public String ExportData()
{
//Document variables
DocInfo docInfo = new DocInfo();
System.Boolean hasOfficialUse = false;
string officialText;
try
{
if (!ExportFilePath.isFilePathOK(".txt"))
{
return("Invalid export file path: " + ExportFilePath);
}
BeforeProcessing();
using (var pdfReader = new PdfReader(PdfPath))
{
// For image checking
var parser = new PdfReaderContentParser(pdfReader);
ImageRenderListener listener = null;
// Check to see if doc has "for official use only" at the bottom
ITextExtractionStrategy officialTextRectangle = MakeRectangle(70, 1, 375, 120);
officialText = PdfTextExtractor.GetTextFromPage(pdfReader, 1, officialTextRectangle);
officialText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(officialText)));
if (officialText.ToString().ToUpper().Contains("FOROFFICIALUSEONLY"))
{
hasOfficialUse = true;
}
else
{
hasOfficialUse = false;
}
// Loop through each page of the PDF
for (Int32 currentPage = 1; currentPage <= pdfReader.NumberOfPages; currentPage++)
{
PageInfo currentPageInfo = new PageInfo()
{
PageNum = currentPage
};
ITextExtractionStrategy rectangleStrategy;
float height = pdfReader.GetPageSize(currentPage).Height;
float width = pdfReader.GetPageSize(currentPage).Width;
if (height > 785 && height < 802 && width > 1215 && width < 1230)
{
rectangleStrategy = MakeRectangle(450, 1, 450, 70);
}
else if (height > 785 && height < 802 && width > 608 && width < 617)
{
rectangleStrategy = MakeRectangle(190, 1, 255, 74);
}
else
{
myLogger.Log("Page # " + currentPage.ToString() + " not 8.5 x 11 or 11 x 17");
continue;
}
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, currentPage, rectangleStrategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
if (hasOfficialUse)
{
currentText = OfficialUseRegex.Replace(currentText, "").Trim();
}
ITextExtractionStrategy workPackageIndexStrategy = MakeRectangle(60, 600, 160, 50);
string WPI = PdfTextExtractor.GetTextFromPage(pdfReader, currentPage, workPackageIndexStrategy);
WPI = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(WPI)));
if (WPI.ToUpper().Contains("WORKPACKAGEINDEX"))
{
currentPageInfo.HasWpIndex = true;
}
// #-#
if (NumDashNumRegex.IsMatch(currentText))
{
currentPageInfo.PageNumText = NumDashNumRegex.Match(currentText).Value.Trim();
currentPageInfo.IsWP = true;
}
else
{
// #-#/blank
if (NumDashNumBlankRegex.IsMatch(currentText))
{
currentPageInfo.PageNumText = NumDashNumBlankRegex.Match(currentText).Value.Trim();
currentPageInfo.IsDashBlank = true;
currentPageInfo.IsWP = true;
}
else
{
if (romanNumRegex.IsMatch(currentText.ToUpper().Trim()))
{
currentPageInfo.PageNumText = romanNumRegex.Match(currentText.ToUpper().Trim()).Value.Trim();
if (String.Equals(currentPageInfo.PageNumText.ToUpper(), "C") || String.Equals(currentPageInfo.PageNumText.ToUpper(), "D"))
{
currentPageInfo.PageNumText = currentPageInfo.PageNumText.ToLower();
currentPageInfo.IsLetter = true;
}
else
{
currentPageInfo.IsRoman = true;
}
}
else
{
if (LetterRegex.IsMatch(currentText.Trim()))
{
currentPageInfo.PageNumText = LetterRegex.Match(currentText).Value.Trim();
currentPageInfo.IsLetter = true;
}
else
{
// Check if whole page is empty
parser.ProcessContent(currentPage, (listener = new ImageRenderListener()));
ITextExtractionStrategy currentTextRectangle = MakeRectangle(1, 1, 1000000, 1000000);
String checkText = PdfTextExtractor.GetTextFromPage(pdfReader, currentPage, currentTextRectangle);
checkText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(checkText)));
if ((listener.Images.Count <= 0) && String.IsNullOrWhiteSpace(checkText))
{
currentPageInfo.IsWholePageEmpty = true;
currentPageInfo.IsPageNumAreaBlank = true;
}
else
{
if (String.IsNullOrWhiteSpace(currentText))
{
currentPageInfo.IsPageNumAreaBlank = true;
}
else
{
if (indexRegex.IsMatch(currentText.Trim()))
{
currentPageInfo.PageNumText = indexRegex.Match(currentText).Value.Trim();
currentPageInfo.IsIndex = true;
}
else
{
currentPageInfo.PageNumText = currentText;
currentPageInfo.IsMisc = true;
}
}
}
}
}
}
}
if (Bw.CancellationPending)
{
myLogger.Log("Processing cancelled at dwg #: " + currentPage.ToString());
break;
}
Bw.ReportProgress(Utils.GetPercentage(currentPage, pdfReader.NumberOfPages));
docInfo.Pages.Add(currentPageInfo);
}
}
WriteDocInfoToTextFile(docInfo);
}
catch (System.Exception se)
{
return(se.Message);
}
finally
{
AfterProcessing();
}
return(String.Concat(docInfo.ToString(),
Environment.NewLine,
"Processing completed in ",
timer.Elapsed.TotalSeconds.PrintTimeFromSeconds(),
Environment.NewLine,
myLogger.ErrorCount.ToString(),
" errors found."));
//return String.Concat(
// docInfo.NumSheets,
// "Processing completed in ",
// timer.Elapsed.TotalSeconds.PrintTimeFromSeconds(),
// " with ",
// myLogger.ErrorCount,
// " errors.");
}
public String Split()
{
Int32 currentPage = 1;
Int32 totalPages = 0;
String currentPageField = String.Empty;
String previousWP = String.Empty;
String currentWP = String.Empty;
FileStream outputStream = null;;
PdfWriter writer;
PdfImportedPage pageImport;
byte[] byteArrayPdf;
PdfContentByte cb;
Document doc = null;
try
{
if (!outputFolder.isDirectoryPathOK())
{
return("Invalid output folder");
}
BeforeProcessing();
//Document doc;
PdfReader pdfReaderTemp = new PdfReader(PdfPath);
Document docTemp = new Document(pdfReaderTemp.GetPageSize(currentPage));
outputStream = new FileStream(outputFolder + "\\tmp.pdf", FileMode.OpenOrCreate);
outputStream.Flush();
writer = PdfWriter.GetInstance(docTemp, outputStream);
outputStream.Close();
pdfReaderTemp.Close();
using (PdfReader pdfReader = new PdfReader(PdfPath))
{
totalPages = pdfReader.NumberOfPages;
ITextExtractionStrategy rectangleStrategy;
/*Document*/
doc = new Document(pdfReader.GetPageSize(1));
for (currentPage = 1; currentPage <= pdfReader.NumberOfPages; currentPage++)
{
// Update progress bar
try { Bw.ReportProgress(Utils.GetPercentage(currentPage, pdfReader.NumberOfPages)); }
catch { }
// check if bw is trying to be cancelled
if (Bw == null || Bw.CancellationPending)
{
myLogger.Log("Processing cancelled on PDF #" + currentPage);
break;
}
float height = pdfReader.GetPageSize(currentPage).Height;
float width = pdfReader.GetPageSize(currentPage).Width;
if (height > 785 && height < 802 && width > 1215 && width < 1230)
{
// Page is 11 x 17
rectangleStrategy = MakeRectangle(450, 1, 450, 70);
}
else if (height > 785 && height < 802 && width > 608 && width < 617)
{
// Page is 8.5 x 11
rectangleStrategy = MakeRectangle(190, 1, 255, 74);
}
else
{
myLogger.Log("Page # " + currentPage.ToString() + " not 8.5 x 11 or 11 x 17");
continue;
}
String currentText = PdfTextExtractor.GetTextFromPage(pdfReader, currentPage, rectangleStrategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
if (pageFieldRegex.IsMatch(currentText))
{
currentPageField = pageFieldRegex.Match(currentText).Value.Trim();
currentWP = ExtractWP(currentPageField, false);
}
else
{
if (pageFieldBlankRegex.IsMatch(currentText))
{
currentPageField = pageFieldBlankRegex.Match(currentText).Value.Trim();
currentWP = ExtractWP(currentPageField, true);
}
else
{
continue;
}
}
if (!String.Equals(previousWP, currentWP))
{
//current wp is different than previous
try { doc.Close(); }
catch { }
doc = new Document(pdfReader.GetPageSize(currentPage));
outputStream = new FileStream(outputFolder + "\\" + currentWP + ".pdf", FileMode.Create);
writer = PdfWriter.GetInstance(doc, outputStream);
byteArrayPdf = pdfReader.GetPageContent(currentPage);
doc.Open();
cb = writer.DirectContent;
pageImport = writer.GetImportedPage(pdfReader, currentPage);
cb.AddTemplate(pageImport, 0, 0);
writer.Flush();
previousWP = currentWP;
}
else
{
//current wp is the same as previous
doc.NewPage();
byteArrayPdf = pdfReader.GetPageContent(currentPage);
cb = writer.DirectContent;
pageImport = writer.GetImportedPage(pdfReader, currentPage);
cb.AddTemplate(pageImport, 0, 0);
writer.Flush();
}
}
//try { doc.Close(); }
//catch { }
try { File.Delete(outputFolder + "\\tmp.pdf"); }
catch { }
}// using PdfReader pdfReader
}
catch (System.Exception se)
{
return(se.Message);
}
finally
{
try { doc.Close(); }
catch { }
try { outputStream.Dispose(); }
catch { }
try { File.Delete(outputFolder + "\\tmp.pdf"); }
catch { }
AfterProcessing();
}
return(String.Concat(totalPages.ToString(),
" pages processed in ",
timer.Elapsed.TotalSeconds.PrintTimeFromSeconds(),
" with ",
myLogger.ErrorCount,
" errors."));
}
public String Extract()
{
String currentPageField = String.Empty;
byte[] byteArrayPdf;
PdfContentByte cb;
PdfImportedPage pageImport;
Int32 totalPages = 0;
try
{
if (!WpFile.isFilePathOK())
{
return("Invalid WP file");
}
if (!outputFolder.isDirectoryPathOK())
{
return("Invalid output folder");
}
BeforeProcessing();
HashSet <String> WPs = GetWPsToExtract();
using (PdfReader pdfReader = new PdfReader(PdfPath))
{
using (Document doc = new Document(pdfReader.GetPageSize(1)))
{
using (FileStream outputStream = new FileStream(outputFolder + "\\ExtractedWPs.pdf", FileMode.Create))
{
PdfWriter writer = PdfWriter.GetInstance(doc, outputStream);
totalPages = pdfReader.NumberOfPages;
ITextExtractionStrategy rectangleStrategy;
for (Int32 currentPage = 1; currentPage <= pdfReader.NumberOfPages; currentPage++)
{
String currentWP = String.Empty;
try { Bw.ReportProgress(Utils.GetPercentage(currentPage, pdfReader.NumberOfPages)); }
catch { }
if (Bw.CancellationPending || Bw == null)
{
myLogger.Log("Processing cancelled on PDF #" + currentPage);
break;
}
float height = pdfReader.GetPageSize(currentPage).Height;
float width = pdfReader.GetPageSize(currentPage).Width;
if (height > 785 && height < 802 && width > 1215 && width < 1230)
{
// Page is 11 x 17
rectangleStrategy = MakeRectangle(450, 1, 450, 70);
}
else if (height > 785 && height < 802 && width > 608 && width < 617)
{
// Page is 8.5 x 11
rectangleStrategy = MakeRectangle(190, 1, 255, 74);
}
else
{
myLogger.Log("Page # " + currentPage.ToString() + " not 8.5 x 11 or 11 x 17");
continue;
}
String currentText = PdfTextExtractor.GetTextFromPage(pdfReader, currentPage, rectangleStrategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
if (pageFieldRegex.IsMatch(currentText))
{
currentPageField = pageFieldRegex.Match(currentText).Value.Trim();
currentWP = ExtractWP(currentPageField, false);
}
else
{
if (pageFieldBlankRegex.IsMatch(currentText))
{
currentPageField = pageFieldBlankRegex.Match(currentText).Value.Trim();
currentWP = ExtractWP(currentPageField, true);
}
else
{
// This page has no Page # field/WP, so skip it
continue;
}
}
if (WPs.Contains(currentWP))
{
// Write this page to document
if (!doc.IsOpen())
{
doc.Open();
}
doc.NewPage();
byteArrayPdf = pdfReader.GetPageContent(currentPage);
cb = writer.DirectContent;
pageImport = writer.GetImportedPage(pdfReader, currentPage);
cb.AddTemplate(pageImport, 0, 0);
writer.Flush();
}
}
try { writer.Dispose(); } catch { }
// PdfWriter
} //FileStream
} //Doc
} //PdfReader
}
catch (System.Exception se)
{
return(se.Message);
}
finally
{
AfterProcessing();
}
return(String.Concat(totalPages.ToString(),
" pages processed in ",
timer.Elapsed.TotalSeconds.PrintTimeFromSeconds(),
" with ",
myLogger.ErrorCount,
" errors."));
}