1 wordcount源码
package org.jediael.hadoopdemo;
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);
}
}
@SuppressWarnings("deprecation")
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] arg = {"/usr/local/hadoop-2.2.0/input","/usr/local/hadoop-2.2.0/output"};
String[] otherArgs = new GenericOptionsParser(conf, arg)
.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);
}
}
之前一直只运行过hadoop-2.2.0 自带的例子程序wordcount,想自己编辑hadoop代码,搞了半天,最后发现原来的代码只需做稍微修改就可以在hadoop上跑,String[] arg = {"/usr/local/hadoop-2.2.0/input","/usr/local/hadoop-2.2.0/output"}; 就是添加它的本地输入路径,并在里边放入输入内容就可以,而本地输出文件夹hadoop会自己建立。当然也可以将文件上传至分布式文件系统中进行运行。