Function extract_objc

graphify/extract.py:12406–12793

Extract interfaces, implementations, protocols, methods, and imports from .m/.mm/.h files.

(path: Path)

def extract_objc(path: Path) -> dict:
    """Extract interfaces, implementations, protocols, methods, and imports from .m/.mm/.h files."""
    try:
        import tree_sitter_objc as tsobjc
        from tree_sitter import Language, Parser
    except ImportError:
        return {"nodes": [], "edges": [], "error": "tree_sitter_objc not installed"}

    try:
        language = Language(tsobjc.language())
        parser = Parser(language)
        source = path.read_bytes()
        # tree-sitter-objc cannot expand these argument-less annotation macros (no
        # trailing ';'), and their presence before @interface makes the parser fail to
        # emit a class_interface node (#1475). Blank them to equal-length spaces so byte
        # offsets / line numbers are preserved and the interface parses.
        _OBJC_BLANK_MACROS = (b"NS_ASSUME_NONNULL_BEGIN", b"NS_ASSUME_NONNULL_END")
        for _m in _OBJC_BLANK_MACROS:
            source = source.replace(_m, b" " * len(_m))
        tree = parser.parse(source)
        root = tree.root_node
    except Exception as e:
        return {"nodes": [], "edges": [], "error": str(e)}

    stem = _file_stem(path)
    str_path = str(path)
    nodes: list[dict] = []
    edges: list[dict] = []
    seen_ids: set[str] = set()
    method_bodies: list[tuple[str, Any, str]] = []
    # #1556: unresolved message sends saved for the cross-file ObjC resolver, plus a
    # per-file `var -> ClassName` table from `Foo *f = ...;` local declarations.
    raw_calls: list[dict] = []
    objc_type_table: dict[str, str] = {}

    def add_node(nid: str, label: str, line: int) -> None:
        if nid not in seen_ids:
            seen_ids.add(nid)
            nodes.append({"id": nid, "label": label, "file_type": "code",
                          "source_file": str_path, "source_location": f"L{line}"})

    def add_edge(src: str, tgt: str, relation: str, line: int,
                 confidence: str = "EXTRACTED", weight: float = 1.0,
                 context: str | None = None) -> None:
        edge = {"source": src, "target": tgt, "relation": relation,
                "confidence": confidence, "source_file": str_path,
                "source_location": f"L{line}", "weight": weight}
        if context:
            edge["context"] = context
        edges.append(edge)

    file_nid = _make_id(str(path))
    add_node(file_nid, path.name, 1)

    def _read(node) -> str:
        return source[node.start_byte:node.end_byte].decode("utf-8", errors="replace")

    def _get_name(node, field: str) -> str | None: