Flink的WordCount (Java版本)

一二三的小仓库

已于 2022-04-09 16:08:35 修改

阅读量2.6k

点赞数 1

分类专栏：大数据Flink 文章标签： java flink

于 2022-04-09 16:07:02 首次发布

本文链接：https://blog.csdn.net/iiiitttttt/article/details/124062531

版权

大数据Flink 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

`Flink使用流程步骤`:

创建Flink 流式处理的核心环境类对象.
通过核心类对象, 添加数据源组件.
在数据源组件中, 设置转换数据操作, 即: 实时计算操作.
在转换后, 添加输出组件, 对统计结果进行输出.
启动执行Flink

注意：在进行执行之前要先在服务器 nc -lk 7777

package com.dcit.wc;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

/**
 * 	Flink使用流程步骤:
 * 		1. 创建Flink 流式处理的核心环境类对象.
 * 		2. 通过核心类对象, 添加 数据源组件.
 * 		3. 在数据源组件中, 设置转换数据操作, 即: 实时计算操作.
 * 		4. 在转换后, 添加输出组件, 对统计结果进行输出.
 * 		5. 启动执行Flink
 */
public class StreamWordCount {
    public static void main(String[] args) throws Exception {
        // 1. 创建Flink 流式处理的核心环境类对象.
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 2. 通过核心类对象, 添加 数据源组件.
        DataStreamSource<String> ds = env.socketTextStream("hadoop102", 7777);

        //3. 在数据源组件中, 设置转换数据操作, 即: 实时计算操作.
        SingleOutputStreamOperator<Tuple2<String, Long>> final_data = ds.flatMap(
                (String line, Collector<Tuple2<String, Long>> out) -> {
                    String[] words = line.split(" ");
                    for (String word : words) {
                        out.collect(Tuple2.of(word, 1L));
                    }
                }
        ).returns(Types.TUPLE(Types.STRING, Types.LONG)).keyBy(data -> data.f0).sum(1);

        //4. 在转换后, 添加输出组件, 对统计结果进行输出.
        final_data.print();
        //5. 启动执行Flink
        env.execute();
    }
    }

附pom.xml文件

<?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>com.dcit</groupId>
    <artifactId>flink0224tutorial</artifactId>
    <version>1.0-SNAPSHOT</version>



    <repositories><!--代码库-->
        <repository>
            <id>aliyun</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <releases><enabled>true</enabled></releases>
            <snapshots>
                <enabled>false</enabled>
                <updatePolicy>never</updatePolicy>
            </snapshots>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime-web_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <!-- flink操作hdfs，所需要导入该包-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-shaded-hadoop-2-uber</artifactId>
            <version>2.7.5-10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-jdbc_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.bahir</groupId>
            <artifactId>flink-connector-redis_2.11</artifactId>
            <version>1.0</version>
        </dependency>
        <!--Hbase 客户端-->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.1.0</version>
        </dependency>
        <!--kafka 客户端-->
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>2.4.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.4</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.62</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.38</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <descriptorRefs>
                        34
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>