NLP2Code: Code Snippet Content Assist via Natural Language Tasks
This addresses the time-saving needs of developers by reducing context switching, though it is incremental as it builds on existing content assist and code search tools.
The paper tackles the problem of developers needing to search for code snippets online by introducing NLP2Code, a tool integrated into source code editors that provides content assist to bridge the vocabulary gap between developer needs and snippet metadata, with preliminary evaluation showing most invocations yield helpful snippets and support diverse tasks.
Developers increasingly take to the Internet for code snippets to integrate into their programs. To save developers the time required to switch from their development environments to a web browser in the quest for a suitable code snippet, we introduce NLP2Code, a content assist for code snippets. Unlike related tools, NLP2Code integrates directly into the source code editor and provides developers with a content assist feature to close the vocabulary gap between developers' needs and code snippet meta data. Our preliminary evaluation of NLP2Code shows that the majority of invocations lead to code snippets rated as helpful by users and that the tool is able to support a wide range of tasks.