A method for automated unit testing of C programs

Abstract

This research proposes an automated test case generation method for C functions. In this method, the source code is transformed into a control flow graph corresponding to the given coverage criterion. After that, a list of feasible test paths are discovered by traversing the control flow graph using backtracking algorithm, symbolic execution, and Z3 solver. We also generate test cases for functions containing one loop or two-nested loop. A tool supporting the proposed method has been developed and applied to test on some C functions. The experimental results show the high coverage with the minimum number of test cases, the ability to improve the total time of the test case generation with a specified coverage criterion, and the increasing precision of checking the feasibility of test paths if comparing with the random technique. The experimental results display the potential usefulness of this tool for automated test case generation in practice.