documentinputstream.java

Office格式转换代码

/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2003 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" and
 *    "Apache POI" must not be used to endorse or promote products
 *    derived from this software without prior written permission. For
 *    written permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    "Apache POI", nor may "Apache" appear in their name, without
 *    prior written permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

package org.apache.poi.poifs.filesystem;

import java.io.*;

/**
 * This class provides methods to read a DocumentEntry managed by a
 * Filesystem instance.
 *
 * @author Marc Johnson (mjohnson at apache dot org)
 */

public class DocumentInputStream
    extends InputStream
{

    // current offset into the Document
    private int              _current_offset;

    // current marked offset into the Document (used by mark and
    // reset)
    private int              _marked_offset;

    // the Document's size
    private int              _document_size;

    // have we been closed?
    private boolean          _closed;

    // the actual Document
    private POIFSDocument    _document;

    // buffer used to read one byte at a time
    private byte[]           _tiny_buffer;

    // returned by read operations if we're at end of document
    static private final int EOD = -1;

    /**
     * Create an InputStream from the specified DocumentEntry
     *
     * @param document the DocumentEntry to be read
     *
     * @exception IOException if the DocumentEntry cannot be opened
     *            (like, maybe it has been deleted?)
     */

    public DocumentInputStream(final DocumentEntry document)
        throws IOException
    {
        _current_offset = 0;
        _marked_offset  = 0;
        _document_size  = document.getSize();
        _closed         = false;
        _tiny_buffer    = null;
        if (document instanceof DocumentNode)
        {
            _document = (( DocumentNode ) document).getDocument();
        }
        else
        {
            throw new IOException("Cannot open internal document storage");
        }
    }

    /**
     * Create an InputStream from the specified Document
     *
     * @param document the Document to be read
     *
     * @exception IOException if the DocumentEntry cannot be opened
     *            (like, maybe it has been deleted?)
     */

    public DocumentInputStream(final POIFSDocument document)
        throws IOException
    {
        _current_offset = 0;
        _marked_offset  = 0;
        _document_size  = document.getSize();
        _closed         = false;
        _tiny_buffer    = null;
        _document       = document;
    }

    /**
     * Returns the number of bytes that can be read (or skipped over)
     * from this input stream without blocking by the next caller of a
     * method for this input stream. The next caller might be the same
     * thread or or another thread.
     *
     * @return the number of bytes that can be read from this input
     *         stream without blocking.
     *
     * @exception IOException on error (such as the stream has been
     *            closed)
     */

    public int available()
        throws IOException
    {
        dieIfClosed();
        return _document_size - _current_offset;
    }

    /**
     * Closes this input stream and releases any system resources
     * associated with the stream.
     *
     * @exception IOException
     */

    public void close()
        throws IOException
    {
        _closed = true;
    }

    /**
     * Marks the current position in this input stream. A subsequent
     * call to the reset method repositions this stream at the last
     * marked position so that subsequent reads re-read the same
     * bytes.
     * <p>
     * The readlimit arguments tells this input stream to allow that
     * many bytes to be read before the mark position gets
     * invalidated. This implementation, however, does not care.
     * <p>
     * The general contract of mark is that, if the method
     * markSupported returns true, the stream somehow remembers all
     * the bytes read after the call to mark and stands ready to
     * supply those same bytes again if and whenever the method reset
     * is called. However, the stream is not required to remember any
     * data at all if more than readlimit bytes are read from the
     * stream before reset is called. But this stream will.
     *
     * @param ignoredReadlimit the maximum limit of bytes that can be
     *                         read before the mark position becomes
     *                         invalid. Ignored by this
     *                         implementation.
     */

    public void mark(int ignoredReadlimit)
    {
        _marked_offset = _current_offset;
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *
     * @return true
     */

    public boolean markSupported()
    {
        return true;
    }

    /**
     * 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. The definition of this method in
     * java.io.InputStream allows this method to block, but it won't.
     *
     * @return the next byte of data, or -1 if the end of the stream
     *         is reached.
     *
     * @exception IOException
     */

    public int read()
        throws IOException
    {
        dieIfClosed();
        if (atEOD())
        {
            return EOD;
        }
        if (_tiny_buffer == null)
        {
            _tiny_buffer = new byte[ 1 ];
        }
        _document.read(_tiny_buffer, _current_offset++);
        return ((int)_tiny_buffer[ 0 ]) & 0x000000FF;
    }

    /**
     * Reads some number of bytes from the input stream and stores
     * them into the buffer array b. The number of bytes actually read