Flink wordcount

1.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.wending.demo</groupId>
    <artifactId>flink-demo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.version>1.7.0</project.version>
    </properties>

    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-java -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.7.1</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.3</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <version>3.1.1</version>
                <configuration>
                    <archive>                      
                        <manifest>                           
                            <mainClass>com.wending.demo.WordCount</mainClass>                                                   
                        </manifest>                   
                    </archive>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

2.wordcountdata

package com.wending.demo;

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"
    };

    public static DataSet<String> getDefaultTextLineDataSet(ExecutionEnvironment env) {
        return env.fromElements(WORDS);
    }
}

3.wordcount

package com.wending.demo;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.util.Collector;


public class WordCount {

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

        final ParameterTool params = ParameterTool.fromArgs(args);

        // set up the execution environment
        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // make parameters available in the web interface
        env.getConfig().setGlobalJobParameters(params);

        // get input data
        DataSet<String> text;
        if (params.has("input")) {
            // read the text file from given input path
            text = env.readTextFile(params.get("input"));
        } else {
            // get default test text data
            System.out.println("Executing WordCount example with default input data set.");
            System.out.println("Use --input to specify file input.");
            text = WordCountData.getDefaultTextLineDataSet(env);
        }

        DataSet<Tuple2<String, Integer>> counts =
                // split up the lines in pairs (2-tuples) containing: (word,1)
                text.flatMap(new Tokenizer())
                        // group by the tuple field "0" and sum up tuple field "1"
                        .groupBy(0)
                        .sum(1);

        // emit resultøøø
        if (params.has("output")) {
            counts.writeAsCsv(params.get("output"), "\n", " ");
            // execute program
            env.execute("WordCount Example");
        } else {
            System.out.println("Printing result to stdout. Use --output to specify output path.");
            counts.print();
        }
    }

    /**
     * Implements the string tokenizer that splits sentences into words as a user-defined
     * FlatMapFunction. The function takes a line (String) and splits it into
     * multiple pairs in the form of "(word,1)" ({@code Tuple2<String, Integer>}).
     */
    public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
            // normalize and split the line
            String[] tokens = value.toLowerCase().split("\\W+");

            // emit the pairs
            for (String token : tokens) {
                if (token.length() > 0) {
                    out.collect(new Tuple2<>(token, 1));
                }
            }
        }
    }
}

4.运行把jar放在机器上运行bin/flink run ./demo/flink-demo-1.0-SNAPSHOT.jar，也可以直接在界面上传jar包