Incorporating Code Structure and Quality in Deep Code Search

Abstract

Developers usually search for reusable code snippets to improve software development efficiency. Existing code search methods, including methods based on full-text or deep learning, have two disadvantages: (1) ignoring structural information of code snippets, such as conditional statements and loop statements, and (2) ignoring quality information of code snippets, such as naming clarity and logical correctness. These disadvantages limit the performance of existing code search methods. In this paper, we propose a novel code search method named Structure and Quality based Deep Code Search (SQ-DeepCS). SQ-DeepCS introduces a code representation method called program slice to represent structual information as well as API usage of code snippets. Meanwhile, SQ-DeepCS introduces a novel deep neural network named Method-Description-Joint Embedding Neural Network (MD-JEnn) to weight the quality of code snippets. To evaluate the proposed methods, we train MD-JEnn and evaluate SQ-DeepCS by searching for code snippets with respect to the top-rated questions from Stack Overflow. We use four evaluation indicators to measure the effectiveness of SQ-DeepCS: FRank, SuccessRate@k, PrecisionRate@k, and Mean Reciprocal Rank (MRR). The experimental results show that our approach can provide better results than existing techniques when searching for relevant code snippets.

Joint Embedding of Semantic and Statistical Features for Effective Code Search

“…During software development, 19% of working time is spent on code search, the existing code snippets in open-source communities can be reused to implement current requirements [2]. An effective code search approach can significantly improve the efficiency of software development [3][4][5]. Existing code search research mainly focuses on query expansion and search engine optimization, which are constructed based on semantic and statistical features.…”

Boosting Code Search with Structural Code Annotation

“…Code search is an important technique to improve effectiveness and efficiency of software development [1][2][3]. Code search is firstly conducted by matching keyword text in a code base, then researchers enrich the matching model with some descriptions about candidate code snippets, i.e., code annotation [4,5]. Code annotation may contain a class name, method name, API sequence, structural relationships among code blocks, and descriptions from code comments and documents.…”