Function extract_terraform

graphify/extract.py:15729–15899

Extract Terraform/HCL blocks and the references between them via tree-sitter. Nodes: resources, data sources, modules, variables, outputs, providers, and locals. Edges: `contains` (file -> block), `references` (block -> the blocks it interpolates, e.g. `aws_instance.web` -> `var.region`

(path: Path)

def extract_terraform(path: Path) -> dict:
    """Extract Terraform/HCL blocks and the references between them via tree-sitter.

    Nodes: resources, data sources, modules, variables, outputs, providers, and
    locals. Edges: `contains` (file -> block), `references` (block -> the blocks
    it interpolates, e.g. `aws_instance.web` -> `var.region`), and `depends_on`
    (explicit dependency edges).

    Node IDs are scoped by the parent directory, not the file stem, because
    Terraform resources are module(directory)-scoped: a resource defined in
    main.tf is referenced from other .tf files in the same directory. Directory
    scoping lets those cross-file references resolve when per-file extractions
    are merged (stem scoping would split a definition from its references).
    """
    try:
        import tree_sitter_hcl as tshcl
        from tree_sitter import Language, Parser
    except ImportError:
        return {"nodes": [], "edges": [], "error": "tree_sitter_hcl not installed. Run: pip install tree-sitter-hcl"}

    try:
        language = Language(tshcl.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)}

    str_path = str(path)
    file_nid = _make_id(str_path)
    scope = path.parent.name or "tf"

    nodes: list[dict] = [{"id": file_nid, "label": path.name, "file_type": "code",
                          "source_file": str_path, "source_location": None}]
    edges: list[dict] = []
    seen_ids: set[str] = {file_nid}
    seen_edges: set[tuple[str, str, str]] = set()

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

    def _label_text(n) -> str:
        return _read(n).strip().strip('"')

    def _add_node(address: str, label: str, line: int) -> str:
        nid = _make_id(scope, address)
        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}"})
            edges.append({"source": file_nid, "target": nid, "relation": "contains",
                          "confidence": "EXTRACTED", "source_file": str_path,
                          "source_location": f"L{line}", "weight": 1.0})
        return nid

    def _add_edge(src: str, address: str, relation: str, line: int) -> None:
        tgt = _make_id(scope, address)