hadoop开发MapReduce程序

<?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>xiaol</groupId>
        <artifactId>xiaol-hadoop</artifactId>
        <version>1.0-SNAPSHOT</version>
        <description>MapReduce</description>

        <properties>
            <project.build.sourceencoding>UTF-8</project.build.sourceencoding>
            <hadoop.version>2.7.3</hadoop.version>
        </properties>
        <dependencies>
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.12</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-client</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-hdfs</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
        </dependencies>
    </project>

package xiaol;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * 整个工作过程：input->split->map->shuffle->reduce->output
 * input:  每一行都是空格分割的单词
 *         hello java
 *         hello python
 * split:   默认按行读取input,每一行作为一个KV对,交给下一步
 *          K就是行首地址,V就是行内容
 *          K:1   V:hello java
 *          K:11  V:hello python
 *          当然这一步可以用户自己重写
 * map:     必须由用户实现的步骤，进行业务逻辑处理
 *          从split的结果中读取数据，统计单词，产生KEYOUT VALUEOUT交给shuffle
 *          这里交给shuffle的K是单词,V是单词出现的次数
 *          hello 1
 *          java 1
 * shuffle  map的结果是KV对的形式，会把相同的K移动到同一个Node上去进行reduce
 *          当传给reduce的时候会相同K的V组装成Iterable<VALUEOUT>类型
 *          hello 1,1
 *          当然这一步可以用户自己重写
 * reduce   必须由用户实现的步骤，进行业务逻辑处理，将shuffle过来的结果进行汇总
 *          从shuffle的结果中读取数据，统计单词，产生KEYOUT VALUEOUT交给output
 *          hello 2
 */
/**
 * org.apache.hadoop.mapreduce.Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
 *     KEYIN    split完成后交给map的key的类型
 *     VALUEIN  split完成后交给map的value的类型
 *     KEYOUT   map完成后交给shuffle的key的类型
 *     VALUEOUT map完成后交给shuffle的key的类型
 * org.apache.hadoop.io.LongWritable    hadoop自己的Long包装类
 * org.apache.hadoop.io.Text            hadoop自己的Text
 * org.apache.hadoop.io.IntWritable     hadoop自己的Int包装类
 */
public class WordMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    /**
     * 重写map方法
     * protected void map(KEYIN key, VALUEIN value, Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context) throws IOException, InterruptedException
     *      KEYIN       split完成后交给map的key的类型，就是那一行的起始地址
     *      VALUEIN     split完成后交给map的value的类型，就是那一行的内容
     *      Context     整个MapReduce的执行环境
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String s = value.toString();
        String[] words = s.split(" ");  //由于每一行都是空格分割的单词，比如hello java这种的，要统计个数，就先拆分
        for(String word: words){
            /**
             * 在执行环境中写入KEYOUT和VALUEOUT作为下一步(shuffle)的输入
             *
             * 这一步是要统计在当前处理这一行里每个单词出现的次数，这里直接给了个1
             * 这里可能有的人会有疑问：如果在某一行里出现了两个相同的单词会怎么样？
             * 这个是不影响的，比如出现了两个hello，结果就是给shuffle的时候会有两个hello 1
             * 然后shuffle的时候会把这两个hello 1交给reduce去处理
             */
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

package xiaol;

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * org.apache.hadoop.mapreduce.Reducer<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
 */
public class WordReducer extends Reducer<Text, IntWritable, Text, LongWritable> {

    /**
     * 重写reduce方法
     * protected void reduce(KEYIN key, Iterable<VALUEIN> values, Reducer<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context) throws IOException, InterruptedException
     *      KEYIN                   shuffle完成后交给reduce的key的类型，其实就是map的KEYOUT
     *      Iterable<VALUEIN>       shuffle完成后交给reduce的value的类型的数组（shuffle那一步会把相同的K分发到同一个node上去进行reduce，所以这里是V数组），其实就是map的VALUEOUT数组
     *      Context                 整个MapReduce的执行环境
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
        long count = 0;
        for(IntWritable v : values) {
            count += v.get();
        }
        context.write(key, new LongWritable(count));
    }

}

package xiaol;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.util.Properties;

/**
 *
 */
public class Test {
    public static void main(String[] args) throws Exception {
        //本地运行直接new一个Configuration，远程运行需要配集群相关的配置
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

        //设定mapper和reducer的class
        job.setMapperClass(WordMapper.class);
        job.setReducerClass(WordReducer.class);

        //设定mapper和outputKey和outputValue的class
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设定reducer和outputKey和outputValue的class
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.setInputPaths(job, "d:/test/test.txt");
        FileOutputFormat.setOutputPath(job, new Path("d:/test/out/"));

        //等待结束，true代表打印中间日志
        job.waitForCompletion(true);
    }
}