Function _get_extractor

graphify/extract.py:16081–16117

Return the correct extractor function for a file, or None if unsupported.

(path: Path)

def _get_extractor(path: Path) -> Any | None:
    """Return the correct extractor function for a file, or None if unsupported."""
    if path.name.lower().endswith(".blade.php"):
        return extract_blade
    # MCP config files (.mcp.json, claude_desktop_config.json, ...) are routed
    # by filename before generic .json dispatch so they get MCP-aware nodes
    # (servers, commands, packages, env vars) instead of opaque JSON keys.
    if is_mcp_config_path(path):
        return extract_mcp_config
    # Package manifests (apm.yml, pyproject.toml, go.mod, pom.xml) → a canonical
    # package node + depends_on edges, by filename before generic suffix dispatch
    # (#1377). apm.yml would otherwise be a .yml document handled by the LLM.
    if is_package_manifest_path(path):
        return extract_package_manifest
    # `.h` is C/C++/ObjC-ambiguous; route Objective-C headers to extract_objc
    # (the suffix map sends `.h` to extract_c, which can't read @interface etc.).
    # ObjC sniffing has priority over the C++ sniff: an Objective-C++ header can
    # contain both `@interface` and inline C++ (`::`), and it must parse as ObjC.
    suffix = path.suffix
    if suffix not in _DISPATCH and suffix.lower() in _DISPATCH:
        suffix = suffix.lower()
    if suffix == ".h":
        if _is_objc_header(path):
            return extract_objc
        # A C++ class header routed to extract_c loses the class entirely (the C
        # grammar has no class_specifier). Reroute to extract_cpp (#1547).
        if _is_cpp_header(path):
            return extract_cpp
    # Extensionless files: resolve by shebang, mirroring detect.classify_file.
    # Without this, detect labels e.g. `#!/usr/bin/env bash` CLIs as code but
    # extraction returns no extractor and the file silently contributes nothing.
    if not suffix:
        from graphify.detect import _shebang_interpreter
        interp = _shebang_interpreter(path)
        if interp is not None:
            return _SHEBANG_DISPATCH.get(interp)
    return _DISPATCH.get(suffix)


def _safe_extract_with_xaml_root(extractor, path: Path, root: Path) -> dict: