Detecting increases in feature coupling using regression tests

Repeated changes to a software system can introduce small weaknesses such as unplanned dependencies between different parts of the system. While such problems usually go undetected, their cumulative effect can result in a noticeable decrease in the quality of a system. We present an approach to warn developers about increased coupling between the (potentially scattered) implementation of different features. Our automated approach can detect sections of the source code contributing to the increased coupling as soon as software changes are tested. Developers can then inspect the results to assess whether the quality of their changes is adequate. We have implemented our approach for C++ and integrated it with the development process of a proprietary 3D graphics software. We report on our evaluation of the approach in the field, and on a study showing that, for files in the target system, causing increases in feature coupling is a significant predictor of future modifications due to bug fixes.