org.apache.pdfbox.PDFSplit 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;

import java.io.File;
import java.io.IOException;
import java.io.FileOutputStream;

import java.util.List;

import org.apache.pdfbox.exceptions.COSVisitorException;

import org.apache.pdfbox.pdmodel.PDDocument;

import org.apache.pdfbox.pdfwriter.COSWriter;

import org.apache.pdfbox.util.Splitter;

/**
 * This is the main program that will take a pdf document and split it into
 * a number of other documents.
 *
 * @author Ben Litchfield
 * @version $Revision: 1.6 $
 */
public class PDFSplit
{
    private static final String PASSWORD = "-password";
    private static final String SPLIT = "-split";
    private static final String START_PAGE = "-startPage";
    private static final String END_PAGE = "-endPage";
    private static final String NONSEQ = "-nonSeq";
    private static final String OUTPUT_PREFIX = "-outputPrefix";

    private PDFSplit()
    {
    }
    /**
     * Infamous main method.
     *
     * @param args Command line arguments, should be one and a reference to a file.
     *
     * @throws Exception If there is an error parsing the document.
     */
    public static void main( String[] args ) throws Exception
    {
        PDFSplit split = new PDFSplit();
        split.split( args );
    }

    private void split( String[] args ) throws Exception
    {
        String password = "";
        String split = null;
        String startPage = null;
        String endPage = null;
        boolean useNonSeqParser = false;
        Splitter splitter = new Splitter();
        String pdfFile = null;
        String outputPrefix = null;
        for( int i=0; i= args.length )
                {
                    usage();
                }
                password = args[i];
            }
            else if( args[i].equals( SPLIT ) )
            {
                i++;
                if( i >= args.length )
                {
                    usage();
                }
                split = args[i];
            }
            else if( args[i].equals( START_PAGE ) )
            {
                i++;
                if( i >= args.length )
                {
                    usage();
                }
                startPage = args[i];
            }
            else if( args[i].equals( END_PAGE ) )
            {
                i++;
                if( i >= args.length )
                {
                    usage();
                }
                endPage = args[i];
            }
            else if( args[i].equals( OUTPUT_PREFIX ) )
            {
                i++;
                outputPrefix = args[i];
            }
            else if( args[i].equals( NONSEQ ) )
            {
                useNonSeqParser = true;
            }
            else
            {
                if( pdfFile == null )
                {
                    pdfFile = args[i];
                }
            }
        }

        if( pdfFile == null )
        {
            usage();
        }
        else
        {          
            if (outputPrefix == null)
            {
                outputPrefix = pdfFile.substring(0, pdfFile.lastIndexOf('.'));
            }
            PDDocument document = null;
            List documents = null;
            try
            {
                if (useNonSeqParser) 
                {
                    document = PDDocument.loadNonSeq(new File(pdfFile), null, password);
                }
                else
                {
                    document = PDDocument.load(pdfFile);
                    if( document.isEncrypted() )
                    {
                        document.decrypt( password );
                    }
                }

                int numberOfPages = document.getNumberOfPages();
                boolean startEndPageSet = false;
                if (startPage != null)
                {
                    splitter.setStartPage(Integer.parseInt( startPage ));
                    startEndPageSet = true;
                    if (split == null)
                    {
                        splitter.setSplitAtPage(numberOfPages);
                    }
                }
                if (endPage != null)
                {
                    splitter.setEndPage(Integer.parseInt( endPage ));
                    startEndPageSet = true;
                    if (split == null)
                    {
                        splitter.setSplitAtPage(Integer.parseInt( endPage ));
                    }
                }
                if (split != null)
                {
                    splitter.setSplitAtPage( Integer.parseInt( split ) );
                }
                else 
                {
                    if (!startEndPageSet)
                    {
                        splitter.setSplitAtPage(1);
                    }
                }
                    
                documents = splitter.split( document );
                for( int i=0; i\n" +
            "  -password    Password to decrypt document\n" +
            "  -split        split after this many pages (default 1, if startPage and endPage are unset)\n"+
            "  -startPage    start page\n" +
            "  -endPage      end page\n" +
            "  -nonSeq                Enables the new non-sequential parser\n" +
            "  -outputPrefix   Filename prefix for image files\n" +    
            "               The PDF document to use\n"
            );
        System.exit( 1 );
    }
}