Flink学习 Java WrodCount

<?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>help.lixin.flink.example</groupId>
    <artifactId>flink-java-example</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.11.2</flink.version>
        <scala.version>2.11.12</scala.version>
        <scala.binary.version>2.11</scala.binary.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>
        <!-- kafka -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.10_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.7</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
            <scope>runtime</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
            <!-- 打jar包插件(会包含所有依赖) -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>2.6</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <!-- 可以设置jar包的入口类(可选)
                                <mainClass>StreamWordCount</mainClass>
                            -->
                        </manifest>
                    </archive>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

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.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;


public class StreamWordCount {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStream<String> text = env.socketTextStream("127.0.0.1", 9000);
        DataStream<Tuple2<String, Integer>> dataStream = text.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] tokens = s.toLowerCase().split("\\W+");
                for (String token : tokens) {
                    if (token.length() > 0) {
                        collector.collect(new Tuple2<String, Integer>(token, 1));
                    }
                }
            }
        }).keyBy(0).timeWindow(Time.seconds(5)).sum(1);

        dataStream.print();
        // execute program
        env.execute("Java WordCount from SocketTextStream Example");
    }
}

lixin-macbook:flink-wordcount lixin$ nc -lk 9000
hello
world
hello scala
hello java

3> (world,1)
2> (hello,1)
2> (hello,2)
1> (scala,1)
1> (java,1)