Function distributeUnicodes

Lib/pagebot/fonttoolbox/unicodes/unicoderanges.py:172–212

Return a dictionary with range names as keys, and subsets of unicodes belonging to the respective range as values. None is used as a key for characters that don't fall into any range. >>> distributeUnicodes([65]) {'Basic Latin': [65]} >>> distributeUnicodes([100000])

(unicodes)

def distributeUnicodes(unicodes):
    """Return a dictionary with range names as keys, and subsets of unicodes
    belonging to the respective range as values. None is used as a key for
    characters that don't fall into any range.

        >>> distributeUnicodes([65])
        {'Basic Latin': [65]}
        >>> distributeUnicodes([100000])
        {None: [100000]}
        >>> distributeUnicodes([65, 165])
        {'Basic Latin': [65], 'Latin-1 Supplement': [165]}
        >>> unicodes = list(range(65, 70)) + list(range(6000, 6005)) + [100000]
        >>> ranges = distributeUnicodes(unicodes)
        >>> sorted(ranges['Basic Latin'])
        [65, 66, 67, 68, 69]
        >>> all = set()
        >>> for unis in ranges.values():
        ...     all.update(unis)
        ...
        >>> assert all == set(unicodes)
    """
    ranges = {}
    noneRanges = []
    unicodes = sorted(unicodes)
    lo = 0
    for rangeMinimum in _rangeMinimums:
        rangeMaximum, bit, name = _byRangeMinimum[rangeMinimum]
        minIndex = bisect_left(unicodes, rangeMinimum, lo=lo)
        if minIndex > lo:
            noneRanges.extend(unicodes[lo:minIndex])
        if minIndex == len(unicodes):
            # done.
            break
        maxIndex = bisect_right(unicodes, rangeMaximum, lo=minIndex)
        lo = maxIndex
        if minIndex == maxIndex:
            continue
        ranges[name] = unicodes[minIndex:maxIndex]
    if noneRanges:
        ranges[None] = noneRanges
    return ranges


def _distributeUnicodes_ReferenceImplementation(unicodes):