You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@pdfbox.apache.org by "John Hewson (JIRA)" <ji...@apache.org> on 2016/08/26 19:49:20 UTC
[jira] [Updated] (PDFBOX-3474) OutofMemoryError while converting
pdf to image
[ https://issues.apache.org/jira/browse/PDFBOX-3474?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
John Hewson updated PDFBOX-3474:
--------------------------------
Description:
Our test PDF contain 4-5 pages with one images in each page. Our requirement is to convert each page to image. While doing load testing on this use case (about 10-15 threads), JVM runs out of memory with following error.
{code}
Caused by: java.lang.OutOfMemoryError: Java heap space
at org.apache.pdfbox.io.ScratchFileBuffer.addPage(ScratchFileBuffer.java:121)
at org.apache.pdfbox.io.ScratchFileBuffer.ensureAvailableBytesInPage(ScratchFileBuffer.java:184)
at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:236)
at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:220)
at org.apache.pdfbox.io.RandomAccessOutputStream.write(RandomAccessOutputStream.java:52)
at org.apache.pdfbox.filter.DCTFilter.decode(DCTFilter.java:174)
at org.apache.pdfbox.cos.COSInputStream.create(COSInputStream.java:69)
at org.apache.pdfbox.cos.COSStream.createInputStream(COSStream.java:163)
at org.apache.pdfbox.pdmodel.common.PDStream.createInputStream(PDStream.java:235)
at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.createInputStream(PDImageXObject.java:565)
at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.from8bit(SampledImageReader.java:233)
at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.getRGBImage(SampledImageReader.java:138)
at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:340)
at org.apache.pdfbox.rendering.PageDrawer.drawImage(PageDrawer.java:793)
at org.apache.pdfbox.contentstream.operator.graphics.DrawObject.process(DrawObject.java:62)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:815)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:472)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:446)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:149)
at org.apache.pdfbox.rendering.PageDrawer.drawPage(PageDrawer.java:189)
at org.apache.pdfbox.rendering.PDFRenderer.renderPage(PDFRenderer.java:208)
at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:139)
at org.apache.pdfbox.rendering.PDFRenderer.renderImageWithDPI(PDFRenderer.java:94)
{code}
CODE:
{code}
private List<Image> convertPDFToImage(ByteArrayOutputStream pdf) throws AXOLServiceException, IOException{
List<Image> images =new ArrayList<Image>();
PDDocument document = PDDocument.load(pdf.toByteArray(),"",null,null,MemoryUsageSetting.setupMainMemoryOnly(5347737));
PDFRenderer pdfRenderer = new PDFRenderer(document);
long contentLength = 0;
for (int page = 0; page < document.getNumberOfPages(); ++page)
{
BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
ByteArrayOutputStream tmp = new ByteArrayOutputStream();
ImageIO.write(bim, "jpeg", tmp);
tmp.flush();
tmp.close();
bim.flush();
contentLength += tmp.size();
if(contentLength>5347737){
document.close();
throw new RuntimeException("Exceeds maximum allowed size limit", EAUDocumentService.EAU_ERR_CODE_EXCCEDS_SIZE_LIMIT, "");
}
images.add(bim);
}
document.close();
return images;
}
{code}
was:
Our test PDF contain 4-5 pages with one images in each page. Our requirement is to convert each page to image. While doing load testing on this use case (about 10-15 threads), JVM runs out of memory with following error.
Caused by: java.lang.OutOfMemoryError: Java heap space
at org.apache.pdfbox.io.ScratchFileBuffer.addPage(ScratchFileBuffer.java:121)
at org.apache.pdfbox.io.ScratchFileBuffer.ensureAvailableBytesInPage(ScratchFileBuffer.java:184)
at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:236)
at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:220)
at org.apache.pdfbox.io.RandomAccessOutputStream.write(RandomAccessOutputStream.java:52)
at org.apache.pdfbox.filter.DCTFilter.decode(DCTFilter.java:174)
at org.apache.pdfbox.cos.COSInputStream.create(COSInputStream.java:69)
at org.apache.pdfbox.cos.COSStream.createInputStream(COSStream.java:163)
at org.apache.pdfbox.pdmodel.common.PDStream.createInputStream(PDStream.java:235)
at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.createInputStream(PDImageXObject.java:565)
at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.from8bit(SampledImageReader.java:233)
at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.getRGBImage(SampledImageReader.java:138)
at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:340)
at org.apache.pdfbox.rendering.PageDrawer.drawImage(PageDrawer.java:793)
at org.apache.pdfbox.contentstream.operator.graphics.DrawObject.process(DrawObject.java:62)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:815)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:472)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:446)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:149)
at org.apache.pdfbox.rendering.PageDrawer.drawPage(PageDrawer.java:189)
at org.apache.pdfbox.rendering.PDFRenderer.renderPage(PDFRenderer.java:208)
at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:139)
at org.apache.pdfbox.rendering.PDFRenderer.renderImageWithDPI(PDFRenderer.java:94)
CODE:
private List<Image> convertPDFToImage(ByteArrayOutputStream pdf) throws AXOLServiceException, IOException{
List<Image> images =new ArrayList<Image>();
PDDocument document = PDDocument.load(pdf.toByteArray(),"",null,null,MemoryUsageSetting.setupMainMemoryOnly(5347737));
PDFRenderer pdfRenderer = new PDFRenderer(document);
long contentLength = 0;
for (int page = 0; page < document.getNumberOfPages(); ++page)
{
BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
ByteArrayOutputStream tmp = new ByteArrayOutputStream();
ImageIO.write(bim, "jpeg", tmp);
tmp.flush();
tmp.close();
bim.flush();
contentLength += tmp.size();
if(contentLength>5347737){
document.close();
throw new RuntimeException("Exceeds maximum allowed size limit", EAUDocumentService.EAU_ERR_CODE_EXCCEDS_SIZE_LIMIT, "");
}
images.add(bim);
}
document.close();
return images;
}
> OutofMemoryError while converting pdf to image
> ----------------------------------------------
>
> Key: PDFBOX-3474
> URL: https://issues.apache.org/jira/browse/PDFBOX-3474
> Project: PDFBox
> Issue Type: Bug
> Components: PDModel
> Affects Versions: 2.0.2
> Environment: Development
> Reporter: Nehal
> Priority: Blocker
>
> Our test PDF contain 4-5 pages with one images in each page. Our requirement is to convert each page to image. While doing load testing on this use case (about 10-15 threads), JVM runs out of memory with following error.
> {code}
> Caused by: java.lang.OutOfMemoryError: Java heap space
> at org.apache.pdfbox.io.ScratchFileBuffer.addPage(ScratchFileBuffer.java:121)
> at org.apache.pdfbox.io.ScratchFileBuffer.ensureAvailableBytesInPage(ScratchFileBuffer.java:184)
> at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:236)
> at org.apache.pdfbox.io.ScratchFileBuffer.write(ScratchFileBuffer.java:220)
> at org.apache.pdfbox.io.RandomAccessOutputStream.write(RandomAccessOutputStream.java:52)
> at org.apache.pdfbox.filter.DCTFilter.decode(DCTFilter.java:174)
> at org.apache.pdfbox.cos.COSInputStream.create(COSInputStream.java:69)
> at org.apache.pdfbox.cos.COSStream.createInputStream(COSStream.java:163)
> at org.apache.pdfbox.pdmodel.common.PDStream.createInputStream(PDStream.java:235)
> at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.createInputStream(PDImageXObject.java:565)
> at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.from8bit(SampledImageReader.java:233)
> at org.apache.pdfbox.pdmodel.graphics.image.SampledImageReader.getRGBImage(SampledImageReader.java:138)
> at org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject.getImage(PDImageXObject.java:340)
> at org.apache.pdfbox.rendering.PageDrawer.drawImage(PageDrawer.java:793)
> at org.apache.pdfbox.contentstream.operator.graphics.DrawObject.process(DrawObject.java:62)
> at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:815)
> at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:472)
> at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:446)
> at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:149)
> at org.apache.pdfbox.rendering.PageDrawer.drawPage(PageDrawer.java:189)
> at org.apache.pdfbox.rendering.PDFRenderer.renderPage(PDFRenderer.java:208)
> at org.apache.pdfbox.rendering.PDFRenderer.renderImage(PDFRenderer.java:139)
> at org.apache.pdfbox.rendering.PDFRenderer.renderImageWithDPI(PDFRenderer.java:94)
> {code}
> CODE:
> {code}
> private List<Image> convertPDFToImage(ByteArrayOutputStream pdf) throws AXOLServiceException, IOException{
>
> List<Image> images =new ArrayList<Image>();
>
> PDDocument document = PDDocument.load(pdf.toByteArray(),"",null,null,MemoryUsageSetting.setupMainMemoryOnly(5347737));
>
> PDFRenderer pdfRenderer = new PDFRenderer(document);
> long contentLength = 0;
> for (int page = 0; page < document.getNumberOfPages(); ++page)
> {
> BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
> ByteArrayOutputStream tmp = new ByteArrayOutputStream();
> ImageIO.write(bim, "jpeg", tmp);
> tmp.flush();
> tmp.close();
> bim.flush();
>
> contentLength += tmp.size();
>
> if(contentLength>5347737){
> document.close();
> throw new RuntimeException("Exceeds maximum allowed size limit", EAUDocumentService.EAU_ERR_CODE_EXCCEDS_SIZE_LIMIT, "");
> }
> images.add(bim);
> }
> document.close();
> return images;
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@pdfbox.apache.org
For additional commands, e-mail: dev-help@pdfbox.apache.org