[
https://issues.apache.org/jira/browse/PDFBOX-4407?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16726737#comment-16726737
]
Dan Anderson commented on PDFBOX-4407:
--------------------------------------
>From your comment on another issue, it looks like 2.0.14 release will probably
>be in about 3 months?
> ParentTree Objects do not match KArray objects after merge
> ----------------------------------------------------------
>
> Key: PDFBOX-4407
> URL: https://issues.apache.org/jira/browse/PDFBOX-4407
> Project: PDFBox
> Issue Type: Bug
> Components: Utilities
> Affects Versions: 2.0.13
> Reporter: Dan Anderson
> Assignee: Tilman Hausherr
> Priority: Major
> Labels: StructureTree
> Fix For: 2.0.14, 3.0.0 PDFBox
>
> Attachments: 4407.patch, reading-order-merged-bad.pdf,
> reading-order-merged-good.pdf, reading-order.pdf
>
>
> After merging tagged documents together, the second page of the resulting
> document is no longer valid. When the field objects are cloned in
> PDFMergerUtility, the new and old objects are stored in a map named
> objMapping. This is used to replace the old references with the new
> references for the acroform, k array, and annotation list. However the
> ParentTree is not updated to this new object reference. This results in the
> K Array and the Parent Tree having different references to the same object.
> This causes issues when using an a11y reader like Jaws, and also causes
> problems displaying the tags in Adobe DC.
> Here is a failing unit test that was created in PDFMergerUtilityTest to
> demonstrate the issue. It was created using an example from W3:
> https://www.w3.org/WAI/WCAG20/Techniques/working-examples/PDF3/reading-order.pdf
> {code:java}
> public void testStructureTreeMerge3() throws IOException
> {
> PDFMergerUtility pdfMergerUtility = new PDFMergerUtility();
> PDDocument src = PDDocument.load(new File(SRCDIR, "reading-order.pdf"));
> PDDocument dst = PDDocument.load(new File(SRCDIR, "reading-order.pdf"));
> pdfMergerUtility.appendDocument(dst, src);
> src.close();
> dst.save(new File(TARGETTESTDIR, "reading-order-merged.pdf"));
> dst.close();
> PDDocument doc = PDDocument.load(new File(TARGETTESTDIR,
> "reading-order-merged.pdf"));
>
> assertTrue(checkAnnotationMatches(doc.getDocumentCatalog().getStructureTreeRoot().getKArray(),
> doc.getDocumentCatalog().getAcroForm().getFields(),
> (COSArray)doc.getDocumentCatalog().getStructureTreeRoot().getParentTree().getCOSObject().getDictionaryObject(COSName.NUMS)));
> }
> private boolean checkAnnotationMatches(COSArray kArray, List<PDField>
> acroformFields, COSArray numbersArray) {
> for (int i = 0; i < kArray.size(); i++) {
> COSBase entry = kArray.get(i);
> if (entry instanceof COSArray){
> COSArray entryAsArray = (COSArray) entry;
> if (!checkAnnotationMatches(entryAsArray, acroformFields,
> numbersArray)) {
> return false;
> }
> } else if (entry instanceof COSInteger) {
> //do nothing, just need to screen these out so next line doesn't
> blow up
> } else if (((COSObject) entry).getObject() instanceof COSDictionary){
> COSDictionary entryDictionary = (COSDictionary)((COSObject)
> entry).getObject();
> if (entryDictionary.getItem(COSName.K) != null) {
> COSBase kids = entryDictionary.getItem(COSName.K);
> if (kids != null) {
> if (kids instanceof COSInteger) {
> //do nothing, don't care about marked content tags
> } else if (kids instanceof COSDictionary) {
> COSDictionary kidsAsDictionary = (COSDictionary) kids;
> if
> (!checkForMatches(kidsAsDictionary.getDictionaryObject(COSName.OBJ),
> acroformFields, numbersArray)) {
> return false;
> }
> } else if (kids instanceof COSArray) {
> COSArray kidsAsArray = (COSArray) kids;
> if (!checkAnnotationMatches(kidsAsArray,
> acroformFields, numbersArray)) {
> return false;
> }
> }
> }
> } else if (entryDictionary.getDictionaryObject(COSName.OBJ) !=
> null) {
> if
> (!checkForMatches(entryDictionary.getDictionaryObject(COSName.OBJ),
> acroformFields, numbersArray)) {
> return false;
> }
> }
> }
> }
> return true;
> }
> private boolean checkForMatches(COSBase objectReference, List<PDField>
> acroformFields, COSArray numbersArray) {
> boolean result = false;
> for (PDField field : acroformFields) {
> if (field.getCOSObject() == objectReference &&
> numbersArray.indexOfObject(objectReference.getCOSObject()) > 0) {
> result = true;
> }
> }
> return result;
> }
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@pdfbox.apache.org
For additional commands, e-mail: dev-h...@pdfbox.apache.org
