feat(data-management): 实现数据集文件版本管理和内部路径保护

- 将数据集文件查询方法替换为只查询可见文件的版本
- 引入文件状态管理（ACTIVE/ARCHIVED）和内部目录结构
- 实现文件重复处理策略，支持版本控制模式而非覆盖
- 添加内部数据目录保护，防止访问.datamate等系统目录
- 重构文件上传流程，引入暂存目录和事务后清理机制
- 实现文件版本归档功能，保留历史版本到专用存储位置
- 优化文件路径规范化和安全验证逻辑
- 修复文件删除逻辑，确保归档文件不会被错误移除
- 更新数据集压缩下载功能以排除内部系统文件

backend/services/data-management-service/src/main/resources/mappers/DatasetFileMapper.xml

@@ -3,7 +3,7 @@
     "http://mybatis.org/dtd/mybatis-3-mapper.dtd">
 <mapper namespace="com.datamate.datamanagement.infrastructure.persistence.mapper.DatasetFileMapper">
     <sql id="Base_Column_List">
-      id, dataset_id, file_name, file_path, file_type, file_size, check_sum, tags, metadata, status,
+      id, dataset_id, file_name, file_path, logical_path, version, file_type, file_size, check_sum, tags, metadata, status,
           upload_time, last_access_time, created_at, updated_at
     </sql>
 
@@ -39,13 +39,17 @@
     </select>
 
     <select id="countByDatasetId" parameterType="string" resultType="long">
-        SELECT COUNT(*) FROM t_dm_dataset_files WHERE dataset_id = #{datasetId}
+        SELECT COUNT(*)
+        FROM t_dm_dataset_files
+        WHERE dataset_id = #{datasetId}
+          AND (status IS NULL OR status <> 'ARCHIVED')
     </select>
 
     <select id="countNonDerivedByDatasetId" parameterType="string" resultType="long">
         SELECT COUNT(*)
         FROM t_dm_dataset_files
         WHERE dataset_id = #{datasetId}
+          AND (status IS NULL OR status <> 'ARCHIVED')
           AND (metadata IS NULL OR JSON_EXTRACT(metadata, '$.derived_from_file_id') IS NULL)
     </select>
 
@@ -54,13 +58,19 @@
     </select>
 
     <select id="sumSizeByDatasetId" parameterType="string" resultType="long">
-        SELECT COALESCE(SUM(file_size), 0) FROM t_dm_dataset_files WHERE dataset_id = #{datasetId}
+        SELECT COALESCE(SUM(file_size), 0)
+        FROM t_dm_dataset_files
+        WHERE dataset_id = #{datasetId}
+          AND (status IS NULL OR status <> 'ARCHIVED')
     </select>
 
   <select id="findByDatasetIdAndFileName" resultType="com.datamate.datamanagement.domain.model.dataset.DatasetFile">
         SELECT <include refid="Base_Column_List"/>
         FROM t_dm_dataset_files
-        WHERE dataset_id = #{datasetId} AND file_name = #{fileName}
+        WHERE dataset_id = #{datasetId}
+          AND file_name = #{fileName}
+          AND (status IS NULL OR status <> 'ARCHIVED')
+        ORDER BY version DESC, upload_time DESC
         LIMIT 1
     </select>
 
@@ -91,6 +101,8 @@
         UPDATE t_dm_dataset_files
         SET file_name = #{fileName},
             file_path = #{filePath},
+            logical_path = #{logicalPath},
+            version = #{version},
             file_type = #{fileType},
             file_size = #{fileSize},
             upload_time = #{uploadTime},
@@ -126,6 +138,7 @@
         <foreach collection="datasetIds" item="datasetId" open="(" separator="," close=")">
             #{datasetId}
         </foreach>
+          AND (status IS NULL OR status <> 'ARCHIVED')
           AND (metadata IS NULL OR JSON_EXTRACT(metadata, '$.derived_from_file_id') IS NULL)
         GROUP BY dataset_id
     </select>