Function extract_bash

graphify/extract.py:13904–14124

Extract functions, source imports, and cross-function calls from a .sh file.

(path: Path)

def extract_bash(path: Path) -> dict:
    """Extract functions, source imports, and cross-function calls from a .sh file."""
    try:
        import tree_sitter_bash as tsbash
        from tree_sitter import Language, Parser
    except ImportError:
        return {"nodes": [], "edges": [], "error": "tree-sitter-bash not installed"}

    try:
        language = Language(tsbash.language())
        parser = Parser(language)
        source = path.read_bytes()
        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()
    function_bodies: list[tuple[str, Any]] = []
    defined_functions: set[str] = set()

    from graphify.security import sanitize_metadata  # module-level cached import

    def add_node(nid: str, label: str, line: int, kind: str = "code") -> None:
        if nid and 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}",
                          "metadata": sanitize_metadata({"language": "bash", "kind": kind})})  # noqa: E501

    def add_edge(src: str, tgt: str, relation: str, line: int,
                 confidence: str = "EXTRACTED", weight: float = 1.0,
                 context: str | None = None) -> None:
        if not src or not tgt or src == tgt:
            return
        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))
    # file_nid is fully path-derived and never produced by _make_id(stem, func_name),
    # so appending "__entry" guarantees a distinct ID from any function node.
    entry_nid = file_nid + "__entry"
    add_node(file_nid, path.name, 1, kind="file")
    add_node(entry_nid, f"{path.name} script", 1, kind="bash_entrypoint")
    add_edge(file_nid, entry_nid, "contains", 1)

    _BASH_SOURCE_COMMANDS = frozenset({"source", "."})
    # Parent node types that mean a contained command is part of a substitution
    # or expansion, not a real function call. Token-level filtering misses
    # these because `$(build)` exposes `build` as a child command whose name