A Preliminary Investigation on the Usage of Quantum Approximate Optimization Algorithms for Test Case Selection - Online Appendix

QAOA-TCS - Quantum Regression Test Case Selection  This repository contains all the necessary resources to reproduce the results of the QAOA-TCS method.  

Dataset Files  The "datasets" folder contains:  - "sir_programs"  

SIR Programs  The "datasets/sir_programs" folder contains, for each SIR program considered by this project, all the files needed to gather statement coverage, execution costs, and past fault coverage information.  

For example, in the "flex" program folder:  - The file "fault-matrix.txt" contains rows representing flex's test cases. Each row has columns representing different versions of the program. Each cell (i,j) contains a binary value (0 or 1) indicating whether the i-th test case detects a fault in the j-th version. This configuration is called the fault matrix and provides historical fault coverage information.  - The folder "json_flex" contains a folder for each test case, with files like "flexi.gcov.json" to recover statement coverage and execution costs. These files detail which basic blocks were executed and how many times, enabling the calculation of total statement coverage and execution costs for each test case.  

Source Code Files  

DIVGA.m  The "MATLAB/DIVGA.m" file contains the pipeline for the DIVGA algorithm. For simplicity, the statement coverage, execution costs, and fault coverage data already gathered by "Notebook.ipynb" are written into text files, which DIVGA.m reads to bypass the actual datasets.  

DIVGA.m must be reconfigured for each target program. Update parameters like M, N, and gamultiobj routine settings. Ensure H_size in line 104 is less than max{N, M} + 1. Update the denominator in line 53 based on the total number of code lines in the target program. Adjust the result reporting target files as well.  

Notebook.ipynb  This file includes pipelines for dataset analysis, algorithm execution, and empirical comparisons.  

It has two main sections:  

1. QAOA-TCS vs SelectQA and Classical Algorithms     - Pipelines analyze SIR programs and compare QAOA-TCS, SelectQA, and classical algorithms. Manual configuration is needed when changing the target program, including updating file paths for Pareto fronts and configuring frontiers to build the reference.     - Statistical analysis requires populating the variables "algorithm_nondom_sirprogram" with the number of non-dominated solutions found during each of the 10 runs.  

Results Files  The "results" folder contains the outcomes of QAOA-TCS, DIV-GA, Additional Greedy, and SelectQA after experiment execution. These files enable empirical evaluations and comparisons between the methods.