沃巴蒂
ff22ed3a8b
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）
71 lines
3.6 KiB
Python
71 lines
3.6 KiB
Python
from sqlalchemy import Column, String, BigInteger, Integer, TIMESTAMP, Index
|
|
from app.db.models.base_entity import BaseEntity, Base
|
|
|
|
|
|
class CleaningTask(BaseEntity):
|
|
"""Data cleaning task entity"""
|
|
__tablename__ = "t_clean_task"
|
|
__ignore_data_scope__ = True
|
|
|
|
id = Column(String(36), primary_key=True, comment="Task ID")
|
|
name = Column(String(255), nullable=False, comment="Task name")
|
|
description = Column(String(1024), nullable=True, comment="Task description")
|
|
status = Column(String(50), nullable=False, default="PENDING", comment="Task status: PENDING, RUNNING, COMPLETED, STOPPED, FAILED")
|
|
src_dataset_id = Column(String(36), nullable=False, comment="Source dataset ID")
|
|
src_dataset_name = Column(String(255), nullable=False, comment="Source dataset name")
|
|
dest_dataset_id = Column(String(36), nullable=True, comment="Destination dataset ID")
|
|
dest_dataset_name = Column(String(255), nullable=True, comment="Destination dataset name")
|
|
before_size = Column(BigInteger, nullable=True, comment="Data size before cleaning")
|
|
after_size = Column(BigInteger, nullable=True, comment="Data size after cleaning")
|
|
file_count = Column(Integer, nullable=True, comment="Total file count")
|
|
retry_count = Column(Integer, default=0, nullable=False, comment="Retry count")
|
|
started_at = Column(TIMESTAMP, nullable=True, comment="Task start time")
|
|
finished_at = Column(TIMESTAMP, nullable=True, comment="Task finish time")
|
|
|
|
__table_args__ = (
|
|
Index("ix_clean_task_status", "status"),
|
|
Index("ix_clean_task_created_at", "created_at"),
|
|
)
|
|
|
|
|
|
class CleaningTemplate(BaseEntity):
|
|
"""Data cleaning template entity"""
|
|
__tablename__ = "t_clean_template"
|
|
|
|
id = Column(String(36), primary_key=True, comment="Template ID")
|
|
name = Column(String(255), nullable=False, comment="Template name")
|
|
description = Column(String(1024), nullable=True, comment="Template description")
|
|
|
|
|
|
class CleaningResult(Base):
|
|
"""Data cleaning result entity"""
|
|
__tablename__ = "t_clean_result"
|
|
|
|
instance_id = Column(String(36), primary_key=True, comment="Instance ID (task or template ID)")
|
|
src_file_id = Column(String(36), primary_key=True, comment="Source file ID")
|
|
dest_file_id = Column(String(36), nullable=True, comment="Destination file ID")
|
|
src_name = Column(String(512), nullable=True, comment="Source file name")
|
|
dest_name = Column(String(512), nullable=True, comment="Destination file name")
|
|
src_type = Column(String(50), nullable=True, comment="Source file type")
|
|
dest_type = Column(String(50), nullable=True, comment="Destination file type")
|
|
src_size = Column(BigInteger, nullable=True, comment="Source file size")
|
|
dest_size = Column(BigInteger, nullable=True, comment="Destination file size")
|
|
status = Column(String(50), nullable=True, comment="Cleaning status: COMPLETED, FAILED, etc.")
|
|
result = Column(String(1024), nullable=True, comment="Cleaning result message")
|
|
|
|
__table_args__ = (
|
|
Index("ix_clean_result_instance_id", "instance_id"),
|
|
Index("ix_clean_result_instance_status", "instance_id", "status"),
|
|
)
|
|
|
|
|
|
class OperatorInstance(Base):
|
|
"""Operator instance in task or template"""
|
|
__tablename__ = "t_operator_instance"
|
|
|
|
instance_id = Column(String(36), primary_key=True, comment="Instance ID (task or template ID)")
|
|
operator_id = Column(String(36), primary_key=True, comment="Operator ID")
|
|
op_index = Column(Integer, nullable=False, comment="Operator execution order")
|
|
settings_override = Column(String(4096), nullable=True, comment="Operator settings override (JSON)")
|
|
|