package com.mzsx.hadoop;
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.output.FileOutputFormat;
public class MySortWordCount {
    public static class MyMapper extends
            Mapper {
        private final static IntWritable one = new IntWritable(1);// 类似于int类型
        private Text word = new Text(); // 可以理解成String类型
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            System.err.println(key + "," + value);
            // 默认情况下即根据空格分隔字符串
            String tmp=value.toString();
            tmp=tmp.replace('\'', ' ');
            tmp=tmp.replace('.', ' ');
            tmp=tmp.replace(',', ' ');
            tmp=tmp.replace(':', ' ');
            tmp=tmp.replace('!', ' ');
            tmp=tmp.replace(';', ' ');
            tmp=tmp.replace('?', ' ');
            tmp=tmp.replace('`', ' ');
            tmp=tmp.replace('"', ' ');
            tmp=tmp.replace('&', ' ');
            tmp=tmp.replace('(', ' ');
            tmp=tmp.replace(')', ' ');
            tmp=tmp.replace('-', ' ');
            StringTokenizer itr = new StringTokenizer(tmp);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        };
    }
    // Reducer
    public static class MyReducer extends
            Reducer {
        private IntWritable result = new IntWritable();
        protected void reduce(Text key, Iterable values,
                Context context) throws IOException, InterruptedException {
            System.err.println(key + "," + values);
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            ;
            context.write(key, result);// 这是最后结果
        };
    }
      
    public static class SortMapper extends Mapper{
          
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
             
            IntWritable times = new IntWritable(1);
            Text password = new Text();
            String eachline=value.toString();
            String[] eachterm =eachline.split("\t");
            password.set(eachterm[0]);
            times.set(Integer.parseInt(eachterm[1]));
            context.write(times,password);
              
        }
      }
         
      public static class SortReducer extends Reducer {
          private Text password = new Text();
          public void reduce(IntWritable key,Iterable values, Context context) throws IOException, InterruptedException {
            for (Text val : values) {
                password.set(val);
                context.write(key,password);
            }
        }
    }
      private static class IntDecreasingComparator extends IntWritable.Comparator {
          public int compare(WritableComparable a, WritableComparable b) {
            //return -super.compare(a, 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);
              return super.compare(b1, s1, l1, b2, s2, l2);
          }
      }
    public static void main(String[] args) throws Exception {
        // 声明配置信息
        Configuration conf = new Configuration();
        // 声明Job
        Job job = new Job(conf, "Word Count");
        // 设置工作类
        job.setJarByClass(MySortWordCount.class);
        // 设置mapper类
        job.setMapperClass(MyMapper.class);
        // 可选
        job.setCombinerClass(MyReducer.class);
        // 设置合并计算类
        job.setReducerClass(MyReducer.class);
        // 设置key为String类型
        job.setOutputKeyClass(Text.class);
        // 设置value为int类型
        job.setOutputValueClass(IntWritable.class);
        //job.setInputFormatClass(KeyValueTextInputFormat.class);
        // 设置或是接收输入输出
        /*FileInputFormat.setInputPaths(job, new Path("/user/root/aoman.txt"));
        FileOutputFormat.setOutputPath(job, new Path("/user/root/r3"));
        // 执行
        System.exit(job.waitForCompletion(true) ? 0 : 1);*/
          
        //定义一个临时目录,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。
        FileInputFormat.addInputPath(job, new Path("/user/root/aoman.txt"));
        Path tempDir = new Path("MySortWordCount-temp-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
        FileOutputFormat.setOutputPath(job, tempDir);
          
        if(job.waitForCompletion(true))
        {
            Job sortJob = new Job(conf, "csdnsort");
            sortJob.setJarByClass(MySortWordCount.class);
              
            FileInputFormat.addInputPath(sortJob, tempDir);
              
            sortJob.setMapperClass(SortMapper.class);
            FileOutputFormat.setOutputPath(sortJob, new Path("/user/root/sort1"));
              
            sortJob.setOutputKeyClass(IntWritable.class);
            sortJob.setOutputValueClass(Text.class);
              
            sortJob.setSortComparatorClass(IntDecreasingComparator.class);
   
            FileSystem.get(conf).deleteOnExit(tempDir);
              
            System.exit(sortJob.waitForCompletion(true) ? 0 : 1);
        }
          
        System.exit(job.waitForCompletion(true) ? 0 : 1);
          
          
    }
}