Search in sources :

Example 21 with OperatorSpecGraph

use of org.apache.samza.operators.OperatorSpecGraph in project samza by apache.

the class TestWindowOperator method testNonKeyedTumblingWindowsDiscardingMode.

@Test
public void testNonKeyedTumblingWindowsDiscardingMode() throws Exception {
    OperatorSpecGraph sgb = this.getTumblingWindowStreamGraph(AccumulationMode.DISCARDING, Duration.ofSeconds(1), Triggers.repeat(Triggers.count(1000))).getOperatorSpecGraph();
    List<WindowPane<Integer, Collection<IntegerEnvelope>>> windowPanes = new ArrayList<>();
    TestClock testClock = new TestClock();
    StreamOperatorTask task = new StreamOperatorTask(sgb, testClock);
    task.init(this.context);
    MessageCollector messageCollector = envelope -> windowPanes.add((WindowPane<Integer, Collection<IntegerEnvelope>>) envelope.getMessage());
    Assert.assertEquals(windowPanes.size(), 0);
    integers.forEach(n -> task.processAsync(new IntegerEnvelope(n), messageCollector, taskCoordinator, taskCallback));
    Assert.assertEquals(windowPanes.size(), 0);
    testClock.advanceTime(Duration.ofSeconds(1));
    Assert.assertEquals(windowPanes.size(), 0);
    task.window(messageCollector, taskCoordinator);
    Assert.assertEquals(windowPanes.size(), 1);
    Assert.assertEquals((windowPanes.get(0).getMessage()).size(), 9);
}
Also used : TestClock(org.apache.samza.testUtils.TestClock) StreamApplicationDescriptorImpl(org.apache.samza.application.descriptors.StreamApplicationDescriptorImpl) TaskModel(org.apache.samza.job.model.TaskModel) GenericInputDescriptor(org.apache.samza.system.descriptors.GenericInputDescriptor) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) AccumulationMode(org.apache.samza.operators.windows.AccumulationMode) Duration(java.time.Duration) Map(java.util.Map) MapConfig(org.apache.samza.config.MapConfig) KV(org.apache.samza.operators.KV) TaskCallback(org.apache.samza.task.TaskCallback) ImmutableSet(com.google.common.collect.ImmutableSet) TaskName(org.apache.samza.container.TaskName) IncomingMessageEnvelope(org.apache.samza.system.IncomingMessageEnvelope) Collection(java.util.Collection) Triggers(org.apache.samza.operators.triggers.Triggers) Context(org.apache.samza.context.Context) List(java.util.List) TestClock(org.apache.samza.testUtils.TestClock) TestInMemoryStore(org.apache.samza.operators.impl.store.TestInMemoryStore) Config(org.apache.samza.config.Config) KVSerde(org.apache.samza.serializers.KVSerde) StreamApplication(org.apache.samza.application.StreamApplication) MetricsRegistryMap(org.apache.samza.metrics.MetricsRegistryMap) Mockito.mock(org.mockito.Mockito.mock) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) GenericSystemDescriptor(org.apache.samza.system.descriptors.GenericSystemDescriptor) HashMap(java.util.HashMap) Serde(org.apache.samza.serializers.Serde) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) ArrayList(java.util.ArrayList) MapFunction(org.apache.samza.operators.functions.MapFunction) WindowPane(org.apache.samza.operators.windows.WindowPane) Trigger(org.apache.samza.operators.triggers.Trigger) ImmutableList(com.google.common.collect.ImmutableList) MessageCollector(org.apache.samza.task.MessageCollector) FiringType(org.apache.samza.operators.triggers.FiringType) SystemStream(org.apache.samza.system.SystemStream) MockContext(org.apache.samza.context.MockContext) IntegerSerde(org.apache.samza.serializers.IntegerSerde) MessageStream(org.apache.samza.operators.MessageStream) Before(org.junit.Before) Windows(org.apache.samza.operators.windows.Windows) Partition(org.apache.samza.Partition) IOException(java.io.IOException) Test(org.junit.Test) Mockito.times(org.mockito.Mockito.times) Mockito.when(org.mockito.Mockito.when) TaskCoordinator(org.apache.samza.task.TaskCoordinator) Mockito.verify(org.mockito.Mockito.verify) OutgoingMessageEnvelope(org.apache.samza.system.OutgoingMessageEnvelope) TaskContextImpl(org.apache.samza.context.TaskContextImpl) Assert(org.junit.Assert) TimeSeriesKeySerde(org.apache.samza.operators.impl.store.TimeSeriesKeySerde) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) MessageCollector(org.apache.samza.task.MessageCollector) ArrayList(java.util.ArrayList) Collection(java.util.Collection) WindowPane(org.apache.samza.operators.windows.WindowPane) Test(org.junit.Test)

Example 22 with OperatorSpecGraph

use of org.apache.samza.operators.OperatorSpecGraph in project samza by apache.

the class TestWindowOperator method testEndOfStreamFlushesWithEarlyTriggerFirings.

@Test
public void testEndOfStreamFlushesWithEarlyTriggerFirings() throws Exception {
    OperatorSpecGraph sgb = this.getTumblingWindowStreamGraph(AccumulationMode.DISCARDING, Duration.ofSeconds(1), Triggers.repeat(Triggers.count(2))).getOperatorSpecGraph();
    List<WindowPane<Integer, Collection<IntegerEnvelope>>> windowPanes = new ArrayList<>();
    TestClock testClock = new TestClock();
    StreamOperatorTask task = new StreamOperatorTask(sgb, testClock);
    task.init(this.context);
    MessageCollector messageCollector = envelope -> windowPanes.add((WindowPane<Integer, Collection<IntegerEnvelope>>) envelope.getMessage());
    Assert.assertEquals(windowPanes.size(), 0);
    List<Integer> integerList = ImmutableList.of(1, 2, 1, 2, 1);
    integerList.forEach(n -> task.processAsync(new IntegerEnvelope(n), messageCollector, taskCoordinator, taskCallback));
    // early triggers should emit (1,2) and (1,2) in the same window.
    Assert.assertEquals(windowPanes.size(), 2);
    testClock.advanceTime(Duration.ofSeconds(1));
    Assert.assertEquals(windowPanes.size(), 2);
    final IncomingMessageEnvelope endOfStream = IncomingMessageEnvelope.buildEndOfStreamEnvelope(new SystemStreamPartition("kafka", "integers", new Partition(0)));
    task.processAsync(endOfStream, messageCollector, taskCoordinator, taskCallback);
    // end of stream flushes the last entry (1)
    Assert.assertEquals(windowPanes.size(), 3);
    Assert.assertEquals((windowPanes.get(0).getMessage()).size(), 2);
    verify(taskCoordinator, times(1)).commit(TaskCoordinator.RequestScope.CURRENT_TASK);
    verify(taskCoordinator, times(1)).shutdown(TaskCoordinator.RequestScope.CURRENT_TASK);
}
Also used : StreamApplicationDescriptorImpl(org.apache.samza.application.descriptors.StreamApplicationDescriptorImpl) TaskModel(org.apache.samza.job.model.TaskModel) GenericInputDescriptor(org.apache.samza.system.descriptors.GenericInputDescriptor) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) AccumulationMode(org.apache.samza.operators.windows.AccumulationMode) Duration(java.time.Duration) Map(java.util.Map) MapConfig(org.apache.samza.config.MapConfig) KV(org.apache.samza.operators.KV) TaskCallback(org.apache.samza.task.TaskCallback) ImmutableSet(com.google.common.collect.ImmutableSet) TaskName(org.apache.samza.container.TaskName) IncomingMessageEnvelope(org.apache.samza.system.IncomingMessageEnvelope) Collection(java.util.Collection) Triggers(org.apache.samza.operators.triggers.Triggers) Context(org.apache.samza.context.Context) List(java.util.List) TestClock(org.apache.samza.testUtils.TestClock) TestInMemoryStore(org.apache.samza.operators.impl.store.TestInMemoryStore) Config(org.apache.samza.config.Config) KVSerde(org.apache.samza.serializers.KVSerde) StreamApplication(org.apache.samza.application.StreamApplication) MetricsRegistryMap(org.apache.samza.metrics.MetricsRegistryMap) Mockito.mock(org.mockito.Mockito.mock) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) GenericSystemDescriptor(org.apache.samza.system.descriptors.GenericSystemDescriptor) HashMap(java.util.HashMap) Serde(org.apache.samza.serializers.Serde) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) ArrayList(java.util.ArrayList) MapFunction(org.apache.samza.operators.functions.MapFunction) WindowPane(org.apache.samza.operators.windows.WindowPane) Trigger(org.apache.samza.operators.triggers.Trigger) ImmutableList(com.google.common.collect.ImmutableList) MessageCollector(org.apache.samza.task.MessageCollector) FiringType(org.apache.samza.operators.triggers.FiringType) SystemStream(org.apache.samza.system.SystemStream) MockContext(org.apache.samza.context.MockContext) IntegerSerde(org.apache.samza.serializers.IntegerSerde) MessageStream(org.apache.samza.operators.MessageStream) Before(org.junit.Before) Windows(org.apache.samza.operators.windows.Windows) Partition(org.apache.samza.Partition) IOException(java.io.IOException) Test(org.junit.Test) Mockito.times(org.mockito.Mockito.times) Mockito.when(org.mockito.Mockito.when) TaskCoordinator(org.apache.samza.task.TaskCoordinator) Mockito.verify(org.mockito.Mockito.verify) OutgoingMessageEnvelope(org.apache.samza.system.OutgoingMessageEnvelope) TaskContextImpl(org.apache.samza.context.TaskContextImpl) Assert(org.junit.Assert) TimeSeriesKeySerde(org.apache.samza.operators.impl.store.TimeSeriesKeySerde) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) Partition(org.apache.samza.Partition) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) IncomingMessageEnvelope(org.apache.samza.system.IncomingMessageEnvelope) ArrayList(java.util.ArrayList) WindowPane(org.apache.samza.operators.windows.WindowPane) TestClock(org.apache.samza.testUtils.TestClock) MessageCollector(org.apache.samza.task.MessageCollector) Collection(java.util.Collection) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) Test(org.junit.Test)

Example 23 with OperatorSpecGraph

use of org.apache.samza.operators.OperatorSpecGraph in project samza by apache.

the class TestWindowOperator method testTumblingWindowsDiscardingMode.

@Test
public void testTumblingWindowsDiscardingMode() throws Exception {
    OperatorSpecGraph sgb = this.getKeyedTumblingWindowStreamGraph(AccumulationMode.DISCARDING, Duration.ofSeconds(1), Triggers.repeat(Triggers.count(2))).getOperatorSpecGraph();
    List<WindowPane<Integer, Collection<IntegerEnvelope>>> windowPanes = new ArrayList<>();
    TestClock testClock = new TestClock();
    StreamOperatorTask task = new StreamOperatorTask(sgb, testClock);
    task.init(this.context);
    MessageCollector messageCollector = envelope -> windowPanes.add((WindowPane<Integer, Collection<IntegerEnvelope>>) envelope.getMessage());
    integers.forEach(n -> task.processAsync(new IntegerEnvelope(n), messageCollector, taskCoordinator, taskCallback));
    testClock.advanceTime(Duration.ofSeconds(1));
    task.window(messageCollector, taskCoordinator);
    Assert.assertEquals(windowPanes.size(), 5);
    Assert.assertEquals(windowPanes.get(0).getKey().getKey(), new Integer(1));
    Assert.assertEquals((windowPanes.get(0).getMessage()).size(), 2);
    Assert.assertEquals(windowPanes.get(1).getKey().getKey(), new Integer(2));
    Assert.assertEquals((windowPanes.get(1).getMessage()).size(), 2);
    Assert.assertEquals(windowPanes.get(2).getKey().getKey(), new Integer(1));
    Assert.assertEquals((windowPanes.get(2).getMessage()).size(), 2);
    Assert.assertEquals(windowPanes.get(3).getKey().getKey(), new Integer(2));
    Assert.assertEquals((windowPanes.get(3).getMessage()).size(), 2);
    Assert.assertEquals(windowPanes.get(4).getKey().getKey(), new Integer(3));
    Assert.assertEquals((windowPanes.get(4).getMessage()).size(), 1);
}
Also used : TestClock(org.apache.samza.testUtils.TestClock) StreamApplicationDescriptorImpl(org.apache.samza.application.descriptors.StreamApplicationDescriptorImpl) TaskModel(org.apache.samza.job.model.TaskModel) GenericInputDescriptor(org.apache.samza.system.descriptors.GenericInputDescriptor) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) AccumulationMode(org.apache.samza.operators.windows.AccumulationMode) Duration(java.time.Duration) Map(java.util.Map) MapConfig(org.apache.samza.config.MapConfig) KV(org.apache.samza.operators.KV) TaskCallback(org.apache.samza.task.TaskCallback) ImmutableSet(com.google.common.collect.ImmutableSet) TaskName(org.apache.samza.container.TaskName) IncomingMessageEnvelope(org.apache.samza.system.IncomingMessageEnvelope) Collection(java.util.Collection) Triggers(org.apache.samza.operators.triggers.Triggers) Context(org.apache.samza.context.Context) List(java.util.List) TestClock(org.apache.samza.testUtils.TestClock) TestInMemoryStore(org.apache.samza.operators.impl.store.TestInMemoryStore) Config(org.apache.samza.config.Config) KVSerde(org.apache.samza.serializers.KVSerde) StreamApplication(org.apache.samza.application.StreamApplication) MetricsRegistryMap(org.apache.samza.metrics.MetricsRegistryMap) Mockito.mock(org.mockito.Mockito.mock) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) GenericSystemDescriptor(org.apache.samza.system.descriptors.GenericSystemDescriptor) HashMap(java.util.HashMap) Serde(org.apache.samza.serializers.Serde) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) ArrayList(java.util.ArrayList) MapFunction(org.apache.samza.operators.functions.MapFunction) WindowPane(org.apache.samza.operators.windows.WindowPane) Trigger(org.apache.samza.operators.triggers.Trigger) ImmutableList(com.google.common.collect.ImmutableList) MessageCollector(org.apache.samza.task.MessageCollector) FiringType(org.apache.samza.operators.triggers.FiringType) SystemStream(org.apache.samza.system.SystemStream) MockContext(org.apache.samza.context.MockContext) IntegerSerde(org.apache.samza.serializers.IntegerSerde) MessageStream(org.apache.samza.operators.MessageStream) Before(org.junit.Before) Windows(org.apache.samza.operators.windows.Windows) Partition(org.apache.samza.Partition) IOException(java.io.IOException) Test(org.junit.Test) Mockito.times(org.mockito.Mockito.times) Mockito.when(org.mockito.Mockito.when) TaskCoordinator(org.apache.samza.task.TaskCoordinator) Mockito.verify(org.mockito.Mockito.verify) OutgoingMessageEnvelope(org.apache.samza.system.OutgoingMessageEnvelope) TaskContextImpl(org.apache.samza.context.TaskContextImpl) Assert(org.junit.Assert) TimeSeriesKeySerde(org.apache.samza.operators.impl.store.TimeSeriesKeySerde) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) MessageCollector(org.apache.samza.task.MessageCollector) ArrayList(java.util.ArrayList) Collection(java.util.Collection) WindowPane(org.apache.samza.operators.windows.WindowPane) Test(org.junit.Test)

Example 24 with OperatorSpecGraph

use of org.apache.samza.operators.OperatorSpecGraph in project samza by apache.

the class TestWindowOperator method testTumblingAggregatingWindowsDiscardingMode.

@Test
public void testTumblingAggregatingWindowsDiscardingMode() throws Exception {
    when(this.context.getTaskContext().getStore("jobName-jobId-window-w1")).thenReturn(new TestInMemoryStore<>(new TimeSeriesKeySerde(new IntegerSerde()), new IntegerSerde()));
    OperatorSpecGraph sgb = this.getAggregateTumblingWindowStreamGraph(AccumulationMode.DISCARDING, Duration.ofSeconds(1), Triggers.repeat(Triggers.count(2))).getOperatorSpecGraph();
    List<WindowPane<Integer, Integer>> windowPanes = new ArrayList<>();
    TestClock testClock = new TestClock();
    StreamOperatorTask task = new StreamOperatorTask(sgb, testClock);
    task.init(this.context);
    MessageCollector messageCollector = envelope -> windowPanes.add((WindowPane<Integer, Integer>) envelope.getMessage());
    integers.forEach(n -> task.processAsync(new IntegerEnvelope(n), messageCollector, taskCoordinator, taskCallback));
    testClock.advanceTime(Duration.ofSeconds(1));
    task.window(messageCollector, taskCoordinator);
    Assert.assertEquals(windowPanes.size(), 5);
    Assert.assertEquals(windowPanes.get(0).getMessage(), new Integer(2));
    Assert.assertEquals(windowPanes.get(1).getMessage(), new Integer(2));
    Assert.assertEquals(windowPanes.get(2).getMessage(), new Integer(2));
    Assert.assertEquals(windowPanes.get(3).getMessage(), new Integer(2));
    Assert.assertEquals(windowPanes.get(4).getMessage(), new Integer(1));
}
Also used : StreamApplicationDescriptorImpl(org.apache.samza.application.descriptors.StreamApplicationDescriptorImpl) TaskModel(org.apache.samza.job.model.TaskModel) GenericInputDescriptor(org.apache.samza.system.descriptors.GenericInputDescriptor) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) AccumulationMode(org.apache.samza.operators.windows.AccumulationMode) Duration(java.time.Duration) Map(java.util.Map) MapConfig(org.apache.samza.config.MapConfig) KV(org.apache.samza.operators.KV) TaskCallback(org.apache.samza.task.TaskCallback) ImmutableSet(com.google.common.collect.ImmutableSet) TaskName(org.apache.samza.container.TaskName) IncomingMessageEnvelope(org.apache.samza.system.IncomingMessageEnvelope) Collection(java.util.Collection) Triggers(org.apache.samza.operators.triggers.Triggers) Context(org.apache.samza.context.Context) List(java.util.List) TestClock(org.apache.samza.testUtils.TestClock) TestInMemoryStore(org.apache.samza.operators.impl.store.TestInMemoryStore) Config(org.apache.samza.config.Config) KVSerde(org.apache.samza.serializers.KVSerde) StreamApplication(org.apache.samza.application.StreamApplication) MetricsRegistryMap(org.apache.samza.metrics.MetricsRegistryMap) Mockito.mock(org.mockito.Mockito.mock) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) GenericSystemDescriptor(org.apache.samza.system.descriptors.GenericSystemDescriptor) HashMap(java.util.HashMap) Serde(org.apache.samza.serializers.Serde) SystemStreamPartition(org.apache.samza.system.SystemStreamPartition) ArrayList(java.util.ArrayList) MapFunction(org.apache.samza.operators.functions.MapFunction) WindowPane(org.apache.samza.operators.windows.WindowPane) Trigger(org.apache.samza.operators.triggers.Trigger) ImmutableList(com.google.common.collect.ImmutableList) MessageCollector(org.apache.samza.task.MessageCollector) FiringType(org.apache.samza.operators.triggers.FiringType) SystemStream(org.apache.samza.system.SystemStream) MockContext(org.apache.samza.context.MockContext) IntegerSerde(org.apache.samza.serializers.IntegerSerde) MessageStream(org.apache.samza.operators.MessageStream) Before(org.junit.Before) Windows(org.apache.samza.operators.windows.Windows) Partition(org.apache.samza.Partition) IOException(java.io.IOException) Test(org.junit.Test) Mockito.times(org.mockito.Mockito.times) Mockito.when(org.mockito.Mockito.when) TaskCoordinator(org.apache.samza.task.TaskCoordinator) Mockito.verify(org.mockito.Mockito.verify) OutgoingMessageEnvelope(org.apache.samza.system.OutgoingMessageEnvelope) TaskContextImpl(org.apache.samza.context.TaskContextImpl) Assert(org.junit.Assert) TimeSeriesKeySerde(org.apache.samza.operators.impl.store.TimeSeriesKeySerde) OperatorSpecGraph(org.apache.samza.operators.OperatorSpecGraph) StreamOperatorTask(org.apache.samza.task.StreamOperatorTask) ArrayList(java.util.ArrayList) WindowPane(org.apache.samza.operators.windows.WindowPane) IntegerSerde(org.apache.samza.serializers.IntegerSerde) TestClock(org.apache.samza.testUtils.TestClock) MessageCollector(org.apache.samza.task.MessageCollector) TimeSeriesKeySerde(org.apache.samza.operators.impl.store.TimeSeriesKeySerde) Test(org.junit.Test)

Aggregations

StreamApplicationDescriptorImpl (org.apache.samza.application.descriptors.StreamApplicationDescriptorImpl)24 OperatorSpecGraph (org.apache.samza.operators.OperatorSpecGraph)24 Test (org.junit.Test)24 Collection (java.util.Collection)22 Config (org.apache.samza.config.Config)22 MapConfig (org.apache.samza.config.MapConfig)22 MessageStream (org.apache.samza.operators.MessageStream)13 KVSerde (org.apache.samza.serializers.KVSerde)13 ImmutableList (com.google.common.collect.ImmutableList)12 ImmutableSet (com.google.common.collect.ImmutableSet)12 IOException (java.io.IOException)12 Duration (java.time.Duration)12 ArrayList (java.util.ArrayList)12 HashMap (java.util.HashMap)12 List (java.util.List)12 Map (java.util.Map)12 Partition (org.apache.samza.Partition)12 StreamApplication (org.apache.samza.application.StreamApplication)12 TaskName (org.apache.samza.container.TaskName)12 Context (org.apache.samza.context.Context)12