Flink2.1.1-WordCount示例

安装

Flink2.1.1 docker安装

Java代码示例

pom.xml

<?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.example.flink</groupId>
    <artifactId>flink-wordcount</artifactId>
    <version>1.0.0</version>
    <name>flink-wordcount</name>
    <packaging>jar</packaging>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.source>11</maven.compiler.source>
        <maven.compiler.target>11</maven.compiler.target>
        <flink.version>2.1.1</flink.version>
        <scala.binary.version>2.12</scala.binary.version>
        <log4j.version>2.24.3</log4j.version>
        <commons-math3.version>3.6.1</commons-math3.version>
        <lombok.version>1.18.26</lombok.version>
    </properties>

    <dependencies>
        <!-- Flink Streaming 核心依赖 -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <!-- Flink 客户端依赖，用于本地执行 -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-math3</artifactId>
            <version>${commons-math3.version}</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- Java 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>${maven.compiler.source}</source>
                    <target>${maven.compiler.target}</target>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.4.1</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>com.example.flink.WordCount</mainClass>
                                </transformer>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

代码

package com.example.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
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.util.Collector;

/**
 * Flink WordCount 运行示例
 */
public class WordCount {

    public static void main(String[] args) throws Exception {
        // 1. 创建本地执行环境
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 2. 创建一个静态的数据源
        DataStream<String> text = env.fromElements(
                "To be, or not to be, that is the question:",
                "Whether 'tis nobler in the mind to suffer",
                "The slings and arrows of outrageous fortune,",
                "Or to take arms against a sea of troubles",
                "And by opposing end them."
        );

        // 3. 执行转换和计算
        DataStream<Tuple2<String, Integer>> counts =
                // 将每行文本分割成单词
                text.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
                            @Override
                            public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
                                String[] words = value.toLowerCase().split("\\s+");
                                for (String word : words) {
                                    // 过滤掉空字符串和标点符号
                                    if (word.length() > 0) {
                                        out.collect(new Tuple2<>(word.replaceAll("[^a-z]", ""), 1));
                                    }
                                }
                            }
                        })
                        // 按单词进行分组
                        .keyBy(value -> value.f0)
                        // 对每个单词的计数进行求和
                        .sum(1);

        // 4. 输出结果到控制台
        counts.print();

        // 5. 执行作业
        env.execute("Socket WordCount");
    }
}

运行示例

上传WordCount的jar包到flink

WordCount任务

WordCount任务日志