73110848f4
- scheduler: ffmpeg 异步线程 + GPU 串行调度 + 模型复用（2N→2 次加载） - pipeline: 阶段拆分（extract/asr/translate），中间数据存 Task 字段 - translate_service: 长度排序批处理，padding 浪费减少 91% - model_manager: ASR/翻译不共驻，BatchedInferencePipeline 批量解码 - 日志分级: INFO=任务流转里程碑，DEBUG=进度详情；默认 INFO - 前端: 日志最新在上+滚动感知+退避轮询；24h 时间；上传中状态显示 - /health: 返回完整 Whisper/NLLB 配置 - upload_service: 单事务 complete + 扩展名白名单 - task_router: 合并 UploadSession 虚拟任务到列表 - Dockerfile: CPU/GPU 独立构建链，deps 缓存稳定 - prefetch_models: 安装时预下载模型权重
93 lines
2.7 KiB
Python
93 lines
2.7 KiB
Python
"""SQLite 引擎、Session、Base、get_db 依赖。
|
||
|
||
自包含：无需外部 MySQL，容器内单文件 SQLite 即可。对齐 server/database.py 的接口形态，
|
||
但用 SQLite（本项目独立运行、无并发写入压力）。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from pathlib import Path
|
||
from typing import Generator
|
||
|
||
from sqlalchemy import create_engine
|
||
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
|
||
|
||
from .config import get_settings
|
||
|
||
_engine = None
|
||
_SessionLocal = None
|
||
|
||
|
||
def _db_path() -> Path:
|
||
"""SQLite 文件落在 work_dir 下，跟数据一起走 volume。"""
|
||
s = get_settings()
|
||
p = s.work_dir() / "audio2text.db"
|
||
p.parent.mkdir(parents=True, exist_ok=True)
|
||
return p
|
||
|
||
|
||
def get_engine():
|
||
global _engine, _SessionLocal
|
||
if _engine is None:
|
||
url = f"sqlite:///{_db_path()}"
|
||
_engine = create_engine(
|
||
url,
|
||
# 后台 reaper / 缓存清理线程与请求线程并发写同一库；busy_timeout 让等待方
|
||
# 在拿锁时阻塞 5s 而非立即报 database is locked。
|
||
connect_args={"check_same_thread": False, "timeout": 30},
|
||
future=True,
|
||
)
|
||
_SessionLocal = sessionmaker(bind=_engine, autoflush=False, expire_on_commit=False)
|
||
return _engine
|
||
|
||
|
||
def get_session_local():
|
||
get_engine()
|
||
return _SessionLocal
|
||
|
||
|
||
class Base(DeclarativeBase):
|
||
pass
|
||
|
||
|
||
def init_db_schema() -> None:
|
||
"""建表（幂等）+ 旧库迁移（给 task 表补新字段）。
|
||
|
||
SQLAlchemy 的 create_all 只建新表不改旧表。对已存在的 task 表，
|
||
需手动 ALTER TABLE ADD COLUMN 补 wav_path / segments_json（nullable）。
|
||
"""
|
||
from .models.task import Task # noqa: F401
|
||
from .models.upload_session import UploadSession # noqa: F401
|
||
|
||
engine = get_engine()
|
||
Base.metadata.create_all(engine)
|
||
_migrate_task_columns(engine)
|
||
|
||
|
||
def _migrate_task_columns(engine) -> None:
|
||
"""检测 task 表缺失的列并 ALTER TABLE 补上（nullable，向后兼容）。"""
|
||
from sqlalchemy import inspect, text
|
||
|
||
insp = inspect(engine)
|
||
if "task" not in insp.get_table_names():
|
||
return # 新库，create_all 已建好完整表
|
||
existing = {c["name"] for c in insp.get_columns("task")}
|
||
# 新增字段：(列名, 列定义)
|
||
additions = [
|
||
("wav_path", "VARCHAR(1024)"),
|
||
("segments_json", "TEXT"),
|
||
]
|
||
with engine.begin() as conn:
|
||
for col, coltype in additions:
|
||
if col not in existing:
|
||
conn.execute(text(f"ALTER TABLE task ADD COLUMN {col} {coltype}"))
|
||
|
||
|
||
def get_db() -> Generator[Session, None, None]:
|
||
"""FastAPI 依赖：每请求一个 Session，结束自动关闭。"""
|
||
db = get_session_local()()
|
||
try:
|
||
yield db
|
||
finally:
|
||
db.close()
|