Interactive Synthesis of Code Snippets

Gvero, Tihomir; Kunčak, Viktor; Piskač, Ružica

doi:10.1007/978-3-642-22110-1_33

Cited by 30 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been much research on helping programmers explore new APIs by mining existing code to find snippets that are used in practice [20,12,27,35,9]. Unlike such systems, by evaluating code at runtime, we can differentiate between different values of the same type, downcast precisely, and use more general specifications, as in Section 2.…”

Section: Related Workmentioning

confidence: 99%

CodeHint: dynamic and interactive synthesis of code snippets

Galenson

Reames

Bodík

et al. 2014

Proceedings of the 36th International Conference on Software Engineering

102

View full text Add to dashboard Cite

There are many tools that help programmers find code fragments, but most are inexpressive and rely on static information. We present a new technique for synthesizing code that is dynamic (giving accurate results and allowing programmers to reason about concrete executions), easy-to-use (supporting a wide range of correctness specifications), and interactive (allowing users to refine the candidate code snippets). Our implementation, which we call CodeHint, generates and evaluates code at runtime and hence can synthesize real-world Java code that involves I/O, reflection, native calls, and other advanced language features. We have evaluated CodeHint in two user studies and show that its algorithms are efficient and that it improves programmer productivity by more than a factor of two.

show abstract

Section: Related Workmentioning

confidence: 99%

CodeHint: dynamic and interactive synthesis of code snippets

Galenson

Reames

Bodík

et al. 2014

Proceedings of the 36th International Conference on Software Engineering

102

View full text Add to dashboard Cite

show abstract

“…Our approach therefore requires fewer inputs than the pioneering work on the Prospector tool [18], or than the recent work of Perelman et al [20]. A general idea of our approach and a first prototype implementation was demonstrated already in [10].…”

Section: Introductionmentioning

confidence: 94%

Complete completion using types and weights

GveroTihomir¹,

KuncakViktor²,

KurajIvan³

et al. 2013

SIGPLAN Not.

Self Cite

View full text Add to dashboard Cite

Developing modern software typically involves composing functionality from existing libraries. This task is difficult because libraries may expose many methods to the developer. To help developers in such scenarios, we present a technique that synthesizes and suggests valid expressions of a given type at a given program point. As the basis of our technique we use type inhabitation for lambda calculus terms in long normal form. We introduce a succinct representation for type judgements that merges types into equivalence classes to reduce the search space, then reconstructs any desired number of solutions on demand. Furthermore, we introduce a method to rank solutions based on weights derived from a corpus of code. We implemented the algorithm and deployed it as a plugin for the Eclipse IDE for Scala. We show that the techniques we incorporated greatly increase the effectiveness of the approach. Our evaluation benchmarks are code examples from programming practice; we make them available for future comparisons.

show abstract

“…PARSEWeb [35] also suggests a sequence of API calls but this time the search for the sequence is guided by the source code available on the Web, thus helping to eliminate many otherwise undesirable sequences. More recent work [15,16,26] focuses on code completion by (statically) synthesizing expressions of a given type at a particular program point (these works examine the program context around that point). To find the most likely expressions desired by the programmer, these approaches also rely on ranking algorithms to handle the large numbers of potential candidates.…”

Section: Related Workmentioning

confidence: 99%

Code completion with statistical language models

Raychev

Vechev

Yahav

2014

Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation

361

156

View full text Add to dashboard Cite

We address the problem of synthesizing code completions for programs using APIs. Given a program with holes, we synthesize completions for holes with the most likely sequences of method calls.Our main idea is to reduce the problem of code completion to a natural-language processing problem of predicting probabilities of sentences. We design a simple and scalable static analysis that extracts sequences of method calls from a large codebase, and index these into a statistical language model. We then employ the language model to find the highest ranked sentences, and use them to synthesize a code completion. Our approach is able to synthesize sequences of calls across multiple objects together with their arguments.Experiments show that our approach is fast and effective. Virtually all computed completions typecheck, and the desired completion appears in the top 3 results in 90% of the cases.

show abstract

Interactive Synthesis of Code Snippets

Cited by 30 publications

References 7 publications

CodeHint: dynamic and interactive synthesis of code snippets

CodeHint: dynamic and interactive synthesis of code snippets

Complete completion using types and weights

Code completion with statistical language models

Contact Info

Product

Resources

About