Towards Unified Combinatorial Interaction Testing

Abstract

We believe that we can exploit the benefits of combinatorial interaction testing (CIT) on many "non-traditional" combinatorial spaces using many "non-traditional" coverage criteria. However, this requires truly flexible CIT approaches. To this end, we introduce Unified Combinatorial Interaction Testing (U-CIT), which enables practitioners to define their own combinatorial spaces and coverage criteria for testing, and present a unified construction approach to compute specific instances of U-CIT objects. We, furthermore, argue that most (if not all) existing CIT objects are a special case of U-CIT and demonstrate the flexibility of U-CIT on a simple, yet realistic scenario.