Incorporating fault-proneness estimations into coverage-based test case prioritization methods
This work addresses regression testing efficiency for software developers, but it is incremental as it builds on existing coverage-based methods.
The paper tackles the problem of costly regression testing by improving coverage-based test case prioritization (TCP) methods through fault-proneness estimations, resulting in significant improvements over a widely used method as shown in experiments on five real-world projects with 357 versions.
Context: During the development process of a software program, regression testing is used to ensure that the correct behavior of the software is retained after updates to the source code. This regression testing becomes costly over time as the number of test cases increases and it makes sense to prioritize test cases in order to execute fault-detecting test cases as soon as possible. There are many coverage-based test case prioritization (TCP) methods that only use the code coverage data to prioritize test cases. By incorporating the fault-proneness estimations of code units into the coverage-based TCP methods, we can improve such techniques. Objective: In this paper, we aim to propose an approach which improves coverage-based TCP methods by considering the fault-proneness distribution over code units. Further, we present the results of an empirical study that shows using our proposed approach significantly improves the additional strategy, which is a widely used coverage-based TCP method. Method: The approach presented in this study uses the bug history of the software in order to introduce a defect prediction method to learn a neural network model. This model is then used to estimate fault-proneness of each area of the source code and then the estimations are incorporated into coverage-based TCP methods. Our proposed approach is a general idea that can be applied to many coverage-based methods, such as the additional and total TCP methods. Results: The proposed methods are evaluated on datasets collected from the development history of five real-world projects including 357 versions in total. The experiments show that using an appropriate bug history can improve coverage-based TCP methods.