A tale of two streams workshop

BatchJob.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 org.myorg.quickstart;

import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.DataSource;

/**
 * Skeleton for a Flink Batch Job.
 *
 * <p>For a tutorial how to write a Flink batch application, check the
 * tutorials and examples on the <a href="https://flink.apache.org/docs/stable/">Flink Website</a>.
 *
 * <p>To package your application into a JAR file for execution,
 * change the main class in the POM.xml file to this class (simply search for 'mainClass')
 * and run 'mvn clean package' on the command line.
 */
public class BatchJob {

	public static void main(String[] args) throws Exception {
		// set up the batch execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		/*
		 * Here, you can start creating your execution plan for Flink.
		 *
		 * Start with getting some data from the environment, like
		 * 	env.readTextFile(textPath);
		 *
		 * then, transform the resulting DataSet<String> using operations
		 * like
		 * 	.filter()
		 * 	.flatMap()
		 * 	.join()
		 * 	.coGroup()
		 *
		 * and many more.
		 * Have a look at the programming guide for the Java API:
		 *
		 * https://flink.apache.org/docs/latest/apis/batch/index.html
		 *
		 * and the examples
		 *
		 * https://flink.apache.org/docs/latest/apis/batch/examples.html
		 *
		 */
    DataSource<String> words = env.readTextFile("test.txt");
    words.writeAsText("output");

		// execute program
		env.execute("Flink Batch Java API Skeleton");
	}
}

KinesisStreamingJob.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 org.myorg.quickstart;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kinesis.FlinkKinesisConsumer;
import org.apache.flink.streaming.connectors.kinesis.FlinkKinesisProducer;
import org.apache.flink.streaming.connectors.kinesis.config.ConsumerConfigConstants;
import org.apache.flink.util.Collector;

import java.util.Properties;

/**
 * Skeleton for a Flink Streaming Job.
 *
 * <p>For a tutorial how to write a Flink streaming application, check the
 * tutorials and examples on the <a href="https://flink.apache.org/docs/stable/">Flink Website</a>.
 *
 * <p>To package your application into a JAR file for execution, run
 * 'mvn clean package' on the command line.
 *
 * <p>If you change the name of the main class (with the public static void main(String[] args))
 * method, change the respective entry in the POM.xml file (simply search for 'mainClass').
 */
public class KinesisStreamingJob {

	public static void main(String[] args) throws Exception {
		// set up the streaming execution environment
		final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

		Properties props = new Properties();
		props.setProperty(ConsumerConfigConstants.AWS_REGION, "eu-west-1");
		props.setProperty(ConsumerConfigConstants.STREAM_INITIAL_POSITION, "LATEST");
	
    DataStream<String> stream = env
      .addSource(new FlinkKinesisConsumer<String>("flink_input", new SimpleStringSchema(), props));


    props = new Properties();
		props.setProperty(ConsumerConfigConstants.AWS_REGION, "eu-west-1");
		props.setProperty("AggregationEnabled", "false");

		FlinkKinesisProducer<String> myProducer = new FlinkKinesisProducer<>(new SimpleStringSchema(), props);
		myProducer.setDefaultStream("flink_output");
		myProducer.setDefaultPartition("0");

  
    DataStream<Tuple2<String, Integer>> counts =
				// split up the lines in pairs (2-tuples) containing: (word,1)
				stream.flatMap(new Tokenizer())
						// group by the tuple field "0" and sum up tuple field "1"
						.keyBy(0).sum(1);

		DataStream<String> strCounts = counts.map(stringIntegerTuple2 -> stringIntegerTuple2.toString());
		strCounts.addSink(myProducer);

		// execute program
		env.execute("Flink Streaming Java API Skeleton");
	}
  // *************************************************************************
	// USER FUNCTIONS
	// *************************************************************************

	/**
	 * Implements the string tokenizer that splits sentences into words as a
	 * user-defined FlatMapFunction. The function takes a line (String) and
	 * splits it into multiple pairs in the form of "(word,1)" ({@code Tuple2<String,
	 * Integer>}).
	 */
	public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

		@Override
		public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
			// normalize and split the line
			String[] tokens = value.toLowerCase().split("\\W+");

			// emit the pairs
			for (String token : tokens) {
				if (token.length() > 0) {
					out.collect(new Tuple2<>(token, 1));
				}
			}
		}
	}

}

pom_for_batch_demo.xml

<!--
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.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>org.myorg.quickstart</groupId>
	<artifactId>quickstart</artifactId>
	<version>0.1</version>
	<packaging>jar</packaging>

	<name>Flink Quickstart Job</name>
	<url>http://www.myorganization.org</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.10-SNAPSHOT</flink.version>
		<java.version>1.8</java.version>
		<scala.binary.version>2.11</scala.binary.version>
		<maven.compiler.source>${java.version}</maven.compiler.source>
		<maven.compiler.target>${java.version}</maven.compiler.target>
	</properties>

	<repositories>
		<repository>
			<id>apache.snapshots</id>
			<name>Apache Development Snapshot Repository</name>
			<url>https://repository.apache.org/content/repositories/snapshots/</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>
	</repositories>

	<dependencies>
		<!-- Apache Flink dependencies -->
	
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>

		<!-- Add connector dependencies here. They must be in the default scope (compile). -->

		<!-- Example:

		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.10_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
		</dependency>
		-->


		<!-- Add logging framework, to produce console output when running in the IDE. -->
		<!-- These dependencies are excluded from the application JAR by default. -->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-log4j12</artifactId>
			<version>1.7.7</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>log4j</groupId>
			<artifactId>log4j</artifactId>
			<version>1.2.17</version>
			<scope>runtime</scope>
		</dependency>
	</dependencies>

	<build>
		<plugins>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>${java.version}</source>
					<target>${java.version}</target>
				</configuration>
			</plugin>

			<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
			<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<!-- Run shade goal on package phase -->
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<artifactSet>
								<excludes>
									<exclude>org.apache.flink:force-shading</exclude>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>log4j:*</exclude>
								</excludes>
							</artifactSet>
							<filters>
								<filter>
									<!-- Do not copy the signatures in the META-INF folder.
									Otherwise, this might cause SecurityExceptions when using the JAR. -->
									<artifact>*:*</artifact>
									<excludes>
										<exclude>META-INF/*.SF</exclude>
										<exclude>META-INF/*.DSA</exclude>
										<exclude>META-INF/*.RSA</exclude>
									</excludes>
								</filter>
							</filters>
							<transformers>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									<mainClass>org.myorg.quickstart.StreamingJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

		<pluginManagement>
			<plugins>

				<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
				<plugin>
					<groupId>org.eclipse.m2e</groupId>
					<artifactId>lifecycle-mapping</artifactId>
					<version>1.0.0</version>
					<configuration>
						<lifecycleMappingMetadata>
							<pluginExecutions>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-shade-plugin</artifactId>
										<versionRange>[3.0.0,)</versionRange>
										<goals>
											<goal>shade</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-compiler-plugin</artifactId>
										<versionRange>[3.1,)</versionRange>
										<goals>
											<goal>testCompile</goal>
											<goal>compile</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
							</pluginExecutions>
						</lifecycleMappingMetadata>
					</configuration>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>

	<!-- This profile helps to make things run out of the box in IntelliJ -->
	<!-- Its adds Flink's core classes to the runtime class path. -->
	<!-- Otherwise they are missing in IntelliJ, because the dependency is 'provided' -->
	<profiles>
		<profile>
			<id>add-dependencies-for-IDEA</id>

			<activation>
				<property>
					<name>idea.version</name>
				</property>
			</activation>

			<dependencies>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-java</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
			</dependencies>
		</profile>
	</profiles>

</project>

pom_for_kafka_demo.xml

<!--
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.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>org.myorg.quickstart</groupId>
	<artifactId>quickstart</artifactId>
	<version>0.1</version>
	<packaging>jar</packaging>

	<name>Flink Quickstart Job</name>
	<url>http://www.myorganization.org</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.6.2</flink.version>
		<java.version>1.8</java.version>
		<scala.binary.version>2.11</scala.binary.version>
		<maven.compiler.source>${java.version}</maven.compiler.source>
		<maven.compiler.target>${java.version}</maven.compiler.target>
	</properties>

	<repositories>
		<repository>
			<id>apache.snapshots</id>
			<name>Apache Development Snapshot Repository</name>
			<url>https://repository.apache.org/content/repositories/snapshots/</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>
	</repositories>

	<dependencies>
		<!-- Apache Flink dependencies -->
		
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>

		<!-- Add connector dependencies here. They must be in the default scope (compile). -->

		
    		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.11_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>


		<!-- Add logging framework, to produce console output when running in the IDE. -->
		<!-- These dependencies are excluded from the application JAR by default. -->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-log4j12</artifactId>
			<version>1.7.7</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>log4j</groupId>
			<artifactId>log4j</artifactId>
			<version>1.2.17</version>
			<scope>runtime</scope>
		</dependency>
	</dependencies>

	<build>
		<plugins>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>${java.version}</source>
					<target>${java.version}</target>
				</configuration>
			</plugin>

			<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
			<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<!-- Run shade goal on package phase -->
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<artifactSet>
								<excludes>
									<exclude>org.apache.flink:force-shading</exclude>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>log4j:*</exclude>
								</excludes>
							</artifactSet>
							<filters>
								<filter>
									<!-- Do not copy the signatures in the META-INF folder.
									Otherwise, this might cause SecurityExceptions when using the JAR. -->
									<artifact>*:*</artifact>
									<excludes>
										<exclude>META-INF/*.SF</exclude>
										<exclude>META-INF/*.DSA</exclude>
										<exclude>META-INF/*.RSA</exclude>
									</excludes>
								</filter>
							</filters>
							<transformers>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									<mainClass>org.myorg.quickstart.StreamingJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

		<pluginManagement>
			<plugins>

				<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
				<plugin>
					<groupId>org.eclipse.m2e</groupId>
					<artifactId>lifecycle-mapping</artifactId>
					<version>1.0.0</version>
					<configuration>
						<lifecycleMappingMetadata>
							<pluginExecutions>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-shade-plugin</artifactId>
										<versionRange>[3.0.0,)</versionRange>
										<goals>
											<goal>shade</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-compiler-plugin</artifactId>
										<versionRange>[3.1,)</versionRange>
										<goals>
											<goal>testCompile</goal>
											<goal>compile</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
							</pluginExecutions>
						</lifecycleMappingMetadata>
					</configuration>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>

	<!-- This profile helps to make things run out of the box in IntelliJ -->
	<!-- Its adds Flink's core classes to the runtime class path. -->
	<!-- Otherwise they are missing in IntelliJ, because the dependency is 'provided' -->
	<profiles>
		<profile>
			<id>add-dependencies-for-IDEA</id>

			<activation>
				<property>
					<name>idea.version</name>
				</property>
			</activation>

			<dependencies>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-java</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
			</dependencies>
		</profile>
	</profiles>

</project>

pom_for_kinesis_data_analytics.xml

<!--
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.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>org.myorg.quickstart</groupId>
	<artifactId>quickstart</artifactId>
	<version>0.1</version>
	<packaging>jar</packaging>

	<name>Flink Quickstart Job</name>
	<url>http://www.myorganization.org</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.6.2</flink.version>
		<java.version>1.8</java.version>
		<scala.binary.version>2.11</scala.binary.version>
		<maven.compiler.source>${java.version}</maven.compiler.source>
		<maven.compiler.target>${java.version}</maven.compiler.target>
	</properties>

	<repositories>
		<repository>
			<id>apache.snapshots</id>
			<name>Apache Development Snapshot Repository</name>
			<url>https://repository.apache.org/content/repositories/snapshots/</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>
	</repositories>

	<dependencies>
		<!-- Apache Flink dependencies -->
		
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>

		<!-- Add connector dependencies here. They must be in the default scope (compile). -->
<dependency>
            <groupId>com.amazonaws</groupId>
            <artifactId>aws-kinesisanalytics-runtime</artifactId>
            <version>1.0.1</version>
        </dependency>

<dependency>
		
    <dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.11_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
    
    <dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kinesis_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
		</dependency>


		<!-- Add logging framework, to produce console output when running in the IDE. -->
		<!-- These dependencies are excluded from the application JAR by default. -->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-log4j12</artifactId>
			<version>1.7.7</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>log4j</groupId>
			<artifactId>log4j</artifactId>
			<version>1.2.17</version>
			<scope>runtime</scope>
		</dependency>
	</dependencies>

	<build>
		<plugins>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>${java.version}</source>
					<target>${java.version}</target>
				</configuration>
			</plugin>

			<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
			<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<!-- Run shade goal on package phase -->
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<artifactSet>
								<excludes>
									<exclude>org.apache.flink:force-shading</exclude>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>log4j:*</exclude>
								</excludes>
							</artifactSet>
							<filters>
								<filter>
									<!-- Do not copy the signatures in the META-INF folder.
									Otherwise, this might cause SecurityExceptions when using the JAR. -->
									<artifact>*:*</artifact>
									<excludes>
										<exclude>META-INF/*.SF</exclude>
										<exclude>META-INF/*.DSA</exclude>
										<exclude>META-INF/*.RSA</exclude>
									</excludes>
								</filter>
							</filters>
							<transformers>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									 <mainClass>org.myorg.quickstart.KinesisStreamingJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

		<pluginManagement>
			<plugins>

				<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
				<plugin>
					<groupId>org.eclipse.m2e</groupId>
					<artifactId>lifecycle-mapping</artifactId>
					<version>1.0.0</version>
					<configuration>
						<lifecycleMappingMetadata>
							<pluginExecutions>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-shade-plugin</artifactId>
										<versionRange>[3.0.0,)</versionRange>
										<goals>
											<goal>shade</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-compiler-plugin</artifactId>
										<versionRange>[3.1,)</versionRange>
										<goals>
											<goal>testCompile</goal>
											<goal>compile</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
							</pluginExecutions>
						</lifecycleMappingMetadata>
					</configuration>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>

	<!-- This profile helps to make things run out of the box in IntelliJ -->
	<!-- Its adds Flink's core classes to the runtime class path. -->
	<!-- Otherwise they are missing in IntelliJ, because the dependency is 'provided' -->
	<profiles>
		<profile>
			<id>add-dependencies-for-IDEA</id>

			<activation>
				<property>
					<name>idea.version</name>
				</property>
			</activation>

			<dependencies>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-java</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
			</dependencies>
		</profile>
	</profiles>

</project>

pom_for_kinesis_demo.xml

<!--
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.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>org.myorg.quickstart</groupId>
	<artifactId>quickstart</artifactId>
	<version>0.1</version>
	<packaging>jar</packaging>

	<name>Flink Quickstart Job</name>
	<url>http://www.myorganization.org</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.6.2</flink.version>
		<java.version>1.8</java.version>
		<scala.binary.version>2.11</scala.binary.version>
		<maven.compiler.source>${java.version}</maven.compiler.source>
		<maven.compiler.target>${java.version}</maven.compiler.target>
	</properties>

	<repositories>
		<repository>
			<id>apache.snapshots</id>
			<name>Apache Development Snapshot Repository</name>
			<url>https://repository.apache.org/content/repositories/snapshots/</url>
			<releases>
				<enabled>false</enabled>
			</releases>
			<snapshots>
				<enabled>true</enabled>
			</snapshots>
		</repository>
	</repositories>

	<dependencies>
		<!-- Apache Flink dependencies -->
		
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>

		<!-- Add connector dependencies here. They must be in the default scope (compile). -->

		
    <dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.11_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>compile</scope>
		</dependency>
    
    <dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kinesis_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
		</dependency>


		<!-- Add logging framework, to produce console output when running in the IDE. -->
		<!-- These dependencies are excluded from the application JAR by default. -->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-log4j12</artifactId>
			<version>1.7.7</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>log4j</groupId>
			<artifactId>log4j</artifactId>
			<version>1.2.17</version>
			<scope>runtime</scope>
		</dependency>
	</dependencies>

	<build>
		<plugins>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>${java.version}</source>
					<target>${java.version}</target>
				</configuration>
			</plugin>

			<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
			<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<!-- Run shade goal on package phase -->
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<artifactSet>
								<excludes>
									<exclude>org.apache.flink:force-shading</exclude>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>log4j:*</exclude>
								</excludes>
							</artifactSet>
							<filters>
								<filter>
									<!-- Do not copy the signatures in the META-INF folder.
									Otherwise, this might cause SecurityExceptions when using the JAR. -->
									<artifact>*:*</artifact>
									<excludes>
										<exclude>META-INF/*.SF</exclude>
										<exclude>META-INF/*.DSA</exclude>
										<exclude>META-INF/*.RSA</exclude>
									</excludes>
								</filter>
							</filters>
							<transformers>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									<mainClass>org.myorg.quickstart.StreamingJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

		<pluginManagement>
			<plugins>

				<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
				<plugin>
					<groupId>org.eclipse.m2e</groupId>
					<artifactId>lifecycle-mapping</artifactId>
					<version>1.0.0</version>
					<configuration>
						<lifecycleMappingMetadata>
							<pluginExecutions>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-shade-plugin</artifactId>
										<versionRange>[3.0.0,)</versionRange>
										<goals>
											<goal>shade</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-compiler-plugin</artifactId>
										<versionRange>[3.1,)</versionRange>
										<goals>
											<goal>testCompile</goal>
											<goal>compile</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
							</pluginExecutions>
						</lifecycleMappingMetadata>
					</configuration>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>

	<!-- This profile helps to make things run out of the box in IntelliJ -->
	<!-- Its adds Flink's core classes to the runtime class path. -->
	<!-- Otherwise they are missing in IntelliJ, because the dependency is 'provided' -->
	<profiles>
		<profile>
			<id>add-dependencies-for-IDEA</id>

			<activation>
				<property>
					<name>idea.version</name>
				</property>
			</activation>

			<dependencies>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-java</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
			</dependencies>
		</profile>
	</profiles>

</project>

StreamingJob.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 org.myorg.quickstart;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer011;

import java.util.Properties;

/**
 * Skeleton for a Flink Streaming Job.
 *
 * <p>For a tutorial how to write a Flink streaming application, check the
 * tutorials and examples on the <a href="https://flink.apache.org/docs/stable/">Flink Website</a>.
 *
 * <p>To package your application into a JAR file for execution, run
 * 'mvn clean package' on the command line.
 *
 * <p>If you change the name of the main class (with the public static void main(String[] args))
 * method, change the respective entry in the POM.xml file (simply search for 'mainClass').
 */
public class StreamingJob {

	public static void main(String[] args) throws Exception {
		// set up the streaming execution environment
		final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

		/*
		 * Here, you can start creating your execution plan for Flink.
		 *
		 * Start with getting some data from the environment, like
		 * 	env.readTextFile(textPath);
		 *
		 * then, transform the resulting DataStream<String> using operations
		 * like
		 * 	.filter()
		 * 	.flatMap()
		 * 	.join()
		 * 	.coGroup()
		 *
		 * and many more.
		 * Have a look at the programming guide for the Java API:
		 *
		 * https://flink.apache.org/docs/latest/apis/streaming/index.html
		 *
		 */

    Properties properties = new Properties();
    properties.setProperty("bootstrap.servers", "localhost:9092");
    // only required for Kafka 0.8
    properties.setProperty("zookeeper.connect", "localhost:2181");
    properties.setProperty("group.id", "test");
    DataStream<String> stream = env
      .addSource(new FlinkKafkaConsumer011<>("flink_input", new SimpleStringSchema(), properties));


    FlinkKafkaProducer011<String> myProducer = new FlinkKafkaProducer011<String>(
            "localhost:9092",            // broker list
            "flink_output",                  // target topic
            new SimpleStringSchema());   // serialization schema

    // versions 0.10+ allow attaching the records' event timestamp when writing them to Kafka;
    // this method is not available for earlier Kafka versions
    myProducer.setWriteTimestampToKafka(true);

    stream.addSink(myProducer);

		// execute program
		env.execute("Flink Streaming Java API Skeleton");
	}
}

streamingJobWithCount.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 org.myorg.quickstart;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer011;
import org.apache.flink.util.Collector;

import java.util.Properties;

/**
 * Skeleton for a Flink Streaming Job.
 *
 * <p>For a tutorial how to write a Flink streaming application, check the
 * tutorials and examples on the <a href="https://flink.apache.org/docs/stable/">Flink Website</a>.
 *
 * <p>To package your application into a JAR file for execution, run
 * 'mvn clean package' on the command line.
 *
 * <p>If you change the name of the main class (with the public static void main(String[] args))
 * method, change the respective entry in the POM.xml file (simply search for 'mainClass').
 */
public class StreamingJobWithCount {

	public static void main(String[] args) throws Exception {
		// set up the streaming execution environment
		final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

		/*
		 * Here, you can start creating your execution plan for Flink.
		 *
		 * Start with getting some data from the environment, like
		 * 	env.readTextFile(textPath);
		 *
		 * then, transform the resulting DataStream<String> using operations
		 * like
		 * 	.filter()
		 * 	.flatMap()
		 * 	.join()
		 * 	.coGroup()
		 *
		 * and many more.
		 * Have a look at the programming guide for the Java API:
		 *
		 * https://flink.apache.org/docs/latest/apis/streaming/index.html
		 *
		 */

    Properties properties = new Properties();
    properties.setProperty("bootstrap.servers", "localhost:9092");
    // only required for Kafka 0.8
    properties.setProperty("zookeeper.connect", "localhost:2181");
    properties.setProperty("group.id", "test");
    DataStream<String> stream = env
      .addSource(new FlinkKafkaConsumer011<>("flink_input", new SimpleStringSchema(), properties));


    FlinkKafkaProducer011<String> myProducer = new FlinkKafkaProducer011<String>(
            "localhost:9092",            // broker list
            "flink_output",                  // target topic
            new SimpleStringSchema());   // serialization schema

    // versions 0.10+ allow attaching the records' event timestamp when writing them to Kafka;
    // this method is not available for earlier Kafka versions
    myProducer.setWriteTimestampToKafka(true);
  
    DataStream<Tuple2<String, Integer>> counts =
				// split up the lines in pairs (2-tuples) containing: (word,1)
				stream.flatMap(new Tokenizer())
						// group by the tuple field "0" and sum up tuple field "1"
						.keyBy(0).sum(1);

		DataStream<String> strCounts = counts.map(stringIntegerTuple2 -> stringIntegerTuple2.toString());
		strCounts.addSink(myProducer);

		// execute program
		env.execute("Flink Streaming Java API Skeleton");
	}
  // *************************************************************************
	// USER FUNCTIONS
	// *************************************************************************

	/**
	 * Implements the string tokenizer that splits sentences into words as a
	 * user-defined FlatMapFunction. The function takes a line (String) and
	 * splits it into multiple pairs in the form of "(word,1)" ({@code Tuple2<String,
	 * Integer>}).
	 */
	public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

		@Override
		public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
			// normalize and split the line
			String[] tokens = value.toLowerCase().split("\\W+");

			// emit the pairs
			for (String token : tokens) {
				if (token.length() > 0) {
					out.collect(new Tuple2<>(token, 1));
				}
			}
		}
	}

}