Data Warehouse Based Approach to the Integration of Semi-structured Data

Semi-structured data play an increasing role in the development of the web through the use of XML. However, the management of semi-structured data poses specific problems because semi-structured data, contrary to classical database, do not rely on a predefined schema. The schema of a document is contained in the document itself and similar documents may be represented by different schemas. Consequently, the techniques and algorithms used for querying or integrating this data are more complex than those used for structured data. In this article we propose the architecture of a Data Warehouse designed for the integration of semi-structured data, so as to make possible searches in data repositories of various origins and structures. This architecture relies on the Osiris system, a DL-based model designed for the representation and management of databases and knowledge bases. In particular, we are interested in the Osiris data model, which gives several points of views on a family of objects. On the other hand, the indexing system of Osiris supports semantic query optimization. We show that the problem of query processing on a XML source is optimized by the objects indexing approach proposed by Osiris.