Function extract_delphi_form

graphify/extract.py:13673–13766

Extract component hierarchy from Delphi .dfm form files. .dfm files come in two formats: - Text (same `object Name: TClassName ... end` syntax as .lfm) - Binary (starts with a TPF0/FF0A magic header — unreadable as text) Binary .dfm files are skipped gracefully: an empty result is

(path: Path)

def extract_delphi_form(path: Path) -> dict:
    """Extract component hierarchy from Delphi .dfm form files.

    .dfm files come in two formats:
    - Text (same `object Name: TClassName ... end` syntax as .lfm)
    - Binary (starts with a TPF0/FF0A magic header — unreadable as text)

    Binary .dfm files are skipped gracefully: an empty result is returned
    so the rest of the pipeline is unaffected.  Convert binary forms to
    text in the Delphi IDE via File → Save As (Text DFM) if you want them
    indexed.

    Text .dfm files are parsed identically to .lfm: component containment
    (`contains`) and event handler references (`references`, context "event").
    """
    try:
        raw = path.read_bytes()
    except Exception as e:
        return {"nodes": [], "edges": [], "error": str(e)}

    # Detect binary DFM: Delphi binary resource streams start with FF 0A
    if raw[:2] == b"\xff\x0a":
        return {
            "nodes": [], "edges": [],
            "error": f"binary DFM (convert to text in Delphi IDE to index): {path.name}",
        }

    # Text DFM — delegate to the shared form parser (same syntax as .lfm)
    try:
        text = raw.decode("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] = {