Reverse engineering feature models

Abstract

Feature models describe the common and variable characteristics of a product line. Their advantages are well recognized in product line methods. Unfortunately, creating a feature model for an existing project is time-consuming and requires substantial effort from a modeler. We present procedures for reverse engineering feature models based on a crucial heuristic for identifying parents - the major challenge of this task. We also automatically recover constructs such as feature groups, mandatory features, and implies/excludes edges. We evaluate the technique on two large-scale software product lines with existing reference feature models--the Linux and eCos kernels--and FreeBSD, a project without a feature model. Our heuristic is effective across all three projects by ranking the correct parent among the top results for a vast majority of features. The procedures effectively reduce the information a modeler has to consider from thousands of choices to typically five or less.