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.

Original languageEnglish
Title of host publicationThird Conference on Software Engineering and Information Management (SEIM-2018)
Place of PublicationSaint Petersburg
Pages37-43
Number of pages7
Volume2135
StatePublished - 2018

Publication series

NameCEUR Workshop Proceedings
ISSN (Print)1613-0073

    Scopus subject areas

  • Computer Science(all)

ID: 35174635