def test_repeat(manifest_type, preserve_id):
data = DummyManifest(manifest_type, begin_id=0, end_id=10)
expected = data + data
eager_result = data.repeat(times=2, preserve_id=preserve_id)
if preserve_id or manifest_type == FeatureSet:
assert list(eager_result) == list(expected)
else:
items = list(eager_result)
ref_items = list(expected)
assert len(items) == len(ref_items)
for i, refi in zip(items, ref_items):
assert i.id.endswith("_repeat0") or i.id.endswith("_repeat1")
i_modi = fastcopy(i, id=refi.id)
assert i_modi == refi
with as_lazy(data) as lazy_data:
lazy_result = lazy_data.repeat(times=2, preserve_id=preserve_id)
if preserve_id or manifest_type == FeatureSet:
assert list(lazy_result) == list(expected)
else:
items = list(lazy_result)
ref_items = list(expected)
assert len(items) == len(ref_items)
for i, refi in zip(items, ref_items):
assert i.id.endswith("_repeat0") or i.id.endswith("_repeat1")
i_modi = fastcopy(i, id=refi.id)
assert i_modi == refi
def test_repeat(manifest_type):
data = DummyManifest(manifest_type, begin_id=0, end_id=10)
expected = data + data
eager_result = data.repeat(times=2)
assert list(eager_result) == list(expected)
with as_lazy(data) as lazy_data:
lazy_result = lazy_data.repeat(times=2)
assert list(lazy_result) == list(expected)
def test_repeat_infinite(manifest_type):
data = DummyManifest(manifest_type, begin_id=0, end_id=10)
# hard to test infinite iterables, iterate it 10x more times than the original size
eager_result = data.repeat()
for idx, item in enumerate(eager_result):
if idx == 105:
break
assert idx == 105
with as_lazy(data) as lazy_data:
lazy_result = lazy_data.repeat()
for idx, item in enumerate(lazy_result):
if idx == 105:
break
assert idx == 105
def test_composable_operations():
expected_durations = [0, 2, 4, 6, 8, 0, 2, 4, 6, 8]
data = DummyManifest(CutSet, begin_id=0, end_id=10)
for idx, cut in enumerate(data):
cut.duration = idx
def less_than_5s(item):
return item.duration < 5
def double_duration(item):
return fastcopy(item, duration=item.duration * 2)
eager_result = data.repeat(2).filter(less_than_5s).map(double_duration)
assert [c.duration for c in eager_result] == expected_durations
with as_lazy(data) as lazy_data:
lazy_result = lazy_data.repeat(2).filter(less_than_5s).map(
double_duration)
assert [item.duration
for item in lazy_result] == list(expected_durations)
