Function verify_metadata

monai/bundle/scripts.py:1047–1105

Verify the provided `metadata` file based on the predefined `schema`. `metadata` content must contain the `schema` field for the URL of schema file to download. The schema standard follows: http://json-schema.org/. Args: meta_file: filepath of the metadata file to verify, i

(
    meta_file: str | Sequence[str] | None = None,
    filepath: PathLike | None = None,
    create_dir: bool | None = None,
    hash_val: str | None = None,
    hash_type: str | None = None,
    args_file: str | None = None,
    **kwargs: Any,
)

def verify_metadata(
    meta_file: str | Sequence[str] | None = None,
    filepath: PathLike | None = None,
    create_dir: bool | None = None,
    hash_val: str | None = None,
    hash_type: str | None = None,
    args_file: str | None = None,
    **kwargs: Any,
) -> None:
    """
    Verify the provided `metadata` file based on the predefined `schema`.
    `metadata` content must contain the `schema` field for the URL of schema file to download.
    The schema standard follows: http://json-schema.org/.

    Args:
        meta_file: filepath of the metadata file to verify, if `None`, must be provided in `args_file`.
            if it is a list of file paths, the content of them will be merged.
        filepath: file path to store the downloaded schema.
        create_dir: whether to create directories if not existing, default to `True`.
        hash_val: if not None, define the hash value to verify the downloaded schema file.
        hash_type: if not None, define the hash type to verify the downloaded schema file. Defaults to "md5".
        args_file: a JSON or YAML file to provide default values for all the args in this function.
            so that the command line inputs can be simplified.
        kwargs: other arguments for `jsonschema.validate()`. for more details:
            https://python-jsonschema.readthedocs.io/en/stable/validate/#jsonschema.validate.

    """

    _args = update_kwargs(
        args=args_file,
        meta_file=meta_file,
        filepath=filepath,
        create_dir=create_dir,
        hash_val=hash_val,
        hash_type=hash_type,
        **kwargs,
    )
    _log_input_summary(tag="verify_metadata", args=_args)
    filepath_, meta_file_, create_dir_, hash_val_, hash_type_ = _pop_args(
        _args, "filepath", "meta_file", create_dir=True, hash_val=None, hash_type="md5"
    )

    check_parent_dir(path=filepath_, create_dir=create_dir_)
    metadata = ConfigParser.load_config_files(files=meta_file_)
    url = metadata.get("schema")
    if url is None:
        raise ValueError("must provide the `schema` field in the metadata for the URL of schema file.")
    download_url(url=url, filepath=filepath_, hash_val=hash_val_, hash_type=hash_type_, progress=True)
    schema = ConfigParser.load_config_file(filepath=filepath_)

    try:
        # the rest key-values in the _args are for `validate` API
        validate(instance=metadata, schema=schema, **_args)
    except ValidationError as e:  # pylint: disable=E0712
        # as the error message is very long, only extract the key information
        raise ValueError(
            re.compile(r".*Failed validating", re.S).findall(str(e))[0] + f" against schema `{url}`."
        ) from e