We examine the query planning problem in information integration systems in the presence of sources that contain disjunctive information. We show that datalog, the language of choice for representing query plans in information integration systems, is not sufficiently expressive in this case. We prove that disjunctive datalog with inequality is sufficiently expressive, and present a construction of query plans that are guaranteed to extract all available information from disjunctive sources. 1 Introduction We examine the query planning problem in information integration systems in the presence of sources that contain disjunctive information. The query planning problem in such systems can be formally stated as the problem of answering queries using views (Levy et al. 1995; Ullman 1997; Duschka & Genesereth 1997a): View definitions describe the information stored by sources, and query planning requires to rewrite a query into one that only uses these views. In this paper we are going to extend the algorithm for answermg queries using conjunctive views that was introduced in (Duschka& Genesereth 1997a) to also be able to handle disjunction in the view definitions.
Jan-11-2006, 14:17:58 GMT