| 本文已被：浏览 3030次 下载 7139次 |
码上扫一扫！ |
|
|
| 一种结构信息增强的代码修改自动转换方法 |
|
曹英魁1,2, 孙泽宇1,2, 邹艳珍1,2, 谢冰1,2
|
|
1.北京大学 信息科学技术学院, 北京 100871;2.高可信软件技术教育部重点实验室(北京大学), 北京 100871
|
|
| 摘要: |
| 在开发过程中，开发人员在进行缺陷修复、版本更新时，常常需要修改多处相似的代码.如何进行自动代码修改已成为软件工程领域的热点研究问题.一种行之有效的方式是：给定一组代码修改示例，通过抽取其中的代码修改模式，辅助相似代码进行自动转换.在现有工作中，基于深度学习的方法取得了一定进展，但在捕获代码间的长程信息依赖关系时，效果不佳.为此，提出了一种结构信息增强的代码修改自动转换方法ExpTrans.ExpTrans在解析代码时采用图的形式来表示修改示例，显式地指出了代码中变量之间的依赖关系，同时结合图卷积网络和Transformer架构，增强了模型对代码的结构信息和依赖信息的捕获能力，从而提升了代码修改自动转换的准确性.实验结果表明，对比同类型基于深度学习的方法，ExpTrans在准确率上提升了11.8%~30.8%；对比基于人工规则的方法，ExpTrans在修改实例的数量和准确率上均有显著提升. |
| 关键词: 代码变更 代码演化 软件维护 代码生成 |
| DOI：10.13328/j.cnki.jos.006227 |
| 分类号:TP311 |
| 基金项目:国家杰出青年科学基金（61525201）；国家自然科学基金（61972006） |
|
| Structurally-enhanced Approach for Automatic Code Change Transformation |
|
CAO Ying-Kui1,2, SUN Ze-Yu1,2, ZOU Yan-Zhen1,2, XIE Bing1,2
|
|
1.School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China;2.Key Laboratory of High Confidence Software Technologies of Ministry of Education (Peking University), Beijing 100871, China
|
| Abstract: |
| In software development, developers often need to change or update lots of similar codes. How to perform code transformation automatically has become a research hotspot in software engineering. An effective way is:Extracting the change pattern from a set of similar code changes and apply it to automatic code change transformation. In the related work, deep-learning-based approaches have achieved much progress, but they suffer from the problem of significant long-dependency among code. To address this challenge, an automatic code change transformation method is proposed, namely ExpTrans, enhanced by code structure information. Based on graph-based representations of code changes, ExpTrans is enhanced with structural information of code. ExpTrans labels the dependency among variables in code parsing, adopts the graph-convolution network and transformer structure, so as to capture the long-dependency among code. To evaluate ExpTrans's effectiveness, it is compared with existing learning-based approaches first, the results show that ExpTrans gains 11.8%~30.8% precision increment. Then, ExpTrans is compared with rule-based the approaches, the results show that ExpTrans significantly improves the correct rate of the modified instances. |
| Key words: code change software evolution software maintenance code generation |
