fix: 完善数据预处理与 JSON 上传链路

backend/app/modules/data_process/storage.py

@@ -137,6 +137,67 @@ class LocalDataProcessStorage:
         self._issued_staged_objects[temporary_path] = staged
         return staged
 
+    def stage_copy(
+        self,
+        *,
+        batch_id: str,
+        source_reference: str,
+        expected_source_task_id: str,
+        expected_source_file_id: str,
+        task_id: str,
+        source_file_id: str,
+        version: int,
+        name: str,
+    ) -> StagedSourceObject:
+        """为不可变源对象创建独立目录项，不把大文件重新读入内存。"""
+
+        batch_id = _safe_component(batch_id, "batch id")
+        task_id = _safe_component(task_id, "task id")
+        source_file_id = _safe_component(source_file_id, "source file id")
+        if isinstance(version, bool) or not isinstance(version, int) or version < 1:
+            raise DataProcessStorageError("invalid source file version")
+        basename = _safe_basename(name)
+        source_relative = self._relative_from_reference(source_reference)
+        if source_relative is None:
+            raise DataProcessStorageError("original source object is not available")
+        self._assert_expected_owner(
+            source_relative,
+            expected_task_id=expected_source_task_id,
+            expected_source_file_id=expected_source_file_id,
+        )
+        descriptor, source_info = self._open_read_descriptor(source_relative)
+        os.close(descriptor)
+
+        batch_directory = self._ensure_directory(self._root / ".staging" / batch_id)
+        temporary_path = batch_directory / f"{source_file_id}-{uuid.uuid4().hex}.tmp"
+        source_path = self._path_for_relative(source_relative)
+        try:
+            os.link(source_path, temporary_path, follow_symlinks=False)
+            copy_info = temporary_path.lstat()
+            if (
+                not stat.S_ISREG(copy_info.st_mode)
+                or source_info.st_dev != copy_info.st_dev
+                or source_info.st_ino != copy_info.st_ino
+            ):
+                raise DataProcessStorageError("source storage object changed while copying")
+        except Exception:
+            temporary_path.unlink(missing_ok=True)
+            raise
+
+        relative_path = PurePosixPath(
+            task_id,
+            source_file_id,
+            f"v{version}",
+            basename,
+        )
+        reference = (
+            "local://data-process/"
+            f"{task_id}/{source_file_id}/v{version}/{quote(basename, safe='')}"
+        )
+        staged = StagedSourceObject(reference, temporary_path, relative_path)
+        self._issued_staged_objects[temporary_path] = staged
+        return staged
+
     def publish(self, objects: Iterable[StagedSourceObject]) -> None:
         staged = list(objects)
         published: list[StagedSourceObject] = []