PULER
OA Version
Citation
Abstract
We address the prevalent challenge of Algebraic Data Type duplication in compiler implementations, which results in increased effort, diminished functionality, and complications in synchronizing language constructs across the compiler. To investigate a novel design solution, we present Tree Shaping, a solution to the expression problem. We then implement an experimental compiler using Tree Shaping and examine its potential implications. This compiler processes programs written in PULER, an ML-based programming language that boasts distinct features such as unification rules for type mismatches. Contrary to traditional compilers that terminate and generate an error when encountering a type mismatch, PULER regards type mismatches as first-class citizens.