1、启动cygwin服务
ssh localhost
//进入hadoop安装目录,注意文件分布系统在与windows有区别。
cd /cygdrive/d/hadoop/run/bin
2、启动hadoop
./start-all.sh
详细方法:http://lusterfly.iteye.com/blog/1813967
3、MyEclipse配置hadoop
【Window】->【Open Perspective】->【Other...】->【Map/Reduce】->【OK】
【Window】->【Show View】->【Other...】->【MapReduce Tools】->【Map/Reduce Locations】->【OK】
注意:Location name随便填,Map/Reduce Master中的host与port在conf文件夹下mapred-site.xml里面mapred.job.tracker里面的ip和port 。
DFS Master是core-site.xml里面fs.default.name里面的ip和port
4、wordCount程序
源码:
package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.StringTokenizer;
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;
public class WordCount {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
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);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.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);
}
}
(1) hadoop的安装目录下新建input文件夹(与bin文件夹在同一级目录),文件夹里新建两个文件。
(2)将文件夹上传到hdfs : bin/hadoop fs -put input in
(3) 配置运行参数:Run As-->Run Configurations ,Arguments中
读入程序的文件夹:hdfs://localhost:9000/user/shirely-pc/cyg_server/in/*
输出结果的文件夹:hdfs://localhost:9000/user/shirely-pc/cyg_server/out/*
虚拟机配置: -xmx1024m 解决java heap out
详细解决方法:http://my.oschina.net/u/570654/blog/112780