A systematic literature review on cross-language source code clone detection

Abstract

Context

Cross-language code Clone Detection (CLCCD) is crucial to maintaining consistency and minimizing redundancy in modern software development, where similar code may appear in different projects written in various programming languages. While previous reviews have explored code clone detection in general, none have exclusively focused on CLCCD.

Objective

This study aims to bridge this gap by reviewing the existing CLCCD approaches, focusing on detection techniques, preprocessing methods, feature extraction approaches, datasets, and evaluation metrics used.

Method

A systematic literature review (SLR) was conducted, analyzing 26 studies published in journals, conferences, and workshops until May 2025. Both quantitative and qualitative data were systematically analyzed to derive the findings.

Results

CLCCD has evolved from traditional techniques to deep learning models, but fully automated tools remain unavailable. Parsing (73 %), normalization (35 %), and tokenization (27 %) are widely used preprocessing techniques in CLCCD methods. Most studies (38.5 %) employ hybrid feature extraction, which combines tree-based and graph-based methods to capture code structure and semantics. However, the datasets primarily sourced from programming competition platforms lack diversity and standardization. Performance evaluation largely relies on metrics like precision, recall, and F1-score, while incorporating additional evaluation metrics could provide more insights into detection performance.

Conclusion

This SLR summarizes current CLCCD research, highlighting advancements and challenges. Significant gaps include the absence of diverse and standardized datasets and the limited exploration of advanced feature extraction techniques. Future research should focus on creating better datasets, adopting novel detection techniques, and exploring feature extraction methods to improve CLCCD performance for modern multi-language systems.