1. 程式人生 > >Hadoop 統計檔案中某個單詞出現的次數

Hadoop 統計檔案中某個單詞出現的次數

轉自:https://www.xuebuyuan.com/1270346.html

 

2013年10月24日 ⁄ 綜合 ⁄ 共 2628字 ⁄ 字號    ⁄ 評論關閉

 

如檔案word.txt內容如下:

what is you name?

my name is zhang san。

要求統計word.txt中出現“is”的次數?

 

程式碼如下:

PerWordMapper

package com.hadoop.wordcount;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class PerWordMapper extends Mapper<Object, Text, Text, IntWritable> {

	public Text keyText = new Text();
	public IntWritable intValue = new IntWritable(1);
	
	@Override
	protected void map(Object key, Text value,
			Context context)
			throws IOException, InterruptedException {
		String str = value.toString();
		StringTokenizer to = new StringTokenizer(str);
		while (to.hasMoreTokens()) {
			String t = to.nextToken();
			//此處為判斷統計字串的地方
			if(t.equals("is")){
				keyText = new Text(t);
				context.write(keyText, intValue);
			}
	       
	     }
	}
}

 

PerWordReducer

package com.hadoop.wordcount;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class PerWordReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

	public IntWritable intValue = new IntWritable(0);
	@Override
	protected void reduce(Text key, Iterable<IntWritable> value,
			Context context)
			throws IOException, InterruptedException {
		int sum = 0;
		while(value.iterator().hasNext()){
			sum += value.iterator().next().get();
		}
		intValue.set(sum);
		context.write(key, intValue);
	}
	
}

PerWordCount

package com.hadoop.wordcount;

import java.io.IOException;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import com.hadoop.mapreducer.MapperClass;
import com.hadoop.mapreducer.ReducerClass;
import com.hadoop.mapreducer.WordCount;

public class PerWordCount {
	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		Configuration conf = new Configuration();
	    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
	    System.out.println("otherArgs.length:"+otherArgs.length);
	    if (otherArgs.length != 2) {
	      System.err.println("Usage: wordcount <in> <out>");
	      System.exit(2);
	    }
	    Job job = new Job(conf, "word count");
	    job.setJarByClass(PerWordCount.class);
	    job.setMapperClass(PerWordMapper.class);
	    job.setCombinerClass(PerWordReducer.class);
	    job.setReducerClass(PerWordReducer.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);
	}

}