def certain_kind_tap(data_items):
"""
As the stream of data items go by, get different
kinds of information from them, in this case,
the things that are fruit and metal, collecting
each kind with a different spigot.
stream_tap doesn't consume the data_items iterator
by itself, it's a generator and must be consumed
by something else. In this case, it's consuming
the items by casting the iterator to a tuple,
but doing it in batches.
Since each batch is not referenced by anything
the memory can be freed by the garbage collector,
so no matter the size of the data_items, only a little
memory is needed. The only things retained
are the results, which should just be a subset
of the items and in this case, the getter functions
only return a portion of each item it matches.
:param data_items: A sequence of unicode strings
"""
fruit_spigot = Bucket(get_fruit)
metal_spigot = Bucket(get_metal)
items = stream_tap((fruit_spigot, metal_spigot), data_items)
for batch in i_batch(100, items):
tuple(batch)
return fruit_spigot.contents(), metal_spigot.contents()
def test_accumulation_handler(self):
"""
Ensure the return value of accumulation_handler
is the contents of a Bucket instance with it's contents
drained.
:return:
"""
spigot = Bucket(unicode)
spigot(1)
spigot(2)
result = accumulation_handler(None, spigot)
self.assertEqual(result, deque([u"1", u"2"]))
self.assertEqual(spigot.contents(), deque([]))
