Flexible design pattern detection based on feature types

Abstract

Accurately recovered design patterns support development related tasks like program comprehension and reengineering. Researchers proposed a variety of recognition approaches already. Though, much progress was made, there is still a lack of accuracy and flexibility in recognition. A major problem is the large variety of variants for implementing the same pattern. Furthermore, the integration of multiple search techniques is required to provide more accurate and effective pattern detection. In this paper, we propose variable pattern definitions composed of reusable feature types. Each feature type is assigned to one of multiple search techniques that is best fitting for its detection. A prototype implementation was applied to three open source applications. For each system a baseline was determined and used for comparison with the results of previous techniques. We reached very good results with an improved pattern catalog, but also demonstrated the necessity for customizations on new inspected systems. These results demonstrate the importance of customizable pattern definitions and multiple search techniques in order to overcome accuracy and flexibility issues of previous approaches.