sstrecord.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;

import java.util.Iterator;
import java.util.List;

/**
 * Title:        Static String Table Record
 * <P>
 * Description:  This holds all the strings for LabelSSTRecords.
 * <P>
 * REFERENCE:    PG 389 Microsoft Excel 97 Developer's Kit (ISBN:
 *               1-57231-498-2)
 * <P>
 * @author Andrew C. Oliver (acoliver at apache dot org)
 * @author Marc Johnson (mjohnson at apache dot org)
 * @author Glen Stampoultzis (glens at apache.org)
 *
 * @see org.apache.poi.hssf.record.LabelSSTRecord
 * @see org.apache.poi.hssf.record.ContinueRecord
 */

public class SSTRecord
        extends Record
{

    /** how big can an SST record be? As big as any record can be: 8228 bytes */
    static final int MAX_RECORD_SIZE = 8228;

    /** standard record overhead: two shorts (record id plus data space size)*/
    static final int STD_RECORD_OVERHEAD =
            2 * LittleEndianConsts.SHORT_SIZE;

    /** SST overhead: the standard record overhead, plus the number of strings and the number of unique strings -- two ints */
    static final int SST_RECORD_OVERHEAD =
            ( STD_RECORD_OVERHEAD + ( 2 * LittleEndianConsts.INT_SIZE ) );

    /** how much data can we stuff into an SST record? That would be _max minus the standard SST record overhead */
    static final int MAX_DATA_SPACE = MAX_RECORD_SIZE - SST_RECORD_OVERHEAD;

    /** overhead for each string includes the string's character count (a short) and the flag describing its characteristics (a byte) */
    static final int STRING_MINIMAL_OVERHEAD = LittleEndianConsts.SHORT_SIZE + LittleEndianConsts.BYTE_SIZE;

    public static final short sid = 0xfc;

    /** union of strings in the SST and EXTSST */
    private int field_1_num_strings;

    /** according to docs ONLY SST */
    private int field_2_num_unique_strings;
    private BinaryTree field_3_strings;

    /** Record lengths for initial SST record and all continue records */
    private List _record_lengths = null;
    private SSTDeserializer deserializer;

    /** Offsets from the beginning of the SST record (even across continuations) */
    int[] bucketAbsoluteOffsets;
    /** Offsets relative the start of the current SST or continue record */
    int[] bucketRelativeOffsets;

    /**
     * default constructor
     */
    public SSTRecord()
    {
        field_1_num_strings = 0;
        field_2_num_unique_strings = 0;
        field_3_strings = new BinaryTree();
        deserializer = new SSTDeserializer(field_3_strings);
    }

    /**
     * Constructs an SST record and sets its fields appropriately.
     *
     * @param id must be 0xfc or an exception will be throw upon
     *           validation
     * @param size the size of the data area of the record
     * @param data of the record (should not contain sid/len)
     */

    public SSTRecord( final short id, final short size, final byte[] data )
    {
        super( id, size, data );
    }

    /**
     * Constructs an SST record and sets its fields appropriately.
     *
     * @param id must be 0xfc or an exception will be throw upon
     *           validation
     * @param size the size of the data area of the record
     * @param data of the record (should not contain sid/len)
     * @param offset of the record
     */

    public SSTRecord( final short id, final short size, final byte[] data,
                      int offset )
    {
        super( id, size, data, offset );
    }

    /**
     * Add a string. Determines whether 8-bit encoding can be used, or
     * whether 16-bit encoding must be used.
     * <p>
     * THIS IS THE PREFERRED METHOD OF ADDING A STRING. IF YOU USE THE
     * OTHER ,code>addString</code> METHOD AND FORCE 8-BIT ENCODING ON
     * A STRING THAT SHOULD USE 16-BIT ENCODING, YOU WILL CORRUPT THE
     * STRING; IF YOU USE THAT METHOD AND FORCE 16-BIT ENCODING, YOU
     * ARE WASTING SPACE WHEN THE WORKBOOK IS WRITTEN OUT.
     *
     * @param string string to be added
     *
     * @return the index of that string in the table
     */

    public int addString( final String string )
    {
        int rval;

        if ( string == null )
        {
            rval = addString( "", false );
        }
        else
        {

            // scan for characters greater than 255 ... if any are
            // present, we have to use 16-bit encoding. Otherwise, we
            // can use 8-bit encoding
            boolean useUTF16 = false;
            int strlen = string.length();

            for ( int j = 0; j < strlen; j++ )
            {
                if ( string.charAt( j ) > 255 )
                {
                    useUTF16 = true;
                    break;
                }
            }
            rval = addString( string, useUTF16 );
        }
        return rval;
    }

    /**
     * Add a string and assert the encoding (8-bit or 16-bit) to be
     * used.
     * <P>
     * USE THIS METHOD AT YOUR OWN RISK. IF YOU FORCE 8-BIT ENCODING,
     * YOU MAY CORRUPT YOUR STRING. IF YOU FORCE 16-BIT ENCODING AND
     * IT ISN'T NECESSARY, YOU WILL WASTE SPACE WHEN THIS RECORD IS
     * WRITTEN OUT.
     *
     * @param string string to be added
     * @param useUTF16 if true, forces 16-bit encoding. If false,
     *                 forces 8-bit encoding
     *
     * @return the index of that string in the table
     */

    public int addString( final String string, final boolean useUTF16 )
    {
        field_1_num_strings++;
        String str = ( string == null ) ? ""
                : string;
        int rval;
        UnicodeString ucs = new UnicodeString();

        ucs.setString( str );
        ucs.setCharCount( (short) str.length() );
        ucs.setOptionFlags( (byte) ( useUTF16 ? 1
                : 0 ) );
        Integer integer = (Integer) field_3_strings.getKeyForValue( ucs );

        if ( integer != null )
        {
            rval = integer.intValue();
        }
        else
        {

            // This is a new string -- we didn't see it among the
            // strings we've already collected
            rval = field_3_strings.size();
            field_2_num_unique_strings++;
            integer = new Integer( rval );
            SSTDeserializer.addToStringTable( field_3_strings, integer, ucs );
//            field_3_strings.put( integer, ucs );
        }
        return rval;
    }

    /**
     * @return number of strings
     */

    public int getNumStrings()
    {
        return field_1_num_strings;
    }

    /**
     * @return number of unique strings
     */

    public int getNumUniqueStrings()
    {
        return field_2_num_unique_strings;
    }

    /**
     * USE THIS METHOD AT YOUR OWN PERIL: THE <code>addString</code>
     * METHODS MANIPULATE THE NUMBER OF STRINGS AS A SIDE EFFECT; YOUR
     * ATTEMPTS AT MANIPULATING THE STRING COUNT IS LIKELY TO BE VERY
     * WRONG AND WILL RESULT IN BAD BEHAVIOR WHEN THIS RECORD IS
     * WRITTEN OUT AND ANOTHER PROCESS ATTEMPTS TO READ THE RECORD
     *
     * @param count  number of strings
     *
     */

    public void setNumStrings( final int count )
    {
        field_1_num_strings = count;
    }

    /**
     * USE THIS METHOD AT YOUR OWN PERIL: THE <code>addString</code>
     * METHODS MANIPULATE THE NUMBER OF UNIQUE STRINGS AS A SIDE
     * EFFECT; YOUR ATTEMPTS AT MANIPULATING THE UNIQUE STRING COUNT
     * IS LIKELY TO BE VERY WRONG AND WILL RESULT IN BAD BEHAVIOR WHEN
     * THIS RECORD IS WRITTEN OUT AND ANOTHER PROCESS ATTEMPTS TO READ
     * THE RECORD
     *
     * @param count  number of strings
     */