出版社：European Association of Software Science and Technology (EASST)
摘要：Thousands of open source software (OOS) projects are available for collaboration in platforms like Github or Sourceforge. However, like traditional software, OOS projects have different quality levels. The developer, or the end-user, need to know the quality of a given project before starting the collaboration or its usage---they might of course to trust in the package before taking a decision. In the context of OSS, trustability is a much more sensible concern; mainly end-users usually prefer to pay for proprietary software, to feel more confident in the package quality. OSS projects can be assessed like traditional software packages using the well known software metrics. In this paper we want to go further and propose a finer grain process to do such quality analysis, precisely tuned for this unique development environment. As it is known, along the last years, open source communities have created their own standards and \emph{best practices}. Nevertheless, the classic software metrics do not take into account the \emph{best practices} established by the community. We feel that it could be worthwhile to consider this peculiarity as a complementary source of assessment data. Taking Ruby OSS community and projects as framework, this paper discusses the role of \emph{best practices} in measuring software quality.
