Features

• Offers multiple pipelines for natural language extraction at granular level.

• Provides comprehensive contextual information for source code comments, more particularly extracts the preceding and succeding source code for each comment apart from other location based attributes.

• Treats multiple consecutive comments as single comment.

• Serializes mined data in highly interchangeable data format JSON and offers explicit loading mechanism of mined data enabling easier transfer and reuse.

• Available as commandline executable and pip installable package (for use in other applications).