flink流处理demo

最新推荐文章于 2024-07-25 11:50:51 发布

代码人的自白

最新推荐文章于 2024-07-25 11:50:51 发布

阅读量3.2k

点赞数

本文链接：https://blog.csdn.net/qq_40990732/article/details/84065526

版权

flink流处理demo

import org.apache.flink.api.common.functions.FoldFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditEvent;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditsSource;

public class KafkaMessageStreaming {

    static private StreamExecutionEnvironment see;

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

        see = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStream<WikipediaEditEvent> edits = see.addSource(new WikipediaEditsSource());
        KeyedStream<WikipediaEditEvent, String> keyedEdits = edits
                .keyBy(new KeySelector<WikipediaEditEvent, String>() {
                    @Override
                    public String getKey(WikipediaEditEvent event) {
                        return event.getUser();
                    }
                });

        DataStream<Tuple2<String, Long>> result = keyedEdits
                .timeWindow(Time.seconds(5))
                .fold(new Tuple2<>("", 0L), new FoldFunction<WikipediaEditEvent, Tuple2<String, Long>>() {
                    @Override
                    public Tuple2<String, Long> fold(Tuple2<String, Long> acc, WikipediaEditEvent event) {
                        System.out.println("+++++++++++++++");
                        System.out.println(event.toString());

                        acc.f0 = event.getUser();
                        acc.f1 += event.getByteDiff();
                        return acc;
                    }
                });

        result.print();
        see.execute();
    }
}

<?xml version="1.0" encoding="UTF-8"?>
<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>wiki-edits</groupId>
	<artifactId>flink</artifactId>
	<version>1.0-SNAPSHOT</version>
	<properties>
		<flink.version>1.4.2</flink.version>
	</properties>
	<dependencies>

		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-clients_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-wikiedits_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>

		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.8_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
		</dependency>

		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-cep_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>

		<dependency>
			<groupId>com.alibaba</groupId>
			<artifactId>fastjson</artifactId>
			<version>1.2.37</version>
		</dependency>

		<!-- https://mvnrepository.com/artifact/org.apache.logging.log4j/log4j-slf4j-impl -->
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-slf4j-impl</artifactId>
			<version>2.11.1</version>
		</dependency>


	</dependencies>

	<build>
		<plugins>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<artifactSet>
								<excludes>
									<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>KafkaMessageStreaming</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<configuration>
					<source>1.7</source>
					<target>1.7</target>
				</configuration>
			</plugin>
		</plugins>
	</build>
</project>