Authors:
Shanto Rahman
;
Md. Mostafijur Rahman
and
Kazi Sakib
Affiliation:
University of Dhaka, Bangladesh
Keyword(s):
Statement Level Bug Localization, Search Space Minimization, Statement Dependency, Similarity Measurement.
Abstract:
Existing bug localization techniques suggest source code methods or classes as buggy which require manual investigations to find the buggy statements. Considering that issue, this paper proposes Statement level Bug Localization (SBL), which can effectively identify buggy statements from the source code. In SBL, relevant buggy methods are ranked using dynamic analysis followed by static analysis of the source code. For each ranked buggy method, a Method Statement Dependency Graph (MSDG) is constructed where each statement acts as a node of the graph. Since each of the statements contains few information, it is maximized by combining the contents of each node and its predecessor nodes in MSDG, resulting a Node Predecessor-node Dependency Graph (NPDG). To identify relevant statements for a bug, similarity is measured between the bug report and each node of the NPDG using Vector Space Model (VSM). Finally, the buggy statements are ranked based on the similarity scores. Rigorous experimen
ts on three open source projects named as Eclipse, SWT and PasswordProtector show that SBL localizes the buggy statements with reasonable accuracies.
(More)