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

runtime/python-executor/datamate/sql_manager/sql/sql_config.json

@@ -1,9 +1,9 @@
 {
   "query_sql": "SELECT * FROM t_task_instance_info WHERE instance_id IN (:instance_id)",
   "insert_sql": "INSERT INTO t_task_instance_info (instance_id, meta_file_name, meta_file_type, meta_file_id, meta_file_size, file_id, file_size, file_type, file_name, file_path, status, operator_id, error_code, incremental, child_id, slice_num) VALUES (:instance_id, :meta_file_name, :meta_file_type, :meta_file_id, :meta_file_size, :file_id, :file_size, :file_type, :file_name, :file_path, :status, :operator_id, :error_code, :incremental, :child_id, :slice_num)",
-  "insert_dataset_file_sql": "INSERT INTO t_dm_dataset_files (id, dataset_id, file_name, file_path, file_type, file_size, status, upload_time, last_access_time, created_at, updated_at) VALUES (:id, :dataset_id, :file_name, :file_path, :file_type, :file_size, :status, :upload_time, :last_access_time, :created_at, :updated_at)",
+  "insert_dataset_file_sql": "INSERT INTO t_dm_dataset_files (id, dataset_id, file_name, file_path, logical_path, version, file_type, file_size, status, upload_time, last_access_time, created_at, updated_at) VALUES (:id, :dataset_id, :file_name, :file_path, :logical_path, :version, :file_type, :file_size, :status, :upload_time, :last_access_time, :created_at, :updated_at)",
   "insert_clean_result_sql": "INSERT INTO t_clean_result (instance_id, src_file_id, dest_file_id, src_name, dest_name, src_type, dest_type, src_size, dest_size, status, result) VALUES (:instance_id, :src_file_id, :dest_file_id, :src_name, :dest_name, :src_type, :dest_type, :src_size, :dest_size, :status, :result)",
-  "query_dataset_sql": "SELECT file_size FROM t_dm_dataset_files WHERE dataset_id = :dataset_id",
+  "query_dataset_sql": "SELECT file_size FROM t_dm_dataset_files WHERE dataset_id = :dataset_id AND (status IS NULL OR status <> 'ARCHIVED')",
   "update_dataset_sql": "UPDATE t_dm_datasets SET size_bytes = :total_size, file_count = :file_count WHERE id = :dataset_id;",
   "update_task_sql": "UPDATE t_clean_task SET status = :status, after_size = :total_size, finished_at = :finished_time WHERE id = :task_id",
   "create_tables_sql": "CREATE TABLE IF NOT EXISTS t_task_instance_info (instance_id VARCHAR(255), meta_file_name TEXT, meta_file_type VARCHAR(100), meta_file_id BIGINT, meta_file_size VARCHAR(100), file_id BIGINT, file_size VARCHAR(100), file_type VARCHAR(100), file_name TEXT, file_path TEXT, status INT, operator_id VARCHAR(255), error_code VARCHAR(100), incremental VARCHAR(50), child_id BIGINT, slice_num INT DEFAULT 0);",
@@ -14,4 +14,4 @@
   "delete_similar_img_tables_sql": "DELETE FROM operator_similar_img_features WHERE flow_id = :flow_id",
   "create_similar_text_tables_sql": "CREATE TABLE IF NOT EXISTS operators_similar_text_features (id INT AUTO_INCREMENT PRIMARY KEY, task_uuid VARCHAR(255),file_feature TEXT,file_name TEXT,timestamp DATETIME);",
   "delete_similar_text_tables_sql": "DELETE FROM operators_similar_text_features WHERE flow_id = :flow_id"
-}
+}