Hadoop实战第一篇

前言：
 　　都说现在是草根为尊的时代，近年来hadoop及spark技术在国内越来越流行。而且渐渐现成为企业的新宠。在DT时代全面来临之前，能提早接触大数据的技术必然能先人一步。本文作为Hadoop系列的第一篇，将HDFS和MapRed两个技术核心用2个实例简单实现一些，希望能供hadoop入门的朋友些许参考。

--HDFS

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;

 public class  HDFStest {
     final static String P_IN="hdfs://hadoop0:9000/data";
     final static String P_F1="hdfs://hadoop0:9000/a.txt";

     public static void main(String[] args) throws IOException {

         FileSystem fileSystem = FileSystem.get(new Configuration());
         System.out.println("make diretory:");
         fileSystem.mkdirs(new Path(P_IN));
         System.out.println("judgy if exist 'File':");
         System.out.println(fileSystem.exists(new Path(P_F1)));

     }

 }

--MapReduce

实现文本单词出现次数的统计：

 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 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 WC {

     static String INPUT="hdfs://hadoop0:9000/hello";
     static String OUTPUT="hdfs://hadoop0:9000/output";

     public static void main(String[] args) throws Exception{

         Job job = new Job(new Configuration(),WC.class.getSimpleName());
         job.setMapperClass(MyMapper.class);
         job.setReducerClass(MyReducer.class);
         job.setJarByClass(WC.class);
         //输出结果格式
         job.setMapOutputKeyClass(Text.class);;
         job.setMapOutputValueClass(LongWritable.class);
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(LongWritable.class);
         //路径设置
         FileInputFormat.setInputPaths(job, INPUT);
         FileOutputFormat.setOutputPath(job, new Path(OUTPUT));
         //waitfor
         job.waitForCompletion(true);

     }

     static class MyMapper extends Mapper<LongWritable, Text,Text,LongWritable >{

         @Override
         protected void map(LongWritable key, Text value,
                 Mapper<LongWritable, Text, Text, LongWritable>.Context context)
                 throws IOException, InterruptedException {

             String[] words = value.toString().split(" ");
             for(String word:words){
                 context.write(new Text(word), new LongWritable(1));
             }
         }
     }
     static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{

         @Override
         protected void reduce(Text arg0, Iterable<LongWritable> arg1,Context context)
                 throws IOException, InterruptedException {

             Long sum=0L;
             for(LongWritable c:arg1){
                 sum += c.get();
             }
             context.write(arg0,new LongWritable(sum));
         }
     }
 }

以上代码相对简单，map读取到一行“Text”之后通过字符串切分函数split()得到各个单词，每个单词出现一次计数为1：

Reduce操作，实际就是一个集合元素累计的操作：