Model transformation, in a simple definition, is a program that accepts a model as input and generates another model as output. Model transformations are the cornerstone of model-driven engineering (MDE), hence testing them and ensuring the correctness of their implementation is a critical task. A challenging aspect of testing model transformations is to generate test models that both conform to their meta-model and satisfy the defined constraints. There exist several solutions for generating test models. Epsilon Model Generation (EMG) is a language for generating appropriate test models that satisfy complex constraints. EMG uses random operations for producing test models, hence it is possible that some tests have the same structure and the same value, i.e., they are redundant. In this Thesis, we propose an approach for generating appropriate test models, i.e., test models which are valuable from the tester’s point of view.
Thus, we have used equivalence partitioning that can be used to generate more efficient test models that in addition to conforming to the corresponding meta-model and satisfying complex constraints, they will be different in terms of the structure. Using this approach, the total number of generated models in testing will be reduced while covering the requirements. Due to a lesser number of test cases, the time of testing will be reduced.
In this approach, the tester specifies the number of model elements that should be generated in the test model, as well as how they are linked. We implemented our approach as an Eclipse plugin. The Graphical User Interface (GUI) of the tool is implemented in Java. We have evaluated the proposed approach via a Class2RDBMS which is a benchmark model transformation program and analysis results using mutation analysis. The results show the superiority of the proposed approach over EMG.
Papers in English