Order-Sensitive XML Query Processing over Relational Sources: An Algebraic Approach

The XML data is order-sensitive. The order problem, that is how ordered XML documents and order-sensitive queries over it can be efficiently supported when mapped into the unordered relational data model, has not yet been adequately addressed. In this paper, we present a general approach for supporting order-sensitive XQuery-to-SQL translation that works irrespective of the chosen XML-to-relational data mapping and the selected order-encoding method. Our approach, called XSOT, utilizes an order-aware XML algebra representation. We propose order-sensitive rewriting rules at the algebraic level to eliminate the dependency of the order determining operators on the implicit XML view order. Furthermore, we introduce a series of order-sensitive optimization steps to transform the XML algebra tree for the purpose of efficient SQL translation. Lastly, we utilize a template-based approach using SQL-99 order features to generate SQL statements.