Source Code Retrieval from Large Software Libraries for Automatic Bug Localization

This dissertation advances the state-of-the-art in information retrieval (IR) based approaches to automatic bug localization in software. In an IR-based approach, one first creates a search engine using a probabilistic or a deterministic model for the files in a software library. Subsequently, a bug report is treated as a query to the search engine for retrieving the files relevant to the bug. With regard to the new work presented, we first demonstrate the importance of taking version histories of the files into account for achieving significant improvements in the precision with which the files related to a bug are located. This is motivated by the realization that the files that have not changed in a long time are likely to have ``stabilized and are therefore less likely to contain bugs. Subsequently, we look at the difficulties created by the fact that developers frequently use abbreviations and concatenations that are not likely to be familiar to someone trying to locate the files related to a bug. We show how an initial query can be automatically reformulated to include the relevant actual terms in the files by an analysis of the files retrieved in response to the original query for terms that are proximal to the original query terms. The last part of this dissertation generalizes our term-proximity based work by using Markov Random Fields (MRF) to model the inter-term dependencies in a query vis-a-vis the files. Our MRF work redresses one of the major defects of the most commonly used modeling approaches in IR, which is the loss of all inter-term relationships in the documents