Develop labeling module (#25)

* refactor: remove db table management from LS adapter (mv to scripts later); change adapter to use the same MySQL DB as other modules.

* refactor: Rename LS Adapter module to datamate-python

runtime/datamate-python/app/schemas/__init__.py

@@ -0,0 +1,29 @@
+# app/schemas/__init__.py
+
+from .common import *
+from .dataset_mapping import *
+from .dm_service import *
+from .label_studio import *
+
+__all__ = [
+    # Common schemas
+    "StandardResponse",
+    
+    # Dataset Mapping schemas
+    "DatasetMappingBase",
+    "DatasetMappingCreateRequest", 
+    "DatasetMappingUpdateRequest",
+    "DatasetMappingResponse",
+    "DatasetMappingCreateResponse",
+    "SyncDatasetResponse", 
+    "DeleteDatasetResponse",
+    
+    # DM Service schemas
+    "DatasetFileResponse",
+    "PagedDatasetFileResponse", 
+    "DatasetResponse",
+    
+    # Label Studio schemas
+    "LabelStudioProject",
+    "LabelStudioTask"
+]

runtime/datamate-python/app/schemas/common.py

@@ -0,0 +1,63 @@
+"""
+通用响应模型
+"""
+from typing import Generic, TypeVar, Optional, List
+from pydantic import BaseModel, Field
+
+# 定义泛型类型变量
+T = TypeVar('T')
+
+# 定义一个将 snake_case 转换为 camelCase 的函数
+def to_camel(string: str) -> str:
+    """将 snake_case 字符串转换为 camelCase"""
+    components = string.split('_')
+    # 首字母小写，其余单词首字母大写
+    return components[0] + ''.join(x.title() for x in components[1:])
+
+class BaseResponseModel(BaseModel):
+    """基础响应模型，启用别名生成器"""
+    
+    class Config:
+        populate_by_name = True
+        alias_generator = to_camel
+
+class StandardResponse(BaseResponseModel, Generic[T]):
+    """
+    标准API响应格式
+    
+    所有API端点应返回此格式，确保响应的一致性
+    """
+    code: int = Field(..., description="HTTP状态码")
+    message: str = Field(..., description="响应消息")
+    data: Optional[T] = Field(None, description="响应数据")
+    
+    class Config:
+        populate_by_name = True
+        alias_generator = to_camel
+        json_schema_extra = {
+            "example": {
+                "code": 200,
+                "message": "success",
+                "data": {}
+            }
+        }
+
+
+class PaginatedData(BaseResponseModel, Generic[T]):
+    """分页数据容器"""
+    page: int = Field(..., description="当前页码（从1开始）")
+    size: int = Field(..., description="页大小")
+    total_elements: int = Field(..., description="总条数")
+    total_pages: int = Field(..., description="总页数")
+    content: List[T] = Field(..., description="当前页数据")
+    
+    class Config:
+        json_schema_extra = {
+            "example": {
+                "page": 1,
+                "size": 20,
+                "totalElements": 100,
+                "totalPages": 5,
+                "content": []
+            }
+        }

runtime/datamate-python/app/schemas/dataset_mapping.py

@@ -0,0 +1,56 @@
+from pydantic import Field
+from typing import Optional
+from datetime import datetime
+
+from .common import BaseResponseModel
+
+class DatasetMappingBase(BaseResponseModel):
+    """数据集映射 基础模型"""
+    dataset_id: str = Field(..., description="源数据集ID")
+
+class DatasetMappingCreateRequest(DatasetMappingBase):
+    """数据集映射 创建 请求模型"""
+    pass
+
+class DatasetMappingCreateResponse(BaseResponseModel):
+    """数据集映射 创建 响应模型"""
+    mapping_id: str = Field(..., description="映射UUID")
+    labelling_project_id: str = Field(..., description="Label Studio项目ID")
+    labelling_project_name: str = Field(..., description="Label Studio项目名称")
+    message: str = Field(..., description="响应消息")
+
+class DatasetMappingUpdateRequest(BaseResponseModel):
+    """数据集映射 更新 请求模型"""
+    dataset_id: Optional[str] = Field(None, description="源数据集ID")
+
+class DatasetMappingResponse(DatasetMappingBase):
+    """数据集映射 查询 响应模型"""
+    mapping_id: str = Field(..., description="映射UUID")
+    labelling_project_id: str = Field(..., description="标注项目ID")
+    labelling_project_name: Optional[str] = Field(None, description="标注项目名称")
+    created_at: datetime = Field(..., description="创建时间")
+    last_updated_at: datetime = Field(..., description="最后更新时间")
+    deleted_at: Optional[datetime] = Field(None, description="删除时间")
+    
+    class Config:
+        from_attributes = True
+        populate_by_name = True
+
+class SyncDatasetRequest(BaseResponseModel):
+    """同步数据集请求模型"""
+    mapping_id: str = Field(..., description="映射ID（mapping UUID）")
+    batch_size: int = Field(50, ge=1, le=100, description="批处理大小")
+
+class SyncDatasetResponse(BaseResponseModel):
+    """同步数据集响应模型"""
+    mapping_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 DeleteDatasetResponse(BaseResponseModel):
+    """删除数据集响应模型"""
+    mapping_id: str = Field(..., description="映射UUID")
+    status: str = Field(..., description="删除状态")
+    message: str = Field(..., description="响应消息")

runtime/datamate-python/app/schemas/dm_service.py

@@ -0,0 +1,58 @@
+from pydantic import BaseModel, Field
+from typing import List, Optional, Dict, Any
+from datetime import datetime
+
+class DatasetFileResponse(BaseModel):
+    """DM服务数据集文件响应模型"""
+    id: str = Field(..., description="文件ID")
+    fileName: str = Field(..., description="文件名")
+    fileType: str = Field(..., description="文件类型")
+    filePath: str = Field(..., description="文件路径")
+    originalName: Optional[str] = Field(None, description="原始文件名")
+    size: Optional[int] = Field(None, description="文件大小（字节）")
+    status: Optional[str] = Field(None, description="文件状态")
+    uploadedAt: Optional[datetime] = Field(None, description="上传时间")
+    description: Optional[str] = Field(None, description="文件描述")
+    uploadedBy: Optional[str] = Field(None, description="上传者")
+    lastAccessTime: Optional[datetime] = Field(None, description="最后访问时间")
+
+class PagedDatasetFileResponse(BaseModel):
+    """DM服务分页文件响应模型"""
+    content: List[DatasetFileResponse] = Field(..., description="文件列表")
+    totalElements: int = Field(..., description="总元素数")
+    totalPages: int = Field(..., description="总页数")
+    page: int = Field(..., description="当前页码")
+    size: int = Field(..., description="每页大小")
+    
+class DatasetTypeResponse(BaseModel):
+    """数据集类型响应模型"""
+    code: str = Field(..., description="类型编码")
+    name: str = Field(..., description="类型名称")
+    description: Optional[str] = Field(None, description="类型描述")
+    supportedFormats: List[str] = Field(default_factory=list, description="支持的文件格式")
+    icon: Optional[str] = Field(None, description="图标")
+
+class DatasetResponse(BaseModel):
+    """DM服务数据集响应模型"""
+    id: str = Field(..., description="数据集ID")
+    name: str = Field(..., description="数据集名称")
+    description: Optional[str] = Field(None, description="数据集描述")
+    datasetType: str = Field(..., description="数据集类型", alias="datasetType")
+    status: str = Field(..., description="数据集状态")
+    fileCount: int = Field(..., description="文件数量")
+    totalSize: int = Field(..., description="总大小（字节）")
+    createdAt: Optional[datetime] = Field(None, description="创建时间")
+    updatedAt: Optional[datetime] = Field(None, description="更新时间")
+    createdBy: Optional[str] = Field(None, description="创建者")
+    
+    # 为了向后兼容，添加一个属性方法返回类型对象
+    @property
+    def type(self) -> DatasetTypeResponse:
+        """兼容属性：返回类型对象"""
+        return DatasetTypeResponse(
+            code=self.datasetType,
+            name=self.datasetType,
+            description=None,
+            supportedFormats=[],
+            icon=None
+        )

runtime/datamate-python/app/schemas/label_studio.py

@@ -0,0 +1,38 @@
+from pydantic import Field
+from typing import Dict, Any, Optional, List
+from datetime import datetime
+from .common import BaseResponseModel
+
+class LabelStudioProject(BaseResponseModel):
+    """Label Studio项目模型"""
+    id: int = Field(..., description="项目ID")
+    title: str = Field(..., description="项目标题")
+    description: Optional[str] = Field(None, description="项目描述")
+    label_config: str = Field(..., description="标注配置")
+    created_at: Optional[datetime] = Field(None, description="创建时间")
+    updated_at: Optional[datetime] = Field(None, description="更新时间")
+
+class LabelStudioTaskData(BaseResponseModel):
+    """Label Studio任务数据模型"""
+    image: Optional[str] = Field(None, description="图像URL")
+    text: Optional[str] = Field(None, description="文本内容")
+    audio: Optional[str] = Field(None, description="音频URL")
+    video: Optional[str] = Field(None, description="视频URL")
+    filename: Optional[str] = Field(None, description="文件名")
+
+class LabelStudioTask(BaseResponseModel):
+    """Label Studio任务模型"""
+    data: LabelStudioTaskData = Field(..., description="任务数据")
+    project: Optional[int] = Field(None, description="项目ID")
+    meta: Optional[Dict[str, Any]] = Field(None, description="元数据")
+
+class LabelStudioCreateProjectRequest(BaseResponseModel):
+    """创建Label Studio项目请求模型"""
+    title: str = Field(..., description="项目标题")
+    description: str = Field("", description="项目描述")
+    label_config: str = Field(..., description="标注配置")
+    
+class LabelStudioCreateTaskRequest(BaseResponseModel):
+    """创建Label Studio任务请求模型"""
+    data: Dict[str, Any] = Field(..., description="任务数据")
+    project: Optional[int] = Field(None, description="项目ID")