daft.functions.guess_mime_type#

def guess_mime_type(bytes_expr: Expression) -> Expression:
    r"""Guess the MIME type of binary data by inspecting magic bytes.

    Detects common file formats including: PNG, JPEG, GIF, WEBP, PDF, ZIP,
    MP3, WAV, OGG, MP4, MPEG, HDF5, and HTML.

    Note: HDF5 detection follows the registered media type and signature documented by IANA:
    https://www.iana.org/assignments/media-types/application/vnd.hdfgroup.hdf5.

    Returns None if the format cannot be determined.

    Args:
        bytes_expr: Binary expression containing raw bytes.

    Returns:
        Expression: String expression containing MIME type (e.g., "image/png") or None.

    Example:
        >>> import daft
        >>> from daft.functions import guess_mime_type
        >>> df = daft.from_pydict({"data": [b"\x89PNG\r\n\x1a\n", b"not a known format"]})
        >>> df = df.with_column("mime", guess_mime_type(df["data"]))
        >>> df.select("mime").show()
        ╭───────────╮
        │ mime      │
        │ ---       │
        │ String    │
        ╞═══════════╡
        │ image/png │
        ├╌╌╌╌╌╌╌╌╌╌╌┤
        │ None      │
        ╰───────────╯
        <BLANKLINE>
        (Showing first 2 of 2 rows)

    """
    return bytes_expr._eval_expressions("guess_mime_type")