BufferedInputSream实现原理
FileInputSream源码分析
/**
* A <code>FileInputStream</code> obtains input bytes
* from a file in a file system. What files
* are available depends on the host environment.
*
* <p><code>FileInputStream</code> is meant for reading streams of raw bytes
* such as image data. For reading streams of characters, consider using
* <code>FileReader</code>.
*/
public class FileInputSream {
/**
* 从输入流中读取一个字节
* 该方法是native本地方法，这是因为Java不能直接与操作系统或计算机硬件交互，
* 需要通过调用C/C++这样更底层的语言来实现对于磁盘数据的访问
* 对于其他的read()底层就是调用该方法
*/
private native int read0() throws IOException;
public int read() throws IOException {
return read0();
}
/**
*从输入流中读取多个字节到byte数组中
* 这也是后面BufferedInputSream实现的基础
*/
private native int readBytes(byte b[], int off, int len) throws IOException;
public int read(byte b[]) throws IOException {
return readBytes(b, 0, b.length);
}
public int read(byte b[], int off, int len) throws IOException {
return readBytes(b, off, len);
}
}
通过对于FileInputSream的源码分析，如果用read()方法读取以恶搞文件，每读取一个字节就需要访问一次磁盘，这样读取方式是及其低效的。
即使使用read(byte[])方法读取时，虽然在一定程度上可以提升效率，但是当文件特别大时，也会频繁的对磁盘进行访问。为了提高输入流的工作效率，Java提供了BufferedInputSream类。
BufferedInputStream
/**
* A <code>BufferedInputStream</code> adds
* functionality to another input stream-namely,
* the ability to buffer the input and to
* support the <code>mark</code> and <code>reset</code>
* methods. When the <code>BufferedInputStream</code>
* is created, an internal buffer array is
* created. As bytes from the stream are read
* or skipped, the internal buffer is refilled
* as necessary from the contained input stream,
* many bytes at a time. The <code>mark</code>
* operation remembers a point in the input
* stream and the <code>reset</code> operation
* causes all the bytes read since the most
* recent <code>mark</code> operation to be
* reread before new bytes are taken from
* the contained input stream.
*/
public class BufferedInputStream extends FilterInputStream {
//缓冲区数据默认大小，也就是8M
private static int DEFAULT_BUFFER_SIZE = 8192;
/**
* 内部缓冲数组，也就是与底层磁盘读取数据时，一次读取8M的数据存放在该数组中
* 大小默认为8M，也可以通过构造函数修改默认值
*/
protected volatile byte buf[];
/**
* 缓冲区中还没有读取的字节数
* 当count=0时，表示缓冲区内容已经读完，需要再次从磁盘读取来填充
*/
protected int count;
/**
* 缓冲指针，记录缓冲区当前读取位置
* 通过pos与count的比较来判断是否需要填充缓冲数组
*/
protected int pos;
/**
* 构造方法之一
* @param in : 在这里使用的是装饰模式
* @param size ：可以修改默认缓冲区大小
*/
public BufferedInputStream(InputStream in, int size) {
super(in);
if (size <= 0) {
throw new IllegalArgumentException("Buffer size <= 0");
}
buf = new byte[size];
}
private InputStream getInIfOpen() throws IOException {
InputStream input = in;
if (input == null)
throw new IOException("Stream closed");
return input;
}
private byte[] getBufIfOpen() throws IOException {
byte[] buffer = buf;
if (buffer == null)
throw new IOException("Stream closed");
return buffer;
}
/**
* 填充缓冲数组
* @throws IOException
*/
private void fill() throws IOException {
byte[] buffer = getBufIfOpen();
if (markpos < 0)
pos = 0; /* no mark: throw away the buffer */
else if (pos >= buffer.length) /* no room left in buffer */
if (markpos > 0) { /* can throw away early part of the buffer */
int sz = pos - markpos;
System.arraycopy(buffer, markpos, buffer, 0, sz);
pos = sz;
markpos = 0;
} else if (buffer.length >= marklimit) {
markpos = -1; /* buffer got too big, invalidate mark */
pos = 0; /* drop buffer contents */
} else if (buffer.length >= MAX_BUFFER_SIZE) {
throw new OutOfMemoryError("Required array size too large");
} else { /* grow buffer */
int nsz = (pos <= MAX_BUFFER_SIZE - pos) ?
pos * 2 : MAX_BUFFER_SIZE;
if (nsz > marklimit)
nsz = marklimit;
byte nbuf[] = new byte[nsz];
System.arraycopy(buffer, 0, nbuf, 0, pos);
if (!bufUpdater.compareAndSet(this, buffer, nbuf)) {
throw new IOException("Stream closed");
}
buffer = nbuf;
}
count = pos;
//在这里会调用构造方法传递进来的in的read方法读取数据至缓冲数组中
int n = getInIfOpen().read(buffer, pos, buffer.length - pos);
if (n > 0)
count = n + pos;
}
/**
* 读取一个字节
* 与FileInputStream中的read()方法不同的是，这里是从缓冲区数组中读取了一个字节
* 也就是直接从内存中获取的，效率远高于前者
*/
public synchronized int read() throws IOException {
/**
* 如果pos >= count
* 说明缓冲数组中的数据被全部读完，需要再次填充缓冲数组
*/
if (pos >= count) {
fill();
if (pos >= count)
return -1;
}
//直接将缓冲数组中的一个字节的内容返回
return getBufIfOpen()[pos++] & 0xff;
}
/**
* 从缓冲区中一次读取多个字节
* 与上面的原理基本类似
*/
private int read1(byte[] b, int off, int len) throws IOException {
int avail = count - pos;
if (avail <= 0) {
if (len >= getBufIfOpen().length && markpos < 0) {
return getInIfOpen().read(b, off, len);
}
fill();
avail = count - pos;
if (avail <= 0) return -1;
}
int cnt = (avail < len) ? avail : len;
System.arraycopy(getBufIfOpen(), pos, b, off, cnt);
pos += cnt;
return cnt;
}
}