MutShrink: a Mutation-based Test Database Shrinking Method

Regression testing for database application is a costly task because frequently treats with large databases and complex SQL statements. Therefore, some works select a subset of the database for testing purpose, i.e. shrink database creating a test database and thus improving the efficiency of the testing. But normally test data selection is also a complex optimization problem. So, this work proposes a test data selection method for SQL regression testing based on mutation, called MutShrink (Mutation-based Test Database Shrinking Method). The goal is minimizing the testing cost reducing database while keeping the similar effectiveness of original database. We performed experiments using a benchmark with some complex SQLs and large database. We compared our proposal against the baseline QAShrink tool and results revealed that our proposal outperformed QAShrink tool in 92.85% of cases when evaluated by Mutation Score metric, and in 57.14% of cases when assessed by Full Predicate Coverage metric.