@article{horton_parnin_2022, title={Dozer: Migrating Shell Commands to Ansible Modules via Execution Profiling and Synthesis}, DOI={10.1145/3510457.3513060}, abstractNote={Software developers frequently use the system shell to perform configuration management tasks. Unfortunately, the shell does not scale well to large systems, and configuration management tools like Ansible are more difficult to learn. We address this problem with Dozer, a technique to help developers push their shell commands into Ansible task definitions. It operates by tracing and comparing system calls to find Ansible modules with similar behaviors to shell commands, then generating and validating migrations to find the task which produces the most similar changes to the system. Dozer is syntax agnostic, which should allow it to generalize to other configuration management platforms. We evaluate Dozer using datasets from open source configuration scripts.}, journal={2022 ACM/IEEE 44TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING IN PRACTICE (ICSE-SEIP 2022)}, author={Horton, Eric and Parnin, Chris}, year={2022}, pages={147–148} }
 @article{horton_parnin_2019, title={DockerizeMe: Automatic Inference of Environment Dependencies for Python Code Snippets}, ISSN={["0270-5257"]}, DOI={10.1109/ICSE.2019.00047}, abstractNote={Platforms like Stack Overflow and GitHub's gist system promote the sharing of ideas and programming techniques via the distribution of code snippets designed to illustrate particular tasks. Python, a popular and fast-growing programming language, sees heavy use on both sites, with nearly one million questions asked on Stack Overflow and 400 thousand public gists on GitHub. Unfortunately, around 75% of the Python example code shared through these sites cannot be directly executed. When run in a clean environment, over 50% of public Python gists fail due to an import error for a missing library. We present DockerizeMe, a technique for inferring the dependencies needed to execute a Python code snippet without import error. DockerizeMe starts with offline knowledge acquisition of the resources and dependencies for popular Python packages from the Python Package Index (PyPI). It then builds Docker specifications using a graph-based inference procedure. Our inference procedure resolves import errors in 892 out of nearly 3,000 gists from the Gistable dataset for which Gistable's baseline approach could not find and install all dependencies.}, journal={2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2019)}, author={Horton, Eric and Parnin, Chris}, year={2019}, pages={328–338} }
 @article{horton_parnin_2019, title={V2: Fast Detection of Configuration Drift in Python}, DOI={10.1109/ASE.2019.00052}, abstractNote={Code snippets are prevalent, but are hard to reuse because they often lack an accompanying environment configuration. Most are not actively maintained, allowing for drift between the most recent possible configuration and the code snippet as the snippet becomes out-of-date over time. Recent work has identified the problem of validating and detecting out-of-date code snippets as the most important consideration for code reuse. However, determining if a snippet is correct, but simply out-of-date, is a non-trivial task. In the best case, breaking changes are well documented, allowing developers to manually determine when a code snippet contains an out-of-date API usage. In the worst case, determining if and when a breaking change was made requires an exhaustive search through previous dependency versions. We present V2, a strategy for determining if a code snippet is out-of-date by detecting discrete instances of configuration drift, where the snippet uses an API which has since undergone a breaking change. Each instance of configuration drift is classified by a failure encountered during validation and a configuration patch, consisting of dependency version changes, which fixes the underlying fault. V2 uses feedback-directed search to explore the possible configuration space for a code snippet, reducing the number of potential environment configurations that need to be validated. When run on a corpus of public Python snippets from prior research, V2 identifies 248 instances of configuration drift.}, journal={34TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING (ASE 2019)}, author={Horton, Eric and Parnin, Chris}, year={2019}, pages={477–488} }
 @article{horton_parnin_2018, title={Gistable: Evaluating the Executability of Python Code Snippets on GitHub}, ISSN={["1063-6773"]}, DOI={10.1109/ICSME.2018.00031}, abstractNote={Software developers create and share code online to demonstrate programming language concepts and programming tasks. Code snippets can be a useful way to explain and demonstrate a programming concept, but may not always be directly executable. A code snippet can contain parse errors, or fail to execute if the environment contains unmet dependencies. This paper presents an empirical analysis of the executable status of Python code snippets shared through the GitHub gist system, and the ability of developers familiar with software configuration to correctly configure and run them. We find that 75.6% of gists require non-trivial configuration to overcome missing dependencies, configuration files, reliance on a specific operating system, or some other environment configuration. Our study also suggests the natural assumption developers make about resource names when resolving configuration errors is correct less than half the time. We also present Gistable, a database and extensible framework built on GitHub's gist system, which provides executable code snippets to enable reproducible studies in software engineering. Gistable contains 10,259 code snippets, approximately 5,000 with a Dockerfile to configure and execute them without import error. Gistable is publicly available at https://github.com/gistable/gistable.}, journal={PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME)}, author={Horton, Eric and Parnin, Chris}, year={2018}, pages={217–227} }