Class bucket

Lib/importlib/metadata/_itertools.py:78–171

Wrap *iterable* and return an object that buckets the iterable into child iterables based on a *key* function. >>> iterable = ['a1', 'b1', 'c1', 'a2', 'b2', 'c2', 'b3'] >>> s = bucket(iterable, key=lambda x: x[0]) # Bucket by 1st character >>> sorted(list(s)) # Get the

# Copied from more_itertools 10.3
class bucket:
    """Wrap *iterable* and return an object that buckets the iterable into
    child iterables based on a *key* function.

        >>> iterable = ['a1', 'b1', 'c1', 'a2', 'b2', 'c2', 'b3']
        >>> s = bucket(iterable, key=lambda x: x[0])  # Bucket by 1st character
        >>> sorted(list(s))  # Get the keys
        ['a', 'b', 'c']
        >>> a_iterable = s['a']
        >>> next(a_iterable)
        'a1'
        >>> next(a_iterable)
        'a2'
        >>> list(s['b'])
        ['b1', 'b2', 'b3']

    The original iterable will be advanced and its items will be cached until
    they are used by the child iterables. This may require significant storage.

    By default, attempting to select a bucket to which no items belong  will
    exhaust the iterable and cache all values.
    If you specify a *validator* function, selected buckets will instead be
    checked against it.

        >>> from itertools import count
        >>> it = count(1, 2)  # Infinite sequence of odd numbers
        >>> key = lambda x: x % 10  # Bucket by last digit
        >>> validator = lambda x: x in {1, 3, 5, 7, 9}  # Odd digits only
        >>> s = bucket(it, key=key, validator=validator)
        >>> 2 in s
        False
        >>> list(s[2])
        []

    """

    def __init__(self, iterable, key, validator=None):
        self._it = iter(iterable)
        self._key = key
        self._cache = defaultdict(deque)
        self._validator = validator or (lambda x: True)

    def __contains__(self, value):
        if not self._validator(value):
            return False

        try:
            item = next(self[value])
        except StopIteration:
            return False
        else:
            self._cache[value].appendleft(item)

        return True

    def _get_values(self, value):
        """
        Helper to yield items from the parent iterator that match *value*.