Structured Grammars are Effective

TL;DR

This paper introduces REGREG, a formalism equivalent to PEG, enabling efficient, linear-time top-down parsers with modest memory use, addressing prefix hiding issues in parsing techniques.

Contribution

The paper presents REGREG, a new formalism for top-down parsing that overcomes prefix hiding and achieves linear-time parsing with modest memory, matching PEG's capabilities.

Findings

REGREG is equivalent to PEG.

REGREG enables linear-time parsing.

Parsers using REGREG have modest memory requirements.

Abstract

Top-down parsing has received much attention recently. Parsing expression grammars (PEG) allows construction of linear time parsers using packrat algorithm. These techniques however suffer from problem of prefix hiding. We use alternative formalism of relativized regular expressions REGREG for which top-down backtracking parser runs in linear time. This formalism allows to construct fast parsers with modest memory requirements for practical grammars. We show that our formalism is equivalent to PEG.