Schema Evolution for XML: A Consistency-Preserving Approach

This paper deals with updates of XML documents that satisfy a given schema, e.g., a DTD. In this context, when a given update violates the schema, it might be the case that this update is accepted, thus implying to change the schema. Our method is intended to be used by a data administrator who is an expert in the domain of application of the database, but who is not required to be a computer science expert. Our approach consists in proposing different schema options that are derived from the original one. The method is consistency-preserving: documents valid with respect to the original schema remain valid. The schema evolution is implemented by an algorithm (called GREC) that performs changes on the graph of a finite state automaton and that generates regular expressions for the modified graphs. Each regular expression proposed by GREC is a choice of schema given to the administrator.