Search in sources :

Example 1 with IRichBolt

use of org.apache.storm.topology.IRichBolt in project storm by apache.

the class WordCountToBolt method main.

public static void main(String[] args) throws Exception {
    StreamBuilder builder = new StreamBuilder();
    // Redis config parameters for the RedisStoreBolt
    JedisPoolConfig poolConfig = new JedisPoolConfig.Builder().setHost("127.0.0.1").setPort(6379).build();
    // Storm tuple to redis key-value mapper
    RedisStoreMapper storeMapper = new WordCountStoreMapper();
    // The redis bolt (sink)
    IRichBolt redisStoreBolt = new RedisStoreBolt(poolConfig, storeMapper);
    // A stream of words
    builder.newStream(new TestWordSpout(), new ValueMapper<String>(0)).mapToPair(w -> Pair.of(w, 1)).countByKey().to(redisStoreBolt);
    Config config = new Config();
    if (args.length > 0) {
        config.setNumWorkers(1);
        StormSubmitter.submitTopologyWithProgressBar(args[0], config, builder.build());
    } else {
        try (LocalCluster cluster = new LocalCluster();
            LocalCluster.LocalTopology topo = cluster.submitTopology("test", config, builder.build())) {
            Utils.sleep(60_000);
        }
    }
}
Also used : IRichBolt(org.apache.storm.topology.IRichBolt) LocalCluster(org.apache.storm.LocalCluster) RedisStoreBolt(org.apache.storm.redis.bolt.RedisStoreBolt) ValueMapper(org.apache.storm.streams.operations.mappers.ValueMapper) Config(org.apache.storm.Config) JedisPoolConfig(org.apache.storm.redis.common.config.JedisPoolConfig) TestWordSpout(org.apache.storm.testing.TestWordSpout) RedisStoreMapper(org.apache.storm.redis.common.mapper.RedisStoreMapper) JedisPoolConfig(org.apache.storm.redis.common.config.JedisPoolConfig) StreamBuilder(org.apache.storm.streams.StreamBuilder)

Example 2 with IRichBolt

use of org.apache.storm.topology.IRichBolt in project storm by apache.

the class StreamBuilder method addSink.

private void addSink(TopologyBuilder topologyBuilder, SinkNode sinkNode) {
    IComponent bolt = sinkNode.getBolt();
    BoltDeclarer boltDeclarer;
    if (bolt instanceof IRichBolt) {
        boltDeclarer = topologyBuilder.setBolt(sinkNode.getComponentId(), (IRichBolt) bolt, sinkNode.getParallelism());
    } else if (bolt instanceof IBasicBolt) {
        boltDeclarer = topologyBuilder.setBolt(sinkNode.getComponentId(), (IBasicBolt) bolt, sinkNode.getParallelism());
    } else {
        throw new IllegalArgumentException("Expect IRichBolt or IBasicBolt in addBolt");
    }
    for (Node parent : parentNodes(sinkNode)) {
        for (String stream : sinkNode.getParentStreams(parent)) {
            declareGrouping(boltDeclarer, parent, stream, nodeGroupingInfo.get(parent, stream));
        }
    }
}
Also used : IRichBolt(org.apache.storm.topology.IRichBolt) BoltDeclarer(org.apache.storm.topology.BoltDeclarer) IComponent(org.apache.storm.topology.IComponent) IBasicBolt(org.apache.storm.topology.IBasicBolt)

Example 3 with IRichBolt

use of org.apache.storm.topology.IRichBolt in project flink by apache.

the class FlinkTopology method translateTopology.

/**
	 * Creates a Flink program that uses the specified spouts and bolts.
	 */
private void translateTopology() {
    unprocessdInputsPerBolt.clear();
    outputStreams.clear();
    declarers.clear();
    availableInputs.clear();
    // Storm defaults to parallelism 1
    env.setParallelism(1);
    for (final Entry<String, IRichSpout> spout : spouts.entrySet()) {
        final String spoutId = spout.getKey();
        final IRichSpout userSpout = spout.getValue();
        final FlinkOutputFieldsDeclarer declarer = new FlinkOutputFieldsDeclarer();
        userSpout.declareOutputFields(declarer);
        final HashMap<String, Fields> sourceStreams = declarer.outputStreams;
        this.outputStreams.put(spoutId, sourceStreams);
        declarers.put(spoutId, declarer);
        final HashMap<String, DataStream<Tuple>> outputStreams = new HashMap<String, DataStream<Tuple>>();
        final DataStreamSource<?> source;
        if (sourceStreams.size() == 1) {
            final SpoutWrapper<Tuple> spoutWrapperSingleOutput = new SpoutWrapper<Tuple>(userSpout, spoutId, null, null);
            spoutWrapperSingleOutput.setStormTopology(stormTopology);
            final String outputStreamId = (String) sourceStreams.keySet().toArray()[0];
            DataStreamSource<Tuple> src = env.addSource(spoutWrapperSingleOutput, spoutId, declarer.getOutputType(outputStreamId));
            outputStreams.put(outputStreamId, src);
            source = src;
        } else {
            final SpoutWrapper<SplitStreamType<Tuple>> spoutWrapperMultipleOutputs = new SpoutWrapper<SplitStreamType<Tuple>>(userSpout, spoutId, null, null);
            spoutWrapperMultipleOutputs.setStormTopology(stormTopology);
            @SuppressWarnings({ "unchecked", "rawtypes" }) DataStreamSource<SplitStreamType<Tuple>> multiSource = env.addSource(spoutWrapperMultipleOutputs, spoutId, (TypeInformation) TypeExtractor.getForClass(SplitStreamType.class));
            SplitStream<SplitStreamType<Tuple>> splitSource = multiSource.split(new StormStreamSelector<Tuple>());
            for (String streamId : sourceStreams.keySet()) {
                SingleOutputStreamOperator<Tuple> outStream = splitSource.select(streamId).map(new SplitStreamMapper<Tuple>());
                outStream.getTransformation().setOutputType(declarer.getOutputType(streamId));
                outputStreams.put(streamId, outStream);
            }
            source = multiSource;
        }
        availableInputs.put(spoutId, outputStreams);
        final ComponentCommon common = stormTopology.get_spouts().get(spoutId).get_common();
        if (common.is_set_parallelism_hint()) {
            int dop = common.get_parallelism_hint();
            source.setParallelism(dop);
        } else {
            common.set_parallelism_hint(1);
        }
    }
    /**
		 * 1. Connect all spout streams with bolts streams
		 * 2. Then proceed with the bolts stream already connected
		 *
		 *  Because we do not know the order in which an iterator steps over a set, we might process a consumer before
		 * its producer
		 * ->thus, we might need to repeat multiple times
		 */
    boolean makeProgress = true;
    while (bolts.size() > 0) {
        if (!makeProgress) {
            StringBuilder strBld = new StringBuilder();
            strBld.append("Unable to build Topology. Could not connect the following bolts:");
            for (String boltId : bolts.keySet()) {
                strBld.append("\n  ");
                strBld.append(boltId);
                strBld.append(": missing input streams [");
                for (Entry<GlobalStreamId, Grouping> streams : unprocessdInputsPerBolt.get(boltId)) {
                    strBld.append("'");
                    strBld.append(streams.getKey().get_streamId());
                    strBld.append("' from '");
                    strBld.append(streams.getKey().get_componentId());
                    strBld.append("'; ");
                }
                strBld.append("]");
            }
            throw new RuntimeException(strBld.toString());
        }
        makeProgress = false;
        final Iterator<Entry<String, IRichBolt>> boltsIterator = bolts.entrySet().iterator();
        while (boltsIterator.hasNext()) {
            final Entry<String, IRichBolt> bolt = boltsIterator.next();
            final String boltId = bolt.getKey();
            final IRichBolt userBolt = copyObject(bolt.getValue());
            final ComponentCommon common = stormTopology.get_bolts().get(boltId).get_common();
            Set<Entry<GlobalStreamId, Grouping>> unprocessedBoltInputs = unprocessdInputsPerBolt.get(boltId);
            if (unprocessedBoltInputs == null) {
                unprocessedBoltInputs = new HashSet<>();
                unprocessedBoltInputs.addAll(common.get_inputs().entrySet());
                unprocessdInputsPerBolt.put(boltId, unprocessedBoltInputs);
            }
            // check if all inputs are available
            final int numberOfInputs = unprocessedBoltInputs.size();
            int inputsAvailable = 0;
            for (Entry<GlobalStreamId, Grouping> entry : unprocessedBoltInputs) {
                final String producerId = entry.getKey().get_componentId();
                final String streamId = entry.getKey().get_streamId();
                final HashMap<String, DataStream<Tuple>> streams = availableInputs.get(producerId);
                if (streams != null && streams.get(streamId) != null) {
                    inputsAvailable++;
                }
            }
            if (inputsAvailable != numberOfInputs) {
                // traverse other bolts first until inputs are available
                continue;
            } else {
                makeProgress = true;
                boltsIterator.remove();
            }
            final Map<GlobalStreamId, DataStream<Tuple>> inputStreams = new HashMap<>(numberOfInputs);
            for (Entry<GlobalStreamId, Grouping> input : unprocessedBoltInputs) {
                final GlobalStreamId streamId = input.getKey();
                final Grouping grouping = input.getValue();
                final String producerId = streamId.get_componentId();
                final Map<String, DataStream<Tuple>> producer = availableInputs.get(producerId);
                inputStreams.put(streamId, processInput(boltId, userBolt, streamId, grouping, producer));
            }
            final SingleOutputStreamOperator<?> outputStream = createOutput(boltId, userBolt, inputStreams);
            if (common.is_set_parallelism_hint()) {
                int dop = common.get_parallelism_hint();
                outputStream.setParallelism(dop);
            } else {
                common.set_parallelism_hint(1);
            }
        }
    }
}
Also used : SpoutWrapper(org.apache.flink.storm.wrappers.SpoutWrapper) HashMap(java.util.HashMap) DataStream(org.apache.flink.streaming.api.datastream.DataStream) Entry(java.util.Map.Entry) ComponentCommon(org.apache.storm.generated.ComponentCommon) IRichBolt(org.apache.storm.topology.IRichBolt) Grouping(org.apache.storm.generated.Grouping) IRichSpout(org.apache.storm.topology.IRichSpout) Fields(org.apache.storm.tuple.Fields) GlobalStreamId(org.apache.storm.generated.GlobalStreamId) StormTuple(org.apache.flink.storm.wrappers.StormTuple) Tuple(org.apache.flink.api.java.tuple.Tuple) SplitStreamType(org.apache.flink.storm.util.SplitStreamType)

Example 4 with IRichBolt

use of org.apache.storm.topology.IRichBolt in project flink by apache.

the class BoltWrapperTest method testOpenSink.

@SuppressWarnings("unchecked")
@Test
public void testOpenSink() throws Exception {
    final StormConfig stormConfig = new StormConfig();
    final Configuration flinkConfig = new Configuration();
    final ExecutionConfig taskConfig = mock(ExecutionConfig.class);
    when(taskConfig.getGlobalJobParameters()).thenReturn(null).thenReturn(stormConfig).thenReturn(flinkConfig);
    final StreamingRuntimeContext taskContext = mock(StreamingRuntimeContext.class);
    when(taskContext.getExecutionConfig()).thenReturn(taskConfig);
    when(taskContext.getTaskName()).thenReturn("name");
    when(taskContext.getMetricGroup()).thenReturn(new UnregisteredMetricsGroup());
    final IRichBolt bolt = mock(IRichBolt.class);
    BoltWrapper<Object, Object> wrapper = new BoltWrapper<Object, Object>(bolt);
    wrapper.setup(createMockStreamTask(), new StreamConfig(new Configuration()), mock(Output.class));
    wrapper.open();
    verify(bolt).prepare(any(Map.class), any(TopologyContext.class), isNotNull(OutputCollector.class));
}
Also used : StormConfig(org.apache.flink.storm.util.StormConfig) IRichBolt(org.apache.storm.topology.IRichBolt) OutputCollector(org.apache.storm.task.OutputCollector) UnregisteredMetricsGroup(org.apache.flink.metrics.groups.UnregisteredMetricsGroup) UnmodifiableConfiguration(org.apache.flink.configuration.UnmodifiableConfiguration) Configuration(org.apache.flink.configuration.Configuration) StreamingRuntimeContext(org.apache.flink.streaming.api.operators.StreamingRuntimeContext) StreamConfig(org.apache.flink.streaming.api.graph.StreamConfig) ExecutionConfig(org.apache.flink.api.common.ExecutionConfig) Output(org.apache.flink.streaming.api.operators.Output) TopologyContext(org.apache.storm.task.TopologyContext) Map(java.util.Map) AbstractTest(org.apache.flink.storm.util.AbstractTest) PrepareForTest(org.powermock.core.classloader.annotations.PrepareForTest) Test(org.junit.Test)

Example 5 with IRichBolt

use of org.apache.storm.topology.IRichBolt in project flink by apache.

the class BoltWrapperTest method testOpen.

@SuppressWarnings("unchecked")
@Test
public void testOpen() throws Exception {
    // utility mocks
    final StormConfig stormConfig = new StormConfig();
    final Configuration flinkConfig = new Configuration();
    final ExecutionConfig taskConfig = mock(ExecutionConfig.class);
    when(taskConfig.getGlobalJobParameters()).thenReturn(null).thenReturn(stormConfig).thenReturn(flinkConfig);
    final StreamingRuntimeContext taskContext = mock(StreamingRuntimeContext.class);
    when(taskContext.getExecutionConfig()).thenReturn(taskConfig);
    when(taskContext.getTaskName()).thenReturn("name");
    when(taskContext.getMetricGroup()).thenReturn(new UnregisteredMetricsGroup());
    final SetupOutputFieldsDeclarer declarer = new SetupOutputFieldsDeclarer();
    declarer.declare(new Fields("dummy"));
    PowerMockito.whenNew(SetupOutputFieldsDeclarer.class).withNoArguments().thenReturn(declarer);
    // (1) open with no configuration
    {
        ExecutionConfig execConfig = mock(ExecutionConfig.class);
        when(execConfig.getGlobalJobParameters()).thenReturn(null);
        final IRichBolt bolt = mock(IRichBolt.class);
        BoltWrapper<Object, Object> wrapper = new BoltWrapper<Object, Object>(bolt);
        wrapper.setup(createMockStreamTask(execConfig), new StreamConfig(new Configuration()), mock(Output.class));
        wrapper.open();
        verify(bolt).prepare(any(Map.class), any(TopologyContext.class), any(OutputCollector.class));
    }
    // (2) open with a storm specific configuration
    {
        ExecutionConfig execConfig = mock(ExecutionConfig.class);
        when(execConfig.getGlobalJobParameters()).thenReturn(stormConfig);
        final IRichBolt bolt = mock(IRichBolt.class);
        BoltWrapper<Object, Object> wrapper = new BoltWrapper<Object, Object>(bolt);
        wrapper.setup(createMockStreamTask(execConfig), new StreamConfig(new Configuration()), mock(Output.class));
        wrapper.open();
        verify(bolt).prepare(same(stormConfig), any(TopologyContext.class), any(OutputCollector.class));
    }
    // (3) open with a flink config
    {
        final Configuration cfg = new Configuration();
        cfg.setString("foo", "bar");
        cfg.setInteger("the end (the int)", Integer.MAX_VALUE);
        ExecutionConfig execConfig = mock(ExecutionConfig.class);
        when(execConfig.getGlobalJobParameters()).thenReturn(new UnmodifiableConfiguration(cfg));
        TestDummyBolt testBolt = new TestDummyBolt();
        BoltWrapper<Object, Object> wrapper = new BoltWrapper<Object, Object>(testBolt);
        wrapper.setup(createMockStreamTask(execConfig), new StreamConfig(new Configuration()), mock(Output.class));
        wrapper.open();
        for (Entry<String, String> entry : cfg.toMap().entrySet()) {
            Assert.assertEquals(entry.getValue(), testBolt.config.get(entry.getKey()));
        }
    }
}
Also used : StormConfig(org.apache.flink.storm.util.StormConfig) IRichBolt(org.apache.storm.topology.IRichBolt) UnregisteredMetricsGroup(org.apache.flink.metrics.groups.UnregisteredMetricsGroup) UnmodifiableConfiguration(org.apache.flink.configuration.UnmodifiableConfiguration) Configuration(org.apache.flink.configuration.Configuration) StreamingRuntimeContext(org.apache.flink.streaming.api.operators.StreamingRuntimeContext) StreamConfig(org.apache.flink.streaming.api.graph.StreamConfig) ExecutionConfig(org.apache.flink.api.common.ExecutionConfig) Entry(java.util.Map.Entry) Fields(org.apache.storm.tuple.Fields) TestDummyBolt(org.apache.flink.storm.util.TestDummyBolt) UnmodifiableConfiguration(org.apache.flink.configuration.UnmodifiableConfiguration) AbstractTest(org.apache.flink.storm.util.AbstractTest) PrepareForTest(org.powermock.core.classloader.annotations.PrepareForTest) Test(org.junit.Test)

Aggregations

IRichBolt (org.apache.storm.topology.IRichBolt)11 Fields (org.apache.storm.tuple.Fields)6 Configuration (org.apache.flink.configuration.Configuration)4 UnmodifiableConfiguration (org.apache.flink.configuration.UnmodifiableConfiguration)4 AbstractTest (org.apache.flink.storm.util.AbstractTest)4 StreamConfig (org.apache.flink.streaming.api.graph.StreamConfig)4 StreamingRuntimeContext (org.apache.flink.streaming.api.operators.StreamingRuntimeContext)4 HashMap (java.util.HashMap)3 ExecutionConfig (org.apache.flink.api.common.ExecutionConfig)3 UnregisteredMetricsGroup (org.apache.flink.metrics.groups.UnregisteredMetricsGroup)3 Output (org.apache.flink.streaming.api.operators.Output)3 ComponentCommon (org.apache.storm.generated.ComponentCommon)3 BoltDeclarer (org.apache.storm.topology.BoltDeclarer)3 TopologyBuilder (org.apache.storm.topology.TopologyBuilder)3 Test (org.junit.Test)3 PrepareForTest (org.powermock.core.classloader.annotations.PrepareForTest)3 Map (java.util.Map)2 Entry (java.util.Map.Entry)2 Tuple (org.apache.flink.api.java.tuple.Tuple)2 StormConfig (org.apache.flink.storm.util.StormConfig)2