A Survey of Source Code Search: A 3-Dimensional Perspective

A collection of academic papers on code search techniques from a 3-dimensional (query-end, code-end, match-end) perspective.

NOTE: We intend to keep updating with the most recent papers whenever time permits, and we warmly welcome pull requests or issues regarding any missing papers. If you find any information is incorrect, please feel free to contact us. We will promptly confirm and make the necessary corrections. All researchers are encouraged to participate in enhancing this repository and expanding the knowledge within the field of source code search.

Citation

Please read and cite our paper:

@article{2023-Code-Search-Survey-3D-Perspective,
  title={A Survey of Source Code Search: A 3-Dimensional Perspective},
  author={Weisong Sun, Chunrong Fang, Yifei Ge, Yuling Hu, Yuchen Chen, Quanjun Zhang, Xiuting Ge, Yang Liu, Zhenyu Chen},
  journal={arXiv preprint arXiv:2301.03270},
  year={2023}
}

---

Overall Framework of the code search technique

Collected Papers in Query End

Number	Paper Title	Venue	Year	Code Available
1	Self-Supervised Query Reformulation for Code Search	arXiv	2023	yes
2	XCoS: Explainable Code Search Based on Query Scoping and Knowledge Graph	TOSEM	2023	no
3	Hyperbolic Code Retrieval: A Novel Approach for Efficient Code Search Using Hyperbolic Space Embeddings	arXiv	2023	no
4	CSSAM:Code Search via Attention Matching of Code Semantics and Structures	arXiv	2022	no
5	Utilizing Edge Attention in Graph-Based Code Search	SEKE	2022	no
6	Incorporating Code Structure and Quality in Deep Code Search	Applied Sciences	2022	no
7	Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus	arXiv	2022	yes
8	Joint Embedding of Semantic and Statistical Features for Effective Code Search	Applied Sciences	2022	no
9	Boosting Code Search with Structural Code Annotation	Electronics	2022	no
10	Fine-grained Co-Attentive Representation Learning for Semantic Code Search	SANER	2022	yes
11	CSRS: Code Search with Relevance Matching and Semantic Matching	arXiv	2022	no
12	OCoR: An Overlapping-Aware Code Retriever	Computing Surveys	2022	yes
13	Deep Graph Matching and Searching for Semantic Code Retrieval	TKDD	2021	yes
14	Two-Stage Attention-Based Model for Code Search with Textual and Structural Features	SANER	2021	yes
15	An Intelligent Code Search Approach Using Hybrid Encoders	WCMC	2021	no
16	deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search	TOSEM	2021
17	Enriching Query Semantics for Code Search with Reinforcement Learning	arXiv	2021	no
18	Multimodal Representation for Neural Code Search	ICSME	2021	yes
19	Search for Compatible Source Code	IJSEKE	2021	no
20	Self-Attention Networks for Code Search	IST	2021	yes
21	CoNCRA: A Convolutional Neural Network Code Retrieval Approach	arXiv	2020	no
22	PSCS: A Path-based Neural Model for Semantic Code Search	arXiv	2020	no
23	Improving Code Search with Co-Attentive Representation Learning	ICPC	2020	no
24	CSDA: A novel attention-based LSTM approach for code search	JPCS	2020	no
25	Adaptive Deep Code Search	ICPC	2020	no
26	CRaDLe: Deep Code Retrieval Based on Semantic Dependency Learning	arXiv	2020	no
27	Unsupervised software repositories mining and its application to code search	SPE	2020	no
28	Automatic query reformulation for code search using crowdsourced knowledge	ESE	2019	no
29	Neural query expansion for code search	PLDI	2019	no
30	Deep learning the semantics of change sequences for query expansion	SPE	2019	no
31	Multi-modal Attention Network Learning for Semantic Source Code Retrieval	ASE	2019	no
32	Query expansion based on statistical learning from code changes	SPE	2018	no
33	LANGUA SOURCE CODE RETRIEVAL USING KEYWORD & IDENTIFIER LEXICAL GE-AGNOSTICPATTERN	IJSECS	2018	no
34	Interactive Query Reformulation for Source-Code Search With Word Relations	IEEE Access	2018	no
35	Retrieval on source code: a neural code search	PLDI	2018	no
36	Deep code search	ICSE	2018	yes
37	Expanding Queries for Code Search Using Semantically Related API Class-names	TSE	2018	no
38	Augmenting and structuring user queries to support efficient free-form code search	ESE	2018	no
39	Learning to rank code examples for code search engines	ESE	2017	no
40	IECS: Intent-Enforced Code Search via Extended Boolean Model	IFS	2017	no
41	APIBook: an effective approach for finding APIs	Internetware	2016	no
42	Query Expansion Based on Crowd Knowledge for Code Search	TSC	2016	no
43	Query expansion via WordNet for effective code search	SANER	2015	no
44	CodeHow: Effective Code Search Based on API Understanding and Extended Boolean Model	ASE	2015	no

---

Collected Papers in Code End

Number	Paper Title	Venue	Year	Code Available
1	GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search	TSE	2023	yes
2	Hyperbolic Code Retrieval: A Novel Approach for Efficient Code Search Using Hyperbolic Space Embeddings	arXiv	2023	no
3	CSRS: Code Search with Relevance Matching and Semantic Matching	arXiv	2022	no
4	SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations	arXiv	2022	no
5	Accelerating Code Search with Deep Hashing and Code Classification	arXiv	2022	no
6	Joint Embedding of Semantic and Statistical Features for Effective Code Search	Applied Sciences	2022	no
7	Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus	arXiv	2022	yes
8	Utilizing Edge Attention in Graph-Based Code Search	SEKE	2022	no
9	CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words	TOSEM	2022	no
10	CSSAM:Code Search via Attention Matching of Code Semantics and Structures	arXiv	2022	no
11	Fine-grained Co-Attentive Representation Learning for Semantic Code Search	SANER	2022	yes
12	Incorporating Code Structure and Quality in Deep Code Search	Applied Sciences	2022	no
13	Boosting Code Search with Structural Code Annotation	Electronics	2022	no
14	OCoR: An Overlapping-Aware Code Retriever	Computing Surveys	2022	yes
15	An Intelligent Code Search Approach Using Hybrid Encoders	WCMC	2021	no
16	Search for Compatible Source Code	IJSEKE	2021	no
17	GraphCodeBERT: Pre-training Code Representations with Data Flow	arXiv	2021	no
18	Self-Attention Networks for Code Search	IST	2021	yes
19	Two-Stage Attention-Based Model for Code Search with Textual and Structural Features	SANER	2021	yes
20	Enriching Query Semantics for Code Search with Reinforcement Learning	arXiv	2021	no
21	Deep Graph Matching and Searching for Semantic Code Retrieval	TKDD	2021	yes
22	deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search	TOSEM	2021	yse
23	FACER: An API Usage-based Code-example Recommender for Opportunistic Reuse	ESE	2021	no
24	Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code Search	arXiv	2021	no
25	Multimodal Representation for Neural Code Search	ICSME	2021	yes
26	Neural joint attention code search over structure embeddings for software Q&A sites	JSS	2020	yes
27	CodeBERT: A Pre-Trained Model for Programming and Natural Languages	arXiv	2020	yes
28	PSCS: A Path-based Neural Model for Semantic Code Search	arXiv	2020	no
29	Recommendation Based on Java Code Analysis and Search	FSDM	2020	yes
30	CSDA: A novel attention-based LSTM approach for code search	JPCS	2020	no
31	A Multi-Perspective Architecture for Semantic Code Search	ACL	2020	yes
32	Enhancing example-based code search with functional semantics	JSS	2020	no
33	Improving Code Search with Co-Attentive Representation Learning	ICPC	2020	no
34	Adaptive Deep Code Search	ICPC	2020	no
35	CoNCRA: A Convolutional Neural Network Code Retrieval Approach	arXiv	2020	no
36	COSEA: Convolutional Code Search with Layer-wise Attention	arXiv	2020	no
37	CRaDLe: Deep Code Retrieval Based on Semantic Dependency Learning	arXiv	2020	no
38	ROSF: Leveraging Information Retrieval and Supervised Learning for Recommending Code Snippets	TSC	2019	no
39	Automatic query reformulation for code search using crowdsourced knowledge	ESE	2019	no
40	Multi-modal Attention Network Learning for Semantic Source Code Retrieval	ASE	2019	no
41	Augmenting and structuring user queries to support efficient free-form code search	ESE	2018	no
42	CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning	arXiv	2018	yes
43	Expanding Queries for Code Search Using Semantically Related API Class-names	TSE	2018	no
44	Retrieval on source code: a neural code search	PLDI	2018	no
45	A neural framework for retrieval and summarization of source code	ASE	2018	no
46	Deep code search	ICSE	2018	yse
47	Learning to rank code examples for code search engines	ESE	2017	no
48	CodeHow: Effective Code Search Based on API Understanding and Extended Boolean Model	ASE	2015	no
49	Portfolio: finding relevant functions and their usage	ICSE	2011	no
50	Sourcerer: mining and searching internet-scale software repositories	DMKD	2009	no

---

Collected Papers in Match End

Number	Paper Title	Venue	Year	Code Available
1	Self-Supervised Query Reformulation for Code Search	arXiv	2023	yes
2	Hyperbolic Code Retrieval: A Novel Approach for Efficient Code Search Using Hyperbolic Space Embeddings	arXiv	2023	no
3	Accelerating Code Search with Deep Hashing and Code Classification	arXiv	2022	no
4	Cascaded Fast and Slow Models for Efficient Semantic Code Search	arXiv	2022	no
5	CSSAM:Code Search via Attention Matching of Code Semantics and Structures	arXiv	2022	no
6	Incorporating Code Structure and Quality in Deep Code Search	Applied Sciences	2022	no
7	Utilizing Edge Attention in Graph-Based Code Search	SEKE	2022	no
8	CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words	TOSEM	2022	no
9	OCoR: An Overlapping-Aware Code Retriever	Computing Surveys	2022	yes
10	Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus	arXiv	2022	yes
11	Joint Embedding of Semantic and Statistical Features for Effective Code Search	Applied Sciences	2022	no
12	Fine-grained Co-Attentive Representation Learning for Semantic Code Search	SANER	2022	yes
13	SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations	arXiv	2022	no
14	Enriching Query Semantics for Code Search with Reinforcement Learning	arXiv	2021	no
15	Two-Stage Attention-Based Model for Code Search with Textual and Structural Features	SANER	2021	yes
16	An Intelligent Code Search Approach Using Hybrid Encoders	WCMC	2021	no
17	Deep Graph Matching and Searching for Semantic Code Retrieval	TKDD	2021	yes
18	Multimodal Representation for Neural Code Search	ICSME	2021	yes
19	Self-Attention Networks for Code Search	IST	2021	yes
20	Search for Compatible Source Code	IJSEKE	2021	no
21	FACER: An API Usage-based Code-example Recommender for Opportunistic Reuse	ESE	2021	no
22	GraphCodeBERT: Pre-training Code Representations with Data Flow	arXiv	2021	no
23	deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search	TOSEM	2021
24	GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search	arXiv	2021	no
25	PSCS: A Path-based Neural Model for Semantic Code Search	arXiv	2020	no
26	CodeBERT: A Pre-Trained Model for Programming and Natural Languages	arXiv	2020	yes
27	Improving Code Search with Co-Attentive Representation Learning	ICPC	2020	no
28	CSDA: A novel attention-based LSTM approach for code search	JPCS	2020	no
29	Adaptive Deep Code Search	ICPC	2020	no
30	Neural joint attention code search over structure embeddings for software Q&A sites	JSS	2020	yes
31	Unsupervised software repositories mining and its application to code search	SPE	2020	no
32	A Multi-Perspective Architecture for Semantic Code Search	ACL	2020	yes
33	CRaDLe: Deep Code Retrieval Based on Semantic Dependency Learning	arXiv	2020	no
34	Recommendation Based on Java Code Analysis and Search	FSDM	2020	yes
35	CoNCRA: A Convolutional Neural Network Code Retrieval Approach	arXiv	2020	no
36	TranS^3: A Transformer-based Framework for Unifying Code Summarization and Code Search	arXiv	2020	no
37	Enhancing example-based code search with functional semantics	JSS	2020	no
38	ROSF: Leveraging Information Retrieval and Supervised Learning for Recommending Code Snippets	TSC	2019	no
39	Multi-modal Attention Network Learning for Semantic Source Code Retrieval	ASE	2019	no
40	Neural query expansion for code search	PLDI	2019	no
41	Expanding Queries for Code Search Using Semantically Related API Class-names	TSE	2018	no
42	Augmenting and structuring user queries to support efficient free-form code search	ESE	2018	no
43	Retrieval on source code: a neural code search	PLDI	2018	no
44	LANGUAGE-AGNOSTIC SOURCE CODE RETRIEVAL USING KEYWORD & IDENTIFIER LEXICAL PATTERN	IJSECS	2018	no
45	A neural framework for retrieval and summarization of source code	ASE	2018	no
46	CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning	arXiv	2018	yes
47	Deep code search	ICSE	2018	yes
48	Query expansion based on statistical learning from code changes	SPE	2018	no
49	IECS: Intent-Enforced Code Search via Extended Boolean Model	IFS	2017	no
50	Learning to rank code examples for code search engines	ESE	2017	no
51	Query Expansion Based on Crowd Knowledge for Code Search	TSC	2016	no
52	CodeHow: Effective Code Search Based on API Understanding and Extended Boolean Model	ASE	2015	no