出版社：European Association of Software Science and Technology (EASST)
摘要：In GRGEN , a graph rewrite generator tool, rules have the outstanding feature that variables in their pattern and replacement graphs may be refined with meta-rules based on contextual hyperedge replacement grammars. A refined rule may delete, copy, and transform subgraphs of unbounded size and of variable shape. In this paper, we show that rules with contextual refinement can be transformed to stan- dard graph rewrite rules that perform the refinement incrementally, and are applied according to a strategy called residual rewriting. With this transformation, it is possi- ble to state precisely whether refinements can be determined in finitely many steps or not, and whether refinements are unique for every form of refined pattern or not.
