RepoSummary: Feature-Oriented Summarization and Documentation Generation for Code Repositories

2025-10-13

AI Summary

Existing code repository summarization methods rely heavily on directory structure, hindering precise traceability between high-level functional features and low-level implementation methods, thereby impeding code comprehension and maintenance efficiency. This paper proposes a feature-oriented, repository-level summarization framework that integrates program analysis with natural language processing to construct a hierarchical functional-code mapping model, enabling automated documentation generation and multi-granularity traceability chain construction. Unlike conventional approaches, our method eliminates dependency on directory hierarchy. Evaluation shows significant improvements: 71.1% feature coverage and a 23.1-percentage-point gain in file-level traceability recall (reaching 53.0%). Moreover, the generated documentation exhibits enhanced conceptual coherence, formatting consistency, and readability. Our framework establishes a scalable, verifiable paradigm for intelligent code documentation.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Machine Learning: Dimensionality Reduction/Feature Selection

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Repository summarization is a crucial research question in development and maintenance for software engineering. Existing repository summarization techniques primarily focus on summarizing code according to the directory tree, which is insufficient for tracing high-level features to the methods that collaboratively implement them. To address these limitations, we propose RepoSummary, a feature-oriented code repository summarization approach that simultaneously generates repository documentation automatically. Furthermore, it establishes more accurate traceability links from functional features to the corresponding code elements, enabling developers to rapidly locate relevant methods and files during code comprehension and maintenance. Comprehensive experiments against the state-of-the-art baseline (HGEN) demonstrate that RepoSummary achieves higher feature coverage and more accurate traceability. On average, it increases the rate of completely covered features in manual documentation from 61.2% to 71.1%, improves file-level traceability recall from 29.9% to 53.0%, and generates documentation that is more conceptually consistent, easier to understand, and better formatted than that produced by existing approaches.

Problem

• Generates feature-oriented code repository summaries automatically
• Establishes traceability links from features to code elements
• Improves feature coverage and documentation quality over existing methods

Innovation

• Generates feature-oriented summaries for code repositories
• Automatically creates repository documentation from code
• Establishes traceability links between features and code