sstdeserializer.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.hssf.record;

import org.apache.poi.util.BinaryTree;
import org.apache.poi.util.LittleEndian;
import org.apache.poi.util.LittleEndianConsts;

/**
 * Handles the task of deserializing a SST string.  The two main entry points are
 *
 * @author Glen Stampoultzis (glens at apache.org)
 * @author Jason Height (jheight at apache.org)
 */
class SSTDeserializer
{

    private BinaryTree strings;
    /** this is the number of characters that have been read prior to the continuation */
    private int continuationReadChars;
    /** this is the string we were working on before hitting the end of the current record. This string is NOT finished. */
    private String unfinishedString;
    /** this is true if the string uses wide characters */
    private boolean wideChar;
    /** this is true if the string is a rich text string */
    private boolean richText;
    /** this is true if the string is a far east string or some other wierd string */
    private boolean extendedText;
    /** Number of formatting runs in this rich text field */
    private short runCount;
    /** Number of characters in current string */
    private int charCount;
    private int extensionLength;
    private int continueSkipBytes = 0;


    public SSTDeserializer( BinaryTree strings )
    {
        this.strings = strings;
        initVars();
    }

    private void initVars()
    {
        runCount = 0;
        continuationReadChars = 0;
        unfinishedString = "";
//        bytesInCurrentSegment = 0;
//        stringDataOffset = 0;
        wideChar = false;
        richText = false;
        extendedText = false;
        continueSkipBytes = 0;
    }

    /**
     * This is the starting point where strings are constructed.  Note that
     * strings may span across multiple continuations. Read the SST record
     * carefully before beginning to hack.
     */
    public void manufactureStrings( final byte[] data, final int initialOffset)
    {
        initVars();

        int offset = initialOffset;
        final int dataSize = data.length;
        while ( offset < dataSize )
        {
            int remaining = dataSize - offset;

            if ( ( remaining > 0 ) && ( remaining < LittleEndianConsts.SHORT_SIZE ) )
            {
                throw new RecordFormatException( "Cannot get length of the last string in SSTRecord" );
            }
            if ( remaining == LittleEndianConsts.SHORT_SIZE )
            {
              //JMH Dont know about this
                setContinuationCharsRead( 0 );//LittleEndian.getUShort( data, offset ) );
                unfinishedString = "";
                break;
            }
            charCount = LittleEndian.getUShort( data, offset );
            int charsRead = charCount;
            readStringHeader( data, offset );
            boolean stringContinuesOverContinuation = remaining < totalStringSize();
            if ( stringContinuesOverContinuation )
            {
                int remainingBytes = dataSize - offset - stringHeaderOverhead();
                //Only read the size of the string or whatever is left before the
                //continuation
                charsRead = Math.min(charsRead, calculateCharCount( remainingBytes ));
                setContinuationCharsRead( charsRead );                
                if (charsRead == charCount) {
                  //Since all of the characters will have been read, but the entire string (including formatting runs etc)
                  //hasnt, Compute the number of bytes to skip when the continue record starts
                  continueSkipBytes = offsetForContinuedRecord(0) - (remainingBytes - calculateByteCount(charsRead));
                }
            }
            processString( data, offset, charsRead );
            offset += totalStringSize();
            if ( stringContinuesOverContinuation )
            {
                break;
            }
        }
    }

//    private void dump( final byte[] data, int offset, int length )
//    {
//        try
//        {
//            System.out.println( "------------------- SST DUMP -------------------------" );
//            HexDump.dump( (byte[]) data, offset, System.out, offset, length );
//        }
//        catch ( IOException e )
//        {
//        }
//        catch ( ArrayIndexOutOfBoundsException e )
//        {
//        }
//        catch ( IllegalArgumentException e )
//        {
//        }
//    }

    /**
     * Detemines the option types for the string (ie, compressed or uncompressed unicode, rich text string or
     * plain string etc) and calculates the length and offset for the string.
     *
     */
    private void readStringHeader( final byte[] data, final int index )
    {

        byte optionFlag = data[index + LittleEndianConsts.SHORT_SIZE];

        wideChar = ( optionFlag & 1 ) == 1;
        extendedText = ( optionFlag & 4 ) == 4;
        richText = ( optionFlag & 8 ) == 8;
        runCount = 0;
        if ( richText )
        {
            runCount = LittleEndian.getShort( data, index + SSTRecord.STRING_MINIMAL_OVERHEAD );
        }
        extensionLength = 0;
        if ( extendedText )
        {
            extensionLength = LittleEndian.getInt( data, index + SSTRecord.STRING_MINIMAL_OVERHEAD
                    + (richText ? LittleEndianConsts.SHORT_SIZE : 0) );
        }

    }


    /**
     * Reads a string or the first part of a string.
     *
     * @param characters the number of characters to write.
     *
     * @return the number of bytes written.
     */
    private int processString( final byte[] data, final int dataIndex, final int characters )
    {

        // length is the length we store it as.  not the length that is read.
        int length = SSTRecord.STRING_MINIMAL_OVERHEAD + calculateByteCount( characters );
        byte[] unicodeStringBuffer = new byte[length];

        int offset = 0;

        // Set the length in characters
        LittleEndian.putUShort( unicodeStringBuffer, offset, characters );
        offset += LittleEndianConsts.SHORT_SIZE;
        // Set the option flags
        unicodeStringBuffer[offset] = data[dataIndex + offset];
        // Copy in the string data
        int bytesRead = unicodeStringBuffer.length - SSTRecord.STRING_MINIMAL_OVERHEAD;
        arraycopy( data, dataIndex + stringHeaderOverhead(), unicodeStringBuffer, SSTRecord.STRING_MINIMAL_OVERHEAD, bytesRead );
        // Create the unicode string
        UnicodeString string = new UnicodeString( UnicodeString.sid,
                (short) unicodeStringBuffer.length,
                unicodeStringBuffer );
        setContinuationCharsRead( calculateCharCount(bytesRead));

        if ( isStringFinished() )
        {
            Integer integer = new Integer( strings.size() );
            addToStringTable( strings, integer, string );
        }
        else
        {
            unfinishedString = string.getString();
        }

        return bytesRead;
    }

    private boolean isStringFinished()
    {
        return getContinuationCharsRead() == charCount;
    }

    /**
     * Okay, we are doing some major cheating here. Because we can't handle rich text strings properly
     * we end up getting duplicate strings.  To get around this I'm doing two things: 1. Converting rich
     * text to normal text and 2. If there's a duplicate I'm adding a space onto the end.  Sneaky perhaps
     * but it gets the job done until we can handle this a little better.
     */
    static public void addToStringTable( BinaryTree strings, Integer integer, UnicodeString string )
    {

        if ( string.isRichText() )
            string.setOptionFlags( (byte) ( string.getOptionFlags() & ( ~8 ) ) );
        if ( string.isExtendedText() )
            string.setOptionFlags( (byte) ( string.getOptionFlags() & ( ~4 ) ) );

        boolean added = false;
        while ( added == false )
        {
            try
            {
                strings.put( integer, string );
                added = true;
            }
            catch ( Exception ignore )
            {
                string.setString( string.getString() + " " );
            }
        }

    }


    private int calculateCharCount( final int byte_count )
    {
        return byte_count / ( wideChar ? LittleEndianConsts.SHORT_SIZE : LittleEndianConsts.BYTE_SIZE );
    }

    /**
     * Process a Continue record. A Continue record for an SST record