Streaming Model Transformations: Scenarios, Challenges and Initial Solutions

摘要

Several styles of model transformations are well-known and widely used, such as batch, live, incremental and lazy transformations. While they permit tackling advanced scenarios, some applications deal with models that are only available as a possibly infinite stream of elements. Hence, in streaming transformations, source model elements are continuously produced by some process, or very large models are fragmented and fed into the transformation engine. This poses a series of issues that cannot be tackled using current transformation engines. In this paper we motivate the applicability of this kind of transformations, explore the elements involved, and review several strategies to deal with them. We also propose a concrete approach, built on top of the Eclectic transformation tool.