Linguistic and architectural requirements for personalized digital libraries

Our vision of digital libraries is influenced by our experience with systems for persistent and networked object management and with polymorphic programming languages for their implementation. When viewed from this perspective, the essence of digital libraries can be captured by the following three essentials: (1) the content of a digital library is represented by two kinds of information entities: on the basic level there are information tokens as supplied by information providers on the net; value is added to such tokens by individually constructing information artifacts over them with the goal of information consumer satisfaction; (2) the services required for artifact construction and use - on the information level as well as on the level of the software artifacts required for these processes - rely heavily on powerful binding environments for multimedial, persistent and networked information; (3) the processes of artifact construction and use are in themselves valuable sources of information about artifacts; for the exploitation of such process information, digital libraries employ advanced tracing environments. We derive linguistic and architectural requirements for digital libraries from these above essentials. On the language level we concentrate on generalized requirements for the typing, binding and scoping of library entities and services. On the system level we discuss architectural requirements in terms of orthogonal persistence, open extensibility, platform independence, mobility and reflection. We present Tycoon, a polymorphic, higher-order language and its system, and demonstrate its potential for digital libraries. We evaluate Tycoon's rich conceptual basis (data, functions and threads), library-based extensibility, powerful binding mechanisms, its orthogonal persistence and its capability of network-wide data, code and thread migration. We conclude by referring to an interdisciplinary digital library project in Art History Research based on icons, texts and data. Here, Tycoon effectively supports the process of individually customizing and scaling library services thus generalizing the notion of a query language into that of a persistent personal reference library.