A Git Source Repository Analysis Tool Based on a Novel Branch-Oriented Approach

Code repositories of the version control systems have been used as important raw material in lots of developer behavior studies. In such research, commits are usually considered as a unit of development phases, even though they contain limited information over development process. Unlike former source code management systems, Git provides branching, which are the unit of concurrent and independent development activities in a whole project. Branches have significant advantages over commits from the viewpoint of the developer behavior researchers. By exploiting the characteristics of branching, we propose a Git branch analysis tool. The proposed tool automatically extracts branching data from Git repositories and performs statistical and graphical analysis on them. Through a few case studies using a number of popular OSS project repositories, we showed that the proposed branch-oriented analyzer is able to perform more insightful analysis than the existing commit-based analyzers.