Java读取大文件

原文地址：http://wgslucky.blog.163.com/blog/static/97562532201332324639689/

[b]java 读取一个巨大的文本文件既能保证内存不溢出又能保证性能 [/b]

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.RandomAccessFile;
import java.nio.ByteBuffer;
import java.nio.MappedByteBuffer;
import java.nio.channels.FileChannel;

public class ReadBig {
public static String fff = "C:\\mq\\read\\from.xml";

public static void main1(String[] args) throws Exception {

  final int BUFFER_SIZE = 0x300000;// 缓冲区大小为3M

  File f = new File(fff);

  /**
   * 
   * map(FileChannel.MapMode mode,long position, long size)
   * 
   * mode - 根据是按只读、读取/写入或专用（写入时拷贝）来映射文件，分别为 FileChannel.MapMode 类中所定义的
   * READ_ONLY、READ_WRITE 或 PRIVATE 之一
   * 
   * position - 文件中的位置，映射区域从此位置开始；必须为非负数
   * 
   * size - 要映射的区域大小；必须为非负数且不大于 Integer.MAX_VALUE
   * 
   * 所以若想读取文件后半部分内容，如例子所写；若想读取文本后1/8内容，需要这样写map(FileChannel.MapMode.READ_ONLY,
   * f.length()*7/8,f.length()/8)
   * 
   * 想读取文件所有内容，需要这样写map(FileChannel.MapMode.READ_ONLY, 0,f.length())
   * 
   */

  MappedByteBuffer inputBuffer = new RandomAccessFile(f, "r")
    .getChannel().map(FileChannel.MapMode.READ_ONLY,
      f.length() / 2, f.length() / 2);

  byte[] dst = new byte[BUFFER_SIZE];// 每次读出3M的内容

  long start = System.currentTimeMillis();

  for (int offset = 0; offset < inputBuffer.capacity(); offset += BUFFER_SIZE) {

   if (inputBuffer.capacity() - offset >= BUFFER_SIZE) {

    for (int i = 0; i < BUFFER_SIZE; i++)

     dst[i] = inputBuffer.get(offset + i);

   } else {

    for (int i = 0; i < inputBuffer.capacity() - offset; i++)

     dst[i] = inputBuffer.get(offset + i);

   }

   int length = (inputBuffer.capacity() % BUFFER_SIZE == 0) ? BUFFER_SIZE
     : inputBuffer.capacity() % BUFFER_SIZE;

   System.out.println(new String(dst, 0, length));// new
   // String(dst,0,length)这样可以取出缓存保存的字符串，可以对其进行操作

  }

  long end = System.currentTimeMillis();

  System.out.println("读取文件文件一半内容花费：" + (end - start) + "毫秒");

}

public static void main2(String[] args) throws Exception {
  int bufSize = 1024;
  byte[] bs = new byte[bufSize];
  ByteBuffer byteBuf = ByteBuffer.allocate(1024);
  FileChannel channel = new RandomAccessFile(fff, "r").getChannel();
  while (channel.read(byteBuf) != -1) {
   int size = byteBuf.position();
   byteBuf.rewind();
   byteBuf.get(bs); // 把文件当字符串处理，直接打印做为一个例子。
   System.out.print(new String(bs, 0, size));
   byteBuf.clear();
  }

}

public static void main(String[] args) throws Exception {
  BufferedReader br = new BufferedReader(new FileReader(fff));
  String line = null;
  while ((line = br.readLine()) != null) {
   System.out.println(line);
  }
}

public static void main(String[] args) throws Exception {
    int bufSize = 1024;
    byte[] bs = new byte[bufSize];
    ByteBuffer byteBuf = ByteBuffer.allocate(1024);
    FileChannel channel = new RandomAccessFile("d:\\filename","r").getChannel();
    while(channel.read(byteBuf) != -1) {
      int size = byteBuf.position();
      byteBuf.rewind();
      byteBuf.get(bs);
      // 把文件当字符串处理，直接打印做为一个例子。
      System.out.print(new String(bs, 0, size));
      byteBuf.clear();
    }
  }

}

[b]java 读取大容量文件，内存溢出？怎么按几行读取，读取多次[/b]

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.Scanner;

public class TestPrint {
	public static void main(String[] args) throws IOException {
		String path = "你要读的文件的路径";
		RandomAccessFile br=new RandomAccessFile(path,"rw");//这里rw看你了。要是之都就只写r
		String str = null, app = null;
		int i=0;
		while ((str = br.readLine()) != null) {
			i++;
			app=app+str;
			if(i>=100){//假设读取100行
				i=0;
//				这里你先对这100行操作，然后继续读
app=null;
			}
		}
		br.close();
	}

}

[b]当逐行读写大于2G的文本文件时推荐使用以下代码[/b]

void largeFileIO(String inputFile, String outputFile) {
        try {
            BufferedInputStream bis = new BufferedInputStream(new FileInputStream(new File(inputFile)));
            BufferedReader in = new BufferedReader(new InputStreamReader(bis, "utf-8"), 10 * 1024 * 1024);//10M缓存
            FileWriter fw = new FileWriter(outputFile);
            while (in.ready()) {
                String line = in.readLine();
                fw.append(line + " ");
            }
            in.close();
            fw.flush();
            fw.close();
        } catch (IOException ex) {
            ex.printStackTrace();
        }

[b]jdk本身就支持超大文件的读写[/b]
网上的文章基本分为两大类，一类是使用BufferedReader类读写超大文件；另一类是使用RandomAccessFile类读取，经过比较，最后使用了前一种方式进行超大文件的读取，下面是相关代码，其实很简单

File file = new File(filepath);   
BufferedInputStream fis = new BufferedInputStream(new FileInputStream(file));    
BufferedReader reader = new BufferedReader(new InputStreamReader(fis,"utf-8"),5*1024*1024);// 用5M的缓冲读取文本文件  

String line = "";
while((line = reader.readLine()) != null){
//TODO: write your business
}