OCLVerifer: Automated verification of OCL contracts in requirements models

Abstract

Object Constraint Language (OCL) is one lightweight formal specification. Integrated within the Unified Modeling Language (UML) standard, it serves as a cornerstone in requirements modeling, enjoying widespread adoption across various domains. OCL can precisely define the pre- and post-condition of system operations and system invariants. While OCL provides a simple yet expressive syntax, it lacks clarity in mapping Object-Oriented (OO) concepts, such as object states, object links, and object attributes. This ambiguity makes it challenging for OO developers to identify errors in requirements. In this paper, we propose an approach named OCLVerifier, which can automatically detect the requirements errors of OCL, such as conflict, redundancy, and failure error. OCLVerifier first transforms OO contracts and detection patterns into SMT formulas and then proves them by using a SMT solver. Finally, the results are mapped to the original OCL contracts to display detailed error type and location information. To evaluate OCLVerifier, we conducted a comprehensive evaluation of four case studies. Experimental results indicate that OCLVerifier successfully identifies 65.5% of error cases, with each identified case offering accurate error location information. Compared with human experts, OCLVerifier can reduce evaluation time by 80.8% while enhancing repair accuracy by 18%. The results are satisfactory, and the proposed approach can be further extended to the software industry for requirements verification.