hadooop的wordcount程序

创建项目文件夹

sudo mkdir -p ~/hpro/com/vs/example

创建主程序类

sudo gedit ~/hpro/com/vs/example/WordCount.java

java类如下

package com.vs.example;import java.io.IOException;import java.util.*;import org.apache.hadoop.fs.Path;import org.apache.hadoop.conf.*;import org.apache.hadoop.io.*;import org.apache.hadoop.mapred.*;import org.apache.hadoop.util.*;public class WordCount {public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {private final static IntWritable one = new IntWritable(1);private Text word = new Text();public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {String line = value.toString();StringTokenizer tokenizer = new StringTokenizer(line);while(tokenizer.hasMoreTokens()){word.set(tokenizer.nextToken());output.collect(word, one);}}}public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {int sum = 0;while(values.hasNext()){sum += values.next().get();}output.collect(key, new IntWritable(sum));}}public static void main(String[] args) throws Exception{JobConf conf = new JobConf(WordCount.class);conf.setJobName("wordcount");conf.setOutputKeyClass(Text.class);conf.setOutputValueClass(IntWritable.class);conf.setMapperClass(Map.class);conf.setReducerClass(Reduce.class);conf.setInputFormat(TextInputFormat.class);conf.setOutputFormat(TextOutputFormat.class);FileInputFormat.setInputPaths(conf, new Path(args[0]));FileOutputFormat.setOutputPath(conf, new Path(args[1]));JobClient.runJob(conf);}}

创建类文件的目录

mkdir ~/hpro/FirstJar

编译

javac -classpath ~/hadoop-1.0.4/hadoop-core-1.0.4.jar -d ~/hpro/FirstJar hpro/com/vs/example/WordCount.java

打成jar包

$JAVA_HOME/bin/jar -cvf ~/hpro/wordcount.jar -C ~/hpro/FirstJar/ .

准备两个输入文件

echo "Hello World Bye World" > ~/hpro/file01

echo "Hello Hadoop GoodBye Hadoop" > ~/hpro/file02

准备上传文件到dfs

~/hadoop-1.0.4/bin/hadoop dfs -mkdir input

~/hadoop-1.0.4/bin/hadoop dfs -put ~/hpro/file0* input

运行程序

~/hadoop-1.0.4/bin/hadoop jar ~/hpro/wordcount.jar com.vs.example.WordCount input output

然后就可以在管理控制台查看运行记录了

http://localhost:50030/jobtracker.jsp

也可以把输出文件拉下来，查看

~/hadoop-1.0.4/bin/hadoop dfs -get output ~/hpro/

~/hpro/outpu就是输出的文件，进入可以查看运行结果

cd hpro/output

gedit part-00000 

文件part-00000的内容如下

Bye1Goodbye1Hadoop2Hello2World2

Good Luck!