5e0b6567cd
New bag implementation improves a lot how bonobo works, even if this is highly backward incompatible (sorry, that's needed, and better sooner than later). * New implementation uses the same approach as python's namedtuple, by dynamically creating the python type's code. This has drawbacks, as it feels like not the right way, but also a lot of benefits that cannot be achieved using a regular approach, especially the constructor parameter order, hardcoded. * Memory usage is now much more efficient. The "keys" memory space will be used only once per "io type", being spent in the underlying type definition instead of in the actual instances. * Transformations now needs to use tuples as output, which will be bound to its "output type". The output type can be infered from the tuple length, or explicitely set by the user using either `context.set_output_type(...)` or `context.set_output_fields(...)` (to build a bag type from a list of field names). Jupyter/Graphviz integration is more tight, allowing to easily display graphs in a notebook, or displaying the live transformation status in an html table instead of a simple <div>. For now, context processors were hacked to stay working as before but the current API is not satisfactory, and should be replaced. This new big change being unreasonable without some time to work on it properly, it is postponed for next versions (0.7, 0.8, ...). Maybe the best idea is to have some kind of "local services", that would use the same dependency injection mechanism as the execution-wide services. Services are now passed by keywoerd arguments only, to avoid confusion with data-arguments.
119 lines
3.5 KiB
Python
119 lines
3.5 KiB
Python
from operator import methodcaller
|
|
from unittest import TestCase
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
import bonobo
|
|
from bonobo.constants import NOT_MODIFIED, EMPTY
|
|
from bonobo.util import ensure_tuple, ValueHolder
|
|
from bonobo.util.testing import BufferingNodeExecutionContext, StaticNodeTest, ConfigurableNodeTest
|
|
|
|
|
|
class CountTest(StaticNodeTest, TestCase):
|
|
node = bonobo.count
|
|
|
|
def test_counter_required(self):
|
|
with pytest.raises(TypeError):
|
|
self.call()
|
|
|
|
def test_manual_call(self):
|
|
counter = ValueHolder(0)
|
|
for i in range(3):
|
|
self.call(counter)
|
|
assert counter == 3
|
|
|
|
def test_execution(self):
|
|
with self.execute() as context:
|
|
context.write_sync(*([EMPTY] * 42))
|
|
assert context.get_buffer() == [(42, )]
|
|
|
|
|
|
class IdentityTest(StaticNodeTest, TestCase):
|
|
node = bonobo.identity
|
|
|
|
def test_basic_call(self):
|
|
assert self.call(42) == 42
|
|
|
|
def test_execution(self):
|
|
object_list = [object() for _ in range(42)]
|
|
with self.execute() as context:
|
|
context.write_sync(*object_list)
|
|
assert context.get_buffer() == list(map(ensure_tuple, object_list))
|
|
|
|
|
|
class LimitTest(ConfigurableNodeTest, TestCase):
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.NodeType = bonobo.Limit
|
|
|
|
def test_execution_default(self):
|
|
object_list = [object() for _ in range(42)]
|
|
with self.execute() as context:
|
|
context.write_sync(*object_list)
|
|
|
|
assert context.get_buffer() == list(map(ensure_tuple, object_list[:10]))
|
|
|
|
def test_execution_custom(self):
|
|
object_list = [object() for _ in range(42)]
|
|
with self.execute(21) as context:
|
|
context.write_sync(*object_list)
|
|
|
|
assert context.get_buffer() == list(map(ensure_tuple, object_list[:21]))
|
|
|
|
def test_manual(self):
|
|
limit = self.NodeType(5)
|
|
buffer = []
|
|
for x in range(10):
|
|
buffer += list(limit(x))
|
|
assert len(buffer) == 5
|
|
|
|
def test_underflow(self):
|
|
limit = self.NodeType(10)
|
|
buffer = []
|
|
for x in range(5):
|
|
buffer += list(limit(x))
|
|
assert len(buffer) == 5
|
|
|
|
|
|
def test_tee():
|
|
inner = MagicMock(side_effect=bonobo.identity)
|
|
tee = bonobo.Tee(inner)
|
|
results = []
|
|
for i in range(10):
|
|
results.append(tee('foo'))
|
|
|
|
assert results == [NOT_MODIFIED] * 10
|
|
assert len(inner.mock_calls) == 10
|
|
|
|
|
|
def test_noop():
|
|
assert bonobo.noop(1, 2, 3, 4, foo='bar') == NOT_MODIFIED
|
|
|
|
|
|
def test_fixedwindow():
|
|
with BufferingNodeExecutionContext(bonobo.FixedWindow(2)) as context:
|
|
context.write_sync(*range(10))
|
|
assert context.get_buffer() == [(0, 1), (2, 3), (4, 5), (6, 7), (8, 9)]
|
|
|
|
with BufferingNodeExecutionContext(bonobo.FixedWindow(2)) as context:
|
|
context.write_sync(*range(9))
|
|
assert context.get_buffer() == [(0, 1), (2, 3), (4, 5), (6, 7), (
|
|
8,
|
|
None,
|
|
)]
|
|
|
|
with BufferingNodeExecutionContext(bonobo.FixedWindow(1)) as context:
|
|
context.write_sync(*range(3))
|
|
assert context.get_buffer() == [(0, ), (1, ), (2, )]
|
|
|
|
|
|
def test_methodcaller():
|
|
with BufferingNodeExecutionContext(methodcaller('swapcase')) as context:
|
|
context.write_sync('aaa', 'bBb', 'CcC')
|
|
assert context.get_buffer() == list(map(ensure_tuple, ['AAA', 'BbB', 'cCc']))
|
|
|
|
with BufferingNodeExecutionContext(methodcaller('zfill', 5)) as context:
|
|
context.write_sync('a', 'bb', 'ccc')
|
|
assert context.get_buffer() == list(map(ensure_tuple, ['0000a', '000bb', '00ccc']))
|