Function extract_lazarus_form

graphify/extract.py:13579–13670

Extract component hierarchy from Lazarus .lfm form files. .lfm is a text-based declarative format for UI component trees, structured as: object ComponentName: TClassName PropertyName = Value OnEvent = HandlerName object ChildName: TChildClass ..

(path: Path)

def extract_lazarus_form(path: Path) -> dict:
    """Extract component hierarchy from Lazarus .lfm form files.

    .lfm is a text-based declarative format for UI component trees, structured as:
        object ComponentName: TClassName
          PropertyName = Value
          OnEvent = HandlerName
          object ChildName: TChildClass
            ...
          end
        end

    Produces nodes for:
    - The form file itself
    - Each component class encountered (TForm1, TButton, TPanel, ...)
    - Event handler names referenced by OnXxx properties

    Produces edges for:
    - file --contains--> root form class
    - parent component --contains--> child component class
    - component --references--> event handler (context: "event")
    """
    try:
        text = path.read_text(encoding="utf-8", errors="replace")
    except Exception as e:
        return {"nodes": [], "edges": [], "error": str(e)}

    import re
    str_path = str(path)
    stem = _file_stem(path)
    nodes: list[dict] = []
    edges: list[dict] = []
    seen_ids: set[str] = set()
    seen_edge_pairs: set[tuple[str, str, str]] = set()

    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,
        context: str | None = None,
    ) -> None:
        key = (src, tgt, relation)
        if key in seen_edge_pairs:
            return
        seen_edge_pairs.add(key)
        edge: dict[str, Any] = {
            "source": src, "target": tgt, "relation": relation,
            "confidence": "EXTRACTED", "source_file": str_path,
            "source_location": f"L{line}", "weight": 1.0,
        }
        if context:
            edge["context"] = context