Test case generation based on program invariant and adaptive random algorithm

Abstract

Testing is a critical activity to find software errors. And choosing an effective test suite is the key problem in software testing area. Program invariant, as an attribute of program, can record the implementation state of test case very well and reveal the coverage of program data. In this paper, we integrate adaptive random testing and invariant technology, and present a new method which makes full use of the feedback information of program invariant and invalid case suite to generate the next case. Experiment results show that, compared with other similar methods, running for the same time, our method can achieve higher coverage and faster convergence speed. © 2011 Springer-Verlag.