humansize.py

humansize.py

SUFFIXES = {1000: ['KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'],
            1024: ['KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB']}

def approximate_size(size, a_kilobyte_is_1024_bytes=True):
    """Convert a file size to human-readable form.

    Keyword arguments:
    size -- file size in bytes
    a_kilobyte_is_1024_bytes -- if True (default), use multiples of 1024,
                                if False, use multiples of 1000

    Returns: string

    """

    if size < 0:
        raise ValueError("Number must be non-negative")

    multiple = 1024 if a_kilobyte_is_1024_bytes else 1000
    for suffix in SUFFIXES[multiple]:
        size /= multiple
        if size < multiple:
            return "{0:.1f} {1}".format(size, suffix)
    
    """
        Can someone tell me how the above for loop selects the correct suffix? It does it as if by magic.
        I understand how everything else works, but don't understand how the right suffix within the list
        is selected.
    """

    raise ValueError("Number too large")

if __name__ == "__main__":
    print(approximate_size(1000000000000, False))
    print(approximate_size(1000000000000))

interestingly my version and yours both have the same bug - they don't test to see if they've 'run off the end'

I guess I've never used mine with petabytes & yours at least has a pretty high top end