wordcount程序
package org.robby.mr;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
public static class Map
extends Mapper<Object, Text, Text, IntWritable>{
//object是每一行的行表、text是每一行的内容,使用的是hadoop内置的数据结构
//后面的text是指输出的行,也就是单词,IntWritable是单词的个数
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())
{
//选出单词放在word里,然后用context输出,对应单词加1
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class Reduce
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
//传入一个单词和其对于的次数迭代器
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> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
// Set up the input
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job, new Path(args[0]));
// Mapper
job.setMapperClass(Map.class);
// Reducer
job.setReducerClass(Reduce.class);
// Output
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
TextOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
使用hadoop jar web.jar [类的全名称] [输入目录] [输出目录]
输入和输出目录都是hdfs的目录。
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。