Software testing is an important technique to assure the quality of software systems, especially high-confidence systems. To automate the process of software testing, many automatic test-data generation techniques hav...Software testing is an important technique to assure the quality of software systems, especially high-confidence systems. To automate the process of software testing, many automatic test-data generation techniques have been proposed. To generate effective test data, we propose a test-data generation technique guided by static defect detection in this paper. Using static defect detection analysis, our approach first identifies a set of suspicious statements which are likely to contain faults, then generates test data to cover these suspicious statements by converting the problem of test-data generation to the constraint satisfaction problem. We performed a case study to validate the effectiveness of our approach, and made a simple comparison with another test-data generation on-line tool, JUnit Factory. The results show that, compared with JUnit Factory, our approach generates fewer test data that are competitive on fault detection.展开更多
基金sponsored by the National High-Tech Research and Development 863 Program of China under Grant No.2007AA010301the National Natural Science Foundation of China under Grant Nos. 60803012 and 90718016China Postdoctoral Science Foundation funded project under Grant No. 20080440254
文摘Software testing is an important technique to assure the quality of software systems, especially high-confidence systems. To automate the process of software testing, many automatic test-data generation techniques have been proposed. To generate effective test data, we propose a test-data generation technique guided by static defect detection in this paper. Using static defect detection analysis, our approach first identifies a set of suspicious statements which are likely to contain faults, then generates test data to cover these suspicious statements by converting the problem of test-data generation to the constraint satisfaction problem. We performed a case study to validate the effectiveness of our approach, and made a simple comparison with another test-data generation on-line tool, JUnit Factory. The results show that, compared with JUnit Factory, our approach generates fewer test data that are competitive on fault detection.
