Hadoop WordCount改进实现正确识别单词以及词频降序排序

0.参考资料:

http://radarradar.javaeye.com/blog/289257

http://blog.chinaunix.net/u3/99156/showart_2157576.html

1.思路:

1.1过滤

MapReduce的第一操作就是要读取文件,不过我们经常会发现一个文本中会有一些我们不需要的字符,比如特殊字符。一般需要进行词频统计的都是单词或者是数字,所以那些非0-9, a-z, A-Z的字符基本都是垃圾字符,我们需要进行统计,这是我们可以通过一个正则表达式来进行过滤,当每次多去一行文字的时候,我们将所有非0-9, a-z, A-Z的垃圾字符都替换为空格,这样就清楚了垃圾字符。在我们最后的词频统计结果中,就不会出现这些特殊字符了。

1.2降序

定义一个用户排序比较的静态内部类,通过这个类来控制词频统计最后的排序结果。我们这里所使用的静态内部类是IntWritableDecreasingComparator。需要注意的是必须在main函数中主动声明使用这个比较器。

2.代码实例

View Code
package org.apache.hadoop.examples;

import java.io.IOException;

import java.util.Random;

import java.util.StringTokenizer;

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.Text;

import org.apache.hadoop.io.WritableComparable;

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.SequenceFileInputFormat;

import org.apache.hadoop.mapreduce.lib.map.InverseMapper;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount2 {

    public static class TokenizerMapper extends

            Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);

        private Text word = new Text();

        private String pattern = "[^//w]"; // 正则表达式,代表不是0-9, a-z, A-Z的所有其它字符,其中还有下划线

        public void map(Object key, Text value, Context context)

                throws IOException, InterruptedException {

            String line = value.toString().toLowerCase(); // 全部转为小写字母

            line = line.replaceAll(pattern, " "); // 将非0-9, a-z, A-Z的字符替换为空格

            StringTokenizer itr = new StringTokenizer(line);

            while (itr.hasMoreTokens()) {

                word.set(itr.nextToken());

                context.write(word, one);

            }

        }

    }

    public static class IntSumReducer extends

            Reducer<Text, IntWritable, Text, IntWritable> {

        private IntWritable result = new IntWritable();

        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);

        }

    }

    

     private static class IntWritableDecreasingComparator extends IntWritable.Comparator {

          public int compare(WritableComparable a, WritableComparable b) {

            return -super.compare(a, b);

          }

          

          public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {

              return -super.compare(b1, s1, l1, b2, s2, l2);

          }

      }

    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);

        }

         Path tempDir = new Path("wordcount-temp-" + Integer.toString(

                    new Random().nextInt(Integer.MAX_VALUE))); //定义一个临时目录

        

        Job job = new Job(conf, "word count");

        job.setJarByClass(WordCount2.class);

        try{

            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, tempDir);//先将词频统计任务的输出结果写到临时目

                                                         //录中, 下一个排序任务以临时目录为输入目录。

            job.setOutputFormatClass(SequenceFileOutputFormat.class);

            if(job.waitForCompletion(true))

            {

                Job sortJob = new Job(conf, "sort");

                sortJob.setJarByClass(WordCount2.class);

                

                FileInputFormat.addInputPath(sortJob, tempDir);

                sortJob.setInputFormatClass(SequenceFileInputFormat.class);

                

                /*InverseMapper由hadoop库提供,作用是实现map()之后的数据对的key和value交换*/

                sortJob.setMapperClass(InverseMapper.class);

                /*将 Reducer 的个数限定为1, 最终输出的结果文件就是一个。*/

                sortJob.setNumReduceTasks(1); 

                FileOutputFormat.setOutputPath(sortJob, new Path(otherArgs[1]));

                

                sortJob.setOutputKeyClass(IntWritable.class);

                sortJob.setOutputValueClass(Text.class);

                /*Hadoop 默认对 IntWritable 按升序排序,而我们需要的是按降序排列。

                 * 因此我们实现了一个 IntWritableDecreasingComparator 类, 

                 * 并指定使用这个自定义的 Comparator 类对输出结果中的 key (词频)进行排序*/

                sortJob.setSortComparatorClass(IntWritableDecreasingComparator.class);

     

                System.exit(sortJob.waitForCompletion(true) ? 0 : 1);

            }

        }finally{

            FileSystem.get(conf).deleteOnExit(tempDir);

        }

    }

}

你可能感兴趣的:(wordcount)