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

Author: JasonW404

runtime/label-studio-adapter/.env.example runtime/datamate-python/.env.exampleruntime/label-studio-adapter/.env.example renamed to runtime/datamate-python/.env.example

@@ -53,9 +53,6 @@ LS_TASK_PAGE_SIZE=1000
 # =========================
 # Data Management 服务配置
 # =========================
-# DM 服务地址
-DM_SERVICE_BASE_URL=http://data-engine:8080
-
 # DM 存储文件夹前缀（通常与 Label Studio 的 local-files 文件夹映射一致）
 DM_FILE_PATH_PREFIX=/
 

runtime/label-studio-adapter/.gitignore runtime/datamate-python/.gitignoreruntime/label-studio-adapter/.gitignore renamed to runtime/datamate-python/.gitignore

@@ -0,0 +1,86 @@
+# Label Studio Adapter (DataMate)
+
+这是 DataMate 的 Label Studio Adapter 服务，负责将 DataMate 的项目与 Label Studio 同步并提供对外的 HTTP API（基于 FastAPI）。
+
+## 简要说明
+
+- 框架：FastAPI
+- 异步数据库/ORM：SQLAlchemy (async)
+- 数据库迁移：Alembic
+- 运行器：uvicorn
+
+## 快速开始（开发）
+
+1. 克隆仓库并进入项目目录
+2. 创建并激活虚拟环境：
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+```
+
+3. 安装依赖：
+
+```bash
+pip install -r requirements.txt
+```
+
+4. 准备环境变量（示例）
+
+创建 `.env` 并设置必要的变量，例如：
+
+- DATABASE_URL（或根据项目配置使用具体变量）
+- LABEL_STUDIO_BASE_URL
+- LABEL_STUDIO_USER_TOKEN
+
+（具体变量请参考 `.env.example`）
+
+5. 数据库迁移（开发环境）：
+
+```bash
+alembic upgrade head
+```
+
+6. 启动开发服务器（示例与常用参数）：
+
+- 本地开发（默认 host/port，自动重载）：
+
+```bash
+uvicorn app.main:app --reload
+```
+
+- 指定主机与端口并打开调试日志：
+
+```bash
+uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload --log-level debug
+```
+
+- 在生产环境使用多个 worker（不使用 --reload）：
+
+```bash
+uvicorn app.main:app --host 0.0.0.0 --port 8000 --workers 4 --log-level info --proxy-headers
+```
+
+- 使用环境变量启动（示例）：
+
+```bash
+HOST=0.0.0.0 PORT=8000 uvicorn app.main:app --reload
+```
+
+注意：
+
+- `--reload` 仅用于开发，会监视文件变化并重启进程；不要在生产中使用。
+- `--workers` 提供并发处理能力，但会增加内存占用；生产时通常配合进程管理或容器编排（Kubernetes）使用。
+- 若需要完整的生产部署建议使用 ASGI 服务器（如 gunicorn + uvicorn workers / 或直接使用 uvicorn 在容器中配合进程管理）。
+
+访问 API 文档：
+
+- Swagger UI: http://127.0.0.1:8000/docs
+- ReDoc: http://127.0.0.1:8000/redoc （推荐使用）
+
+## 使用（简要）
+
+- 所有 API 路径以 `/api` 前缀注册（见 `app/main.py` 中 `app.include_router(api_router, prefix="/api")`）。
+- 根路径 `/` 返回服务信息和文档链接。
+
+更多细节请查看 `doc/usage.md`（接口使用）和 `doc/development.md`（开发说明）。

runtime/datamate-python/README.md

@@ -4,7 +4,7 @@
 
 from app.db.database import get_db
 from app.services.dataset_mapping_service import DatasetMappingService
-from app.clients import get_clients
+from app.infrastructure import DatamateClient, LabelStudioClient
 from app.schemas.dataset_mapping import (
     DatasetMappingCreateRequest,
     DatasetMappingCreateResponse,
@@ -30,18 +30,19 @@ async def create_dataset_mapping(
     注意：一个数据集可以创建多个标注项目
     """
     try:
-        # 获取全局客户端实例
-        dm_client_instance, ls_client_instance = get_clients()
+        dm_client = DatamateClient(db)
+        ls_client = LabelStudioClient(base_url=settings.label_studio_base_url,
+                                      token=settings.label_studio_user_token)
         service = DatasetMappingService(db)
 
-        logger.info(f"Create dataset mapping request: {request.source_dataset_id}")
+        logger.info(f"Create dataset mapping request: {request.dataset_id}")
 
         # 从DM服务获取数据集信息
-        dataset_info = await dm_client_instance.get_dataset(request.source_dataset_id)
+        dataset_info = await dm_client.get_dataset(request.dataset_id)
         if not dataset_info:
             raise HTTPException(
                 status_code=404,
-                detail=f"Dataset not found in DM service: {request.source_dataset_id}"
+                detail=f"Dataset not found in DM service: {request.dataset_id}"
             )
 
         # 确定数据类型（基于数据集类型）
@@ -55,11 +56,10 @@ async def create_dataset_mapping(
             elif "text" in type_code:
                 data_type = "text"
 
-        # 生成项目名称
         project_name = f"{dataset_info.name}"
 
         # 在Label Studio中创建项目
-        project_data = await ls_client_instance.create_project(
+        project_data = await ls_client.create_project(
             title=project_name,
             description=dataset_info.description or f"Imported from DM dataset {dataset_info.id}",
             data_type=data_type
@@ -74,8 +74,8 @@ async def create_dataset_mapping(
         project_id = project_data["id"]
 
         # 配置本地存储：dataset/<id>
-        local_storage_path = f"{settings.label_studio_local_storage_dataset_base_path}/{request.source_dataset_id}"
-        storage_result = await ls_client_instance.create_local_storage(
+        local_storage_path = f"{settings.label_studio_local_storage_dataset_base_path}/{request.dataset_id}"
+        storage_result = await ls_client.create_local_storage(
             project_id=project_id,
             path=local_storage_path,
             title="Dataset_BLOB",
@@ -85,7 +85,7 @@ async def create_dataset_mapping(
 
         # 配置本地存储：upload
         local_storage_path = f"{settings.label_studio_local_storage_upload_base_path}"
-        storage_result = await ls_client_instance.create_local_storage(
+        storage_result = await ls_client.create_local_storage(
             project_id=project_id,
             path=local_storage_path,
             title="Upload_BLOB",
@@ -107,7 +107,7 @@ async def create_dataset_mapping(
         )
 
         logger.debug(
-            f"Dataset mapping created: {mapping.mapping_id} -> S {mapping.source_dataset_id} <> L {mapping.labelling_project_id}"
+            f"Dataset mapping created: {mapping.mapping_id} -> S {mapping.dataset_id} <> L {mapping.labelling_project_id}"
         )
 
         response_data = DatasetMappingCreateResponse(

…ime/label-studio-adapter/app/__init__.py runtime/datamate-python/app/__init__.pyruntime/label-studio-adapter/app/__init__.py renamed to runtime/datamate-python/app/__init__.py runtime/label-studio-adapter/app/__init__.py renamed to runtime/datamate-python/app/__init__.py

@@ -1,13 +1,15 @@
-from fastapi import APIRouter, Depends, HTTPException, Query
+from fastapi import Depends, HTTPException, Query
 from sqlalchemy.ext.asyncio import AsyncSession
 from typing import Optional
 
 from app.db.database import get_db
 from app.services.dataset_mapping_service import DatasetMappingService
-from app.clients import get_clients
+from app.infrastructure import DatamateClient, LabelStudioClient
 from app.schemas.dataset_mapping import DeleteDatasetResponse
 from app.schemas import StandardResponse
 from app.core.logging import get_logger
+from app.core.config import settings
+
 from . import project_router
 
 logger = get_logger(__name__)
@@ -37,39 +39,39 @@ async def delete_mapping(
                 status_code=400,
                 detail="Either 'm' (mapping UUID) or 'proj' (project ID) must be provided"
             )
-        
-        # 获取全局客户端实例
-        dm_client_instance, ls_client_instance = get_clients()
+
+        ls_client = LabelStudioClient(base_url=settings.label_studio_base_url,
+                                      token=settings.label_studio_user_token)
         service = DatasetMappingService(db)
 
-        mapping = None
-        
         # 优先使用 mapping_id 查询
         if m:
-            logger.info(f"Deleting by mapping UUID: {m}")
+            logger.debug(f"Deleting by mapping UUID: {m}")
             mapping = await service.get_mapping_by_uuid(m)
         # 如果没有提供 m，使用 proj 查询
         elif proj:
-            logger.info(f"Deleting by project ID: {proj}")
+            logger.debug(f"Deleting by project ID: {proj}")
             mapping = await service.get_mapping_by_labelling_project_id(proj)
+        else:
+            mapping = None
 
         if not mapping:
             raise HTTPException(
                 status_code=404,
-                detail=f"Mapping not found"
+                detail=f"Mapping either not found or not specified."
             )
 
         mapping_id = mapping.mapping_id
         labelling_project_id = mapping.labelling_project_id
         labelling_project_name = mapping.labelling_project_name
 
-        logger.info(f"Found mapping: {mapping_id}, Label Studio project ID: {labelling_project_id}")
+        logger.debug(f"Found mapping: {mapping_id}, Label Studio project ID: {labelling_project_id}")
 
         # 1. 删除 Label Studio 项目
         try:
-            delete_success = await ls_client_instance.delete_project(int(labelling_project_id))
+            delete_success = await ls_client.delete_project(int(labelling_project_id))
             if delete_success:
-                logger.info(f"Successfully deleted Label Studio project: {labelling_project_id}")
+                logger.debug(f"Successfully deleted Label Studio project: {labelling_project_id}")
             else:
                 logger.warning(f"Failed to delete Label Studio project or project not found: {labelling_project_id}")
         except Exception as e:
@@ -84,19 +86,17 @@ async def delete_mapping(
                 status_code=500,
                 detail="Failed to delete mapping record"
             )
-        
-        logger.info(f"Successfully deleted mapping: {mapping_id}")
-        
-        response_data = DeleteDatasetResponse(
-            mapping_id=mapping_id,
-            status="success",
-            message=f"Successfully deleted mapping and Label Studio project '{labelling_project_name}'"
-        )
-        
+
+        logger.info(f"Successfully deleted mapping: {mapping_id}, Label Studio project: {labelling_project_id}")
+
         return StandardResponse(
             code=200,
             message="success",
-            data=response_data
+            data=DeleteDatasetResponse(
+                mapping_id=mapping_id,
+                status="success",
+                message=f"Successfully deleted mapping and Label Studio project '{labelling_project_name}'"
+            )
         )
 
     except HTTPException:

…label-studio-adapter/app/api/__init__.py …time/datamate-python/app/api/__init__.pyruntime/label-studio-adapter/app/api/__init__.py renamed to runtime/datamate-python/app/api/__init__.py runtime/label-studio-adapter/app/api/__init__.py renamed to runtime/datamate-python/app/api/__init__.py

@@ -98,9 +98,9 @@ async def get_mapping(
         raise HTTPException(status_code=500, detail="Internal server error")
 
 
-@project_router.get("/mappings/by-source/{source_dataset_id}", response_model=StandardResponse[PaginatedData[DatasetMappingResponse]])
+@project_router.get("/mappings/by-source/{dataset_id}", response_model=StandardResponse[PaginatedData[DatasetMappingResponse]])
 async def get_mappings_by_source(
-    source_dataset_id: str,
+    dataset_id: str,
     page: int = Query(1, ge=1, description="页码（从1开始）"),
     page_size: int = Query(20, ge=1, le=100, description="每页记录数"),
     db: AsyncSession = Depends(get_db)
@@ -116,11 +116,11 @@ async def get_mappings_by_source(
         # 计算 skip
         skip = (page - 1) * page_size
 
-        logger.info(f"Get mappings by source dataset id: {source_dataset_id}, page={page}, page_size={page_size}")
+        logger.info(f"Get mappings by source dataset id: {dataset_id}, page={page}, page_size={page_size}")
 
         # 获取数据和总数
         mappings, total = await service.get_mappings_by_source_with_count(
-            source_dataset_id=source_dataset_id,
+            dataset_id=dataset_id,
             skip=skip,
             limit=page_size
         )

…udio-adapter/app/api/project/__init__.py …amate-python/app/api/project/__init__.pyruntime/label-studio-adapter/app/api/project/__init__.py renamed to runtime/datamate-python/app/api/project/__init__.py runtime/label-studio-adapter/app/api/project/__init__.py renamed to runtime/datamate-python/app/api/project/__init__.py

@@ -5,7 +5,7 @@
 from app.db.database import get_db
 from app.services.dataset_mapping_service import DatasetMappingService
 from app.services.sync_service import SyncService
-from app.clients import get_clients
+from app.infrastructure import DatamateClient, LabelStudioClient
 from app.exceptions import NoDatasetInfoFoundError, DatasetMappingNotFoundError
 from app.schemas.dataset_mapping import (
     DatasetMappingResponse,
@@ -14,6 +14,7 @@
 )
 from app.schemas import StandardResponse
 from app.core.logging import get_logger
+from app.core.config import settings
 from . import project_router
 
 logger = get_logger(__name__)
@@ -30,10 +31,12 @@ async def sync_dataset_content(
     在数据库中记录更新时间，返回更新状态
     """
     try:
-        dm_client_instance, ls_client_instance = get_clients()
+        ls_client = LabelStudioClient(base_url=settings.label_studio_base_url,
+                                      token=settings.label_studio_user_token)
+        dm_client = DatamateClient(db)
         mapping_service = DatasetMappingService(db)
-        sync_service = SyncService(dm_client_instance, ls_client_instance, mapping_service)
-        
+        sync_service = SyncService(dm_client, ls_client, mapping_service)
+
         logger.info(f"Sync dataset content request: mapping_id={request.mapping_id}")
 
         # 根据 mapping_id 获取映射关系