Summarizing Semantic Model Differences
Fundamental building blocks for managing and understanding software evolution in the context of model-driven engineering are differencing operators one can use for model comparisons. Semantic model differencing deals with the definition and computation of semantic diff operators for model comparison, operators whose input consists of two models and whose output is a set of diff witnesses, instances of one model that are not instances of the other. However, in many cases the complete set of diff witnesses is too large to be efficiently computed and effectively presented. Moreover, many of the witnesses are very similar and hence not interesting. Thus, an important challenge of semantic differencing relates to witness selection and presentation. In this paper we propose to address this challenge using a summarization technique, based on a notion of equivalence that partitions the set of diff witnesses. The result of the computation is a summary set, consisting of a single representative witness from each equivalence class. We demonstrate our ideas using two concrete diff operators, for class diagrams and for activity diagrams, where the computation of the summary set is efficient and does not require the enumeration of all witnesses.