[PDFBOX-2778] PDF to Image conversion fails with "Invalid code word encountered"

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.8.9, 2.0.0
• Fix Version/s: 1.8.10, 2.0.0
• Component/s: Rendering
• Labels: CCITTFaxDecode ccitt
• Assignee: Tilman Hausherr
• Reporter: Siegfried Goeschl
• Created: 28/Apr/15 19:05
• Updated: 23/Jul/15 06:35
• Resolved: 30/Apr/15 16:55

Description

One real-life PDF throws

pdfbox-1.8.9> ./pdf-to-image.sh pdf/invalid-code-word-01.pdf
java -jar pdfbox-app-1.8.9.jar PDFToImage pdf/invalid-code-word-01.pdf
Apr 28, 2015 8:57:43 PM org.apache.pdfbox.util.operator.pagedrawer.Invoke process
SEVERE: java.io.IOException: Invalid code word encountered
java.io.IOException: Invalid code word encountered
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:360)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream$NonLeafLookupTreeNode.getNextCodeWord(CCITTFaxG31DDecodeInputStream.java:358)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream.decodeLine(CCITTFaxG31DDecodeInputStream.java:143)
at org.apache.pdfbox.io.ccitt.CCITTFaxG31DDecodeInputStream.read(CCITTFaxG31DDecodeInputStream.java:104)
at java.io.InputStream.read(InputStream.java:170)
at java.io.FilterInputStream.read(FilterInputStream.java:133)
at org.apache.pdfbox.io.ccitt.FillOrderChangeInputStream.read(FillOrderChangeInputStream.java:45)
at java.io.FilterInputStream.read(FilterInputStream.java:107)
at org.apache.pdfbox.io.IOUtils.copy(IOUtils.java:68)
at org.apache.pdfbox.io.IOUtils.toByteArray(IOUtils.java:52)
at org.apache.pdfbox.filter.CCITTFaxDecodeFilter.decode(CCITTFaxDecodeFilter.java:110)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:379)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.graphics.xobject.PDCcitt.getRGBImage(PDCcitt.java:201)
at org.apache.pdfbox.util.operator.pagedrawer.Invoke.process(Invoke.java:87)
at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:557)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:268)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.pdfviewer.PageDrawer.drawPage(PageDrawer.java:139)
at org.apache.pdfbox.pdmodel.PDPage.convertToImage(PDPage.java:801)
at org.apache.pdfbox.util.PDFImageWriter.writeImage(PDFImageWriter.java:130)
at org.apache.pdfbox.PDFToImage.main(PDFToImage.java:226)
at org.apache.pdfbox.PDFBox.main(PDFBox.java:96)