mirror of
https://github.com/colbymchenry/codegraph.git
synced 2026-09-19 07:34:57 +08:00
Colby Mchenry
2d72891b59
Parity: 0 diffs on redis/git/fmt/protobuf/ALS sweeps; full-init dumps byte-identical on all five + linux at kernel scale (10.4M dump lines, same sha256 both arms). Linux 2c/6GB envelope: kernel-arm 19.1min vs wasm-arm 22.9min (parse 356s vs 435s) on a much richer graph (the new blanks recover error-swallowed code: git 2x nodes, linux kernel/+mm/ 3x). Deferral guard corrected by measurement (C/C++ error incidence 9-42%; --max-deferral flag); defer-reuse memo kills the 3x re-blank/re-parse cost deferred files paid. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
37 lines
1.8 KiB
Rust
37 lines
1.8 KiB
Rust
//! Grammar registry: codegraph `Language` string → native tree-sitter grammar.
|
|
//!
|
|
//! Mirrors the wasm side's `WASM_GRAMMAR_FILES` mapping (src/extraction/
|
|
//! grammars.ts): `tsx` and `jsx` reuse another language's grammar exactly the
|
|
//! way the wasm map does. The kernel-grammar-parity test asserts each entry is
|
|
//! built from the SAME grammar revision as the vendored wasm — bump the crate
|
|
//! and the wasm together.
|
|
//!
|
|
//! (R1 shipped a generic `.scm`-query emitter here; R2 replaced it with the
|
|
//! bespoke per-language walker — see tsjs/ and the migration plan §3a — because
|
|
//! extraction parity needs logic queries can't express. New languages add a
|
|
//! grammar entry + a walker module.)
|
|
|
|
use tree_sitter::Language;
|
|
|
|
/// Languages this kernel binary can extract (reported by contractInfo;
|
|
/// TS-side routing policy decides what actually routes).
|
|
pub const LANGUAGES: [&str; 9] =
|
|
["typescript", "tsx", "javascript", "jsx", "java", "python", "go", "c", "cpp"];
|
|
|
|
pub fn grammar_for(language: &str) -> Option<Language> {
|
|
match language {
|
|
"typescript" => Some(tree_sitter_typescript::LANGUAGE_TYPESCRIPT.into()),
|
|
"tsx" => Some(tree_sitter_typescript::LANGUAGE_TSX.into()),
|
|
"javascript" | "jsx" => Some(tree_sitter_javascript::LANGUAGE.into()),
|
|
"java" => Some(tree_sitter_java::LANGUAGE.into()),
|
|
"python" => Some(tree_sitter_python::LANGUAGE.into()),
|
|
"go" => Some(tree_sitter_go::LANGUAGE.into()),
|
|
// `.metal`/`.cu`/`.cuh` map to language 'cpp' at detectLanguage, so the
|
|
// dialects ride this grammar too (their blanking pre-passes stay
|
|
// TS-side — the route point applies preParse before the kernel call).
|
|
"c" => Some(tree_sitter_c::LANGUAGE.into()),
|
|
"cpp" => Some(tree_sitter_cpp::LANGUAGE.into()),
|
|
_ => None,
|
|
}
|
|
}
|