Model Konversi Otomatis Antar Bahasa Pemrograman untuk Meningkatkan Portabilitas Perangkat Lunak
DOI:
https://doi.org/10.47134/jacis.v5i2.120Keywords:
konversi kode, rule-based, antar bahasa pemrograman, portabilitas perangkat lunakAbstract
Seiring meningkatnya kebutuhan akan perangkat lunak yang portabel di berbagai platform, konversi lintas bahasa pemrograman menjadi tantangan utama dalam rekayasa perangkat lunak modern. Penelitian ini mengembangkan sistem konversi otomatis dari bahasa Java ke Python menggunakan pendekatan hybrid yang menggabungkan metode berbasis aturan (rule-based) dan model kecerdasan buatan generatif (Large Language Models) seperti GPT-4 dan Gemini. Model AI dalam sistem ini diperlakukan sebagai black box translator, yaitu entitas yang menerima input kode Java dan menghasilkan keluaran Python tanpa proses konversi eksplisit diungkapkan. Evaluasi dilakukan pada 30 potongan kode dengan tiga tingkat kompleksitas (sederhana, menengah, kompleks), dan dinilai berdasarkan akurasi sintaksis, kesesuaian semantik melalui unit test, serta efisiensi waktu proses. Hasil menunjukkan rata-rata akurasi sintaksis mencapai 96,3%, kesesuaian semantik sebesar 93,0%, dan waktu konversi rata-rata 3,1 detik. Pendekatan hybrid terbukti lebih unggul dibandingkan metode tunggal karena menggabungkan presisi transformasi eksplisit dan fleksibilitas semantik AI. Temuan ini berkontribusi terhadap pengembangan solusi migrasi kode otomatis yang andal dan efisien. Ke depan, sistem dapat diperluas untuk mendukung lebih banyak bahasa pemrograman dan struktur kode yang lebih dinamis
References
[1] R. C. M. Series, Clean Code, A Handbook of Agile Software Craftsmanship. United States of America: Prentice Hall, 2009.
[2] A. H. Adepoju, A. Eweje, A. Collins, and B. A.- Gabriel, “Framework for Migrating Legacy Systems to Next-Generation Data Architectures While Ensuring Seamless Integration and Scalability,” Int. J. Multidiscip. Res. Growth Eval., vol. 5, no. 6, pp. 1462–1474, 2024, doi: 10.54660/.ijmrge.2024.5.6.1462-1474. DOI: https://doi.org/10.54660/.IJMRGE.2024.5.6.1462-1474
[3] S. T. Gollapudi and S. Sasi, “Semantic Rule-based Automatic Code conversion System,” 2020 Int. Conf. Data Sci. Eng. ICDSE 2020, pp. 1–5, 2020, doi: 10.1109/ICDSE50459.2020.9310169. DOI: https://doi.org/10.1109/ICDSE50459.2020.9310169
[4] B. Roziere, M. A. Lachaux, L. Chanussot, and G. Lample, “Unsupervised Translation of Programming Languages,” Adv. Neural Inf. Process. Syst., vol. 2020-Decem, no. NeurIPS, 2020.
[5] Z. Yang et al., “Exploring and Unleashing the Power of Large Language Models in Automated Code Translation,” Proc. ACM Softw. Eng., vol. 1, no. FSE, pp. 1585–1608, 2024, doi: 10.1145/3660778. DOI: https://doi.org/10.1145/3660778
[6] P. Jana, P. Jha, H. Ju, G. Kishore, A. Mahajan, and V. Ganesh, “CoTran: An LLM-Based Code Translator Using Reinforcement Learning with Feedback from Compiler and Symbolic Execution,” Front. Artif. Intell. Appl., vol. 392, pp. 4011–4018, 2024, doi: 10.3233/FAIA240968. DOI: https://doi.org/10.3233/FAIA240968
[7] Z. Feng et al., “CodeBERT: A pre-trained model for programming and natural languages,” Find. Assoc. Comput. Linguist. Find. ACL EMNLP 2020, pp. 1536–1547, 2020, doi: 10.18653/v1/2020.findings-emnlp.139. DOI: https://doi.org/10.18653/v1/2020.findings-emnlp.139
[8] A. Dhruv and A. Dubey, “Leveraging Large Language Models for Code Translation and Software Development in Scientific Computing,” in PASC ’25: Platform for Advanced Scientific Computing Conference, 2025, pp. 1–9. doi: 10.1145/3732775.3733572. DOI: https://doi.org/10.1145/3732775.3733572
[9] Y. Cao et al., “A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT,” J. ACM, vol. 37, no. 4, 2023, [Online]. Available: http://arxiv.org/abs/2303.04226
[10] D. V. Christensen et al., “2022 Roadmap on Neuromorphic Computing and Engineering,” Neuromorphic Comput. Eng., vol. 2, no. 2, 2022, doi: 10.1088/2634-4386/ac4a83. DOI: https://doi.org/10.1088/2634-4386/ac4a83
[11] Y. Golubev, Z. Kurbatova, E. A. Alomar, T. Bryksin, and M. W. Mkaouer, “One thousand and one stories: A large-scale survey of software refactoring,” in ESEC/FSE 2021 - Proceedings of the 29th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2021, no. 1, pp. 1303–1313. doi: 10.1145/3468264.3473924. DOI: https://doi.org/10.1145/3468264.3473924
[12] E. Dehaerne, B. Dey, S. Halder, S. De Gendt, and W. Meert, “Code Generation Using Machine Learning: A Systematic Review,” IEEE Access, vol. 10, no. July, pp. 82434–82455, 2022, doi: 10.1109/ACCESS.2022.3196347. DOI: https://doi.org/10.1109/ACCESS.2022.3196347
[13] Y. Lee and J. Cho, “Knowledge representation for computational thinking using knowledge discovery computing,” Inf. Technol. Manag., vol. 21, no. 1, pp. 15–28, 2020, doi: 10.1007/s10799-019-00299-9. DOI: https://doi.org/10.1007/s10799-019-00299-9
[14] T. D. Harjanto, A. Vatresia, and R. Faurina, “Analisis Penetapan Skala Prioritas Penanganan Balita Stunting Menggunakan Metode DBSCAN Clustering (Studi Kasus Data Dinas Kesehatan Kabupaten Lebong),” Rekursif J. Inform., vol. 9, no. 1, pp. 30–42, 2021, doi: 10.33369/rekursif.v9i1.14982. DOI: https://doi.org/10.33369/rekursif.v9i1.14982
[15] R. Ambarwati, “PENGEMBANGAN MAKANAN TAMBAHAN BERBASIS F100 DENGAN SUBSTITUSI TEPUNG LABU KUNING DAN TEPUNG PISANG,” J. Nutr. Coll., 2020, doi: 10.14710/jnc.v9i2.27033. DOI: https://doi.org/10.14710/jnc.v9i2.27033
[16] M. Suhendra, W. Swastika, and M. Subianto, “Analisis Sentimen Pada Ulasan Aplikasi Video Conference Menggunakan Naive Bayes,” Sainsbertek J. Ilm. Sains Teknol., vol. 2, no. 1, pp. 1–9, 2021, doi: 10.33479/sb.v2i1.145. DOI: https://doi.org/10.33479/sb.v2i1.145
[17] M. N. Maskuri, Harliana, K. Sukerti, and R. M. H. Bhakti, “Penerapan Algoritma K-Nearest Neighbor (KNN) untuk Memprediksi Penyakit Stroke,” J. Ilm. Intech Inf. Technol. J. UMUS, vol. 4, no. 1, pp. 130–140, 2022.
[18] D. Darwis, N. Siskawati, and Z. Abidin, “Penerapan Algoritma Naive Bayes Untuk Analisis Sentimen Review Data Twitter BMKG Nasional,” J. Tekno Kompak, vol. 15, no. 1, p. 131, 2021, doi: 10.33365/jtk.v15i1.744. DOI: https://doi.org/10.33365/jtk.v15i1.744
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Kaswiyah Kaswiyah, Briliano Yusuf Najma Rasyada, Muhammad Ainul Yaqin
This work is licensed under a Creative Commons Attribution 4.0 International License.
