPException(400, "新名称无效")
|
||||
|
||||
new_filename = f"{safe_base}{old_ext}"
|
||||
|
||||
prefix = None
|
||||
if "_" in old_name:
|
||||
maybe_prefix, _ = old_name.split("_", 1)
|
||||
if maybe_prefix.isdigit():
|
||||
prefix = maybe_prefix
|
||||
if prefix:
|
||||
new_filename = f"{prefix}_{new_filename}"
|
||||
|
||||
new_path = f"{user_id}/{new_filename}"
|
||||
try:
|
||||
if new_path != material_id:
|
||||
await storage_service.move_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
from_path=material_id,
|
||||
to_path=new_path
|
||||
)
|
||||
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=new_path
|
||||
)
|
||||
|
||||
display_name = new_filename
|
||||
if "_" in new_filename:
|
||||
parts = new_filename.split("_", 1)
|
||||
if parts[0].isdigit():
|
||||
display_name = parts[1]
|
||||
|
||||
return success_response({
|
||||
"id": new_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
}, message="重命名成功")
|
||||
except Exception as e:
|
||||
raise HTTPException(500, f"重命名失败: {str(e)}")
|
||||
|
||||
await service.delete_material(material_id, user_id)
|
||||
return success_response(message="素材已删除")
|
||||
except PermissionError as e:
|
||||
raise HTTPException(403, str(e))
|
||||
except Exception as e:
|
||||
raise HTTPException(500, f"删除失败: {str(e)}")
|
||||
|
||||
|
||||
@router.put("/{material_id:path}")
|
||||
async def rename_material(
|
||||
material_id: str,
|
||||
payload: RenameMaterialRequest,
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
user_id = current_user["id"]
|
||||
try:
|
||||
result = await service.rename_material(material_id, payload.new_name, user_id)
|
||||
return success_response(result, message="重命名成功")
|
||||
except PermissionError as e:
|
||||
raise HTTPException(403, str(e))
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
except Exception as e:
|
||||
raise HTTPException(500, f"重命名失败: {str(e)}")
|
||||
|
||||
14
backend/app/modules/materials/schemas.py
Normal file
14
backend/app/modules/materials/schemas.py
Normal file
@@ -0,0 +1,14 @@
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class RenameMaterialRequest(BaseModel):
|
||||
new_name: str
|
||||
|
||||
|
||||
class MaterialItem(BaseModel):
|
||||
id: str
|
||||
name: str
|
||||
path: str
|
||||
size_mb: float
|
||||
type: str = "video"
|
||||
created_at: int = 0
|
||||
296
backend/app/modules/materials/service.py
Normal file
296
backend/app/modules/materials/service.py
Normal file
@@ -0,0 +1,296 @@
|
||||
import re
|
||||
import os
|
||||
import time
|
||||
import asyncio
|
||||
import traceback
|
||||
import aiofiles
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
|
||||
from app.services.storage import storage_service
|
||||
|
||||
|
||||
def sanitize_filename(filename: str) -> str:
|
||||
safe_name = re.sub(r'[<>:"/\\|?*]', '_', filename)
|
||||
if len(safe_name) > 100:
|
||||
ext = Path(safe_name).suffix
|
||||
safe_name = safe_name[:100 - len(ext)] + ext
|
||||
return safe_name
|
||||
|
||||
|
||||
def _extract_display_name(storage_name: str) -> str:
|
||||
"""从存储文件名中提取显示名（去掉时间戳前缀）"""
|
||||
if '_' in storage_name:
|
||||
parts = storage_name.split('_', 1)
|
||||
if parts[0].isdigit():
|
||||
return parts[1]
|
||||
return storage_name
|
||||
|
||||
|
||||
async def _process_and_upload(temp_file_path: str, original_filename: str, content_type: str, user_id: str) -> str:
|
||||
"""Strip multipart headers and upload to Supabase, return storage_path"""
|
||||
try:
|
||||
logger.info(f"Processing raw upload: {temp_file_path} for user {user_id}")
|
||||
|
||||
file_size = os.path.getsize(temp_file_path)
|
||||
|
||||
with open(temp_file_path, 'rb') as f:
|
||||
head = f.read(4096)
|
||||
|
||||
first_line_end = head.find(b'\r\n')
|
||||
if first_line_end == -1:
|
||||
raise Exception("Could not find boundary in multipart body")
|
||||
|
||||
boundary = head[:first_line_end]
|
||||
logger.info(f"Detected boundary: {boundary}")
|
||||
|
||||
header_end = head.find(b'\r\n\r\n')
|
||||
if header_end == -1:
|
||||
raise Exception("Could not find end of multipart headers")
|
||||
|
||||
start_offset = header_end + 4
|
||||
logger.info(f"Video data starts at offset: {start_offset}")
|
||||
|
||||
f.seek(max(0, file_size - 200))
|
||||
tail = f.read()
|
||||
|
||||
last_boundary_pos = tail.rfind(boundary)
|
||||
if last_boundary_pos != -1:
|
||||
end_offset = (max(0, file_size - 200) + last_boundary_pos) - 2
|
||||
else:
|
||||
logger.warning("Could not find closing boundary, assuming EOF")
|
||||
end_offset = file_size
|
||||
|
||||
logger.info(f"Video data ends at offset: {end_offset}. Total video size: {end_offset - start_offset}")
|
||||
|
||||
video_path = temp_file_path + "_video.mp4"
|
||||
with open(temp_file_path, 'rb') as src, open(video_path, 'wb') as dst:
|
||||
src.seek(start_offset)
|
||||
bytes_to_copy = end_offset - start_offset
|
||||
copied = 0
|
||||
while copied < bytes_to_copy:
|
||||
chunk_size = min(1024 * 1024 * 10, bytes_to_copy - copied)
|
||||
chunk = src.read(chunk_size)
|
||||
if not chunk:
|
||||
break
|
||||
dst.write(chunk)
|
||||
copied += len(chunk)
|
||||
|
||||
logger.info(f"Extracted video content to {video_path}")
|
||||
|
||||
timestamp = int(time.time())
|
||||
safe_name = re.sub(r'[^a-zA-Z0-9._-]', '', original_filename)
|
||||
storage_path = f"{user_id}/{timestamp}_{safe_name}"
|
||||
|
||||
with open(video_path, 'rb') as f:
|
||||
file_content = f.read()
|
||||
await storage_service.upload_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=storage_path,
|
||||
file_data=file_content,
|
||||
content_type=content_type
|
||||
)
|
||||
|
||||
logger.info(f"Upload to Supabase complete: {storage_path}")
|
||||
|
||||
os.remove(temp_file_path)
|
||||
os.remove(video_path)
|
||||
|
||||
return storage_path
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Background upload processing failed: {e}\n{traceback.format_exc()}")
|
||||
raise
|
||||
|
||||
|
||||
async def upload_material(request, user_id: str) -> dict:
|
||||
"""接收流式上传并存储到 Supabase，返回素材信息"""
|
||||
filename = "unknown_video.mp4"
|
||||
content_type = "video/mp4"
|
||||
|
||||
timestamp = int(time.time())
|
||||
temp_filename = f"upload_{timestamp}.raw"
|
||||
temp_path = os.path.join("/tmp", temp_filename)
|
||||
if os.name == 'nt':
|
||||
temp_path = f"d:/tmp/{temp_filename}"
|
||||
os.makedirs("d:/tmp", exist_ok=True)
|
||||
|
||||
try:
|
||||
total_size = 0
|
||||
last_log = 0
|
||||
|
||||
async with aiofiles.open(temp_path, 'wb') as f:
|
||||
async for chunk in request.stream():
|
||||
await f.write(chunk)
|
||||
total_size += len(chunk)
|
||||
|
||||
if total_size - last_log > 20 * 1024 * 1024:
|
||||
logger.info(f"Receiving stream... Processed {total_size / (1024*1024):.2f} MB")
|
||||
last_log = total_size
|
||||
|
||||
logger.info(f"Stream reception complete. Total size: {total_size} bytes. Saved to {temp_path}")
|
||||
|
||||
if total_size == 0:
|
||||
raise ValueError("Received empty body")
|
||||
|
||||
with open(temp_path, 'rb') as f:
|
||||
head = f.read(4096).decode('utf-8', errors='ignore')
|
||||
match = re.search(r'filename="([^"]+)"', head)
|
||||
if match:
|
||||
filename = match.group(1)
|
||||
logger.info(f"Extracted filename from body: {filename}")
|
||||
|
||||
storage_path = await _process_and_upload(temp_path, filename, content_type, user_id)
|
||||
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=storage_path
|
||||
)
|
||||
|
||||
size_mb = total_size / (1024 * 1024)
|
||||
display_name = _extract_display_name(storage_path.split('/')[-1])
|
||||
|
||||
return {
|
||||
"id": storage_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
"size_mb": size_mb,
|
||||
"type": "video"
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Streaming upload failed: {str(e)}"
|
||||
detail_msg = f"Exception: {repr(e)}\nArgs: {e.args}\n{traceback.format_exc()}"
|
||||
logger.error(error_msg + "\n" + detail_msg)
|
||||
|
||||
try:
|
||||
with open("debug_upload.log", "a") as logf:
|
||||
logf.write(f"\n--- Error at {time.ctime()} ---\n")
|
||||
logf.write(detail_msg)
|
||||
logf.write("\n-----------------------------\n")
|
||||
except:
|
||||
pass
|
||||
|
||||
if os.path.exists(temp_path):
|
||||
try:
|
||||
os.remove(temp_path)
|
||||
except:
|
||||
pass
|
||||
raise
|
||||
|
||||
|
||||
async def list_materials(user_id: str) -> list[dict]:
|
||||
"""列出用户的所有素材"""
|
||||
try:
|
||||
files_obj = await storage_service.list_files(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=user_id
|
||||
)
|
||||
semaphore = asyncio.Semaphore(8)
|
||||
|
||||
async def build_item(f):
|
||||
name = f.get('name')
|
||||
if not name or name == '.emptyFolderPlaceholder':
|
||||
return None
|
||||
display_name = _extract_display_name(name)
|
||||
full_path = f"{user_id}/{name}"
|
||||
async with semaphore:
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=full_path
|
||||
)
|
||||
metadata = f.get('metadata', {})
|
||||
size = metadata.get('size', 0)
|
||||
created_at_str = f.get('created_at', '')
|
||||
created_at = 0
|
||||
if created_at_str:
|
||||
from datetime import datetime
|
||||
try:
|
||||
dt = datetime.fromisoformat(created_at_str.replace('Z', '+00:00'))
|
||||
created_at = int(dt.timestamp())
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
"id": full_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
"size_mb": size / (1024 * 1024),
|
||||
"type": "video",
|
||||
"created_at": created_at
|
||||
}
|
||||
|
||||
tasks = [build_item(f) for f in files_obj]
|
||||
results = await asyncio.gather(*tasks, return_exceptions=True)
|
||||
|
||||
materials = []
|
||||
for item in results:
|
||||
if not item:
|
||||
continue
|
||||
if isinstance(item, Exception):
|
||||
logger.warning(f"Material signed url build failed: {item}")
|
||||
continue
|
||||
materials.append(item)
|
||||
materials.sort(key=lambda x: x['id'], reverse=True)
|
||||
return materials
|
||||
except Exception as e:
|
||||
logger.error(f"List materials failed: {e}")
|
||||
return []
|
||||
|
||||
|
||||
async def delete_material(material_id: str, user_id: str) -> None:
|
||||
"""删除素材"""
|
||||
if not material_id.startswith(f"{user_id}/"):
|
||||
raise PermissionError("无权删除此素材")
|
||||
await storage_service.delete_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=material_id
|
||||
)
|
||||
|
||||
|
||||
async def rename_material(material_id: str, new_name_raw: str, user_id: str) -> dict:
|
||||
"""重命名素材，返回更新后的素材信息"""
|
||||
if not material_id.startswith(f"{user_id}/"):
|
||||
raise PermissionError("无权重命名此素材")
|
||||
|
||||
new_name_raw = new_name_raw.strip() if new_name_raw else ""
|
||||
if not new_name_raw:
|
||||
raise ValueError("新名称不能为空")
|
||||
|
||||
old_name = material_id.split("/", 1)[1]
|
||||
old_ext = Path(old_name).suffix
|
||||
base_name = Path(new_name_raw).stem if Path(new_name_raw).suffix else new_name_raw
|
||||
safe_base = sanitize_filename(base_name).strip()
|
||||
if not safe_base:
|
||||
raise ValueError("新名称无效")
|
||||
|
||||
new_filename = f"{safe_base}{old_ext}"
|
||||
|
||||
prefix = None
|
||||
if "_" in old_name:
|
||||
maybe_prefix, _ = old_name.split("_", 1)
|
||||
if maybe_prefix.isdigit():
|
||||
prefix = maybe_prefix
|
||||
if prefix:
|
||||
new_filename = f"{prefix}_{new_filename}"
|
||||
|
||||
new_path = f"{user_id}/{new_filename}"
|
||||
|
||||
if new_path != material_id:
|
||||
await storage_service.move_file(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
from_path=material_id,
|
||||
to_path=new_path
|
||||
)
|
||||
|
||||
signed_url = await storage_service.get_signed_url(
|
||||
bucket=storage_service.BUCKET_MATERIALS,
|
||||
path=new_path
|
||||
)
|
||||
|
||||
display_name = _extract_display_name(new_filename)
|
||||
|
||||
return {
|
||||
"id": new_path,
|
||||
"name": display_name,
|
||||
"path": signed_url,
|
||||
}
|
||||
@@ -1,83 +1,14 @@
|
||||
"""
|
||||
参考音频管理 API
|
||||
支持上传/列表/删除参考音频，用于 Qwen3-TTS 声音克隆
|
||||
"""
|
||||
"""参考音频管理 API"""
|
||||
from fastapi import APIRouter, UploadFile, File, Form, HTTPException, Depends
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Optional
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
import time
|
||||
import json
|
||||
import subprocess
|
||||
import tempfile
|
||||
import os
|
||||
import re
|
||||
|
||||
from app.core.deps import get_current_user
|
||||
from app.services.storage import storage_service
|
||||
from app.core.response import success_response
|
||||
from app.modules.ref_audios.schemas import RenameRequest
|
||||
from app.modules.ref_audios import service
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# 支持的音频格式
|
||||
ALLOWED_AUDIO_EXTENSIONS = {'.wav', '.mp3', '.m4a', '.webm', '.ogg', '.flac', '.aac'}
|
||||
|
||||
# 参考音频 bucket
|
||||
BUCKET_REF_AUDIOS = "ref-audios"
|
||||
|
||||
|
||||
class RefAudioResponse(BaseModel):
|
||||
id: str
|
||||
name: str
|
||||
path: str # signed URL for playback
|
||||
ref_text: str
|
||||
duration_sec: float
|
||||
created_at: int
|
||||
|
||||
|
||||
class RefAudioListResponse(BaseModel):
|
||||
items: List[RefAudioResponse]
|
||||
|
||||
|
||||
def sanitize_filename(filename: str) -> str:
|
||||
"""清理文件名，移除特殊字符"""
|
||||
safe_name = re.sub(r'[<>:"/\\|?*\s]', '_', filename)
|
||||
if len(safe_name) > 50:
|
||||
ext = Path(safe_name).suffix
|
||||
safe_name = safe_name[:50 - len(ext)] + ext
|
||||
return safe_name
|
||||
|
||||
|
||||
def get_audio_duration(file_path: str) -> float:
|
||||
"""获取音频时长 (秒)"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
['ffprobe', '-v', 'quiet', '-show_entries', 'format=duration',
|
||||
'-of', 'csv=p=0', file_path],
|
||||
capture_output=True, text=True, timeout=10
|
||||
)
|
||||
return float(result.stdout.strip())
|
||||
except Exception as e:
|
||||
logger.warning(f"获取音频时长失败: {e}")
|
||||
return 0.0
|
||||
|
||||
|
||||
def convert_to_wav(input_path: str, output_path: str) -> bool:
|
||||
"""将音频转换为 WAV 格式 (16kHz, mono)"""
|
||||
try:
|
||||
subprocess.run([
|
||||
'ffmpeg', '-y', '-i', input_path,
|
||||
'-ar', '16000', # 16kHz 采样率
|
||||
'-ac', '1', # 单声道
|
||||
'-acodec', 'pcm_s16le', # 16-bit PCM
|
||||
output_path
|
||||
], capture_output=True, timeout=60, check=True)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"音频转换失败: {e}")
|
||||
return False
|
||||
|
||||
|
||||
@router.post("")
|
||||
async def upload_ref_audio(
|
||||
@@ -85,156 +16,12 @@ async def upload_ref_audio(
|
||||
ref_text: str = Form(...),
|
||||
user: dict = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
上传参考音频
|
||||
|
||||
- file: 音频文件 (支持 wav, mp3, m4a, webm 等)
|
||||
- ref_text: 参考音频的转写文字 (必填)
|
||||
"""
|
||||
user_id = user["id"]
|
||||
|
||||
if not file.filename:
|
||||
raise HTTPException(status_code=400, detail="文件名无效")
|
||||
filename = file.filename
|
||||
|
||||
# 验证文件扩展名
|
||||
ext = Path(filename).suffix.lower()
|
||||
if ext not in ALLOWED_AUDIO_EXTENSIONS:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的音频格式: {ext}。支持的格式: {', '.join(ALLOWED_AUDIO_EXTENSIONS)}"
|
||||
)
|
||||
|
||||
# 验证 ref_text
|
||||
if not ref_text or len(ref_text.strip()) < 2:
|
||||
raise HTTPException(status_code=400, detail="参考文字不能为空")
|
||||
|
||||
"""上传参考音频"""
|
||||
try:
|
||||
# 创建临时文件
|
||||
with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp_input:
|
||||
content = await file.read()
|
||||
tmp_input.write(content)
|
||||
tmp_input_path = tmp_input.name
|
||||
|
||||
# 转换为 WAV 格式
|
||||
tmp_wav_path = tmp_input_path + ".wav"
|
||||
if ext != '.wav':
|
||||
if not convert_to_wav(tmp_input_path, tmp_wav_path):
|
||||
raise HTTPException(status_code=500, detail="音频格式转换失败")
|
||||
else:
|
||||
# 即使是 wav 也要标准化格式
|
||||
convert_to_wav(tmp_input_path, tmp_wav_path)
|
||||
|
||||
# 获取音频时长
|
||||
duration = get_audio_duration(tmp_wav_path)
|
||||
if duration < 1.0:
|
||||
raise HTTPException(status_code=400, detail="音频时长过短，至少需要 1 秒")
|
||||
if duration > 60.0:
|
||||
raise HTTPException(status_code=400, detail="音频时长过长，最多 60 秒")
|
||||
|
||||
|
||||
# 3. 处理重名逻辑 (Friendly Display Name)
|
||||
original_name = filename
|
||||
|
||||
# 获取用户现有的所有参考音频列表 (为了检查文件名冲突)
|
||||
# 注意: 这种列表方式在文件极多时性能一般，但考虑到单用户参考音频数量有限，目前可行
|
||||
existing_files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
|
||||
existing_names = set()
|
||||
|
||||
# 预加载所有现有的 display name
|
||||
# 这里需要并发请求 metadata 可能会慢，优化: 仅检查 metadata 文件并解析
|
||||
# 简易方案: 仅在 metadata 中读取 original_filename
|
||||
# 但 list_files 返回的是 name，我们需要 metadata
|
||||
# 考虑到性能，这里使用一种妥协方案：
|
||||
# 我们不做全量检查，而是简单的检查：如果用户上传 myvoice.wav
|
||||
# 我们看看有没有 (timestamp)_myvoice.wav 这种其实并不能准确判断 display name 是否冲突
|
||||
#
|
||||
# 正确做法: 应该有个数据库表存 metadata。但目前是无数据库设计。
|
||||
#
|
||||
# 改用简单方案:
|
||||
# 既然我们无法快速获取所有 display name，
|
||||
# 我们暂时只处理 "在新上传时，original_filename 保持原样"
|
||||
# 但用户希望 "如果在列表中看到重复的，自动加(1)"
|
||||
#
|
||||
# 鉴于无数据库架构的限制，要在上传时知道"已有的 display name" 成本太高(需遍历下载所有json)。
|
||||
#
|
||||
# 💡 替代方案:
|
||||
# 我们不检查旧的。我们只保证**存储**唯一。
|
||||
# 对于用户提到的 "新上传的文件名后加个数字" -> 这通常是指 "另存为" 的逻辑。
|
||||
# 既然用户现在的痛点是 "显示了时间戳太丑"，而我已经去掉了时间戳显示。
|
||||
# 那么如果用户上传两个 "TEST.wav"，列表里就会有两个 "TEST.wav" (但时间不同)。
|
||||
# 这其实是可以接受的。
|
||||
#
|
||||
# 但如果用户强求 "自动重命名":
|
||||
# 我们可以在这里做一个轻量级的 "同名检测"：
|
||||
# 检查有没有 *_{original_name} 的文件存在。
|
||||
# 如果 storage 里已经有 123_abc.wav, 456_abc.wav
|
||||
# 我们可以认为 abc.wav 已经存在。
|
||||
|
||||
dup_count = 0
|
||||
search_suffix = f"_{original_name}" # 比如 _test.wav
|
||||
|
||||
for f in existing_files:
|
||||
fname = f.get('name', '')
|
||||
if fname.endswith(search_suffix):
|
||||
dup_count += 1
|
||||
|
||||
final_display_name = original_name
|
||||
if dup_count > 0:
|
||||
name_stem = Path(original_name).stem
|
||||
name_ext = Path(original_name).suffix
|
||||
final_display_name = f"{name_stem}({dup_count}){name_ext}"
|
||||
|
||||
# 生成存储路径 (唯一ID)
|
||||
timestamp = int(time.time())
|
||||
safe_name = sanitize_filename(Path(filename).stem)
|
||||
storage_path = f"{user_id}/{timestamp}_{safe_name}.wav"
|
||||
|
||||
# 上传 WAV 文件到 Supabase
|
||||
with open(tmp_wav_path, 'rb') as f:
|
||||
wav_data = f.read()
|
||||
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=storage_path,
|
||||
file_data=wav_data,
|
||||
content_type="audio/wav"
|
||||
)
|
||||
|
||||
# 上传元数据 JSON
|
||||
metadata = {
|
||||
"ref_text": ref_text.strip(),
|
||||
"original_filename": final_display_name, # 这里的名字如果有重复会自动加(1)
|
||||
"duration_sec": duration,
|
||||
"created_at": timestamp
|
||||
}
|
||||
metadata_path = f"{user_id}/{timestamp}_{safe_name}.json"
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=metadata_path,
|
||||
file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
|
||||
content_type="application/json"
|
||||
)
|
||||
|
||||
# 获取签名 URL
|
||||
signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
|
||||
|
||||
# 清理临时文件
|
||||
os.unlink(tmp_input_path)
|
||||
if os.path.exists(tmp_wav_path):
|
||||
os.unlink(tmp_wav_path)
|
||||
|
||||
return success_response(RefAudioResponse(
|
||||
id=storage_path,
|
||||
name=filename,
|
||||
path=signed_url,
|
||||
ref_text=ref_text.strip(),
|
||||
duration_sec=duration,
|
||||
created_at=timestamp
|
||||
).model_dump())
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
result = await service.upload_ref_audio(file, ref_text, user["id"])
|
||||
return success_response(result)
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
logger.error(f"上传参考音频失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"上传失败: {str(e)}")
|
||||
@@ -243,81 +30,9 @@ async def upload_ref_audio(
|
||||
@router.get("")
|
||||
async def list_ref_audios(user: dict = Depends(get_current_user)):
|
||||
"""列出当前用户的所有参考音频"""
|
||||
user_id = user["id"]
|
||||
|
||||
try:
|
||||
# 列出用户目录下的文件
|
||||
files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
|
||||
|
||||
# 过滤出 .wav 文件
|
||||
wav_files = [f for f in files if f.get("name", "").endswith(".wav")]
|
||||
|
||||
if not wav_files:
|
||||
return success_response(RefAudioListResponse(items=[]).model_dump())
|
||||
|
||||
# 并发获取所有 metadata 和签名 URL
|
||||
async def fetch_audio_info(f):
|
||||
"""获取单个音频的信息（metadata + signed URL）"""
|
||||
name = f.get("name", "")
|
||||
storage_path = f"{user_id}/{name}"
|
||||
metadata_name = name.replace(".wav", ".json")
|
||||
metadata_path = f"{user_id}/{metadata_name}"
|
||||
|
||||
ref_text = ""
|
||||
duration_sec = 0.0
|
||||
created_at = 0
|
||||
original_filename = ""
|
||||
|
||||
try:
|
||||
# 获取 metadata 内容
|
||||
metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
|
||||
import httpx
|
||||
async with httpx.AsyncClient(timeout=5.0) as client:
|
||||
resp = await client.get(metadata_url)
|
||||
if resp.status_code == 200:
|
||||
metadata = resp.json()
|
||||
ref_text = metadata.get("ref_text", "")
|
||||
duration_sec = metadata.get("duration_sec", 0.0)
|
||||
created_at = metadata.get("created_at", 0)
|
||||
original_filename = metadata.get("original_filename", "")
|
||||
except Exception as e:
|
||||
logger.debug(f"读取 metadata 失败: {e}")
|
||||
# 从文件名提取时间戳
|
||||
try:
|
||||
created_at = int(name.split("_")[0])
|
||||
except:
|
||||
pass
|
||||
|
||||
# 获取音频签名 URL
|
||||
signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
|
||||
|
||||
# 优先显示原始文件名 (去掉时间戳前缀)
|
||||
display_name = original_filename if original_filename else name
|
||||
# 如果原始文件名丢失，尝试从现有文件名中通过正则去掉时间戳
|
||||
if not display_name or display_name == name:
|
||||
# 匹配 "1234567890_filename.wav"
|
||||
match = re.match(r'^\d+_(.+)$', name)
|
||||
if match:
|
||||
display_name = match.group(1)
|
||||
|
||||
return RefAudioResponse(
|
||||
id=storage_path,
|
||||
name=display_name,
|
||||
path=signed_url,
|
||||
ref_text=ref_text,
|
||||
duration_sec=duration_sec,
|
||||
created_at=created_at
|
||||
)
|
||||
|
||||
# 使用 asyncio.gather 并发获取所有音频信息
|
||||
import asyncio
|
||||
items = await asyncio.gather(*[fetch_audio_info(f) for f in wav_files])
|
||||
|
||||
# 按创建时间倒序排列
|
||||
items = sorted(items, key=lambda x: x.created_at, reverse=True)
|
||||
|
||||
return success_response(RefAudioListResponse(items=items).model_dump())
|
||||
|
||||
result = await service.list_ref_audios(user["id"])
|
||||
return success_response(result)
|
||||
except Exception as e:
|
||||
logger.error(f"列出参考音频失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"获取列表失败: {str(e)}")
|
||||
@@ -326,96 +41,30 @@ async def list_ref_audios(user: dict = Depends(get_current_user)):
|
||||
@router.delete("/{audio_id:path}")
|
||||
async def delete_ref_audio(audio_id: str, user: dict = Depends(get_current_user)):
|
||||
"""删除参考音频"""
|
||||
user_id = user["id"]
|
||||
|
||||
# 安全检查：确保只能删除自己的文件
|
||||
if not audio_id.startswith(f"{user_id}/"):
|
||||
raise HTTPException(status_code=403, detail="无权删除此文件")
|
||||
|
||||
try:
|
||||
# 删除 WAV 文件
|
||||
await storage_service.delete_file(BUCKET_REF_AUDIOS, audio_id)
|
||||
|
||||
# 删除 metadata JSON
|
||||
metadata_path = audio_id.replace(".wav", ".json")
|
||||
try:
|
||||
await storage_service.delete_file(BUCKET_REF_AUDIOS, metadata_path)
|
||||
except:
|
||||
pass # metadata 可能不存在
|
||||
|
||||
await service.delete_ref_audio(audio_id, user["id"])
|
||||
return success_response(message="删除成功")
|
||||
|
||||
except PermissionError as e:
|
||||
raise HTTPException(status_code=403, detail=str(e))
|
||||
except Exception as e:
|
||||
logger.error(f"删除参考音频失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"删除失败: {str(e)}")
|
||||
|
||||
|
||||
class RenameRequest(BaseModel):
|
||||
new_name: str
|
||||
|
||||
|
||||
@router.put("/{audio_id:path}")
|
||||
async def rename_ref_audio(
|
||||
audio_id: str,
|
||||
request: RenameRequest,
|
||||
user: dict = Depends(get_current_user)
|
||||
):
|
||||
"""重命名参考音频 (修改 metadata 中的 display name)"""
|
||||
user_id = user["id"]
|
||||
|
||||
# 安全检查
|
||||
if not audio_id.startswith(f"{user_id}/"):
|
||||
raise HTTPException(status_code=403, detail="无权修改此文件")
|
||||
|
||||
new_name = request.new_name.strip()
|
||||
if not new_name:
|
||||
raise HTTPException(status_code=400, detail="新名称不能为空")
|
||||
|
||||
# 确保新名称有后缀 (保留原后缀或添加 .wav)
|
||||
if not Path(new_name).suffix:
|
||||
new_name += ".wav"
|
||||
|
||||
"""重命名参考音频"""
|
||||
try:
|
||||
# 1. 下载现有的 metadata
|
||||
metadata_path = audio_id.replace(".wav", ".json")
|
||||
try:
|
||||
# 获取已有的 JSON
|
||||
import httpx
|
||||
metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
|
||||
if not metadata_url:
|
||||
# 如果 json 不存在，则需要新建一个基础的
|
||||
raise Exception("Metadata not found")
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(metadata_url)
|
||||
if resp.status_code == 200:
|
||||
metadata = resp.json()
|
||||
else:
|
||||
raise Exception(f"Failed to fetch metadata: {resp.status_code}")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"无法读取元数据: {e}, 将创建新的元数据")
|
||||
# 兜底：如果读取失败，构建最小元数据
|
||||
metadata = {
|
||||
"ref_text": "", # 可能丢失
|
||||
"duration_sec": 0.0,
|
||||
"created_at": int(time.time()),
|
||||
"original_filename": new_name
|
||||
}
|
||||
|
||||
# 2. 更新 original_filename
|
||||
metadata["original_filename"] = new_name
|
||||
|
||||
# 3. 覆盖上传 metadata
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=metadata_path,
|
||||
file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
|
||||
content_type="application/json"
|
||||
)
|
||||
|
||||
return success_response({"name": new_name}, message="重命名成功")
|
||||
|
||||
result = await service.rename_ref_audio(audio_id, request.new_name, user["id"])
|
||||
return success_response(result, message="重命名成功")
|
||||
except PermissionError as e:
|
||||
raise HTTPException(status_code=403, detail=str(e))
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
logger.error(f"重命名失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"重命名失败: {str(e)}")
|
||||
|
||||
19
backend/app/modules/ref_audios/schemas.py
Normal file
19
backend/app/modules/ref_audios/schemas.py
Normal file
@@ -0,0 +1,19 @@
|
||||
from pydantic import BaseModel
|
||||
from typing import List
|
||||
|
||||
|
||||
class RefAudioResponse(BaseModel):
|
||||
id: str
|
||||
name: str
|
||||
path: str
|
||||
ref_text: str
|
||||
duration_sec: float
|
||||
created_at: int
|
||||
|
||||
|
||||
class RefAudioListResponse(BaseModel):
|
||||
items: List[RefAudioResponse]
|
||||
|
||||
|
||||
class RenameRequest(BaseModel):
|
||||
new_name: str
|
||||
269
backend/app/modules/ref_audios/service.py
Normal file
269
backend/app/modules/ref_audios/service.py
Normal file
@@ -0,0 +1,269 @@
|
||||
import re
|
||||
import os
|
||||
import time
|
||||
import json
|
||||
import asyncio
|
||||
import subprocess
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
from loguru import logger
|
||||
|
||||
from app.services.storage import storage_service
|
||||
from app.modules.ref_audios.schemas import RefAudioResponse, RefAudioListResponse
|
||||
|
||||
ALLOWED_AUDIO_EXTENSIONS = {'.wav', '.mp3', '.m4a', '.webm', '.ogg', '.flac', '.aac'}
|
||||
BUCKET_REF_AUDIOS = "ref-audios"
|
||||
|
||||
|
||||
def sanitize_filename(filename: str) -> str:
|
||||
"""清理文件名，移除特殊字符"""
|
||||
safe_name = re.sub(r'[<>:"/\\|?*\s]', '_', filename)
|
||||
if len(safe_name) > 50:
|
||||
ext = Path(safe_name).suffix
|
||||
safe_name = safe_name[:50 - len(ext)] + ext
|
||||
return safe_name
|
||||
|
||||
|
||||
def _get_audio_duration(file_path: str) -> float:
|
||||
"""获取音频时长 (秒)"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
['ffprobe', '-v', 'quiet', '-show_entries', 'format=duration',
|
||||
'-of', 'csv=p=0', file_path],
|
||||
capture_output=True, text=True, timeout=10
|
||||
)
|
||||
return float(result.stdout.strip())
|
||||
except Exception as e:
|
||||
logger.warning(f"获取音频时长失败: {e}")
|
||||
return 0.0
|
||||
|
||||
|
||||
def _convert_to_wav(input_path: str, output_path: str) -> bool:
|
||||
"""将音频转换为 WAV 格式 (16kHz, mono)"""
|
||||
try:
|
||||
subprocess.run([
|
||||
'ffmpeg', '-y', '-i', input_path,
|
||||
'-ar', '16000',
|
||||
'-ac', '1',
|
||||
'-acodec', 'pcm_s16le',
|
||||
output_path
|
||||
], capture_output=True, timeout=60, check=True)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"音频转换失败: {e}")
|
||||
return False
|
||||
|
||||
|
||||
async def upload_ref_audio(file, ref_text: str, user_id: str) -> dict:
|
||||
"""上传参考音频：转码、获取时长、存储到 Supabase"""
|
||||
if not file.filename:
|
||||
raise ValueError("文件名无效")
|
||||
filename = file.filename
|
||||
|
||||
ext = Path(filename).suffix.lower()
|
||||
if ext not in ALLOWED_AUDIO_EXTENSIONS:
|
||||
raise ValueError(f"不支持的音频格式: {ext}。支持的格式: {', '.join(ALLOWED_AUDIO_EXTENSIONS)}")
|
||||
|
||||
if not ref_text or len(ref_text.strip()) < 2:
|
||||
raise ValueError("参考文字不能为空")
|
||||
|
||||
# 创建临时文件
|
||||
with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp_input:
|
||||
content = await file.read()
|
||||
tmp_input.write(content)
|
||||
tmp_input_path = tmp_input.name
|
||||
|
||||
try:
|
||||
# 转换为 WAV 格式
|
||||
tmp_wav_path = tmp_input_path + ".wav"
|
||||
if not _convert_to_wav(tmp_input_path, tmp_wav_path):
|
||||
raise RuntimeError("音频格式转换失败")
|
||||
|
||||
# 获取音频时长
|
||||
duration = _get_audio_duration(tmp_wav_path)
|
||||
if duration < 1.0:
|
||||
raise ValueError("音频时长过短，至少需要 1 秒")
|
||||
if duration > 60.0:
|
||||
raise ValueError("音频时长过长，最多 60 秒")
|
||||
|
||||
# 检查重名
|
||||
existing_files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
|
||||
dup_count = 0
|
||||
search_suffix = f"_{filename}"
|
||||
for f in existing_files:
|
||||
fname = f.get('name', '')
|
||||
if fname.endswith(search_suffix):
|
||||
dup_count += 1
|
||||
|
||||
final_display_name = filename
|
||||
if dup_count > 0:
|
||||
name_stem = Path(filename).stem
|
||||
name_ext = Path(filename).suffix
|
||||
final_display_name = f"{name_stem}({dup_count}){name_ext}"
|
||||
|
||||
# 生成存储路径
|
||||
timestamp = int(time.time())
|
||||
safe_name = sanitize_filename(Path(filename).stem)
|
||||
storage_path = f"{user_id}/{timestamp}_{safe_name}.wav"
|
||||
|
||||
# 上传 WAV 文件
|
||||
with open(tmp_wav_path, 'rb') as f:
|
||||
wav_data = f.read()
|
||||
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=storage_path,
|
||||
file_data=wav_data,
|
||||
content_type="audio/wav"
|
||||
)
|
||||
|
||||
# 上传元数据 JSON
|
||||
metadata = {
|
||||
"ref_text": ref_text.strip(),
|
||||
"original_filename": final_display_name,
|
||||
"duration_sec": duration,
|
||||
"created_at": timestamp
|
||||
}
|
||||
metadata_path = f"{user_id}/{timestamp}_{safe_name}.json"
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=metadata_path,
|
||||
file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
|
||||
content_type="application/json"
|
||||
)
|
||||
|
||||
# 获取签名 URL
|
||||
signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
|
||||
|
||||
return RefAudioResponse(
|
||||
id=storage_path,
|
||||
name=filename,
|
||||
path=signed_url,
|
||||
ref_text=ref_text.strip(),
|
||||
duration_sec=duration,
|
||||
created_at=timestamp
|
||||
).model_dump()
|
||||
|
||||
finally:
|
||||
os.unlink(tmp_input_path)
|
||||
if os.path.exists(tmp_input_path + ".wav"):
|
||||
os.unlink(tmp_input_path + ".wav")
|
||||
|
||||
|
||||
async def list_ref_audios(user_id: str) -> dict:
|
||||
"""列出用户的所有参考音频"""
|
||||
files = await storage_service.list_files(BUCKET_REF_AUDIOS, user_id)
|
||||
wav_files = [f for f in files if f.get("name", "").endswith(".wav")]
|
||||
|
||||
if not wav_files:
|
||||
return RefAudioListResponse(items=[]).model_dump()
|
||||
|
||||
async def fetch_audio_info(f):
|
||||
name = f.get("name", "")
|
||||
storage_path = f"{user_id}/{name}"
|
||||
metadata_name = name.replace(".wav", ".json")
|
||||
metadata_path = f"{user_id}/{metadata_name}"
|
||||
|
||||
ref_text = ""
|
||||
duration_sec = 0.0
|
||||
created_at = 0
|
||||
original_filename = ""
|
||||
|
||||
try:
|
||||
metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
|
||||
async with httpx.AsyncClient(timeout=5.0) as client:
|
||||
resp = await client.get(metadata_url)
|
||||
if resp.status_code == 200:
|
||||
metadata = resp.json()
|
||||
ref_text = metadata.get("ref_text", "")
|
||||
duration_sec = metadata.get("duration_sec", 0.0)
|
||||
created_at = metadata.get("created_at", 0)
|
||||
original_filename = metadata.get("original_filename", "")
|
||||
except Exception as e:
|
||||
logger.debug(f"读取 metadata 失败: {e}")
|
||||
try:
|
||||
created_at = int(name.split("_")[0])
|
||||
except:
|
||||
pass
|
||||
|
||||
signed_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, storage_path)
|
||||
|
||||
display_name = original_filename if original_filename else name
|
||||
if not display_name or display_name == name:
|
||||
match = re.match(r'^\d+_(.+)$', name)
|
||||
if match:
|
||||
display_name = match.group(1)
|
||||
|
||||
return RefAudioResponse(
|
||||
id=storage_path,
|
||||
name=display_name,
|
||||
path=signed_url,
|
||||
ref_text=ref_text,
|
||||
duration_sec=duration_sec,
|
||||
created_at=created_at
|
||||
)
|
||||
|
||||
items = await asyncio.gather(*[fetch_audio_info(f) for f in wav_files])
|
||||
items = sorted(items, key=lambda x: x.created_at, reverse=True)
|
||||
|
||||
return RefAudioListResponse(items=items).model_dump()
|
||||
|
||||
|
||||
async def delete_ref_audio(audio_id: str, user_id: str) -> None:
|
||||
"""删除参考音频及其元数据"""
|
||||
if not audio_id.startswith(f"{user_id}/"):
|
||||
raise PermissionError("无权删除此文件")
|
||||
|
||||
await storage_service.delete_file(BUCKET_REF_AUDIOS, audio_id)
|
||||
|
||||
metadata_path = audio_id.replace(".wav", ".json")
|
||||
try:
|
||||
await storage_service.delete_file(BUCKET_REF_AUDIOS, metadata_path)
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
async def rename_ref_audio(audio_id: str, new_name: str, user_id: str) -> dict:
|
||||
"""重命名参考音频（修改 metadata 中的 display name）"""
|
||||
if not audio_id.startswith(f"{user_id}/"):
|
||||
raise PermissionError("无权修改此文件")
|
||||
|
||||
new_name = new_name.strip()
|
||||
if not new_name:
|
||||
raise ValueError("新名称不能为空")
|
||||
|
||||
if not Path(new_name).suffix:
|
||||
new_name += ".wav"
|
||||
|
||||
# 下载现有 metadata
|
||||
metadata_path = audio_id.replace(".wav", ".json")
|
||||
try:
|
||||
metadata_url = await storage_service.get_signed_url(BUCKET_REF_AUDIOS, metadata_path)
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(metadata_url)
|
||||
if resp.status_code == 200:
|
||||
metadata = resp.json()
|
||||
else:
|
||||
raise Exception(f"Failed to fetch metadata: {resp.status_code}")
|
||||
except Exception as e:
|
||||
logger.warning(f"无法读取元数据: {e}, 将创建新的元数据")
|
||||
metadata = {
|
||||
"ref_text": "",
|
||||
"duration_sec": 0.0,
|
||||
"created_at": int(time.time()),
|
||||
"original_filename": new_name
|
||||
}
|
||||
|
||||
# 更新并覆盖上传
|
||||
metadata["original_filename"] = new_name
|
||||
await storage_service.upload_file(
|
||||
bucket=BUCKET_REF_AUDIOS,
|
||||
path=metadata_path,
|
||||
file_data=json.dumps(metadata, ensure_ascii=False).encode('utf-8'),
|
||||
content_type="application/json"
|
||||
)
|
||||
|
||||
return {"name": new_name}
|
||||
@@ -1,417 +1,32 @@
|
||||
from fastapi import APIRouter, UploadFile, File, Form, HTTPException
|
||||
from typing import Optional, Any, cast
|
||||
import asyncio
|
||||
import shutil
|
||||
import os
|
||||
import time
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
from typing import Optional
|
||||
import traceback
|
||||
import re
|
||||
import json
|
||||
import requests
|
||||
from urllib.parse import unquote
|
||||
from loguru import logger
|
||||
|
||||
from app.services.whisper_service import whisper_service
|
||||
from app.services.glm_service import glm_service
|
||||
from app.core.response import success_response
|
||||
from app.modules.tools import service
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("/extract-script")
|
||||
async def extract_script_tool(
|
||||
file: Optional[UploadFile] = File(None),
|
||||
url: Optional[str] = Form(None),
|
||||
rewrite: bool = Form(True)
|
||||
):
|
||||
"""
|
||||
独立文案提取工具
|
||||
支持上传视频/音频 OR 输入视频链接 -> 提取文字 -> (可选) AI洗稿
|
||||
"""
|
||||
if not file and not url:
|
||||
raise HTTPException(400, "必须提供文件或视频链接")
|
||||
|
||||
temp_path = None
|
||||
"""独立文案提取工具"""
|
||||
try:
|
||||
timestamp = int(time.time())
|
||||
temp_dir = Path("/tmp")
|
||||
if os.name == 'nt':
|
||||
temp_dir = Path("d:/tmp")
|
||||
temp_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# 1. 获取/保存文件
|
||||
loop = asyncio.get_event_loop()
|
||||
|
||||
if file:
|
||||
filename = file.filename
|
||||
if not filename:
|
||||
raise HTTPException(400, "文件名无效")
|
||||
safe_filename = Path(filename).name.replace(" ", "_")
|
||||
temp_path = temp_dir / f"tool_extract_{timestamp}_{safe_filename}"
|
||||
# 文件 I/O 放入线程池
|
||||
await loop.run_in_executor(None, lambda: shutil.copyfileobj(file.file, open(temp_path, "wb")))
|
||||
logger.info(f"Tool processing upload file: {temp_path}")
|
||||
else:
|
||||
if not url:
|
||||
raise HTTPException(400, "必须提供视频链接")
|
||||
url_value: str = url
|
||||
# URL 下载逻辑
|
||||
# 自动提取文案中的链接 (支持 Douyin/Bilibili 等分享文案)
|
||||
url_match = re.search(r'https?://[^\s]+', url_value)
|
||||
if url_match:
|
||||
extracted_url = url_match.group(0)
|
||||
logger.info(f"Extracted URL from text: {extracted_url}")
|
||||
url_value = extracted_url
|
||||
|
||||
logger.info(f"Tool downloading URL: {url_value}")
|
||||
|
||||
# 封装 yt-dlp 下载函数 (Blocking)
|
||||
def _download_yt_dlp():
|
||||
import yt_dlp
|
||||
logger.info("Attempting download with yt-dlp...")
|
||||
|
||||
ydl_opts = {
|
||||
'format': 'bestaudio/best',
|
||||
'outtmpl': str(temp_dir / f"tool_download_{timestamp}_%(id)s.%(ext)s"),
|
||||
'quiet': True,
|
||||
'no_warnings': True,
|
||||
'http_headers': {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': 'https://www.douyin.com/',
|
||||
}
|
||||
}
|
||||
|
||||
with yt_dlp.YoutubeDL() as ydl_raw:
|
||||
ydl: Any = ydl_raw
|
||||
ydl.params.update(ydl_opts)
|
||||
info = ydl.extract_info(url_value, download=True)
|
||||
if 'requested_downloads' in info:
|
||||
downloaded_file = info['requested_downloads'][0]['filepath']
|
||||
else:
|
||||
ext = info.get('ext', 'mp4')
|
||||
id = info.get('id')
|
||||
downloaded_file = str(temp_dir / f"tool_download_{timestamp}_{id}.{ext}")
|
||||
|
||||
return Path(downloaded_file)
|
||||
|
||||
# 先尝试 yt-dlp (Run in Executor)
|
||||
try:
|
||||
temp_path = await loop.run_in_executor(None, _download_yt_dlp)
|
||||
logger.info(f"yt-dlp downloaded to: {temp_path}")
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"yt-dlp download failed: {e}. Trying manual Douyin fallback...")
|
||||
|
||||
# 失败则尝试手动解析 (Douyin Fallback)
|
||||
if "douyin" in url_value:
|
||||
manual_path = await download_douyin_manual(url_value, temp_dir, timestamp)
|
||||
if manual_path:
|
||||
temp_path = manual_path
|
||||
logger.info(f"Manual Douyin fallback successful: {temp_path}")
|
||||
else:
|
||||
raise HTTPException(400, f"视频下载失败。yt-dlp 报错: {str(e)}")
|
||||
elif "bilibili" in url_value:
|
||||
manual_path = await download_bilibili_manual(url_value, temp_dir, timestamp)
|
||||
if manual_path:
|
||||
temp_path = manual_path
|
||||
logger.info(f"Manual Bilibili fallback successful: {temp_path}")
|
||||
else:
|
||||
raise HTTPException(400, f"视频下载失败。yt-dlp 报错: {str(e)}")
|
||||
else:
|
||||
raise HTTPException(400, f"视频下载失败: {str(e)}")
|
||||
|
||||
if not temp_path or not temp_path.exists():
|
||||
raise HTTPException(400, "文件获取失败")
|
||||
|
||||
# 1.5 安全转换: 强制转为 WAV (16k)
|
||||
import subprocess
|
||||
audio_path = temp_dir / f"extract_audio_{timestamp}.wav"
|
||||
|
||||
def _convert_audio():
|
||||
try:
|
||||
convert_cmd = [
|
||||
'ffmpeg',
|
||||
'-i', str(temp_path),
|
||||
'-vn', # 忽略视频
|
||||
'-acodec', 'pcm_s16le',
|
||||
'-ar', '16000', # Whisper 推荐采样率
|
||||
'-ac', '1', # 单声道
|
||||
'-y', # 覆盖
|
||||
str(audio_path)
|
||||
]
|
||||
# 捕获 stderr
|
||||
subprocess.run(convert_cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
return True
|
||||
except subprocess.CalledProcessError as e:
|
||||
error_log = e.stderr.decode('utf-8', errors='ignore') if e.stderr else str(e)
|
||||
logger.error(f"FFmpeg check/convert failed: {error_log}")
|
||||
# 检查是否为 HTML
|
||||
head = b""
|
||||
try:
|
||||
with open(temp_path, 'rb') as f:
|
||||
head = f.read(100)
|
||||
except: pass
|
||||
if b'<!DOCTYPE html' in head or b'<html' in head:
|
||||
raise ValueError("HTML_DETECTED")
|
||||
raise ValueError("CONVERT_FAILED")
|
||||
|
||||
# 执行转换 (Run in Executor)
|
||||
try:
|
||||
await loop.run_in_executor(None, _convert_audio)
|
||||
logger.info(f"Converted to WAV: {audio_path}")
|
||||
target_path = audio_path
|
||||
except ValueError as ve:
|
||||
if str(ve) == "HTML_DETECTED":
|
||||
raise HTTPException(400, "下载的文件是网页而非视频，请重试或手动上传。")
|
||||
else:
|
||||
raise HTTPException(400, "下载的文件已损坏或格式无法识别。")
|
||||
|
||||
# 2. 提取文案 (Whisper)
|
||||
script = await whisper_service.transcribe(str(target_path))
|
||||
|
||||
# 3. AI 洗稿 (GLM)
|
||||
rewritten = None
|
||||
if rewrite:
|
||||
if script and len(script.strip()) > 0:
|
||||
logger.info("Rewriting script...")
|
||||
rewritten = await glm_service.rewrite_script(script)
|
||||
else:
|
||||
logger.warning("No script extracted, skipping rewrite")
|
||||
|
||||
return success_response({
|
||||
"original_script": script,
|
||||
"rewritten_script": rewritten
|
||||
})
|
||||
|
||||
except HTTPException as he:
|
||||
raise he
|
||||
result = await service.extract_script(file=file, url=url, rewrite=rewrite)
|
||||
return success_response(result)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Tool extract failed: {e}")
|
||||
logger.error(traceback.format_exc())
|
||||
|
||||
# Friendly error message
|
||||
msg = str(e)
|
||||
if "Fresh cookies" in msg:
|
||||
msg = "下载失败：目标平台开启了反爬验证，请过段时间重试或直接上传视频文件。"
|
||||
|
||||
raise HTTPException(500, f"提取失败: {msg}")
|
||||
finally:
|
||||
# 清理临时文件
|
||||
if temp_path and temp_path.exists():
|
||||
try:
|
||||
os.remove(temp_path)
|
||||
logger.info(f"Cleaned up temp file: {temp_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup temp file {temp_path}: {e}")
|
||||
|
||||
|
||||
async def download_douyin_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
|
||||
"""
|
||||
手动下载抖音视频 (Fallback logic - Ported from SuperIPAgent/douyinDownloader)
|
||||
使用特定的 User Profile URL 和硬编码 Cookie 绕过反爬
|
||||
"""
|
||||
import httpx
|
||||
|
||||
logger.info(f"[SuperIPAgent] Starting download for: {url}")
|
||||
|
||||
try:
|
||||
# 1. 提取 Modal ID (支持短链跳转)
|
||||
headers = {
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
|
||||
}
|
||||
|
||||
# 如果是短链或重定向 - 使用异步 httpx
|
||||
async with httpx.AsyncClient(follow_redirects=True, timeout=10.0) as client:
|
||||
resp = await client.get(url, headers=headers)
|
||||
final_url = str(resp.url)
|
||||
|
||||
logger.info(f"[SuperIPAgent] Final URL: {final_url}")
|
||||
|
||||
modal_id = None
|
||||
match = re.search(r'/video/(\d+)', final_url)
|
||||
if match:
|
||||
modal_id = match.group(1)
|
||||
|
||||
if not modal_id:
|
||||
logger.error("[SuperIPAgent] Could not extract modal_id")
|
||||
return None
|
||||
|
||||
logger.info(f"[SuperIPAgent] Extracted modal_id: {modal_id}")
|
||||
|
||||
# 2. 构造特定请求 URL (Copy from SuperIPAgent)
|
||||
# 使用特定用户的 Profile 页 + modal_id 参数，配合特定 Cookie
|
||||
target_url = f"https://www.douyin.com/user/MS4wLjABAAAAN_s_hups7LD0N4qnrM3o2gI0vuG3pozNaEolz2_py3cHTTrpVr1Z4dukFD9SOlwY?from_tab_name=main&modal_id={modal_id}"
|
||||
|
||||
# 3. 使用配置的 Cookie (从环境变量 DOUYIN_COOKIE 读取)
|
||||
from app.core.config import settings
|
||||
if not settings.DOUYIN_COOKIE:
|
||||
logger.warning("[SuperIPAgent] DOUYIN_COOKIE 未配置，视频下载可能失败")
|
||||
|
||||
headers_with_cookie = {
|
||||
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
||||
"cookie": settings.DOUYIN_COOKIE,
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
||||
}
|
||||
|
||||
logger.info(f"[SuperIPAgent] Requesting page with Cookie...")
|
||||
|
||||
async with httpx.AsyncClient(timeout=10.0) as client:
|
||||
response = await client.get(target_url, headers=headers_with_cookie)
|
||||
|
||||
# 4. 解析 RENDER_DATA
|
||||
content_match = re.findall(r'<script id="RENDER_DATA" type="application/json">(.*?)</script>', response.text)
|
||||
if not content_match:
|
||||
# 尝试解码后再查找？或者结构变了
|
||||
# 再尝试找 SSR_HYDRATED_DATA
|
||||
if "SSR_HYDRATED_DATA" in response.text:
|
||||
content_match = re.findall(r'<script id="SSR_HYDRATED_DATA" type="application/json">(.*?)</script>', response.text)
|
||||
|
||||
if not content_match:
|
||||
logger.error(f"[SuperIPAgent] Could not find RENDER_DATA in page (len={len(response.text)})")
|
||||
return None
|
||||
|
||||
content = unquote(content_match[0])
|
||||
try:
|
||||
data = json.loads(content)
|
||||
except:
|
||||
logger.error("[SuperIPAgent] JSON decode failed")
|
||||
return None
|
||||
|
||||
# 5. 提取视频流
|
||||
video_url = None
|
||||
try:
|
||||
# 路径通常是: app -> videoDetail -> video -> bitRateList -> playAddr -> src
|
||||
if "app" in data and "videoDetail" in data["app"]:
|
||||
info = data["app"]["videoDetail"]["video"]
|
||||
if "bitRateList" in info and info["bitRateList"]:
|
||||
video_url = info["bitRateList"][0]["playAddr"][0]["src"]
|
||||
elif "playAddr" in info and info["playAddr"]:
|
||||
video_url = info["playAddr"][0]["src"]
|
||||
except Exception as e:
|
||||
logger.error(f"[SuperIPAgent] Path extraction failed: {e}")
|
||||
|
||||
if not video_url:
|
||||
logger.error("[SuperIPAgent] No video_url found")
|
||||
return None
|
||||
|
||||
if video_url.startswith("//"):
|
||||
video_url = "https:" + video_url
|
||||
|
||||
logger.info(f"[SuperIPAgent] Found video URL: {video_url[:50]}...")
|
||||
|
||||
# 6. 下载 (带 Header) - 使用异步 httpx
|
||||
temp_path = temp_dir / f"douyin_manual_{timestamp}.mp4"
|
||||
download_headers = {
|
||||
'Referer': 'https://www.douyin.com/',
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
||||
}
|
||||
|
||||
async with httpx.AsyncClient(timeout=60.0) as client:
|
||||
async with client.stream("GET", video_url, headers=download_headers) as dl_resp:
|
||||
if dl_resp.status_code == 200:
|
||||
with open(temp_path, 'wb') as f:
|
||||
async for chunk in dl_resp.aiter_bytes(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
|
||||
logger.info(f"[SuperIPAgent] Downloaded successfully: {temp_path}")
|
||||
return temp_path
|
||||
else:
|
||||
logger.error(f"[SuperIPAgent] Download failed: {dl_resp.status_code}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[SuperIPAgent] Logic failed: {e}")
|
||||
return None
|
||||
|
||||
async def download_bilibili_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
|
||||
"""
|
||||
手动下载 Bilibili 视频 (Fallback logic - Playwright Version)
|
||||
B站通常音视频分离，这里只提取音频即可（因为只需要文案）
|
||||
"""
|
||||
from playwright.async_api import async_playwright
|
||||
|
||||
logger.info(f"[Playwright] Starting Bilibili download for: {url}")
|
||||
|
||||
playwright = None
|
||||
browser = None
|
||||
try:
|
||||
playwright = await async_playwright().start()
|
||||
# Launch browser (ensure chromium is installed: playwright install chromium)
|
||||
browser = await playwright.chromium.launch(headless=True, args=['--no-sandbox', '--disable-setuid-sandbox'])
|
||||
|
||||
# Mobile User Agent often gives single stream?
|
||||
# But Bilibili mobile web is tricky. Desktop is fine.
|
||||
context = await browser.new_context(
|
||||
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
)
|
||||
|
||||
page = await context.new_page()
|
||||
|
||||
# Intercept audio responses?
|
||||
# Bilibili streams are usually .m4s
|
||||
# But finding the initial state is easier.
|
||||
|
||||
logger.info("[Playwright] Navigating to Bilibili...")
|
||||
await page.goto(url, timeout=45000)
|
||||
|
||||
# Wait for video element (triggers loading)
|
||||
try:
|
||||
await page.wait_for_selector('video', timeout=15000)
|
||||
except:
|
||||
logger.warning("[Playwright] Video selector timeout")
|
||||
|
||||
# 1. Try extracting from __playinfo__
|
||||
# window.__playinfo__ contains dash streams
|
||||
playinfo = await page.evaluate("window.__playinfo__")
|
||||
|
||||
audio_url = None
|
||||
|
||||
if playinfo and "data" in playinfo and "dash" in playinfo["data"]:
|
||||
dash = playinfo["data"]["dash"]
|
||||
if "audio" in dash and dash["audio"]:
|
||||
audio_url = dash["audio"][0]["baseUrl"]
|
||||
logger.info(f"[Playwright] Found audio stream in __playinfo__: {audio_url[:50]}...")
|
||||
|
||||
# 2. If playinfo fails, try extracting video src (sometimes it's a blob, which we can't fetch easily without interception)
|
||||
# But interception is complex. Let's try requests with Referer if we have URL.
|
||||
|
||||
if not audio_url:
|
||||
logger.warning("[Playwright] Could not find audio in __playinfo__")
|
||||
return None
|
||||
|
||||
# Download the audio stream
|
||||
temp_path = temp_dir / f"bilibili_audio_{timestamp}.m4s" # usually m4s
|
||||
|
||||
try:
|
||||
api_request = context.request
|
||||
headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Referer": "https://www.bilibili.com/"
|
||||
}
|
||||
|
||||
logger.info(f"[Playwright] Downloading audio stream...")
|
||||
response = await api_request.get(audio_url, headers=headers)
|
||||
|
||||
if response.status == 200:
|
||||
body = await response.body()
|
||||
with open(temp_path, 'wb') as f:
|
||||
f.write(body)
|
||||
|
||||
logger.info(f"[Playwright] Downloaded successfully: {temp_path}")
|
||||
return temp_path
|
||||
else:
|
||||
logger.error(f"[Playwright] API Request failed: {response.status}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Playwright] Download logic error: {e}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Playwright] Bilibili download failed: {e}")
|
||||
return None
|
||||
finally:
|
||||
if browser:
|
||||
await browser.close()
|
||||
if playwright:
|
||||
await playwright.stop()
|
||||
|
||||
7
backend/app/modules/tools/schemas.py
Normal file
7
backend/app/modules/tools/schemas.py
Normal file
@@ -0,0 +1,7 @@
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional
|
||||
|
||||
|
||||
class ExtractScriptResponse(BaseModel):
|
||||
original_script: Optional[str] = None
|
||||
rewritten_script: Optional[str] = None
|
||||
355
backend/app/modules/tools/service.py
Normal file
355
backend/app/modules/tools/service.py
Normal file
@@ -0,0 +1,355 @@
|
||||
import asyncio
|
||||
import os
|
||||
import re
|
||||
import json
|
||||
import time
|
||||
import shutil
|
||||
import subprocess
|
||||
import traceback
|
||||
from pathlib import Path
|
||||
from typing import Optional, Any
|
||||
from urllib.parse import unquote
|
||||
|
||||
import httpx
|
||||
from loguru import logger
|
||||
|
||||
from app.services.whisper_service import whisper_service
|
||||
from app.services.glm_service import glm_service
|
||||
|
||||
|
||||
async def extract_script(file=None, url: Optional[str] = None, rewrite: bool = True) -> dict:
|
||||
"""
|
||||
文案提取：上传文件或视频链接 -> Whisper 转写 -> (可选) GLM 洗稿
|
||||
"""
|
||||
if not file and not url:
|
||||
raise ValueError("必须提供文件或视频链接")
|
||||
|
||||
temp_path = None
|
||||
try:
|
||||
timestamp = int(time.time())
|
||||
temp_dir = Path("/tmp")
|
||||
if os.name == 'nt':
|
||||
temp_dir = Path("d:/tmp")
|
||||
temp_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
loop = asyncio.get_event_loop()
|
||||
|
||||
# 1. 获取/保存文件
|
||||
if file:
|
||||
filename = file.filename
|
||||
if not filename:
|
||||
raise ValueError("文件名无效")
|
||||
safe_filename = Path(filename).name.replace(" ", "_")
|
||||
temp_path = temp_dir / f"tool_extract_{timestamp}_{safe_filename}"
|
||||
await loop.run_in_executor(None, lambda: shutil.copyfileobj(file.file, open(temp_path, "wb")))
|
||||
logger.info(f"Tool processing upload file: {temp_path}")
|
||||
else:
|
||||
temp_path = await _download_video(url, temp_dir, timestamp)
|
||||
|
||||
if not temp_path or not temp_path.exists():
|
||||
raise ValueError("文件获取失败")
|
||||
|
||||
# 1.5 安全转换: 强制转为 WAV (16k)
|
||||
audio_path = temp_dir / f"extract_audio_{timestamp}.wav"
|
||||
try:
|
||||
await loop.run_in_executor(None, lambda: _convert_to_wav(temp_path, audio_path))
|
||||
logger.info(f"Converted to WAV: {audio_path}")
|
||||
except ValueError as ve:
|
||||
if str(ve) == "HTML_DETECTED":
|
||||
raise ValueError("下载的文件是网页而非视频，请重试或手动上传。")
|
||||
else:
|
||||
raise ValueError("下载的文件已损坏或格式无法识别。")
|
||||
|
||||
# 2. 提取文案 (Whisper)
|
||||
script = await whisper_service.transcribe(str(audio_path))
|
||||
|
||||
# 3. AI 洗稿 (GLM)
|
||||
rewritten = None
|
||||
if rewrite and script and len(script.strip()) > 0:
|
||||
logger.info("Rewriting script...")
|
||||
rewritten = await glm_service.rewrite_script(script)
|
||||
|
||||
return {
|
||||
"original_script": script,
|
||||
"rewritten_script": rewritten
|
||||
}
|
||||
|
||||
finally:
|
||||
if temp_path and temp_path.exists():
|
||||
try:
|
||||
os.remove(temp_path)
|
||||
logger.info(f"Cleaned up temp file: {temp_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup temp file {temp_path}: {e}")
|
||||
|
||||
|
||||
def _convert_to_wav(input_path: Path, output_path: Path) -> None:
|
||||
"""FFmpeg 转换为 16k WAV"""
|
||||
try:
|
||||
convert_cmd = [
|
||||
'ffmpeg',
|
||||
'-i', str(input_path),
|
||||
'-vn',
|
||||
'-acodec', 'pcm_s16le',
|
||||
'-ar', '16000',
|
||||
'-ac', '1',
|
||||
'-y',
|
||||
str(output_path)
|
||||
]
|
||||
subprocess.run(convert_cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
except subprocess.CalledProcessError as e:
|
||||
error_log = e.stderr.decode('utf-8', errors='ignore') if e.stderr else str(e)
|
||||
logger.error(f"FFmpeg check/convert failed: {error_log}")
|
||||
head = b""
|
||||
try:
|
||||
with open(input_path, 'rb') as f:
|
||||
head = f.read(100)
|
||||
except:
|
||||
pass
|
||||
if b'<!DOCTYPE html' in head or b'<html' in head:
|
||||
raise ValueError("HTML_DETECTED")
|
||||
raise ValueError("CONVERT_FAILED")
|
||||
|
||||
|
||||
async def _download_video(url: str, temp_dir: Path, timestamp: int) -> Path:
|
||||
"""下载视频（yt-dlp 优先，失败回退手动解析）"""
|
||||
url_value = url
|
||||
url_match = re.search(r'https?://[^\s]+', url_value)
|
||||
if url_match:
|
||||
extracted_url = url_match.group(0)
|
||||
logger.info(f"Extracted URL from text: {extracted_url}")
|
||||
url_value = extracted_url
|
||||
|
||||
logger.info(f"Tool downloading URL: {url_value}")
|
||||
loop = asyncio.get_event_loop()
|
||||
|
||||
# 先尝试 yt-dlp
|
||||
try:
|
||||
temp_path = await loop.run_in_executor(None, lambda: _download_yt_dlp(url_value, temp_dir, timestamp))
|
||||
logger.info(f"yt-dlp downloaded to: {temp_path}")
|
||||
return temp_path
|
||||
except Exception as e:
|
||||
logger.warning(f"yt-dlp download failed: {e}. Trying manual fallback...")
|
||||
|
||||
if "douyin" in url_value:
|
||||
manual_path = await _download_douyin_manual(url_value, temp_dir, timestamp)
|
||||
if manual_path:
|
||||
return manual_path
|
||||
raise ValueError(f"视频下载失败。yt-dlp 报错: {str(e)}")
|
||||
elif "bilibili" in url_value:
|
||||
manual_path = await _download_bilibili_manual(url_value, temp_dir, timestamp)
|
||||
if manual_path:
|
||||
return manual_path
|
||||
raise ValueError(f"视频下载失败。yt-dlp 报错: {str(e)}")
|
||||
else:
|
||||
raise ValueError(f"视频下载失败: {str(e)}")
|
||||
|
||||
|
||||
def _download_yt_dlp(url_value: str, temp_dir: Path, timestamp: int) -> Path:
|
||||
"""yt-dlp 下载（阻塞调用，应在线程池中运行）"""
|
||||
import yt_dlp
|
||||
logger.info("Attempting download with yt-dlp...")
|
||||
|
||||
ydl_opts = {
|
||||
'format': 'bestaudio/best',
|
||||
'outtmpl': str(temp_dir / f"tool_download_{timestamp}_%(id)s.%(ext)s"),
|
||||
'quiet': True,
|
||||
'no_warnings': True,
|
||||
'http_headers': {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': 'https://www.douyin.com/',
|
||||
}
|
||||
}
|
||||
|
||||
with yt_dlp.YoutubeDL() as ydl_raw:
|
||||
ydl: Any = ydl_raw
|
||||
ydl.params.update(ydl_opts)
|
||||
info = ydl.extract_info(url_value, download=True)
|
||||
if 'requested_downloads' in info:
|
||||
downloaded_file = info['requested_downloads'][0]['filepath']
|
||||
else:
|
||||
ext = info.get('ext', 'mp4')
|
||||
id = info.get('id')
|
||||
downloaded_file = str(temp_dir / f"tool_download_{timestamp}_{id}.{ext}")
|
||||
|
||||
return Path(downloaded_file)
|
||||
|
||||
|
||||
async def _download_douyin_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
|
||||
"""手动下载抖音视频 (Fallback)"""
|
||||
logger.info(f"[SuperIPAgent] Starting download for: {url}")
|
||||
|
||||
try:
|
||||
headers = {
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
|
||||
}
|
||||
|
||||
async with httpx.AsyncClient(follow_redirects=True, timeout=10.0) as client:
|
||||
resp = await client.get(url, headers=headers)
|
||||
final_url = str(resp.url)
|
||||
|
||||
logger.info(f"[SuperIPAgent] Final URL: {final_url}")
|
||||
|
||||
modal_id = None
|
||||
match = re.search(r'/video/(\d+)', final_url)
|
||||
if match:
|
||||
modal_id = match.group(1)
|
||||
|
||||
if not modal_id:
|
||||
logger.error("[SuperIPAgent] Could not extract modal_id")
|
||||
return None
|
||||
|
||||
logger.info(f"[SuperIPAgent] Extracted modal_id: {modal_id}")
|
||||
|
||||
target_url = f"https://www.douyin.com/user/MS4wLjABAAAAN_s_hups7LD0N4qnrM3o2gI0vuG3pozNaEolz2_py3cHTTrpVr1Z4dukFD9SOlwY?from_tab_name=main&modal_id={modal_id}"
|
||||
|
||||
from app.core.config import settings
|
||||
if not settings.DOUYIN_COOKIE:
|
||||
logger.warning("[SuperIPAgent] DOUYIN_COOKIE 未配置，视频下载可能失败")
|
||||
|
||||
headers_with_cookie = {
|
||||
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
|
||||
"cookie": settings.DOUYIN_COOKIE,
|
||||
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36",
|
||||
}
|
||||
|
||||
logger.info(f"[SuperIPAgent] Requesting page with Cookie...")
|
||||
|
||||
async with httpx.AsyncClient(timeout=10.0) as client:
|
||||
response = await client.get(target_url, headers=headers_with_cookie)
|
||||
|
||||
content_match = re.findall(r'<script id="RENDER_DATA" type="application/json">(.*?)</script>', response.text)
|
||||
if not content_match:
|
||||
if "SSR_HYDRATED_DATA" in response.text:
|
||||
content_match = re.findall(r'<script id="SSR_HYDRATED_DATA" type="application/json">(.*?)</script>', response.text)
|
||||
|
||||
if not content_match:
|
||||
logger.error(f"[SuperIPAgent] Could not find RENDER_DATA in page (len={len(response.text)})")
|
||||
return None
|
||||
|
||||
content = unquote(content_match[0])
|
||||
try:
|
||||
data = json.loads(content)
|
||||
except:
|
||||
logger.error("[SuperIPAgent] JSON decode failed")
|
||||
return None
|
||||
|
||||
video_url = None
|
||||
try:
|
||||
if "app" in data and "videoDetail" in data["app"]:
|
||||
info = data["app"]["videoDetail"]["video"]
|
||||
if "bitRateList" in info and info["bitRateList"]:
|
||||
video_url = info["bitRateList"][0]["playAddr"][0]["src"]
|
||||
elif "playAddr" in info and info["playAddr"]:
|
||||
video_url = info["playAddr"][0]["src"]
|
||||
except Exception as e:
|
||||
logger.error(f"[SuperIPAgent] Path extraction failed: {e}")
|
||||
|
||||
if not video_url:
|
||||
logger.error("[SuperIPAgent] No video_url found")
|
||||
return None
|
||||
|
||||
if video_url.startswith("//"):
|
||||
video_url = "https:" + video_url
|
||||
|
||||
logger.info(f"[SuperIPAgent] Found video URL: {video_url[:50]}...")
|
||||
|
||||
temp_path = temp_dir / f"douyin_manual_{timestamp}.mp4"
|
||||
download_headers = {
|
||||
'Referer': 'https://www.douyin.com/',
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
||||
}
|
||||
|
||||
async with httpx.AsyncClient(timeout=60.0) as client:
|
||||
async with client.stream("GET", video_url, headers=download_headers) as dl_resp:
|
||||
if dl_resp.status_code == 200:
|
||||
with open(temp_path, 'wb') as f:
|
||||
async for chunk in dl_resp.aiter_bytes(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
|
||||
logger.info(f"[SuperIPAgent] Downloaded successfully: {temp_path}")
|
||||
return temp_path
|
||||
else:
|
||||
logger.error(f"[SuperIPAgent] Download failed: {dl_resp.status_code}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[SuperIPAgent] Logic failed: {e}")
|
||||
return None
|
||||
|
||||
|
||||
async def _download_bilibili_manual(url: str, temp_dir: Path, timestamp: int) -> Optional[Path]:
|
||||
"""手动下载 Bilibili 视频 (Playwright Fallback)"""
|
||||
from playwright.async_api import async_playwright
|
||||
|
||||
logger.info(f"[Playwright] Starting Bilibili download for: {url}")
|
||||
|
||||
playwright = None
|
||||
browser = None
|
||||
try:
|
||||
playwright = await async_playwright().start()
|
||||
browser = await playwright.chromium.launch(headless=True, args=['--no-sandbox', '--disable-setuid-sandbox'])
|
||||
|
||||
context = await browser.new_context(
|
||||
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
)
|
||||
|
||||
page = await context.new_page()
|
||||
|
||||
logger.info("[Playwright] Navigating to Bilibili...")
|
||||
await page.goto(url, timeout=45000)
|
||||
|
||||
try:
|
||||
await page.wait_for_selector('video', timeout=15000)
|
||||
except:
|
||||
logger.warning("[Playwright] Video selector timeout")
|
||||
|
||||
playinfo = await page.evaluate("window.__playinfo__")
|
||||
|
||||
audio_url = None
|
||||
|
||||
if playinfo and "data" in playinfo and "dash" in playinfo["data"]:
|
||||
dash = playinfo["data"]["dash"]
|
||||
if "audio" in dash and dash["audio"]:
|
||||
audio_url = dash["audio"][0]["baseUrl"]
|
||||
logger.info(f"[Playwright] Found audio stream in __playinfo__: {audio_url[:50]}...")
|
||||
|
||||
if not audio_url:
|
||||
logger.warning("[Playwright] Could not find audio in __playinfo__")
|
||||
return None
|
||||
|
||||
temp_path = temp_dir / f"bilibili_audio_{timestamp}.m4s"
|
||||
|
||||
try:
|
||||
api_request = context.request
|
||||
headers = {
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Referer": "https://www.bilibili.com/"
|
||||
}
|
||||
|
||||
logger.info(f"[Playwright] Downloading audio stream...")
|
||||
response = await api_request.get(audio_url, headers=headers)
|
||||
|
||||
if response.status == 200:
|
||||
body = await response.body()
|
||||
with open(temp_path, 'wb') as f:
|
||||
f.write(body)
|
||||
|
||||
logger.info(f"[Playwright] Downloaded successfully: {temp_path}")
|
||||
return temp_path
|
||||
else:
|
||||
logger.error(f"[Playwright] API Request failed: {response.status}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Playwright] Download logic error: {e}")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Playwright] Bilibili download failed: {e}")
|
||||
return None
|
||||
finally:
|
||||
if browser:
|
||||
await browser.close()
|
||||
if playwright:
|
||||
await playwright.stop()
|
||||
@@ -1,14 +1,16 @@
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional
|
||||
from typing import Optional, List
|
||||
|
||||
|
||||
class GenerateRequest(BaseModel):
|
||||
text: str
|
||||
voice: str = "zh-CN-YunxiNeural"
|
||||
material_path: str
|
||||
material_paths: Optional[List[str]] = None
|
||||
tts_mode: str = "edgetts"
|
||||
ref_audio_id: Optional[str] = None
|
||||
ref_text: Optional[str] = None
|
||||
language: str = "zh-CN"
|
||||
title: Optional[str] = None
|
||||
enable_subtitles: bool = True
|
||||
subtitle_style_id: Optional[str] = None
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from typing import Optional, Any
|
||||
from typing import Optional, Any, List
|
||||
from pathlib import Path
|
||||
import time
|
||||
import traceback
|
||||
@@ -24,6 +24,17 @@ from .schemas import GenerateRequest
|
||||
from .task_store import task_store
|
||||
|
||||
|
||||
def _locale_to_whisper_lang(locale: str) -> str:
|
||||
"""'en-US' → 'en', 'zh-CN' → 'zh'"""
|
||||
return locale.split("-")[0] if "-" in locale else locale
|
||||
|
||||
|
||||
def _locale_to_qwen_lang(locale: str) -> str:
|
||||
"""'zh-CN' → 'Chinese', 'en-US' → 'English', 其他 → 'Auto'"""
|
||||
mapping = {"zh": "Chinese", "en": "English"}
|
||||
return mapping.get(locale.split("-")[0], "Auto")
|
||||
|
||||
|
||||
_lipsync_service: Optional[LipSyncService] = None
|
||||
_lipsync_ready: Optional[bool] = None
|
||||
_lipsync_last_check: float = 0
|
||||
@@ -79,19 +90,107 @@ def _update_task(task_id: str, **updates: Any) -> None:
|
||||
task_store.update(task_id, updates)
|
||||
|
||||
|
||||
# ── 多素材辅助函数 ──
|
||||
|
||||
|
||||
def _split_equal(segments: List[dict], material_paths: List[str]) -> List[dict]:
|
||||
"""按素材数量均分音频时长，对齐到最近的 Whisper 字边界。
|
||||
|
||||
Args:
|
||||
segments: Whisper 产出的 segment 列表, 每个包含 words (字级时间戳)
|
||||
material_paths: 素材路径列表
|
||||
|
||||
Returns:
|
||||
[{"material_path": "...", "start": 0.0, "end": 5.2, "index": 0}, ...]
|
||||
"""
|
||||
# 展平所有 Whisper 字符
|
||||
all_chars: List[dict] = []
|
||||
for seg in segments:
|
||||
for w in seg.get("words", []):
|
||||
all_chars.append(w)
|
||||
|
||||
n = len(material_paths)
|
||||
|
||||
if not all_chars or n == 0:
|
||||
return [{"material_path": material_paths[0] if material_paths else "",
|
||||
"start": 0.0, "end": 99999.0, "index": 0}]
|
||||
|
||||
# 素材数不能超过字符数，否则边界会重复
|
||||
if n > len(all_chars):
|
||||
logger.warning(f"[MultiMat] 素材数({n}) > 字符数({len(all_chars)})，裁剪为 {len(all_chars)}")
|
||||
n = len(all_chars)
|
||||
|
||||
total_start = all_chars[0]["start"]
|
||||
total_end = all_chars[-1]["end"]
|
||||
seg_dur = (total_end - total_start) / n
|
||||
|
||||
# 计算 N-1 个分割点，对齐到最近的字边界
|
||||
boundaries = [0] # 第一段从第 0 个字开始
|
||||
for i in range(1, n):
|
||||
target_time = total_start + i * seg_dur
|
||||
# 找到 start 时间最接近 target_time 的字
|
||||
best_idx = boundaries[-1] + 1 # 至少比上一个边界后移 1
|
||||
best_diff = float("inf")
|
||||
for j in range(boundaries[-1] + 1, len(all_chars)):
|
||||
diff = abs(all_chars[j]["start"] - target_time)
|
||||
if diff < best_diff:
|
||||
best_diff = diff
|
||||
best_idx = j
|
||||
elif diff > best_diff:
|
||||
break # 时间递增，差值开始变大后可以停了
|
||||
boundaries.append(min(best_idx, len(all_chars) - 1))
|
||||
boundaries.append(len(all_chars)) # 最后一段到末尾
|
||||
|
||||
# 按边界生成分配结果
|
||||
assignments: List[dict] = []
|
||||
for i in range(n):
|
||||
s_idx = boundaries[i]
|
||||
e_idx = boundaries[i + 1]
|
||||
if s_idx >= len(all_chars) or s_idx >= e_idx:
|
||||
continue
|
||||
assignments.append({
|
||||
"material_path": material_paths[i],
|
||||
"start": all_chars[s_idx]["start"],
|
||||
"end": all_chars[e_idx - 1]["end"],
|
||||
"text": "".join(c["word"] for c in all_chars[s_idx:e_idx]),
|
||||
"index": len(assignments),
|
||||
})
|
||||
|
||||
if not assignments:
|
||||
return [{"material_path": material_paths[0], "start": 0.0, "end": 99999.0, "index": 0}]
|
||||
|
||||
logger.info(f"[MultiMat] 均分 {len(all_chars)} 字为 {len(assignments)} 段")
|
||||
for a in assignments:
|
||||
dur = a["end"] - a["start"]
|
||||
logger.info(f" 段{a['index']}: [{a['start']:.2f}-{a['end']:.2f}s] ({dur:.1f}s) {a['text'][:20]}")
|
||||
|
||||
return assignments
|
||||
|
||||
|
||||
async def process_video_generation(task_id: str, req: GenerateRequest, user_id: str):
|
||||
temp_files = []
|
||||
try:
|
||||
start_time = time.time()
|
||||
|
||||
# ── 确定素材列表 ──
|
||||
material_paths: List[str] = []
|
||||
if req.material_paths and len(req.material_paths) > 1:
|
||||
material_paths = req.material_paths
|
||||
else:
|
||||
material_paths = [req.material_path]
|
||||
|
||||
is_multi = len(material_paths) > 1
|
||||
|
||||
_update_task(task_id, status="processing", progress=5, message="正在下载素材...")
|
||||
|
||||
temp_dir = settings.UPLOAD_DIR / "temp"
|
||||
temp_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
input_material_path = temp_dir / f"{task_id}_input.mp4"
|
||||
temp_files.append(input_material_path)
|
||||
|
||||
await _download_material(req.material_path, input_material_path)
|
||||
# 单素材模式：下载主素材
|
||||
if not is_multi:
|
||||
input_material_path = temp_dir / f"{task_id}_input.mp4"
|
||||
temp_files.append(input_material_path)
|
||||
await _download_material(material_paths[0], input_material_path)
|
||||
|
||||
_update_task(task_id, message="正在生成语音...", progress=10)
|
||||
|
||||
@@ -119,7 +218,7 @@ async def process_video_generation(task_id: str, req: GenerateRequest, user_id:
|
||||
ref_audio_path=str(ref_audio_local),
|
||||
ref_text=req.ref_text,
|
||||
output_path=str(audio_path),
|
||||
language="Chinese"
|
||||
language=_locale_to_qwen_lang(req.language)
|
||||
)
|
||||
else:
|
||||
_update_task(task_id, message="正在生成语音 (EdgeTTS)...")
|
||||
@@ -128,52 +227,183 @@ async def process_video_generation(task_id: str, req: GenerateRequest, user_id:
|
||||
|
||||
tts_time = time.time() - start_time
|
||||
print(f"[Pipeline] TTS completed in {tts_time:.1f}s")
|
||||
_update_task(task_id, progress=25)
|
||||
|
||||
_update_task(task_id, message="正在合成唇形 (LatentSync)...", progress=30)
|
||||
|
||||
lipsync = _get_lipsync_service()
|
||||
lipsync_video_path = temp_dir / f"{task_id}_lipsync.mp4"
|
||||
temp_files.append(lipsync_video_path)
|
||||
|
||||
lipsync_start = time.time()
|
||||
is_ready = await _check_lipsync_ready()
|
||||
|
||||
if is_ready:
|
||||
print(f"[LipSync] Starting LatentSync inference...")
|
||||
_update_task(task_id, progress=35, message="正在运行 LatentSync 推理...")
|
||||
await lipsync.generate(str(input_material_path), str(audio_path), str(lipsync_video_path))
|
||||
else:
|
||||
print(f"[LipSync] LatentSync not ready, copying original video")
|
||||
_update_task(task_id, message="唇形同步不可用，使用原始视频...")
|
||||
import shutil
|
||||
shutil.copy(str(input_material_path), lipsync_video_path)
|
||||
|
||||
lipsync_time = time.time() - lipsync_start
|
||||
print(f"[Pipeline] LipSync completed in {lipsync_time:.1f}s")
|
||||
_update_task(task_id, progress=80)
|
||||
|
||||
video = VideoService()
|
||||
captions_path = None
|
||||
if req.enable_subtitles:
|
||||
_update_task(task_id, message="正在生成字幕 (Whisper)...", progress=82)
|
||||
|
||||
if is_multi:
|
||||
# ══════════════════════════════════════
|
||||
# 多素材流水线
|
||||
# ══════════════════════════════════════
|
||||
_update_task(task_id, progress=12, message="正在生成字幕 (Whisper)...")
|
||||
|
||||
captions_path = temp_dir / f"{task_id}_captions.json"
|
||||
temp_files.append(captions_path)
|
||||
|
||||
try:
|
||||
await whisper_service.align(
|
||||
captions_data = await whisper_service.align(
|
||||
audio_path=str(audio_path),
|
||||
text=req.text,
|
||||
output_path=str(captions_path)
|
||||
output_path=str(captions_path),
|
||||
language=_locale_to_whisper_lang(req.language),
|
||||
)
|
||||
print(f"[Pipeline] Whisper alignment completed")
|
||||
print(f"[Pipeline] Whisper alignment completed (multi-material)")
|
||||
except Exception as e:
|
||||
logger.warning(f"Whisper alignment failed, skipping subtitles: {e}")
|
||||
logger.warning(f"Whisper alignment failed: {e}")
|
||||
captions_data = None
|
||||
captions_path = None
|
||||
|
||||
_update_task(task_id, progress=15, message="正在分配素材...")
|
||||
|
||||
if captions_data and captions_data.get("segments"):
|
||||
assignments = _split_equal(captions_data["segments"], material_paths)
|
||||
else:
|
||||
# Whisper 失败 → 按时长均分（不依赖字符对齐）
|
||||
logger.warning("[MultiMat] Whisper 无数据，按时长均分")
|
||||
audio_dur = video._get_duration(str(audio_path))
|
||||
if audio_dur <= 0:
|
||||
audio_dur = 30.0 # 安全兜底
|
||||
seg_dur = audio_dur / len(material_paths)
|
||||
assignments = [
|
||||
{"material_path": material_paths[i], "start": i * seg_dur,
|
||||
"end": (i + 1) * seg_dur, "index": i}
|
||||
for i in range(len(material_paths))
|
||||
]
|
||||
|
||||
# 扩展段覆盖完整音频范围：首段从0开始，末段到音频结尾
|
||||
audio_duration = video._get_duration(str(audio_path))
|
||||
if assignments and audio_duration > 0:
|
||||
assignments[0]["start"] = 0.0
|
||||
assignments[-1]["end"] = audio_duration
|
||||
|
||||
num_segments = len(assignments)
|
||||
print(f"[Pipeline] Multi-material: {num_segments} segments, {len(material_paths)} materials")
|
||||
|
||||
if num_segments == 0:
|
||||
raise RuntimeError("Multi-material: no valid segments after splitting")
|
||||
|
||||
lipsync_start = time.time()
|
||||
|
||||
# ── 第一步：下载所有素材并检测分辨率 ──
|
||||
material_locals: List[Path] = []
|
||||
resolutions = []
|
||||
|
||||
for i, assignment in enumerate(assignments):
|
||||
material_local = temp_dir / f"{task_id}_material_{i}.mp4"
|
||||
temp_files.append(material_local)
|
||||
await _download_material(assignment["material_path"], material_local)
|
||||
material_locals.append(material_local)
|
||||
resolutions.append(video.get_resolution(str(material_local)))
|
||||
|
||||
# 分辨率不一致时，统一到第一个素材的分辨率
|
||||
base_res = resolutions[0] if resolutions else (0, 0)
|
||||
need_scale = any(r != base_res for r in resolutions) and base_res[0] > 0
|
||||
if need_scale:
|
||||
logger.info(f"[MultiMat] 素材分辨率不一致，统一到 {base_res[0]}x{base_res[1]}")
|
||||
|
||||
# ── 第二步：裁剪每段素材到对应时长 ──
|
||||
prepared_segments: List[Path] = []
|
||||
|
||||
for i, assignment in enumerate(assignments):
|
||||
seg_progress = 15 + int((i / num_segments) * 30) # 15% → 45%
|
||||
seg_dur = assignment["end"] - assignment["start"]
|
||||
_update_task(
|
||||
task_id,
|
||||
progress=seg_progress,
|
||||
message=f"正在准备素材 {i+1}/{num_segments}..."
|
||||
)
|
||||
|
||||
prepared_path = temp_dir / f"{task_id}_prepared_{i}.mp4"
|
||||
temp_files.append(prepared_path)
|
||||
video.prepare_segment(
|
||||
str(material_locals[i]), seg_dur, str(prepared_path),
|
||||
target_resolution=base_res if need_scale else None
|
||||
)
|
||||
prepared_segments.append(prepared_path)
|
||||
|
||||
# ── 第二步：拼接所有素材片段 ──
|
||||
_update_task(task_id, progress=50, message="正在拼接素材片段...")
|
||||
concat_path = temp_dir / f"{task_id}_concat.mp4"
|
||||
temp_files.append(concat_path)
|
||||
video.concat_videos(
|
||||
[str(p) for p in prepared_segments],
|
||||
str(concat_path)
|
||||
)
|
||||
|
||||
# ── 第三步：一次 LatentSync 推理 ──
|
||||
is_ready = await _check_lipsync_ready()
|
||||
|
||||
if is_ready:
|
||||
_update_task(task_id, progress=55, message="正在合成唇形 (LatentSync)...")
|
||||
print(f"[LipSync] Multi-material: single LatentSync on concatenated video")
|
||||
try:
|
||||
await lipsync.generate(str(concat_path), str(audio_path), str(lipsync_video_path))
|
||||
except Exception as e:
|
||||
logger.warning(f"[LipSync] Failed, fallback to concat without lipsync: {e}")
|
||||
import shutil
|
||||
shutil.copy(str(concat_path), str(lipsync_video_path))
|
||||
else:
|
||||
print(f"[LipSync] Not ready, using concatenated video without lipsync")
|
||||
import shutil
|
||||
shutil.copy(str(concat_path), str(lipsync_video_path))
|
||||
|
||||
lipsync_time = time.time() - lipsync_start
|
||||
print(f"[Pipeline] Multi-material prepare + concat + LipSync completed in {lipsync_time:.1f}s")
|
||||
_update_task(task_id, progress=80)
|
||||
|
||||
# 如果用户关闭了字幕，清除 captions_path（Whisper 仅用于句子切分）
|
||||
if not req.enable_subtitles:
|
||||
captions_path = None
|
||||
|
||||
else:
|
||||
# ══════════════════════════════════════
|
||||
# 单素材流水线（原有逻辑）
|
||||
# ══════════════════════════════════════
|
||||
_update_task(task_id, progress=25)
|
||||
_update_task(task_id, message="正在合成唇形 (LatentSync)...", progress=30)
|
||||
|
||||
lipsync_start = time.time()
|
||||
is_ready = await _check_lipsync_ready()
|
||||
|
||||
if is_ready:
|
||||
print(f"[LipSync] Starting LatentSync inference...")
|
||||
_update_task(task_id, progress=35, message="正在运行 LatentSync 推理...")
|
||||
await lipsync.generate(str(input_material_path), str(audio_path), str(lipsync_video_path))
|
||||
else:
|
||||
print(f"[LipSync] LatentSync not ready, copying original video")
|
||||
_update_task(task_id, message="唇形同步不可用，使用原始视频...")
|
||||
import shutil
|
||||
shutil.copy(str(input_material_path), lipsync_video_path)
|
||||
|
||||
lipsync_time = time.time() - lipsync_start
|
||||
print(f"[Pipeline] LipSync completed in {lipsync_time:.1f}s")
|
||||
_update_task(task_id, progress=80)
|
||||
|
||||
# 单素材模式：Whisper 在 LatentSync 之后
|
||||
if req.enable_subtitles:
|
||||
_update_task(task_id, message="正在生成字幕 (Whisper)...", progress=82)
|
||||
|
||||
captions_path = temp_dir / f"{task_id}_captions.json"
|
||||
temp_files.append(captions_path)
|
||||
|
||||
try:
|
||||
await whisper_service.align(
|
||||
audio_path=str(audio_path),
|
||||
text=req.text,
|
||||
output_path=str(captions_path),
|
||||
language=_locale_to_whisper_lang(req.language),
|
||||
)
|
||||
print(f"[Pipeline] Whisper alignment completed")
|
||||
except Exception as e:
|
||||
logger.warning(f"Whisper alignment failed, skipping subtitles: {e}")
|
||||
captions_path = None
|
||||
|
||||
_update_task(task_id, progress=85)
|
||||
|
||||
video = VideoService()
|
||||
final_audio_path = audio_path
|
||||
if req.bgm_id:
|
||||
_update_task(task_id, message="正在合成背景音乐...", progress=86)
|
||||
|
||||
@@ -43,6 +43,7 @@ class GLMService:
|
||||
要求：
|
||||
1. 标题要简洁有力，能吸引观众点击，不超过10个字
|
||||
2. 标签要与内容相关，便于搜索和推荐，只要3个
|
||||
3. 标题和标签必须使用与口播文案相同的语言（如文案是英文就用英文，日文就用日文）
|
||||
|
||||
请严格按以下JSON格式返回（不要包含其他内容）：
|
||||
{{"title": "标题", "tags": ["标签1", "标签2", "标签3"]}}"""
|
||||
@@ -120,6 +121,49 @@ class GLMService:
|
||||
|
||||
|
||||
|
||||
async def translate_text(self, text: str, target_lang: str) -> str:
|
||||
"""
|
||||
将文案翻译为指定语言
|
||||
|
||||
Args:
|
||||
text: 原始文案
|
||||
target_lang: 目标语言（如 English, 日本語 等）
|
||||
|
||||
Returns:
|
||||
翻译后的文案
|
||||
"""
|
||||
prompt = f"""请将以下文案翻译为{target_lang}。
|
||||
|
||||
原文：
|
||||
{text}
|
||||
|
||||
要求：
|
||||
1. 只返回翻译后的文案，不要添加任何解释或说明
|
||||
2. 保持原文的语气和风格
|
||||
3. 翻译要自然流畅，符合目标语言的表达习惯"""
|
||||
|
||||
try:
|
||||
client = self._get_client()
|
||||
logger.info(f"Using GLM to translate text to {target_lang}")
|
||||
|
||||
import asyncio
|
||||
response = await asyncio.to_thread(
|
||||
client.chat.completions.create,
|
||||
model=settings.GLM_MODEL,
|
||||
messages=[{"role": "user", "content": prompt}],
|
||||
thinking={"type": "disabled"},
|
||||
max_tokens=2000,
|
||||
temperature=0.3
|
||||
)
|
||||
|
||||
content = response.choices[0].message.content
|
||||
logger.info("GLM translation completed")
|
||||
return content.strip()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"GLM translate error: {e}")
|
||||
raise Exception(f"AI 翻译失败: {str(e)}")
|
||||
|
||||
def _parse_json_response(self, content: str) -> dict:
|
||||
"""解析 GLM 返回的 JSON 内容"""
|
||||
# 尝试直接解析
|
||||
|
||||
@@ -138,3 +138,109 @@ class VideoService:
|
||||
return output_path
|
||||
else:
|
||||
raise RuntimeError("FFmpeg composition failed")
|
||||
|
||||
def concat_videos(self, video_paths: list, output_path: str) -> str:
|
||||
"""使用 FFmpeg concat demuxer 拼接多个视频片段"""
|
||||
if not video_paths:
|
||||
raise ValueError("No video segments to concat")
|
||||
|
||||
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# 生成 concat list 文件
|
||||
list_path = Path(output_path).parent / f"{Path(output_path).stem}_concat.txt"
|
||||
with open(list_path, "w", encoding="utf-8") as f:
|
||||
for vp in video_paths:
|
||||
f.write(f"file '{vp}'\n")
|
||||
|
||||
cmd = [
|
||||
"ffmpeg", "-y",
|
||||
"-f", "concat",
|
||||
"-safe", "0",
|
||||
"-i", str(list_path),
|
||||
"-c", "copy",
|
||||
output_path,
|
||||
]
|
||||
|
||||
try:
|
||||
if self._run_ffmpeg(cmd):
|
||||
return output_path
|
||||
else:
|
||||
raise RuntimeError("FFmpeg concat failed")
|
||||
finally:
|
||||
try:
|
||||
list_path.unlink(missing_ok=True)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def split_audio(self, audio_path: str, start: float, end: float, output_path: str) -> str:
|
||||
"""用 FFmpeg 按时间范围切分音频"""
|
||||
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
duration = end - start
|
||||
if duration <= 0:
|
||||
raise ValueError(f"Invalid audio split range: start={start}, end={end}, duration={duration}")
|
||||
|
||||
cmd = [
|
||||
"ffmpeg", "-y",
|
||||
"-ss", str(start),
|
||||
"-t", str(duration),
|
||||
"-i", audio_path,
|
||||
"-c", "copy",
|
||||
output_path,
|
||||
]
|
||||
|
||||
if self._run_ffmpeg(cmd):
|
||||
return output_path
|
||||
raise RuntimeError(f"FFmpeg audio split failed: {start}-{end}")
|
||||
|
||||
def get_resolution(self, file_path: str) -> tuple:
|
||||
"""获取视频分辨率，返回 (width, height)"""
|
||||
cmd = [
|
||||
'ffprobe', '-v', 'error',
|
||||
'-select_streams', 'v:0',
|
||||
'-show_entries', 'stream=width,height',
|
||||
'-of', 'csv=p=0',
|
||||
file_path
|
||||
]
|
||||
try:
|
||||
result = subprocess.run(cmd, capture_output=True, text=True, timeout=10)
|
||||
parts = result.stdout.strip().split(',')
|
||||
return (int(parts[0]), int(parts[1]))
|
||||
except Exception:
|
||||
return (0, 0)
|
||||
|
||||
def prepare_segment(self, video_path: str, target_duration: float, output_path: str,
|
||||
target_resolution: tuple = None) -> str:
|
||||
"""将素材视频裁剪或循环到指定时长（无音频）。
|
||||
target_resolution: (width, height) 如需统一分辨率则传入，否则保持原分辨率。
|
||||
"""
|
||||
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
video_dur = self._get_duration(video_path)
|
||||
if video_dur <= 0:
|
||||
video_dur = target_duration
|
||||
|
||||
needs_loop = target_duration > video_dur
|
||||
needs_scale = target_resolution is not None
|
||||
|
||||
cmd = ["ffmpeg", "-y"]
|
||||
if needs_loop:
|
||||
loop_count = int(target_duration / video_dur) + 1
|
||||
cmd.extend(["-stream_loop", str(loop_count)])
|
||||
cmd.extend(["-i", video_path, "-t", str(target_duration), "-an"])
|
||||
|
||||
if needs_scale:
|
||||
w, h = target_resolution
|
||||
cmd.extend(["-vf", f"scale={w}:{h}:force_original_aspect_ratio=decrease,pad={w}:{h}:(ow-iw)/2:(oh-ih)/2"])
|
||||
|
||||
# 需要循环或缩放时必须重编码，否则用 stream copy 保持原画质
|
||||
if needs_loop or needs_scale:
|
||||
cmd.extend(["-c:v", "libx264", "-preset", "fast", "-crf", "18"])
|
||||
else:
|
||||
cmd.extend(["-c:v", "copy"])
|
||||
|
||||
cmd.append(output_path)
|
||||
|
||||
if self._run_ffmpeg(cmd):
|
||||
return output_path
|
||||
raise RuntimeError(f"FFmpeg prepare_segment failed: {video_path}")
|
||||
|
||||
@@ -48,7 +48,7 @@ class VoiceCloneService:
|
||||
"""
|
||||
# 使用锁确保串行执行，避免 GPU 显存溢出
|
||||
async with self._lock:
|
||||
logger.info(f"🎤 Voice Clone: {text[:30]}...")
|
||||
logger.info(f"🎤 Voice Clone: {text[:30]}... (language={language})")
|
||||
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# 读取参考音频
|
||||
|
||||
@@ -20,16 +20,23 @@ MAX_CHARS_PER_LINE = 12
|
||||
|
||||
def split_word_to_chars(word: str, start: float, end: float) -> list:
|
||||
"""
|
||||
将词拆分成单个字符，时间戳线性插值
|
||||
将词拆分成单个字符，时间戳线性插值。
|
||||
保留英文词前的空格（Whisper 输出如 " Hello"），用于正确重建英文字幕。
|
||||
|
||||
Args:
|
||||
word: 词文本
|
||||
word: 词文本（可能含前导空格）
|
||||
start: 词开始时间
|
||||
end: 词结束时间
|
||||
|
||||
Returns:
|
||||
单字符列表，每个包含 word/start/end
|
||||
"""
|
||||
# 保留前导空格（英文 Whisper 输出常见 " Hello" 形式）
|
||||
leading_space = ""
|
||||
if word and not word[0].strip():
|
||||
leading_space = " "
|
||||
word = word.lstrip()
|
||||
|
||||
tokens = []
|
||||
ascii_buffer = ""
|
||||
|
||||
@@ -54,7 +61,8 @@ def split_word_to_chars(word: str, start: float, end: float) -> list:
|
||||
return []
|
||||
|
||||
if len(tokens) == 1:
|
||||
return [{"word": tokens[0], "start": start, "end": end}]
|
||||
w = leading_space + tokens[0] if leading_space else tokens[0]
|
||||
return [{"word": w, "start": start, "end": end}]
|
||||
|
||||
# 线性插值时间戳
|
||||
duration = end - start
|
||||
@@ -64,8 +72,11 @@ def split_word_to_chars(word: str, start: float, end: float) -> list:
|
||||
for i, token in enumerate(tokens):
|
||||
token_start = start + i * token_duration
|
||||
token_end = start + (i + 1) * token_duration
|
||||
w = token
|
||||
if i == 0 and leading_space:
|
||||
w = leading_space + w
|
||||
result.append({
|
||||
"word": token,
|
||||
"word": w,
|
||||
"start": round(token_start, 3),
|
||||
"end": round(token_end, 3)
|
||||
})
|
||||
@@ -108,7 +119,7 @@ def split_segment_to_lines(words: List[dict], max_chars: int = MAX_CHARS_PER_LIN
|
||||
|
||||
if should_break and current_words:
|
||||
segments.append({
|
||||
"text": current_text,
|
||||
"text": current_text.strip(),
|
||||
"start": current_words[0]["start"],
|
||||
"end": current_words[-1]["end"],
|
||||
"words": current_words.copy()
|
||||
@@ -119,7 +130,7 @@ def split_segment_to_lines(words: List[dict], max_chars: int = MAX_CHARS_PER_LIN
|
||||
# 处理剩余的字
|
||||
if current_words:
|
||||
segments.append({
|
||||
"text": current_text,
|
||||
"text": current_text.strip(),
|
||||
"start": current_words[0]["start"],
|
||||
"end": current_words[-1]["end"],
|
||||
"words": current_words.copy()
|
||||
@@ -162,7 +173,8 @@ class WhisperService:
|
||||
self,
|
||||
audio_path: str,
|
||||
text: str,
|
||||
output_path: Optional[str] = None
|
||||
output_path: Optional[str] = None,
|
||||
language: str = "zh",
|
||||
) -> dict:
|
||||
"""
|
||||
对音频进行转录，生成字级别时间戳
|
||||
@@ -171,12 +183,16 @@ class WhisperService:
|
||||
audio_path: 音频文件路径
|
||||
text: 原始文本（用于参考，但实际使用 whisper 转录结果）
|
||||
output_path: 可选，输出 JSON 文件路径
|
||||
language: 语言代码 (zh/en 等)
|
||||
|
||||
Returns:
|
||||
包含字级别时间戳的字典
|
||||
"""
|
||||
import asyncio
|
||||
|
||||
# 英文等西文需要更大的每行字数
|
||||
max_chars = 40 if language != "zh" else MAX_CHARS_PER_LINE
|
||||
|
||||
def _do_transcribe():
|
||||
model = self._load_model()
|
||||
|
||||
@@ -185,7 +201,7 @@ class WhisperService:
|
||||
# 转录并获取字级别时间戳
|
||||
segments_iter, info = model.transcribe(
|
||||
audio_path,
|
||||
language="zh",
|
||||
language=language,
|
||||
word_timestamps=True, # 启用字级别时间戳
|
||||
vad_filter=True, # 启用 VAD 过滤静音
|
||||
)
|
||||
@@ -198,9 +214,10 @@ class WhisperService:
|
||||
all_words = []
|
||||
if segment.words:
|
||||
for word_info in segment.words:
|
||||
word_text = word_info.word.strip()
|
||||
if word_text:
|
||||
word_text = word_info.word
|
||||
if word_text.strip():
|
||||
# 将词拆分成单字，时间戳线性插值
|
||||
# 保留前导空格用于英文词间距
|
||||
chars = split_word_to_chars(
|
||||
word_text,
|
||||
word_info.start,
|
||||
@@ -210,7 +227,7 @@ class WhisperService:
|
||||
|
||||
# 将长段落按标点和字数拆分成多行
|
||||
if all_words:
|
||||
line_segments = split_segment_to_lines(all_words, MAX_CHARS_PER_LINE)
|
||||
line_segments = split_segment_to_lines(all_words, max_chars)
|
||||
all_segments.extend(line_segments)
|
||||
|
||||
logger.info(f"Generated {len(all_segments)} subtitle segments")
|
||||
|
||||
56
frontend/package-lock.json
generated
56
frontend/package-lock.json
generated
@@ -8,6 +8,9 @@
|
||||
"name": "frontend",
|
||||
"version": "0.1.0",
|
||||
"dependencies": {
|
||||
"@dnd-kit/core": "^6.3.1",
|
||||
"@dnd-kit/sortable": "^10.0.0",
|
||||
"@dnd-kit/utilities": "^3.2.2",
|
||||
"@supabase/supabase-js": "^2.93.1",
|
||||
"axios": "^1.13.4",
|
||||
"lucide-react": "^0.563.0",
|
||||
@@ -281,6 +284,59 @@
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@dnd-kit/accessibility": {
|
||||
"version": "3.1.1",
|
||||
"resolved": "https://registry.npmjs.org/@dnd-kit/accessibility/-/accessibility-3.1.1.tgz",
|
||||
"integrity": "sha512-2P+YgaXF+gRsIihwwY1gCsQSYnu9Zyj2py8kY5fFvUM1qm2WA2u639R6YNVfU4GWr+ZM5mqEsfHZZLoRONbemw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tslib": "^2.0.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"react": ">=16.8.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@dnd-kit/core": {
|
||||
"version": "6.3.1",
|
||||
"resolved": "https://registry.npmjs.org/@dnd-kit/core/-/core-6.3.1.tgz",
|
||||
"integrity": "sha512-xkGBRQQab4RLwgXxoqETICr6S5JlogafbhNsidmrkVv2YRs5MLwpjoF2qpiGjQt8S9AoxtIV603s0GIUpY5eYQ==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@dnd-kit/accessibility": "^3.1.1",
|
||||
"@dnd-kit/utilities": "^3.2.2",
|
||||
"tslib": "^2.0.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"react": ">=16.8.0",
|
||||
"react-dom": ">=16.8.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@dnd-kit/sortable": {
|
||||
"version": "10.0.0",
|
||||
"resolved": "https://registry.npmjs.org/@dnd-kit/sortable/-/sortable-10.0.0.tgz",
|
||||
"integrity": "sha512-+xqhmIIzvAYMGfBYYnbKuNicfSsk4RksY2XdmJhT+HAC01nix6fHCztU68jooFiMUB01Ky3F0FyOvhG/BZrWkg==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@dnd-kit/utilities": "^3.2.2",
|
||||
"tslib": "^2.0.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@dnd-kit/core": "^6.3.0",
|
||||
"react": ">=16.8.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@dnd-kit/utilities": {
|
||||
"version": "3.2.2",
|
||||
"resolved": "https://registry.npmjs.org/@dnd-kit/utilities/-/utilities-3.2.2.tgz",
|
||||
"integrity": "sha512-+MKAJEOfaBe5SmV6t34p80MMKhjvUz0vRrvVJbPT0WElzaOJ/1xs+D+KDv+tD/NE5ujfrChEcshd4fLn0wpiqg==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tslib": "^2.0.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"react": ">=16.8.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@emnapi/core": {
|
||||
"version": "1.8.1",
|
||||
"resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.8.1.tgz",
|
||||
|
||||
@@ -9,6 +9,9 @@
|
||||
"lint": "eslint"
|
||||
},
|
||||
"dependencies": {
|
||||
"@dnd-kit/core": "^6.3.1",
|
||||
"@dnd-kit/sortable": "^10.0.0",
|
||||
"@dnd-kit/utilities": "^3.2.2",
|
||||
"@supabase/supabase-js": "^2.93.1",
|
||||
"axios": "^1.13.4",
|
||||
"lucide-react": "^0.563.0",
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
import type { Metadata, Viewport } from "next";
|
||||
import { Geist, Geist_Mono } from "next/font/google";
|
||||
import "./globals.css";
|
||||
import { AuthProvider } from "@/contexts/AuthContext";
|
||||
import { TaskProvider } from "@/contexts/TaskContext";
|
||||
import { AuthProvider } from "@/shared/contexts/AuthContext";
|
||||
import { TaskProvider } from "@/shared/contexts/TaskContext";
|
||||
|
||||
import { Toaster } from "sonner";
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
"use client";
|
||||
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { useAuth } from "@/contexts/AuthContext";
|
||||
import { useAuth } from "@/shared/contexts/AuthContext";
|
||||
import api from "@/shared/api/axios";
|
||||
import { ApiResponse } from "@/shared/api/types";
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"use client";
|
||||
|
||||
import { useTask } from "@/contexts/TaskContext";
|
||||
import { useTask } from "@/shared/contexts/TaskContext";
|
||||
import Link from "next/link";
|
||||
import { usePathname } from "next/navigation";
|
||||
|
||||
|
||||
@@ -11,8 +11,8 @@ import {
|
||||
} from "@/shared/lib/media";
|
||||
import { clampTitle } from "@/shared/lib/title";
|
||||
import { useTitleInput } from "@/shared/hooks/useTitleInput";
|
||||
import { useAuth } from "@/contexts/AuthContext";
|
||||
import { useTask } from "@/contexts/TaskContext";
|
||||
import { useAuth } from "@/shared/contexts/AuthContext";
|
||||
import { useTask } from "@/shared/contexts/TaskContext";
|
||||
import { toast } from "sonner";
|
||||
import { usePublishPrefetch } from "@/shared/hooks/usePublishPrefetch";
|
||||
import { PublishAccount } from "@/shared/types/publish";
|
||||
@@ -25,13 +25,64 @@ import { useRefAudios } from "@/features/home/model/useRefAudios";
|
||||
import { useTitleSubtitleStyles } from "@/features/home/model/useTitleSubtitleStyles";
|
||||
import { ApiResponse, unwrap } from "@/shared/api/types";
|
||||
|
||||
const VOICES = [
|
||||
{ id: "zh-CN-YunxiNeural", name: "云溪 (男声-年轻)" },
|
||||
{ id: "zh-CN-YunjianNeural", name: "云健 (男声-新闻)" },
|
||||
{ id: "zh-CN-YunyangNeural", name: "云扬 (男声-专业)" },
|
||||
{ id: "zh-CN-XiaoxiaoNeural", name: "晓晓 (女声-活泼)" },
|
||||
{ id: "zh-CN-XiaoyiNeural", name: "晓伊 (女声-温柔)" },
|
||||
];
|
||||
const VOICES: Record<string, { id: string; name: string }[]> = {
|
||||
"zh-CN": [
|
||||
{ id: "zh-CN-YunxiNeural", name: "云溪 (男声-年轻)" },
|
||||
{ id: "zh-CN-YunjianNeural", name: "云健 (男声-新闻)" },
|
||||
{ id: "zh-CN-YunyangNeural", name: "云扬 (男声-专业)" },
|
||||
{ id: "zh-CN-XiaoxiaoNeural", name: "晓晓 (女声-活泼)" },
|
||||
{ id: "zh-CN-XiaoyiNeural", name: "晓伊 (女声-温柔)" },
|
||||
],
|
||||
"en-US": [
|
||||
{ id: "en-US-GuyNeural", name: "Guy (Male)" },
|
||||
{ id: "en-US-JennyNeural", name: "Jenny (Female)" },
|
||||
],
|
||||
"ja-JP": [
|
||||
{ id: "ja-JP-KeitaNeural", name: "圭太 (男声)" },
|
||||
{ id: "ja-JP-NanamiNeural", name: "七海 (女声)" },
|
||||
],
|
||||
"ko-KR": [
|
||||
{ id: "ko-KR-InJoonNeural", name: "인준 (男声)" },
|
||||
{ id: "ko-KR-SunHiNeural", name: "선히 (女声)" },
|
||||
],
|
||||
"fr-FR": [
|
||||
{ id: "fr-FR-HenriNeural", name: "Henri (Male)" },
|
||||
{ id: "fr-FR-DeniseNeural", name: "Denise (Female)" },
|
||||
],
|
||||
"de-DE": [
|
||||
{ id: "de-DE-ConradNeural", name: "Conrad (Male)" },
|
||||
{ id: "de-DE-KatjaNeural", name: "Katja (Female)" },
|
||||
],
|
||||
"es-ES": [
|
||||
{ id: "es-ES-AlvaroNeural", name: "Álvaro (Male)" },
|
||||
{ id: "es-ES-ElviraNeural", name: "Elvira (Female)" },
|
||||
],
|
||||
"ru-RU": [
|
||||
{ id: "ru-RU-DmitryNeural", name: "Дмитрий (Male)" },
|
||||
{ id: "ru-RU-SvetlanaNeural", name: "Светлана (Female)" },
|
||||
],
|
||||
"it-IT": [
|
||||
{ id: "it-IT-DiegoNeural", name: "Diego (Male)" },
|
||||
{ id: "it-IT-ElsaNeural", name: "Elsa (Female)" },
|
||||
],
|
||||
"pt-BR": [
|
||||
{ id: "pt-BR-AntonioNeural", name: "Antonio (Male)" },
|
||||
{ id: "pt-BR-FranciscaNeural", name: "Francisca (Female)" },
|
||||
],
|
||||
};
|
||||
|
||||
const LANG_TO_LOCALE: Record<string, string> = {
|
||||
"中文": "zh-CN",
|
||||
"English": "en-US",
|
||||
"日本語": "ja-JP",
|
||||
"한국어": "ko-KR",
|
||||
"Français": "fr-FR",
|
||||
"Deutsch": "de-DE",
|
||||
"Español": "es-ES",
|
||||
"Русский": "ru-RU",
|
||||
"Italiano": "it-IT",
|
||||
"Português": "pt-BR",
|
||||
};
|
||||
|
||||
|
||||
|
||||
@@ -70,22 +121,17 @@ interface RefAudio {
|
||||
created_at: number;
|
||||
}
|
||||
|
||||
interface Material {
|
||||
id: string;
|
||||
name: string;
|
||||
path: string;
|
||||
size_mb: number;
|
||||
scene?: string;
|
||||
}
|
||||
import type { Material } from "@/shared/types/material";
|
||||
|
||||
export const useHomeController = () => {
|
||||
const apiBase = getApiBaseUrl();
|
||||
|
||||
const [selectedMaterial, setSelectedMaterial] = useState<string>("");
|
||||
const [selectedMaterials, setSelectedMaterials] = useState<string[]>([]);
|
||||
const [previewMaterial, setPreviewMaterial] = useState<string | null>(null);
|
||||
|
||||
const [text, setText] = useState<string>("");
|
||||
const [voice, setVoice] = useState<string>("zh-CN-YunxiNeural");
|
||||
const [textLang, setTextLang] = useState<string>("zh-CN");
|
||||
|
||||
// 使用全局任务状态
|
||||
const { currentTask, isGenerating, startTask } = useTask();
|
||||
@@ -96,7 +142,6 @@ export const useHomeController = () => {
|
||||
|
||||
// 字幕和标题相关状态
|
||||
const [videoTitle, setVideoTitle] = useState<string>("");
|
||||
const [enableSubtitles, setEnableSubtitles] = useState<boolean>(true);
|
||||
const [selectedSubtitleStyleId, setSelectedSubtitleStyleId] = useState<string>("");
|
||||
const [selectedTitleStyleId, setSelectedTitleStyleId] = useState<string>("");
|
||||
const [subtitleFontSize, setSubtitleFontSize] = useState<number>(80);
|
||||
@@ -181,8 +226,8 @@ export const useHomeController = () => {
|
||||
{ new_name: editMaterialName.trim() }
|
||||
);
|
||||
const payload = unwrap(res);
|
||||
if (selectedMaterial === materialId && payload?.id) {
|
||||
setSelectedMaterial(payload.id);
|
||||
if (selectedMaterials.includes(materialId) && payload?.id) {
|
||||
setSelectedMaterials((prev) => prev.map((x) => (x === materialId ? payload.id : x)));
|
||||
}
|
||||
setEditingMaterialId(null);
|
||||
setEditMaterialName("");
|
||||
@@ -197,6 +242,10 @@ export const useHomeController = () => {
|
||||
// AI 生成标题标签
|
||||
const [isGeneratingMeta, setIsGeneratingMeta] = useState(false);
|
||||
|
||||
// AI 多语言翻译
|
||||
const [isTranslating, setIsTranslating] = useState(false);
|
||||
const [originalText, setOriginalText] = useState<string | null>(null);
|
||||
|
||||
// 在线录音相关
|
||||
const [isRecording, setIsRecording] = useState(false);
|
||||
const [recordedBlob, setRecordedBlob] = useState<Blob | null>(null);
|
||||
@@ -226,11 +275,13 @@ export const useHomeController = () => {
|
||||
uploadError,
|
||||
setUploadError,
|
||||
fetchMaterials,
|
||||
toggleMaterial,
|
||||
reorderMaterials,
|
||||
deleteMaterial,
|
||||
handleUpload,
|
||||
} = useMaterials({
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
selectedMaterials,
|
||||
setSelectedMaterials,
|
||||
});
|
||||
|
||||
const {
|
||||
@@ -338,14 +389,14 @@ export const useHomeController = () => {
|
||||
setText,
|
||||
videoTitle,
|
||||
setVideoTitle,
|
||||
enableSubtitles,
|
||||
setEnableSubtitles,
|
||||
ttsMode,
|
||||
setTtsMode,
|
||||
voice,
|
||||
setVoice,
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
textLang,
|
||||
setTextLang,
|
||||
selectedMaterials,
|
||||
setSelectedMaterials,
|
||||
selectedSubtitleStyleId,
|
||||
setSelectedSubtitleStyleId,
|
||||
selectedTitleStyleId,
|
||||
@@ -410,7 +461,8 @@ export const useHomeController = () => {
|
||||
}, [isGenerating, currentTask, fetchGeneratedVideos]);
|
||||
|
||||
useEffect(() => {
|
||||
const material = materials.find((item) => item.id === selectedMaterial);
|
||||
const firstSelected = selectedMaterials[0];
|
||||
const material = materials.find((item) => item.id === firstSelected);
|
||||
if (!material?.path) {
|
||||
setMaterialDimensions(null);
|
||||
return;
|
||||
@@ -450,7 +502,7 @@ export const useHomeController = () => {
|
||||
video.removeEventListener("loadedmetadata", handleLoaded);
|
||||
video.removeEventListener("error", handleError);
|
||||
};
|
||||
}, [materials, selectedMaterial]);
|
||||
}, [materials, selectedMaterials]);
|
||||
|
||||
|
||||
useEffect(() => {
|
||||
@@ -486,12 +538,13 @@ export const useHomeController = () => {
|
||||
}, [selectedBgmId, bgmList]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!selectedMaterial) return;
|
||||
const target = materialItemRefs.current[selectedMaterial];
|
||||
const firstSelected = selectedMaterials[0];
|
||||
if (!firstSelected) return;
|
||||
const target = materialItemRefs.current[firstSelected];
|
||||
if (target) {
|
||||
target.scrollIntoView({ block: "nearest", behavior: "smooth" });
|
||||
}
|
||||
}, [selectedMaterial, materials]);
|
||||
}, [selectedMaterials, materials]);
|
||||
|
||||
// 【修复】历史视频默认选中逻辑
|
||||
// 当持久化恢复完成，且列表加载完毕，如果没选中任何视频，默认选中第一个
|
||||
@@ -639,9 +692,58 @@ export const useHomeController = () => {
|
||||
}
|
||||
};
|
||||
|
||||
// AI 多语言翻译
|
||||
const handleTranslate = async (targetLang: string) => {
|
||||
if (!text.trim()) {
|
||||
toast.error("请先输入口播文案");
|
||||
return;
|
||||
}
|
||||
|
||||
// 首次翻译时保存原文
|
||||
if (originalText === null) {
|
||||
setOriginalText(text);
|
||||
}
|
||||
|
||||
setIsTranslating(true);
|
||||
try {
|
||||
const { data: res } = await api.post<ApiResponse<{ translated_text: string }>>(
|
||||
"/api/ai/translate",
|
||||
{ text: text.trim(), target_lang: targetLang }
|
||||
);
|
||||
const payload = unwrap(res);
|
||||
setText(payload.translated_text || "");
|
||||
|
||||
// 根据翻译目标语言更新 textLang 并自动切换声音
|
||||
const locale = LANG_TO_LOCALE[targetLang] || "zh-CN";
|
||||
setTextLang(locale);
|
||||
if (ttsMode === "edgetts") {
|
||||
const langVoices = VOICES[locale] || VOICES["zh-CN"];
|
||||
setVoice(langVoices[0].id);
|
||||
}
|
||||
} catch (err: unknown) {
|
||||
console.error("AI translate failed:", err);
|
||||
const axiosErr = err as { response?: { data?: { message?: string } }; message?: string };
|
||||
const errorMsg = axiosErr.response?.data?.message || axiosErr.message || String(err);
|
||||
toast.error(`AI 翻译失败: ${errorMsg}`);
|
||||
} finally {
|
||||
setIsTranslating(false);
|
||||
}
|
||||
};
|
||||
|
||||
const handleRestoreOriginal = () => {
|
||||
if (originalText !== null) {
|
||||
setText(originalText);
|
||||
setOriginalText(null);
|
||||
setTextLang("zh-CN");
|
||||
if (ttsMode === "edgetts") {
|
||||
setVoice(VOICES["zh-CN"][0].id);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// 生成视频
|
||||
const handleGenerate = async () => {
|
||||
if (!selectedMaterial || !text.trim()) {
|
||||
if (selectedMaterials.length === 0 || !text.trim()) {
|
||||
toast.error("请先选择素材并填写文案");
|
||||
return;
|
||||
}
|
||||
@@ -663,26 +765,33 @@ export const useHomeController = () => {
|
||||
|
||||
try {
|
||||
// 查找选中的素材对象以获取路径
|
||||
const materialObj = materials.find((m) => m.id === selectedMaterial);
|
||||
if (!materialObj) {
|
||||
const firstMaterialObj = materials.find((m) => m.id === selectedMaterials[0]);
|
||||
if (!firstMaterialObj) {
|
||||
toast.error("素材数据异常");
|
||||
return;
|
||||
}
|
||||
|
||||
// 构建请求参数
|
||||
const payload: Record<string, unknown> = {
|
||||
material_path: materialObj.path,
|
||||
material_path: firstMaterialObj.path,
|
||||
text: text,
|
||||
tts_mode: ttsMode,
|
||||
title: videoTitle.trim() || undefined,
|
||||
enable_subtitles: enableSubtitles,
|
||||
enable_subtitles: true,
|
||||
};
|
||||
|
||||
if (enableSubtitles && selectedSubtitleStyleId) {
|
||||
// 多素材
|
||||
if (selectedMaterials.length > 1) {
|
||||
payload.material_paths = selectedMaterials
|
||||
.map((id) => materials.find((x) => x.id === id)?.path)
|
||||
.filter((path): path is string => !!path);
|
||||
}
|
||||
|
||||
if (selectedSubtitleStyleId) {
|
||||
payload.subtitle_style_id = selectedSubtitleStyleId;
|
||||
}
|
||||
|
||||
if (enableSubtitles && subtitleFontSize) {
|
||||
if (subtitleFontSize) {
|
||||
payload.subtitle_font_size = Math.round(subtitleFontSize);
|
||||
}
|
||||
|
||||
@@ -698,15 +807,15 @@ export const useHomeController = () => {
|
||||
payload.title_top_margin = Math.round(titleTopMargin);
|
||||
}
|
||||
|
||||
if (enableSubtitles) {
|
||||
payload.subtitle_bottom_margin = Math.round(subtitleBottomMargin);
|
||||
}
|
||||
payload.subtitle_bottom_margin = Math.round(subtitleBottomMargin);
|
||||
|
||||
if (enableBgm && selectedBgmId) {
|
||||
payload.bgm_id = selectedBgmId;
|
||||
payload.bgm_volume = bgmVolume;
|
||||
}
|
||||
|
||||
payload.language = textLang;
|
||||
|
||||
if (ttsMode === "edgetts") {
|
||||
payload.voice = voice;
|
||||
} else {
|
||||
@@ -774,8 +883,9 @@ export const useHomeController = () => {
|
||||
fetchMaterials,
|
||||
deleteMaterial,
|
||||
handleUpload,
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
selectedMaterials,
|
||||
toggleMaterial,
|
||||
reorderMaterials,
|
||||
handlePreviewMaterial,
|
||||
editingMaterialId,
|
||||
editMaterialName,
|
||||
@@ -789,6 +899,10 @@ export const useHomeController = () => {
|
||||
setExtractModalOpen,
|
||||
handleGenerateMeta,
|
||||
isGeneratingMeta,
|
||||
handleTranslate,
|
||||
isTranslating,
|
||||
originalText,
|
||||
handleRestoreOriginal,
|
||||
showStylePreview,
|
||||
setShowStylePreview,
|
||||
videoTitle,
|
||||
@@ -809,17 +923,16 @@ export const useHomeController = () => {
|
||||
setTitleTopMargin,
|
||||
subtitleBottomMargin,
|
||||
setSubtitleBottomMargin,
|
||||
enableSubtitles,
|
||||
setEnableSubtitles,
|
||||
resolveAssetUrl,
|
||||
getFontFormat,
|
||||
buildTextShadow,
|
||||
materialDimensions,
|
||||
ttsMode,
|
||||
setTtsMode,
|
||||
voices: VOICES,
|
||||
voices: VOICES[textLang] || VOICES["zh-CN"],
|
||||
voice,
|
||||
setVoice,
|
||||
textLang,
|
||||
refAudios,
|
||||
selectedRefAudio,
|
||||
handleSelectRefAudio,
|
||||
|
||||
@@ -17,14 +17,14 @@ interface UseHomePersistenceOptions {
|
||||
setText: React.Dispatch<React.SetStateAction<string>>;
|
||||
videoTitle: string;
|
||||
setVideoTitle: React.Dispatch<React.SetStateAction<string>>;
|
||||
enableSubtitles: boolean;
|
||||
setEnableSubtitles: React.Dispatch<React.SetStateAction<boolean>>;
|
||||
ttsMode: 'edgetts' | 'voiceclone';
|
||||
setTtsMode: React.Dispatch<React.SetStateAction<'edgetts' | 'voiceclone'>>;
|
||||
voice: string;
|
||||
setVoice: React.Dispatch<React.SetStateAction<string>>;
|
||||
selectedMaterial: string;
|
||||
setSelectedMaterial: React.Dispatch<React.SetStateAction<string>>;
|
||||
textLang: string;
|
||||
setTextLang: React.Dispatch<React.SetStateAction<string>>;
|
||||
selectedMaterials: string[];
|
||||
setSelectedMaterials: React.Dispatch<React.SetStateAction<string[]>>;
|
||||
selectedSubtitleStyleId: string;
|
||||
setSelectedSubtitleStyleId: React.Dispatch<React.SetStateAction<string>>;
|
||||
selectedTitleStyleId: string;
|
||||
@@ -57,14 +57,14 @@ export const useHomePersistence = ({
|
||||
setText,
|
||||
videoTitle,
|
||||
setVideoTitle,
|
||||
enableSubtitles,
|
||||
setEnableSubtitles,
|
||||
ttsMode,
|
||||
setTtsMode,
|
||||
voice,
|
||||
setVoice,
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
textLang,
|
||||
setTextLang,
|
||||
selectedMaterials,
|
||||
setSelectedMaterials,
|
||||
selectedSubtitleStyleId,
|
||||
setSelectedSubtitleStyleId,
|
||||
selectedTitleStyleId,
|
||||
@@ -96,9 +96,9 @@ export const useHomePersistence = ({
|
||||
|
||||
const savedText = localStorage.getItem(`vigent_${storageKey}_text`);
|
||||
const savedTitle = localStorage.getItem(`vigent_${storageKey}_title`);
|
||||
const savedSubtitles = localStorage.getItem(`vigent_${storageKey}_subtitles`);
|
||||
const savedTtsMode = localStorage.getItem(`vigent_${storageKey}_ttsMode`);
|
||||
const savedVoice = localStorage.getItem(`vigent_${storageKey}_voice`);
|
||||
const savedTextLang = localStorage.getItem(`vigent_${storageKey}_textLang`);
|
||||
const savedMaterial = localStorage.getItem(`vigent_${storageKey}_material`);
|
||||
const savedSubtitleStyle = localStorage.getItem(`vigent_${storageKey}_subtitleStyle`);
|
||||
const savedTitleStyle = localStorage.getItem(`vigent_${storageKey}_titleStyle`);
|
||||
@@ -113,11 +113,23 @@ export const useHomePersistence = ({
|
||||
|
||||
setText(savedText || "大家好，欢迎来到我的频道，今天给大家分享一些有趣的内容。");
|
||||
setVideoTitle(savedTitle ? clampTitle(savedTitle) : "");
|
||||
setEnableSubtitles(savedSubtitles !== null ? savedSubtitles === 'true' : true);
|
||||
setTtsMode((savedTtsMode as 'edgetts' | 'voiceclone') || 'edgetts');
|
||||
setVoice(savedVoice || "zh-CN-YunxiNeural");
|
||||
if (savedTextLang) setTextLang(savedTextLang);
|
||||
|
||||
if (savedMaterial) setSelectedMaterial(savedMaterial);
|
||||
if (savedMaterial) {
|
||||
try {
|
||||
const parsed = JSON.parse(savedMaterial);
|
||||
if (Array.isArray(parsed)) {
|
||||
setSelectedMaterials(parsed);
|
||||
} else {
|
||||
setSelectedMaterials([savedMaterial]);
|
||||
}
|
||||
} catch {
|
||||
// 旧格式: 单字符串
|
||||
setSelectedMaterials([savedMaterial]);
|
||||
}
|
||||
}
|
||||
if (savedSubtitleStyle) setSelectedSubtitleStyleId(savedSubtitleStyle);
|
||||
if (savedTitleStyle) setSelectedTitleStyleId(savedTitleStyle);
|
||||
|
||||
@@ -157,15 +169,15 @@ export const useHomePersistence = ({
|
||||
isAuthLoading,
|
||||
setBgmVolume,
|
||||
setEnableBgm,
|
||||
setEnableSubtitles,
|
||||
setSelectedBgmId,
|
||||
setSelectedMaterial,
|
||||
setSelectedMaterials,
|
||||
setSelectedSubtitleStyleId,
|
||||
setSelectedTitleStyleId,
|
||||
setSelectedVideoId,
|
||||
setSubtitleFontSize,
|
||||
setSubtitleSizeLocked,
|
||||
setText,
|
||||
setTextLang,
|
||||
setTitleFontSize,
|
||||
setTitleSizeLocked,
|
||||
setTitleTopMargin,
|
||||
@@ -192,10 +204,6 @@ export const useHomePersistence = ({
|
||||
return () => clearTimeout(timeout);
|
||||
}, [videoTitle, storageKey, isRestored]);
|
||||
|
||||
useEffect(() => {
|
||||
if (isRestored) localStorage.setItem(`vigent_${storageKey}_subtitles`, String(enableSubtitles));
|
||||
}, [enableSubtitles, storageKey, isRestored]);
|
||||
|
||||
useEffect(() => {
|
||||
if (isRestored) localStorage.setItem(`vigent_${storageKey}_ttsMode`, ttsMode);
|
||||
}, [ttsMode, storageKey, isRestored]);
|
||||
@@ -205,10 +213,14 @@ export const useHomePersistence = ({
|
||||
}, [voice, storageKey, isRestored]);
|
||||
|
||||
useEffect(() => {
|
||||
if (isRestored && selectedMaterial) {
|
||||
localStorage.setItem(`vigent_${storageKey}_material`, selectedMaterial);
|
||||
if (isRestored) localStorage.setItem(`vigent_${storageKey}_textLang`, textLang);
|
||||
}, [textLang, storageKey, isRestored]);
|
||||
|
||||
useEffect(() => {
|
||||
if (isRestored && selectedMaterials.length > 0) {
|
||||
localStorage.setItem(`vigent_${storageKey}_material`, JSON.stringify(selectedMaterials));
|
||||
}
|
||||
}, [selectedMaterial, storageKey, isRestored]);
|
||||
}, [selectedMaterials, storageKey, isRestored]);
|
||||
|
||||
useEffect(() => {
|
||||
if (isRestored && selectedSubtitleStyleId) {
|
||||
|
||||
@@ -2,23 +2,16 @@ import { useCallback, useState } from "react";
|
||||
import api from "@/shared/api/axios";
|
||||
import { ApiResponse, unwrap } from "@/shared/api/types";
|
||||
import { toast } from "sonner";
|
||||
|
||||
interface Material {
|
||||
id: string;
|
||||
name: string;
|
||||
scene: string;
|
||||
size_mb: number;
|
||||
path: string;
|
||||
}
|
||||
import type { Material } from "@/shared/types/material";
|
||||
|
||||
interface UseMaterialsOptions {
|
||||
selectedMaterial: string;
|
||||
setSelectedMaterial: React.Dispatch<React.SetStateAction<string>>;
|
||||
selectedMaterials: string[];
|
||||
setSelectedMaterials: React.Dispatch<React.SetStateAction<string[]>>;
|
||||
}
|
||||
|
||||
export const useMaterials = ({
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
selectedMaterials,
|
||||
setSelectedMaterials,
|
||||
}: UseMaterialsOptions) => {
|
||||
const [materials, setMaterials] = useState<Material[]>([]);
|
||||
const [fetchError, setFetchError] = useState<string | null>(null);
|
||||
@@ -41,12 +34,13 @@ export const useMaterials = ({
|
||||
setMaterials(nextMaterials);
|
||||
setLastMaterialCount(nextMaterials.length);
|
||||
|
||||
setSelectedMaterial((prev) => {
|
||||
// 如果当前选中的素材在列表中依然存在，保持选中
|
||||
const exists = nextMaterials.some((item) => item.id === prev);
|
||||
if (exists) return prev;
|
||||
setSelectedMaterials((prev) => {
|
||||
// 保留已选中且仍存在的
|
||||
const existingIds = new Set(nextMaterials.map((m) => m.id));
|
||||
const kept = prev.filter((id) => existingIds.has(id));
|
||||
if (kept.length > 0) return kept;
|
||||
// 否则默认选中第一个
|
||||
return nextMaterials[0]?.id || "";
|
||||
return nextMaterials[0]?.id ? [nextMaterials[0].id] : [];
|
||||
});
|
||||
} catch (error) {
|
||||
console.error("获取素材失败:", error);
|
||||
@@ -54,29 +48,58 @@ export const useMaterials = ({
|
||||
} finally {
|
||||
setIsFetching(false);
|
||||
}
|
||||
}, [setSelectedMaterial]);
|
||||
}, [setSelectedMaterials]);
|
||||
|
||||
const MAX_MATERIALS = 4;
|
||||
|
||||
const toggleMaterial = useCallback((id: string) => {
|
||||
setSelectedMaterials((prev) => {
|
||||
if (prev.includes(id)) {
|
||||
// 不能取消最后一个
|
||||
if (prev.length <= 1) return prev;
|
||||
return prev.filter((x) => x !== id);
|
||||
}
|
||||
if (prev.length >= MAX_MATERIALS) return prev;
|
||||
return [...prev, id];
|
||||
});
|
||||
}, [setSelectedMaterials]);
|
||||
|
||||
const reorderMaterials = useCallback((activeId: string, overId: string) => {
|
||||
setSelectedMaterials((prev) => {
|
||||
const oldIndex = prev.indexOf(activeId);
|
||||
const newIndex = prev.indexOf(overId);
|
||||
if (oldIndex === -1 || newIndex === -1) return prev;
|
||||
const next = [...prev];
|
||||
next.splice(oldIndex, 1);
|
||||
next.splice(newIndex, 0, activeId);
|
||||
return next;
|
||||
});
|
||||
}, [setSelectedMaterials]);
|
||||
|
||||
const deleteMaterial = useCallback(async (materialId: string) => {
|
||||
if (!confirm("确定要删除这个素材吗？")) return;
|
||||
try {
|
||||
await api.delete(`/api/materials/${materialId}`);
|
||||
fetchMaterials();
|
||||
if (selectedMaterial === materialId) {
|
||||
setSelectedMaterial("");
|
||||
if (selectedMaterials.includes(materialId)) {
|
||||
setSelectedMaterials((prev) => {
|
||||
const next = prev.filter((id) => id !== materialId);
|
||||
return next.length > 0 ? next : [];
|
||||
});
|
||||
}
|
||||
} catch (error) {
|
||||
toast.error("删除失败: " + error);
|
||||
}
|
||||
}, [fetchMaterials, selectedMaterial, setSelectedMaterial]);
|
||||
}, [fetchMaterials, selectedMaterials, setSelectedMaterials]);
|
||||
|
||||
const handleUpload = useCallback(async (e: React.ChangeEvent<HTMLInputElement>) => {
|
||||
const file = e.target.files?.[0];
|
||||
if (!file) return;
|
||||
|
||||
const validTypes = ['.mp4', '.mov', '.avi'];
|
||||
const validTypes = ['.mp4', '.mov', '.avi', '.mkv', '.webm', '.flv', '.wmv', '.m4v', '.ts', '.mts'];
|
||||
const ext = file.name.toLowerCase().slice(file.name.lastIndexOf('.'));
|
||||
if (!validTypes.includes(ext)) {
|
||||
setUploadError('仅支持 MP4、MOV、AVI 格式');
|
||||
setUploadError('不支持的视频格式');
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -100,7 +123,22 @@ export const useMaterials = ({
|
||||
|
||||
setUploadProgress(100);
|
||||
setIsUploading(false);
|
||||
fetchMaterials();
|
||||
|
||||
// 上传后重新拉列表并自动选中新素材
|
||||
const { data: res } = await api.get<ApiResponse<{ materials: Material[] }>>(
|
||||
`/api/materials?t=${new Date().getTime()}`
|
||||
);
|
||||
const payload = unwrap(res);
|
||||
const nextMaterials = payload.materials || [];
|
||||
setMaterials(nextMaterials);
|
||||
setLastMaterialCount(nextMaterials.length);
|
||||
|
||||
// 找出新增的素材 ID 并自动选中
|
||||
const oldIds = new Set(materials.map((m) => m.id));
|
||||
const newIds = nextMaterials.filter((m) => !oldIds.has(m.id)).map((m) => m.id);
|
||||
if (newIds.length > 0) {
|
||||
setSelectedMaterials((prev) => [...prev, ...newIds]);
|
||||
}
|
||||
} catch (err: unknown) {
|
||||
console.error("Upload failed:", err);
|
||||
setIsUploading(false);
|
||||
@@ -122,6 +160,8 @@ export const useMaterials = ({
|
||||
uploadError,
|
||||
setUploadError,
|
||||
fetchMaterials,
|
||||
toggleMaterial,
|
||||
reorderMaterials,
|
||||
deleteMaterial,
|
||||
handleUpload,
|
||||
};
|
||||
|
||||
@@ -4,6 +4,7 @@ interface GenerateActionBarProps {
|
||||
isGenerating: boolean;
|
||||
progress: number;
|
||||
disabled: boolean;
|
||||
materialCount?: number;
|
||||
onGenerate: () => void;
|
||||
}
|
||||
|
||||
@@ -11,43 +12,51 @@ export function GenerateActionBar({
|
||||
isGenerating,
|
||||
progress,
|
||||
disabled,
|
||||
materialCount = 1,
|
||||
onGenerate,
|
||||
}: GenerateActionBarProps) {
|
||||
return (
|
||||
<button
|
||||
onClick={onGenerate}
|
||||
disabled={disabled}
|
||||
className={`w-full py-4 rounded-xl font-bold text-lg transition-all ${disabled
|
||||
? "bg-gray-600 cursor-not-allowed text-gray-400"
|
||||
: "bg-gradient-to-r from-purple-600 to-pink-600 hover:from-purple-700 hover:to-pink-700 text-white shadow-lg hover:shadow-purple-500/25"
|
||||
}`}
|
||||
>
|
||||
{isGenerating ? (
|
||||
<span className="flex items-center justify-center gap-3">
|
||||
<svg className="animate-spin h-5 w-5" viewBox="0 0 24 24">
|
||||
<circle
|
||||
className="opacity-25"
|
||||
cx="12"
|
||||
cy="12"
|
||||
r="10"
|
||||
stroke="currentColor"
|
||||
strokeWidth="4"
|
||||
fill="none"
|
||||
/>
|
||||
<path
|
||||
className="opacity-75"
|
||||
fill="currentColor"
|
||||
d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4z"
|
||||
/>
|
||||
</svg>
|
||||
生成中... {progress}%
|
||||
</span>
|
||||
) : (
|
||||
<span className="flex items-center justify-center gap-2">
|
||||
<Rocket className="h-5 w-5" />
|
||||
生成视频
|
||||
</span>
|
||||
<div>
|
||||
<button
|
||||
onClick={onGenerate}
|
||||
disabled={disabled}
|
||||
className={`w-full py-4 rounded-xl font-bold text-lg transition-all ${disabled
|
||||
? "bg-gray-600 cursor-not-allowed text-gray-400"
|
||||
: "bg-gradient-to-r from-purple-600 to-pink-600 hover:from-purple-700 hover:to-pink-700 text-white shadow-lg hover:shadow-purple-500/25"
|
||||
}`}
|
||||
>
|
||||
{isGenerating ? (
|
||||
<span className="flex items-center justify-center gap-3">
|
||||
<svg className="animate-spin h-5 w-5" viewBox="0 0 24 24">
|
||||
<circle
|
||||
className="opacity-25"
|
||||
cx="12"
|
||||
cy="12"
|
||||
r="10"
|
||||
stroke="currentColor"
|
||||
strokeWidth="4"
|
||||
fill="none"
|
||||
/>
|
||||
<path
|
||||
className="opacity-75"
|
||||
fill="currentColor"
|
||||
d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4z"
|
||||
/>
|
||||
</svg>
|
||||
生成中... {progress}%
|
||||
</span>
|
||||
) : (
|
||||
<span className="flex items-center justify-center gap-2">
|
||||
<Rocket className="h-5 w-5" />
|
||||
生成视频
|
||||
</span>
|
||||
)}
|
||||
</button>
|
||||
{!isGenerating && materialCount >= 2 && (
|
||||
<p className="text-xs text-gray-400 text-center mt-1.5">
|
||||
多素材模式 ({materialCount} 个机位)，生成耗时较长
|
||||
</p>
|
||||
)}
|
||||
</button>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
import { useEffect } from "react";
|
||||
import { useRouter } from "next/navigation";
|
||||
import VideoPreviewModal from "@/components/VideoPreviewModal";
|
||||
import ScriptExtractionModal from "@/components/ScriptExtractionModal";
|
||||
import ScriptExtractionModal from "./ScriptExtractionModal";
|
||||
import { useHomeController } from "@/features/home/model/useHomeController";
|
||||
import { BgmPanel } from "@/features/home/ui/BgmPanel";
|
||||
import { GenerateActionBar } from "@/features/home/ui/GenerateActionBar";
|
||||
@@ -34,8 +34,9 @@ export function HomePage() {
|
||||
fetchMaterials,
|
||||
deleteMaterial,
|
||||
handleUpload,
|
||||
selectedMaterial,
|
||||
setSelectedMaterial,
|
||||
selectedMaterials,
|
||||
toggleMaterial,
|
||||
reorderMaterials,
|
||||
handlePreviewMaterial,
|
||||
editingMaterialId,
|
||||
editMaterialName,
|
||||
@@ -49,6 +50,10 @@ export function HomePage() {
|
||||
setExtractModalOpen,
|
||||
handleGenerateMeta,
|
||||
isGeneratingMeta,
|
||||
handleTranslate,
|
||||
isTranslating,
|
||||
originalText,
|
||||
handleRestoreOriginal,
|
||||
showStylePreview,
|
||||
setShowStylePreview,
|
||||
videoTitle,
|
||||
@@ -69,8 +74,6 @@ export function HomePage() {
|
||||
setTitleTopMargin,
|
||||
subtitleBottomMargin,
|
||||
setSubtitleBottomMargin,
|
||||
enableSubtitles,
|
||||
setEnableSubtitles,
|
||||
resolveAssetUrl,
|
||||
getFontFormat,
|
||||
buildTextShadow,
|
||||
@@ -147,7 +150,7 @@ export function HomePage() {
|
||||
{/* 素材选择 */}
|
||||
<MaterialSelector
|
||||
materials={materials}
|
||||
selectedMaterial={selectedMaterial}
|
||||
selectedMaterials={selectedMaterials}
|
||||
isFetching={isFetching}
|
||||
lastMaterialCount={lastMaterialCount}
|
||||
editingMaterialId={editingMaterialId}
|
||||
@@ -159,7 +162,8 @@ export function HomePage() {
|
||||
apiBase={apiBase}
|
||||
onUploadChange={handleUpload}
|
||||
onRefresh={fetchMaterials}
|
||||
onSelectMaterial={setSelectedMaterial}
|
||||
onToggleMaterial={toggleMaterial}
|
||||
onReorderMaterials={reorderMaterials}
|
||||
onPreviewMaterial={handlePreviewMaterial}
|
||||
onStartEditing={startMaterialEditing}
|
||||
onEditNameChange={setEditMaterialName}
|
||||
@@ -177,6 +181,10 @@ export function HomePage() {
|
||||
onOpenExtractModal={() => setExtractModalOpen(true)}
|
||||
onGenerateMeta={handleGenerateMeta}
|
||||
isGeneratingMeta={isGeneratingMeta}
|
||||
onTranslate={handleTranslate}
|
||||
isTranslating={isTranslating}
|
||||
hasOriginalText={originalText !== null}
|
||||
onRestoreOriginal={handleRestoreOriginal}
|
||||
/>
|
||||
|
||||
{/* 标题和字幕设置 */}
|
||||
@@ -207,8 +215,6 @@ export function HomePage() {
|
||||
onTitleTopMarginChange={setTitleTopMargin}
|
||||
subtitleBottomMargin={subtitleBottomMargin}
|
||||
onSubtitleBottomMarginChange={setSubtitleBottomMargin}
|
||||
enableSubtitles={enableSubtitles}
|
||||
onToggleSubtitles={setEnableSubtitles}
|
||||
resolveAssetUrl={resolveAssetUrl}
|
||||
getFontFormat={getFontFormat}
|
||||
buildTextShadow={buildTextShadow}
|
||||
@@ -276,7 +282,8 @@ export function HomePage() {
|
||||
<GenerateActionBar
|
||||
isGenerating={isGenerating}
|
||||
progress={currentTask?.progress || 0}
|
||||
disabled={isGenerating || !selectedMaterial || (ttsMode === "voiceclone" && !selectedRefAudio)}
|
||||
materialCount={selectedMaterials.length}
|
||||
disabled={isGenerating || selectedMaterials.length === 0 || (ttsMode === "voiceclone" && !selectedRefAudio)}
|
||||
onGenerate={handleGenerate}
|
||||
/>
|
||||
</div>
|
||||
|
||||
@@ -1,17 +1,25 @@
|
||||
import type { ChangeEvent, MouseEvent } from "react";
|
||||
import { Upload, RefreshCw, Eye, Trash2, X, Pencil, Check } from "lucide-react";
|
||||
|
||||
interface Material {
|
||||
id: string;
|
||||
name: string;
|
||||
scene: string;
|
||||
size_mb: number;
|
||||
path: string;
|
||||
}
|
||||
import { type ChangeEvent, type MouseEvent } from "react";
|
||||
import { Upload, RefreshCw, Eye, Trash2, X, Pencil, Check, GripVertical } from "lucide-react";
|
||||
import type { Material } from "@/shared/types/material";
|
||||
import {
|
||||
DndContext,
|
||||
closestCenter,
|
||||
KeyboardSensor,
|
||||
PointerSensor,
|
||||
useSensor,
|
||||
useSensors,
|
||||
type DragEndEvent,
|
||||
} from "@dnd-kit/core";
|
||||
import {
|
||||
SortableContext,
|
||||
horizontalListSortingStrategy,
|
||||
useSortable,
|
||||
} from "@dnd-kit/sortable";
|
||||
import { CSS } from "@dnd-kit/utilities";
|
||||
|
||||
interface MaterialSelectorProps {
|
||||
materials: Material[];
|
||||
selectedMaterial: string;
|
||||
selectedMaterials: string[];
|
||||
isFetching: boolean;
|
||||
lastMaterialCount: number;
|
||||
editingMaterialId: string | null;
|
||||
@@ -23,7 +31,8 @@ interface MaterialSelectorProps {
|
||||
apiBase: string;
|
||||
onUploadChange: (event: ChangeEvent<HTMLInputElement>) => void;
|
||||
onRefresh: () => void;
|
||||
onSelectMaterial: (id: string) => void;
|
||||
onToggleMaterial: (id: string) => void;
|
||||
onReorderMaterials: (activeId: string, overId: string) => void;
|
||||
onPreviewMaterial: (path: string) => void;
|
||||
onStartEditing: (material: Material, event: MouseEvent) => void;
|
||||
onEditNameChange: (value: string) => void;
|
||||
@@ -34,9 +43,64 @@ interface MaterialSelectorProps {
|
||||
registerMaterialRef: (id: string, element: HTMLDivElement | null) => void;
|
||||
}
|
||||
|
||||
function SortableChip({
|
||||
id,
|
||||
index,
|
||||
label,
|
||||
onRemove,
|
||||
}: {
|
||||
id: string;
|
||||
index: number;
|
||||
label: string;
|
||||
onRemove: () => void;
|
||||
}) {
|
||||
const {
|
||||
attributes,
|
||||
listeners,
|
||||
setNodeRef,
|
||||
transform,
|
||||
transition,
|
||||
isDragging,
|
||||
} = useSortable({ id });
|
||||
|
||||
const style = {
|
||||
transform: CSS.Translate.toString(transform),
|
||||
transition,
|
||||
};
|
||||
|
||||
const circledNumbers = ["\u2460", "\u2461", "\u2462", "\u2463", "\u2464", "\u2465", "\u2466", "\u2467", "\u2468", "\u2469"];
|
||||
|
||||
return (
|
||||
<div
|
||||
ref={setNodeRef}
|
||||
style={style}
|
||||
className={`flex items-center gap-1 rounded-lg px-2 py-1 text-xs whitespace-nowrap transition-colors ${
|
||||
isDragging
|
||||
? "bg-purple-500/50 border border-purple-400 text-white shadow-lg shadow-purple-500/30 z-10"
|
||||
: "bg-purple-500/30 border border-purple-500/50 text-purple-200"
|
||||
}`}
|
||||
>
|
||||
<span {...attributes} {...listeners} className="cursor-grab active:cursor-grabbing text-purple-400">
|
||||
<GripVertical className="h-3 w-3" />
|
||||
</span>
|
||||
<span className="text-purple-300">{circledNumbers[index] || `${index + 1}`}</span>
|
||||
<span className="max-w-[80px] truncate">{label}</span>
|
||||
<button
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
onRemove();
|
||||
}}
|
||||
className="text-purple-400 hover:text-white ml-0.5"
|
||||
>
|
||||
<X className="h-3 w-3" />
|
||||
</button>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
export function MaterialSelector({
|
||||
materials,
|
||||
selectedMaterial,
|
||||
selectedMaterials,
|
||||
isFetching,
|
||||
lastMaterialCount,
|
||||
editingMaterialId,
|
||||
@@ -48,7 +112,8 @@ export function MaterialSelector({
|
||||
apiBase,
|
||||
onUploadChange,
|
||||
onRefresh,
|
||||
onSelectMaterial,
|
||||
onToggleMaterial,
|
||||
onReorderMaterials,
|
||||
onPreviewMaterial,
|
||||
onStartEditing,
|
||||
onEditNameChange,
|
||||
@@ -58,20 +123,36 @@ export function MaterialSelector({
|
||||
onClearUploadError,
|
||||
registerMaterialRef,
|
||||
}: MaterialSelectorProps) {
|
||||
const sensors = useSensors(
|
||||
useSensor(PointerSensor, { activationConstraint: { distance: 5 } }),
|
||||
useSensor(KeyboardSensor)
|
||||
);
|
||||
|
||||
const handleDragEnd = (event: DragEndEvent) => {
|
||||
const { active, over } = event;
|
||||
if (over && active.id !== over.id) {
|
||||
onReorderMaterials(String(active.id), String(over.id));
|
||||
}
|
||||
};
|
||||
|
||||
const selectedSet = new Set(selectedMaterials);
|
||||
const isFull = selectedMaterials.length >= 4;
|
||||
const circledNumbers = ["\u2460", "\u2461", "\u2462", "\u2463", "\u2464", "\u2465", "\u2466", "\u2467", "\u2468", "\u2469"];
|
||||
|
||||
return (
|
||||
<div className="bg-white/5 rounded-2xl p-4 sm:p-6 border border-white/10 backdrop-blur-sm">
|
||||
<div className="flex justify-between items-center gap-2 mb-4">
|
||||
<h2 className="text-base sm:text-lg font-semibold text-white flex items-center gap-2 whitespace-nowrap">
|
||||
📹 视频素材
|
||||
<span className="ml-1 text-[11px] sm:text-xs text-gray-400/90 font-normal">
|
||||
(上传自拍视频)
|
||||
(可多选，最多4个)
|
||||
</span>
|
||||
</h2>
|
||||
<div className="flex gap-1.5">
|
||||
<input
|
||||
type="file"
|
||||
id="video-upload"
|
||||
accept=".mp4,.mov,.avi"
|
||||
accept="video/*"
|
||||
onChange={onUploadChange}
|
||||
className="hidden"
|
||||
/>
|
||||
@@ -119,6 +200,38 @@ export function MaterialSelector({
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* 已选素材排列（拖拽排序区） - 仅当选中 >= 2 个时显示 */}
|
||||
{selectedMaterials.length >= 2 && (
|
||||
<div className="mb-3 p-3 bg-purple-500/10 rounded-xl border border-purple-500/20">
|
||||
<div className="text-[11px] text-purple-300/70 mb-2">🎬 机位顺序 (拖拽调整)</div>
|
||||
<DndContext
|
||||
sensors={sensors}
|
||||
collisionDetection={closestCenter}
|
||||
onDragEnd={handleDragEnd}
|
||||
>
|
||||
<SortableContext
|
||||
items={selectedMaterials}
|
||||
strategy={horizontalListSortingStrategy}
|
||||
>
|
||||
<div className="flex flex-wrap gap-1.5">
|
||||
{selectedMaterials.map((id, index) => {
|
||||
const m = materials.find((x) => x.id === id);
|
||||
return (
|
||||
<SortableChip
|
||||
key={id}
|
||||
id={id}
|
||||
index={index}
|
||||
label={m?.scene || m?.name || id}
|
||||
onRemove={() => onToggleMaterial(id)}
|
||||
/>
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
</SortableContext>
|
||||
</DndContext>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{fetchError ? (
|
||||
<div className="p-4 bg-red-500/20 text-red-200 rounded-xl text-sm mb-4">
|
||||
获取素材失败: {fetchError}
|
||||
@@ -126,7 +239,7 @@ export function MaterialSelector({
|
||||
API: {apiBase}/api/materials/
|
||||
</div>
|
||||
) : isFetching && materials.length === 0 ? (
|
||||
<div className="space-y-2 max-h-64 overflow-y-auto hide-scrollbar" style={{ contentVisibility: 'auto' }}>
|
||||
<div className="space-y-2 max-h-48 sm:max-h-64 overflow-y-auto hide-scrollbar" style={{ contentVisibility: 'auto' }}>
|
||||
{Array.from({ length: Math.min(4, Math.max(1, lastMaterialCount || 1)) }).map((_, index) => (
|
||||
<div
|
||||
key={`material-skeleton-${index}`}
|
||||
@@ -147,82 +260,99 @@ export function MaterialSelector({
|
||||
</div>
|
||||
) : (
|
||||
<div
|
||||
className="space-y-2 max-h-64 overflow-y-auto hide-scrollbar"
|
||||
className="space-y-2 max-h-48 sm:max-h-64 overflow-y-auto hide-scrollbar"
|
||||
style={{ contentVisibility: 'auto' }}
|
||||
>
|
||||
{materials.map((m) => (
|
||||
<div
|
||||
key={m.id}
|
||||
ref={(el) => registerMaterialRef(m.id, el)}
|
||||
className={`p-3 rounded-lg border transition-all flex items-center justify-between group ${selectedMaterial === m.id
|
||||
? "border-purple-500 bg-purple-500/20"
|
||||
: "border-white/10 bg-white/5 hover:border-white/30"
|
||||
}`}
|
||||
>
|
||||
{editingMaterialId === m.id ? (
|
||||
<div className="flex-1 flex items-center gap-2" onClick={(e) => e.stopPropagation()}>
|
||||
<input
|
||||
value={editMaterialName}
|
||||
onChange={(e) => onEditNameChange(e.target.value)}
|
||||
className="flex-1 bg-black/40 border border-white/20 rounded-md px-2 py-1 text-xs text-white"
|
||||
autoFocus
|
||||
/>
|
||||
<button
|
||||
onClick={(e) => onSaveEditing(m.id, e)}
|
||||
className="p-1 text-green-400 hover:text-green-300"
|
||||
title="保存"
|
||||
>
|
||||
<Check className="h-4 w-4" />
|
||||
</button>
|
||||
<button
|
||||
onClick={onCancelEditing}
|
||||
className="p-1 text-gray-400 hover:text-white"
|
||||
title="取消"
|
||||
>
|
||||
<X className="h-4 w-4" />
|
||||
</button>
|
||||
</div>
|
||||
) : (
|
||||
<button onClick={() => onSelectMaterial(m.id)} className="flex-1 text-left">
|
||||
<div className="text-white text-sm truncate">{m.scene || m.name}</div>
|
||||
<div className="text-gray-400 text-xs">{m.size_mb.toFixed(1)} MB</div>
|
||||
</button>
|
||||
)}
|
||||
<div className="flex items-center gap-2 pl-2">
|
||||
<button
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
if (m.path) {
|
||||
onPreviewMaterial(m.path);
|
||||
}
|
||||
}}
|
||||
className="p-1 text-gray-500 hover:text-white opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="预览视频"
|
||||
>
|
||||
<Eye className="h-4 w-4" />
|
||||
</button>
|
||||
{editingMaterialId !== m.id && (
|
||||
<button
|
||||
onClick={(e) => onStartEditing(m, e)}
|
||||
className="p-1 text-gray-500 hover:text-white opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="重命名"
|
||||
>
|
||||
<Pencil className="h-4 w-4" />
|
||||
{materials.map((m) => {
|
||||
const isSelected = selectedSet.has(m.id);
|
||||
const selIndex = selectedMaterials.indexOf(m.id);
|
||||
return (
|
||||
<div
|
||||
key={m.id}
|
||||
ref={(el) => registerMaterialRef(m.id, el)}
|
||||
className={`p-3 rounded-lg border transition-all flex items-center justify-between group ${isSelected
|
||||
? "border-purple-500 bg-purple-500/20"
|
||||
: isFull
|
||||
? "border-white/5 bg-white/[0.02] opacity-50 cursor-not-allowed"
|
||||
: "border-white/10 bg-white/5 hover:border-white/30"
|
||||
}`}
|
||||
>
|
||||
{editingMaterialId === m.id ? (
|
||||
<div className="flex-1 flex items-center gap-2" onClick={(e) => e.stopPropagation()}>
|
||||
<input
|
||||
value={editMaterialName}
|
||||
onChange={(e) => onEditNameChange(e.target.value)}
|
||||
className="flex-1 bg-black/40 border border-white/20 rounded-md px-2 py-1 text-xs text-white"
|
||||
autoFocus
|
||||
/>
|
||||
<button
|
||||
onClick={(e) => onSaveEditing(m.id, e)}
|
||||
className="p-1 text-green-400 hover:text-green-300"
|
||||
title="保存"
|
||||
>
|
||||
<Check className="h-4 w-4" />
|
||||
</button>
|
||||
<button
|
||||
onClick={onCancelEditing}
|
||||
className="p-1 text-gray-400 hover:text-white"
|
||||
title="取消"
|
||||
>
|
||||
<X className="h-4 w-4" />
|
||||
</button>
|
||||
</div>
|
||||
) : (
|
||||
<button onClick={() => onToggleMaterial(m.id)} className="flex-1 text-left flex items-center gap-2">
|
||||
{/* 复选框 */}
|
||||
<span
|
||||
className={`flex-shrink-0 w-4 h-4 rounded border flex items-center justify-center text-[10px] ${isSelected
|
||||
? "border-purple-500 bg-purple-500 text-white"
|
||||
: "border-white/30 text-transparent"
|
||||
}`}
|
||||
>
|
||||
{isSelected ? (selIndex >= 0 ? circledNumbers[selIndex] || "✓" : "✓") : ""}
|
||||
</span>
|
||||
<div className="min-w-0">
|
||||
<div className="text-white text-sm truncate">{m.scene || m.name}</div>
|
||||
<div className="text-gray-400 text-xs">{m.size_mb.toFixed(1)} MB</div>
|
||||
</div>
|
||||
</button>
|
||||
)}
|
||||
<button
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
onDeleteMaterial(m.id);
|
||||
}}
|
||||
className="p-1 text-gray-500 hover:text-red-400 opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="删除素材"
|
||||
>
|
||||
<Trash2 className="h-4 w-4" />
|
||||
</button>
|
||||
<div className="flex items-center gap-2 pl-2">
|
||||
<button
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
if (m.path) {
|
||||
onPreviewMaterial(m.path);
|
||||
}
|
||||
}}
|
||||
className="p-1 text-gray-500 hover:text-white opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="预览视频"
|
||||
>
|
||||
<Eye className="h-4 w-4" />
|
||||
</button>
|
||||
{editingMaterialId !== m.id && (
|
||||
<button
|
||||
onClick={(e) => onStartEditing(m, e)}
|
||||
className="p-1 text-gray-500 hover:text-white opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="重命名"
|
||||
>
|
||||
<Pencil className="h-4 w-4" />
|
||||
</button>
|
||||
)}
|
||||
<button
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
onDeleteMaterial(m.id);
|
||||
}}
|
||||
className="p-1 text-gray-500 hover:text-red-400 opacity-0 group-hover:opacity-100 transition-opacity"
|
||||
title="删除素材"
|
||||
>
|
||||
<Trash2 className="h-4 w-4" />
|
||||
</button>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
))}
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
|
||||
@@ -1,4 +1,17 @@
|
||||
import { FileText, Loader2, Sparkles } from "lucide-react";
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import { FileText, Languages, Loader2, RotateCcw, Sparkles } from "lucide-react";
|
||||
|
||||
const LANGUAGES = [
|
||||
{ code: "English", label: "英语 English" },
|
||||
{ code: "日本語", label: "日语 日本語" },
|
||||
{ code: "한국어", label: "韩语 한국어" },
|
||||
{ code: "Français", label: "法语 Français" },
|
||||
{ code: "Deutsch", label: "德语 Deutsch" },
|
||||
{ code: "Español", label: "西班牙语 Español" },
|
||||
{ code: "Русский", label: "俄语 Русский" },
|
||||
{ code: "Italiano", label: "意大利语 Italiano" },
|
||||
{ code: "Português", label: "葡萄牙语 Português" },
|
||||
];
|
||||
|
||||
interface ScriptEditorProps {
|
||||
text: string;
|
||||
@@ -6,6 +19,10 @@ interface ScriptEditorProps {
|
||||
onOpenExtractModal: () => void;
|
||||
onGenerateMeta: () => void;
|
||||
isGeneratingMeta: boolean;
|
||||
onTranslate: (targetLang: string) => void;
|
||||
isTranslating: boolean;
|
||||
hasOriginalText: boolean;
|
||||
onRestoreOriginal: () => void;
|
||||
}
|
||||
|
||||
export function ScriptEditor({
|
||||
@@ -14,14 +31,37 @@ export function ScriptEditor({
|
||||
onOpenExtractModal,
|
||||
onGenerateMeta,
|
||||
isGeneratingMeta,
|
||||
onTranslate,
|
||||
isTranslating,
|
||||
hasOriginalText,
|
||||
onRestoreOriginal,
|
||||
}: ScriptEditorProps) {
|
||||
const [showLangMenu, setShowLangMenu] = useState(false);
|
||||
const langMenuRef = useRef<HTMLDivElement>(null);
|
||||
|
||||
useEffect(() => {
|
||||
if (!showLangMenu) return;
|
||||
const handleClickOutside = (e: MouseEvent) => {
|
||||
if (langMenuRef.current && !langMenuRef.current.contains(e.target as Node)) {
|
||||
setShowLangMenu(false);
|
||||
}
|
||||
};
|
||||
document.addEventListener("mousedown", handleClickOutside);
|
||||
return () => document.removeEventListener("mousedown", handleClickOutside);
|
||||
}, [showLangMenu]);
|
||||
|
||||
const handleSelectLang = (langCode: string) => {
|
||||
setShowLangMenu(false);
|
||||
onTranslate(langCode);
|
||||
};
|
||||
|
||||
return (
|
||||
<div className="bg-white/5 rounded-2xl p-4 sm:p-6 border border-white/10 backdrop-blur-sm">
|
||||
<div className="flex flex-wrap justify-between items-center gap-2 mb-4">
|
||||
<h2 className="text-base sm:text-lg font-semibold text-white flex items-center gap-2 whitespace-nowrap">
|
||||
<div className="relative z-10 bg-white/5 rounded-2xl p-4 sm:p-6 border border-white/10 backdrop-blur-sm">
|
||||
<div className="mb-4 space-y-3">
|
||||
<h2 className="text-base sm:text-lg font-semibold text-white flex items-center gap-2">
|
||||
✍️ 文案提取与编辑
|
||||
</h2>
|
||||
<div className="flex gap-2 flex-shrink-0">
|
||||
<div className="flex gap-2 flex-wrap justify-end">
|
||||
<button
|
||||
onClick={onOpenExtractModal}
|
||||
className="px-2 py-1 text-xs rounded transition-all whitespace-nowrap bg-purple-600 hover:bg-purple-700 text-white flex items-center gap-1"
|
||||
@@ -29,6 +69,54 @@ export function ScriptEditor({
|
||||
<FileText className="h-3.5 w-3.5" />
|
||||
文案提取助手
|
||||
</button>
|
||||
<div className="relative" ref={langMenuRef}>
|
||||
<button
|
||||
onClick={() => setShowLangMenu((prev) => !prev)}
|
||||
disabled={isTranslating || !text.trim()}
|
||||
className={`px-2 py-1 text-xs rounded transition-all whitespace-nowrap ${
|
||||
isTranslating || !text.trim()
|
||||
? "bg-gray-600 cursor-not-allowed text-gray-400"
|
||||
: "bg-gradient-to-r from-emerald-600 to-teal-600 hover:from-emerald-700 hover:to-teal-700 text-white"
|
||||
}`}
|
||||
>
|
||||
{isTranslating ? (
|
||||
<span className="flex items-center gap-1">
|
||||
<Loader2 className="h-3.5 w-3.5 animate-spin" />
|
||||
翻译中...
|
||||
</span>
|
||||
) : (
|
||||
<span className="flex items-center gap-1">
|
||||
<Languages className="h-3.5 w-3.5" />
|
||||
AI多语言
|
||||
</span>
|
||||
)}
|
||||
</button>
|
||||
{showLangMenu && (
|
||||
<div className="absolute right-0 top-full mt-1 z-50 bg-gray-800 border border-white/10 rounded-lg shadow-xl py-1 min-w-[160px]">
|
||||
{hasOriginalText && (
|
||||
<>
|
||||
<button
|
||||
onClick={() => { setShowLangMenu(false); onRestoreOriginal(); }}
|
||||
className="w-full text-left px-3 py-1.5 text-xs text-amber-400 hover:bg-white/10 transition-colors flex items-center gap-1"
|
||||
>
|
||||
<RotateCcw className="h-3 w-3" />
|
||||
还原原文
|
||||
</button>
|
||||
<div className="border-t border-white/10 my-1" />
|
||||
</>
|
||||
)}
|
||||
{LANGUAGES.map((lang) => (
|
||||
<button
|
||||
key={lang.code}
|
||||
onClick={() => handleSelectLang(lang.code)}
|
||||
className="w-full text-left px-3 py-1.5 text-xs text-gray-200 hover:bg-white/10 transition-colors"
|
||||
>
|
||||
{lang.label}
|
||||
</button>
|
||||
))}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
<button
|
||||
onClick={onGenerateMeta}
|
||||
disabled={isGeneratingMeta || !text.trim()}
|
||||
|
||||
@@ -52,8 +52,6 @@ interface TitleSubtitlePanelProps {
|
||||
onTitleTopMarginChange: (value: number) => void;
|
||||
subtitleBottomMargin: number;
|
||||
onSubtitleBottomMarginChange: (value: number) => void;
|
||||
enableSubtitles: boolean;
|
||||
onToggleSubtitles: (value: boolean) => void;
|
||||
resolveAssetUrl: (path?: string | null) => string | null;
|
||||
getFontFormat: (fontFile?: string) => string;
|
||||
buildTextShadow: (color: string, size: number) => string;
|
||||
@@ -82,8 +80,6 @@ export function TitleSubtitlePanel({
|
||||
onTitleTopMarginChange,
|
||||
subtitleBottomMargin,
|
||||
onSubtitleBottomMarginChange,
|
||||
enableSubtitles,
|
||||
onToggleSubtitles,
|
||||
resolveAssetUrl,
|
||||
getFontFormat,
|
||||
buildTextShadow,
|
||||
@@ -117,7 +113,7 @@ export function TitleSubtitlePanel({
|
||||
subtitleFontSize={subtitleFontSize}
|
||||
titleTopMargin={titleTopMargin}
|
||||
subtitleBottomMargin={subtitleBottomMargin}
|
||||
enableSubtitles={enableSubtitles}
|
||||
enableSubtitles={true}
|
||||
resolveAssetUrl={resolveAssetUrl}
|
||||
getFontFormat={getFontFormat}
|
||||
buildTextShadow={buildTextShadow}
|
||||
@@ -186,7 +182,7 @@ export function TitleSubtitlePanel({
|
||||
</div>
|
||||
)}
|
||||
|
||||
{enableSubtitles && subtitleStyles.length > 0 && (
|
||||
{subtitleStyles.length > 0 && (
|
||||
<div className="mt-4">
|
||||
<label className="text-sm text-gray-300 mb-2 block">字幕样式</label>
|
||||
<div className="grid grid-cols-2 gap-2">
|
||||
@@ -232,22 +228,6 @@ export function TitleSubtitlePanel({
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
|
||||
<div className="mt-4 pt-4 border-t border-white/10 flex items-center justify-between">
|
||||
<div>
|
||||
<span className="text-sm text-gray-300">逐字高亮字幕</span>
|
||||
<p className="text-xs text-gray-500 mt-1">自动生成卡拉OK效果字幕</p>
|
||||
</div>
|
||||
<label className="relative inline-flex items-center cursor-pointer">
|
||||
<input
|
||||
type="checkbox"
|
||||
checked={enableSubtitles}
|
||||
onChange={(e) => onToggleSubtitles(e.target.checked)}
|
||||
className="sr-only peer"
|
||||
/>
|
||||
<div className="w-11 h-6 bg-gray-600 peer-focus:outline-none rounded-full peer peer-checked:after:translate-x-full peer-checked:after:border-white after:content-[''] after:absolute after:top-[2px] after:left-[2px] after:bg-white after:border-gray-300 after:border after:rounded-full after:h-5 after:w-5 after:transition-all peer-checked:bg-purple-600"></div>
|
||||
</label>
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -5,8 +5,8 @@ import { ApiResponse, unwrap } from "@/shared/api/types";
|
||||
import { formatDate, getApiBaseUrl, isAbsoluteUrl, resolveMediaUrl } from "@/shared/lib/media";
|
||||
import { clampTitle } from "@/shared/lib/title";
|
||||
import { useTitleInput } from "@/shared/hooks/useTitleInput";
|
||||
import { useAuth } from "@/contexts/AuthContext";
|
||||
import { useTask } from "@/contexts/TaskContext";
|
||||
import { useAuth } from "@/shared/contexts/AuthContext";
|
||||
import { useTask } from "@/shared/contexts/TaskContext";
|
||||
import { toast } from "sonner";
|
||||
import { usePublishPrefetch } from "@/shared/hooks/usePublishPrefetch";
|
||||
import {
|
||||
|
||||
7
frontend/src/shared/types/material.ts
Normal file
7
frontend/src/shared/types/material.ts
Normal file
@@ -0,0 +1,7 @@
|
||||
export interface Material {
|
||||
id: string;
|
||||
name: string;
|
||||
path: string;
|
||||
size_mb: number;
|
||||
scene?: string;
|
||||
}
|
||||
@@ -134,10 +134,14 @@ async def generate(
|
||||
try:
|
||||
print(f"🎤 Generating: {text[:30]}...")
|
||||
print(f"📝 Ref text: {ref_text[:50]}...")
|
||||
print(f"🌐 Language: {language}")
|
||||
|
||||
start = time.time()
|
||||
|
||||
wavs, sr = _model.generate_voice_clone(
|
||||
# 在线程池中运行，避免阻塞事件循环导致健康检查超时
|
||||
import asyncio
|
||||
wavs, sr = await asyncio.to_thread(
|
||||
_model.generate_voice_clone,
|
||||
text=text,
|
||||
language=language,
|
||||
ref_audio=ref_audio_path,
|
||||
|
||||
Reference in New Issue
Block a user