Avoiding code pitfalls in Aspect-Oriented Programming

摘要

Aspect-Oriented Programming (AOP) is a maturing technique that requires a good comprehension of which types of mistakes programmers make during the development of applications. Unfortunately, the lack of such knowledge seems to represent one of the reasons for the cautious adoption of AOP in real software development projects. This paper reports on the results of a series of experiments whose main goal is to analyze and catalogue code pitfalls that are likely to lead programmers to make mistakes in AOP refactoring. Each experiment consists of a task that requires the aspectization of a crosscutting concern in one object-oriented application. Eight rounds of the experiment provided us with data of 98 AOP implementations from four crosscutting concerns in four different applications. Each participant of the experiment produced one implementation. Based on the analysis of these implementations, we (ⅰ) document six categories of recurring mistakes made by programmers, (ⅱ) correlate these mistakes with the programmer expertise in object-oriented programming, years of software development, and pair programming, and (ⅲ) derive a catalogue of code pitfalls which are likely to lead programmers to make the documented mistakes. We apply significance tests in order to statistically evaluate our results. We also present a prototype tool to warn programmers of the code pitfalls during refactoring activities.