public void ExtractTextTest1()
{
PDFManager pdfManager = new PDFManager(); // TODO: Initialize to an appropriate value
//byte[] input = File.ReadAllBytes(DiscoveryManager.GetDiscoveryPath("M:\\DFD", "http://unicode.org/charts/PDF/U0590.pdf", ".pdf"));
byte[] input = File.ReadAllBytes(@"");
string path = @"M:\COL\hebrew.pdf";
string destinationFileName = @"M:\COL\hebrew1.pdf";
PdfReader reader = new PdfReader(path);
int n = reader.NumberOfPages;
Document document = new Document(PageSize.A4);
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(destinationFileName, FileMode.Create));
int i = 0;
document.Open();
PdfContentByte cb = writer.DirectContent;
PdfTemplate template = cb.CreateTemplate(0, 0);
while (i < n)
{
document.NewPage();
i++;
PdfImportedPage importedPage = writer.GetImportedPage(reader, i);
Image img = Image.GetInstance(importedPage);
img.ScalePercent(100);
document.Add(img);
cb.AddTemplate(importedPage, 0, 100);
}
document.Close();
writer.Close();
PdfReader pdfReader = new PdfReader(input);
StringBuilder stringBuilder = new StringBuilder();
string dingle = string.Empty;
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
stringBuilder.Append(pdfManager.ExtractText(pdfReader.GetPageContent(page)) + " ");
PRTokeniser prTokeniser = new PRTokeniser(pdfReader.GetPageContent(page));
PdfDictionary pdfDictionary = pdfReader.GetPageN(page);
byte[] dinas = pdfReader.GetPageContent(page);
string winsdgf = Encoding.GetEncoding(1255).GetString(dinas);
try
{
while (prTokeniser.NextToken())
{
if (prTokeniser.TokenType == PRTokeniser.TokType.STRING)
{
dingle += prTokeniser.StringValue;
try
{
//dingle += (char)(int.Parse(prTokeniser.StringValue));
//dingle += iTextSharp.text.Utilities.ConvertFromUtf32(prTokeniser.FilePointer);
//dingle += ((char)prTokeniser.Read()).ToString();
dingle += prTokeniser.ReadString(2);
Chunk chunk = new Chunk(prTokeniser.StringValue);
//string wangle = PRTokeniser.GetHex(prTokeniser.IntValue).ToString();
}
catch (Exception)
{
}
}
}
}
catch (Exception)
{
{
}
//throw;
}
//int ij = 0;
// #
//If Not IsNothing(pageBytes) Then
//#
// token = New PRTokeniser(pageBytes)
//#
// While token.NextToken()
//#
// tknType = token.TokenType()
//#
// tknValue = token.StringValue
//#
// If tknType = PRTokeniser.TK_STRING Then
//#
// sb.Append(token.StringValue)
//#
// 'I need to add these additional tests to properly add whitespace to the output string
//#
// ElseIf tknType = 1 AndAlso tknValue = "-600" Then
//#
// sb.Append(" ")
//#
// ElseIf tknType = 10 AndAlso tknValue = "TJ" Then
//#
// sb.Append(" ")
//#
// End If
//#
// End While
}
string actual = pdfManager.ExtractText(input);
}
