On the application of model-driven engineering in data reengineering

Abstract Model-Driven Engineering (MDE) emphasizes the systematic use of models to improve software productivity and some aspects of the software quality such as maintainability or interoperability. Model-driven techniques have proven useful not only as regards developing new software applications but also the reengineering of legacy systems. Models and metamodels provide a high-level formalism with which to represent artefacts commonly manipulated in the different stages of a software evolution process (e.g., a software migration) while model transformation allows the automation of the evolution tasks to be performed. Some approaches and experiences of model-driven software reengineering have recently been presented but they have been focused on the code while data reengineering aspects have been overlooked. The objective of this work is to assess to what extent data reengineering processes could also take advantage of MDE techniques. The article starts by characterising data-reengineering in terms of the tasks involved. It then goes on to state that MDE is particularly amenable as regards addressing the tasks previously identified. We present an MDE-based approach for the reengineering of data whose purpose is to improve the quality of the logical schema in a relational data migration scenario. As a proof of concept, the approach is illustrated for two common problems in data re-engineering: undeclared foreign keys and disabled constraints. This approach is organised following the three stages of a software reengineering process: reverse engineering, restructuring and forward engineering. We show how each stage is implemented by means of model transformation chains. A running example is used to illustrate each stage of the process throughout the article. The approach is validated with a real widely-used database. An assessment of the application of MDE in each stage is then presented, and we conclude by identifying the main benefits and drawbacks of using MDE in data reengineering.