/// <summary>Scan the DOM tree for all (internal) link targets</summary>
/// <param name="root">the DOM tree root node</param>
/// <returns>this LinkContext</returns>
public virtual iText.Html2pdf.Attach.Impl.LinkContext ScanForIds(INode root)
{
// clear previous
linkDestinations.Clear();
// expensive scan operation
while (root.ParentNode() != null)
{
root = root.ParentNode();
}
Stack <INode> stk = new Stack <INode>();
stk.Push(root);
while (!stk.IsEmpty())
{
INode n = stk.Pop();
if (n is IElementNode)
{
IElementNode elem = (IElementNode)n;
if (TagConstants.A.Equals(elem.Name()))
{
String href = elem.GetAttribute(AttributeConstants.HREF);
if (href != null && href.StartsWith("#"))
{
linkDestinations.Add(href.Substring(1));
}
}
}
if (!n.ChildNodes().IsEmpty())
{
stk.AddAll(n.ChildNodes());
}
}
return(this);
}
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);
}
}
}
