mapreduce实现一天内用户使用总时长

根据公司需要使用mapreduce实现用户一天内使用总时长，代码如下：

package com.online.time;

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

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

public class UserOnlineTime {
	// mapper
	public static class OnlineMapper extends Mapper
   
   
    
    {
		private Text info = new Text();
		private Text otherInfo = new Text();
		// 数据输入格式：手机号(空格)数据访问时间(空格)动作(空格)访问的页面
		public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
			String[] userInfo = value.toString().split(" ");
			String phone = userInfo[1];
			String other = timeToSecond(userInfo[0]) + "-" + userInfo[2] + "-" + userInfo[3];
			
			info.set(phone);
			otherInfo.set(other);
			// map的输出为:
    
    <手机号, 数据访问时间-动作标识(共有两个动作：in-进入页面，out-退出页面)-访问的页面>
     
     
			context.write(info, otherInfo);
		}
	}

	// reduce
	public static class OnlineReduce extends Reducer
     
     
      
      {
		private Text result = new Text();
		// 获取昨天日期
		String yesterday = getYesterday();
		public void reduce(Text key, Iterable
      
      
       
        values, Context context) throws IOException, InterruptedException{
			List
       
       
         list = new ArrayList 
        
          (); for (Text val : values) { list.add(val.toString()); } // 将集合转换为数组 String[] valueArray = (String[]) list.toArray(new String[list.size()]); String[] resultInfo = sortReduceValue(valueArray); // 36666-In-HouseController int resultTime = 0; for(int i = 0; i < resultInfo.length; i++){ String[] tls = resultInfo[i].split("-"); if("In".equals(tls[1])){ // 数据已按照时间升序排序 int inTime = Integer.parseInt(tls[0]); String inLocal = tls[2]; for(int j = i + 1; j < resultInfo.length; j++){ String[] ols = resultInfo[j].split("-"); String outLocal = ols[2]; // 判断是否是同一页面 if(inLocal.equals(outLocal)){ if("Out".equals(ols[1])){ int outTime = Integer.parseInt(ols[0]); // 在本页面停留的时间 int stayTime = outTime - inTime; // 在本页面停留时间大于10分钟,则抛弃此数据 if(stayTime < 600){ resultTime = resultTime + stayTime; break; }else{ break; } }else{ break; } } } } } if(resultTime == 0){ resultTime = 1; } // 数据分隔符为 Tab键，方便交给hive管理 result.set(String.valueOf(resultTime) + " " + yesterday); context.write(key, result); } } // 将时间转换为秒 public static int timeToSecond(String time){ int second = 0; if(time != null && !"".equals(time)){ String[] times = time.split(":"); int hourSecond = Integer.parseInt(times[1]) * 60 * 60; int minuteSecond = Integer.parseInt(times[2]) * 60; second = hourSecond + minuteSecond + Integer.parseInt(times[3]); } return second; } // 对reduce数据按照时间从小到大排序(冒泡排序) public static String[] sortReduceValue(String[] values){ for (int i = 0; i < values.length -1; i++){ for(int j = 0 ;j < values.length - i - 1; j++){ if(Integer.parseInt(values[j].split("-")[0]) > Integer.parseInt(values[j + 1].split("-")[0])){ String temp = values[j]; values[j] = values[j + 1]; values[j + 1] = temp; } } } return values; } // 获取昨天的日期 public static String getYesterday(){ Calendar cal=Calendar.getInstance(); cal.add(Calendar.DATE,-1); Date time=cal.getTime(); String yesterday = new SimpleDateFormat("yyyyMMdd").format(time); return yesterday; } // main函数 @SuppressWarnings("deprecation") 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 
          
          
            "); System.exit(2); } Job job = new Job(conf, "User Online Job"); job.setNumReduceTasks(1); job.setJarByClass(UserOnlineTime.class); job.setMapperClass(OnlineMapper.class); job.setReducerClass(OnlineReduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }