Object-Oriented Querying of Existing Relational Databases

Abstract

In this paper, we present algorithms which allow an object-oriented querying of existing relational databases. Our goal is to provide an improved query interface for relational systems with better query facilities than SQL. This seems to be very important since, in real world applications, relational systems are most commonly used and their dominance will remain in the near future. To overcome the drawbacks of relational systems, especially the poor query facilities of SQL, we propose a schema transformation and a query translation algorithm. The schema transformation algorithm uses additional semantic information to enhance the relational schema and transform it into a corresponding object-oriented schema. If the additional semantic information can be deducted from an underlying entity-relationship design schema, the schema transformation may be done fully automatically. To query the created object-oriented schema, we use the Structured Object Query Language (SOQL) which provides declarative query facilities on objects. SOQL queries using the created object-oriented schema are much shorter, easier to write and understand and more intuitive than corresponding SQL queries leading to an enhanced usability and an improved querying of the database. The query translation algorithm automatically translates SOQL queries into equivalent SQL queries for the original relational schema.