diff options
| author | tknall <tknall@7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c> | 2006-12-01 12:20:24 +0000 |
|---|---|---|
| committer | tknall <tknall@7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c> | 2006-12-01 12:20:24 +0000 |
| commit | 6025b6016517c6d898d8957d1d7e03ba71431912 (patch) | |
| tree | b15bd6fa5ffe9588a9bca3f2b8a7e358f83b6eba /src/main/java/org/pdfbox/PDFToImage.java | |
| parent | d2c77e820ab4aba8235d71275755021347b3ad10 (diff) | |
| download | pdf-as-3-8a76a3f538808ec75b0d46c545d00dbf4fdc2abd.tar.gz pdf-as-3-8a76a3f538808ec75b0d46c545d00dbf4fdc2abd.tar.bz2 pdf-as-3-8a76a3f538808ec75b0d46c545d00dbf4fdc2abd.zip | |
Initial import of release 2.2.REL-2.2@923
git-svn-id: https://joinup.ec.europa.eu/svn/pdf-as/trunk@4 7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c
Diffstat (limited to 'src/main/java/org/pdfbox/PDFToImage.java')
| -rw-r--r-- | src/main/java/org/pdfbox/PDFToImage.java | 270 |
1 files changed, 270 insertions, 0 deletions
diff --git a/src/main/java/org/pdfbox/PDFToImage.java b/src/main/java/org/pdfbox/PDFToImage.java new file mode 100644 index 0000000..7a6df6b --- /dev/null +++ b/src/main/java/org/pdfbox/PDFToImage.java @@ -0,0 +1,270 @@ +/**
+ * Copyright (c) 2005, www.pdfbox.org
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ * 3. Neither the name of pdfbox; nor the names of its
+ * contributors may be used to endorse or promote products derived from this
+ * software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * http://www.pdfbox.org
+ *
+ */
+package org.pdfbox;
+
+import java.awt.image.BufferedImage;
+import java.io.File;
+import java.util.Iterator;
+import java.util.List;
+
+import javax.imageio.IIOException;
+import javax.imageio.IIOImage;
+import javax.imageio.ImageIO;
+import javax.imageio.ImageWriteParam;
+import javax.imageio.ImageWriter;
+import javax.imageio.stream.ImageOutputStream;
+
+import org.pdfbox.exceptions.InvalidPasswordException;
+
+import org.pdfbox.pdmodel.PDDocument;
+import org.pdfbox.pdmodel.PDPage;
+
+/**
+ * Convert a PDF document to an image.
+ *
+ * @author Ben Litchfield (ben@csh.rit.edu)
+ * @version $Revision: 1.3 $
+ */
+public class PDFToImage
+{
+
+
+
+ private static final String PASSWORD = "-password";
+ private static final String START_PAGE = "-startPage";
+ private static final String END_PAGE = "-endPage";
+ private static final String IMAGE_TYPE = "-imageType";
+ private static final String OUTPUT_PREFIX = "-outputPrefix";
+
+ /**
+ * private constructor.
+ */
+ private PDFToImage()
+ {
+ //static class
+ }
+
+ /**
+ * 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
+ {
+ String password = "";
+ String pdfFile = null;
+ String outputPrefix = null;
+ String imageType = "jpg";
+ int startPage = 1;
+ int endPage = Integer.MAX_VALUE;
+ for( int i=0; i<args.length; i++ )
+ {
+ if( args[i].equals( PASSWORD ) )
+ {
+ i++;
+ if( i >= args.length )
+ {
+ usage();
+ }
+ password = args[i];
+ }
+ else if( args[i].equals( START_PAGE ) )
+ {
+ i++;
+ if( i >= args.length )
+ {
+ usage();
+ }
+ startPage = Integer.parseInt( args[i] );
+ }
+ else if( args[i].equals( END_PAGE ) )
+ {
+ i++;
+ if( i >= args.length )
+ {
+ usage();
+ }
+ endPage = Integer.parseInt( args[i] );
+ }
+ else if( args[i].equals( IMAGE_TYPE ) )
+ {
+ i++;
+ imageType = args[i];
+ }
+ else if( args[i].equals( OUTPUT_PREFIX ) )
+ {
+ i++;
+ outputPrefix = args[i];
+ }
+ else
+ {
+ if( pdfFile == null )
+ {
+ pdfFile = args[i];
+ }
+ }
+ }
+
+ if( pdfFile == null )
+ {
+ usage();
+ }
+ if(outputPrefix == null)
+ {
+ outputPrefix = pdfFile.substring( 0, pdfFile.lastIndexOf( '.' ));
+ }
+
+ PDDocument document = null;
+ try
+ {
+ document = PDDocument.load( pdfFile );
+
+
+ //document.print();
+ if( document.isEncrypted() )
+ {
+ try
+ {
+ document.decrypt( password );
+ }
+ catch( InvalidPasswordException e )
+ {
+ if( args.length == 4 )//they supplied the wrong password
+ {
+ System.err.println( "Error: The supplied password is incorrect." );
+ System.exit( 2 );
+ }
+ else
+ {
+ //they didn't suppply a password and the default of "" was wrong.
+ System.err.println( "Error: The document is encrypted." );
+ usage();
+ }
+ }
+ }
+ List pages = document.getDocumentCatalog().getAllPages();
+ for( int i=startPage-1; i<endPage && i<pages.size(); i++ )
+ {
+ ImageOutputStream output = null;
+ ImageWriter imageWriter = null;
+ try
+ {
+ PDPage page = (PDPage)pages.get( i );
+ BufferedImage image = page.convertToImage();
+ String fileName = outputPrefix + (i+1) + "." + imageType;
+ System.out.println( "Writing:" + fileName );
+ output = ImageIO.createImageOutputStream( new File( fileName ) );
+
+ boolean foundWriter = false;
+ Iterator writerIter = ImageIO.getImageWritersByFormatName( imageType );
+ while( writerIter.hasNext() && !foundWriter )
+ {
+ try
+ {
+ imageWriter = (ImageWriter)writerIter.next();
+ ImageWriteParam writerParams = imageWriter.getDefaultWriteParam();
+ if(writerParams.canWriteCompressed() )
+ {
+ writerParams.setCompressionMode(ImageWriteParam.MODE_EXPLICIT);
+ writerParams.setCompressionQuality(1.0f);
+ }
+
+
+ imageWriter.setOutput( output );
+ imageWriter.write( null, new IIOImage( image, null, null), writerParams );
+ foundWriter = true;
+ }
+ catch( IIOException io )
+ {
+ //ignore exception
+ }
+ finally
+ {
+ imageWriter.dispose();
+ }
+ }
+ if( !foundWriter )
+ {
+ throw new RuntimeException( "Error: no writer found for image type '" + imageType + "'" );
+ }
+ }
+ finally
+ {
+ if( output != null )
+ {
+ output.flush();
+ output.close();
+ }
+ }
+ }
+ }
+ finally
+ {
+ if( document != null )
+ {
+ document.close();
+ }
+ }
+ }
+
+ /**
+ * This will print the usage requirements and exit.
+ */
+ private static void usage()
+ {
+ System.err.println( "Usage: java org.pdfbox.ExtractText [OPTIONS] <PDF file> [Text File]\n" +
+ " -password <password> Password to decrypt document\n" +
+ " -imageType <image type> (" + getImageFormats() + ")\n" +
+ " -outputPrefix <output prefix> Filename prefix for image files\n" +
+ " -startPage <number> The first page to start extraction(1 based)\n" +
+ " -endPage <number> The last page to extract(inclusive)\n" +
+ " <PDF file> The PDF document to use\n"
+ );
+ System.exit( 1 );
+ }
+
+ private static String getImageFormats()
+ {
+ StringBuffer retval = new StringBuffer();
+ String[] formats = ImageIO.getReaderFormatNames();
+ for( int i=0; i<formats.length; i++ )
+ {
+ retval.append( formats[i] );
+ if( i+1<formats.length )
+ {
+ retval.append( "," );
+ }
+ }
+ return retval.toString();
+ }
+}
\ No newline at end of file |