001/*
002 * $Id: ContentByteUtils.java 4784 2011-03-15 08:33:00Z blowagie $
003 *
004 * This file is part of the iText (R) project.
005 * Copyright (c) 1998-2011 1T3XT BVBA
006 * Authors: Kevin Day, Bruno Lowagie, Paulo Soares, et al.
007 *
008 * This program is free software; you can redistribute it and/or modify
009 * it under the terms of the GNU Affero General Public License version 3
010 * as published by the Free Software Foundation with the addition of the
011 * following permission added to Section 15 as permitted in Section 7(a):
012 * FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY 1T3XT,
013 * 1T3XT DISCLAIMS THE WARRANTY OF NON INFRINGEMENT OF THIRD PARTY RIGHTS.
014 *
015 * This program is distributed in the hope that it will be useful, but
016 * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
017 * or FITNESS FOR A PARTICULAR PURPOSE.
018 * See the GNU Affero General Public License for more details.
019 * You should have received a copy of the GNU Affero General Public License
020 * along with this program; if not, see http://www.gnu.org/licenses or write to
021 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
022 * Boston, MA, 02110-1301 USA, or download the license from the following URL:
023 * http://itextpdf.com/terms-of-use/
024 *
025 * The interactive user interfaces in modified source and object code versions
026 * of this program must display Appropriate Legal Notices, as required under
027 * Section 5 of the GNU Affero General Public License.
028 *
029 * In accordance with Section 7(b) of the GNU Affero General Public License,
030 * a covered work must retain the producer line in every PDF that is created
031 * or manipulated using iText.
032 *
033 * You can be released from the requirements of the license by purchasing
034 * a commercial license. Buying such a license is mandatory as soon as you
035 * develop commercial activities involving the iText software without
036 * disclosing the source code of your own applications.
037 * These activities include: offering paid services to customers as an ASP,
038 * serving PDFs on the fly in a web application, shipping iText with a closed
039 * source product.
040 *
041 * For more information, please contact iText Software Corp. at this
042 * address: sales@itextpdf.com
043 */
044package com.itextpdf.text.pdf.parser;
045
046import java.io.ByteArrayOutputStream;
047import java.io.IOException;
048import java.util.ListIterator;
049
050import com.itextpdf.text.pdf.PRIndirectReference;
051import com.itextpdf.text.pdf.PRStream;
052import com.itextpdf.text.pdf.PdfArray;
053import com.itextpdf.text.pdf.PdfDictionary;
054import com.itextpdf.text.pdf.PdfName;
055import com.itextpdf.text.pdf.PdfObject;
056import com.itextpdf.text.pdf.PdfReader;
057
058/**
059 * @author kevin
060 * @since 5.0.1
061 */
062public class ContentByteUtils {
063    private ContentByteUtils() {
064        // TODO Auto-generated constructor stub
065    }
066
067    /**
068     * Gets the content bytes from a content object, which may be a reference
069     * a stream or an array.
070     * @param contentObject the object to read bytes from
071     * @return the content bytes
072     * @throws IOException
073     */
074    public static byte[] getContentBytesFromContentObject(final PdfObject contentObject) throws IOException {
075        final byte[] result;
076        switch (contentObject.type())
077        {
078            case PdfObject.INDIRECT:
079                final PRIndirectReference ref = (PRIndirectReference) contentObject;
080                final PdfObject directObject = PdfReader.getPdfObject(ref);
081                result = getContentBytesFromContentObject(directObject);
082                break;
083            case PdfObject.STREAM:
084                final PRStream stream = (PRStream) PdfReader.getPdfObject(contentObject);
085                result = PdfReader.getStreamBytes(stream);
086                break;
087            case PdfObject.ARRAY:
088                // Stitch together all content before calling processContent(), because
089                // processContent() resets state.
090                final ByteArrayOutputStream allBytes = new ByteArrayOutputStream();
091                final PdfArray contentArray = (PdfArray) contentObject;
092                final ListIterator<PdfObject> iter = contentArray.listIterator();
093                while (iter.hasNext())
094                {
095                    final PdfObject element = iter.next();
096                    allBytes.write(getContentBytesFromContentObject(element));
097                    allBytes.write((byte)' ');
098                }
099                result = allBytes.toByteArray();
100                break;
101            default:
102                final String msg = "Unable to handle Content of type " + contentObject.getClass();
103            throw new IllegalStateException(msg);
104        }
105        return result;
106    }
107    
108    /**
109     * Gets the content bytes of a page from a reader
110     * @param reader  the reader to get content bytes from
111     * @param pageNum   the page number of page you want get the content stream from
112     * @return  a byte array with the effective content stream of a page
113     * @throws IOException
114     * @since 5.0.1
115     */
116    public static byte[] getContentBytesForPage(PdfReader reader, int pageNum) throws IOException {
117        final PdfDictionary pageDictionary = reader.getPageN(pageNum);
118        final PdfObject contentObject = pageDictionary.get(PdfName.CONTENTS);
119        if (contentObject == null)
120            return new byte[0];
121        
122        final byte[] contentBytes = ContentByteUtils.getContentBytesFromContentObject(contentObject);
123        return contentBytes;
124    }
125
126}