Flink入门(一)(Java和scala)

微瞰技术 2019-09-10 06:59:12

1754

分类专栏：大数据文章标签： Flink wordcount scala java pom

最后发布:2019-09-10 06:59:12首次发布:2019-09-10 06:46:53

本文链接：https://blog.csdn.net/u011342403/article/details/100686326

版权

Flink批处理

从文件中读取单词，计算频次

Scala版本

import org.apache.flink.api.scala.ExecutionEnvironment

object BatchWordCountJob {

  def main(args: Array[String]) {
    val env = ExecutionEnvironment.getExecutionEnvironment
    val input ="/Users/mac126/Desktop/hello.txt";

    val  text = env.readTextFile(input)
    import org.apache.flink.api.scala._
    text.flatMap(_.toLowerCase().split("\t")).filter(_.nonEmpty).map((_,1))
      .groupBy(0).sum(1).print()
  }

最后可在控制台看到打印的内容

Java版本

mport org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

/**
 * java开发wordcount
 */
public class BatchWordCountJob {



    public static void main(String[] args) throws Exception{


        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        String file="/Users/mac126/Desktop/hello.txt";

        DataSet<String>  text = env.readTextFile(file);

        text.flatMap(new FlatMapFunction<String, Tuple2<String,Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String,Integer>> collector) throws Exception {
                    String [] tokens = value.toLowerCase().split("\t");
                    for (String token :tokens){
                        if (token.trim().length()>0){
                            collector.collect(new Tuple2<String, Integer>(token,1));
                        }
                    }
            }
        }).groupBy(0).sum(1).print();

    }
}

Flink流处理

flink入门一般使用socket数据作为流式数据来源。在mac上命令行使用nc -lk 9000开启socket发送端，在flink中接收socket消息如下

Scala版本

import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
import org.apache.flink.streaming.api.windowing.time.Time

object StreamWordCountJob {
  def main(args: Array[String]) {
    // set up the streaming execution environment
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    val  text =env.socketTextStream("localhost",9000)
    import org.apache.flink.api.scala._
    text.flatMap(_.split(",")).map((_,1)).keyBy(0).timeWindow(Time.seconds(5)).sum(1).print().setParallelism(1)
    env.execute("StreamWordCountJob")
  }
}

Java版本

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;

public class StreamWordCountJob {
    public static void main(String[] args) throws Exception{

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        DataStreamSource<String> text = env.socketTextStream("localhost",9000);
        text.flatMap(new FlatMapFunction<String, Tuple2<String,Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String [] tokens = value.toLowerCase().split(",");
                for (String token:tokens){
                    if (token.length()>0){
                        collector.collect(new Tuple2<String, Integer>(token,1));
                    }
                }
            }
        }).keyBy(0).sum(1).print().setParallelism(1);
        env.execute("StreamWordCountJob");

    }
}

以上就是Flink入门的第一个小例子。大家可以在自己电脑上试下。

前置pom文件

一般在IDEA上安装Scala插件进行开发

scala版本 pom文件

<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>my.flink.quickstart</groupId>
	<artifactId>quickstart</artifactId>
	<version>0.1</version>
	<packaging>jar</packaging>

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

	<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>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.8.0</flink.version>
		<scala.binary.version>2.11</scala.binary.version>
		<scala.version>2.11.12</scala.version>
	</properties>

	<dependencies>
		<!-- Apache Flink dependencies -->
		<!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-scala_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>provided</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>provided</scope>
		</dependency>

		<!-- Scala Library, provided by Flink as well. -->
		<dependency>
			<groupId>org.scala-lang</groupId>
			<artifactId>scala-library</artifactId>
			<version>${scala.version}</version>
			<scope>provided</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>
			<!-- 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>my.flink.quickstart.StreamingJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>1.8</source>
					<target>1.8</target>
				</configuration>
			</plugin>

			<!-- Scala Compiler -->
			<plugin>
				<groupId>net.alchim31.maven</groupId>
				<artifactId>scala-maven-plugin</artifactId>
				<version>3.2.2</version>
				<executions>
					<execution>
						<goals>
							<goal>compile</goal>
							<goal>testCompile</goal>
						</goals>
					</execution>
				</executions>
			</plugin>

			<!-- Eclipse Scala Integration -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-eclipse-plugin</artifactId>
				<version>2.8</version>
				<configuration>
					<downloadSources>true</downloadSources>
					<projectnatures>
						<projectnature>org.scala-ide.sdt.core.scalanature</projectnature>
						<projectnature>org.eclipse.jdt.core.javanature</projectnature>
					</projectnatures>
					<buildcommands>
						<buildcommand>org.scala-ide.sdt.core.scalabuilder</buildcommand>
					</buildcommands>
					<classpathContainers>
						<classpathContainer>org.scala-ide.sdt.launching.SCALA_CONTAINER</classpathContainer>
						<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
					</classpathContainers>
					<excludes>
						<exclude>org.scala-lang:scala-library</exclude>
						<exclude>org.scala-lang:scala-compiler</exclude>
					</excludes>
					<sourceIncludes>
						<sourceInclude>**/*.scala</sourceInclude>
						<sourceInclude>**/*.java</sourceInclude>
					</sourceIncludes>
				</configuration>
			</plugin>
			<plugin>
				<groupId>org.codehaus.mojo</groupId>
				<artifactId>build-helper-maven-plugin</artifactId>
				<version>1.7</version>
				<executions>
					<!-- Add src/main/scala to eclipse build path -->
					<execution>
						<id>add-source</id>
						<phase>generate-sources</phase>
						<goals>
							<goal>add-source</goal>
						</goals>
						<configuration>
							<sources>
								<source>src/main/scala</source>
							</sources>
						</configuration>
					</execution>
					<!-- Add src/test/scala to eclipse build path -->
					<execution>
						<id>add-test-source</id>
						<phase>generate-test-sources</phase>
						<goals>
							<goal>add-test-source</goal>
						</goals>
						<configuration>
							<sources>
								<source>src/test/scala</source>
							</sources>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>
	</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-scala_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.apache.flink</groupId>
					<artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
					<version>${flink.version}</version>
					<scope>compile</scope>
				</dependency>
				<dependency>
					<groupId>org.scala-lang</groupId>
					<artifactId>scala-library</artifactId>
					<version>${scala.version}</version>
					<scope>compile</scope>
				</dependency>
			</dependencies>
		</profile>
	</profiles>

</project>

Java版本pom文件为

<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>my-flink-project</groupId>
	<artifactId>my-flink-project</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 -->
		<!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
			<scope>provided</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
			<version>${flink.version}</version>
			<scope>provided</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>myflink.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>