Java-读取大文本文件

介绍读取大文本文件的两种方式，避免堆内存溢出。

1.生成测试文件

package com.example.demo;

import org.apache.commons.io.IOUtils;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.List;

/**
 * @author Walker
 * @since 1.0 2018-10-08
 */
public class RandomAccessFileTest {

    public static void main(String[] args) throws IOException {
    	//写文件
        RandomAccessFile randomAccessFile = new RandomAccessFile(new File("C:\\result.txt"), "rw");
        randomAccessFile.seek(randomAccessFile.length());
        long count = 0;
        while (true) {
            randomAccessFile.write(("测试数据" + System.getProperty("line.separator")).getBytes("utf-8"));
            if (count >= Long.MAX_VALUE) {
                break;
            }
            count++;
        }
        randomAccessFile.close();
        //读文件
        List<String> list = IOUtils.readLines(new FileInputStream("C:\\result.txt"), "utf-8");
        System.out.println(list.size());

    }

}

生成测试文件后，调用读取文件的方法将报错。

Exception in thread "main" java.lang.OutOfMemoryError: Java heap space
	at java.util.Arrays.copyOf(Arrays.java:3210)
	at java.util.Arrays.copyOf(Arrays.java:3181)
	at java.util.ArrayList.grow(ArrayList.java:265)
	at java.util.ArrayList.ensureExplicitCapacity(ArrayList.java:239)
	at java.util.ArrayList.ensureCapacityInternal(ArrayList.java:231)
	at java.util.ArrayList.add(ArrayList.java:462)
	at org.apache.commons.io.IOUtils.readLines(IOUtils.java:1461)
	at org.apache.commons.io.IOUtils.readLines(IOUtils.java:1416)
	at org.apache.commons.io.IOUtils.readLines(IOUtils.java:1440)
	at com.example.demo.RandomAccessFileTest.main(RandomAccessFileTest.java:50)

2.使用Apache common-io中的FileUtils类读取文件

package com.example.demo;

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

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;

/**
 * @author Walker
 * @since 1.0 2018-10-08
 */
public class RandomAccessFileTest {

    public static void main(String[] args) throws IOException {
        LineIterator lineIterator = FileUtils.lineIterator(new File("C:\\result.txt"), "utf-8");
        while (lineIterator.hasNext()) {
            String result = lineIterator.next();
            System.out.println(result);
        }
    }

}

3.使用Scanner读取

package com.example.demo;

import java.io.FileInputStream;
import java.io.IOException;
import java.util.Scanner;

/**
 * @author Walker
 * @since 1.0 2018-10-08
 */
public class RandomAccessFileTest {

    public static void main(String[] args) throws IOException {
        FileInputStream fileInputStream = new FileInputStream("C:\\result.txt");
        Scanner scanner = new Scanner(fileInputStream, "utf-8");
        while (scanner.hasNext()) {
            String result = scanner.nextLine();
            System.out.println(result);
        }
        fileInputStream.close();
        scanner.close();
    }

}