Towards Automating Class-Splitting Using Betweenness Clustering

Abstract

Large, unwieldy classes are a significant maintenance problem. Programmers dislike them because the fundamental logic is often obscured, making them hard to understand and modify. This paper proposes a solution - a semi-automatic technique for splitting large classes into smaller, more cohesive ones. The core of the technique is the use of betweenness clustering to identify the best way of partitioning a class. This turned a tedious manual process into a quick and simple semi-automated one in roughly one third of the cases we examined.