1. 需要编译打包的代码如下：
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> [<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);
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);
}
}
2.编译
编译之前需要设置classpath，有两种方式一种是修改 /etc/profile文件，另一种是在编译时动态指定classpath
a .修改/etc/profile添加如下代码：
export CLASSPATH=$HDOOP_HOME/share/hadoop/common/hadoop-common-2.5.0.jar:$HDOOP_HOME/share/hadoop/common/lib/commons-cli-1.2.jar:$HDOOP_HOME/share/hadoop/common/lib/hadoop-annotations-2.5.0.jar:$HDOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.5.0.jar
保存并生效 source /etc/profile
javac -d /root/test/bin/ /root/test/org/apache/hadoop/examples/WordCount.java
注意：$HDOOP_HOME 为hadoop的根目录
/root/test/bin/ 为生成class文件的存放路径
b.动态设置classpath
javac -classpath $HDOOP_HOME/share/hadoop/common/hadoop-common-2.5.0.jar:$HDOOP_HOME/share/hadoop/common/lib/commons-cli-1.2.jar:$HDOOP_HOME/share/hadoop/common/lib/hadoop-annotations-2.5.0.jar:$HDOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.5.0.jar -d
/root/test/bin/ /root/test/org/apache/hadoop/examples/WordCount.java
3.打包
切换到打包目录下 cd /root/test/bin/
jar -cvf WordCount.jar org/apache/hadoop/examples/*.class
4.运行
hadoop jar WordCount.jar org/apache/hadoop/examples/WordCount hdfs://hadoop1:9000/home/input/ hdfs://hadoop1:9000/home/output/result
注意：hdfs 的/home/input/目录下存放需要统计的文件。
在hdfs上创建/home/output/目录result目录不用创建，运行程序时会自己创建，否则会提示给文件已经存在
5.查看
hdfs dfs -cat /home/output/result/part-r-00000