java 讀取大數據文件，處理大數據文件性能比較？

通過使用java提供的io，scanner類，apache提供的api處理大文件數據性能分析比較，代碼如下：

package test;

import java.io.BufferedOutputStream;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Reader;
import java.util.Random;
import java.util.Scanner;

import org.apache.commons.io.FileUtils;
import org.apache.commons.io.LineIterator;
import org.junit.Test;

public class TestFile {

    //@Test
    //造數據，測試下面各個方法讀取數據性能
    public void makeFile() throws IOException
    {
        File file = new File("D:\\phone.txt");

        OutputStream os = new BufferedOutputStream(new FileOutputStream(file));
        BufferedWriter bw=new BufferedWriter(new OutputStreamWriter(os));

        //2百萬
        for(int i=0; i < 2000000; i++)
        {
            bw.write(bulidPhone());
            bw.newLine();
        }

        bw.close();
        os.close();
    }

    //生成字符串
    private String bulidPhone()
    {
        Long lo = new Random().nextLong();
        return String.valueOf(lo);
    }

    /**
     * @Title: readTxt1
     * @Description: 使用常規的jdk的io解析輸出文件數據
     * @throws IOException
     */
    @Test
    public void readTxt1() throws IOException
    {
        long start = System.currentTimeMillis();
        File file = new File("D:\\phone.txt");
        Reader in = new FileReader(file);
        BufferedReader br = new BufferedReader(in);
        while(br.ready())
        {
            //System.out.println(br.readLine());
            br.readLine();
        }

        in.close();
        br.close();
        long end = System.currentTimeMillis();
        System.out.println("readTxt1方法，使用內存="+(Runtime.getRuntime().totalMemory()-Runtime.getRuntime().freeMemory())+",使用時間毫秒="+(end-start));
    }

    /**
     * @Title: readTxt2
     * @Description: 使用Scanner掃面文件解析文件數據
     * @throws IOException
     */
    @Test
    public void readTxt2() throws IOException
    {
        long start = System.currentTimeMillis();
        File file = new File("D:\\phone.txt");
        InputStream is = new FileInputStream(file);
        Scanner scan = new Scanner(is,"UTF-8");

        while(scan.hasNextLine())
        {
            //System.out.println(scan.nextLine());
            scan.nextLine();
            //scan.next();
        }

        is.close();
        scan.close();

        long end = System.currentTimeMillis();
        System.out.println("readTxt2方法，使用內存="+(Runtime.getRuntime().totalMemory()-Runtime.getRuntime().freeMemory())+",使用時間毫秒="+(end-start));
    }

    /**
     * @Title: readTxt3
     * @Description: 使用org.apache.commons.io.FileUtils，apache工具類解析文件
     * @throws IOException
     */
    @Test
    public void readTxt3() throws IOException
    {
        long start = System.currentTimeMillis();
        File file = new File("D:\\phone.txt");

        LineIterator it = FileUtils.lineIterator(file, "UTF-8");

        while(it.hasNext())
        {
            it.next();
        }

        it.close();

        long end = System.currentTimeMillis();
        System.out.println("readTxt3方法，使用內存="+(Runtime.getRuntime().totalMemory()-Runtime.getRuntime().freeMemory())+",使用時間毫秒="+(end-start));
    }
}

運行結果如下： 
 

通過分析比較： 獲取【下載地址】  
1.apache的api處理時間最短，但是消耗的內存比jdk的io多。 
2.scanner類表現的最差，銷售內存高，時間久。 
3.傳統的jdk的io處理時間稍長，內存消耗低。