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

TL;DR

This paper explores using large language models to automate the translation of a large legacy PL/SQL system into Java, demonstrating promising results despite limited data and validation resources.

Contribution

It introduces a novel prompting strategy combining chain-of-guidance and $n$-shot prompting for LLM-based code translation from PL/SQL to Java.

Findings

LLMs can generate syntactically correct PL/SQL to Java translations.

The customized prompting improves translation quality and functional correctness.

Limitations include small dataset and limited validation scope.

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.