public static PdfFileSpec Wrap(PdfDictionary dictionary)
{
if (!PdfName.EncryptedPayload.Equals(dictionary.GetAsName(PdfName.AFRelationship)))
{
LogManager.GetLogger(typeof(PdfEncryptedPayloadFileSpecFactory)).Error(iText.IO.LogMessageConstant.ENCRYPTED_PAYLOAD_FILE_SPEC_SHALL_HAVE_AFRELATIONSHIP_FILED_EQUAL_TO_ENCRYPTED_PAYLOAD
);
}
PdfDictionary ef = dictionary.GetAsDictionary(PdfName.EF);
if (ef == null || (ef.GetAsStream(PdfName.F) == null) && (ef.GetAsStream(PdfName.UF) == null))
{
throw new PdfException(PdfException.EncryptedPayloadFileSpecShallHaveEFDictionary);
}
if (!PdfName.Filespec.Equals(dictionary.GetAsName(PdfName.Type)))
{
throw new PdfException(PdfException.EncryptedPayloadFileSpecShallHaveTypeEqualToFilespec);
}
if (!dictionary.IsIndirect())
{
throw new PdfException(PdfException.EncryptedPayloadFileSpecShallBeIndirect);
}
PdfFileSpec fileSpec = PdfFileSpec.WrapFileSpecObject(dictionary);
if (PdfEncryptedPayload.ExtractFrom(fileSpec) == null)
{
throw new PdfException(PdfException.EncryptedPayloadFileSpecDoesntHaveEncryptedPayloadDictionary);
}
return(fileSpec);
}
private bool UpdateStructParentTreeForContentStreamEntries(IDictionary <int, PdfMcr> mcrsOfContentStream, int
pageStructParentIndex)
{
// element indices in parentsOfMcrs shall be the same as mcid of one of their kids.
// See "Finding Structure Elements from Content Items" in pdf spec.
PdfArray parentsOfMcrs = new PdfArray();
int currentMcid = 0;
foreach (KeyValuePair <int, PdfMcr> entry in mcrsOfContentStream)
{
PdfMcr mcr = entry.Value;
PdfDictionary parentObj = ((PdfStructElem)mcr.GetParent()).GetPdfObject();
if (!parentObj.IsIndirect())
{
continue;
}
// if for some reason some mcrs were not registered or don't exist, we ensure that the rest
// of the parent objects were placed at correct index
while (currentMcid++ < mcr.GetMcid())
{
parentsOfMcrs.Add(PdfNull.PDF_NULL);
}
parentsOfMcrs.Add(parentObj);
}
if (!parentsOfMcrs.IsEmpty())
{
parentsOfMcrs.MakeIndirect(structTreeRoot.GetDocument());
parentTree.AddEntry(pageStructParentIndex, parentsOfMcrs);
structTreeRoot.GetDocument().CheckIsoConformance(parentsOfMcrs, IsoKey.TAG_STRUCTURE_ELEMENT);
parentsOfMcrs.Flush();
return(true);
}
return(false);
}
private bool UpdateStructParentTreeEntries(PdfPage page, IDictionary <int, PdfMcr> mcrs)
{
bool res = false;
// element indexes in parentsOfPageMcrs shall be the same as mcid of one of their kids.
// See "Finding Structure Elements from Content Items" in pdf spec.
PdfArray parentsOfPageMcrs = new PdfArray();
int currentMcid = 0;
foreach (KeyValuePair <int, PdfMcr> entry in mcrs)
{
PdfMcr mcr = entry.Value;
PdfDictionary parentObj = ((PdfStructElem)mcr.GetParent()).GetPdfObject();
if (!parentObj.IsIndirect())
{
continue;
}
if (mcr is PdfObjRef)
{
int structParent = KeyIntoStructParentIndex((int)entry.Key);
parentTree.AddEntry(structParent, parentObj);
res = true;
}
else
{
// if for some reason some mcr where not registered or don't exist, we ensure that the rest
// of the parent objects were placed at correct index
while (currentMcid++ < mcr.GetMcid())
{
parentsOfPageMcrs.Add(PdfNull.PDF_NULL);
}
parentsOfPageMcrs.Add(parentObj);
}
}
if (!parentsOfPageMcrs.IsEmpty())
{
int pageStructParentIndex;
if (page.IsFlushed())
{
PdfIndirectReference pageRef = page.GetPdfObject().GetIndirectReference();
if (!pageToStructParentsInd.ContainsKey(pageRef))
{
return(res);
}
pageStructParentIndex = (int)pageToStructParentsInd.JRemove(pageRef);
}
else
{
pageStructParentIndex = GetOrCreatePageStructParentIndex(page);
}
parentsOfPageMcrs.MakeIndirect(structTreeRoot.GetDocument());
parentTree.AddEntry(pageStructParentIndex, parentsOfPageMcrs);
res = true;
structTreeRoot.GetDocument().CheckIsoConformance(parentsOfPageMcrs, IsoKey.TAG_STRUCTURE_ELEMENT);
parentsOfPageMcrs.Flush();
}
return(res);
}
private bool UpdateStructParentTreeEntries(PdfPage page, ParentTreeHandler.PageMcrsContainer mcrs)
{
bool res = false;
foreach (KeyValuePair <int, PdfMcr> entry in mcrs.GetObjRefs())
{
PdfMcr mcr = entry.Value;
PdfDictionary parentObj = ((PdfStructElem)mcr.GetParent()).GetPdfObject();
if (!parentObj.IsIndirect())
{
continue;
}
int structParent = entry.Key;
parentTree.AddEntry(structParent, parentObj);
res = true;
}
int pageStructParentIndex;
foreach (KeyValuePair <PdfIndirectReference, SortedDictionary <int, PdfMcr> > entry in mcrs.GetPageResourceXObjects
())
{
PdfIndirectReference xObjectRef = entry.Key;
if (xObjectToStructParentsInd.ContainsKey(xObjectRef))
{
pageStructParentIndex = (int)xObjectToStructParentsInd.JRemove(xObjectRef);
if (UpdateStructParentTreeForContentStreamEntries(entry.Value, pageStructParentIndex))
{
res = true;
}
}
}
if (page.IsFlushed())
{
PdfIndirectReference pageRef = page.GetPdfObject().GetIndirectReference();
if (!pageToStructParentsInd.ContainsKey(pageRef))
{
return(res);
}
pageStructParentIndex = (int)pageToStructParentsInd.JRemove(pageRef);
}
else
{
pageStructParentIndex = GetOrCreatePageStructParentIndex(page);
}
if (UpdateStructParentTreeForContentStreamEntries(mcrs.GetPageContentStreamsMcrs(), pageStructParentIndex)
)
{
res = true;
}
return(res);
}
private void UpdateStructParentTreeEntries(PdfPage page, IDictionary <int, PdfMcr> mcrs)
{
// element indexes in parentsOfPageMcrs shall be the same as mcid of one of their kids.
// See "Finding Structure Elements from Content Items" in pdf spec.
PdfArray parentsOfPageMcrs = new PdfArray();
int currentMcid = 0;
foreach (KeyValuePair <int, PdfMcr> entry in mcrs)
{
PdfMcr mcr = entry.Value;
PdfDictionary parentObj = ((PdfStructElem)mcr.GetParent()).GetPdfObject();
if (!parentObj.IsIndirect())
{
continue;
}
if (mcr is PdfObjRef)
{
int structParent = KeyIntoStructParentIndex((int)entry.Key);
parentTree.AddEntry(structParent, parentObj);
}
else
{
// if for some reason some mcr where not registered or don't exist, we ensure that the rest
// of the parent objects were placed at correct index
while (currentMcid++ < mcr.GetMcid())
{
parentsOfPageMcrs.Add(PdfNull.PDF_NULL);
}
parentsOfPageMcrs.Add(parentObj);
}
}
if (parentsOfPageMcrs.Size() > 0)
{
parentsOfPageMcrs.MakeIndirect(structTreeRoot.GetDocument());
int structParents = page.GetStructParentIndex() != -1 ? page.GetStructParentIndex() : page.GetDocument().GetNextStructParentIndex
();
page.GetPdfObject().Put(PdfName.StructParents, new PdfNumber(structParents));
parentTree.AddEntry(structParents, parentsOfPageMcrs);
structTreeRoot.GetDocument().CheckIsoConformance(parentsOfPageMcrs, IsoKey.TAG_STRUCTURE_ELEMENT);
parentsOfPageMcrs.Flush();
}
}
private static PdfDictionary CopyObject(PdfDictionary source, ICollection <PdfObject> objectsToCopy, PdfDocument
toDocument, IDictionary <PdfDictionary, PdfDictionary> page2page, bool copyFromDestDocument)
{
PdfDictionary copied;
if (copyFromDestDocument)
{
copied = source.Clone(ignoreKeysForCopy);
if (source.IsIndirect())
{
copied.MakeIndirect(toDocument);
}
}
else
{
copied = source.CopyTo(toDocument, ignoreKeysForCopy, true);
}
if (source.ContainsKey(PdfName.Obj))
{
PdfDictionary obj = source.GetAsDictionary(PdfName.Obj);
if (!copyFromDestDocument && obj != null)
{
// Link annotations could be not added to the toDocument, so we need to identify this case.
// When obj.copyTo is called, and annotation was already copied, we would get this already created copy.
// If it was already copied and added, /P key would be set. Otherwise /P won't be set.
obj = obj.CopyTo(toDocument, iText.IO.Util.JavaUtil.ArraysAsList(PdfName.P), false);
copied.Put(PdfName.Obj, obj);
}
}
PdfDictionary pg = source.GetAsDictionary(PdfName.Pg);
if (pg != null)
{
//TODO It is possible, that pg will not be present in the page2page map. Consider the situation,
// that we want to copy structElem because it has marked content dictionary reference, which belongs to the page from page2page,
// but the structElem itself has /Pg which value could be arbitrary page.
copied.Put(PdfName.Pg, page2page.Get(pg));
}
PdfObject k = source.Get(PdfName.K);
if (k != null)
{
if (k.IsArray())
{
PdfArray kArr = (PdfArray)k;
PdfArray newArr = new PdfArray();
for (int i = 0; i < kArr.Size(); i++)
{
PdfObject copiedKid = CopyObjectKid(kArr.Get(i), copied, objectsToCopy, toDocument, page2page, copyFromDestDocument
);
if (copiedKid != null)
{
newArr.Add(copiedKid);
}
}
// TODO new array may be empty or with single element
copied.Put(PdfName.K, newArr);
}
else
{
PdfObject copiedKid = CopyObjectKid(k, copied, objectsToCopy, toDocument, page2page, copyFromDestDocument);
if (copiedKid != null)
{
copied.Put(PdfName.K, copiedKid);
}
}
}
return(copied);
}
private static PdfDictionary CopyObject(PdfDictionary source, PdfDictionary destPage, bool parentChangePg,
StructureTreeCopier.StructElemCopyingParams copyingParams)
{
PdfDictionary copied;
if (copyingParams.IsCopyFromDestDocument())
{
//TODO: detect wether object is needed to be cloned at all
copied = source.Clone(ignoreKeysForClone);
if (source.IsIndirect())
{
copied.MakeIndirect(copyingParams.GetToDocument());
}
PdfDictionary pg = source.GetAsDictionary(PdfName.Pg);
if (pg != null)
{
if (copyingParams.IsCopyFromDestDocument())
{
if (pg != destPage)
{
copied.Put(PdfName.Pg, destPage);
parentChangePg = true;
}
else
{
parentChangePg = false;
}
}
}
}
else
{
copied = source.CopyTo(copyingParams.GetToDocument(), ignoreKeysForCopy, true);
PdfDictionary obj = source.GetAsDictionary(PdfName.Obj);
if (obj != null)
{
// Link annotations could be not added to the toDocument, so we need to identify this case.
// When obj.copyTo is called, and annotation was already copied, we would get this already created copy.
// If it was already copied and added, /P key would be set. Otherwise /P won't be set.
obj = obj.CopyTo(copyingParams.GetToDocument(), JavaUtil.ArraysAsList(PdfName.P), false);
copied.Put(PdfName.Obj, obj);
}
PdfDictionary nsDict = source.GetAsDictionary(PdfName.NS);
if (nsDict != null)
{
PdfDictionary copiedNsDict = CopyNamespaceDict(nsDict, copyingParams);
copied.Put(PdfName.NS, copiedNsDict);
}
PdfDictionary pg = source.GetAsDictionary(PdfName.Pg);
if (pg != null)
{
PdfDictionary pageAnalog = copyingParams.GetPage2page().Get(pg);
if (pageAnalog == null)
{
pageAnalog = destPage;
parentChangePg = true;
}
else
{
parentChangePg = false;
}
copied.Put(PdfName.Pg, pageAnalog);
}
}
PdfObject k = source.Get(PdfName.K);
if (k != null)
{
if (k.IsArray())
{
PdfArray kArr = (PdfArray)k;
PdfArray newArr = new PdfArray();
for (int i = 0; i < kArr.Size(); i++)
{
PdfObject copiedKid = CopyObjectKid(kArr.Get(i), copied, destPage, parentChangePg, copyingParams);
if (copiedKid != null)
{
newArr.Add(copiedKid);
}
}
if (!newArr.IsEmpty())
{
if (newArr.Size() == 1)
{
copied.Put(PdfName.K, newArr.Get(0));
}
else
{
copied.Put(PdfName.K, newArr);
}
}
}
else
{
PdfObject copiedKid = CopyObjectKid(k, copied, destPage, parentChangePg, copyingParams);
if (copiedKid != null)
{
copied.Put(PdfName.K, copiedKid);
}
}
}
return(copied);
}
private IDictionary <int, CleanUpImagesCompareTool.PageImageObjectsPaths> ExtractImagesFromPdf(String pdf,
String outputPath)
{
using (PdfReader readerPdf = new PdfReader(pdf)) {
using (PdfDocument pdfDoc = new PdfDocument(readerPdf)) {
IDictionary <int, CleanUpImagesCompareTool.PageImageObjectsPaths> imageObjectDatas = new Dictionary <int, CleanUpImagesCompareTool.PageImageObjectsPaths
>();
for (int i = 1; i <= pdfDoc.GetNumberOfPages(); i++)
{
PdfPage page = pdfDoc.GetPage(i);
CleanUpImagesCompareTool.PageImageObjectsPaths imageObjectData = new CleanUpImagesCompareTool.PageImageObjectsPaths
(page.GetPdfObject().GetIndirectReference());
Stack <LocalPathItem> baseLocalPath = new Stack <LocalPathItem>();
PdfResources pdfResources = page.GetResources();
if (pdfResources.GetPdfObject().IsIndirect())
{
imageObjectData.AddIndirectReference(pdfResources.GetPdfObject().GetIndirectReference());
}
else
{
baseLocalPath.Push(new DictPathItem(PdfName.Resources));
}
PdfDictionary xObjects = pdfResources.GetResource(PdfName.XObject);
if (xObjects == null)
{
continue;
}
if (xObjects.IsIndirect())
{
imageObjectData.AddIndirectReference(xObjects.GetIndirectReference());
baseLocalPath.Clear();
}
else
{
baseLocalPath.Push(new DictPathItem(PdfName.XObject));
}
bool isPageToGsExtract = false;
foreach (PdfName objectName in xObjects.KeySet())
{
if (!xObjects.Get(objectName).IsStream() || !PdfName.Image.Equals(xObjects.GetAsStream(objectName).GetAsName
(PdfName.Subtype)))
{
continue;
}
PdfImageXObject pdfObject = new PdfImageXObject(xObjects.GetAsStream(objectName));
baseLocalPath.Push(new DictPathItem(objectName));
if (!useGs)
{
String extension = pdfObject.IdentifyImageFileExtension();
String fileName = outputPath + objectName + "_" + i + "." + extension;
CreateImageFromPdfXObject(fileName, pdfObject);
}
else
{
isPageToGsExtract = true;
}
Stack <LocalPathItem> reversedStack = new Stack <LocalPathItem>();
reversedStack.AddAll(baseLocalPath);
Stack <LocalPathItem> resultStack = new Stack <LocalPathItem>();
resultStack.AddAll(reversedStack);
imageObjectData.AddLocalPath(resultStack);
baseLocalPath.Pop();
}
if (useGs && isPageToGsExtract)
{
String fileName = "Page_" + i;
ghostscriptHelper.RunGhostScriptImageGeneration(pdf, outputPath, fileName, i.ToString());
}
CleanUpImagesCompareTool.ImageRenderListener listener = new CleanUpImagesCompareTool.ImageRenderListener();
PdfCanvasProcessor parser = new PdfCanvasProcessor(listener);
parser.ProcessPageContent(page);
ignoredImagesAreas.Put(i, listener.GetImageRectangles());
imageObjectDatas.Put(i, imageObjectData);
}
return(imageObjectDatas);
}
}
}
