q792602257/DataMate
0
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(annotation): 添加标注状态管理功能

Browse Source 
- 引入 AnnotationResultStatus 枚举类型区分已标注和无标注状态
- 在前端组件中实现空标注检测和确认对话框逻辑
- 添加数据库表字段 annotation_status 存储标注状态
- 扩展后端服务验证和处理标注状态逻辑
- 更新 API 接口支持标注状态参数传递
- 改进任务列表显示逻辑以反映不同标注状态
- 实现分段模式下的标注结果检查机制
This commit is contained in:
Jerry Yan
2026-01-31 13:23:38 +08:00
parent 52a2a73a8e
commit f4fc574687
6 changed files with 194 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
runtime/datamate-python/app/db/models/annotation_management.py
View File

@@ -2,11 +2,15 @@
import uuid
from sqlalchemy import Column, String, Boolean, TIMESTAMP, Text, Integer, JSON, ForeignKey, UniqueConstraint, Index
from sqlalchemy.sql import func
from app.db.session import Base
class AnnotationTemplate(Base):
from sqlalchemy.sql import func
from app.db.session import Base
ANNOTATION_STATUS_ANNOTATED = "ANNOTATED"
ANNOTATION_STATUS_NO_ANNOTATION = "NO_ANNOTATION"
ANNOTATION_STATUS_VALUES = {ANNOTATION_STATUS_ANNOTATED, ANNOTATION_STATUS_NO_ANNOTATION}
class AnnotationTemplate(Base):
"""标注配置模板模型"""
__tablename__ = "t_dm_annotation_templates"
@@ -84,12 +88,18 @@ class AnnotationResult(Base):
__tablename__ = "t_dm_annotation_results"
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
project_id = Column(String(36), nullable=False, comment="标注项目ID（t_dm_labeling_projects.id）")
file_id = Column(String(36), nullable=False, comment="文件ID（t_dm_dataset_files.id）")
annotation = Column(JSON, nullable=False, comment="Label Studio annotation 原始JSON（单人单份最终结果）")
created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
project_id = Column(String(36), nullable=False, comment="标注项目ID（t_dm_labeling_projects.id）")
file_id = Column(String(36), nullable=False, comment="文件ID（t_dm_dataset_files.id）")
annotation = Column(JSON, nullable=False, comment="Label Studio annotation 原始JSON（单人单份最终结果）")
annotation_status = Column(
String(32),
nullable=False,
default=ANNOTATION_STATUS_ANNOTATED,
comment="标注状态: ANNOTATED/NO_ANNOTATION",
)
created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
def __repr__(self):
return f"<AnnotationResult(id={self.id}, project_id={self.project_id}, file_id={self.file_id})>"

27
runtime/datamate-python/app/module/annotation/schema/editor.py
View File

@@ -9,10 +9,23 @@
from __future__ import annotations
from datetime import datetime
from enum import Enum
from typing import Any, Dict, List, Optional
from pydantic import BaseModel, Field, ConfigDict
from app.db.models.annotation_management import (
ANNOTATION_STATUS_ANNOTATED,
ANNOTATION_STATUS_NO_ANNOTATION,
)
class AnnotationStatus(str, Enum):
"""标注状态枚举"""
ANNOTATED = ANNOTATION_STATUS_ANNOTATED
NO_ANNOTATION = ANNOTATION_STATUS_NO_ANNOTATION
class EditorProjectInfo(BaseModel):
"""编辑器项目元信息"""
@@ -40,8 +53,13 @@ class EditorTaskListItem(BaseModel):
file_type: Optional[str] = Field(None, alias="fileType", description="文件类型")
has_annotation: bool = Field(..., alias="hasAnnotation", description="是否已有最终标注")
annotation_updated_at: Optional[datetime] = Field(None, alias="annotationUpdatedAt", description="标注更新时间")
annotation_status: Optional[AnnotationStatus] = Field(
None,
alias="annotationStatus",
description="标注状态",
)
model_config = ConfigDict(populate_by_name=True)
model_config = ConfigDict(populate_by_name=True, use_enum_values=True)
class EditorTaskListResponse(BaseModel):
@@ -89,6 +107,11 @@ class UpsertAnnotationRequest(BaseModel):
"""保存/覆盖最终标注（Label Studio annotation 原始对象）"""
annotation: Dict[str, Any] = Field(..., description="Label Studio annotation 对象（包含 result 等）")
annotation_status: Optional[AnnotationStatus] = Field(
None,
alias="annotationStatus",
description="标注状态（无标注/不适用时传 NO_ANNOTATION）",
)
expected_updated_at: Optional[datetime] = Field(
None,
alias="expectedUpdatedAt",
@@ -101,7 +124,7 @@ class UpsertAnnotationRequest(BaseModel):
description="段落索引（分段模式下必填）",
)
model_config = ConfigDict(populate_by_name=True)
model_config = ConfigDict(populate_by_name=True, use_enum_values=True)
class UpsertAnnotationResponse(BaseModel):

48
runtime/datamate-python/app/module/annotation/service/editor.py
View File

@@ -24,6 +24,11 @@ from sqlalchemy.ext.asyncio import AsyncSession
from app.core.config import settings
from app.core.logging import get_logger
from app.db.models import AnnotationResult, Dataset, DatasetFiles, LabelingProject, LabelingProjectFile
from app.db.models.annotation_management import (
ANNOTATION_STATUS_ANNOTATED,
ANNOTATION_STATUS_NO_ANNOTATION,
ANNOTATION_STATUS_VALUES,
)
from app.module.annotation.config import LabelStudioTagConfig
from app.module.annotation.schema.editor import (
EditorProjectInfo,
@@ -348,6 +353,24 @@ class AnnotationEditorService:
return ET.tostring(root, encoding="unicode")
@staticmethod
def _has_annotation_result(payload: Optional[Dict[str, Any]]) -> bool:
if not payload or not isinstance(payload, dict):
return False
if payload.get("segmented"):
segments = payload.get("segments", {})
if not isinstance(segments, dict):
return False
for segment in segments.values():
if not isinstance(segment, dict):
continue
result = segment.get("result")
if isinstance(result, list) and len(result) > 0:
return True
return False
result = payload.get("result")
return isinstance(result, list) and len(result) > 0
@classmethod
def _build_source_document_filter(cls):
file_type_lower = func.lower(DatasetFiles.file_type)
@@ -447,7 +470,12 @@ class AnnotationEditorService:
else_=0,
)
files_result = await self.db.execute(
select(DatasetFiles, AnnotationResult.id, AnnotationResult.updated_at)
select(
DatasetFiles,
AnnotationResult.id,
AnnotationResult.updated_at,
AnnotationResult.annotation_status,
)
.join(LabelingProjectFile, LabelingProjectFile.file_id == DatasetFiles.id)
.outerjoin(
AnnotationResult,
@@ -462,7 +490,7 @@ class AnnotationEditorService:
rows = files_result.all()
items: List[EditorTaskListItem] = []
for file_record, annotation_id, annotation_updated_at in rows:
for file_record, annotation_id, annotation_updated_at, annotation_status in rows:
fid = str(file_record.id) # type: ignore[arg-type]
items.append(
EditorTaskListItem(
@@ -471,6 +499,7 @@ class AnnotationEditorService:
fileType=getattr(file_record, "file_type", None),
hasAnnotation=annotation_id is not None,
annotationUpdatedAt=annotation_updated_at,
annotationStatus=annotation_status,
)
)
@@ -869,12 +898,26 @@ class AnnotationEditorService:
annotation_payload["id"] = self._make_ls_annotation_id(project_id, file_id)
final_payload = annotation_payload
requested_status = request.annotation_status
if requested_status is not None and requested_status not in ANNOTATION_STATUS_VALUES:
raise HTTPException(status_code=400, detail="annotationStatus 不合法")
has_result = self._has_annotation_result(final_payload)
if has_result:
final_status = ANNOTATION_STATUS_ANNOTATED
else:
if requested_status == ANNOTATION_STATUS_NO_ANNOTATION:
final_status = ANNOTATION_STATUS_NO_ANNOTATION
else:
raise HTTPException(status_code=400, detail="未发现标注内容，请确认无标注/不适用后再保存")
if existing:
if request.expected_updated_at and existing.updated_at:
if existing.updated_at != request.expected_updated_at.replace(tzinfo=None):
raise HTTPException(status_code=409, detail="标注已被更新，请刷新后重试")
existing.annotation = final_payload # type: ignore[assignment]
existing.annotation_status = final_status # type: ignore[assignment]
existing.updated_at = now # type: ignore[assignment]
await self.db.commit()
await self.db.refresh(existing)
@@ -892,6 +935,7 @@ class AnnotationEditorService:
project_id=project_id,
file_id=file_id,
annotation=final_payload,
annotation_status=final_status,
created_at=now,
updated_at=now,
)