An Empirical Study of Bugs in Eclipse Stable Internal Interfaces

Abstract

The Eclipse framework is a popular and widely used framework that has been evolving for over a decade. The framework provides both stable interfaces (APIs) and unstable interfaces (non-APIs). Despite being discouraged by Eclipse; application developers often use non-APIs which cause their systems to fail when ported to new framework releases. Previous studies showed that applications using relatively old non-APIs are more likely to be compatible with new releases compared to the ones that used newly introduced non-APIs. Furthermore, from our previous study about the stability of Eclipse internal interfaces, we discovered that there exist 327K stable non-API methods as the Eclipse framework evolves. In the same study, we recommended that 327K stable non-API methods can be used by Eclipse interface providers as possible candidates for promotion to stable interfaces. However, since non-APIs are unsupported and considered to be immature i.e. can contain bugs, to this end there exist a need to first investigate the stable non-APIs for possible bugs before they can be promoted to APIs. In this study, we empirically investigated the stable non-API for possible bugs using Sonarqube software quality tool. We discovered that over 79:8% classes containing old stable non-APIs methods have zero bugs. These results can be used by both interface providers and users as a starting point to analyze which interfaces are well tested and also estimate how much work could be involved when performing bug fixing for a given eclipse release.