Reusing code by reasoning about its purpose

Abstract

When programmers face unfamiliar or challenging tasks, code written by others could give them inspiration or reusable pieces. But how can they find code appropriate for their goals? This thesis describes a programming interface, called Zones, that connects code with descriptions of purpose, encouraging annotation, sharing, and reuse of code. The backend, called ProcedureSpace, reasons jointly over both the words that people used to describe code fragments and syntactic features derived from static analysis of that code to enable searching for code given purpose descriptions or vice versa. It uses a technique called Bridge Blending to do joint inference across data of many types, including using domain-specific and commonsense background knowledge to help understand different ways of describing goals. Since Zones uses the same interface for searching as for annotating, users can leave searches around as annotations, even if the search fails, which helps the system learn from user interaction. This thesis describes the design, implementation, and evaluation of the Zones and ProcedureSpace system, showing that reasoning jointly over natural language and programming language helps programmers reuse code.