Flink版本的WordCount

环境准备：监听8888端口号的nc

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>org.example</groupId>
    <artifactId>flink-in-action</artifactId>
    <version>1.0-SNAPSHOT</version>
    <packaging>jar</packaging>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.11.1</flink.version>
        <java.version>1.8</java.version>
        <scala.binary.version>2.12</scala.binary.version>
        <maven.compiler.source>${java.version}</maven.compiler.source>
        <maven.compiler.target>${java.version}</maven.compiler.target>
        <log4j.version>2.12.1</log4j.version>
    </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>${flink.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>

        <!-- web ui的依赖 -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>


        <!-- Add connector dependencies here. They must be in the default scope (compile). -->

        <!-- Example:

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
            <version>${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.apache.logging.log4j</groupId>
            <artifactId>log4j-slf4j-impl</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-api</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>${log4j.version}</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>3.1.1</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>org.apache.logging.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>cn._51doit.flink.StreamingJob</mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>

        <pluginManagement>
            <plugins>

            </plugins>
        </pluginManagement>
    </build>

</project>

java版

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.LocalStreamEnvironment;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

import java.util.Arrays;

public class LambdaStreamWordCount {

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


        LocalStreamEnvironment env = StreamExecutionEnvironment.createLocalEnvironment(8);

        DataStreamSource<String> lines = env.socketTextStream("localhost", 8888);

        //使用Java8的Lambda表达式
        //SingleOutputStreamOperator<Object> words = lines.flatMap((line, out) -> Arrays.asList(line.split(" ")).forEach(w -> out.collect(w)));

        //使用Lambda表达式，如果遇到有Collector，调用完Transformation后一定再调用returns方法指定返回的数据类型
        //SingleOutputStreamOperator<String> words = lines.flatMap((String line, Collector<String> out) -> Arrays.asList(line.split(" ")).forEach(out::collect)).returns(Types.STRING);

        //SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = lines.flatMap((String line, Collector<Tuple2<String, Integer>> out) -> Arrays.stream(line.split(" ")).forEach(w -> out.collect(Tuple2.of(w, 1)))).returns(Types.TUPLE(Types.STRING, Types.INT));

        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = lines.flatMap((String line, Collector<Tuple2<String, Integer>> out) -> {
            Arrays.stream(line.split(" ")).forEach(w -> {
                out.collect(Tuple2.of(w, 1));
            });
        }).returns(Types.TUPLE(Types.STRING, Types.INT));

        SingleOutputStreamOperator<Tuple2<String, Integer>> result = wordAndOne.keyBy(t -> t.f0).sum(1);

        result.print();

        env.execute("LambdaStreamWordCount");
    }
}

Scala版

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
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.util.Collector;

public class StreamWordCount {

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

        //创建ENV
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        //调用Source创建DataStream
        DataStream<String> lines = env.socketTextStream(args[0], Integer.parseInt(args[1]));

        /**
        //调用Transformation 开始
        SingleOutputStreamOperator<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String line, Collector<String> out) throws Exception {
                String[] words = line.split(" ");
                for (String word : words) {
                    //输出
                    out.collect(word);
                }
            }
        });

        //将单词和一组合
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String word) throws Exception {
                return Tuple2.of(word, 1);
            }
        });
        */

        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = lines.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String line, Collector<Tuple2<String, Integer>> out) throws Exception {
                String[] words = line.split(" ");
                for (String word : words) {
                    //Tuple2.of(word, 1);
                    //输出数据
                    out.collect(Tuple2.of(word, 1));
                }
            }
        });

        //分组
        KeyedStream<Tuple2<String, Integer>, String> keyed = wordAndOne.keyBy(t -> t.f0);

        //聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> summed = keyed.sum(1);
        //Transformation结束

        //调用sink
        summed.print();

        //启动
        env.execute("StreamWordCount");

    }
}