/**

  *  Licensed under the Apache License, Version 2.0 (the "License");

  *  you may not use this file except in compliance with the License.

  *  You may obtain a copy of the License at

  *

  *      http://www.apache.org/licenses/LICENSE-2.0

  *

  *  Unless required by applicable law or agreed to in writing, software

  *  distributed under the License is distributed on an "AS IS" BASIS,

  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

  *  See the License for the specific language governing permissions and

  *  limitations under the License.

  */

 package org.apache.hadoop.examples;

 import java.io.IOException;

 import java.util.StringTokenizer;

 //导入各种Hadoop包

 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.Mapper;

 import org.apache.hadoop.mapreduce.Reducer;

 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

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

 import org.apache.hadoop.util.GenericOptionsParser;

 // 主类

 public class WordCount {

     // Mapper类

     public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{

         // new一个值为1的整数对象

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

         // new一个空的Text对象

         private Text word = new Text();

         // 实现map函数

         public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

             // 创建value的字符串迭代器

             StringTokenizer itr = new StringTokenizer(value.toString());

             // 对数据进行再次分割并输出map结果。初始格式为<字节偏移量，单词> 目标格式为<单词，频率>

             while (itr.hasMoreTokens()) {

                     word.set(itr.nextToken());

                     context.write(word, one);

             }

         }

     }

     // Reducer类

     public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {

         // new一个值为空的整数对象

         private IntWritable result = new IntWritable();

         // 实现reduce函数

         public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

             int sum = 0;

             for (IntWritable val : values) {

                 sum += val.get();

             }

             // 得到本次计算的单词的频数

             result.set(sum);

             // 输出reduce结果

             context.write(key, result);

         }

     }

     // 主函数

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

         // 获取配置参数

         Configuration conf = new Configuration();

         String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

         // 检查命令语法

         if (otherArgs.length != 2) {

                 System.err.println("Usage: wordcount <in> <out>");

                 System.exit(2);

         }

         // 定义作业对象

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

         // 注册分布式类

         job.setJarByClass(WordCount.class);

         // 注册Mapper类

         job.setMapperClass(TokenizerMapper.class);

         // 注册合并类

         job.setCombinerClass(IntSumReducer.class);

         // 注册Reducer类

         job.setReducerClass(IntSumReducer.class);

         // 注册输出格式类

         job.setOutputKeyClass(Text.class);

         job.setOutputValueClass(IntWritable.class);

         // 设置输入输出路径

         FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

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

         // 运行程序

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

     }

 }

 ./bin/hadoop fs -put ../workspace/Hadoop_t1/input/ input01

 ./bin/hadoop fs -ls

 ./bin/hadoop fs -cat output01/*