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）
92 lines
4.3 KiB
Python
92 lines
4.3 KiB
Python
from typing import Literal, List, Dict, Any, Optional
|
||
from datetime import datetime
|
||
|
||
from pydantic import Field, ConfigDict
|
||
|
||
from app.module.shared.schema import BaseResponseModel
|
||
from app.module.shared.schema import StandardResponse
|
||
|
||
|
||
class SyncDatasetRequest(BaseResponseModel):
|
||
"""同步数据集请求模型"""
|
||
model_config = ConfigDict(populate_by_name=True)
|
||
|
||
id: str = Field(..., description="映射ID（mapping UUID）")
|
||
batch_size: int = Field(50, ge=1, le=100, description="批处理大小", alias="batchSize")
|
||
file_priority: Literal[0, 1] = Field(0, description="0 数据集为主，1 标注平台为主", alias="filePriority")
|
||
label_priority: Literal[0, 1] = Field(0, description="0 数据集为主，1 标注平台为主", alias="labelPriority")
|
||
sync_annotations: bool = Field(True, description="是否同步标注数据", alias="syncAnnotations")
|
||
annotation_direction: Literal["ls_to_dm", "dm_to_ls", "bidirectional"] = Field(
|
||
"bidirectional",
|
||
description="标注同步方向: ls_to_dm(Label Studio到数据集), dm_to_ls(数据集到Label Studio), bidirectional(双向)",
|
||
alias="annotationDirection"
|
||
)
|
||
overwrite: bool = Field(
|
||
True,
|
||
description="是否覆盖DeepData中的标注（基于时间戳比较）"
|
||
)
|
||
overwrite_labeling_project: bool = Field(
|
||
True,
|
||
description="是否覆盖Label Studio中的标注（基于时间戳比较）",
|
||
alias="overwriteLabelingProject"
|
||
)
|
||
|
||
class SyncDatasetResponse(BaseResponseModel):
|
||
"""同步数据集响应模型"""
|
||
id: str = Field(..., description="映射UUID")
|
||
status: str = Field(..., description="同步状态")
|
||
synced_files: int = Field(..., description="已同步文件数量")
|
||
total_files: int = Field(0, description="总文件数量")
|
||
message: str = Field(..., description="响应消息")
|
||
|
||
class SyncDatasetResponseStd(StandardResponse[SyncDatasetResponse]):
|
||
pass
|
||
|
||
|
||
class SyncAnnotationsRequest(BaseResponseModel):
|
||
"""同步标注请求模型
|
||
|
||
使用camelCase作为API接口字段名（通过alias），但Python代码内部使用snake_case。
|
||
Pydantic会自动处理两种格式的转换。
|
||
"""
|
||
model_config = ConfigDict(populate_by_name=True)
|
||
|
||
id: str = Field(..., description="映射ID（mapping UUID）")
|
||
batch_size: int = Field(50, ge=1, le=100, description="批处理大小", alias="batchSize")
|
||
direction: Literal["ls_to_dm", "dm_to_ls", "bidirectional"] = Field(
|
||
"bidirectional",
|
||
description="同步方向: ls_to_dm(Label Studio到数据集), dm_to_ls(数据集到Label Studio), bidirectional(双向)"
|
||
)
|
||
overwrite: bool = Field(
|
||
True,
|
||
description="是否覆盖DeepData中的标注（基于时间戳比较）。True时，如果Label Studio的标注更新时间更新，则覆盖DeepData的标注"
|
||
)
|
||
overwrite_labeling_project: bool = Field(
|
||
True,
|
||
description="是否覆盖Label Studio中的标注（基于时间戳比较）。True时，如果DeepData的标注更新时间更新，则覆盖Label Studio的标注",
|
||
alias="overwriteLabelingProject"
|
||
)
|
||
|
||
|
||
class TagInfo(BaseResponseModel):
|
||
"""标注信息结构（不包含时间戳，时间戳存储在文件级别的tags_updated_at字段）"""
|
||
from_name: str = Field(..., description="标注工具名称")
|
||
to_name: str = Field(..., description="目标对象名称")
|
||
type: str = Field(..., description="标注类型")
|
||
values: Dict[str, Any] = Field(..., description="标注值")
|
||
|
||
|
||
class SyncAnnotationsResponse(BaseResponseModel):
|
||
"""同步标注响应模型"""
|
||
id: str = Field(..., description="映射UUID")
|
||
status: str = Field(..., description="同步状态: success/partial/error")
|
||
synced_to_dm: int = Field(0, description="同步到数据集的标注数量")
|
||
synced_to_ls: int = Field(0, description="同步到Label Studio的标注数量")
|
||
skipped: int = Field(0, description="跳过的标注数量")
|
||
failed: int = Field(0, description="失败的标注数量")
|
||
conflicts_resolved: int = Field(0, description="解决的冲突数量")
|
||
message: str = Field(..., description="响应消息")
|
||
|
||
|
||
class SyncAnnotationsResponseStd(StandardResponse[SyncAnnotationsResponse]):
|
||
pass |