<property>
 <name>dfs.permissions</name>
 <value>false</value>
 </property>

package yjmyzz;

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> [<in>...] <out>");
  System.exit(2);
 }
 Job job = Job.getInstance(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);
 for (int i = 0; i < otherArgs.length - 1; ++i) {
  FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
 }
 FileOutputFormat.setOutputPath(job,
  new Path(otherArgs[otherArgs.length - 1]));
 System.exit(job.waitForCompletion(true) ? 0 : 1);
 }
}

log4j.rootLogger=INFO, stdout

#log4j.logger.org.springframework=INFO
#log4j.logger.org.apache.activemq=INFO
#log4j.logger.org.apache.activemq.spring=WARN
#log4j.logger.org.apache.activemq.store.journal=INFO
#log4j.logger.org.activeio.journal=INFO

log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{ABSOLUTE} | %-5.5p | %-16.16t | %-32.32c{1} | %-32.32C %4L | %m%n

<?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>yjmyzz</groupId>
 <artifactId>mapreduce-helloworld</artifactId>
 <version>1.0-SNAPSHOT</version>

 <dependencies>
 <dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-common</artifactId>
  <version>2.6.0</version>
 </dependency>
 <dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
  <version>2.6.0</version>
 </dependency>
 <dependency>
  <groupId>commons-cli</groupId>
  <artifactId>commons-cli</artifactId>
  <version>1.2</version>
 </dependency>
 </dependencies>

 <build>
 <finalName>${project.artifactId}</finalName>
 </build>

</project>

package yjmyzz;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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);
 }
 }


 /**
 * 删除指定目录
 *
 * @param conf
 * @param dirPath
 * @throws IOException
 */
 private static void deleteDir(Configuration conf, String dirPath) throws IOException {
 FileSystem fs = FileSystem.get(conf);
 Path targetPath = new Path(dirPath);
 if (fs.exists(targetPath)) {
  boolean delResult = fs.delete(targetPath, true);
  if (delResult) {
  System.out.println(targetPath + " has been deleted sucessfullly.");
  } else {
  System.out.println(targetPath + " deletion failed.");
  }
 }

 }

 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> [<in>...] <out>");
  System.exit(2);
 }

 //先删除output目录
 deleteDir(conf, otherArgs[otherArgs.length - 1]);

 Job job = Job.getInstance(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);
 for (int i = 0; i < otherArgs.length - 1; ++i) {
  FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
 }
 FileOutputFormat.setOutputPath(job,
  new Path(otherArgs[otherArgs.length - 1]));
 System.exit(job.waitForCompletion(true) ? 0 : 1);
 }
}

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
 <property>
 <name>fs.defaultFS</name>
 <value>hdfs://172.28.20.***:9000</value>
 </property>
</configuration>