Initial commit: audio2text 双语字幕生成服务

- 音频/视频转双语(英/中)SRT 字幕，Docker 容器化，CPU 开发/GPU 生产同一份代码
- faster-whisper ASR(词级时间戳) + 断句时间戳重算 + NLLB 翻译(模型不共驻)
- 分片上传(断点续传) + SQLite 持久化 + 主页/历史/日志页面
- 历史页文件名搜索；缓存定时清理(默认保留7天，可配置)
- 双 Dockerfile(cpu/gpu) + setup/start/stop 脚本

app/controllers/__init__.py

@@ -0,0 +1,7 @@
+"""路由聚合：导出各 controller 的 router，供 main.py include。"""
+
+from .log_router import router as log_router
+from .task_router import router as task_router
+from .upload_router import router as upload_router
+
+__all__ = ["log_router", "task_router", "upload_router"]

app/controllers/log_router.py

@@ -0,0 +1,31 @@
+"""日志路由：查询内存日志缓冲，供 /logs 页面消费。
+
+分层语义：
+- debug：详细（ffmpeg 命令、模型加载/卸载、转写逐段、翻译逐批进度）
+- info：简略（仅任务阶段转换，如 "任务 N [transcribing 55%]"）
+- warning / error：更详细，error 含完整 traceback
+"""
+
+from __future__ import annotations
+
+from fastapi import APIRouter, Query
+
+from ..services.log_buffer import get_log_buffer
+
+router = APIRouter(prefix="/api/logs", tags=["logs"])
+
+
+@router.get("", summary="查询日志（按级别过滤）")
+def get_logs(
+    level: str = Query("info", pattern="^(debug|info|warning|error)$",
+                       description="最小级别：debug=详细, info=简略, error=仅错误"),
+    tail: int = Query(200, ge=1, le=2000, description="最多返回条数"),
+) -> dict:
+    records = get_log_buffer().get_records(level=level, tail=tail)
+    return {"level": level, "tail": tail, "count": len(records), "logs": records}
+
+
+@router.delete("", summary="清空日志缓冲")
+def clear_logs() -> dict:
+    get_log_buffer().clear()
+    return {"status": "cleared"}

app/controllers/task_router.py

@@ -0,0 +1,88 @@
+"""任务路由：列表 / 状态 / 下载字幕。"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from fastapi import APIRouter, Depends, HTTPException, Query
+from fastapi.responses import FileResponse
+from sqlalchemy.orm import Session
+
+from ..config import get_settings
+from ..database import get_db
+from ..models.task import Task
+from ..schemas.task import TaskListResponse, TaskResponse
+
+router = APIRouter(prefix="/api/tasks", tags=["task"])
+
+
+def _to_resp(task: Task) -> TaskResponse:
+    return TaskResponse(
+        id=task.id,
+        filename=task.filename,
+        status=task.status,
+        progress=task.progress,
+        error=task.error,
+        created_at=task.created_at,
+        updated_at=task.updated_at,
+    )
+
+
+@router.get("", response_model=TaskListResponse, summary="任务列表")
+def list_tasks(
+    limit: int = Query(100, ge=1, le=500),
+    offset: int = Query(0, ge=0),
+    q: str = Query("", description="按文件名模糊搜索（大小写不敏感，匹配子串）"),
+    db: Session = Depends(get_db),
+) -> TaskListResponse:
+    q_base = db.query(Task).order_by(Task.id.desc())
+    if q.strip():
+        # SQLite 的 LIKE 默认大小写不敏感（ASCII），ilike 等价于 LIKE
+        like = f"%{q.strip()}%"
+        q_base = q_base.filter(Task.filename.ilike(like))
+    total = q_base.count()
+    tasks = q_base.offset(offset).limit(limit).all()
+    return TaskListResponse(tasks=[_to_resp(t) for t in tasks], total=total)
+
+
+@router.get("/{task_id}", response_model=TaskResponse, summary="任务状态")
+def get_task(task_id: int, db: Session = Depends(get_db)) -> TaskResponse:
+    task = db.get(Task, task_id)
+    if task is None:
+        raise HTTPException(404, f"任务不存在：{task_id}")
+    return _to_resp(task)
+
+
+@router.get("/{task_id}/subtitle", summary="下载字幕")
+def download_subtitle(
+    task_id: int,
+    type: str = Query("bilingual", pattern="^(bilingual|en|zh)$"),
+    db: Session = Depends(get_db),
+) -> FileResponse:
+    task = db.get(Task, task_id)
+    if task is None:
+        raise HTTPException(404, f"任务不存在：{task_id}")
+    if task.status != "done":
+        raise HTTPException(409, f"任务尚未完成（当前状态：{task.status}）")
+
+    rel = {
+        "bilingual": task.bilingual_srt_path,
+        "en": task.en_srt_path,
+        "zh": task.zh_srt_path,
+    }[type]
+    if not rel:
+        raise HTTPException(404, f"该类型字幕不存在：{type}")
+
+    s = get_settings()
+    path = s.output_dir() / rel
+    if not path.is_file():
+        raise HTTPException(404, f"字幕文件丢失：{path}")
+
+    base = Path(task.filename).stem
+    suffix = "" if type == "bilingual" else f".{type}"
+    download_name = f"{base}{suffix}.srt"
+    return FileResponse(
+        path=path,
+        media_type="application/x-subrip",
+        filename=download_name,
+    )

app/controllers/upload_router.py

@@ -0,0 +1,69 @@
+"""分片上传路由：建会话 / 查状态 / 传分片 / complete。
+
+协议与 server 完全一致，区别仅在 complete 后创建的是转写 Task 而非 UploadedFile。
+"""
+
+from __future__ import annotations
+
+from fastapi import APIRouter, Depends, Request
+from sqlalchemy.orm import Session
+
+from ..database import get_db
+from ..schemas.task import (
+    ChunkUploadResponse,
+    CompleteResponse,
+    CreateSessionRequest,
+    CreateSessionResponse,
+    SessionStatusResponse,
+)
+from ..services.upload_service import UploadService
+
+router = APIRouter(prefix="/api/tasks/chunk-uploads", tags=["upload"])
+
+
+def _service(db: Session = Depends(get_db)) -> UploadService:
+    return UploadService(db)
+
+
+@router.post("", response_model=CreateSessionResponse, summary="创建分片上传会话")
+def create_session(
+    body: CreateSessionRequest,
+    service: UploadService = Depends(_service),
+) -> CreateSessionResponse:
+    return service.create_session(body)
+
+
+@router.get("/{upload_id}/status", response_model=SessionStatusResponse, summary="查询会话状态（断点续传）")
+def session_status(
+    upload_id: str,
+    service: UploadService = Depends(_service),
+) -> SessionStatusResponse:
+    return service.get_status(upload_id)
+
+
+@router.post("/{upload_id}/chunks/{index}", response_model=ChunkUploadResponse, summary="上传单个分片")
+async def upload_chunk(
+    upload_id: str,
+    index: int,
+    request: Request,
+    service: UploadService = Depends(_service),
+) -> ChunkUploadResponse:
+    uploaded = service.write_chunk(upload_id, index, await request.body())
+    return ChunkUploadResponse(upload_id=upload_id, index=index, uploaded_chunks=uploaded)
+
+
+@router.post("/{upload_id}/complete", response_model=CompleteResponse, summary="完成拼接并创建转写任务")
+def complete_session(
+    upload_id: str,
+    service: UploadService = Depends(_service),
+) -> CompleteResponse:
+    """拼接分片 + 创建转写任务 + 入队管线。
+
+    controller 负责编排：service.complete 只管存储（拼接 + 建 Task），
+    管线触发由 controller 调用，service 不依赖 pipeline（避免循环依赖）。
+    """
+    resp = service.complete(upload_id)
+    # 仅新建任务时入队（幂等 complete 返回的也是同一 task_id，enqueue 幂等无副作用）
+    from ..services.pipeline import enqueue_task
+    enqueue_task(resp.task_id)
+    return resp