Function extractall

monai/apps/utils.py:303–355

Extract file to the output directory. Expected file types are: `zip`, `tar.gz` and `tar`. Args: filepath: the file path of compressed file. output_dir: target directory to save extracted files. hash_val: expected hash value to validate the compressed file.

(
    filepath: PathLike,
    output_dir: PathLike = ".",
    hash_val: str | None = None,
    hash_type: str = "md5",
    file_type: str = "",
    has_base: bool = True,
)

def extractall(
    filepath: PathLike,
    output_dir: PathLike = ".",
    hash_val: str | None = None,
    hash_type: str = "md5",
    file_type: str = "",
    has_base: bool = True,
) -> None:
    """
    Extract file to the output directory.
    Expected file types are: `zip`, `tar.gz` and `tar`.

    Args:
        filepath: the file path of compressed file.
        output_dir: target directory to save extracted files.
        hash_val: expected hash value to validate the compressed file.
            if None, skip hash validation.
        hash_type: 'md5' or 'sha1', defaults to 'md5'.
        file_type: string of file type for decompressing. Leave it empty to infer the type from the filepath basename.
        has_base: whether the extracted files have a base folder. This flag is used when checking if the existing
            folder is a result of `extractall`, if it is, the extraction is skipped. For example, if A.zip is unzipped
            to folder structure `A/*.png`, this flag should be True; if B.zip is unzipped to `*.png`, this flag should
            be False.

    Raises:
        RuntimeError: When the hash validation of the ``filepath`` compressed file fails.
        NotImplementedError: When the ``filepath`` file extension is not one of [zip", "tar.gz", "tar"].

    """
    if has_base:
        # the extracted files will be in this folder
        cache_dir = Path(output_dir, _basename(filepath).split(".")[0])
    else:
        cache_dir = Path(output_dir)
    if cache_dir.exists() and next(cache_dir.iterdir(), None) is not None:
        logger.info(f"Non-empty folder exists in {cache_dir}, skipped extracting.")
        return
    filepath = Path(filepath)
    if hash_val and not check_hash(filepath, hash_val, hash_type):
        raise RuntimeError(
            f"{hash_type} check of compressed file failed: " f"filepath={filepath}, expected {hash_type}={hash_val}."
        )
    logger.info(f"Writing into directory: {output_dir}.")
    _file_type = file_type.lower().strip()
    if filepath.name.endswith("zip") or _file_type == "zip":
        _extract_zip(filepath, output_dir)
        return
    if filepath.name.endswith("tar") or filepath.name.endswith("tar.gz") or "tar" in _file_type:
        _extract_tar(filepath, output_dir)
        return
    raise NotImplementedError(
        f'Unsupported file type, available options are: ["zip", "tar.gz", "tar"]. name={filepath} type={file_type}.'
    )


def get_filename_from_url(data_url: str) -> str: