Hadoop最基本的wordcount(统计词频)

package com.uniclick.dapa.dstest;

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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;

public class WordCount {
	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		String inputFilePath = "/user/zhouyuanlong/wordcount/input/wordTest*.txt";
		String outputFilePath = "/user/zhouyuanlong/wordcount/output/";
		String queue = "default";
		String jobName = "wordCount";
		if(args == null || args.length < 2){
			System.out.println("[-INPUT <inputFilePath>"
					+ "[-OUTPUT <outputFilePath>");
		}else{
			for(int i=0;i<args.length;i++){
				if("-Q".equals(args[i])){
					queue = args[++i];
				}
			}
		}
		Configuration conf = new Configuration();
		conf.set("mapred.job.queue.name", queue);
		Job job = new Job(conf, jobName);
		job.setJarByClass(WordCount.class);
		job.setMapperClass(WordCountMapper.class);
//		job.setCombinerClass(cls);
		job.setReducerClass(WordCountReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.addInputPath(job, new Path(inputFilePath));
		Path path = new Path(outputFilePath);
		FileSystem fs = FileSystem.get(URI.create(outputFilePath), conf);
		if(fs.exists(path)){
//			fs.delete(path);
			fs.delete(path, true);
		}
		FileOutputFormat.setOutputPath(job, new Path(outputFilePath));
		System.exit(job.waitForCompletion(true) ? 1 : 0);
	}

	public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
		private Text kt = new Text();
		private final static IntWritable vt = new IntWritable(1);

		public void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			String[] arr = value.toString().split("\t");
			for(int i = 0; i < arr.length; i++){
				kt.set(arr[i]);
				context.write(kt, vt);
			}
		}
	}

	public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
		private IntWritable vt = new IntWritable();

		public void reduce(Text key, Iterable<IntWritable> values, Context context)
				throws IOException, InterruptedException{
			int sum = 0;
			for(IntWritable intVal : values){
				sum += intVal.get();
			}
			vt.set(sum);
			context.write(key, vt);
		}
	}

}

input目录中文件wordTest1.txt的内容(每行以table键分隔):

hello    world
hello    hadoop
hello    mapredruce

input目录中文件wordTest2.txt的内容(每行以table键分隔):

hello    world
hello    hadoop
hello    mapredruce

hdfs输出结果:

web     2
mapredruce      1
python  1
hadoop  1
hello   6
clojure 2
world   1
java    2

PS:对Hadoop自带的wordcount的例子略有改变