/**
* Reads a PDF file for retrieving its metadata.
*
* @param file File
*/
public void createTextFromPDF(File file) {
if (file.exists()) {
int page = 1;
PdfReader reader = null;
try {
reader = new PdfReader(new RandomAccessFileOrArray(file.getAbsolutePath()), null);
HashMap<String, String> pdfinfo = reader.getInfo();
StringBuffer sb = new StringBuffer();
sb.append("<html>=== Document Information ===<p>");
sb.append(
reader.getCropBox(page).getHeight() + "*" + reader.getCropBox(page).getWidth() + "<p>");
sb.append("PDF Version: " + reader.getPdfVersion() + "<p>");
sb.append("Number of pages: " + reader.getNumberOfPages() + "<p>");
sb.append("Number of PDF objects: " + reader.getXrefSize() + "<p>");
sb.append("File length: " + reader.getFileLength() + "<p>");
sb.append("Encrypted= " + reader.isEncrypted() + "<p>");
if (pdfinfo.get("Title") != null) {
sb.append("Title= " + pdfinfo.get("Title") + "<p>");
}
if (pdfinfo.get("Author") != null) {
sb.append("Author= " + pdfinfo.get("Author") + "<p>");
}
if (pdfinfo.get("Subject") != null) {
sb.append("Subject= " + pdfinfo.get("Subject") + "<p>");
}
if (pdfinfo.get("Producer") != null) {
sb.append("Producer= " + pdfinfo.get("Producer") + "<p>");
}
if (pdfinfo.get("ModDate") != null) {
sb.append("ModDate= " + PdfDate.decode(pdfinfo.get("ModDate")).getTime() + "<p>");
}
if (pdfinfo.get("CreationDate") != null) {
sb.append(
"CreationDate= " + PdfDate.decode(pdfinfo.get("CreationDate")).getTime() + "<p>");
}
sb.append("</html>");
label.setText(sb.toString());
} catch (IOException ex) {
label.setText("");
}
}
}
/**
* This method searches for all image objects from the currently processed PDF file and stores
* them as PDF in the given export directory or in the same directory where the original PDF file
* is stored.
*
* <p>The filename of the images is build based on the original PDF filename (without extension)
* and additional details like page number, image number and if available the internal image name.
*
* @param fullExportDirectoryPath The optional full export path where the images should be stored.
* If not given, the location of the original PDF file is used.
* @throws Exception
*/
private void imageExtractor(String fullExportDirectoryPath) throws Exception {
if (fullExportDirectoryPath != null) {
fullExportDirectoryPath = GlobalTools.checkDirectoryPath(fullExportDirectoryPath);
File exportDirectory = new File(fullExportDirectoryPath);
if (!exportDirectory.exists()) {
exportDirectory.mkdirs();
} // end if
} // end if
int totalNumberOfPDFObjects = pdfReader.getXrefSize();
for (int pdfObjectCounter = 0; pdfObjectCounter < totalNumberOfPDFObjects; pdfObjectCounter++) {
PdfObject pdfObject = pdfReader.getPdfObject(pdfObjectCounter);
if (pdfObject != null) {
if (pdfObject.isStream()) {
PdfStream pdfStream = (PdfStream) pdfObject;
PdfObject pdfObjectSubType = pdfStream.get(PdfName.SUBTYPE);
if (pdfObject == null) {
logger.debug("The internal PDF object is null.");
} // end if
if (!pdfObject.isStream()) {
logger.debug("The internal PDF object is not representing a stream object.");
} // end if
// Check PDF subtype and make sure it's an Image type
if (pdfObjectSubType != null
&& pdfObjectSubType.toString().equals(PdfName.IMAGE.toString())) {
// Now we have a PDF stream object with an image but what is that exactly?
// byte[] byteArrayImage = PdfReader.getStreamBytesRaw((PRStream) pdfStream);
byte[] byteArrayImage = null;
if (PdfName.FLATEDECODE.equals(pdfStream.getAsName(PdfName.FILTER))) {
byteArrayImage = PdfReader.getStreamBytes((PRStream) pdfStream);
// else if other filter (not supported yet)
} else {
byteArrayImage = PdfReader.getStreamBytesRaw((PRStream) pdfStream);
} // end if..else
// Test PdfImage - START
/*
PdfImage pdfImage = (PdfImage) ((PdfStream)((PRStream)pdfStream));
logger.trace("pdfImage --> pdfName --> Width...........: " + pdfStream.get(PdfName.WIDTH));
logger.trace("pdfImage --> pdfName --> Height..........: " + pdfStream.get(PdfName.HEIGHT));
logger.trace("pdfImage --> pdfName --> Id..............: " + pdfImage.get(PdfName.ID));
logger.trace("pdfImage --> pdfName --> Image...........: " + pdfImage.get(PdfName.IMAGE));
logger.trace("pdfImage --> pdfName --> ImageB..........: " + pdfImage.get(PdfName.IMAGEB));
logger.trace("pdfImage --> pdfName --> ImageC..........: " + pdfImage.get(PdfName.IMAGEC));
logger.trace("pdfImage --> pdfName --> ImageI..........: " + pdfImage.get(PdfName.IMAGEI));
logger.trace("pdfImage --> pdfName --> Imagemask.......: " + pdfImage.get(PdfName.IMAGEMASK));
logger.trace("pdfImage --> pdfName --> Info............: " + pdfImage.get(PdfName.INFO));
logger.trace("pdfImage --> pdfName --> Name............: " + pdfImage.get(PdfName.NAME));
logger.trace("pdfImage --> pdfName --> Named...........: " + pdfImage.get(PdfName.NAMED));
logger.trace("pdfImage --> pdfName --> Page............: " + pdfStream.get(PdfName.PAGE));
*/
// Test PdfImage - STOP
// STREAM
/*
logger.trace("pdfObject.toString()): " + pdfObject.toString());
logger.trace("pdfObjectCounter.................: " + pdfObjectCounter);
logger.trace("pdfObject.getIndRef().getNumber(): " + (pdfObject.getIndRef()!=null?pdfObject.getIndRef().toString():"null"));
logger.trace("pdfStream.getIndRef().getNumber(): " + (pdfStream.getIndRef()!=null?pdfStream.getIndRef().toString():"null"));
logger.trace("pdfStream --> pdfName --> toString........: " + pdfStream.toString());
logger.trace("pdfStream --> pdfName --> Width...........: " + pdfStream.get(PdfName.WIDTH));
logger.trace("pdfStream --> pdfName --> Height..........: " + pdfStream.get(PdfName.HEIGHT));
logger.trace("pdfStream --> pdfName --> BitsPerComponent: " + pdfStream.get(PdfName.BITSPERCOMPONENT));
logger.trace("pdfStream --> pdfName --> BitsPerSample...: " + pdfStream.get(PdfName.BITSPERSAMPLE));
logger.trace("pdfStream --> pdfName --> ColorSpace......: " + pdfStream.get(PdfName.COLORSPACE));
logger.trace("pdfStream --> pdfName --> CCITTFaxDecode..: " + pdfStream.get(PdfName.CCITTFAXDECODE));
logger.trace("pdfStream --> pdfName --> Document........: " + pdfStream.get(PdfName.DOCUMENT));
logger.trace("pdfStream --> pdfName --> Decode..........: " + pdfStream.get(PdfName.DECODE));
logger.trace("pdfStream --> pdfName --> DecodeParms.....: " + pdfStream.get(PdfName.DECODEPARMS));
logger.trace("pdfStream --> pdfName --> DeviceGray......: " + pdfStream.get(PdfName.DEVICEGRAY));
logger.trace("pdfStream --> pdfName --> DeviceCMYK......: " + pdfStream.get(PdfName.DEVICECMYK));
logger.trace("pdfStream --> pdfName --> DeviceRGB.......: " + pdfStream.get(PdfName.DEVICERGB));
logger.trace("pdfStream --> pdfName --> Filter..........: " + pdfStream.get(PdfName.FILTER));
logger.trace("pdfStream --> pdfName --> Filter - as name: " + pdfStream.getAsName(PdfName.FILTER));
logger.trace("pdfStream --> pdfName --> Id..............: " + pdfStream.get(PdfName.ID));
logger.trace("pdfStream --> pdfName --> Image...........: " + pdfStream.get(PdfName.IMAGE));
logger.trace("pdfStream --> pdfName --> ImageB..........: " + pdfStream.get(PdfName.IMAGEB));
logger.trace("pdfStream --> pdfName --> ImageC..........: " + pdfStream.get(PdfName.IMAGEC));
logger.trace("pdfStream --> pdfName --> ImageI..........: " + pdfStream.get(PdfName.IMAGEI));
logger.trace("pdfStream --> pdfName --> Imagemask.......: " + pdfStream.get(PdfName.IMAGEMASK));
logger.trace("pdfStream --> pdfName --> Info............: " + pdfStream.get(PdfName.INFO));
logger.trace("pdfStream --> pdfName --> Name............: " + pdfStream.get(PdfName.NAME));
logger.trace("pdfStream --> pdfName --> Named...........: " + pdfStream.get(PdfName.NAMED));
logger.trace("pdfStream --> pdfName --> Named - as name.: " + pdfStream.getAsName(PdfName.NAMED));
logger.trace("pdfStream --> pdfName --> Page............: " + pdfStream.get(PdfName.PAGE));
logger.trace("pdfStream --> pdfName --> PageElement.....: " + pdfStream.get(PdfName.PAGEELEMENT));
logger.trace("pdfStream --> pdfName --> Pdf.............: " + pdfStream.get(PdfName.PDF));
logger.trace("pdfStream --> pdfName --> PdfDocEncoding..: " + pdfStream.get(PdfName.PDFDOCENCODING));
logger.trace("pdfStream --> pdfName --> Position........: " + pdfStream.get(PdfName.POSITION));
logger.trace("pdfStream --> pdfName --> Producer........: " + pdfStream.get(PdfName.PRODUCER));
logger.trace("pdfStream --> pdfName --> Properties......: " + pdfStream.get(PdfName.PROPERTIES));
logger.trace("pdfStream --> pdfName --> Sect............: " + pdfStream.get(PdfName.SECT));
logger.trace("pdfStream --> pdfName --> SubType.........: " + pdfStream.get(PdfName.SUBTYPE));
logger.trace("pdfStream --> pdfName --> Supplement......: " + pdfStream.get(PdfName.SUPPLEMENT));
logger.trace("pdfStream --> pdfName --> Title...........: " + pdfStream.get(PdfName.TITLE));
*/
// logger.trace("pdfImage --> pdfName --> : " + (pdfName.).toString());
// Extract the image name
String streamImageName =
(pdfStream.get(PdfName.NAME) == null
? null
: pdfStream.get(PdfName.NAME).toString());
if (streamImageName != null
&& streamImageName.length() > 1
&& streamImageName.startsWith("/")) {
streamImageName = streamImageName.substring(1);
} else {
streamImageName = null;
} // end if..else
String exportFileWithoutExtension =
(fullExportDirectoryPath != null
? fullExportDirectoryPath
: this.fullPDFDirectoryPath)
+ GlobalTools.getFileNameWithoutExtension(this.fullPDFFilePath)
+ "_("
+ "p000"
+ "_ref"
+ REF_NUMBER_FORMAT.format(pdfObjectCounter)
+ (streamImageName == null ? "_unk" : "_" + streamImageName)
+ ")";
// Test
FileOutputStream fileOutputStream =
new FileOutputStream(exportFileWithoutExtension + ".jpg");
/*
* Write given byte array to a file.
*/
fileOutputStream.write(byteArrayImage);
fileOutputStream.flush();
fileOutputStream.close();
fileOutputStream = null;
/*
* Check image details
*/
int pdfImageBitsPerComponent = -1;
try {
if (pdfStream.get(PdfName.BITSPERCOMPONENT).isNumber()) {
pdfImageBitsPerComponent =
new Integer(pdfStream.get(PdfName.BITSPERCOMPONENT).toString()).intValue();
}
} catch (NumberFormatException ex) {
}
int pdfImageHeight = -1;
try {
if (pdfStream.get(PdfName.HEIGHT).isNumber()) {
pdfImageHeight = new Integer(pdfStream.get(PdfName.HEIGHT).toString()).intValue();
}
} catch (NumberFormatException ex) {
}
int pdfImageWidth = -1;
try {
if (pdfStream.get(PdfName.WIDTH).isNumber()) {
pdfImageWidth = new Integer(pdfStream.get(PdfName.WIDTH).toString()).intValue();
}
} catch (NumberFormatException ex) {
}
logger.debug("Height..........:" + pdfImageHeight);
logger.debug("Width...........:" + pdfImageWidth);
logger.debug("BitsPerComponent:" + pdfImageBitsPerComponent);
// or you could try making a java.awt.Image from the array:
if (PdfName.DEVICERGB.equals(pdfStream.get(PdfName.COLORSPACE))
&& PdfName.FLATEDECODE.equals(pdfStream.get(PdfName.FILTER))
&& pdfImageBitsPerComponent > 0
&& pdfImageWidth > 0
&& pdfImageHeight > 0) {
BufferedImage bufferedImage =
ImageProcessingTools.toBufferedImage(
byteArrayImage, pdfImageWidth, pdfImageHeight, pdfImageBitsPerComponent);
if (bufferedImage != null) {
ImageIO.write(
bufferedImage,
"PNG",
new FileOutputStream(exportFileWithoutExtension + "_imageIO" + ".png"));
} // end if
} else if (PdfName.DEVICEGRAY.equals(pdfStream.get(PdfName.COLORSPACE))
&& PdfName.RUNLENGTHDECODE.equals(pdfStream.get(PdfName.FILTER))
&& pdfImageBitsPerComponent > 0
&& pdfImageWidth > 0) {
BufferedImage bufferedImage =
ImageProcessingTools.toBufferedImage(
ImageProcessingTools.runLengthDecode(byteArrayImage),
pdfImageWidth,
2233,
pdfImageBitsPerComponent);
if (bufferedImage != null) {
ImageIO.write(
bufferedImage,
"PNG",
new FileOutputStream(exportFileWithoutExtension + "_imageIO" + ".png"));
} // end if
} // end if...
/*
Image image = Toolkit.getDefaultToolkit().createImage(imageByteArray);
BufferedImage bufferedImage = ImageProcessingTools.toBufferedImage(image, pdfImageWidth, pdfImageHeight);
if (bufferedImage != null) {
System.out.println("Image-Height....:" + bufferedImage.getHeight());
System.out.println("Image-Width.....:" + bufferedImage.getWidth());
System.out.println("Image-isAlphaP..:" + bufferedImage.isAlphaPremultiplied());
File pngOutputFile = new File(exportFileWithoutExtension + "_imageIO.jpg");
ImageIO.write(bufferedImage, "jpg", pngOutputFile);
}
*/
/**/
} // end if
} // end if
} // end if
} // end for
}
/**
* Creates a list that will contain all the indirect objects in a PDF document.
*
* @param reader the reader that will read the PDF document
*/
public IndirectObjectFactory(PdfReader reader) {
this.reader = reader;
current = -1;
n = reader.getXrefSize();
}
