A simple C++ library for manipulating scientific data sets as structured data

TL;DR

This paper introduces a straightforward C++ library for creating and accessing structured scientific data files, facilitating easier interpretation and manipulation of complex data without heavy dependencies.

Contribution

It presents a simple, flexible C++ library enabling structured data storage and access, supporting complex data types and extensions like late binding and persistence.

Findings

Supports complex data structures like arrays and unions

Enables efficient data access without specialized routines

Suitable for applications like molecular dynamics simulations

Abstract

Representing scientific data sets efficiently on external storage usually involves converting them to a byte string representation using specialized reader/writer routines. The resulting storage files are frequently difficult to interpret without these specialized routines as they do not contain information about the logical structure of the data. Avoiding such problems usually involves heavy-weight data format libraries or data base systems. We present a simple C++ library that allows to create and access data files that store structured data. The structure of the data is described by a data type that can be built from elementary data types (integer and floating-point numbers, byte strings) and composite data types (arrays, structures, unions). An abstract data access class presents the data to the application. Different actual data file structures can be implemented under this layer. This method is particularly suited to applications that require complex data structures, e.g. molecular dynamics simulations. Extensions such as late type binding and object persistence are discussed.