Checkstyle+: Reducing Technical Debt Through The Use of Linters with LLMs

TL;DR

Checkstyle+ enhances traditional static code analysis tools by integrating large language models to better detect nuanced style violations, thereby improving code quality and maintainability.

Contribution

This paper introduces Checkstyle+, a hybrid system combining Checkstyle with LLMs to identify complex style violations beyond static rule-based detection.

Findings

Checkstyle+ outperforms standard Checkstyle in detecting nuanced style violations.

Evaluation on 380 Java files shows improved detection accuracy.

Checkstyle+ effectively reduces technical debt related to code style.

Abstract

Good code style improves program readability, maintainability, and collaboration, and is an integral component of software quality. Developers, however, often cut corners when following style rules, leading to the wide adoption of tools such as linters in professional software development projects. Traditional linters like Checkstyle operate using rigid, rule-based mechanisms that effectively detect many surface-level violations. However, in most programming languages, there is a subset of style rules that require a more nuanced understanding of code, and fall outside the scope of such static analysis. In this paper, we propose Checkstyle+, a hybrid approach that augments Checkstyle with large language model (LLM) capabilities, to identify style violations that elude the conventional rule-based analysis. Checkstyle+ is evaluated on a sample of 380 Java code files, drawn from a broader dataset of 30,800 real-world Java programs sourced from accepted Codeforces submissions. The results show that Checkstyle+ achieves superior performance over standard Checkstyle in detecting violations of the semantically nuanced rules.