NIO - ByteBuffer

ByteBuffer

1、 ByteBuffer 正确使用姿势

1. 向 buffer 写入数据，例如调用 channel.read(buffer)
2. 调用 flip() 切换至读模式
3. 从 buffer 读取数据，例如调用 buffer.get()
4. 调用 clear() 或 compact() 切换至写模式
5. 重复 1~4 步骤

有一普通文本文件 data.txt，内容为

1234567890abcd

使用 FileChannel 来读取文件内容

package com.itcxc.netty.c1;

import lombok.extern.slf4j.Slf4j;

import java.io.FileInputStream;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;

/**
 * @author chenxc
 * @date 2021/8/4 22:01
 */
@Slf4j
public class TsetByteBuffer {

    public static void main(String[] args) {
        //FileChannel
        //获取FileChannel的方式 1、输入输出流 2、RandomAccessFile
        try (FileChannel channel = new FileInputStream("data.txt").getChannel()) {
            //准备缓存区
            ByteBuffer buffer = ByteBuffer.allocate(10);
            while (true) {
                //读取通道中的数据，写入到缓存区中
                int i = channel.read(buffer);
                log.debug("读取到的字节数：{}",i);
                if (i == -1){  //没有内容了
                    break;
                }
                //打印数据
                buffer.flip();  //切换到读模式
                while (buffer.hasRemaining()){  //是否还有剩余未读数据
                    byte b = buffer.get();
                    log.debug("实际字节：{}",(char) b);
                }
                buffer.clear();  //切换到写模型
            }
        } catch (IOException e) {
        }
    }
}

输出

10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 读取到的字节数：10
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：1
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：2
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：3
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：4
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：5
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：6
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：7
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：8
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：9
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：0
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 读取到的字节数：3
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：a
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：b
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 实际字节：c
10:33:55 [DEBUG] [main] c.i.n.c.TsetByteBuffer - 读取到的字节数：-1

2、ByteBuffer 结构

ByteBuffer 有以下重要属性

• capacity
• position
• limit

一开始

写模式下，position 是写入位置，limit 等于容量，下图表示写入了 4 个字节后的状态

flip 动作发生后，position 切换为读取位置，limit 切换为读取限制

读取 4 个字节后，状态

clear 动作发生后，状态

compact 方法，是把未读完的部分向前压缩，然后切换至写模式

💡 调试工具类

public class ByteBufferUtil {
    private static final char[] BYTE2CHAR = new char[256];
    private static final char[] HEXDUMP_TABLE = new char[256 * 4];
    private static final String[] HEXPADDING = new String[16];
    private static final String[] HEXDUMP_ROWPREFIXES = new String[65536 >>> 4];
    private static final String[] BYTE2HEX = new String[256];
    private static final String[] BYTEPADDING = new String[16];

    static {
        final char[] DIGITS = "0123456789abcdef".toCharArray();
        for (int i = 0; i < 256; i++) {
            HEXDUMP_TABLE[i << 1] = DIGITS[i >>> 4 & 0x0F];
            HEXDUMP_TABLE[(i << 1) + 1] = DIGITS[i & 0x0F];
        }

        int i;

        // Generate the lookup table for hex dump paddings
        for (i = 0; i < HEXPADDING.length; i++) {
            int padding = HEXPADDING.length - i;
            StringBuilder buf = new StringBuilder(padding * 3);
            for (int j = 0; j < padding; j++) {
                buf.append("   ");
            }
            HEXPADDING[i] = buf.toString();
        }

        // Generate the lookup table for the start-offset header in each row (up to 64KiB).
        for (i = 0; i < HEXDUMP_ROWPREFIXES.length; i++) {
            StringBuilder buf = new StringBuilder(12);
            buf.append(NEWLINE);
            buf.append(Long.toHexString(i << 4 & 0xFFFFFFFFL | 0x100000000L));
            buf.setCharAt(buf.length() - 9, '|');
            buf.append('|');
            HEXDUMP_ROWPREFIXES[i] = buf.toString();
        }

        // Generate the lookup table for byte-to-hex-dump conversion
        for (i = 0; i < BYTE2HEX.length; i++) {
            BYTE2HEX[i] = ' ' + StringUtil.byteToHexStringPadded(i);
        }

        // Generate the lookup table for byte dump paddings
        for (i = 0; i < BYTEPADDING.length; i++) {
            int padding = BYTEPADDING.length - i;
            StringBuilder buf = new StringBuilder(padding);
            for (int j = 0; j < padding; j++) {
                buf.append(' ');
            }
            BYTEPADDING[i] = buf.toString();
        }

        // Generate the lookup table for byte-to-char conversion
        for (i = 0; i < BYTE2CHAR.length; i++) {
            if (i <= 0x1f || i >= 0x7f) {
                BYTE2CHAR[i] = '.';
            } else {
                BYTE2CHAR[i] = (char) i;
            }
        }
    }

    /**
     * 打印所有内容
     * @param buffer
     */
    public static void debugAll(ByteBuffer buffer) {
        int oldlimit = buffer.limit();
        buffer.limit(buffer.capacity());
        StringBuilder origin = new StringBuilder(256);
        appendPrettyHexDump(origin, buffer, 0, buffer.capacity());
        System.out.println("+--------+-------------------- all ------------------------+----------------+");
        System.out.printf("position: [%d], limit: [%d]\n", buffer.position(), oldlimit);
        System.out.println(origin);
        buffer.limit(oldlimit);
    }

    /**
     * 打印可读取内容
     * @param buffer
     */
    public static void debugRead(ByteBuffer buffer) {
        StringBuilder builder = new StringBuilder(256);
        appendPrettyHexDump(builder, buffer, buffer.position(), buffer.limit() - buffer.position());
        System.out.println("+--------+-------------------- read -----------------------+----------------+");
        System.out.printf("position: [%d], limit: [%d]\n", buffer.position(), buffer.limit());
        System.out.println(builder);
    }

    private static void appendPrettyHexDump(StringBuilder dump, ByteBuffer buf, int offset, int length) {
        if (isOutOfBounds(offset, length, buf.capacity())) {
            throw new IndexOutOfBoundsException(
                    "expected: " + "0 <= offset(" + offset + ") <= offset + length(" + length
                            + ") <= " + "buf.capacity(" + buf.capacity() + ')');
        }
        if (length == 0) {
            return;
        }
        dump.append(
                "         +-------------------------------------------------+" +
                        NEWLINE + "         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |" +
                        NEWLINE + "+--------+-------------------------------------------------+----------------+");

        final int startIndex = offset;
        final int fullRows = length >>> 4;
        final int remainder = length & 0xF;

        // Dump the rows which have 16 bytes.
        for (int row = 0; row < fullRows; row++) {
            int rowStartIndex = (row << 4) + startIndex;

            // Per-row prefix.
            appendHexDumpRowPrefix(dump, row, rowStartIndex);

            // Hex dump
            int rowEndIndex = rowStartIndex + 16;
            for (int j = rowStartIndex; j < rowEndIndex; j++) {
                dump.append(BYTE2HEX[getUnsignedByte(buf, j)]);
            }
            dump.append(" |");

            // ASCII dump
            for (int j = rowStartIndex; j < rowEndIndex; j++) {
                dump.append(BYTE2CHAR[getUnsignedByte(buf, j)]);
            }
            dump.append('|');
        }

        // Dump the last row which has less than 16 bytes.
        if (remainder != 0) {
            int rowStartIndex = (fullRows << 4) + startIndex;
            appendHexDumpRowPrefix(dump, fullRows, rowStartIndex);

            // Hex dump
            int rowEndIndex = rowStartIndex + remainder;
            for (int j = rowStartIndex; j < rowEndIndex; j++) {
                dump.append(BYTE2HEX[getUnsignedByte(buf, j)]);
            }
            dump.append(HEXPADDING[remainder]);
            dump.append(" |");

            // Ascii dump
            for (int j = rowStartIndex; j < rowEndIndex; j++) {
                dump.append(BYTE2CHAR[getUnsignedByte(buf, j)]);
            }
            dump.append(BYTEPADDING[remainder]);
            dump.append('|');
        }

        dump.append(NEWLINE +
                "+--------+-------------------------------------------------+----------------+");
    }

    private static void appendHexDumpRowPrefix(StringBuilder dump, int row, int rowStartIndex) {
        if (row < HEXDUMP_ROWPREFIXES.length) {
            dump.append(HEXDUMP_ROWPREFIXES[row]);
        } else {
            dump.append(NEWLINE);
            dump.append(Long.toHexString(rowStartIndex & 0xFFFFFFFFL | 0x100000000L));
            dump.setCharAt(dump.length() - 9, '|');
            dump.append('|');
        }
    }

    public static short getUnsignedByte(ByteBuffer buffer, int index) {
        return (short) (buffer.get(index) & 0xFF);
    }
}

3 ByteBuffer 常见方法

3.1 分配空间

可以使用 allocate 方法为 ByteBuffer 分配空间，其它 buffer 类也有该方法

Bytebuffer heapByteBuffer= ByteBuffer.allocate(16);
Bytebuffer directByteBuffer  = ByteBuffer.allocateDirect(16).getClass()
/**
* class java.nio.HeapByteBuffer  Java堆内存，读写效率较低，受到GC的影响
* class java.nio.DirectByteBuffer  直接内存(操作系统分配的)，读写效率高(少一次拷贝)，不受GC影响，分配效率低(就是创建慢)，要自己释放
*/

3.2 向 buffer 写入数据

有两种办法

• 调用 channel 的 read 方法
• 调用 buffer 自己的 put 方法

int readBytes = channel.read(buf);

和

buf.put((byte)127);

3.3 从 buffer 读取数据

同样有两种办法

• 调用 channel 的 write 方法
• 调用 buffer 自己的 get 方法

int writeBytes = channel.write(buf);

和

byte b = buf.get();

get 方法会让 position 读指针向后走，如果想重复读取数据

• 可以调用 rewind 方法将 position 重新置为 0
• 或者调用 get(int i) 方法获取索引 i 的内容，它不会移动读指针

3.4 mark 和 reset

mark 是在读取时，做一个标记，即使 position 改变，只要调用 reset 就能回到 mark 的位置

package com.itcxc.netty.c1;

import java.nio.ByteBuffer;

/**
 * @author chenxc
 * @date 2021/8/5 22:41
 */
public class TsetByteBufferRead {

    public static void main(String[] args) {
        ByteBuffer buffer = ByteBuffer.allocate(10);
        buffer.put(new byte[]{'a','b','c','d'});
        buffer.flip();

        buffer.get(new byte[4]);
        ByteBufferUtil.debugAll(buffer);
        //重头开始读
        buffer.rewind();
        System.out.println((char) buffer.get());
        ByteBufferUtil.debugAll(buffer);

        //mark & reset  mark做一个标记，记录position的位置，reset将position重置到mark的位置
        buffer.mark();  //加标记
        buffer.get(new byte[3]);
        ByteBufferUtil.debugAll(buffer);
        buffer.reset(); //返回到标记的位置
        ByteBufferUtil.debugAll(buffer);

        //读取指定位置，不会影响position的位置
        System.out.println(buffer.get(2));

    }
}

结果

+--------+-------------------- all ------------------------+----------------+
position: [4], limit: [4]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 61 62 63 64 00 00 00 00 00 00                   |abcd......      |
+--------+-------------------------------------------------+----------------+
a
+--------+-------------------- all ------------------------+----------------+
position: [1], limit: [4]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 61 62 63 64 00 00 00 00 00 00                   |abcd......      |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [4], limit: [4]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 61 62 63 64 00 00 00 00 00 00                   |abcd......      |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [1], limit: [4]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 61 62 63 64 00 00 00 00 00 00                   |abcd......      |
+--------+-------------------------------------------------+----------------+
99

注意

rewind 和 flip 都会清除 mark 位置

3.5字符串与 ByteBuffer 互转

package com.itcxc.netty.c1;

import java.nio.ByteBuffer;
import java.nio.charset.StandardCharsets;

/**
 * @author chenxc
 * @date 2021/8/5 22:58
 */
public class TsetByteBufferString {

    public static void main(String[] args) {
        //1.字符串转为ByteBuffer
        //1.1 写入
        ByteBuffer buffer = ByteBuffer.allocate(10);
        byte[] bytes = "中国".getBytes(StandardCharsets.UTF_8);
        buffer.put(bytes);
        ByteBufferUtil.debugAll(buffer);
        //1.2 Charset  直接切为读模式
        ByteBuffer buffer1 = StandardCharsets.UTF_8.encode("中国");
        ByteBufferUtil.debugAll(buffer1);
        //1.3 wrap  直接切为读模式
        ByteBuffer buffer2 = ByteBuffer.wrap("中国".getBytes(StandardCharsets.UTF_8));
        ByteBufferUtil.debugAll(buffer2);
        //2.ByteBuffer转为字符串
        buffer.flip();  //要先切换为读模式
        System.out.println(StandardCharsets.UTF_8.decode(buffer).toString());

        System.out.println(StandardCharsets.UTF_8.decode(buffer1).toString());

        System.out.println(StandardCharsets.UTF_8.decode(buffer2).toString());

    }
}

输出

+--------+-------------------- all ------------------------+----------------+
position: [6], limit: [10]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| e4 b8 ad e5 9b bd 00 00 00 00                   |..........      |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [0], limit: [6]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| e4 b8 ad e5 9b bd 00 00 00 00 00                |...........     |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [0], limit: [6]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| e4 b8 ad e5 9b bd                               |......          |
+--------+-------------------------------------------------+----------------+
中国
中国
中国

Process finished with exit code 0

3.6 ⚠️ Buffer 的线程安全

Buffer 是非线程安全的

4 Scattering Reads

分散读取，有一个文本文件 words.txt

onetwothree

使用如下方式读取，可以将数据填充至多个 buffer

package com.itcxc.netty.c1;

import java.io.IOException;
import java.io.RandomAccessFile;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;

/**
 * @author chenxc
 * @date 2021/8/5 23:24
 */
public class TsetScatteringReads {

    public static void main(String[] args) {
        //分别读取
        try (FileChannel channel = new RandomAccessFile("words.txt", "r").getChannel()) {
            ByteBuffer b1 = ByteBuffer.allocate(3);
            ByteBuffer b2 = ByteBuffer.allocate(3);
            ByteBuffer b3 = ByteBuffer.allocate(5);
            channel.read(new ByteBuffer[]{b1,b2,b3});
            ByteBufferUtil.debugAll(b1);
            ByteBufferUtil.debugAll(b2);
            ByteBufferUtil.debugAll(b3);
        } catch (IOException e) {
        }
    }
}

结果

+--------+-------------------- all ------------------------+----------------+
position: [3], limit: [3]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 6f 6e 65                                        |one             |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [3], limit: [3]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 74 77 6f                                        |two             |
+--------+-------------------------------------------------+----------------+
+--------+-------------------- all ------------------------+----------------+
position: [5], limit: [5]
         +-------------------------------------------------+
         |  0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f |
+--------+-------------------------------------------------+----------------+
|00000000| 74 68 72 65 65                                  |three           |
+--------+-------------------------------------------------+----------------+

5 Gathering Writes

使用如下方式写入，可以将多个 buffer 的数据填充至 channel

package com.itcxc.netty.c1;

import java.io.IOException;
import java.io.RandomAccessFile;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;
import java.nio.charset.StandardCharsets;

/**
 * @author chenxc
 * @date 2021/8/5 23:29
 */
public class TsetGatheringWrites {

    public static void main(String[] args) {
        //集中写
        ByteBuffer b1 = StandardCharsets.UTF_8.encode("hello");
        ByteBuffer b2 = StandardCharsets.UTF_8.encode("world");
        ByteBuffer b3 = StandardCharsets.UTF_8.encode("你好");

        try (FileChannel channel = new RandomAccessFile("words1.txt", "rw").getChannel()) {
            channel.write(new ByteBuffer[]{b1,b2,b3});
        } catch (IOException e) {
        }
    }
}

文件内容

helloworld你好

6 练习

网络上有多条数据发送给服务端，数据之间使用 \n 进行分隔
但由于某种原因这些数据在接收时，被进行了重新组合，例如原始数据有3条为

• Hello,world\n
• I’m zhangsan\n
• How are you?\n

变成了下面的两个 byteBuffer (黏包，半包)

• Hello,world\nI’m zhangsan\nHo
• w are you?\n

现在要求你编写程序，将错乱的数据恢复成原始的按 \n 分隔的数据

package com.itcxc.netty.c1;

import java.nio.ByteBuffer;
import java.nio.charset.StandardCharsets;

/**
 * @author chenxc
 * @date 2021/8/5 23:38
 */
public class TsetByteBufferExam {

    public static void main(String[] args) {
        
        ByteBuffer buffer = ByteBuffer.allocate(32);

        buffer.put("Hello World\nI'm zhangsan\nHo".getBytes(StandardCharsets.UTF_8));
        split(buffer);
        buffer.put("w are you?\nhaha!\n".getBytes(StandardCharsets.UTF_8));
        split(buffer);

    }

    private static void split(ByteBuffer source) {
        source.flip();
        for (int i = 0; i < source.limit(); i++) {
            if (source.get(i) == '\n'){
                int length = i + 1 - source.position();
                ByteBuffer buffer = ByteBuffer.allocate(length);
                for (int j = 0; j < length; j++) {
                    buffer.put(source.get());
                }
                //ByteBufferUtil.debugAll(buffer);
                buffer.flip();
                System.out.println(StandardCharsets.UTF_8.decode(buffer).toString());
            }
        }
        source.compact();
    }
}

结果

Hello World

I'm zhangsan

How are you?

haha!