Identifying the effects of modifications as data dependencies

摘要

Dependence analysis on an extended finite state machine (EFSM) representation of the requirements of a system under test has been used in model-based regression testing for regression test suite (RTS) reduction (reducing the size of a given test suite by eliminating redundancies), for RTS prioritization (ordering test cases in a given test suite for early fault detection), or for RTS selection (selecting a subset of a test suite covering the identified dependencies). These particular uses of dependence analysis are based on the definitions of various types of control and data dependencies (between transitions in an EFSM) caused by a given set of modifications on the requirements. This paper considers the existing definitions of data dependencies for capturing the effects of the modifications, gives examples of their inaccuracy and incompleteness, proposes new definitions, and proves the soundness and completeness of these new definitions. Any previous work on regression testing using definitions of data dependencies capturing the effects of modifications can benefit from the proposed definitions.