public void RunPdfTron(string input_path)
{
PDFNet.Initialize();
// string output_path = "../../../../TestFiles/Output/";
try
{
// Open the test file
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
PageIterator itr;
ElementReader page_reader = new ElementReader();
for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next()) // Read every page
{
int pageno = itr.GetPageNumber();
page_reader.Begin(itr.Current());
ProcessElements(page_reader);
page_reader.End();
}
page_reader.Dispose(); // Calling Dispose() on ElementReader/Writer/Builder can result in increased performance and lower memory consumption.
doc.Close();
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
PDFNet.Terminate();
}
protected override void Dispose(bool disposing)
{
base.Dispose(disposing);
mPdfViewCtrl?.CloseDoc();
mPdfViewCtrl = null;
mPdfDoc?.Close();
mPdfDoc = null;
}
public void Dispose()
{
if (pdfDoc != null)
{
pdfDoc.Close();
pdfDoc.Dispose();
}
pdfDoc = null;
}
public FileStreamWithPdftron(string pdfFilePath, FileItemStreamType streamType, WaterMarkInfo watermarkInfo)
{
var tempFilePath = string.Empty;
try
{
tempFilePath = Path.GetTempFileName();
pdftron.PDFNet.Initialize(Properties.Settings.Default.PDFTronLicense);
using (var doc = new PDFDoc(pdfFilePath))
{
if (null != watermarkInfo)
{
WatermarkFile(doc, watermarkInfo);
}
if (streamType == FileItemStreamType.Downloadable)
{
doc.Save(tempFilePath, SDFDoc.SaveOptions.e_compatibility);
}
else
{
Convert.ToXod(doc, tempFilePath);
}
doc.Close();
}
_wrappedStream = new FileStreamWithDelete(tempFilePath, FileMode.Open);
}
catch
{
if (File.Exists(tempFilePath))
{
File.Delete(tempFilePath);
}
throw;
}
finally
{
if (File.Exists(pdfFilePath))
{
File.Delete(pdfFilePath);
}
}
}
protected override void Dispose(bool disposing)
{
base.Dispose(disposing);
PTTabbedDocumentViewController tabbedDocumentViewController = mTabViewController;
mTabViewController = null;
nuint index = tabbedDocumentViewController.SelectedIndex;
PTDocumentViewController documentViewController = tabbedDocumentViewController.SelectedViewController;
PDFDoc pdfDoc = TypeConvertHelper.ConvPdfDocToManaged(documentViewController.PdfViewCtrl.GetDoc());
documentViewController.CloseDocumentWithCompletionHandler((bool success) => {
pdfDoc.Close();
pdfDoc = null;
});
tabbedDocumentViewController.RemoveTabAtIndex(index);
tabbedDocumentViewController = null;
GC.Collect();
}
public void ReadTextFromCoordinates(string input_path, int pagenumber, int urx, int ury, int llx, int lly)
{
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
Page page = doc.GetPage(pagenumber);
ElementReader reader = new ElementReader();
PageIterator itr = doc.GetPageIterator();
reader.Begin(itr.Current());
LowLevelTextExtractUtils u = new LowLevelTextExtractUtils();
//u.DumpAllText(reader);
//ConsoleLog += u.ConsoleLog;
//reader.End();
string field3 = u.ReadTextFromRect(page, new Rect(urx, ury, llx, lly), reader);
ConsoleLog = field3;
reader.Dispose();
doc.Close();
}
// GET: api/InboundFax/5
public HttpResponseMessage Get(string id)
{
HttpResponseMessage result = new HttpResponseMessage(HttpStatusCode.OK);
try
{
Logging.LogErrors(ConfigurationValues.ErrorLogPath, ConfigurationValues.PdfTronLicenseKey);
PDFNet.Initialize(ConfigurationValues.PdfTronLicenseKey);
PDFDoc documentToAdd = new PDFDoc();
string xodFileName = Guid.NewGuid().ToString() + ".xod";
string pdfFileName = xodFileName.Replace(".xod", ".pdf");
string filePathXod = ConfigurationValues.PathToXodFile + xodFileName;
string filePathPdf = ConfigurationValues.PathToXodFile + pdfFileName;
PDFDoc newDocument = new PDFDoc();
if (string.IsNullOrEmpty(id))
{
try
{
File.Delete(filePathXod);
}
catch { }
File.Create(filePathXod).Dispose();
result = new HttpResponseMessage(HttpStatusCode.OK);
var stream = new FileStream(filePathXod, FileMode.Open);
result.Content = new StreamContent(stream);
result.Content.Headers.ContentType =
new MediaTypeHeaderValue("application/octet-stream");
result.Content.Headers.ContentDisposition = new ContentDispositionHeaderValue("attachment")
{
FileName = ConfigurationValues.XodFileName
};
return result;
}
else
{
string[] documents = id.Split('~');
for (int i = 0; i < documents.Length - 1; i++)
{
FaxRepository faxData = new FaxRepository();
//documentToAdd = new PDFDoc(faxData.GetFullPathInboundFax(documents[i]));
documentToAdd = new PDFDoc(documents[i]);
PageIterator itr = documentToAdd.GetPageIterator();
for (; itr.HasNext(); itr.Next())
{
try
{
pdftron.PDF.Page page = itr.Current();
newDocument.PageInsert(newDocument.GetPageIterator(itr.GetPageNumber()), page);
}
catch (Exception er)
{
string s1 = er.ToString();
}
}
}
try
{
File.Delete(filePathXod);
}
catch { }
documentToAdd.Close();
documentToAdd.Dispose();
DocumentRepository documentData = new DocumentRepository();
documentData.AddUpdateCurrentDocument(Utility.GetUserName(), filePathXod, filePathPdf, id, documentData.GetFullPathToDocument(Utility.GetUserName()));
File.Create(filePathXod).Dispose();
newDocument.Save(filePathPdf, 0);
pdftron.Filters.Filter objFilter = pdftron.PDF.Convert.ToXod(newDocument);
System.Threading.Thread.Sleep(ConfigurationValues.XodSaveDelay);
objFilter.WriteToFile(filePathXod, true);
var stream = new FileStream(filePathXod, FileMode.Open);
result.Content = new StreamContent(stream);
result.Content.Headers.ContentType =
new MediaTypeHeaderValue("application/octet-stream");
result.Content.Headers.ContentDisposition = new ContentDispositionHeaderValue("attachment")
{
FileName = ConfigurationValues.XodFileName
};
newDocument.Close();
newDocument.Dispose();
}
return result;
}
catch (Exception er)
{
Logging.LogErrors(ConfigurationValues.ErrorLogPath, er.ToString());
return result;
}
}
public void ReadAdvanced(string input_path)
{
PDFNet.Initialize();
try
{
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
Page page = doc.GetPage(1);
if (page == null)
{
ConsoleLog += "Page not found.";
return;
}
TextExtractor txt = new TextExtractor();
txt.Begin(page); // Read the page.
// Other options you may want to consider...
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_no_dup_remove);
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_remove_hidden_text);
// ...
// Example 1. Get all text on the page in a single string.
// Words will be separated with space or new line characters.
if (example1_basic)
{
// Get the word count.
ConsoleLog += "Word Count: {0}" + txt.GetWordCount();
ConsoleLog += "\n\n- GetAsText --------------------------\n{0}" + txt.GetAsText();
ConsoleLog += "-----------------------------------------------------------";
}
// Example 2. Get XML logical structure for the page.
if (example2_xml)
{
String text = txt.GetAsXML(TextExtractor.XMLOutputFlags.e_words_as_elements | TextExtractor.XMLOutputFlags.e_output_bbox | TextExtractor.XMLOutputFlags.e_output_style_info);
ConsoleLog += "\n\n- GetAsXML --------------------------\n{0}" + text;
ConsoleLog += "-----------------------------------------------------------";
}
// Example 3. Extract words one by one.
if (example3_wordlist)
{
TextExtractor.Word word;
for (TextExtractor.Line line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
ConsoleLog += word.GetString();
}
}
ConsoleLog += "-----------------------------------------------------------";
}
// Example 3. A more advanced text extraction example.
// The output is XML structure containing paragraphs, lines, words,
// as well as style and positioning information.
if (example4_advanced)
{
Rect bbox;
int cur_flow_id = -1, cur_para_id = -1;
TextExtractor.Line line;
TextExtractor.Word word;
TextExtractor.Style s, line_style;
// For each line on the page...
for (line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
if (line.GetNumWords() == 0)
{
continue;
}
if (cur_flow_id != line.GetFlowID())
{
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
ConsoleLog += "</Para>";
}
ConsoleLog += "</Flow>";
}
cur_flow_id = line.GetFlowID();
ConsoleLog += "<Flow id=\"{0}\">" + cur_flow_id;
}
if (cur_para_id != line.GetParagraphID())
{
if (cur_para_id != -1)
{
ConsoleLog += "</Para>";
}
cur_para_id = line.GetParagraphID();
ConsoleLog += "<Para id=\"{0}\">" + cur_para_id;
}
bbox = line.GetBBox();
line_style = line.GetStyle();
Console.Write("<Line box=\"" + bbox.y1 + "," + bbox.y2 + "," + bbox.x1 + "," + bbox.x2 + ">");
PrintStyle(line_style);
ConsoleLog += "";
// For each word in the line...
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
// Output the bounding box for the word.
bbox = word.GetBBox();
ConsoleLog += "<Word box=\"{0}, {1}, {2}, {3}\"" + bbox.x1 + bbox.y1 + bbox.x2 + bbox.y2;
int sz = word.GetStringLen();
if (sz == 0)
{
continue;
}
// If the word style is different from the parent style, output the new style.
s = word.GetStyle();
if (s != line_style)
{
PrintStyle(s);
}
ConsoleLog += ">\n" + word.GetString();
ConsoleLog += "</Word>";
}
ConsoleLog += "</Line>";
}
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
ConsoleLog += "</Para>";
}
ConsoleLog += "</Flow>";
}
}
// Note: Calling Dispose() on TextExtractor when it is not anymore in use can result in increased performance and lower memory consumption.
txt.Dispose();
doc.Close();
ConsoleLog += "Done.";
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
// Sample code showing how to use low-level text extraction APIs.
if (example5_low_level)
{
try
{
LowLevelTextExtractUtils util = new LowLevelTextExtractUtils();
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
// Example 1. Extract all text content from the document
ElementReader reader = new ElementReader();
PageIterator itr = doc.GetPageIterator();
//for (; itr.HasNext(); itr.Next()) // Read every page
{
reader.Begin(itr.Current());
LowLevelTextExtractUtils u = new LowLevelTextExtractUtils();
u.DumpAllText(reader);
ConsoleLog += u.ConsoleLog;
reader.End();
}
// Example 2. Extract text based on the selection rectangle.
ConsoleLog += "----------------------------------------------------";
ConsoleLog += "Extract text based on the selection rectangle.";
ConsoleLog += "----------------------------------------------------";
Page first_page = doc.GetPage(1);
string field1 = util.ReadTextFromRect(first_page, new Rect(27, 392, 563, 534), reader);
string field2 = util.ReadTextFromRect(first_page, new Rect(28, 551, 106, 623), reader);
string field3 = util.ReadTextFromRect(first_page, new Rect(208, 550, 387, 621), reader);
ConsoleLog += "Field 1: {0}" + field1;
ConsoleLog += "Field 2: {0}" + field2;
ConsoleLog += "Field 3: {0}" + field3;
// ...
reader.Dispose();
doc.Close();
ConsoleLog += "Done.";
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
}
PDFNet.Terminate();
}
/// <summary>
/// The main entry point for the application.
/// </summary>
static void Main()
{
// Initialize PDFNet before calling any other PDFNet function.
PDFNet.Initialize();
string input_path = "../../TestFiles/";
string output_path = "../../TestFiles/Output/";
string input_filename = "US061222892-a.pdf";
PDFDoc pdf_doc = new PDFDoc(input_path + input_filename);
pdf_doc.InitSecurityHandler();
SDFDoc cos_doc = pdf_doc.GetSDFDoc();
int num_objs = cos_doc.XRefSize();
for (int i = 1; i < num_objs; ++i)
{
Obj obj = cos_doc.GetObj(i);
if (obj != null && !obj.IsFree() && obj.IsStream())
{
// Process only images
DictIterator itr = obj.Find("Subtype");
if (!itr.HasNext() || itr.Value().GetName() != "Image")
{
continue;
}
pdftron.PDF.Image input_image = new pdftron.PDF.Image(obj);
pdftron.PDF.Image new_image = null;
// Process only gray-scale images
if (input_image.GetComponentNum() != 1)
{
continue;
}
int bpc = input_image.GetBitsPerComponent();
if (bpc != 1) // Recompress 1 BPC images
{
continue;
}
// Skip images that are already compressed using JBIG2
itr = obj.Find("Filter");
if (itr.HasNext() && itr.Value().IsName() &&
itr.Value().GetName() == "JBIG2Decode")
{
continue;
}
FilterReader reader = new FilterReader(obj.GetDecodedStream());
ObjSet hint_set = new ObjSet();
Obj hint = hint_set.CreateArray();
hint.PushBackName("JBIG2");
hint.PushBackName("Lossless");
hint.PushBackName("Threshold");
hint.PushBackNumber(0.4);
hint.PushBackName("SharePages");
hint.PushBackNumber(10000);
new_image = pdftron.PDF.Image.Create(
cos_doc,
reader,
input_image.GetImageWidth(),
input_image.GetImageHeight(),
1,
ColorSpace.CreateDeviceGray(),
hint // A hint to image encoder to use JBIG2 compression
);
Obj new_img_obj = new_image.GetSDFObj();
// Copy any important entries from the image dictionary
itr = obj.Find("ImageMask");
if (itr.HasNext())
{
new_img_obj.Put("ImageMask", itr.Value());
}
itr = obj.Find("Mask");
if (itr.HasNext())
{
new_img_obj.Put("Mask", itr.Value());
}
cos_doc.Swap(i, new_image.GetSDFObj().GetObjNum());
}
}
pdf_doc.Save(output_path + "US061222892_JBIG2.pdf", SDFDoc.SaveOptions.e_remove_unused);
pdf_doc.Close();
}
// GET: api/SeparatePDF/5
public IHttpActionResult Get(string id)
{
try
{
id = id + ",";
PDFNet.Initialize(ConfigurationValues.PdfTronLicenseKey);
string[] pagesSeparationGroups = id.Split('~');
string[] newPdfNames = new string[pagesSeparationGroups.Length - 1];
PDFDoc[] newPdfDocs = new PDFDoc[pagesSeparationGroups.Length - 1];
for (int i = 0; i < newPdfNames.Length; i++)
{
newPdfNames[i] = Guid.NewGuid().ToString() + ".pdf";
newPdfDocs[i] = new PDFDoc();
}
DocumentRepository documentData = new DocumentRepository();
CurrentDocuments currentDocuments = documentData.GetCurrentDocumentPathPdf(Utility.GetUserName());
string[] currentDocumentCount = currentDocuments.CurrentDocumentList.Split('~');
string[] currentDocumentList = currentDocumentCount[0].Split('\\');
string pathToCurrentPdfFile = currentDocuments.PathToCurrentPdfDocument;
string currentPdfPath = currentDocumentCount[0].Replace(currentDocumentList[currentDocumentList.Length - 1], "");
PDFDoc separatePagesFromDocument = new PDFDoc(pathToCurrentPdfFile);
for (int i = 0; i < pagesSeparationGroups.Length - 1; i++)
{
string[] beginEndPageValues = pagesSeparationGroups[i].Split(',');
string pagesSeparationBegin = beginEndPageValues[0];
string pagesSeparationEnd = beginEndPageValues[1];
if (pagesSeparationBegin.Length > 0)
{
newPdfDocs[i].InsertPages(0, separatePagesFromDocument, int.Parse(pagesSeparationBegin), int.Parse(pagesSeparationEnd), PDFDoc.InsertFlag.e_none);
//newPdfDocs[i].Save(ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\" + newPdfNames[i], 0);
newPdfDocs[i].Save(currentPdfPath + newPdfNames[i], 0);
}
}
separatePagesFromDocument.Close();
separatePagesFromDocument.Dispose();
File.Delete(currentDocumentCount[0]);
for (int i = 0; i < newPdfNames.Length; i++)
{
newPdfDocs[i].Close();
newPdfDocs[i].Dispose();
}
string[] deleteTheDocumentList = currentDocuments.CurrentDocumentList.Split('~');
for (int i = 0; i < deleteTheDocumentList.Length - 1; i++)
{
try
{
File.Delete(ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\" + deleteTheDocumentList[i]);
}
catch { }
}
// ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\"
return Ok();
}
catch
{
return BadRequest("Error in splitting document. Please try again");
}
}
// GET: api/FileFromFolder/5
public HttpResponseMessage Get(string id)
{
string fullPath = System.Configuration.ConfigurationManager.AppSettings["holdFolder"] + id;
PDFNet.Initialize("CT Orthopaedic Specialists(ct-ortho.com):ENTCPU:1::W:AMS(20160714):DF4FD2223CBF58B9128E100F400DD2BC2BFD701DC22C3C2E6D83F6B6F5C7");
PDFDoc documentToAdd = new PDFDoc();
string xodFileName = Guid.NewGuid().ToString() + ".xod";
string pdfFileName = xodFileName.Replace(".xod", ".pdf");
string filePathXod = ConfigurationValues.PathToXodFile + xodFileName;
string filePathPdf = ConfigurationValues.PathToXodFile + pdfFileName;
PDFDoc newDocument = new PDFDoc();
if (string.IsNullOrEmpty(id))
{
try
{
File.Delete(filePathXod);
}
catch { }
File.Create(filePathXod).Dispose();
HttpResponseMessage result = new HttpResponseMessage(HttpStatusCode.OK);
var stream = new FileStream(filePathXod, FileMode.Open);
result.Content = new StreamContent(stream);
result.Content.Headers.ContentType =
new MediaTypeHeaderValue("application/octet-stream");
result.Content.Headers.ContentDisposition = new ContentDispositionHeaderValue("attachment")
{
FileName = ConfigurationValues.XodFileName
};
return result;
}
else
{
string[] documents = id.Split('~');
documentToAdd = new PDFDoc(fullPath);
PageIterator itr = documentToAdd.GetPageIterator();
for (; itr.HasNext(); itr.Next())
{
try
{
pdftron.PDF.Page page = itr.Current();
newDocument.PageInsert(newDocument.GetPageIterator(itr.GetPageNumber()), page);
}
catch (Exception er)
{
string s1 = er.ToString();
}
}
try
{
File.Delete(filePathXod);
}
catch { }
documentToAdd.Close();
documentToAdd.Dispose();
DocumentRepository documentData = new DocumentRepository();
documentData.AddUpdateCurrentDocument(Utility.GetUserName(), filePathXod, filePathPdf, id, documentData.GetFullPathToDocument(Utility.GetUserName()));
File.Create(filePathXod).Dispose();
newDocument.Save(filePathPdf, 0);
pdftron.Filters.Filter objFilter = pdftron.PDF.Convert.ToXod(newDocument);
System.Threading.Thread.Sleep(ConfigurationValues.XodSaveDelay);
objFilter.WriteToFile(filePathXod, true);
HttpResponseMessage result = new HttpResponseMessage(HttpStatusCode.OK);
var stream = new FileStream(filePathXod, FileMode.Open);
result.Content = new StreamContent(stream);
result.Content.Headers.ContentType =
new MediaTypeHeaderValue("application/octet-stream");
result.Content.Headers.ContentDisposition = new ContentDispositionHeaderValue("attachment")
{
FileName = ConfigurationValues.XodFileName
};
newDocument.Close();
newDocument.Dispose();
return result;
}
}
// GET: api/SeparatePDF/5
public HttpResponseMessage Get(string id)
//public string Get(string id)
{
id = id + ",";
PDFNet.Initialize("CT Orthopaedic Specialists(ct-ortho.com):ENTCPU:1::W:AMS(20160714):DF4FD2223CBF58B9128E100F400DD2BC2BFD701DC22C3C2E6D83F6B6F5C7");
PDFDoc newDocument = new PDFDoc();
string[] pagesSeparationGroups = id.Split(',');
string[] newPDFNames = new string[pagesSeparationGroups.Length - 1];
PDFDoc[] NewPDFDocs = new PDFDoc[pagesSeparationGroups.Length - 1];
//string pathToCurrentPdfFile = documentData.GetCurrentDocumentPathPDF(Utility.GetUserName());
for (int i = 0; i < newPDFNames.Length; i++)
{
newPDFNames[i] = Guid.NewGuid().ToString() + ".pdf";
NewPDFDocs[i] = new PDFDoc();
}
DocumentRepository documentData = new DocumentRepository();
//int pageCount = 0;
CurrentDocuments currentDocuments = documentData.GetCurrentDocumentPathPDF(Utility.GetUserName());
string pathToCurrentPdfFile = currentDocuments.PathToCurrentPDFDocument;
//string[] fileName = pathToCurrentPdfFile.Split('\\');
//File.Move(pathToCurrentPdfFile, ConfigurationValues.TemporaryFaxPath + "\\" + pathToCurrentPdfFile[pathToCurrentPdfFile.Length - 1]);
PDFDoc separatePagesFromDocument = new PDFDoc(pathToCurrentPdfFile);
for (int i = 0; i < pagesSeparationGroups.Length - 1; i++)
{
string[] pagesSeparation = pagesSeparationGroups[i].Split('-');
//PageIterator itr = separatePagesFromDocument.GetPageIterator(i);
NewPDFDocs[i].InsertPages(0, separatePagesFromDocument, int.Parse(pagesSeparation[0]), int.Parse(pagesSeparation[1]), PDFDoc.InsertFlag.e_none);
NewPDFDocs[i].Save(ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\" + newPDFNames[i], 0);
}
// string pathToCurrentPdfFileTemp = pathToCurrentPdfFile.Replace(".pdf", "temp.pdf");
//string pathToCurrentXodFile = documentData.GetCurrentDocumentPathXOD(Utility.GetUserName());
separatePagesFromDocument.Close();
separatePagesFromDocument.Dispose();
File.Delete(pathToCurrentPdfFile);
for (int i = 0; i < newPDFNames.Length; i++)
{
NewPDFDocs[i].Close();
NewPDFDocs[i].Dispose();
}
string[] deleteTheDocumentList = currentDocuments.CurrentDocumentList.Split('~');
for (int i = 0; i < deleteTheDocumentList.Length - 1; i++)
{
File.Delete(ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\" + deleteTheDocumentList[i]);
}
// ConfigurationValues.OutboundFaxDirectory + "\\" + Utility.GetUserName() + "\\"
HttpResponseMessage result = new HttpResponseMessage(HttpStatusCode.OK);
return result;
}
