Function extract

codegraph-kernel/src/ccpp/mod.rs:351–437

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

}

pub fn extract(file_path: &str, source: &str, language: &str) -> Result<EmitOut, String> {
    let variant = match language {
        "c" => Variant::C,
        "cpp" => Variant::Cpp,
        other => return Err(format!("ccpp walker got language '{other}'")),
    };
    let grammar = crate::langs::grammar_for(language).ok_or("no c/cpp grammar")?;
    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())?;
    // Measurement hatch (parity sweeps only — never set in production): skip
    // the defer so the sweep can QUANTIFY how often UTF-8 vs UTF-16 error
    // recovery actually diverges on this language's erroring files.
    let no_defer = std::env::var("CODEGRAPH_KERNEL_CCPP_ERROR_EXTRACT").as_deref() == Ok("1");
    if tree.root_node().has_error() && !no_defer {
        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(),
        tables: Tables::default(),
        stack: Vec::new(),
        nodes_meta: Vec::new(),
        node_ids: Vec::new(),
        namespace_prefix: Vec::new(),
        local_fn_ptrs: HashMap::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(),
    };

    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(),
        visibility: 0,
        flags,
        start_line: 1,
        end_line: line_count,
        start_column: 0,
        end_column: 0,