??Mapreduce??????е??????
???????????? ???????[ 2014/11/24 14:02:46 ] ??????????????? ??????? ????
????hadoop??????wordcount?????????????????????????????????????????????????????£?
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{
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 = new Text(itr.nextToken()); //to unitest??should be new Text word.set(itr.nextToken())
context.write(word?? new IntWritable(1));
}
}
}
public static class IntSumReducer
extends Reducer {
private IntWritable result = new IntWritable();
public void reduce(Text key?? Iterable 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 ");
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);
}
}
??????
???·???
??????????????????
2023/3/23 14:23:39???д?ò??????????
2023/3/22 16:17:39????????????????????Щ??
2022/6/14 16:14:27??????????????????????????
2021/10/18 15:37:44???????????????
2021/9/17 15:19:29???·???????·
2021/9/14 15:42:25?????????????
2021/5/28 17:25:47??????APP??????????
2021/5/8 17:01:11