An Eclipse Plugin to Support Code Smells Detection
This tool addresses the challenge of improving software readability and design for developers, but it is incremental as it applies an existing statistical method to a specific domain.
The paper tackles the problem of subjective and error-prone code smell detection in large Java systems by presenting an Eclipse plugin that automates detection using a Binary Logistic Regression model calibrated with expert knowledge.
Eradication of code smells is often pointed out as a way to improve readability, extensibility and design in existing software. However, code smell detection in large systems remains time consuming and error-prone, partly due to the inherent subjectivity of the detection processes presently available. In view of mitigating the subjectivity problem, this paper presents a tool that automates a technique for the detection and assessment of code smells in Java source code, developed as an Eclipse plug-in. The technique is based upon a Binary Logistic Regression model and calibrated by expert's knowledge. A short overview of the technique is provided and the tool is described.