org.apache.pdfbox.pdfparser.PDFObjectStreamParser Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of pdfbox Show documentation
The Apache PDFBox library is an open source Java tool for working with PDF documents.
There is a newer version: 3.0.2
/*
 * 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.pdfbox.pdfparser;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.pdfbox.cos.COSBase;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.cos.COSObject;
import org.apache.pdfbox.cos.COSStream;

/**
 * This will parse a PDF 1.5 object stream and extract all of the objects from the stream.
 *
 * @author Ben Litchfield
 * 
 */
public class PDFObjectStreamParser extends BaseParser
{
    /**
     * Log instance.
     */
    private static final Log LOG = LogFactory.getLog(PDFObjectStreamParser.class);

    private List streamObjects = null;
    private final COSStream stream;

    /**
     * Constructor.
     *
     * @param stream The stream to parse.
     * @param document The document for the current parsing.
     * @throws IOException If there is an error initializing the stream.
     */
    public PDFObjectStreamParser(COSStream stream, COSDocument document) throws IOException
    {
        super(new InputStreamSource(stream.createInputStream()));
        this.stream = stream;
        this.document = document;
    }

    /**
     * This will parse the tokens in the stream.  This will close the
     * stream when it is finished parsing.
     *
     * @throws IOException If there is an error while parsing the stream.
     */
    public void parse() throws IOException
    {
        try
        {
            //need to first parse the header.
            int numberOfObjects = stream.getInt( "N" );
            List objectNumbers = new ArrayList( numberOfObjects );
            streamObjects = new ArrayList( numberOfObjects );
            for( int i=0; i= objectNumbers.size())
                {
                    LOG.error("/ObjStm (object stream) has more objects than /N " + numberOfObjects);
                    break;
                }
                object.setObjectNumber( objectNumbers.get( objectCounter) );
                streamObjects.add( object );
                if(LOG.isDebugEnabled())
                {
                    LOG.debug( "parsed=" + object );
                }
                // According to the spec objects within an object stream shall not be enclosed 
                // by obj/endobj tags, but there are some pdfs in the wild using those tags 
                // skip endobject marker if present
                if (!seqSource.isEOF() && seqSource.peek() == 'e')
                {
                    readLine();
                }
                objectCounter++;
            }
        }
        finally
        {
            seqSource.close();
        }
    }

    /**
     * This will get the objects that were parsed from the stream.
     *
     * @return All of the objects in the stream.
     */
    public List getObjects()
    {
        return streamObjects;
    }
}