Design, implementation, and validation of a benchmark generator for combinatorial interaction testing tools

Combinatorial testing is a widely adopted technique for efficiently detecting faults in software. The quality of combinatorial test generators plays a crucial role in achieving effective test coverage. Evaluating combinatorial test generators remains a challenging task that requires diverse and representative benchmarks. Having such benchmarks might help developers to test their tools, and improve their performance.For this reason, in this paper, we present BENCIGEN, a highly configurable generator of benchmarks to be used by combinatorial test generators, empowering users to customize the type of benchmarks generated, including constraints and parameters, as well as their complexity. An initial version of such a tool has been used during the CT-Competition, held yearly during the International Workshop on Combinatorial Testing. This paper describes the requirements, the design, the implementation, and the validation of BENCIGEN. Tests for the validation of BENCIGEN are derived from its requirements by using a combinatorial interaction approach. Moreover, we demonstrate the tool's ability to generate benchmarks that reflect the characteristics of real software systems.BENCIGEN not only facilitates the evaluation of existing generators but also serves as a valuable resource for researchers and practitioners seeking to enhance the quality and effectiveness of combinatorial testing methodologies.