Function extract_powershell

graphify/extract.py:9134–9444

Extract functions, classes, methods, and using statements from a .ps1 file.

(path: Path)

# ── PowerShell ────────────────────────────────────────────────────────────────

def extract_powershell(path: Path) -> dict:
    """Extract functions, classes, methods, and using statements from a .ps1 file."""
    try:
        import tree_sitter_powershell as tsps
        from tree_sitter import Language, Parser
    except ImportError:
        return {"nodes": [], "edges": [], "error": "tree_sitter_powershell not installed"}

    try:
        language = Language(tsps.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]] = []

    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)

    _PS_SKIP = frozenset({
        "using", "return", "if", "else", "elseif", "foreach", "for",
        "while", "do", "switch", "try", "catch", "finally", "throw",
        "break", "continue", "exit", "param", "begin", "process", "end",
        # Import commands — handled as import edges, not function calls
        "import-module",
    })

    def _find_script_block_body(node):
        for child in node.children:
            if child.type == "script_block":
                for sc in child.children:
                    if sc.type == "script_block_body":
                        return sc
                return child