__init__.py 文件源码

def script(char):
    """ Return the four-letter script code assigned to the Unicode character
    'char' as string.

    >>> script("a")
    'Latn'
    >>> script(",")
    'Zyyy'
    >>> script(unichr(0x10FFFF))
    'Zzzz'
    """
    code = byteord(char)
    # 'bisect_right(a, x, lo=0, hi=len(a))' returns an insertion point which
    # comes after (to the right of) any existing entries of x in a, and it
    # partitions array a into two halves so that, for the left side
    # all(val <= x for val in a[lo:i]), and for the right side
    # all(val > x for val in a[i:hi]).
    # Our 'SCRIPT_RANGES' is a sorted list of ranges (only their starting
    # breakpoints); we want to use `bisect_right` to look up the range that
    # contains the given codepoint: i.e. whose start is less than or equal
    # to the codepoint. Thus, we subtract -1 from the index returned.
    i = bisect_right(Scripts.RANGES, code)
    return Scripts.VALUES[i-1]