Deep code search

Over the years of software development, a vast amount of source code has been accumulated. Many code search tools were proposed to help programmers reuse previously-written code by performing free-text queries over a large-scale codebase. Our experience shows that the accuracy of these code search tools are often unsatisfactory. One major reason is that existing tools lack of query understanding ability. In this paper, we propose CodeHow, a code search technique that can recognize potential APIs a user query refers to. Having understood the potentially relevant APIs, CodeHow expands the query with the APIs and performs code retrieval by applying the Extended Boolean model, which considers the impact of both text similarity and potential APIs on code search. We deploy the backend of CodeHow as a Microsoft Azure service and implement the front-end as a Visual Studio extension. We evaluate CodeHow on a large-scale codebase consisting of 26K C# projects downloaded from GitHub. The experimental results show that when the top 1 results are inspected, CodeHow achieves a precision score of 0.794 (i.e., 79.4% of the first returned results are relevant code snippets). The results also show that CodeHow outperforms conventional code search tools. Furthermore, we perform a controlled experiment and a survey of Microsoft developers. The results confirm the usefulness and effectiveness of CodeHow in programming practices.

Code retrieval is to find the code snippet from a large corpus of source code repositories that highly matches the query of natural language description. Recent work mainly uses natural language processing techniques to process both query texts (i.e., human natural language) and code snippets (i.e., machine programming language), however, neglecting the deep structured features of query texts and source codes, both of which contain rich semantic information. In this article, we propose an end-to-end deep graph matching and searching (DGMS) model based on graph neural networks for the task of semantic code retrieval. To this end, we first represent both natural language query texts and programming language code snippets with the unified graph-structured data, and then use the proposed graph matching and searching model to retrieve the best matching code snippet. In particular, DGMS not only captures more structural information for individual query texts or code snippets, but also learns the fine-grained similarity between them by cross-attention based semantic matching operations. We evaluate the proposed DGMS model on two public code retrieval datasets with two representative programming languages (i.e., Java and Python). Experiment results demonstrate that DGMS significantly outperforms state-of-the-art baseline models by a large margin on both datasets. Moreover, our extensive ablation studies systematically investigate and illustrate the impact of each part of DGMS.

CRaDLe: Deep code retrieval based on semantic Dependency Learning

To accelerate software development, developers frequently search and reuse existing code snippets from a large-scale codebase, e.g., GitHub. Over the years, researchers proposed many information retrieval (IR)-based models for code search, but they fail to connect the semantic gap between query and code. An early successful deep learning (DL)-based model DeepCS solved this issue by learning the relationship between pairs of code methods and corresponding natural language descriptions. Two major advantages of DeepCS are the capability of understanding irrelevant/noisy keywords and capturing sequential relationships between words in query and code. In this article, we proposed an IR-based model CodeMatcher that inherits the advantages of DeepCS (i.e., the capability of understanding the sequential semantics in important query words), while it can leverage the indexing technique in the IR-based model to accelerate the search response time substantially. CodeMatcher first collects metadata for query words to identify irrelevant/noisy ones, then iteratively performs fuzzy search with important query words on the codebase that is indexed by the Elasticsearch tool and finally reranks a set of returned candidate code according to how the tokens in the candidate code snippet sequentially matched the important words in a query. We verified its effectiveness on a large-scale codebase with ~41K repositories. Experimental results showed that CodeMatcher achieves an MRR (a widely used accuracy measure for code search) of 0.60, outperforming DeepCS, CodeHow, and UNIF by 82%, 62%, and 46%, respectively. Our proposed model is over 1.2K times faster than DeepCS. Moreover, CodeMatcher outperforms two existing online search engines (GitHub and Google search) by 46% and 33%, respectively, in terms of MRR. We also observed that: fusing the advantages of IR-based and DL-based models is promising; improving the quality of method naming helps code search, since method name plays an important role in connecting query and code.

JavaScript frameworks, such as jQuery, are widely used for developing web applications. To facilitate using these JavaScript frameworks to implement a feature (e.g., functionality), a large number of programmers often search for code snippets that implement the same or similar feature. However, existing code search approaches tend to be ineffective, without taking into account the fact that JavaScript code snippets often implement a feature based on various relationships (e.g., sequencing, condition, and callback relationships) among the invoked framework API methods. To address this issue, we present a novel Relationship-Aware Code Search (RACS) approach for finding code snippets that use JavaScript frameworks to implement a specific feature. In advance, RACS collects a large number of code snippets that use some JavaScript frameworks, mines API usage patterns from the collected code snippets, and represents the mined patterns with method call relationship (MCR) graphs, which capture framework API methods' signatures and their relationships. Given a natural language (NL) search query issued by a programmer, RACS conducts NL processing to automatically extract an action relationship (AR) graph, which consists of actions and their relationships inferred from the query. In this way, RACS reduces code search to the problem of graph search: finding similar MCR graphs for a given AR graph. We conduct evaluations against representative real-world jQuery questions posted on Stack Overflow, based on 308,294 code snippets collected from over 81,540 files on the Internet. The evaluation results show the effectiveness of RACS: the top 1 snippet produced by RACS matches the target code snippet for 46% questions, compared to only 4% achieved by a relationship-oblivious approach.

Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance. However, researchers have yet been able to effectively leverage the intrinsic connection between the two tasks as they train these tasks in a separate or pipeline manner, which means their performance can not be well balanced. In this paper, we propose a novel end-to-end model for the two tasks by introducing an additional code generation task. More specifically, we explicitly exploit the probabilistic correlation between code summarization and code generation with dual learning, and utilize the two encoders for code summarization and code generation to train the code retrieval task via multi-task learning. We have carried out extensive experiments on an existing dataset of SQL and Python, and results show that our model can significantly improve the results of the code retrieval task over the-state-of-art models, as well as achieve competitive performance in terms of BLEU score for the code summarization task.

In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the principal challenge of modality misalignment between code snippets and natural language queries, particularly with the demonstrated code generation capabilities of Large Language Models (LLMs). Nevertheless, our preliminary investigations indicate that the improvements conferred by such an LLM-augmented framework are somewhat constrained. This limitation could potentially be ascribed to the fact that the generated codes, albeit functionally accurate, frequently display a pronounced stylistic deviation from the ground truth code in the codebase. In this paper, we extend the foundational GAR framework and propose a simple yet effective method that additionally Rewrites the Code (ReCo) within the codebase for style normalization. Experimental results demonstrate that ReCo significantly boosts retrieval accuracy across sparse (up to 35.7%), zero-shot dense (up to 27.6%), and fine-tuned dense (up to 23.6%) retrieval settings in diverse search scenarios. To further elucidate the advantages of ReCo and stimulate research in code style normalization, we introduce Code Style Similarity, the first metric tailored to quantify stylistic similarities in code. Notably, our empirical findings reveal the inadequacy of existing metrics in capturing stylistic nuances. The source code and data are available at https: //github.com/Alex-HaochenLi/ReCo.

Code search methods, especially those that allow programmers to raise queries in a natural language, plays an important role in software development. It helps to improve programmers' productivity by returning sample code snippets from the Internet and/or source-code repositories for their natural-language queries. Meanwhile, there are many code search methods in the literature that support natural-language queries. Difficulties exist in recognizing the strengths and weaknesses of each method and choosing the right one for different usage scenarios, because (1) the implementations of those methods and the datasets for evaluating them are usually not publicly available, and (2) some methods leverage different training datasets or auxiliary data sources and thus their effectiveness cannot be fairly measured and may be negatively affected in practical uses. To build a common ground for measuring code search methods, this paper builds CosBench, a dataset that consists of 1000 projects, 52 code-independent natural-language queries with ground truths, and a set of scripts for calculating four metrics on code research results. We have evaluated four IR (Information Retrieval)-based and two DL (Deep Learning)-based code search methods on CosBench. The empirical evaluation results clearly show the usefulness of the CosBench dataset and various strengths of each code search method. We found that DL-based methods are more suitable for queries on reusing code, and IR-based ones for queries on resolving bugs and learning API uses.

This paper describes two approaches to the automatic generation of behavioral VHDL models from descriptions written in natural language. Both approaches are based on a modeling style in which behavior is represented by a system of interconnected processes. The first approach employs a semantic grammar to directly generate a single VHDL process from a paragraph written in a restricted English called ModelSpeak. The second approach accepts more general English and generates models consisting of multiple processes. series of sentences describing the behavior of a single process and generated correct VHDL code for it. This interface requires the behavior be expressed in a highly restricted English called ModelSpeak (10). Conditional expressions (if statements) may be nested to two levels, and interaction is invoked by the interface to resolve scope ambiguity of loops. This interface is implemented with a semantic grammar (3) in Prolog. The second interface (Approach II) to the Modeler's Assistant for natural language is substantially more complex, but accepts more general English expressions and generates multiple-process models. In this approach, each sentence is parsed by a bottom-up, parallel chart parser to generate a set of valid parse trees. The trees are examined by a Semantic Analyzer (7) to determine one which is semantically correct, and a conceptual graph (14) (semantic network) of its meaning is generated. Once the conceptual graph of individual sentences are joined together (12), a program called the Linker (8) analyzes the graph to produce a Process Model Graph and VHDL process code for the Modeler's Assistant. Nodes in the conceptual graph representing verbs typically generate processes or the conditions which govern them. Nodes representing objects generate signals. The modeling style underlying the Linker produces a sizable collection of processes, each consisting of a single if_then statement. To avoid unnecessary bus resolutions, multiple processes assigning to the same signal are merged. Since signal types are generally not expressed in the English description, they may be added interactively later. Before describing the approaches in more detail, related research on natural language interfaces is reviewed briefly.

Traditional source code authorship identification methods often rely on features such as textual similarity, programming style or metadata, however, these methods often struggle to extract the precise source code authoring style when dealing with large-scale code bases or complex programming patterns, resulting in poor performance. Therefore, this paper proposes a Transformer-based high fine-grained source code author attribution method.Aiming at the problem of roughness of existing literature on word segmentation, this paper proposes a high fine-grained source code segmentation method to extract higher fine-grained features. Aiming at the problem of feature dimension redundancy, this paper adopts the Transformer network to locate sensitive features that can characterise the author's style.To verify the effectiveness of the model, it was tested on GCJ-C++ and GCJ-Java datasets. The experimental results show that the proposed method model achieves higher recognition accuracy in the source code authorship attribution problem compared to the traditional methods.

Internet code search is quite popular research area. StackOverflow allows developers to ask and answer questions about code. Previous approach to search code on StackOverflow uses tf-idf method that based on number of occurrences of words to recommend source code. This method has the disadvantage that variable or method identifiers are considered as normal words, even though identifiers are often a combination of two or more words. For example, there is an identifier named “randomString”. In that case, if we search using a keyword “random” the system probably will not recommend “randomString” because both words are different. Concept location can tackle this problem. Concept location has been used widely to obtain the correlation between code with a specific concepts or features. Previous research of concept location only focused on source code's comments, and relation among the objects within the source code. This research proposes a mechanism for finding code on StackOverflow uses Latent Dirichlet Allocation (LDA) using concept location in the preprocessing stage. Questions, answers, and code snippets about Java programming are downloaded from StackOverflow to a local repository. Corpuses are generated by extracting questions, answers and code snippets. Inferencing concept location from source code is created using LDA algorithm. Developers query concepts and then system will recommend source code based on the relevant concepts. The result of the experiment shows that the system is able to recommend source code with 48% average of precision and 58% average of recall.

Modern Q&A websites, such as Stack Overflow, use social media to provide concise answers, and offer rich technical context with quality assessment capabilities. Although some of the answers may include executable code snippets, they are entangled in free text and are not easily extracted. Q&A websites are not designed for such direct code reuse. We present Example Overflow, a code search and recommendation tool which brings together social media and code recommendation systems. Example Overflow enables crowd-sourced software development by utilizing both textual and social information, which accompany source code on the Web. Its browsing mechanism minimizes the context switch associated with other code search tools. In this paper we describe the development of the tool, provide preliminary evaluation, and discuss its contribution to an example centric programming paradigm.

The task of semantic code search is to retrieve code snippets from a source code corpus based on an information need expressed in natural language. The semantic gap between natural language and programming languages has for long been regarded as one of the most significant obstacles to the effectiveness of keyword-based information retrieval (IR) methods. It is a common assumption that “traditional” bag-of-words IR methods are poorly suited for semantic code search: our work empirically investigates this assumption. Specifically, we examine the effectiveness of two traditional IR methods, namely BM25 and RM3, on the CodeSearchNet Corpus, which consists of natural language queries paired with relevant code snippets. We find that the two keyword-based methods outperform several pre-BERT neural models. We also compare several code-specific data pre-processing strategies and find that specialized tokenization improves effectiveness.

Automatic pseudocode generation has become a growing demand for software engineers. However, most code snippets in production environments do not have corresponding pseudocode, because writing comments or textual descriptions of program source code typically consumes a lot of manpower. In this paper, we treat pseudocode generation task as a language translation task which means translating programming code into natural language description, and conduct a sophisticated neural machine translation model, attention seq2seq model, on this task. Experiments on a real-world dataset from an open source Python project reveal that seq2seq model could generate understandable pseudocode for practical usage.

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.