Function extract

codegraph-kernel/src/tsjs/mod.rs:192–285

(file_path: &str, source: &str, language: &str)

const MAX_VALUE_REF_NODES: usize = 20_000;

pub fn extract(file_path: &str, source: &str, language: &str) -> Result<EmitOut, String> {
    let variant = Variant::from_language(language)
        .ok_or_else(|| format!("tsjs walker does not handle language: {language}"))?;
    let grammar = langs::grammar_for(language)
        .ok_or_else(|| format!("no grammar for language: {language}"))?;

    let t0 = std::time::Instant::now();
    let mut parser = Parser::new();
    parser
        .set_language(&grammar)
        .map_err(|e| format!("set_language({language}) failed: {e}"))?;
    let tree = parser
        .parse(source, None)
        .ok_or_else(|| "parser returned null tree".to_string())?;

    // Files with parse ERRORS defer to the wasm extractor (the `defer:` prefix
    // tells the TS side this is expected routing, not a malfunction). Reason:
    // tree-sitter's error RECOVERY — same grammar, same core version — resolves
    // differently under UTF-8 (native) vs UTF-16 (web-tree-sitter) parsing, so
    // an erroring file's tree can differ between the paths (proven on vscode:
    // `readonly import('x').T[]` recovered with the ERROR inside vs outside the
    // type annotation). Erroring files are rare (0-0.42% across express/
    // excalidraw/vscode) and per-file wasm fallback keeps routing graph-neutral
    // by construction; clean files — 99.6%+ — stay on the fast path.
    if tree.root_node().has_error() {
        return Err("defer: parse tree contains errors — wasm recovery is canonical".to_string());
    }

    let mut w = Walker {
        src: source,
        file_path,
        variant,
        line_starts: util::line_starts(source),
        arena: Arena::default(),
        node_id_allocator: ids::NodeIdAllocator::default(),
        tables: Tables::default(),
        stack: Vec::new(),
        node_ids: Vec::new(),
        defined_fn_names: HashSet::new(),
        imported_names: HashSet::new(),
        fn_ref_cands: Vec::new(),
        fs_values: HashMap::new(),
        fs_value_counts: HashMap::new(),
        value_scopes: Vec::new(),
        vue_store_file: None,
    };

    // File node (TreeSitterExtractor.extract): id `file:<path>`, endLine =
    // newline count + 1, isExported explicitly false.
    let line_count = source.bytes().filter(|b| *b == b'\n').count() as u32 + 1;
    let base_name = file_path.rsplit(['/', '\\']).next().unwrap_or(file_path);
    let mut flags = BoolFlags::default();
    flags.set(FLAG_IS_EXPORTED, false);
    let file_id = w.arena.put(&ids::file_node_id(file_path));
    let name_ref = w.arena.put(base_name);
    let qn_ref = w.arena.put(file_path);
    w.tables.push_node(&NodeRow {
        kind: node_kind_index("file").unwrap(),