林子雨编著《大数据基础编程、实验和案例教程(第2版)》教材第10章的代码

大数据学习路线图

林子雨编著《大数据基础编程、实验和案例教程(第2版)》(教材官网)教材中的命令行和代码,在纸质教材中的印刷效果不是很好,可能会影响读者对命令行和代码的理解,为了方便读者正确理解命令行和代码或者直接拷贝命令行和代码用于上机实验,这里提供全书配套的所有命令行和代码。
查看教材所有章节的代码

第10章 Flink的安装和基础编程

教材第165页

(温馨提示:代码框上方的复制代码按钮,也就是“两张A4纸图标”,用鼠标点击复制代码按钮,就可以把代码框中的代码复制到粘贴板,粘贴到其他地方。但是,有的浏览器可能不支持该功能)

cd ~/Downloads
sudo tar -zxvf flink-1.9.1-bin-scala_2.11.tgz -C /usr/local
cd /usr/local
sudo mv ./ flink-1.9.1 ./flink
sudo chown -R hadoop:hadoop ./flink
vim ~/.bashrc

教材第166页

export FLNK_HOME=/usr/local/flink
export PATH=$FLINK_HOME/bin:$PATH
source ~/.bashrc
cd /usr/local/flink
./bin/start-cluster.sh
jps

教材第167页

cd /usr/local/flink/bin
./flink run /usr/local/flink/examples/batch/WordCount.jar
https://downloads.apache.org/maven/maven-3/3.6.3/binaries/apache-maven-3.6.3-bin.zip
sudo unzip ~/Downloads/apache-maven-3.6.3-bin.zip -d /usr/local
cd /usr/local
sudo mv apache-maven-3.6.3/ ./maven
sudo chown -R hadoop ./maven

教材第168页

cd ~ #进入用户主文件夹
mkdir -p ./flinkapp/src/main/java
package cn.edu.xmu;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;

public class WordCountData {
    public static final String[] WORDS=new String[]{"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?--To die,--to sleep,--", "No more; and by a sleep to say we end", "The heartache, and the thousand natural shocks", "That flesh is heir to,--\'tis a consummation", "Devoutly to be wish\'d. To die,--to sleep;--", "To sleep! perchance to dream:--ay, there\'s the rub;", "For in that sleep of death what dreams may come,", "When we have shuffled off this mortal coil,", "Must give us pause: there\'s the respect", "That makes calamity of so long life;", "For who would bear the whips and scorns of time,", "The oppressor\'s wrong, the proud man\'s contumely,", "The pangs of despis\'d love, the law\'s delay,", "The insolence of office, and the spurns", "That patient merit of the unworthy takes,", "When he himself might his quietus make", "With a bare bodkin? who would these fardels bear,", "To grunt and sweat under a weary life,", "But that the dread of something after death,--", "The undiscover\'d country, from whose bourn", "No traveller returns,--puzzles the will,", "And makes us rather bear those ills we have", "Than fly to others that we know not of?", "Thus conscience does make cowards of us all;", "And thus the native hue of resolution", "Is sicklied o\'er with the pale cast of thought;", "And enterprises of great pith and moment,", "With this regard, their currents turn awry,", "And lose the name of action.--Soft you now!", "The fair Ophelia!--Nymph, in thy orisons", "Be all my sins remember\'d."};
    public WordCountData() {
    }
    public static DataSet<String> getDefaultTextLineDataset(ExecutionEnvironment env){
        return env.fromElements(WORDS);
    }
}

教材第169页

package cn.edu.xmu;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;


public class WordCountTokenizer implements FlatMapFunction<String, Tuple2<String,Integer>>{

    public WordCountTokenizer(){}


    public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
        String[] tokens = value.toLowerCase().split("\\W+");
        int len = tokens.length;

        for(int i = 0; i<len;i++){
            String tmp = tokens[i];
            if(tmp.length()>0){
                out.collect(new Tuple2<String, Integer>(tmp,Integer.valueOf(1)));
            }
        }
    }
}
package cn.edu.xmu;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.utils.ParameterTool;


public class WordCount {

    public WordCount(){}

    public static void main(String[] args) throws Exception {
        ParameterTool params = ParameterTool.fromArgs(args);
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.getConfig().setGlobalJobParameters(params);
        Object text;
        //如果没有指定输入路径,则默认使用WordCountData中提供的数据
        if(params.has("input")){
            text = env.readTextFile(params.get("input"));
        }else{
            System.out.println("Executing WordCount example with default input data set.");
            System.out.println("Use -- input to specify file input.");
            text = WordCountData.getDefaultTextLineDataset(env);
        }

        AggregateOperator counts = ((DataSet)text).flatMap(new WordCountTokenizer()).groupBy(new int[]{0}).sum(1);
        //如果没有指定输出,则默认打印到控制台
        if(params.has("output")){
            counts.writeAsCsv(params.get("output"),"\n", " ");
            env.execute();
        }else{
            System.out.println("Printing result to stdout. Use --output to specify output path.");
            counts.print();
        }

    }
}

教材第170页

<project>
    <groupId>cn.edu.xmu</groupId>
    <artifactId>simple-project</artifactId>
    <modelVersion>4.0.0</modelVersion>
    <name>Simple Project</name>
    <packaging>jar</packaging>
    <version>1.0</version>
    <repositories>
        <repository>
            <id>jboss</id>
            <name>JBoss Repository</name>
            <url>http://repository.jboss.com/maven2/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.9.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
<version>1.9.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.11</artifactId>
            <version>1.9.1</version>
        </dependency>
    </dependencies>
</project>

教材第171页

cd ~/flinkapp
find .
cd ~/flinkapp    #一定把这个目录设置为当前目录
/usr/local/maven/bin/mvn package

教材第172页

/usr/local/flink/bin/flink run --class cn.edu.xmu.WordCount ~/flinkapp/target/simple-project-1.0.jar