Graph-based method for inductive bug localization
A computer-implemented method executed by at least one processor for software bug localization is presented. The method includes constructing a bug localization graph to capture relationships between bug tickets and relevant source code files from historical change-sets and an underlying source code repository, leveraging natural processing language tools to evaluate semantic similarity between a new bug ticket and a historical ticket, in response to the evaluated semantic similarity, for the new bug ticket, adding links between the new bug ticket a set of similar historical tickets, incorporating the new bug ticket in the bug localization graph, and developing a mathematical graph expression to determine a closeness relationship between the relevant source code files and the new bug ticket.
1. A computer-implemented method executed by at least one processor for software bug localization, the method comprising:
constructing a bug localization graph to capture relationships between bug tickets and relevant source code files from historical change-sets and an underlying source code repository;
leveraging a natural language processing tool to evaluate semantic similarity between a new bug ticket and a historical ticket;
in response to the evaluated semantic similarity, for the new bug ticket, adding links between the new bug ticket a set of similar historical tickets;
incorporating the new bug ticket in the bug localization graph; and
developing a mathematical graph expression to determine a closeness relationship between the relevant source code files and the new bug ticket,
wherein constructing the bug localization graph includes extracting reference relations and change-set relations;
wherein the bug localization graph includes a plurality of nodes and a plurality of edges connecting the nodes, each node representing either a relevant source code file or a bug ticket, and wherein two nodes are connected if they have reference relations; and
wherein the mathematical graph expression generates a closeness score for each new bug ticket node.
2. The method of claim 1 , wherein updates for the closeness score are performed iteratively.
3. A system for software bug localization, the system comprising:
a memory; and
a processor in communication with the memory, wherein the processor runs program code to:
construct a bug localization graph to capture relationships between bug tickets and relevant source code files from historical change-sets and an underlying source code repository;
leverage a natural language processing tool to evaluate semantic similarity between a new bug ticket and a historical ticket;
in response to the evaluated semantic similarity, for the new bug ticket, add links between the new bug ticket a set of similar historical tickets;
incorporate the new bug ticket in the bug localization graph; and
develop a mathematical graph expression to determine a closeness relationship between the relevant source code files and the new bug ticket,
wherein constructing the bug localization graph includes extracting reference relations and change-set relations;
wherein the bug localization graph includes a plurality of nodes and a plurality of edges connecting the nodes, each node representing either a relevant source code file or a bug ticket, and wherein two nodes are connected if they have reference relations; and
wherein the mathematical graph expression generates a closeness score for each new bug ticket node.
4. The system of claim 3 , wherein updates for the closeness score are performed iteratively.
5. A non-transitory computer-readable storage medium comprising a computer-readable program for software bug localization, wherein the computer-readable program when executed on a computer causes the computer to perform the steps of:
constructing a bug localization graph to capture relationships between bug tickets and relevant source code files from historical change-sets and an underlying source code repository;
leveraging a natural language processing tool to evaluate semantic similarity between a new bug ticket and a historical ticket;
in response to the evaluated semantic similarity, for the new bug ticket, adding links between the new bug ticket a set of similar historical tickets;
incorporating the new bug ticket in the bug localization graph; and
developing a mathematical graph expression to determine a closeness relationship between the relevant source code files and the new bug ticket,
wherein constructing the bug localization graph includes extracting reference relations and change-set relations;
wherein the bug localization graph includes a plurality of nodes and a plurality of edges connecting the nodes, each node representing either a relevant source code file or a bug ticket, and wherein two nodes are connected if they have reference relations; and
wherein the mathematical graph expression generates a closeness score for each new bug ticket node.