Leveraging LLMs for Automated Translation of Legacy Code: A Case Study on PL/SQL to Java Transformation

International Conference on Evaluation and Assessment in Software Engineering (EASE), pp. 809–813

Abstract

The VT legacy system, comprising approximately 2.5 million lines of PL/SQL code, lacks consistent documentation and automated tests, posing significant challenges for refactoring and modernisation. This study investigates the feasibility of leveraging large language models (LLMs) to assist in translating PL/SQL code into Java for the modernised "VTF3" system. By leveraging a dataset comprising 10 PL/SQL-to-Java code pairs and 15 Java classes, which collectively established a domain model for the translated files, multiple LLMs were evaluated. Furthermore, we propose a customized prompting strategy that integrates chain-of-guidance reasoning with n-shot prompting. Our findings indicate that this methodology effectively guides LLMs in generating syntactically accurate translations while also achieving functional correctness. However, the findings are limited by the small sample size of available code files and the restricted access to test cases used for validating the correctness of the generated code. Nevertheless, these findings lay the groundwork for scalable, automated solutions in modernising large legacy systems.

Authors 6

1. Lola Solovyeva

   University of Twente

   Affiliation as printed

   University of Twente, Enschede, Netherlands

2. Eduardo Carneiro de Oliveira

   Utrecht University

   Affiliation as printed

   Utrecht University, Utrecht, Netherlands

3. Shiyu Fan

   Eindhoven University of Technology

   Affiliation as printed

   Eindhoven University of Technology, Eindhoven, Netherlands

4. Alper Tuncay Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, Netherlands

5. Shamil Gareev

   Eötvös Loránd University

   Affiliation as printed

   Eötvös Loránd University, Budapest, Hungary

6. Andrea Capiluppi

   University of Groningen

   Affiliation as printed

   University of Groningen, Groningen, Netherlands