Flink读取Kafka Source中数据做WordCount

添加相应的依赖这里我所使用的是Flink1.12.0的版本:

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-kafka_2.11</artifactId>
    <version>1.12.0</version>
</dependency>

pom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.mo</groupId>
    <artifactId>Flink1.12</artifactId>
    <version>1.0-SNAPSHOT</version>


    <properties>
        <flink.version>1.12.0</flink.version>
        <java.version>1.8</java.version>
        <scala.binary.version>2.11</scala.binary.version>
        <slf4j.version>1.7.30</slf4j.version>
    </properties>

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

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.16</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_2.11</artifactId>
            <version>1.12.0</version>
        </dependency>


    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.3.0</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>7</source>
                    <target>7</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

kafka首先创建wc_test主题,bin/kafka-topics.sh --zookeeper hadoop102:2181 --create --replication-factor 3 --partitions 1 --topic wc_test

参考代码:

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.serialization.DeserializationSchema;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.util.Collector;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import java.util.Properties;

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

        //1.获取执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        //2.Kafka相关配置信息
        Properties pro = new Properties();
        pro.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "hadoop102:9092,hadoop103:9092,hadoop104:9092");
        pro.put(ConsumerConfig.GROUP_ID_CONFIG, "wc_test");

        DeserializationSchema<String> deserializationSchema = new SimpleStringSchema();

        DataStreamSource<String> kafkaSource = env.addSource(new FlinkKafkaConsumer<String>("wc_test", deserializationSchema, pro));

        //3. FlatMap操作转换成元祖
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordone = kafkaSource.flatMap(new wordToWordOne());

        //4.对单词进行分组
        KeyedStream<Tuple2<String, Integer>, String> keyedStream = wordone.keyBy(new MyKeyBy());

        //5.进行聚合操作,按照元祖的第一位key进行聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> res = keyedStream.sum(1);

        res.print();

        env.execute("kafka_wc_test");
    }

    //将单词转为(word,one)的形式
    public static class wordToWordOne implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            String[] words = value.split(",");
            for (String word : words) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }

    //对单词进行KeyBy操作
    public static class MyKeyBy implements KeySelector<Tuple2<String, Integer>, String> {
        @Override
        public String getKey(Tuple2<String, Integer> value) throws Exception {
            return value.f0;
        }
    }

}

kafka开启生产者:bin/kafka-console-producer.sh --broker-list hadoop102:9092 --topic wc_test

运行结果: