01.Mapreduce实例——去重——代码

教程是eclipse的但是我的eclipse一直导包导不进去，配置了好久，最后用的maven才把包导了进去，但是一直出问题。前面是问题解决的办法

这个是我的工程目录：

 

 pom.xml:可能是包导的多了，但是代码没有问题

 

<?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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.6.0</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.ya</groupId>
    <artifactId>mapreduce</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>mapreduce</name>
    <description>Demo project for Spring Boot</description>
    <properties>
        <java.version>11</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>3.1.3</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
            </plugin>
        </plugins>
    </build>

</project>

Filter.java

package com.ya.mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class Filter {
    static {
        try {
            System.load("D:\\install\\winutils-master\\winutils-master\\hadoop-3.0.0\\bin\\hadoop.dll");//建议采用绝对地址，bin目录下的hadoop.dll文件路径
        } catch (UnsatisfiedLinkError e) {
            System.err.println("Native code library failed to load.\n"+ e);
            System.exit(1);
        }
    }
    public static class Map extends Mapper<Object, Text, Text, NullWritable> {
        private static Text newKey = new Text();
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            System.out.println(line);
            String arr[] = line.split("\t");
            newKey.set(arr[1]);
            context.write(newKey, NullWritable.get());
            System.out.println(newKey);
        }
    }

    public static class Reduce extends Reducer<Text, NullWritable, Text, NullWritable> {
        public void reduce(Text key, Iterable<NullWritable> values, Context context)
                throws IOException, InterruptedException {
            context.write(key, NullWritable.get());
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        BasicConfigurator.configure();
        Configuration conf = new Configuration();
        System.out.println("start");
        Job job = new Job(conf, "filter");
        job.setJarByClass(Filter.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        Path in = new Path("hdfs://node01:8020/kkb/data/mapreduce2/in/buyer_favorite1.txt");
        System.out.println("kashi");
        Path out = new Path("hdfs://node01:8020/kkb/data/mapreduce2/out01");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

结果：

 

 

 

最后文档：