[
https://issues.apache.org/jira/browse/PDFBOX-616?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
James A. Thomas updated PDFBOX-616:
-----------------------------------
Description:
When getting images from a PDF document using PDXObjectImage (code fragment
below), it returns an image with invalid characteristics. The PDXObjectImage
is not null, but attributes like .getColorSpace() return null. The image has a
height and width, but the getRGBImage() method returns null.
This happens on EVERY image of the attached file. Code fragment and output is
shown below.
If I use the write2file() method of PDXObjectImage to write out the image to a
fil, then I get a valid image. (At least, it displays fine.)
Code Fragment:
// Get a list of pages from the input PDF document
List pages = InputDoc.getDocumentCatalog().getAllPages();
// Process each page
int i = 0;
for (Object obj : pages)
{
String Barcode = null;
i++;
PDPage page = (PDPage)obj;
// Get the image on the page and process it
PDResources resources = page.getResources();
Map images = resources.getImages();
System.out.println("Found " + images.size() + " images on
Page " + i);
if( images != null )
{
Iterator imageIter = images.keySet().iterator();
while ( imageIter.hasNext() )
{
String key = (String)imageIter.next();
System.out.println("key = " + key);
PDXObjectImage image = (PDXObjectImage)images.get(
key );
if (image != null)
{
System.out.println("Image subtype = " +
image.SUB_TYPE.toString());
System.out.println("Image suffix = " +
image.getSuffix());
System.out.println("PDX image has height = " +
image.getHeight()
+ " and width " +
image.getWidth());
// Convert image to a Buffered Image, so we can
// look for a barcode and decode it
BufferedImage RGBimage = image.getRGBImage();
if (RGBimage == null)
System.out.println("RGBimage is null");
}
}
}
Output:
Found 1 images on Page 1
key = Obj3
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 2
key = Obj8
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 3
key = Obj13
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 4
key = Obj18
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 5
key = Obj23
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 6
key = Obj28
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 7
key = Obj33
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 8
key = Obj38
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 9
key = Obj43
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 10
key = Obj48
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
was:
When getting images from a PDF document using PDXObjectImage (code fragment
below), it returns an image with invalid characteristics. The PDXObjectImage
is not null, but attributes like .getColorSpace() return null. The image has a
height and width, but the getRGBImage() method returns null.
This happens on EVERY image of the attached file. Code fragment and output is
shown below.
Code Fragment:
// Get a list of pages from the input PDF document
List pages = InputDoc.getDocumentCatalog().getAllPages();
// Process each page
int i = 0;
for (Object obj : pages)
{
String Barcode = null;
i++;
PDPage page = (PDPage)obj;
// Get the image on the page and process it
PDResources resources = page.getResources();
Map images = resources.getImages();
System.out.println("Found " + images.size() + " images on
Page " + i);
if( images != null )
{
Iterator imageIter = images.keySet().iterator();
while ( imageIter.hasNext() )
{
String key = (String)imageIter.next();
System.out.println("key = " + key);
PDXObjectImage image = (PDXObjectImage)images.get(
key );
if (image != null)
{
System.out.println("Image subtype = " +
image.SUB_TYPE.toString());
System.out.println("Image suffix = " +
image.getSuffix());
System.out.println("PDX image has height = " +
image.getHeight()
+ " and width " +
image.getWidth());
// Convert image to a Buffered Image, so we can
// look for a barcode and decode it
BufferedImage RGBimage = image.getRGBImage();
if (RGBimage == null)
System.out.println("RGBimage is null");
}
}
}
Output:
Found 1 images on Page 1
key = Obj3
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 2
key = Obj8
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 3
key = Obj13
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 4
key = Obj18
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 5
key = Obj23
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 6
key = Obj28
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 7
key = Obj33
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 8
key = Obj38
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 9
key = Obj43
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
Found 1 images on Page 10
key = Obj48
Image subtype = Image
Image suffix = tiff
PDX image has height = 2335 and width 1651
RGBimage is null
> Invalid Images Returned
> -----------------------
>
> Key: PDFBOX-616
> URL: https://issues.apache.org/jira/browse/PDFBOX-616
> Project: PDFBox
> Issue Type: Bug
> Components: PDModel
> Affects Versions: 0.8.0-incubator
> Environment: Multiple (Windows)
> Reporter: James A. Thomas
> Attachments: TIFFimageProblem.pdf
>
>
> When getting images from a PDF document using PDXObjectImage (code fragment
> below), it returns an image with invalid characteristics. The PDXObjectImage
> is not null, but attributes like .getColorSpace() return null. The image has
> a height and width, but the getRGBImage() method returns null.
> This happens on EVERY image of the attached file. Code fragment and output
> is shown below.
> If I use the write2file() method of PDXObjectImage to write out the image to
> a fil, then I get a valid image. (At least, it displays fine.)
> Code Fragment:
> // Get a list of pages from the input PDF document
> List pages = InputDoc.getDocumentCatalog().getAllPages();
> // Process each page
> int i = 0;
> for (Object obj : pages)
> {
> String Barcode = null;
> i++;
> PDPage page = (PDPage)obj;
> // Get the image on the page and process it
> PDResources resources = page.getResources();
> Map images = resources.getImages();
> System.out.println("Found " + images.size() + " images on
> Page " + i);
> if( images != null )
> {
> Iterator imageIter = images.keySet().iterator();
> while ( imageIter.hasNext() )
> {
> String key = (String)imageIter.next();
> System.out.println("key = " + key);
> PDXObjectImage image =
> (PDXObjectImage)images.get( key );
> if (image != null)
> {
> System.out.println("Image subtype = " +
> image.SUB_TYPE.toString());
> System.out.println("Image suffix = " +
> image.getSuffix());
> System.out.println("PDX image has height = " +
> image.getHeight()
> + " and width " +
> image.getWidth());
> // Convert image to a Buffered Image, so we can
> // look for a barcode and decode it
> BufferedImage RGBimage = image.getRGBImage();
> if (RGBimage == null)
> System.out.println("RGBimage is null");
> }
> }
> }
> Output:
> Found 1 images on Page 1
> key = Obj3
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 2
> key = Obj8
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 3
> key = Obj13
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 4
> key = Obj18
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 5
> key = Obj23
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 6
> key = Obj28
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 7
> key = Obj33
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 8
> key = Obj38
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 9
> key = Obj43
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
> Found 1 images on Page 10
> key = Obj48
> Image subtype = Image
> Image suffix = tiff
> PDX image has height = 2335 and width 1651
> RGBimage is null
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
