windows 开发mapreduce程序的配置

第一：下载所有hadoop二进制包

第二：将所有的jar 做成user libary 

第三：设置二个环境变量

HADOOP_HOME=D:\hadoop-2.7.6
HADOOP_USER_NAME=hdfs

package com.jsptpd.test1314;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import java.io.IOException;
import java.util.StringTokenizer;

public class WordCount {
	private static String PATH_TO_CORE_SITE_XML = "D:\\workspace_scala1\\test1314\\conf\\core-site.xml";
	private static String PATH_TO_YARN_SITE_XML = "D:\\workspace_scala1\\test1314\\conf\\yarn-site.xml";
	private static String PATH_TO_MAP_SITE_XML = "D:\\workspace_scala1\\test1314\\conf\\mapred-site.xml";
	private static String PATH_TO_HDFS_SITE_XML = "D:\\workspace_scala1\\test1314\\conf\\hdfs-site.xml";

    public static void main(String[] args) throws Exception {
    	//设置hadoop运行用户
    	System.setProperty("HADOOP_USER_NAME", "hdfs");
    	//获取默认配置信息
        Configuration conf = new Configuration();
		//conf.addResource(new Path(PATH_TO_HDFS_SITE_XML));
        //增加hadoop的配置信息
		conf.addResource(new Path(PATH_TO_CORE_SITE_XML));
		//重新加载mapreduce配置包
		conf.set("mapreduce.application.framework.path", "file:///D:/mapreduce.tar.gz");
		//conf.addResource(new Path(PATH_TO_YARN_SITE_XML));
		//conf.addResource(new Path(PATH_TO_MAP_SITE_XML));
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }

        Job job = Job.getInstance(conf);
        job.setJobName("WordCount");

        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);
        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            //System.out.println(value.toString());
        	String cleanLine = value.toString().toLowerCase().replaceAll("[_|$#<>\\^=\\[\\]\\*\\\\,;,.\\-:()?!\"']", " ");
            System.out.println(cleanLine);
        	StringTokenizer itr = new StringTokenizer(cleanLine," ",true);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken().trim());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
       
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
}

 

第四：配置windos二制包：

 

 

 

 

 

 

 

 

 

 

 

 

只需要配置core-sit.xml

  <configuration>
    <property>
    <name>io.map.index.interval</name>
    </property>
    
    
  </configuration>