Detecting Java Code Clones with Multi-granularities Based on Bytecode

TL;DR: A novel code clone detection method based on Java bytecode that can simultaneously detect code clones at both method level and block level and is shown to be more effective than the state-of-the-art methods.

Abstract: Sequences of duplicate code, either with or without modification, are known as code clones or just clones. Code clones are generally considered undesirable for a number of reasons, although they can offer some convenience to developers. The detection of code clones helps to improve the quality of source code through software re-engineering. Numerous methods have been proposed for code clone detection in Java code. However, the existing methods are mostly based on the Java source code, while only a few focus on its bytecode, in fact, the Java bytecode reflects more of the semantic nature of the source code than the source code itself does. In this paper, we propose a novel code clone detection method based on Java bytecode. Using the block-level code fragments extracted from bytecode, it can simultaneously detect code clones at both method level and block level. In addition, during the process of code clone detection, the similarities of both method call sequences and instruction sequences are calculated in order to improve accuracy. We conduct two extensive experiments to evaluate the performance of our method. The results show that the proposed method can detect code clones more effectively than the state-of-the-art methods.