Package-Aware Approach for Repository-Level Code Completion in Pharo

TL;DR

This paper introduces a package-aware heuristic for code completion in Pharo that improves suggestion relevance by prioritizing classes within the same package or repository, enhancing developer productivity.

Contribution

It proposes a novel heuristic that incorporates repository structure into code completion, addressing limitations of existing global name suggestions in Pharo.

Findings

MRR improved with package-aware heuristic

More relevant suggestions within same package or repository

Outperforms default global namespace heuristic

Abstract

Pharo offers a sophisticated completion engine based on semantic heuristics, which coordinates specific fetchers within a lazy architecture. These heuristics can be recomposed to support various activities (e.g., live programming or history usage navigation). While this system is powerful, it does not account for the repository structure when suggesting global names such as class names, class variables, or global variables. As a result, it does not prioritize classes within the same package or project, treating all global names equally. In this paper, we present a new heuristic that addresses this limitation. Our approach searches variable names in a structured manner: it begins with the package of the requesting class, then expands to other packages within the same repository, and finally considers the global namespace. We describe the logic behind this heuristic and evaluate it against the default semantic heuristic and one that directly queries the global namespace. Preliminary results indicate that the Mean Reciprocal Rank (MRR) improves, confirming that package-awareness completions deliver more accurate and relevant suggestions than the previous flat global approach.