hadoop学习笔记之五：hadoop MapReduce wordcount

      搭建好了Eclipse的开发环境，接下来就是Helloword，hadoop 的HelloWord是一个Wordcount的例子，就是统计单词在不同的文档里出现的次数。

 

     我这边准备了三个文档：（存入hdfs 的文件系统中)

 

[root@bigdata2 hadoop-1.0.1]# ./bin/hadoop fs -cat /user/root/in/helloword.txt
Warning: $HADOOP_HOME is deprecated.

Hello,Word!
[root@bigdata2 hadoop-1.0.1]# ./bin/hadoop fs -cat /user/root/in/input1.txt
Warning: $HADOOP_HOME is deprecated.

hello,word !
what's your name ?
haow are you ?
are you ok ?
are  you ok ?

[root@bigdata2 hadoop-1.0.1]# ./bin/hadoop fs -cat /user/root/in/input2.txt
Warning: $HADOOP_HOME is deprecated.

hello,mobile.
hello,word !
what's your name ?
haow are you ?
are you ok ?
are  you ok ?

    WordCount.java

  

package wordcount;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;

public class WordCount {

        public static class MapClass extends MapReduceBase implements
                        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,
                                OutputCollector<Text, IntWritable> output, Reporter reporter)
                                throws IOException {
                        String line = value.toString();
                        StringTokenizer itr = new StringTokenizer(line);
                        while (itr.hasMoreTokens()) {
                                word.set(itr.nextToken());
                                output.collect(word, one);
                        }
                }
        }

        /**
         * A reducer class that just emits the sum of the input values.
         */
        public static class Reduce extends MapReduceBase implements
                        Reducer<Text, IntWritable, Text, IntWritable> {

                public void reduce(Text key, Iterator<IntWritable> values,
                                OutputCollector<Text, IntWritable> output, Reporter reporter)
                                throws IOException {
                        int sum = 0;
                        while (values.hasNext()) {
                                sum += values.next().get();
                        }
                        output.collect(key, new IntWritable(sum));
                }
        }

        public static void main(String[] args) throws Exception {
                JobConf conf = new JobConf(WordCount.class);
                conf.setJobName("wordcount");

                conf.setOutputKeyClass(Text.class);
                conf.setOutputValueClass(IntWritable.class);

                conf.setMapperClass(MapClass.class);
                conf.setCombinerClass(Reduce.class);
                conf.setReducerClass(Reduce.class);

                conf.setInputFormat(TextInputFormat.class);
                conf.setOutputFormat(TextOutputFormat.class);
            String outFileExt = "_" + new SimpleDateFormat("yyyyMMddHHmmss").format(new Date());
                FileInputFormat.setInputPaths(conf,new Path("hdfs://192.168.1.2:9000/user/root/in/"));
                FileOutputFormat.setOutputPath(conf, new Path("hdfs://192.168.1.2:9000/user/root/out/"+outFileExt));
                JobClient.runJob(conf);
        }

}

   直接运行

  

结果 写道

! 2
? 8
Hello,Word! 1
are 6
haow 2
hello,mobile. 1
hello,word 2
name 2
ok 4
what's 2
you 6
your 2

    代码解释：

  

  JobConf conf = new JobConf(WordCount.class);
                conf.setJobName("wordcount");

                conf.setOutputKeyClass(Text.class);
                conf.setOutputValueClass(IntWritable.class);

                conf.setMapperClass(MapClass.class);
                conf.setCombinerClass(Reduce.class);
                conf.setReducerClass(Reduce.class);

                conf.setInputFormat(TextInputFormat.class);
                conf.setOutputFormat(TextOutputFormat.class);

 

JobConf 负责读取配置文件（主要包括：core-site.xml,hdfs-site.xml,mapred-site.xml等）

 conf.setJobName("wordcount");主要用来设置JOB名称，便于页面监控

   InputFormat 主要负责调用getRecodeReader()方法生成RecordReader对象，RecordReader对象则调用CreatKey和CreatValue方法生产可以供Map处理的<Key,Value>键值对

 

   InputFormat方法有很多重写版本，支持不同的数据源，例如FileInputFormat，DbInputFormat等

  OutputFormat这负责输出的格式应为Key和value 是Object类型，那么内部会转为String来输出。

 

public void map(LongWritable key, Text value,
                                OutputCollector<Text, IntWritable> output, Reporter reporter

  

   Map函数产生<Key，ValueList>类型的键值对，交由Reduce函数进行处理

  

  int sum = 0;
                        while (values.hasNext()) {
                                sum += values.next().get();
                        }
                        output.collect(key, new IntWritable(sum));

  Reduce函数则负责将Value的值做Count，计算出次数，然后将结果输出。