Analysis of function-call graphs of open-source software systems using complex network analysis

摘要

Software systems are usually designed in a modular and hierarchical fashion, where functional responsibility of a system is decomposed into multiple functional software elements optimally such as subsystems, modules, packages, classes, methods, and functions. These elements are coupled with each other with some kind of dependency relationships to some degree, and their interactions naturally form a graph or network structure. In this study, we generated the static function-call graphs of several open-source software systems, where functions were the most basic type of interacting elements calling each other. Then, we analyzed the call graphs both visually and topologically using the techniques of complex network analysis. We found the call graphs to reveal scale-free and small-world network properties similar to the findings of the previous studies. In addition, we identified the most central and important functions in each call-graph using several centrality measures. We also performed community analysis and found that the call graphs exhibited a tendency to form communities. Finally, we showed that analysis of static function-call graphs of software systems through complex network analysis has the potential to reveal useful information about them.