一句话：提出 HECS，用类内依赖超图神经网络与 LLM 建模一对多依赖，推荐 Extract Class 重构机会。
过大的类常承担多重职责，难以理解和维护。现有 Extract Class 重构工具多构建类内依赖图并依据硬编码规则发现机会，但图主要刻画实体间直接的一对一关系，忽略现实中普遍存在的一对多依赖，使建议可能偏离开发者需求。本文提出 HECS：为每个目标类构建类内依赖超图，用预训练代码模型为节点赋属性，输入增强超图神经网络训练，并结合大语言模型构建重构建议系统。作者在大规模数据集上训练，并在两个真实数据集上评估。相比 JDeodorant、SSECS 和 LLMRefactor，精确率提升 38.5%、召回率提升 9.7%、F1 提升 44.4%，对 64% 的参与者更有用，并给出对现有 Extract Class 技术的实践启示。
Excessively large classes that encapsulate multiple responsibilities are challenging to comprehend and maintain. Addressing this issue, several Extract Class refactoring tools have been proposed, employing a two-phase process: identifying suitable fields or methods for extraction, and implementing the mechanics of refactoring. These tools traditionally generate an intra-class dependency graph to analyze the class structure, applying hard-coded rules based on this graph to unearth refactoring opportunities. Yet, the graph-based approach predominantly illuminates direct, “one-to-one” relationship between pairwise entities. Such a perspective is restrictive as it overlooks the complex, “one-to-many” dependencies among multiple entities that are prevalent in real-world classes. This narrow focus can lead to refactoring suggestions that may diverge from developers’ actual needs, given their multifaceted nature. To bridge this gap, our paper leverages the concept of intra-class dependency hypergraph to model one-to-many dependency relationship and proposes a hypergraph learning-based approach to suggest Extract Class refactoring opportunities named HECS. For each target class, we first construct its intra-class dependency hypergraph and assign attributes to nodes with a pre-trained code model. All the attributed hypergraphs are fed into an enhanced hypergraph neural network for training. Utilizing this trained neural network alongside a large language model (LLM), we construct a refactoring suggestion system. We trained HECS on a large-scale dataset and evaluated it on two real-world datasets. The results show that demonstrates an increase of 38.5% in precision, 9.7% in recall, and 44.4% in f1-measure compared to 3 state-of-the-art refactoring tools including JDeodorant, SSECS, and LLMRefactor, which is more useful for 64% of participants. The results also unveil practical suggestions and new insights that benefit existing extract-related refactoring techniques.
DOI 原文 ·
@inproceedings{paperbot8564,
title = {One-to-One or One-to-Many? Suggesting Extract Class Refactoring Opportunities with Intra-class Dependency Hypergraph Neural Network},
author = {Di Cui and Qiangqiang Wang and Yutong Zhao and Jiaqi Wang and Minjie Wei and Jingzhao Hu and Luqiao Wang and Qingshan Li},
booktitle = {ISSTA},
year = {2024},
doi = {10.1145/3650212.3680379}
}