Files
沃巴蒂 ff22ed3a8b feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强,deepflow 改名为 deep-flow
本次同步 09-12 至 09-28 的代码变更,主要内容:

新增功能
- 修改密码:后端新增 ChangePasswordRequest DTO 与UserController/UserService
  对应接口,前端新增 ChangePasswordDialog 并在 Header 接入入口
- 文件预览组件重构:file-preview 目录拆分出 VideoPreview(支持 blobUrl 直传)、
  ImagePreview、AudioPreview,index.tsx 统一调度各类型预览器
- 新增 my_ops 算子模块:markitdown_parser、mineru_pdf_parser、text_quality_evaluator
- 新增 tools/minio-file-server MinIO 文件服务

功能增强
- 数据清洗:cleaning_task_service/scheduler/routes 重构,
  data_juicer_executor 与 wrapper 增强,OperatorTable/LogsTable/TaskDetail 同步调整
- 数据标注:annotation sync.py、project.py 接口与schema 更新
- 数据采集、算子市场、首页与菜单路由相关页面调整
- DataJuicer 算子接入(useOperatorOperations、dj_ops_schema)

结构调整
- deepflow/ 更名为 deep-flow/(419 个文件重命名)
- 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本

未纳入本次提交
- scripts-backup/、runtime/python-executor-backup/、components_backup/(备份目录)
- *.backup*、__pycache__ 产物
- zh_core_web_sm-3.8.0-py3-none-any.whl(46MB 构建产物)
- DataX/(内嵌独立仓库,远程亦未收录其源码)
2026-10-03 22:44:56 +08:00

122 lines
4.0 KiB
Python

import logging
import re
import sys
from logging.handlers import RotatingFileHandler
from pathlib import Path
from app.core.config import settings
_SIZE_PATTERN = re.compile(r"^\s*(\d+)\s*([KMG]?B?)?\s*$", re.IGNORECASE)
class CenteredLevelNameFormatter(logging.Formatter):
"""Center the level name in the log output"""
def format(self, record):
# 将 levelname 居中对齐到8个字符
record.levelname = record.levelname.center(8)
return super().format(record)
def _parse_size_to_bytes(value: str) -> int:
match = _SIZE_PATTERN.match(value)
if not match:
return 100 * 1024 * 1024
amount = int(match.group(1))
unit = (match.group(2) or "B").upper()
if unit in {"G", "GB"}:
return amount * 1024 * 1024 * 1024
if unit in {"M", "MB"}:
return amount * 1024 * 1024
if unit in {"K", "KB"}:
return amount * 1024
return amount
def _rotated_log_namer(default_name: str) -> str:
path = Path(default_name)
index_suffix = path.suffix
if not index_suffix.lstrip(".").isdigit():
return default_name
base_path = Path(str(path)[: -len(index_suffix)])
if not base_path.suffix:
return default_name
return str(base_path.with_name(f"{base_path.stem}{index_suffix}{base_path.suffix}"))
def _remove_managed_handlers(logger: logging.Logger) -> None:
for handler in list(logger.handlers):
if getattr(handler, "_DeepData_managed", False):
logger.removeHandler(handler)
handler.close()
def _mark_managed(handler: logging.Handler) -> logging.Handler:
setattr(handler, "_DeepData_managed", True)
return handler
def setup_logging():
log_format = "%(asctime)s [%(levelname)s] - %(name)s - %(message)s"
date_format = "%Y-%m-%d %H:%M:%S"
console_handler = _mark_managed(logging.StreamHandler(sys.stdout))
console_handler.setLevel(getattr(logging, settings.log_level.upper()))
log_dir = Path(settings.log_file_dir)
log_dir.mkdir(exist_ok=True)
file_handler = _mark_managed(RotatingFileHandler(
log_dir / "python-backend.log",
maxBytes=_parse_size_to_bytes(settings.log_rotation_max_size),
backupCount=max(1, settings.log_rotation_backup_count),
encoding="utf-8"
))
file_handler.namer = _rotated_log_namer
file_handler.setLevel(getattr(logging, settings.log_level.upper()))
# Style setting - Centered level names
formatter = CenteredLevelNameFormatter(log_format, date_format)
console_handler.setFormatter(formatter)
file_handler.setFormatter(formatter)
# Root Logger
root_logger = logging.getLogger()
_remove_managed_handlers(root_logger)
root_logger.setLevel(getattr(logging, settings.log_level.upper()))
root_logger.addHandler(console_handler)
root_logger.addHandler(file_handler)
# Uvicorn
uvicorn_logger = logging.getLogger("uvicorn")
uvicorn_logger.handlers.clear()
uvicorn_logger.addHandler(console_handler)
uvicorn_logger.setLevel(logging.INFO)
uvicorn_access = logging.getLogger("uvicorn.access")
uvicorn_access.handlers.clear()
uvicorn_access.addHandler(console_handler)
uvicorn_access.setLevel(logging.DEBUG)
uvicorn_error = logging.getLogger("uvicorn.error")
uvicorn_error.handlers.clear()
uvicorn_error.addHandler(console_handler)
uvicorn_error.setLevel(logging.ERROR)
# SQLAlchemy (ERROR only)
sqlalchemy_logger = logging.getLogger("sqlalchemy.engine")
_remove_managed_handlers(sqlalchemy_logger)
sqlalchemy_logger.setLevel(logging.ERROR)
sqlalchemy_logger.addHandler(console_handler)
sqlalchemy_logger.setLevel(logging.ERROR)
# Minimize noise from HTTPX and HTTPCore
logging.getLogger("httpx").setLevel(logging.ERROR)
logging.getLogger("httpcore").setLevel(logging.ERROR)
def get_logger(name: str) -> logging.Logger:
return logging.getLogger(name)