@conference {1721, title = {Orion: A Software Project Search Engine with Integrated Diverse Software Artifacts}, booktitle = {2013 18th International Conference on Engineering of Complex Computer Systems (ICECCS)}, year = {2013}, note = {The FLOSSMole12, Flossmetrics [3] and Sourcerer [1] projects collect data and/or provide statistics on their collected data, but are not suitable for selecting a subset or identifying a unique project based on desired properties.}, pages = {242 - 245}, publisher = {IEEE}, organization = {IEEE}, address = {Singapore, Singapore}, abstract = {What projects contain more than 10, 000 lines of code developed by less than 10 people and are still actively maintained with a high bug-fixing rate? To address the challenges for answering such enquiries, we develop an integrated search engine architecture that combines information from different types of software repositories from multiple sources. Our search engine facilitates the construction and execution of complex search queries using a uniform interface that transparently correlates different artifacts of project development and maintenance, such as source code information, version control systems metadata, bug tracking systems elements, and metadata on developer activities and interactions extracted from hosting platforms. We have built an extensible system with an initial capability of over 100, 000 projects collected from the web, featuring various software development artifacts. Using scenarios, we illustrate the benefits of such a search engine for different kinds of project seekers. }, keywords = {flossmole cited}, doi = {10.1109/ICECCS.2013.42}, url = {http://www.mysmu.edu/faculty/davidlo/papers/iceccs13-projectsearch.pdf}, author = {Bissyande, Tegawende F. and Thung, Ferdian and Lo, David and Jiang, Lingxiao and Reveillere, Laurent} }