在Java中Iterable gzip放气/充气

Question

是否有隐藏在互联网中的ByteBuffers的gzip泄气库？什么东西可以让我们推送原始数据然后拉出泄气数据？我们搜索过它，但只找到了处理InputStreams和OutputStreams的库。

我们的任务是创建gzip过滤器，用于在管道架构中释放ByteBuffers流。这是一个拉式架构，最后一个元素从以前的元素中提取数据。我们的gzip过滤器处理ByteBuffers流，没有单一的Stream对象可用。

我们已经将数据流调整为某种InputStream，然后使用GZipOutputStream来满足我们的需求，但是适配器代码的数量至少是令人讨厌的。

Post-接受编辑：为了记录在案，我们的架构与GStreamer和其他类似的架构相似。

Answer 1

马克·阿德勒( Mark )提出了这种方法，这比我最初的回答要好得多。

package stack;

import java.io.*;
import java.nio.ByteBuffer;
import java.nio.channels.FileChannel;
import java.util.zip.CRC32;
import java.util.zip.Deflater;

public class BufferDeflate2 {
    /** The standard 10 byte GZIP header */
    private static final byte[] GZIP_HEADER = new byte[] { 0x1f, (byte) 0x8b,
            Deflater.DEFLATED, 0, 0, 0, 0, 0, 0, 0 };

    /** CRC-32 of uncompressed data. */
    private final CRC32 crc = new CRC32();

    /** Deflater to deflate data */
    private final Deflater deflater = new Deflater(Deflater.BEST_COMPRESSION,
            true);

    /** Output buffer building area */
    private final ByteArrayOutputStream buffer = new ByteArrayOutputStream();

    /** Internal transfer space */
    private final byte[] transfer = new byte[1000];

    /** The flush mode to use at the end of each buffer */
    private final int flushMode;


    /**
     * New buffer deflater
     * 
     * @param syncFlush
     *            if true, all data in buffer can be immediately decompressed
     *            from output buffer
     */
    public BufferDeflate2(boolean syncFlush) {
        flushMode = syncFlush ? Deflater.SYNC_FLUSH : Deflater.NO_FLUSH;
        buffer.write(GZIP_HEADER, 0, GZIP_HEADER.length);
    }


    /**
     * Deflate the buffer
     * 
     * @param in
     *            the buffer to deflate
     * @return deflated representation of the buffer
     */
    public ByteBuffer deflate(ByteBuffer in) {
        // convert buffer to bytes
        byte[] inBytes;
        int off = in.position();
        int len = in.remaining();
        if( in.hasArray() ) {
            inBytes = in.array();
        } else {
            off = 0;
            inBytes = new byte[len];
            in.get(inBytes);
        }

        // update CRC and deflater
        crc.update(inBytes, off, len);
        deflater.setInput(inBytes, off, len);

        while( !deflater.needsInput() ) {
            int r = deflater.deflate(transfer, 0, transfer.length, flushMode);
            buffer.write(transfer, 0, r);
        }

        byte[] outBytes = buffer.toByteArray();
        buffer.reset();
        return ByteBuffer.wrap(outBytes);
    }


    /**
     * Write the final buffer. This writes any remaining compressed data and the GZIP trailer.
     * @return the final buffer
     */
    public ByteBuffer doFinal() {
        // finish deflating
        deflater.finish();

        // write all remaining data
        int r;
        do {
            r = deflater.deflate(transfer, 0, transfer.length,
                    Deflater.FULL_FLUSH);
            buffer.write(transfer, 0, r);
        } while( r == transfer.length );

        // write GZIP trailer
        writeInt((int) crc.getValue());
        writeInt((int) deflater.getBytesRead());

        // reset deflater
        deflater.reset();

        // final output
        byte[] outBytes = buffer.toByteArray();
        buffer.reset();
        return ByteBuffer.wrap(outBytes);
    }


    /**
     * Write a 32 bit value in little-endian order
     * 
     * @param v
     *            the value to write
     */
    private void writeInt(int v) {
        System.out.println("v="+v);
        buffer.write(v & 0xff);
        buffer.write((v >> 8) & 0xff);
        buffer.write((v >> 16) & 0xff);
        buffer.write((v >> 24) & 0xff);
    }


    /**
     * For testing. Pass in the name of a file to GZIP compress
     * @param args
     * @throws IOException
     */
    public static void main(String[] args) throws IOException {
        File inFile = new File(args[0]);
        File outFile = new File(args[0]+".test.gz");
        FileChannel inChan = (new FileInputStream(inFile)).getChannel();
        FileChannel outChan = (new FileOutputStream(outFile)).getChannel();

        BufferDeflate2 def = new BufferDeflate2(false);

        ByteBuffer buf = ByteBuffer.allocate(500);
        while( true ) {
            buf.clear();
            int r = inChan.read(buf);
            if( r==-1 ) break;
            buf.flip();
            ByteBuffer compBuf = def.deflate(buf);
            outChan.write(compBuf);
        }

        ByteBuffer compBuf = def.doFinal();
        outChan.write(compBuf);

        inChan.close();
        outChan.close();
    }
}

Answer 2

处理ByteBuffers并不困难。请参阅下面的示例代码。您需要知道缓冲区是如何创建的。备选方案如下：

1. 每个缓冲区都是独立压缩的。这是如此简单的处理，我想这不是这样。您只需将缓冲区转换为字节数组，并将其包装在ByteArrayInputStream中的GZIPInputStream中。
2. 每个缓冲区由写入器以一个SYNC_FLUSH结束，因此包含一个流中的整个数据块。写入缓冲区的所有数据都可以由读取器立即读取。
3. 每个缓冲区只是GZIP流的一部分。不能保证读取器可以从缓冲区读取任何内容。

GZIP生成的数据必须按顺序处理。必须按照生成的顺序处理ByteBuffers。

样本代码：

package stack;

import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.nio.ByteBuffer;
import java.nio.channels.Channels;
import java.nio.channels.Pipe;
import java.nio.channels.SelectableChannel;
import java.util.concurrent.BlockingQueue;
import java.util.concurrent.LinkedBlockingQueue;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.zip.GZIPInputStream;

public class BufferDeflate {

    static AtomicInteger idSrc = new AtomicInteger(1);

    /** Queue for transferring buffers */
    final BlockingQueue<ByteBuffer> buffers = new LinkedBlockingQueue<ByteBuffer>();

    /** The entry point for deflated buffers */
    final Pipe.SinkChannel bufSink;

    /** The source for the inflater */
    final Pipe.SourceChannel infSource;

    /** The destination for the inflater */
    final Pipe.SinkChannel infSink;

    /** The source for the outside world */
    public final SelectableChannel source;



    class Relayer extends Thread {
        public Relayer(int id) {
            super("BufferRelayer" + id);
        }


        public void run() {
            try {
                while( true ) {
                    ByteBuffer buf = buffers.take();
                    if( buf != null ) {
                        bufSink.write(buf);
                    } else {
                        bufSink.close();
                        break;
                    }
                }
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }



    class Inflater extends Thread {
        public Inflater(int id) {
            super("BufferInflater" + id);
        }


        public void run() {
            try {
                InputStream in = Channels.newInputStream(infSource);
                GZIPInputStream gzip = new GZIPInputStream(in);
                OutputStream out = Channels.newOutputStream(infSink);

                int ch;
                while( (ch = gzip.read()) != -1 ) {
                    out.write(ch);
                }
                out.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }


    /**
     * New buffer inflater
     */
    public BufferDeflate() throws IOException {
        Pipe pipe = Pipe.open();
        bufSink = pipe.sink();
        infSource = pipe.source();

        pipe = Pipe.open();
        infSink = pipe.sink();
        source = pipe.source().configureBlocking(false);

        int id = idSrc.incrementAndGet();

        Thread thread = new Relayer(id);
        thread.setDaemon(true);
        thread.start();

        thread = new Inflater(id);
        thread.setDaemon(true);
        thread.start();
    }


    /**
     * Add the buffer to the stream. A null buffer closes the stream
     * 
     * @param buf
     *            the buffer to add
     * @throws IOException
     */
    public void add(ByteBuffer buf) throws IOException {
        buffers.offer(buf);
    }
}

只需将缓冲区传递给add方法并从公共source通道读取即可。在处理给定字节数之后，可以从GZIP读取的数据量是无法预测的。因此，我已经实现了source通道的非阻塞，这样您就可以在添加字节缓冲区的线程中安全地读取它。