Data-Based Code Synthesis in IntelliJ IDEA

Vladislav Tankov and Timofey Bryksin

April, 2018. Published in the proceedings of SEIM'18 (Regional).

Abstract. Automatic code synthesis has been attracting more attention lately. Some recent papers in this traditionally academic field even present results that could be applicable for industrial programmers. This paper provides an overview of Bayesian Sketch Learning (BSL) approach, describes basic concepts and workflow of a BSL synthesizer. Based on this we discuss an architecture of a configurable BSL synthesizer that could work as a part of an integrated development environment. We describe the implementation of such synthesizer for JVM platform and its integration with IntelliJ IDEA as a plugin. Two approaches to implement user interaction in a plugin like this are presented: method annotations and a domain-specific language. The paper concludes with an evaluation and a discussion on limitations of selected approach for industrial programmers.