SPELL: Synthesis of Programmatic Edits using LLMs

TL;DR

This paper introduces SPELL, a novel method that leverages large language models to extract and synthesize reusable code transformation scripts for automated library migration, overcoming data scarcity and manual effort.

Contribution

SPELL uses LLMs to generate migration examples and generalize them into transformation scripts, enabling automated API migration without relying on existing migration data.

Findings

Successfully generates diverse migration examples.

Synthesizes transformation scripts that generalize to real-world code.

Outperforms existing tools in Python library migrations.

Abstract

Library migration is a common but error-prone task in software development. Developers may need to replace one library with another due to reasons like changing requirements or licensing changes. Migration typically entails updating and rewriting source code manually. While automated migration tools exist, most rely on mining examples from real-world projects that have already undergone similar migrations. However, these data are scarce, and collecting them for arbitrary pairs of libraries is difficult. Moreover, these migration tools often miss out on leveraging modern code transformation infrastructure. In this paper, we present a new approach to automated API migration that sidesteps the limitations described above. Instead of relying on existing migration data or using LLMs directly for transformation, we use LLMs to extract migration examples. Next, we use an Agent to generalize those examples to reusable transformation scripts in PolyglotPiranha, a modern code transformation tool. Our method distills latent migration knowledge from LLMs into structured, testable, and repeatable migration logic, without requiring preexisting corpora or manual engineering effort. Experimental results across Python libraries show that our system can generate diverse migration examples and synthesize transformation scripts that generalize to real-world codebases.