[Research Paper] Semantics-Based Code Search Using Input/Output Examples

Abstract

As the quality and quantity of open source code increase, semantics-based code search has become an emerging need for software developers to retrieve and reuse existing source code. We present an approach of semantics-based code search using input/output examples for the Java language. Our approach encodes Java methods in code repositories into path constraints via symbolic analysis and leverages SMT solvers to find the methods whose path constraints can satisfy the given input/output examples. Our approach extends the applicability of the semantics-based search technology to more general Java code compared with existing methods. To evaluate our approach, we encoded 1228 methods from GitHub and applied semanticsbased code search on 35 queries extracted from Stack Overflow. Correct method code for 29 queries was obtained during the search and the average search time was just about 48 seconds.

Enhancing example-based code search with functional semantics

“…This work extends our previous research reported in [22]. The main differences between this work and the previous one include the following.…”

Bind the gap: compiling real software to hardware FFT accelerators

“…Embeddings such as ProGraML [42] achieve upwards of 95% accuracy in clone detection, and a number of other machine-learning approaches using static information exist [30,51,55,95,101,132,134,139]. Dynamic runtime information can also be used for this task [129] and numerous approaches developed without machine learning exist [69,70,74,110]. API-recommendation tools [65,68] can also be used for algorithm identification.…”

Code Sophistication: From Code Recommendation to Logic Recommendation

“…Most code search approaches are based on information retrieval techniques to find relevant code snippets depending on a query either formulated directly by the developer or inferred from the code [1]. Some approaches focus on recommending specific types of snippets, such as framework usages [21], Java methods [1], exception handling examples [43], auxiliary functionalities [29] or API usages [42], while others are general purpose [22,23,25,35,45,49]. Approaches inferring a query from the code can be based on tokens and/or statements similarity [1,49], structural code features [21,25,35,43], or lexical ones [43].…”