Formal Concept Analysis Applied to Fault Localization

摘要

One time-consuming task in the development of software is debugging. Recent work in fault localization crosschecks traces of correct and failing execution traces, it implicitly searches for association rules which indicate that executing a line will most probably cause the whole execution to fail. This technique has some limitations: it assumes that an error has a single faulty statement origin, and that lines are independent. Our research hypothesis is that using association rules with more expressive premises, some limitations can be alleviated. The solution that we propose combines association rules and formal concept analysis. Our technique is already usable when the size of the execution traces is not too large. We conjecture that the technique can be used to analyze large executions, thanks to the information contained in the Abstract Syntax Tree.