下面是Hadoop官網(wǎng)的一個WordCount程序：

package org.myorg;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.mapreduce.*; 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;public class WordCount {public static class Map extends 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, Context context) throws IOException, InterruptedException { String line = value.toString(); StringTokenizer tokenizer = new StringTokenizer(line); while (tokenizer.hasMoreTokens()) { word.set(tokenizer.nextToken()); context.write(word, one); } } } public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } context.write(key, new IntWritable(sum)); } }public static void main(String[] args) throws Exception { Configuration conf = new Configuration();Job job = new Job(conf, "wordcount");job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class);job.setMapperClass(Map.class); job.setReducerClass(Reduce.class);job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class);FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1]));job.waitForCompletion(true); }}

from: http://wiki.apache.org/hadoop/WordCount

總結(jié)

以上是生活随笔為你收集整理的Hadoop官网的一个WordCount程序的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。