class StreamingContextTests(PySparkStreamingTestCase):
duration = 0.1
setupCalled = False
def _add_input_stream(self):
inputs = [range(1, x) for x in range(101)]
stream = self.ssc.queueStream(inputs)
self._collect(stream, 1, block=False)
def test_stop_only_streaming_context(self):
self._add_input_stream()
self.ssc.start()
self.ssc.stop(False)
self.assertEqual(
len(self.sc.parallelize(range(5), 5).glom().collect()), 5)
def test_stop_multiple_times(self):
self._add_input_stream()
self.ssc.start()
self.ssc.stop(False)
self.ssc.stop(False)
def test_queue_stream(self):
input = [list(range(i + 1)) for i in range(3)]
dstream = self.ssc.queueStream(input)
result = self._collect(dstream, 3)
self.assertEqual(input, result)
def test_text_file_stream(self):
d = tempfile.mkdtemp()
self.ssc = StreamingContext(self.sc, self.duration)
dstream2 = self.ssc.textFileStream(d).map(int)
result = self._collect(dstream2, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "w") as f:
f.writelines(["%d\n" % i for i in range(10)])
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))], result)
def test_binary_records_stream(self):
d = tempfile.mkdtemp()
self.ssc = StreamingContext(self.sc, self.duration)
dstream = self.ssc.binaryRecordsStream(
d, 10).map(lambda v: struct.unpack("10b", bytes(v)))
result = self._collect(dstream, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "wb") as f:
f.write(bytearray(range(10)))
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))],
[list(v[0]) for v in result])
def test_union(self):
input = [list(range(i + 1)) for i in range(3)]
dstream = self.ssc.queueStream(input)
dstream2 = self.ssc.queueStream(input)
dstream3 = self.ssc.union(dstream, dstream2)
result = self._collect(dstream3, 3)
expected = [i * 2 for i in input]
self.assertEqual(expected, result)
def test_transform(self):
dstream1 = self.ssc.queueStream([[1]])
dstream2 = self.ssc.queueStream([[2]])
dstream3 = self.ssc.queueStream([[3]])
def func(rdds):
rdd1, rdd2, rdd3 = rdds
return rdd2.union(rdd3).union(rdd1)
dstream = self.ssc.transform([dstream1, dstream2, dstream3], func)
self.assertEqual([2, 3, 1], self._take(dstream, 3))
def test_transform_pairrdd(self):
# This regression test case is for SPARK-17756.
dstream = self.ssc.queueStream(
[[1], [2], [3]]).transform(lambda rdd: rdd.cartesian(rdd))
self.assertEqual([(1, 1), (2, 2), (3, 3)], self._take(dstream, 3))
def test_get_active(self):
self.assertEqual(StreamingContext.getActive(), None)
# Verify that getActive() returns the active context
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
# Verify that getActive() returns None
self.ssc.stop(False)
self.assertEqual(StreamingContext.getActive(), None)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = StreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.assertEqual(StreamingContext.getActive(), None)
def test_get_active_or_create(self):
# Test StreamingContext.getActiveOrCreate() without checkpoint data
# See CheckpointTests for tests with checkpoint data
self.ssc = None
self.assertEqual(StreamingContext.getActive(), None)
def setupFunc():
ssc = StreamingContext(self.sc, self.duration)
ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.setupCalled = True
return ssc
# Verify that getActiveOrCreate() (w/o checkpoint) calls setupFunc when no context is active
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that getActiveOrCreate() returns active context and does not call the setupFunc
self.ssc.start()
self.setupCalled = False
self.assertEqual(StreamingContext.getActiveOrCreate(None, setupFunc),
self.ssc)
self.assertFalse(self.setupCalled)
# Verify that getActiveOrCreate() calls setupFunc after active context is stopped
self.ssc.stop(False)
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = StreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
def test_await_termination_or_timeout(self):
self._add_input_stream()
self.ssc.start()
self.assertFalse(self.ssc.awaitTerminationOrTimeout(0.001))
self.ssc.stop(False)
self.assertTrue(self.ssc.awaitTerminationOrTimeout(0.001))
class StreamingContextTests(PySparkStreamingTestCase):
duration = 0.1
setupCalled = False
def _add_input_stream(self):
inputs = [range(1, x) for x in range(101)]
stream = self.ssc.queueStream(inputs)
self._collect(stream, 1, block=False)
def test_stop_only_streaming_context(self):
self._add_input_stream()
self.ssc.start()
self.ssc.stop(False)
self.assertEqual(len(self.sc.parallelize(range(5), 5).glom().collect()), 5)
def test_stop_multiple_times(self):
self._add_input_stream()
self.ssc.start()
self.ssc.stop(False)
self.ssc.stop(False)
def test_queue_stream(self):
input = [list(range(i + 1)) for i in range(3)]
dstream = self.ssc.queueStream(input)
result = self._collect(dstream, 3)
self.assertEqual(input, result)
def test_text_file_stream(self):
d = tempfile.mkdtemp()
self.ssc = StreamingContext(self.sc, self.duration)
dstream2 = self.ssc.textFileStream(d).map(int)
result = self._collect(dstream2, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "w") as f:
f.writelines(["%d\n" % i for i in range(10)])
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))], result)
def test_binary_records_stream(self):
d = tempfile.mkdtemp()
self.ssc = StreamingContext(self.sc, self.duration)
dstream = self.ssc.binaryRecordsStream(d, 10).map(
lambda v: struct.unpack("10b", bytes(v)))
result = self._collect(dstream, 2, block=False)
self.ssc.start()
for name in ('a', 'b'):
time.sleep(1)
with open(os.path.join(d, name), "wb") as f:
f.write(bytearray(range(10)))
self.wait_for(result, 2)
self.assertEqual([list(range(10)), list(range(10))], [list(v[0]) for v in result])
def test_union(self):
input = [list(range(i + 1)) for i in range(3)]
dstream = self.ssc.queueStream(input)
dstream2 = self.ssc.queueStream(input)
dstream3 = self.ssc.union(dstream, dstream2)
result = self._collect(dstream3, 3)
expected = [i * 2 for i in input]
self.assertEqual(expected, result)
def test_transform(self):
dstream1 = self.ssc.queueStream([[1]])
dstream2 = self.ssc.queueStream([[2]])
dstream3 = self.ssc.queueStream([[3]])
def func(rdds):
rdd1, rdd2, rdd3 = rdds
return rdd2.union(rdd3).union(rdd1)
dstream = self.ssc.transform([dstream1, dstream2, dstream3], func)
self.assertEqual([2, 3, 1], self._take(dstream, 3))
def test_transform_pairrdd(self):
# This regression test case is for SPARK-17756.
dstream = self.ssc.queueStream(
[[1], [2], [3]]).transform(lambda rdd: rdd.cartesian(rdd))
self.assertEqual([(1, 1), (2, 2), (3, 3)], self._take(dstream, 3))
def test_get_active(self):
self.assertEqual(StreamingContext.getActive(), None)
# Verify that getActive() returns the active context
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
# Verify that getActive() returns None
self.ssc.stop(False)
self.assertEqual(StreamingContext.getActive(), None)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = StreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.assertEqual(StreamingContext.getActive(), None)
def test_get_active_or_create(self):
# Test StreamingContext.getActiveOrCreate() without checkpoint data
# See CheckpointTests for tests with checkpoint data
self.ssc = None
self.assertEqual(StreamingContext.getActive(), None)
def setupFunc():
ssc = StreamingContext(self.sc, self.duration)
ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.setupCalled = True
return ssc
# Verify that getActiveOrCreate() (w/o checkpoint) calls setupFunc when no context is active
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that getActiveOrCreate() returns active context and does not call the setupFunc
self.ssc.start()
self.setupCalled = False
self.assertEqual(StreamingContext.getActiveOrCreate(None, setupFunc), self.ssc)
self.assertFalse(self.setupCalled)
# Verify that getActiveOrCreate() calls setupFunc after active context is stopped
self.ssc.stop(False)
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
# Verify that if the Java context is stopped, then getActive() returns None
self.ssc = StreamingContext(self.sc, self.duration)
self.ssc.queueStream([[1]]).foreachRDD(lambda rdd: rdd.count())
self.ssc.start()
self.assertEqual(StreamingContext.getActive(), self.ssc)
self.ssc._jssc.stop(False)
self.setupCalled = False
self.ssc = StreamingContext.getActiveOrCreate(None, setupFunc)
self.assertTrue(self.setupCalled)
def test_await_termination_or_timeout(self):
self._add_input_stream()
self.ssc.start()
self.assertFalse(self.ssc.awaitTerminationOrTimeout(0.001))
self.ssc.stop(False)
self.assertTrue(self.ssc.awaitTerminationOrTimeout(0.001))
class BasicOperationTests(PySparkStreamingTestCase):
def test_map(self):
"""Basic operation test for DStream.map."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.map(str)
expected = [list(map(str, x)) for x in input]
self._test_func(input, func, expected)
def test_flatMap(self):
"""Basic operation test for DStream.flatMap."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.flatMap(lambda x: (x, x * 2))
expected = [
list(chain.from_iterable((map(lambda y: [y, y * 2], x))))
for x in input
]
self._test_func(input, func, expected)
def test_filter(self):
"""Basic operation test for DStream.filter."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.filter(lambda x: x % 2 == 0)
expected = [[y for y in x if y % 2 == 0] for x in input]
self._test_func(input, func, expected)
def test_count(self):
"""Basic operation test for DStream.count."""
input = [range(5), range(10), range(20)]
def func(dstream):
return dstream.count()
expected = [[len(x)] for x in input]
self._test_func(input, func, expected)
def test_slice(self):
"""Basic operation test for DStream.slice."""
import datetime as dt
self.ssc = StreamingContext(self.sc, 1.0)
self.ssc.remember(4.0)
input = [[1], [2], [3], [4]]
stream = self.ssc.queueStream(
[self.sc.parallelize(d, 1) for d in input])
time_vals = []
def get_times(t, rdd):
if rdd and len(time_vals) < len(input):
time_vals.append(t)
stream.foreachRDD(get_times)
self.ssc.start()
self.wait_for(time_vals, 4)
begin_time = time_vals[0]
def get_sliced(begin_delta, end_delta):
begin = begin_time + dt.timedelta(seconds=begin_delta)
end = begin_time + dt.timedelta(seconds=end_delta)
rdds = stream.slice(begin, end)
result_list = [rdd.collect() for rdd in rdds]
return [r for result in result_list for r in result]
self.assertEqual(set([1]), set(get_sliced(0, 0)))
self.assertEqual(set([2, 3]), set(get_sliced(1, 2)))
self.assertEqual(set([2, 3, 4]), set(get_sliced(1, 4)))
self.assertEqual(set([1, 2, 3, 4]), set(get_sliced(0, 4)))
def test_reduce(self):
"""Basic operation test for DStream.reduce."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.reduce(operator.add)
expected = [[reduce(operator.add, x)] for x in input]
self._test_func(input, func, expected)
def test_reduceByKey(self):
"""Basic operation test for DStream.reduceByKey."""
input = [[("a", 1), ("a", 1), ("b", 1), ("b", 1)],
[("", 1), ("", 1), ("", 1), ("", 1)],
[(1, 1), (1, 1), (2, 1), (2, 1), (3, 1)]]
def func(dstream):
return dstream.reduceByKey(operator.add)
expected = [[("a", 2), ("b", 2)], [("", 4)], [(1, 2), (2, 2), (3, 1)]]
self._test_func(input, func, expected, sort=True)
def test_mapValues(self):
"""Basic operation test for DStream.mapValues."""
input = [[("a", 2), ("b", 2), ("c", 1), ("d", 1)],
[(0, 4), (1, 1), (2, 2), (3, 3)],
[(1, 1), (2, 1), (3, 1), (4, 1)]]
def func(dstream):
return dstream.mapValues(lambda x: x + 10)
expected = [[("a", 12), ("b", 12), ("c", 11), ("d", 11)],
[(0, 14), (1, 11), (2, 12), (3, 13)],
[(1, 11), (2, 11), (3, 11), (4, 11)]]
self._test_func(input, func, expected, sort=True)
def test_flatMapValues(self):
"""Basic operation test for DStream.flatMapValues."""
input = [[("a", 2), ("b", 2), ("c", 1), ("d", 1)],
[(0, 4), (1, 1), (2, 1), (3, 1)],
[(1, 1), (2, 1), (3, 1), (4, 1)]]
def func(dstream):
return dstream.flatMapValues(lambda x: (x, x + 10))
expected = [[("a", 2), ("a", 12), ("b", 2), ("b", 12), ("c", 1),
("c", 11), ("d", 1), ("d", 11)],
[(0, 4), (0, 14), (1, 1), (1, 11), (2, 1), (2, 11), (3, 1),
(3, 11)],
[(1, 1), (1, 11), (2, 1), (2, 11), (3, 1), (3, 11), (4, 1),
(4, 11)]]
self._test_func(input, func, expected)
def test_glom(self):
"""Basic operation test for DStream.glom."""
input = [range(1, 5), range(5, 9), range(9, 13)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
return dstream.glom()
expected = [[[1, 2], [3, 4]], [[5, 6], [7, 8]], [[9, 10], [11, 12]]]
self._test_func(rdds, func, expected)
def test_mapPartitions(self):
"""Basic operation test for DStream.mapPartitions."""
input = [range(1, 5), range(5, 9), range(9, 13)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
def f(iterator):
yield sum(iterator)
return dstream.mapPartitions(f)
expected = [[3, 7], [11, 15], [19, 23]]
self._test_func(rdds, func, expected)
def test_countByValue(self):
"""Basic operation test for DStream.countByValue."""
input = [
list(range(1, 5)) * 2,
list(range(5, 7)) + list(range(5, 9)), ["a", "a", "b", ""]
]
def func(dstream):
return dstream.countByValue()
expected = [[(1, 2), (2, 2), (3, 2), (4, 2)],
[(5, 2), (6, 2), (7, 1), (8, 1)],
[("a", 2), ("b", 1), ("", 1)]]
self._test_func(input, func, expected, sort=True)
def test_groupByKey(self):
"""Basic operation test for DStream.groupByKey."""
input = [[(1, 1), (2, 1), (3, 1), (4, 1)],
[(1, 1), (1, 1), (1, 1), (2, 1), (2, 1), (3, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1), ("", 1)]]
def func(dstream):
return dstream.groupByKey().mapValues(list)
expected = [[(1, [1]), (2, [1]), (3, [1]), (4, [1])],
[(1, [1, 1, 1]), (2, [1, 1]), (3, [1])],
[("a", [1, 1]), ("b", [1]), ("", [1, 1, 1])]]
self._test_func(input, func, expected, sort=True)
def test_combineByKey(self):
"""Basic operation test for DStream.combineByKey."""
input = [[(1, 1), (2, 1), (3, 1), (4, 1)],
[(1, 1), (1, 1), (1, 1), (2, 1), (2, 1), (3, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1), ("", 1)]]
def func(dstream):
def add(a, b):
return a + str(b)
return dstream.combineByKey(str, add, add)
expected = [[(1, "1"), (2, "1"), (3, "1"), (4, "1")],
[(1, "111"), (2, "11"), (3, "1")],
[("a", "11"), ("b", "1"), ("", "111")]]
self._test_func(input, func, expected, sort=True)
def test_repartition(self):
input = [range(1, 5), range(5, 9)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
return dstream.repartition(1).glom()
expected = [[[1, 2, 3, 4]], [[5, 6, 7, 8]]]
self._test_func(rdds, func, expected)
def test_union(self):
input1 = [range(3), range(5), range(6)]
input2 = [range(3, 6), range(5, 6)]
def func(d1, d2):
return d1.union(d2)
expected = [list(range(6)), list(range(6)), list(range(6))]
self._test_func(input1, func, expected, input2=input2)
def test_cogroup(self):
input = [[(1, 1), (2, 1), (3, 1)], [(1, 1), (1, 1), (1, 1), (2, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1)]]
input2 = [[(1, 2)], [(4, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 2)]]
def func(d1, d2):
return d1.cogroup(d2).mapValues(lambda vs: tuple(map(list, vs)))
expected = [[(1, ([1], [2])), (2, ([1], [])), (3, ([1], []))],
[(1, ([1, 1, 1], [])), (2, ([1], [])), (4, ([], [1]))],
[("a", ([1, 1], [1, 1])), ("b", ([1], [1])),
("", ([1, 1], [1, 2]))]]
self._test_func(input, func, expected, sort=True, input2=input2)
def test_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.join(b)
expected = [[('b', (2, 3))]]
self._test_func(input, func, expected, True, input2)
def test_left_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.leftOuterJoin(b)
expected = [[('a', (1, None)), ('b', (2, 3))]]
self._test_func(input, func, expected, True, input2)
def test_right_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.rightOuterJoin(b)
expected = [[('b', (2, 3)), ('c', (None, 4))]]
self._test_func(input, func, expected, True, input2)
def test_full_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.fullOuterJoin(b)
expected = [[('a', (1, None)), ('b', (2, 3)), ('c', (None, 4))]]
self._test_func(input, func, expected, True, input2)
def test_update_state_by_key(self):
def updater(vs, s):
if not s:
s = []
s.extend(vs)
return s
input = [[('k', i)] for i in range(5)]
def func(dstream):
return dstream.updateStateByKey(updater)
expected = [[0], [0, 1], [0, 1, 2], [0, 1, 2, 3], [0, 1, 2, 3, 4]]
expected = [[('k', v)] for v in expected]
self._test_func(input, func, expected)
def test_update_state_by_key_initial_rdd(self):
def updater(vs, s):
if not s:
s = []
s.extend(vs)
return s
initial = [('k', [0, 1])]
initial = self.sc.parallelize(initial, 1)
input = [[('k', i)] for i in range(2, 5)]
def func(dstream):
return dstream.updateStateByKey(updater, initialRDD=initial)
expected = [[0, 1, 2], [0, 1, 2, 3], [0, 1, 2, 3, 4]]
expected = [[('k', v)] for v in expected]
self._test_func(input, func, expected)
def test_failed_func(self):
# Test failure in
# TransformFunction.apply(rdd: Option[RDD[_]], time: Time)
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream = self.ssc.queueStream(input)
def failed_func(i):
raise ValueError("This is a special error")
input_stream.map(failed_func).pprint()
self.ssc.start()
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
def test_failed_func2(self):
# Test failure in
# TransformFunction.apply(rdd: Option[RDD[_]], rdd2: Option[RDD[_]], time: Time)
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream1 = self.ssc.queueStream(input)
input_stream2 = self.ssc.queueStream(input)
def failed_func(rdd1, rdd2):
raise ValueError("This is a special error")
input_stream1.transformWith(failed_func, input_stream2, True).pprint()
self.ssc.start()
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
def test_failed_func_with_reseting_failure(self):
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream = self.ssc.queueStream(input)
def failed_func(i):
if i == 1:
# Make it fail in the second batch
raise ValueError("This is a special error")
else:
return i
# We should be able to see the results of the 3rd and 4th batches even if the second batch
# fails
expected = [[0], [2], [3]]
self.assertEqual(expected,
self._collect(input_stream.map(failed_func), 3))
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
class BasicOperationTests(PySparkStreamingTestCase):
def test_map(self):
"""Basic operation test for DStream.map."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.map(str)
expected = [list(map(str, x)) for x in input]
self._test_func(input, func, expected)
def test_flatMap(self):
"""Basic operation test for DStream.flatMap."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.flatMap(lambda x: (x, x * 2))
expected = [list(chain.from_iterable((map(lambda y: [y, y * 2], x))))
for x in input]
self._test_func(input, func, expected)
def test_filter(self):
"""Basic operation test for DStream.filter."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.filter(lambda x: x % 2 == 0)
expected = [[y for y in x if y % 2 == 0] for x in input]
self._test_func(input, func, expected)
def test_count(self):
"""Basic operation test for DStream.count."""
input = [range(5), range(10), range(20)]
def func(dstream):
return dstream.count()
expected = [[len(x)] for x in input]
self._test_func(input, func, expected)
def test_slice(self):
"""Basic operation test for DStream.slice."""
import datetime as dt
self.ssc = StreamingContext(self.sc, 1.0)
self.ssc.remember(4.0)
input = [[1], [2], [3], [4]]
stream = self.ssc.queueStream([self.sc.parallelize(d, 1) for d in input])
time_vals = []
def get_times(t, rdd):
if rdd and len(time_vals) < len(input):
time_vals.append(t)
stream.foreachRDD(get_times)
self.ssc.start()
self.wait_for(time_vals, 4)
begin_time = time_vals[0]
def get_sliced(begin_delta, end_delta):
begin = begin_time + dt.timedelta(seconds=begin_delta)
end = begin_time + dt.timedelta(seconds=end_delta)
rdds = stream.slice(begin, end)
result_list = [rdd.collect() for rdd in rdds]
return [r for result in result_list for r in result]
self.assertEqual(set([1]), set(get_sliced(0, 0)))
self.assertEqual(set([2, 3]), set(get_sliced(1, 2)))
self.assertEqual(set([2, 3, 4]), set(get_sliced(1, 4)))
self.assertEqual(set([1, 2, 3, 4]), set(get_sliced(0, 4)))
def test_reduce(self):
"""Basic operation test for DStream.reduce."""
input = [range(1, 5), range(5, 9), range(9, 13)]
def func(dstream):
return dstream.reduce(operator.add)
expected = [[reduce(operator.add, x)] for x in input]
self._test_func(input, func, expected)
def test_reduceByKey(self):
"""Basic operation test for DStream.reduceByKey."""
input = [[("a", 1), ("a", 1), ("b", 1), ("b", 1)],
[("", 1), ("", 1), ("", 1), ("", 1)],
[(1, 1), (1, 1), (2, 1), (2, 1), (3, 1)]]
def func(dstream):
return dstream.reduceByKey(operator.add)
expected = [[("a", 2), ("b", 2)], [("", 4)], [(1, 2), (2, 2), (3, 1)]]
self._test_func(input, func, expected, sort=True)
def test_mapValues(self):
"""Basic operation test for DStream.mapValues."""
input = [[("a", 2), ("b", 2), ("c", 1), ("d", 1)],
[(0, 4), (1, 1), (2, 2), (3, 3)],
[(1, 1), (2, 1), (3, 1), (4, 1)]]
def func(dstream):
return dstream.mapValues(lambda x: x + 10)
expected = [[("a", 12), ("b", 12), ("c", 11), ("d", 11)],
[(0, 14), (1, 11), (2, 12), (3, 13)],
[(1, 11), (2, 11), (3, 11), (4, 11)]]
self._test_func(input, func, expected, sort=True)
def test_flatMapValues(self):
"""Basic operation test for DStream.flatMapValues."""
input = [[("a", 2), ("b", 2), ("c", 1), ("d", 1)],
[(0, 4), (1, 1), (2, 1), (3, 1)],
[(1, 1), (2, 1), (3, 1), (4, 1)]]
def func(dstream):
return dstream.flatMapValues(lambda x: (x, x + 10))
expected = [[("a", 2), ("a", 12), ("b", 2), ("b", 12),
("c", 1), ("c", 11), ("d", 1), ("d", 11)],
[(0, 4), (0, 14), (1, 1), (1, 11), (2, 1), (2, 11), (3, 1), (3, 11)],
[(1, 1), (1, 11), (2, 1), (2, 11), (3, 1), (3, 11), (4, 1), (4, 11)]]
self._test_func(input, func, expected)
def test_glom(self):
"""Basic operation test for DStream.glom."""
input = [range(1, 5), range(5, 9), range(9, 13)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
return dstream.glom()
expected = [[[1, 2], [3, 4]], [[5, 6], [7, 8]], [[9, 10], [11, 12]]]
self._test_func(rdds, func, expected)
def test_mapPartitions(self):
"""Basic operation test for DStream.mapPartitions."""
input = [range(1, 5), range(5, 9), range(9, 13)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
def f(iterator):
yield sum(iterator)
return dstream.mapPartitions(f)
expected = [[3, 7], [11, 15], [19, 23]]
self._test_func(rdds, func, expected)
def test_countByValue(self):
"""Basic operation test for DStream.countByValue."""
input = [list(range(1, 5)) * 2, list(range(5, 7)) + list(range(5, 9)), ["a", "a", "b", ""]]
def func(dstream):
return dstream.countByValue()
expected = [[(1, 2), (2, 2), (3, 2), (4, 2)],
[(5, 2), (6, 2), (7, 1), (8, 1)],
[("a", 2), ("b", 1), ("", 1)]]
self._test_func(input, func, expected, sort=True)
def test_groupByKey(self):
"""Basic operation test for DStream.groupByKey."""
input = [[(1, 1), (2, 1), (3, 1), (4, 1)],
[(1, 1), (1, 1), (1, 1), (2, 1), (2, 1), (3, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1), ("", 1)]]
def func(dstream):
return dstream.groupByKey().mapValues(list)
expected = [[(1, [1]), (2, [1]), (3, [1]), (4, [1])],
[(1, [1, 1, 1]), (2, [1, 1]), (3, [1])],
[("a", [1, 1]), ("b", [1]), ("", [1, 1, 1])]]
self._test_func(input, func, expected, sort=True)
def test_combineByKey(self):
"""Basic operation test for DStream.combineByKey."""
input = [[(1, 1), (2, 1), (3, 1), (4, 1)],
[(1, 1), (1, 1), (1, 1), (2, 1), (2, 1), (3, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1), ("", 1)]]
def func(dstream):
def add(a, b):
return a + str(b)
return dstream.combineByKey(str, add, add)
expected = [[(1, "1"), (2, "1"), (3, "1"), (4, "1")],
[(1, "111"), (2, "11"), (3, "1")],
[("a", "11"), ("b", "1"), ("", "111")]]
self._test_func(input, func, expected, sort=True)
def test_repartition(self):
input = [range(1, 5), range(5, 9)]
rdds = [self.sc.parallelize(r, 2) for r in input]
def func(dstream):
return dstream.repartition(1).glom()
expected = [[[1, 2, 3, 4]], [[5, 6, 7, 8]]]
self._test_func(rdds, func, expected)
def test_union(self):
input1 = [range(3), range(5), range(6)]
input2 = [range(3, 6), range(5, 6)]
def func(d1, d2):
return d1.union(d2)
expected = [list(range(6)), list(range(6)), list(range(6))]
self._test_func(input1, func, expected, input2=input2)
def test_cogroup(self):
input = [[(1, 1), (2, 1), (3, 1)],
[(1, 1), (1, 1), (1, 1), (2, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 1)]]
input2 = [[(1, 2)],
[(4, 1)],
[("a", 1), ("a", 1), ("b", 1), ("", 1), ("", 2)]]
def func(d1, d2):
return d1.cogroup(d2).mapValues(lambda vs: tuple(map(list, vs)))
expected = [[(1, ([1], [2])), (2, ([1], [])), (3, ([1], []))],
[(1, ([1, 1, 1], [])), (2, ([1], [])), (4, ([], [1]))],
[("a", ([1, 1], [1, 1])), ("b", ([1], [1])), ("", ([1, 1], [1, 2]))]]
self._test_func(input, func, expected, sort=True, input2=input2)
def test_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.join(b)
expected = [[('b', (2, 3))]]
self._test_func(input, func, expected, True, input2)
def test_left_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.leftOuterJoin(b)
expected = [[('a', (1, None)), ('b', (2, 3))]]
self._test_func(input, func, expected, True, input2)
def test_right_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.rightOuterJoin(b)
expected = [[('b', (2, 3)), ('c', (None, 4))]]
self._test_func(input, func, expected, True, input2)
def test_full_outer_join(self):
input = [[('a', 1), ('b', 2)]]
input2 = [[('b', 3), ('c', 4)]]
def func(a, b):
return a.fullOuterJoin(b)
expected = [[('a', (1, None)), ('b', (2, 3)), ('c', (None, 4))]]
self._test_func(input, func, expected, True, input2)
def test_update_state_by_key(self):
def updater(vs, s):
if not s:
s = []
s.extend(vs)
return s
input = [[('k', i)] for i in range(5)]
def func(dstream):
return dstream.updateStateByKey(updater)
expected = [[0], [0, 1], [0, 1, 2], [0, 1, 2, 3], [0, 1, 2, 3, 4]]
expected = [[('k', v)] for v in expected]
self._test_func(input, func, expected)
def test_update_state_by_key_initial_rdd(self):
def updater(vs, s):
if not s:
s = []
s.extend(vs)
return s
initial = [('k', [0, 1])]
initial = self.sc.parallelize(initial, 1)
input = [[('k', i)] for i in range(2, 5)]
def func(dstream):
return dstream.updateStateByKey(updater, initialRDD=initial)
expected = [[0, 1, 2], [0, 1, 2, 3], [0, 1, 2, 3, 4]]
expected = [[('k', v)] for v in expected]
self._test_func(input, func, expected)
def test_failed_func(self):
# Test failure in
# TransformFunction.apply(rdd: Option[RDD[_]], time: Time)
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream = self.ssc.queueStream(input)
def failed_func(i):
raise ValueError("This is a special error")
input_stream.map(failed_func).pprint()
self.ssc.start()
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
def test_failed_func2(self):
# Test failure in
# TransformFunction.apply(rdd: Option[RDD[_]], rdd2: Option[RDD[_]], time: Time)
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream1 = self.ssc.queueStream(input)
input_stream2 = self.ssc.queueStream(input)
def failed_func(rdd1, rdd2):
raise ValueError("This is a special error")
input_stream1.transformWith(failed_func, input_stream2, True).pprint()
self.ssc.start()
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
def test_failed_func_with_reseting_failure(self):
input = [self.sc.parallelize([d], 1) for d in range(4)]
input_stream = self.ssc.queueStream(input)
def failed_func(i):
if i == 1:
# Make it fail in the second batch
raise ValueError("This is a special error")
else:
return i
# We should be able to see the results of the 3rd and 4th batches even if the second batch
# fails
expected = [[0], [2], [3]]
self.assertEqual(expected, self._collect(input_stream.map(failed_func), 3))
try:
self.ssc.awaitTerminationOrTimeout(10)
except:
import traceback
failure = traceback.format_exc()
self.assertTrue("This is a special error" in failure)
return
self.fail("a failed func should throw an error")
