CQUniversity
Browse

An empirical study on compatibility issues in Android API field evolution

journal contribution
posted on 2025-08-12, 04:53 authored by T Mahmud, Meiru CheMeiru Che, G Yang
Context: The continuous evolution of the Android operating system requires regular API updates, which may affect the functionality of Android apps. This is becoming increasingly common due to the frequent evolution of the Android platform, which introduces new APIs and deprecates existing ones. Recent studies investigated API evolution to ensure the reliability of Android apps; however, they focused on API methods alone. Objectives: This study aims to understand how API fields evolve and how this affects API compatibility in real-world Android apps and their development. Method: We perform an empirical study on compatibility issues in Android API field evolution by analyzing the nature and resolution of these issues across 681 open-source Android apps. Results: Our experimental results yield interesting findings: (1) On average two API field compatibility issues exist per app in each tag; (2) Although API method evolution and API field evolution are related, current API method-level analysis techniques may fail to detect numerous API field compatibility issues; (3) Different types of checks are preferred when addressing different types of compatibility issues; (4) It takes on average three and a half months for an API field compatibility issue to get fixed since when it is introduced; (5) Developers pay proper attention to API field compatibility issues and address them soon after becoming aware of them in the apps. Conclusion: These findings highlight the significance of including API fields in future research on API evolution and can assist developers and researchers in understanding, detecting, and handling compatibility issues in API field evolution.<p></p>

Funding

Category 2 - Other Public Sector Grants Category

History

Volume

175

Start Page

1

End Page

12

Number of Pages

12

eISSN

1873-6025

ISSN

0950-5849

Publisher

Elsevier BV

Language

en

Peer Reviewed

  • Yes

Open Access

  • No

Acceptance Date

2024-07-17

Era Eligible

  • Yes

Journal

Information and Software Technology

Article Number

107530

Usage metrics

    CQUniversity

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC