external/storm-kafka/src/test/storm/kafka/TridentKafkaTopology.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package storm.kafka;

import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.generated.StormTopology;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Values;
import storm.kafka.trident.TridentKafkaState;
import storm.kafka.trident.TridentKafkaStateFactory;
import storm.kafka.trident.TridentKafkaUpdater;
import storm.kafka.trident.mapper.FieldNameBasedTupleToKafkaMapper;
import storm.kafka.trident.selector.DefaultTopicSelector;
import storm.trident.Stream;
import storm.trident.TridentTopology;
import storm.trident.testing.FixedBatchSpout;

import java.util.HashMap;
import java.util.Map;
import java.util.Properties;


public class TridentKafkaTopology {

    private static StormTopology buildTopology() {
        Fields fields = new Fields("word", "count");
        FixedBatchSpout spout = new FixedBatchSpout(fields, 4,
                new Values("storm", "1"),
                new Values("trident", "1"),
                new Values("needs", "1"),
                new Values("javadoc", "1")
        );
        spout.setCycle(true);

        TridentTopology topology = new TridentTopology();
        Stream stream = topology.newStream("spout1", spout);

        TridentKafkaStateFactory stateFactory = new TridentKafkaStateFactory()
                .withKafkaTopicSelector(new DefaultTopicSelector("test"))
                .withTridentTupleToKafkaMapper(new FieldNameBasedTupleToKafkaMapper("word", "count"));
        stream.partitionPersist(stateFactory, fields, new TridentKafkaUpdater(), new Fields());

        return topology.build();
    }

    /**
     * To run this topology ensure you have a kafka broker running and provide connection string to broker as argument.
     * Create a topic test with command line,
     * kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partition 1 --topic test
     *
     * run this program and run the kafka consumer:
     * kafka-console-consumer.sh --zookeeper localhost:2181 --topic test --from-beginning
     *
     * you should see the messages flowing through.
     *
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        if(args.length < 1) {
            System.out.println("Please provide kafka broker url ,e.g. localhost:9092");
        }

        Config conf = getConfig(args[0]);
        LocalCluster cluster = new LocalCluster();
        cluster.submitTopology("wordCounter", conf, buildTopology());
        Thread.sleep(60 * 1000);
        cluster.killTopology("wordCounter");

        cluster.shutdown();
    }

    private  static Config getConfig(String brokerConnectionString) {
        Config conf = new Config();
        Map config = new HashMap();
        Properties props = new Properties();
        props.put("metadata.broker.list", brokerConnectionString);
        props.put("request.required.acks", "1");
        props.put("serializer.class", "kafka.serializer.StringEncoder");
        conf.put(TridentKafkaState.KAFKA_BROKER_PROPERTIES, props);
        return conf;
    }

}