从我的角度来看,java.io.PipedInputStream / java.io.PipedOutputStream是考虑的最佳选择。 在某些情况下,您可能希望使用ByteArrayInputStream / ByteArrayOutputStream。 问题是您需要复制缓冲区以将ByteArrayOutputStream转换为ByteArrayInputStream。 ByteArrayOutpuStream / ByteArrayInputStream也限制为2GB。 这是我编写的OutpuStream / InputStream实现,它绕过了ByteArrayOutputStream / ByteArrayInputStream限制(Scala代码,但对java开发人员来说很容易理解):
import java.io.{IOException, InputStream, OutputStream}
import scala.annotation.tailrec
/** Acts as a replacement for ByteArrayOutputStream
*
*/
class HugeMemoryOutputStream(capacity: Long) extends OutputStream {
private val PAGE_SIZE: Int = 1024000
private val ALLOC_STEP: Int = 1024
/** Pages array
*
*/
private var streamBuffers: Array[Array[Byte]] = Array.empty[Array[Byte]]
/** Allocated pages count
*
*/
private var pageCount: Int = 0
/** Allocated bytes count
*
*/
private var allocatedBytes: Long = 0
/** Current position in stream
*
*/
private var position: Long = 0
/** Stream length
*
*/
private var length: Long = 0
allocSpaceIfNeeded(capacity)
/** Gets page count based on given length
*
* @param length Buffer length
* @return Page count to hold the specified amount of data
*/
private def getPageCount(length: Long) = {
var pageCount = (length / PAGE_SIZE).toInt + 1
if ((length % PAGE_SIZE) == 0) {
pageCount -= 1
}
pageCount
}
/** Extends pages array
*
*/
private def extendPages(): Unit = {
if (streamBuffers.isEmpty) {
streamBuffers = new Array[Array[Byte]](ALLOC_STEP)
}
else {
val newStreamBuffers = new Array[Array[Byte]](streamBuffers.length + ALLOC_STEP)
Array.copy(streamBuffers, 0, newStreamBuffers, 0, streamBuffers.length)
streamBuffers = newStreamBuffers
}
pageCount = streamBuffers.length
}
/** Ensures buffers are bug enough to hold specified amount of data
*
* @param value Amount of data
*/
private def allocSpaceIfNeeded(value: Long): Unit = {
@tailrec
def allocSpaceIfNeededIter(value: Long): Unit = {
val currentPageCount = getPageCount(allocatedBytes)
val neededPageCount = getPageCount(value)
if (currentPageCount < neededPageCount) {
if (currentPageCount == pageCount) extendPages()
streamBuffers(currentPageCount) = new Array[Byte](PAGE_SIZE)
allocatedBytes = (currentPageCount + 1).toLong * PAGE_SIZE
allocSpaceIfNeededIter(value)
}
}
if (value < 0) throw new Error("AllocSpaceIfNeeded < 0")
if (value > 0) {
allocSpaceIfNeededIter(value)
length = Math.max(value, length)
if (position > length) position = length
}
}
/**
* Writes the specified byte to this output stream. The general
* contract for write
is that one byte is written
* to the output stream. The byte to be written is the eight
* low-order bits of the argument b
. The 24
* high-order bits of b
are ignored.
*
* Subclasses of OutputStream
must provide an
* implementation for this method.
*
* @param b the byte
.
*/
@throws[IOException]
override def write(b: Int): Unit = {
val buffer: Array[Byte] = new Array[Byte](1)
buffer(0) = b.toByte
write(buffer)
}
/**
* Writes len
bytes from the specified byte array
* starting at offset off
to this output stream.
* The general contract for write(b, off, len)
is that
* some of the bytes in the array b
are written to the
* output stream in order; element b[off]
is the first
* byte written and b[off+len-1]
is the last byte written
* by this operation.
*
* The write
method of OutputStream
calls
* the write method of one argument on each of the bytes to be
* written out. Subclasses are encouraged to override this method and
* provide a more efficient implementation.
*
* If b
is null
, a
* NullPointerException
is thrown.
*
* If off
is negative, or len
is negative, or
* off+len
is greater than the length of the array
* b
, then an IndexOutOfBoundsException is thrown.
*
* @param b the data.
* @param off the start offset in the data.
* @param len the number of bytes to write.
*/
@throws[IOException]
override def write(b: Array[Byte], off: Int, len: Int): Unit = {
@tailrec
def writeIter(b: Array[Byte], off: Int, len: Int): Unit = {
val currentPage: Int = (position / PAGE_SIZE).toInt
val currentOffset: Int = (position % PAGE_SIZE).toInt
if (len != 0) {
val currentLength: Int = Math.min(PAGE_SIZE - currentOffset, len)
Array.copy(b, off, streamBuffers(currentPage), currentOffset, currentLength)
position += currentLength
writeIter(b, off + currentLength, len - currentLength)
}
}
allocSpaceIfNeeded(position + len)
writeIter(b, off, len)
}
/** Gets an InputStream that points to HugeMemoryOutputStream buffer
*
* @return InputStream
*/
def asInputStream(): InputStream = {
new HugeMemoryInputStream(streamBuffers, length)
}
private class HugeMemoryInputStream(streamBuffers: Array[Array[Byte]], val length: Long) extends InputStream {
/** Current position in stream
*
*/
private var position: Long = 0
/**
* Reads the next byte of data from the input stream. The value byte is
* returned as an int
in the range 0
to
* 255
. If no byte is available because the end of the stream
* has been reached, the value -1
is returned. This method
* blocks until input data is available, the end of the stream is detected,
* or an exception is thrown.
*
*
A subclass must provide an implementation of this method.
*
* @return the next byte of data, or -1
if the end of the
* stream is reached.
*/
@throws[IOException]
def read: Int = {
val buffer: Array[Byte] = new Array[Byte](1)
if (read(buffer) == 0) throw new Error("End of stream")
else buffer(0)
}
/**
* Reads up to len
bytes of data from the input stream into
* an array of bytes. An attempt is made to read as many as
* len
bytes, but a smaller number may be read.
* The number of bytes actually read is returned as an integer.
*
*
This method blocks until input data is available, end of file is
* detected, or an exception is thrown.
*
*
If len
is zero, then no bytes are read and
* 0
is returned; otherwise, there is an attempt to read at
* least one byte. If no byte is available because the stream is at end of
* file, the value -1
is returned; otherwise, at least one
* byte is read and stored into b
.
*
*
The first byte read is stored into element b[off]
, the
* next one into b[off+1]
, and so on. The number of bytes read
* is, at most, equal to len
. Let k be the number of
* bytes actually read; these bytes will be stored in elements
* b[off]
through b[off+
k-1]
,
* leaving elements b[off+
k]
through
* b[off+len-1]
unaffected.
*
*
In every case, elements b[0]
through
* b[off]
and elements b[off+len]
through
* b[b.length-1]
are unaffected.
*
*
The read(b,
off,
len)
method
* for class InputStream
simply calls the method
* read()
repeatedly. If the first such call results in an
* IOException
, that exception is returned from the call to
* the read(b,
off,
len)
method. If
* any subsequent call to read()
results in a
* IOException
, the exception is caught and treated as if it
* were end of file; the bytes read up to that point are stored into
* b
and the number of bytes read before the exception
* occurred is returned. The default implementation of this method blocks
* until the requested amount of input data len
has been read,
* end of file is detected, or an exception is thrown. Subclasses are encouraged
* to provide a more efficient implementation of this method.
*
* @param b the buffer into which the data is read.
* @param off the start offset in array b
* at which the data is written.
* @param len the maximum number of bytes to read.
* @return the total number of bytes read into the buffer, or
* -1
if there is no more data because the end of
* the stream has been reached.
* @see java.io.InputStream#read()
*/
@throws[IOException]
override def read(b: Array[Byte], off: Int, len: Int): Int = {
@tailrec
def readIter(acc: Int, b: Array[Byte], off: Int, len: Int): Int = {
val currentPage: Int = (position / PAGE_SIZE).toInt
val currentOffset: Int = (position % PAGE_SIZE).toInt
val count: Int = Math.min(len, length - position).toInt
if (count == 0 || position >= length) acc
else {
val currentLength = Math.min(PAGE_SIZE - currentOffset, count)
Array.copy(streamBuffers(currentPage), currentOffset, b, off, currentLength)
position += currentLength
readIter(acc + currentLength, b, off + currentLength, len - currentLength)
}
}
readIter(0, b, off, len)
}
/**
* Skips over and discards n
bytes of data from this input
* stream. The skip
method may, for a variety of reasons, end
* up skipping over some smaller number of bytes, possibly 0
.
* This may result from any of a number of conditions; reaching end of file
* before n
bytes have been skipped is only one possibility.
* The actual number of bytes skipped is returned. If n
is
* negative, the skip
method for class InputStream
always
* returns 0, and no bytes are skipped. Subclasses may handle the negative
* value differently.
*
* The skip
method of this class creates a
* byte array and then repeatedly reads into it until n
bytes
* have been read or the end of the stream has been reached. Subclasses are
* encouraged to provide a more efficient implementation of this method.
* For instance, the implementation may depend on the ability to seek.
*
* @param n the number of bytes to be skipped.
* @return the actual number of bytes skipped.
*/
@throws[IOException]
override def skip(n: Long): Long = {
if (n < 0) 0
else {
position = Math.min(position + n, length)
length - position
}
}
}
}
易于使用,没有缓冲区重复,没有2GB内存限制
val out: HugeMemoryOutputStream = new HugeMemoryOutputStream(initialCapacity /*may be 0*/)
out.write(...)
...
val in1: InputStream = out.asInputStream()
in1.read(...)
...
val in2: InputStream = out.asInputStream()
in2.read(...)
...