Optimizing the readability of tests generated by symbolic execution

Taking up about half of the development time, testing remains the most common method of software quality control and its disadvantage can lead to financial losses. With a systematic approach, the test suite is considered to be complete if it provides a certain amount of code coverage. At the moment there are a large number of systematic test generators aimed at finding standard errors. Such tools generate a huge number of difficult-to-read tests that require human veri- fication which is very expensive. The method presented in this paper allows improving the readability of tests that are automatically generated using symbolic execution, providing a qualitative reduction in the cost of verification. Experi- mental studies of the test generator, including this method as the final phase of the work, were conducted on 12 string functions from the Linux repository. The assessment of the readability of the lines contained in the optimized tests is comparable to the case of using words of a natural language, which has a positive effect on the process of verification of test results by humans.