Bug localization based on syntactical and semantic information of source code

doi:10.23919/JSEE.2023.000010

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (1): 236-246.doi: 10.23919/JSEE.2023.000010

• RELIABILITY • Previous Articles Next Articles

Bug localization based on syntactical and semantic information of source code

Xuefeng YAN¹^,²^,*(), Shasha CHENG¹(), Liqin GUO³()

¹ College of Computer Science Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
² Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 211106, China
³ State Key Laboratory of Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China

Received:2021-02-22 Online:2023-02-18 Published:2023-03-03
Contact: Xuefeng YAN E-mail:yxf@nuaa.edu.cn;shasha@nuaa.edu.cn;guo_96@163.com
About author:
YAN Xuefeng was born in 1975. He received his Ph.D. degree from Beijing Institute of Technology, China, in 2005. He is currently a professor with the College of Computer Science and Technology at Nanjing University of Aeronautics and Astronautics. His research interests include intelligent modeling, big data analysis, model based system engineering, complex system modeling and simulation theory and method. E-mail: yxf@nuaa.edu.cn

CHENG Shasha was born in 1996. She received her B.S. degree in computer science technology from Anhui University of Technology in 2018. Now she is pursuing her M.S. degree at Nanjing University of Aeronautics and Astronautics, China. Her research interests are bug localization, system engineering, and big data analysis. E-mail: shasha@nuaa.edu.cn

GUO Liqin was born in 1976. She is currently a senior engineer at State Key Laboratory of Intelligent Manufacturing System Technology. Her research interests include intelligent manufacture, complex system modeling and simulation theory and method. E-mail: guo_96@163.com
Supported by:
This work was supported by the National Key R&D Program of China (2018YFB1702700).

Abstract

Abstract:

The existing software bug localization models treat the source file as natural language, which leads to the loss of syntactical and structure information of the source file. A bug localization model based on syntactical and semantic information of source code is proposed. Firstly, abstract syntax tree (AST) is divided based on node category to obtain statement sequence. The statement tree is encoded into vectors to capture lexical and syntactical knowledge at the statement level. Secondly, the source code is transformed into vector representation by the sequence naturalness of the statement. Therefore, the problem of gradient vanishing and explosion caused by a large AST size is obviated when using AST to the represent source code. Finally, the correlation between bug reports and source files are comprehensively analyzed from three aspects of syntax, semantics and text to locate the buggy code. Experiments show that compared with other standard models, the proposed model improves the performance of bug localization, and it has good advantages in mean reciprocal rank (MRR), mean average precision (MAP) and Top N Rank.

Key words: bug report, abstract syntax tree, code representation, software bug localization

Xuefeng YAN, Shasha CHENG, Liqin GUO. Bug localization based on syntactical and semantic information of source code[J]. Journal of Systems Engineering and Electronics, 2023, 34(1): 236-246.

Figures/Tables 14

Fig 1

Fig 2

Fig 3

Table 1

Fig 4

Fig 5

Table 2

Table 3

Fig 6

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

References 24

1	ZHOU J, ZHANG H Y, LO D Where should the bugs be fixed? More accurate information retrieval-based bug localization based on bug reports. Proc. of the IEEE 34th International Conference on Software Engineering, 2012, 14- 24.
2	HUO X, LI M, ZHOU Z H Learning unified features from natural and programming languages for locating buggy source code. Proc. of the 25th International Joint Conference on Artificial Intelligence, 2016, 1606- 1612.
3	LIU Y H Optimal selection of tests for fault detection and isolation in multi-operating mode system. Journal of Systems Engineering and Electronics, 2019, 30 (2): 425- 434. doi: 10.21629/JSEE.2019.02.20
4	KHATIWADA S, TUSHEV M, MAHMOUD A Just enough semantics: an information theoretic approach for IR-based software bug localization. Journal of Information and Software Technology, 2018, 93, 45- 57. doi: 10.1016/j.infsof.2017.08.012
5	YOUM K, AHN J, LEE E Improved bug localization based on code change histories and bug reports. Journal of Information and Software Technology, 2017, 82, 177- 192. doi: 10.1016/j.infsof.2016.11.002
6	YE X, SHEN H, MA X, et al From word embeddings to document similarities for improved information retrieval in software engineering. Proc. of the 38th International Conference on Software Engineering, 2016, 404- 415.
7	YAN X, JACKY K, KWABENA E B, et al Improving bug localization with word embedding and enhanced convolutional neural networks. Information and Software Technology, 2019, 105, 17- 29. doi: 10.1016/j.infsof.2018.08.002
8	HUO X, LI M Enhancing the unified features to locate buggy files by exploiting the sequential nature of source code. Proc. of the 26th International Joint Conference on Artificial Intelligence, 2017, 1909- 1915.
9	MOU L L, LI G, ZHANG L, et al Convolutional neural networks over tree structures for programming language processing. Proc. of the 30th AAAI Conference on Artificial Intelligence, 2016, 1287- 1293.
10	WEI H H, LI M Supervised deep features for software functional clone detection by exploiting lexical and syntactical information in source code. Proc. of the 26th International Joint Conference on Artificial Intelligence, 2017, 3034- 3040.
11	TAI K S, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks. Proc. of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015, 1: 1556−1566.
12	MOU L L, LI G, LIU Y, et al Building program vector representations for deep learning. Proc. of the International Conference on Knowledge Science, Engineering and Management, 2014, 547- 553.
13	JAYASUNDARA V, BUI N D Q, JIANG L, et al. TreeCaps: tree-structured capsule networks for program source code processing. https://doi.org/10.48550/arXiv.1910.12306.
14	HUO X, LI M, ZHOU Z H Control flow graph embedding based on multi-instance decomposition for bug localization. Proc. of the AAAI Conference on Artificial Intelligence, 2020, 34 (4): 4223- 4230. doi: 10.1609/aaai.v34i04.5844
15	HU J C, CHEN J F, ZHANG L, et al A memory-related vulnerability detection approach based on vulnerability features. Journal of Tsinghua Science and Technology, 2020, 25 (5): 604- 613. doi: 10.26599/TST.2019.9010068
16	WANG W H, LI G, MA B, et al Detecting code clones with graph neural network and flow-augmented abstract syntax tree. Proc. of the IEEE 27th International Conference on Software Analysis, Evolution and Reengineering, 2020, 261- 271.
17	SOCHER R, LIN C C, MANNING C D, et al Parsing natural scenes and natural language with recursive neural networks. Proc. of the 28th International Conference on Machine Learning, 2011, 129- 136.
18	HINDLE A, BARR E T, SU Z, et al On the naturalness of software. Proc. of the India Software Engineering Conference, 2012, 837- 847.
19	SCHRTER A, SCHROTER A, BETTENBURG N, et al Do stack traces help developers fix bugs? Proc. of the 7th IEEE Working Conference on Mining Software Repositories, 2010, 118- 121.
20	WONG C P, XIONG Y, ZHANG H, et al Boosting bug-report-oriented fault localization with segmentation and stack-trace analysis. Proc. of the IEEE International Conference on Software Maintenance and Evolution, 2014, 181- 190.
21	GHARIBI R, RASEKH A H, SADREDDINI M H Leveraging textual properties of bug reports to localize relevant source files. Information Processing & Management, 2018, 54 (6): 1058- 1076.
22	YE X, BUNESCU R, LIU C Learning to rank relevant files for bug reports using domain knowledge. Proc. of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering, 2014, 689- 699.
23	LAM A N, NGUYEN A T, NGUYEN H A Bug localization with combination of deep learning and information retrieval. Proc. of the IEEE/ACM 25th International Conference on Program Comprehension, 2017, 218- 229.
24	LIANG H L, SUN L, WANG M L, et al Deep learning with customized abstract syntax tree for bug localization. IEEE Access, 2019, 7, 116309- 116320. doi: 10.1109/ACCESS.2019.2936948

Type	Definition
Class declaration	Type1={head, body}
Condition statement	Type2={control, block}
Try catch statement	Type3={block, catches}

Project	Time	#Bug report	#Source file
AspectJ	03/02-01/14	593	4 439
Tomcat	07/02-01/14	1 056	1 552
SWT	02/02-01/14	4 151	2 056
JDT	10/01-01/14	6 274	8 184

Project	Method	Top@1	Top@5	Top@10	MAP	MRR
AspectJ	BugLocator	0.216	0.473	0.571	0.276	0.369
	DNNLOC	0.478	0.712	0.804	0.320	0.520
	DeepLocator	0.400	0.660	0.780	0.340	0.490
	NP-CNN	0.460	0.730	0.810	0.401	0.531
	CAST	0.500	0.766	0.803	0.418	0.536
	Our model	0.573	0.808	0.884	0.503	0.578
SWT	BugLocator	0.246	0.408	0.533	0.284	0.325
	DNNLOC	0.352	0.690	0.803	0.370	0.450
	DeepLocator	0.360	0.600	0.750	0.390	0.480
	NP-CNN	0.365	0.700	0.812	0.381	0.475
	CAST	0.372	0.701	0.825	0.425	0.503
	Our model	0.464	0.771	0.898	0.468	0.549
JDT	BugLocator	0.183	0.427	0.508	0.307	0.389
	DNNLOC	0.403	0.650	0.743	0.340	0.450
	DeepLocator	0.400	0.640	0.730	0.390	0.470
	NP-CNN	0.420	0.669	0.749	0.383	0.461
	CAST	0.432	0.681	0.757	0.388	0.467
	Our model	0.515	0.726	0.826	0.434	0.516
Tomcat	BugLocator	0.354	0.645	0.709	0.431	0.485
	DNNLOC	0.539	0.729	0.804	0.520	0.600
	DeepLocator	0.520	0.720	0.800	0.540	0.600
	NP-CNN	0.530	0.700	0.792	0.529	0.597
	CAST	0.507	0.766	0.825	0.556	0.612
	Our model	0.625	0.814	0.877	0.601	0.658

Bug localization based on syntactical and semantic information of source code

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 14

References 24

Related Articles 0

Recommended Articles

Metrics

Comments