You've already forked DataMate
Jerry Yan
0b69845a29
- 在 EditorProjectInfo 中增加 datasetType 字段 - 移除前端硬编码的源文档扩展名列表 - 添加 isTextProject 判断逻辑 - 实现 prefetch 和 loadTasks 中的源文档排除参数 - 在后端接口中添加 excludeSourceDocuments 参数 - 实现源文档类型的数据库查询过滤逻辑 - 优化任务列表加载性能，避免不必要的源文档加载
104 lines
3.5 KiB
Python
104 lines
3.5 KiB
Python
"""
|
|
Label Studio Editor（前端嵌入式）接口
|
|
|
|
说明：
|
|
- 不依赖 Label Studio Server；仅复用其“编辑器”前端库
|
|
- DataMate 负责提供 tasks/annotations 数据与保存能力
|
|
- 当前支持 dataset_type=TEXT/IMAGE 的项目
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Optional
|
|
|
|
from fastapi import APIRouter, Depends, Query, Path
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.core.logging import get_logger
|
|
from app.db.session import get_db
|
|
from app.module.annotation.schema.editor import (
|
|
EditorProjectInfo,
|
|
EditorTaskListResponse,
|
|
EditorTaskResponse,
|
|
UpsertAnnotationRequest,
|
|
UpsertAnnotationResponse,
|
|
)
|
|
from app.module.annotation.service.editor import AnnotationEditorService
|
|
from app.module.shared.schema import StandardResponse
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
router = APIRouter(
|
|
prefix="/editor",
|
|
tags=["annotation/editor"],
|
|
)
|
|
|
|
|
|
@router.get(
|
|
"/projects/{project_id}",
|
|
response_model=StandardResponse[EditorProjectInfo],
|
|
)
|
|
async def get_editor_project_info(
|
|
project_id: str = Path(..., description="标注项目ID（t_dm_labeling_projects.id）"),
|
|
db: AsyncSession = Depends(get_db),
|
|
):
|
|
service = AnnotationEditorService(db)
|
|
info = await service.get_project_info(project_id)
|
|
return StandardResponse(code=200, message="success", data=info)
|
|
|
|
|
|
@router.get(
|
|
"/projects/{project_id}/tasks",
|
|
response_model=StandardResponse[EditorTaskListResponse],
|
|
)
|
|
async def list_editor_tasks(
|
|
project_id: str = Path(..., description="标注项目ID（t_dm_labeling_projects.id）"),
|
|
page: int = Query(0, ge=0, description="页码（从0开始）"),
|
|
size: int = Query(50, ge=1, le=200, description="每页大小"),
|
|
exclude_source_documents: Optional[bool] = Query(
|
|
None,
|
|
alias="excludeSourceDocuments",
|
|
description="是否排除已被转换为TXT的源文档文件（PDF/DOC/DOCX，仅文本数据集生效）",
|
|
),
|
|
db: AsyncSession = Depends(get_db),
|
|
):
|
|
service = AnnotationEditorService(db)
|
|
result = await service.list_tasks(
|
|
project_id,
|
|
page=page,
|
|
size=size,
|
|
exclude_source_documents=exclude_source_documents,
|
|
)
|
|
return StandardResponse(code=200, message="success", data=result)
|
|
|
|
|
|
@router.get(
|
|
"/projects/{project_id}/tasks/{file_id}",
|
|
response_model=StandardResponse[EditorTaskResponse],
|
|
)
|
|
async def get_editor_task(
|
|
project_id: str = Path(..., description="标注项目ID（t_dm_labeling_projects.id）"),
|
|
file_id: str = Path(..., description="文件ID（t_dm_dataset_files.id）"),
|
|
segment_index: Optional[int] = Query(None, alias="segmentIndex", description="段落索引（分段模式下使用）"),
|
|
db: AsyncSession = Depends(get_db),
|
|
):
|
|
service = AnnotationEditorService(db)
|
|
task = await service.get_task(project_id, file_id, segment_index=segment_index)
|
|
return StandardResponse(code=200, message="success", data=task)
|
|
|
|
|
|
@router.put(
|
|
"/projects/{project_id}/tasks/{file_id}/annotation",
|
|
response_model=StandardResponse[UpsertAnnotationResponse],
|
|
)
|
|
async def upsert_editor_annotation(
|
|
request: UpsertAnnotationRequest,
|
|
project_id: str = Path(..., description="标注项目ID（t_dm_labeling_projects.id）"),
|
|
file_id: str = Path(..., description="文件ID（t_dm_dataset_files.id）"),
|
|
db: AsyncSession = Depends(get_db),
|
|
):
|
|
service = AnnotationEditorService(db)
|
|
result = await service.upsert_annotation(project_id, file_id, request)
|
|
return StandardResponse(code=200, message="success", data=result)
|
|
|