hadoop学习过程-2013.08.22.2--hadoop1.2.1修改WordCount并编译

hadoop1.2.1修改WordCount并编译

1. 代码:

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 {
System.out.print("(" + key + ":" + value + ") ---map---> [");
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
System.out.print("(" + word + ":" + one + "), ");
context.write(word, one);
}
System.out.println("]");
}
}

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 {
String vals="#";
int sum = 0;
for (IntWritable val : values) {
vals+=(val+",");
sum += val.get();
}
vals+="#";
System.out.print("(" + key+":" +vals+ ") ---reduce---> ");

result.set(sum);
System.out.println("(" + key + ":" + result+ ")");
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);
}
}

2. 依赖的jar

hadoop-1.2.1\hadoop-core-1.2.1.jar

hadoop-1.2.1\lib\commons-cli-1.2.jar

3. 编译运行

在eclipse里新建java项目，加入1中的WordCount代码、2中的两个jar，将项目导出成wordcount.jar，放到hadoop集群环境中运行即可。

运行命令是:

hadoop jar
xxx/wordcount.jar org.apache.hadoop.examples.WordCount input output

(具体运行步骤参见文章 ”hadoop-1.2.1运行WordCount”)

下载本文