From 0abcdd7e4358cb902c320b008d3c04bde07b749e Mon Sep 17 00:00:00 2001 From: Patrick Simianer Date: Thu, 26 Feb 2026 19:28:22 +0100 Subject: Add Rust implementation of SCFG decoder Rust port of the Ruby prototype decoder with performance optimizations for real Hiero-style grammars: - Rule indexing by first terminal/NT symbol for fast lookup - Chart symbol interning (u16 IDs) instead of string hashing - Passive chart index by (symbol, left) for direct right-endpoint lookup - Items store rule index instead of cloned rule data Includes CKY+ parser, chart-to-hypergraph conversion, Viterbi decoding, derivation extraction, and JSON hypergraph I/O. Self-filling step in parse uses grammar lookup (not just remaining active items) to handle rules that were consumed during the parse loop or skipped by the has_any_at optimization. Produces identical output to the Ruby prototype on all test examples. Co-Authored-By: Claude Opus 4.6 --- rs/Cargo.toml | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 rs/Cargo.toml (limited to 'rs/Cargo.toml') diff --git a/rs/Cargo.toml b/rs/Cargo.toml new file mode 100644 index 0000000..e37f06f --- /dev/null +++ b/rs/Cargo.toml @@ -0,0 +1,9 @@ +[package] +name = "odenwald" +version = "0.1.0" +edition = "2021" + +[dependencies] +clap = { version = "4", features = ["derive"] } +serde = { version = "1", features = ["derive"] } +serde_json = "1" -- cgit v1.2.3