Java使用MapReduce切分檔案

比如有海量的文本檔案，如訂單，頁面點擊事件的記錄，量特別大，很難搞定，
那么我們該怎樣解決海量資料的計算？

1、獲取總行數
2、計算每個檔案中存多少資料
3、split切分檔案
4、reduce將檔案進行匯總

例如這里有百萬條資料，單個檔案操作太麻煩，所以我們需要進行切分
在切分檔案的程序中會出現檔案不能整個切分的情況，可能有剩下的資料并沒有被讀取到，所以我們每個切分128條資料，不足128條再保留到一個檔案中

創建MapTask

import java.io.*;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;

public class MapTask extends Thread {
    //用來接收具體的哪一個檔案
    private File file;
    private int flag;

    public MapTask(File file, int flag) {
        this.file = file;
        this.flag = flag;
    }

    @Override
    public void run() {
        try {
            BufferedReader br = new BufferedReader(new FileReader(file));
            String line;
            HashMap<String, Integer> map = new HashMap<String, Integer>();
            while ((line = br.readLine()) != null) {
                /**
                 * 統計班級人數HashMap存盤
                 */
                String clazz = line.split(",")[4];
                if (!map.containsKey(clazz)) {
                    map.put(clazz, 1);
                } else {
                    map.put(clazz, map.get(clazz) + 1);
                }
            }
            br.close();
            BufferedWriter bw = new BufferedWriter(
                    new FileWriter("F:\\IDEADEMO\\shujiabigdata\\part\\part---" + flag));
            Set<Map.Entry<String, Integer>> entries = map.entrySet();
            for (Map.Entry<String, Integer> entry : entries) {
                String key = entry.getKey();
                Integer value = entry.getValue();
                bw.write(key + ":" + value);
                bw.newLine();
            }
            bw.flush();
            bw.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

創建Map

import java.io.File;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

public class Map {
    public static void main(String[] args) {
        long start = System.currentTimeMillis();
        // 多執行緒連接池(執行緒池)
        ExecutorService executorService = Executors.newFixedThreadPool(8);
        // 獲取檔案串列
        File file = new File("F:\\IDEADEMO\\shujiabigdata\\split");
        File[] files = file.listFiles();
        //創建多執行緒物件
        int flag = 0;
        for (File f : files) {
            //為每一個檔案啟動一個執行緒
            MapTask mapTask = new MapTask(f, flag);
            executorService.submit(mapTask);
            flag++;
        }
        executorService.shutdown();
        long end = System.currentTimeMillis();
        System.out.println(end-start);
    }
}

創建ClazzSum

import java.io.BufferedReader;
import java.io.FileReader;
import java.util.HashMap;

public class ClazzSum {
    public static void main(String[] args) throws Exception {
        long start = System.currentTimeMillis();
        BufferedReader br = new BufferedReader(
                new FileReader("F:\\IDEADEMO\\shujiabigdata\\data\\bigstudents.txt"));
        String line;
        HashMap<String, Integer> map = new HashMap<String, Integer>();
        while ((line = br.readLine()) != null) {
            String clazz = line.split(",")[4];
            if (!map.containsKey(clazz)) {
                map.put(clazz, 1);
            } else {
                map.put(clazz, map.get(clazz) + 1);
            }
        }
        System.out.println(map);
        long end = System.currentTimeMillis();
        System.out.println(end-start);
    }
}

創建split128

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.util.ArrayList;

public class Split128 {
    public static void main(String[] args) throws Exception {
        BufferedReader br = new BufferedReader(
                new FileReader("F:\\IDEADEMO\\shujiabigdata\\data\\students.txt"));

        //用作標記檔案，也作為檔案名稱
        int index = 0;
        BufferedWriter bw = new BufferedWriter(
                new FileWriter("F:\\IDEADEMO\\shujiabigdata\\split01\\split---" + index));

        ArrayList<String> list = new ArrayList<String>();
        String line;
        //用作累計讀取了多少行資料
        int flag = 0;
        int row = 0;
        while ((line = br.readLine()) != null) {
            list.add(line);
            flag++;
            // flag = 140
            if (flag == 140) {// 一個檔案讀寫完成，生成新的檔案
                row = 0 + 128 * index;
                for (int i = row; i <= row + 127; i++) {
                    bw.write(list.get(i));
                    bw.newLine();
                }
                bw.flush();
                bw.close();
                /**
                 * 生成新的檔案
                 * 計數清零
                 */
                index++;
                flag = 12;
                bw = new BufferedWriter(
                        new FileWriter("F:\\IDEADEMO\\shujiabigdata\\split01\\split---" + index));
            }
        }
        //檔案讀取剩余128*1.1范圍之內
        for (int i = list.size() - flag; i < list.size(); i++) {
            bw.write(list.get(i));
            bw.newLine();
        }
        bw.flush();
        bw.close();
    }
}

創建Reduce

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.HashMap;

public class Reduce {
    public static void main(String[] args) throws Exception {
        long start = System.currentTimeMillis();
        HashMap<String, Integer> map = new HashMap<String, Integer>();
        File file = new File("F:\\IDEADEMO\\shujiabigdata\\part");
        File[] files = file.listFiles();
        for (File f : files) {
            BufferedReader br = new BufferedReader(new FileReader(f));
            String line;
            while ((line = br.readLine()) != null) {
                String clazz = line.split(":")[0];
                int sum = Integer.valueOf(line.split(":")[1]);
                if (!map.containsKey(clazz)) {
                    map.put(clazz, sum);
                } else {
                    map.put(clazz, map.get(clazz) + sum);
                }
            }
        }
        long end = System.currentTimeMillis();
        System.out.println(end-start);
        System.out.println(map);
    }
}

最后將檔案切分了8份，這里采用了執行緒池，建立執行緒連接，多個執行緒同時啟動，比單一檔案采用多執行緒效率更高更好使，