A Mixed-Method Approach to Recommend Corrections and Correct REST Antipatterns

Many companies, e.g., Facebook and YouTube, use the REST architecture and provide REST APIs to their clients. Like any other software systems, REST APIs need maintenance and must evolve to improve and stay relevant. Antipatterns-poor design practices-hinder this maintenance and evolution. Although the literature defines many antipatterns and proposes approaches for their (automatic) detection, their correction did not receive much attention. Therefore, we apply a mixed-method approach to study REST APIs and REST antipatterns with the objectives to recommend corrections or, when possible, actually correct the REST antipatterns. Qualitatively, via case studies, we analyse the evolution of 11 REST APIs, including Facebook, Twitter, and YouTube, over six years. We detect occurrences of eight REST antipatterns in the years 2014, 2017, and 2020 in 17 versions of 11 REST APIs. Thus, we show that (1) REST APIs and antipatterns evolve over time and (2) developers seem to remove antipatterns. Qualitatively via a discourse analysis, we analyse developers' forums and report that developers are concerned with the occurrences of REST antipatterns and discuss corrections to these antipatterns. Following these qualitative studies, using an engineering-research approach, we propose the following novel and unique contributions: (1) we describe and compare the corrections of eight REST antipatterns from the academic literature and from developers' forums; (2) we devise and describe algorithms to recommend corrections to some of these antipatterns; (3) we present algorithms and a tool to correct some of these antipatterns by intercepting and modifying responses from REST APIs; and, (4) we validate the recommendations and the corrections manually and via a survey answered by 24 REST developers. Thus, we propose to REST API developers and researchers the first, grounded approach to correct REST antipatterns.