下载的是apache稳定版hadoop-0.23.9,0.23之后apache版本往两个分支走:hadoop 1.0和hadoop 2.0。由于这个版本较新却和0.20接近，配置上相似一些，有了之前尝试的教训，就是这个了。解压之后要设定好path，path加上hadoop bin目录。默认配置文件在hadoop etc/hadoop下。

公共配置:core-site.xml

hdfs配置:hdfs-site.xml

mapreduce配置: mapred-site.xml

有三种模式,standalone模式，伪分布式,和分布式。什么都不改启动的是本机模式。这里就是跑在本机模式。

WordCount2.java:

package com.imd.examples;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;

public class WordCount2 {
public static void main(String[] args) throws Exception {
// 不配置一个入口类会导致底层无法调用setJarByClass方法,运行时ClassNotFound.
JobConf conf = new JobConf(WordCount2.class);
conf.setMapperClass(WordCountMapper.class);
conf.setReducerClass(WordCountReducer.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);

// 输入参数除最后一个外都是input path,最后一个是output path
for (int i = 0; i < args.length - 1; ++i) {
FileInputFormat.addInputPath(conf, new Path(args[i]));
}

FileOutputFormat.setOutputPath(conf, new Path(args[args.length - 1]));
JobClient.runJob(conf);
}
}

WordCountMapper.java:

package com.imd.examples;

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

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;

public class WordCountMapper extends MapReduceBase implements Mapper {
private IntWritable one = new IntWritable(1);

@Override
// 怎么切分的呢 key是什么
public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter) throws IOException {
StringTokenizer st = new StringTokenizer(value.toString());
Text text = new Text();
while (st.hasMoreTokens()) {
text.set(st.nextToken());
output.collect(text, one);
}
}
}

推荐阅读：