Function _safe_filename

codewiki/mcp/workspace.py:37–53

Sanitize a component ID for use as a filename. Component IDs look like ``src/main.py::MyClass``. We replace any character that is not a word char, hyphen, or dot with ``__``. A short hash suffix is appended to prevent collisions when different component IDs sanitize to the same str

(component_id: str)

_WORKSPACE_REL = Path(".codewiki") / "sessions"


def _safe_filename(component_id: str) -> str:
    """Sanitize a component ID for use as a filename.

    Component IDs look like ``src/main.py::MyClass``.  We replace any
    character that is not a word char, hyphen, or dot with ``__``.
    A short hash suffix is appended to prevent collisions when different
    component IDs sanitize to the same string (e.g. ``src/a-b.py`` vs
    ``src/a_b.py``).

    The sanitized part is truncated so the filename stays under the
    common 255-byte NAME_MAX (separator chars expand to two chars each,
    so deep paths overflow it easily); the hash suffix keeps truncated
    names unique.
    """
    sanitized = re.sub(r"[^\w\-.]", "__", component_id)[:180]
    hash_suffix = hashlib.sha1(component_id.encode()).hexdigest()[:8]
    return f"{sanitized}_{hash_suffix}.src"