hslfslideshow.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.hslf;

import java.util.*;
import java.io.*;

import org.apache.poi.POIDocument;
import org.apache.poi.util.LittleEndian;
import org.apache.poi.util.POILogger;
import org.apache.poi.util.POILogFactory;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.DocumentInputStream;

import org.apache.poi.hpsf.PropertySet;
import org.apache.poi.hpsf.PropertySetFactory;
import org.apache.poi.hpsf.MutablePropertySet;
import org.apache.poi.hpsf.SummaryInformation;
import org.apache.poi.hpsf.DocumentSummaryInformation;

import org.apache.poi.hslf.exceptions.CorruptPowerPointFileException;
import org.apache.poi.hslf.exceptions.EncryptedPowerPointFileException;
import org.apache.poi.hslf.exceptions.HSLFException;
import org.apache.poi.hslf.record.*;
import org.apache.poi.hslf.usermodel.PictureData;

/**
 * This class contains the main functionality for the Powerpoint file 
 * "reader". It is only a very basic class for now
 *
 * @author Nick Burch
 */

public class HSLFSlideShow extends POIDocument
{
    // For logging
    protected POILogger logger = POILogFactory.getLogger(this.getClass());

	private InputStream istream;

	// Holds metadata on where things are in our document
	private CurrentUserAtom currentUser;

	// Low level contents of the file
	private byte[] _docstream;

	// Low level contents
	private Record[] _records;

	// Raw Pictures contained in the pictures stream
	private PictureData[] _pictures;
	
	/**
	 * Returns the underlying POIFSFileSystem for the document
	 *  that is open.
	 */
	protected POIFSFileSystem getPOIFSFileSystem() {
		return filesystem;
	}

	/**
	 * Constructs a Powerpoint 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 HSLFSlideShow(String fileName) throws IOException
	{
		this(new FileInputStream(fileName));
	}
  
	/**
	 * Constructs a Powerpoint document from an input stream. Parses the 
	 * document and places all the important stuff into data structures.
	 *
	 * @param inputStream the source of the data
	 * @throws IOException if there is a problem while parsing the document.
	 */
	public HSLFSlideShow(InputStream inputStream) throws IOException
	{
		//do Ole stuff
		this(new POIFSFileSystem(inputStream));
		istream = inputStream;
	}

	/**
	 * Constructs a Powerpoint document from a POIFS Filesystem. Parses the 
	 * document and places all the important stuff into data structures.
	 *
	 * @param filesystem the POIFS FileSystem to read from
	 * @throws IOException if there is a problem while parsing the document.
	 */
	public HSLFSlideShow(POIFSFileSystem filesystem) throws IOException
	{
		this.filesystem = filesystem;
		
		// First up, grab the "Current User" stream
		// We need this before we can detect Encrypted Documents
		readCurrentUserStream();
		
		// Next up, grab the data that makes up the 
		//  PowerPoint stream
		readPowerPointStream();
		
		// Check to see if we have an encrypted document,
		//  bailing out if we do
		boolean encrypted = EncryptedSlideShow.checkIfEncrypted(this);
		if(encrypted) {
			throw new EncryptedPowerPointFileException("Encrypted PowerPoint files are not supported");
		}

		// Now, build records based on the PowerPoint stream
		buildRecords();

		// Look for Property Streams:
		readProperties();
		
		// Look for any other streams
		readOtherStreams();

		// Look for Picture Streams:
		readPictures();
	}

	/**
	 * Constructs a new, empty, Powerpoint document.
	 */
	public HSLFSlideShow() throws IOException 
	{
		this(HSLFSlideShow.class.getResourceAsStream("/org/apache/poi/hslf/data/empty.ppt"));
	}

	/**
	 * Shuts things down. Closes underlying streams etc
	 *
	 * @throws IOException
	 */
	public void close() throws IOException
	{
		if(istream != null) {
			istream.close();
		}
		filesystem = null;
	}


	/**
	 * Extracts the main PowerPoint document stream from the 
	 *  POI file, ready to be passed 
	 *
	 * @throws IOException
	 */
	private void readPowerPointStream() throws IOException
	{
		// Get the main document stream
		DocumentEntry docProps =
			(DocumentEntry)filesystem.getRoot().getEntry("PowerPoint Document");

		// Grab the document stream
		_docstream = new byte[docProps.getSize()];
		filesystem.createDocumentInputStream("PowerPoint Document").read(_docstream);
	}
	
	/**
	 * Builds the list of records, based on the contents  
	 *  of the PowerPoint stream
	 */
	private void buildRecords()
	{
		// The format of records in a powerpoint file are:
		//   <little endian 2 byte "info">
		//   <little endian 2 byte "type">
		//   <little endian 4 byte "length">
		// If it has a zero length, following it will be another record
		//		<xx xx yy yy 00 00 00 00> <xx xx yy yy zz zz zz zz>
		// If it has a length, depending on its type it may have children or data
		// If it has children, these will follow straight away
		//		<xx xx yy yy zz zz zz zz <xx xx yy yy zz zz zz zz>>
		// If it has data, this will come straigh after, and run for the length
		//      <xx xx yy yy zz zz zz zz dd dd dd dd dd dd dd>
		// All lengths given exclude the 8 byte record header
		// (Data records are known as Atoms)
	
		// Document should start with:
		//   0F 00 E8 03 ## ## ## ##
	    //     (type 1000 = document, info 00 0f is normal, rest is document length)
		//   01 00 E9 03 28 00 00 00
		//     (type 1001 = document atom, info 00 01 normal, 28 bytes long)
		//   80 16 00 00 E0 10 00 00 xx xx xx xx xx xx xx xx
		//   05 00 00 00 0A 00 00 00 xx xx xx
		//     (the contents of the document atom, not sure what it means yet)
		//   (records then follow)
	
		// When parsing a document, look to see if you know about that type
		//  of the current record. If you know it's a type that has children, 
		//  process the record's data area looking for more records
		// If you know about the type and it doesn't have children, either do
		//  something with the data (eg TextRun) or skip over it
		// If you don't know about the type, play safe and skip over it (using
		//  its length to know where the next record will start)
		//

        _records = read(_docstream, (int)currentUser.getCurrentEditOffset());
	}

    private Record[] read(byte[] docstream, int usrOffset){
        ArrayList lst = new ArrayList();
        while (usrOffset != 0){
            UserEditAtom usr = (UserEditAtom) Record.buildRecordAtOffset(docstream, usrOffset);
            lst.add(new Integer(usrOffset));
            int psrOffset = usr.getPersistPointersOffset();

            PersistPtrHolder ptr = (PersistPtrHolder)Record.buildRecordAtOffset(docstream, psrOffset);
            lst.add(new Integer(psrOffset));
            Hashtable entries = ptr.getSlideLocationsLookup();
            for (Iterator it = entries.keySet().iterator(); it.hasNext(); ) {
                Integer id = (Integer)it.next();
                Integer offset = (Integer)entries.get(id);

                lst.add(offset);
            }

            usrOffset = usr.getLastUserEditAtomOffset();
        }
        //sort found records by offset.
        //(it is not necessary but SlideShow.findMostRecentCoreRecords() expects them sorted)
        Object a[] = lst.toArray();
        Arrays.sort(a);
        Record[] rec = new Record[lst.size()];
        for (int i = 0; i < a.length; i++) {
            Integer offset = (Integer)a[i];
            rec[i] = (Record)Record.buildRecordAtOffset(docstream, offset.intValue());
        }

        return rec;
    }