private void InitializeIgnoredObjectPath(CleanUpImagesCompareTool.PageImageObjectsPaths cmpPageObjects, CleanUpImagesCompareTool.PageImageObjectsPaths
outPageObjects)
{
try {
IList <PdfIndirectReference> cmpIndirects = cmpPageObjects.GetIndirectReferences();
IList <PdfIndirectReference> outIndirects = outPageObjects.GetIndirectReferences();
PdfIndirectReference baseCmpIndirect = cmpIndirects[0];
PdfIndirectReference baseOutIndirect = outIndirects[0];
ObjectPath baseObjectPath = new ObjectPath(baseCmpIndirect, baseCmpIndirect);
for (int i = 1; i < cmpIndirects.Count; i++)
{
baseObjectPath.ResetDirectPath(cmpIndirects[i], outIndirects[i]);
baseCmpIndirect = cmpIndirects[i];
baseOutIndirect = outIndirects[i];
}
foreach (Stack <LocalPathItem> path in cmpPageObjects.GetDirectPaths())
{
ignoredObjectPaths.Add(new ObjectPath(baseCmpIndirect, baseOutIndirect, path, baseObjectPath.GetIndirectPath
()));
}
}
catch (Exception) {
throw new ArgumentException("Out and cmp pdf documents have different object structure");
}
}
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);
}
}
}
