Output data to PDF from a GridView has encoding problems
I'm generating a PDF (using iTextSharp) from a gridview that is present on the page, but the PDF output has encoding issues. For example this on the page:
Aplicação para posicionar
Appears like this on the PDF:
Aplicação para posicionar
I'm a generating this directly from the gridview since I need user input (checkboxes for example) so I can't read this data from a database. I assume some sort of encode/decode is in order, but I'm quite at a loss here.
Steps involved in creating the PDF:
BaseFont helvetica = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.CP1252, false);
Font helvetica14 = new Font(helvetica, 14, Font.NORMAL);
Font helvetica12BOLDITALIC = new Font(helvetica, 12, Font.BOLDITALIC);
Font helvetica8BOLDITALIC = new Font(helvetica, 8, Font.BOLDITALIC);
Font helvetica6 = new Font(helvetica, 6, Font.NORMAL);
//Create PDF document
Document doc = new Document(PageSize.A4);
MemoryStream outputStream = new MemoryStream();
PdfWriter.GetInstance(doc, outputStream);
doc.Open();
//Add title
doc.Add(new Paragraph(importantlblTitleGlobal + "\n\n\n\n", helvetica14));
//Copy the Api Transaction table
if (detailsApiTransactionRowCount > 1)
{
//Create PDF table
PdfPTable tableDetailsInput = new PdfPTable(detailsApiTransactionCellCount);
//Create title table
PdfPCell cell = new PdfPCell(new Phrase("Api Transaction List", helvetica12BOLDITALIC));
cell.BackgroundColor = new BaseColor(128, 128, 128);
cell.Colspan = detailsApiTransactionCellCount;
cell.HorizontalAlignment = 1; //0=Left, 1=Centre, 2=Right
tableDetailsInput.AddCell(cell);
string[] headers = { "Transaction Name", "Transaction Description" };
for (iteratorCell = 0; iteratorCell < detailsApiTransactionCellCount; iteratorCell++)
{
PdfPCell newCell = new PdfPCell(new Phrase(headers[iteratorCell], helvetica8BOLDITALIC));
newCell.BackgroundColor = new BaseColor(192, 192, 192);
tableDetailsInput.AddCell(newCell);
}
//Create content table
for (iteratorRow = 0; iteratorRow < detailsApiTransactionRowCount; iteratorRow++)
{
for (iteratorCell = 0; iteratorCell < detailsApiTransactionCellCount; iteratorCell++)
{
Phrase newPhrase = new Phrase(apiTransactionListGrid.Rows[iteratorRow].Cells[iteratorCell].Text, helvetica6);
tableDetailsInput.AddCell(newPhrase);
}
}
doc.Add(tableDetailsInput);
}
//Line break
doc.Add(new Paragraph("\n\n\n"));
//Copy the INPUT/OUTPUT table
if (detailsInputOutputRowCount > 0)
{
//Create PDF table
PdfPTable tableDetailsInputOutput = new PdfPTable(detailsInputOutputCellCount);
//Create title table
PdfPCell cell = new PdfPCell(new Phrase("Input/Output Details", helvetica12BOLDITALIC));
cell.BackgroundColor = new BaseColor(128, 128, 128);
cell.Colspan = detailsInputOutputCellCount;
cell.HorizontalAlignment = 1; //0=Left, 1=Centre, 2=Right
tableDetailsInputOutput.AddCell(cell);
//Create headers table
string[] headers = { "Name", "Format", "Description", "Observation", "isInput", "isOutput", "SpecialType" };
for (iteratorCell = 0; iteratorCell < detailsInputOutputCellCount; iteratorCell++)
{
PdfPCell newCell = new PdfPCell(new Phrase(headers[iteratorCell], helvetica8BOLDITALIC));
newCell.BackgroundColor = new BaseColor(192, 192, 192);
tableDetailsInputOutput.AddCell(newCell);
}
for (iteratorRow = 0; iteratorRow < detailsInputOutputRowCount; iteratorRow++)
{
for (iteratorCell = 0; iteratorCell < detailsInputOutputCellCount; iteratorCell++)
{
switch (iteratorCell)
{
case 3:
{
if (apiInputOutputGrid.Rows[iteratorRow].Cells[iteratorCell].Text == " ")
tableDetailsInputOutput.AddCell(new Phrase("", helvetica6));
else
tableDetailsInputOutput.AddCell(new Phrase(apiInputOutputGrid.Rows[iteratorRow].Cells[iteratorCell].Text, helvetica6));
}
break;
case 4:
{
if (iteratorRow >= 9)
{
Phrase newPhrase = new Phrase("", helvetica6);
if (booleanIsInput[iteratorRow])
{
newPhrase = new Phrase("X", helvetica6);
tableDetailsInputOutput.AddCell(newPhrase);
}
else
tableDetailsInputOutput.AddCell(newPhrase);
}
else
{
Phrase newPhrase = new Phrase("", helvetica6);
PdfPCell newCell = new PdfPCell(newPhrase);
newCell.BackgroundColor = new BaseColor(192, 192, 192);
tableDetailsInputOutput.AddCell(newCell);
}
}
break;
case 5:
{
if (iteratorRow >= 9)
{
Phrase newPhrase = new Phrase("", helvetica6);
if (booleanIsOutput[iteratorRow])
{
newPhrase = new Phrase("X", helvetica6);
tableDetailsInputOutput.AddCell(newPhrase);
}
else
tableDetailsInputOutput.AddCell(newPhrase);
}
else
{
Phrase newPhrase = new Phrase("", helvetica6);
PdfPCell newCell = new PdfPCell(newPhrase);
newCell.BackgroundColor = new BaseColor(192, 192, 192);
tableDetailsInputOutput.AddCell(newCell);
}
}
break;
case 6:
{
tableDetailsInputOutput.AddCell(new Phrase(specialType[iteratorRow], helvetica6));
}
break;
default:
tableDetailsInputOutput.AddCell(new Phrase(apiInputOutputGrid.Rows[iteratorRow].Cells[iteratorCell].Text, helvetica6));
break;
}
}
}
doc.Add(table开发者_C百科DetailsInputOutput);
}
//CloseDocument
doc.Close();
//Clear the response buffer'
Response.Clear();
//Set the output type as a PDF'
Response.ContentType = "application/pdf";
//Disable caching'
Response.AddHeader("Expires", "0");
Response.AddHeader("Cache-Control", "");
//Set the filename'
string filename = "filename.pdf";
filename = filename.Replace(' ', '_');
Response.AddHeader("Content-Disposition", "attachment; filename=" + filename);
//Set the length of the file so the browser can display an accurate progress bar'
Response.AddHeader("Content-length", outputStream.GetBuffer().Length.ToString());
//Write the contents of the memory stream'
Response.OutputStream.Write(outputStream.GetBuffer(), 0, outputStream.GetBuffer().Length);
//Close the response stream'
Response.End();
Any hints?
EDIT: add a new line. The page is UTF-8, when I define the basefont I can't find UTF in the constants of iTextSharp. EDIT2: Also I just checked the properties of the PDF file in Adobe Reader and it says that it's encoding is Ansi.
Thanks.
Try decoding the Text from the grid, i.e. instead
apiInputOutputGrid.Rows[iteratorRow].Cells[iteratorCell].Text
use (from System.Web):
HttpUtility.HtmlDecode(apiInputOutputGrid.Rows[iteratorRow].Cells[iteratorCell].Text)
Either its an encoding issue in the pdf component,parsing of the pdf, or the data returned from the grid which is prob not new info : ) Check out the grid results and look at each field, etc. Are any of them encoded? Something is html encoding - so need to figure out if its your grid code or the pdf code.
What about adding this to your function:
Response.charset="utf-8"
...or whatever the charset should be, if not utf-8 -- maybe latin 1?
Otherwise, this SO post looks like it might be related to yours: Html to pdf some characters are missing (itextsharp)
精彩评论