Service Mining from Legacy Database Applications

As software consumption is shifting to mobile platforms, enterprises are looking for efficient ways to reuse their existing legacy systems by exposing their functionalities as services. Mining services from legacy code is therefore an important problem for the enterprises. In this paper we present a technique for mining service candidates from the database applications. Central to our mining technique is the specification and identification of data-access patterns which specify how a program interacts with the databases. In addition to finding service candidates which are internal functions in the source code, we also provide an algorithm to expose the function as a stateless service by generating a wrapper function around the internal function. We demonstrate the effectiveness of our technique on two open source applications and twelve industrial applications.