worddocument.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.hdf.extractor;


import org.apache.poi.hdf.extractor.util.*;
import org.apache.poi.hdf.extractor.data.*;
import java.util.*;
import java.io.*;
import javax.swing.*;

import java.awt.*;

import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.poifs.filesystem.POIFSDocument;
import org.apache.poi.poifs.filesystem.DocumentEntry;

import org.apache.poi.util.LittleEndian;

/**
 * This class contains the main functionality for the Word file "reader". Much
 * of the code in this class is based on the Word 97 document file format. Only
 * works for non-complex files
 *
 * @author Ryan Ackley
 */

public class WordDocument
{
  /** byte buffer containing the main Document stream*/
  byte[] _header;
  /** contains all style information for this document see Word 97 Doc spec*/
  StyleSheet _styleSheet;
  /** contains All list information for this document*/
  ListTables _listTables;
  /** contains global Document properties for this document*/
  DOP _docProps = new DOP();

  int _currentList = -1;
  int _tableSize;
  int _sectionCounter = 1;
  /** fonts available for this document*/
  FontTable _fonts;

  /** document's text blocks*/
  BTreeSet _text = new BTreeSet();
  /** document's character runs */
  BTreeSet _characterTable = new BTreeSet();
  /** document's paragraphs*/
  BTreeSet _paragraphTable = new BTreeSet();
  /** doucment's sections*/
  BTreeSet _sectionTable = new BTreeSet();

  /** used for XSL-FO conversion*/
  StringBuffer _headerBuffer = new StringBuffer();
  /** used for XSL-FO conversion*/
  StringBuffer _bodyBuffer = new StringBuffer();
  /** used for XSL-FO table conversion*/
  StringBuffer _cellBuffer;
  /** used for XSL-FO table conversion*/
  ArrayList _cells;
  /** used for XSL-FO table conversion*/
  ArrayList _table;

  /** document's header and footer information*/
  byte[] _plcfHdd;

  /** starting position of text in main document stream*/
  int _fcMin;
  /** length of main document text stream*/
  int _ccpText;
  /** length of footnotes text*/
  int _ccpFtn;

  /** The name of the file to write to */
  private static String _outName;

  /** OLE stuff*/
  private InputStream istream;
  /** OLE stuff*/
  private POIFSFileSystem filesystem;

  //used internally
  private static int HEADER_EVEN_INDEX = 0;
  private static int HEADER_ODD_INDEX = 1;
  private static int FOOTER_EVEN_INDEX = 2;
  private static int FOOTER_ODD_INDEX = 3;
  private static int HEADER_FIRST_INDEX = 4;
  private static int FOOTER_FIRST_INDEX = 5;

  /**
   *  right now this function takes one parameter: a Word file, and outputs an
   *  XSL-FO document at c:\test.xml (this is hardcoded)
   */
  public static void main(String args[])
  {
      /*try
      {
        WordDocument file = new WordDocument(args[0], "r");
        Writer out = new BufferedWriter(new FileWriter(args[1]));
        file.writeAllText(out);
        out.flush();
        out.close();
      }
      catch(Throwable t)
      {
        t.printStackTrace();
      }*/
      try
      {
          _outName = args[1];
          WordDocument file = new WordDocument(args[0]);
          file.closeDoc();
      }
      catch(Exception e)
      {
          e.printStackTrace();
      }
      System.exit(0);
  }
  /**
   * Spits out the document text
   *
   * @param out The Writer to write the text to.
   * @throws IOException if there is a problem while reading from the file or
   *         writing out the text.
   */
  public void writeAllText(Writer out) throws IOException
  {
    int textStart = Utils.convertBytesToInt(_header, 0x18);
    int textEnd = Utils.convertBytesToInt(_header, 0x1c);
    ArrayList textPieces = findProperties(textStart, textEnd, _text.root);
    int size = textPieces.size();

    for(int x = 0; x < size; x++)
    {
      TextPiece nextPiece = (TextPiece)textPieces.get(x);
      int start = nextPiece.getStart();
      int end = nextPiece.getEnd();
      boolean unicode = nextPiece.usesUnicode();
      int add = 1;

      if(unicode)
      {
        add = 2;
        char ch;
        for(int y = start; y < end; y += add)
        {
	  ch = (char)Utils.convertBytesToShort(_header, y);
	  out.write(ch);
        }
      }
      else
      {
	String sText = new String(_header, start, end-start);
	out.write(sText);
      }
    }
  }
  /**
   * Constructs a Word document from fileName. Parses the document and places
   * all the important stuff into data structures.
   *
   * @param fileName The name of the file to read.
   * @throws IOException if there is a problem while parsing the document.
   */
  public WordDocument(String fileName) throws IOException
  {
  	this(new FileInputStream(fileName));
  }
  
  public WordDocument(InputStream inputStream) throws IOException
  {
        //do Ole stuff
        istream = inputStream;
        filesystem = new POIFSFileSystem(istream);

        //get important stuff from the Header block and parse all the
        //data structures
        readFIB();

        //get the SEPS for the main document text
        ArrayList sections = findProperties(_fcMin, _fcMin + _ccpText, _sectionTable.root);

        //iterate through sections, paragraphs, and character runs doing what
        //you will with the data.
        int size = sections.size();
        for(int x = 0; x < size; x++)
        {
          SepxNode node = (SepxNode)sections.get(x);
          int start = node.getStart();
          int end = node.getEnd();
          SEP sep = (SEP)StyleSheet.uncompressProperty(node.getSepx(), new SEP(), _styleSheet);
          writeSection(Math.max(_fcMin, start), Math.min(_fcMin + _ccpText, end), sep, _text, _paragraphTable, _characterTable, _styleSheet);
        }
        //finish
        istream.close();

  }
  /**
   * Extracts the main document stream from the POI file then hands off to other
   * functions that parse other areas.
   *
   * @throws IOException
   */
  private void readFIB() throws IOException
  {
      //get the main document stream
      DocumentEntry headerProps =
        (DocumentEntry)filesystem.getRoot().getEntry("WordDocument");

      //I call it the header but its also the main document stream
      _header = new byte[headerProps.getSize()];
      filesystem.createDocumentInputStream("WordDocument").read(_header);

      //Get the information we need from the header
      int info = LittleEndian.getShort(_header, 0xa);

      _fcMin = LittleEndian.getInt(_header, 0x18);
      _ccpText = LittleEndian.getInt(_header, 0x4c);
      _ccpFtn = LittleEndian.getInt(_header, 0x50);

      int charPLC = LittleEndian.getInt(_header, 0xfa);
      int charPlcSize = LittleEndian.getInt(_header, 0xfe);
      int parPLC = LittleEndian.getInt(_header, 0x102);
      int parPlcSize = LittleEndian.getInt(_header, 0x106);
      boolean useTable1 = (info & 0x200) != 0;

      //process the text and formatting properties
      processComplexFile(useTable1, charPLC, charPlcSize, parPLC, parPlcSize);
  }

  /**
   * Extracts the correct Table stream from the POI filesystem then hands off to
   * other functions to process text and formatting info. the name is based on
   * the fact that in Word 8(97) all text (not character or paragraph formatting)
   * is stored in complex format.
   *
   * @param useTable1 boolean that specifies if we should use table1 or table0
   * @param charTable offset in table stream of character property bin table
   * @param charPlcSize size of character property bin table
   * @param parTable offset in table stream of paragraph property bin table.
   * @param parPlcSize size of paragraph property bin table.
   * @return boolean indocating success of
   * @throws IOException
   */
  private void processComplexFile(boolean useTable1, int charTable,
                                     int charPlcSize, int parTable, int parPlcSize) throws IOException
  {

      //get the location of the piece table
      int complexOffset = LittleEndian.getInt(_header, 0x1a2);

      String tablename=null;
      DocumentEntry tableEntry = null;
      if(useTable1)
      {
          tablename="1Table";
      }
      else
      {
          tablename="0Table";
      }
      tableEntry = (DocumentEntry)filesystem.getRoot().getEntry(tablename);

      //load the table stream into a buffer
      int size = tableEntry.getSize();
      byte[] tableStream = new byte[size];
      filesystem.createDocumentInputStream(tablename).read(tableStream);

      //init the DOP for this document
      initDocProperties(tableStream);
      //load the header/footer raw data for this document
      initPclfHdd(tableStream);
      //parse out the text locations
      findText(tableStream, complexOffset);
      //parse out text formatting
      findFormatting(tableStream, charTable, charPlcSize, parTable, parPlcSize);

  }
  /**
   * Goes through the piece table and parses out the info regarding the text
   * blocks. For Word 97 and greater all text is stored in the "complex" way
   * because of unicode.
   *
   * @param tableStream buffer containing the main table stream.
   * @param beginning of the complex data.
   * @throws IOException
   */
  private void findText(byte[] tableStream, int complexOffset) throws IOException
  {
    //actual text
    int pos = complexOffset;
    //skips through the prms before we reach the piece table. These contain data
    //for actual fast saved files
    while(tableStream[pos] == 1)
    {
        pos++;
        int skip = LittleEndian.getShort(tableStream, pos);
        pos += 2 + skip;
    }
    if(tableStream[pos] != 2)
    {
        throw new IOException("corrupted Word file");
    }
    else
    {
        //parse out the text pieces
        int pieceTableSize = LittleEndian.getInt(tableStream, ++pos);
        pos += 4;
        int pieces = (pieceTableSize - 4) / 12;
        for (int x = 0; x < pieces; x++)
        {
            int filePos = LittleEndian.getInt(tableStream, pos + ((pieces + 1) * 4) + (x * 8) + 2);
            boolean unicode = false;
            if ((filePos & 0x40000000) == 0)
            {
                unicode = true;
            }
            else
            {
                unicode = false;
                filePos &= ~(0x40000000);//gives me FC in doc stream
                filePos /= 2;
            }
            int totLength = LittleEndian.getInt(tableStream, pos + (x + 1) * 4) -
                            LittleEndian.getInt(tableStream, pos + (x * 4));

            TextPiece piece = new TextPiece(filePos, totLength, unicode);
            _text.add(piece);

        }

    }
  }

  /**
   * Does all of the formatting parsing
   *
   * @param tableStream Main table stream buffer.
   * @param charOffset beginning of the character bin table.
   * @param chrPlcSize size of the char bin table.
   * @param parOffset offset of the paragraph bin table.
   * @param size of the paragraph bin table.
   */
  private void findFormatting(byte[] tableStream, int charOffset,
                              int charPlcSize, int parOffset, int parPlcSize) throws IOException
  {
      openDoc();
      createStyleSheet(tableStream);
      createListTables(tableStream);
      createFontTable(tableStream);

      //find character runs
      //Get all the chpx info and store it

      int arraySize = (charPlcSize - 4)/8;

      //first we must go through the bin table and find the fkps
      for(int x = 0; x < arraySize; x++)
      {


          //get page number(has nothing to do with document page)
          //containing the chpx for the paragraph
          int PN = LittleEndian.getInt(tableStream, charOffset + (4 * (arraySize + 1) + (4 * x)));

          byte[] fkp = new byte[512];
          System.arraycopy(_header, (PN * 512), fkp, 0, 512);
          //take each fkp and get the chpxs
          int crun = Utils.convertUnsignedByteToInt(fkp[511]);
          for(int y = 0; y < crun; y++)
          {
              //get the beginning fc of each paragraph text run
              int fcStart = LittleEndian.getInt(fkp, y * 4);
              int fcEnd = LittleEndian.getInt(fkp, (y+1) * 4);
              //get the offset in fkp of the papx for this paragraph
              int chpxOffset = 2 * Utils.convertUnsignedByteToInt(fkp[((crun + 1) * 4) + y]);

              //optimization if offset == 0 use "Normal" style
              if(chpxOffset == 0)

              {
                _characterTable.add(new ChpxNode(fcStart, fcEnd, new byte[0]));
                continue;
              }

              int size = Utils.convertUnsignedByteToInt(fkp[chpxOffset]);

              byte[] chpx = new byte[size];
              System.arraycopy(fkp, ++chpxOffset, chpx, 0, size);
              //_papTable.put(new Integer(fcStart), papx);
              _characterTable.add(new ChpxNode(fcStart, fcEnd, chpx));
          }

      }

      //find paragraphs
      arraySize = (parPlcSize - 4)/8;
      //first we must go through the bin table and find the fkps
      for(int x = 0; x < arraySize; x++)
      {
          int PN = LittleEndian.getInt(tableStream, parOffset + (4 * (arraySize + 1) + (4 * x)));

          byte[] fkp = new byte[512];
          System.arraycopy(_header, (PN * 512), fkp, 0, 512);
          //take each fkp and get the paps
          int crun = Utils.convertUnsignedByteToInt(fkp[511]);
          for(int y = 0; y < crun; y++)
          {
              //get the beginning fc of each paragraph text run
              int fcStart = LittleEndian.getInt(fkp, y * 4);
              int fcEnd = LittleEndian.getInt(fkp, (y+1) * 4);