Dierk Ehmke

Sebastian Krings, Joshua Schmidt, Patrick Skowronek et al.

In order to properly test software, test data of a certain quality is needed. However, useful test data is often unavailable: Existing or hand-crafted data might not be diverse enough to enable desired test cases. Furthermore, using production data might be prohibited due to security or privacy concerns or other regulations. At the same time, existing tools for test data generation are often limited. In this paper, we evaluate to what extent constraint logic programming can be used to generate test data, focussing on strings in particular. To do so, we introduce a prototypical CLP solver over string constraints. As case studies, we use it to generate IBAN numbers and calender dates.