hwpfdocument.java

java 读写word excel ppt

/* ====================================================================
   Licensed to the Apache Software Foundation (ASF) under one or more
   contributor license agreements.  See the NOTICE file distributed with
   this work for additional information regarding copyright ownership.
   The ASF licenses this file to You under the Apache License, Version 2.0
   (the "License"); you may not use this file except in compliance with
   the License.  You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.
==================================================================== */


package org.apache.poi.hwpf;

import java.io.InputStream;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.PushbackInputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.ByteArrayInputStream;

import java.util.Iterator;

import org.apache.poi.POIDocument;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.common.POIFSConstants;

import org.apache.poi.hwpf.model.*;
import org.apache.poi.hwpf.model.io.*;
import org.apache.poi.hwpf.usermodel.*;


/**
 *
 * This class acts as the bucket that we throw all of the Word data structures
 * into.
 *
 * @author Ryan Ackley
 */
public class HWPFDocument extends POIDocument
//  implements Cloneable
{
  /** The FIB*/
  protected FileInformationBlock _fib;

  /** main document stream buffer*/
  private byte[] _mainStream;

  /** table stream buffer*/
  private byte[] _tableStream;

  /** data stream buffer*/
  protected byte[] _dataStream;

  /** Document wide Properties*/
  protected DocumentProperties _dop;

  /** Contains text of the document wrapped in a obfuscated Word data
  * structure*/
  protected ComplexFileTable _cft;

  protected TextPieceTable _tpt;

  /** Contains formatting properties for text*/
  protected CHPBinTable _cbt;

  /** Contains formatting properties for paragraphs*/
  protected PAPBinTable _pbt;

  /** Contains formatting properties for sections.*/
  protected SectionTable _st;

  /** Holds styles for this document.*/
  protected StyleSheet _ss;

  /** Holds fonts for this document.*/
  protected FontTable _ft;

  /** Hold list tables */
  protected ListTables _lt;

  /** Holds the save history for this document. */
  protected SavedByTable _sbt;
  
  /** Holds pictures table */
  protected PicturesTable _pictures;

  protected HWPFDocument()
  {

  }

  /**
   * Takens an InputStream, verifies that it's not RTF, builds a
   *  POIFSFileSystem from it, and returns that.
   */
  public static POIFSFileSystem verifyAndBuildPOIFS(InputStream istream) throws IOException {
	// Open a PushbackInputStream, so we can peek at the first few bytes
	PushbackInputStream pis = new PushbackInputStream(istream,6);
	byte[] first6 = new byte[6];
	pis.read(first6);

	// Does it start with {\rtf ? If so, it's really RTF
	if(first6[0] == '{' && first6[1] == '\\' && first6[2] == 'r'
		&& first6[3] == 't' && first6[4] == 'f') {
		throw new IllegalArgumentException("The document is really a RTF file");
	}

	// OK, so it's not RTF
	// Open a POIFSFileSystem on the (pushed back) stream
	pis.unread(first6);
	return new POIFSFileSystem(pis);
  }

  /**
   * This constructor loads a Word document from an InputStream.
   *
   * @param istream The InputStream that contains the Word document.
   * @throws IOException If there is an unexpected IOException from the passed
   *         in InputStream.
   */
  public HWPFDocument(InputStream istream) throws IOException
  {
    //do Ole stuff
    this( verifyAndBuildPOIFS(istream) );
  }

  /**
   * This constructor loads a Word document from a POIFSFileSystem
   *
   * @param pfilesystem The POIFSFileSystem that contains the Word document.
   * @throws IOException If there is an unexpected IOException from the passed
   *         in POIFSFileSystem.
   */
  public HWPFDocument(POIFSFileSystem pfilesystem) throws IOException
  {
    // Sort out the hpsf properties
    filesystem = pfilesystem;
    readProperties();
    
    // read in the main stream.
    DocumentEntry documentProps =
       (DocumentEntry)filesystem.getRoot().getEntry("WordDocument");
    _mainStream = new byte[documentProps.getSize()];
    filesystem.createDocumentInputStream("WordDocument").read(_mainStream);

    // use the fib to determine the name of the table stream.
    _fib = new FileInformationBlock(_mainStream);

    String name = "0Table";
    if (_fib.isFWhichTblStm())
    {
      name = "1Table";
    }

    // Grab the table stream.
    DocumentEntry tableProps;
	try {
		tableProps =
			(DocumentEntry)filesystem.getRoot().getEntry(name);
	} catch(FileNotFoundException fnfe) {
		throw new IllegalStateException("Table Stream '" + name + "' wasn't found - Either the document is corrupt, or is Word95 (or earlier)");
	}

    // read in the table stream.
    _tableStream = new byte[tableProps.getSize()];
    filesystem.createDocumentInputStream(name).read(_tableStream);

    _fib.fillVariableFields(_mainStream, _tableStream);

    // read in the data stream.
    try
    {
      DocumentEntry dataProps =
          (DocumentEntry) filesystem.getRoot().getEntry("Data");
      _dataStream = new byte[dataProps.getSize()];
      filesystem.createDocumentInputStream("Data").read(_dataStream);
    }
    catch(java.io.FileNotFoundException e)
    {
        _dataStream = new byte[0];
    }
    
    // read in the pictures stream
    _pictures = new PicturesTable(_dataStream);

    // get the start of text in the main stream
    int fcMin = _fib.getFcMin();

    // load up our standard structures.
    _dop = new DocumentProperties(_tableStream, _fib.getFcDop());
    _cft = new ComplexFileTable(_mainStream, _tableStream, _fib.getFcClx(), fcMin);
    _tpt = _cft.getTextPieceTable();
    _cbt = new CHPBinTable(_mainStream, _tableStream, _fib.getFcPlcfbteChpx(), _fib.getLcbPlcfbteChpx(), fcMin);
    _pbt = new PAPBinTable(_mainStream, _tableStream, _dataStream, _fib.getFcPlcfbtePapx(), _fib.getLcbPlcfbtePapx(), fcMin);

    // Word XP puts in a zero filled buffer in front of the text and it screws
    // up my system for offsets. This is an adjustment.
    int cpMin = _tpt.getCpMin();
    if (cpMin > 0)
    {
      _cbt.adjustForDelete(0, 0, cpMin);
      _pbt.adjustForDelete(0, 0, cpMin);
    }

    _st = new SectionTable(_mainStream, _tableStream, _fib.getFcPlcfsed(), _fib.getLcbPlcfsed(), fcMin, getTextTable().getTextPieces());
    _ss = new StyleSheet(_tableStream, _fib.getFcStshf());
    _ft = new FontTable(_tableStream, _fib.getFcSttbfffn(), _fib.getLcbSttbfffn());

    int listOffset = _fib.getFcPlcfLst();
    int lfoOffset = _fib.getFcPlfLfo();
    if (listOffset != 0 && _fib.getLcbPlcfLst() != 0)
    {
      _lt = new ListTables(_tableStream, _fib.getFcPlcfLst(), _fib.getFcPlfLfo());
    }

    int sbtOffset = _fib.getFcSttbSavedBy();
    int sbtLength = _fib.getLcbSttbSavedBy();
    if (sbtOffset != 0 && sbtLength != 0)
    {
      _sbt = new SavedByTable(_tableStream, sbtOffset, sbtLength);
    }

    PlexOfCps plc = new PlexOfCps(_tableStream, _fib.getFcPlcffldMom(), _fib.getLcbPlcffldMom(), 2);
    for (int x = 0; x < plc.length(); x++)
    {
      GenericPropertyNode node = plc.getProperty(x);
      byte[] fld = node.getBytes();
      int breakpoint = 0;
    }
  }

  public StyleSheet getStyleSheet()
  {
    return _ss;
  }

  public FileInformationBlock getFileInformationBlock()
  {
    return _fib;
  }

  public DocumentProperties getDocProperties()
  {
    return _dop;
  }

  public Range getRange()
  {
    // hack to get the ending cp of the document, Have to revisit this.
    java.util.List text = _tpt.getTextPieces();
    PropertyNode p = (PropertyNode)text.get(text.size() - 1);

    return new Range(0, p.getEnd(), this);
  }

  /**
   * Returns the character length of a document.
   * @return the character length of a document
   */
  public int characterLength()
  {
    java.util.List textPieces = _tpt.getTextPieces();
    Iterator textIt = textPieces.iterator();

    int length = 0;
    while(textIt.hasNext())