If you use Megadiff, please cite the following technical report: "Megadiff: A Dataset of 600k Java Source Code Changes Categorized by Diff Size". Technical Report 2108.04631, Arxiv; 2021.
(I'm not maintaining this code as I neither have personal resources nor am I still using this project. I'll be happy to oblige if you have any pull requests or even if you wish to be a co-maintainer.) ...