问题
I cannot locate within the FAQ whether this functionality exists in the API although its mentioned in a book as something that is potentially available. Has anyone had any experience implementing this feature?
回答1:
On This thread (dated June 2007) Paulo Soares provides code that shows support for PDF/A. Here's the C# code (he also has a Java sample):
private void PdfATest() {
Document doc = new Document(PageSize.A4);
PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream("C:\\hello_A1-b_cs.pdf", FileMode.Create));
writer.PDFXConformance = PdfWriter.PDFA1B;
doc.Open();
PdfDictionary outi = new PdfDictionary(PdfName.OUTPUTINTENT);
outi.Put(PdfName.OUTPUTCONDITIONIDENTIFIER, new PdfString("sRGB IEC61966-2.1"));
outi.Put(PdfName.INFO, new PdfString("sRGB IEC61966-2.1"));
outi.Put(PdfName.S, PdfName.GTS_PDFA1);
// get this file here: http://old.nabble.com/attachment/10971467/0/srgb.profile
ICC_Profile icc = ICC_Profile.GetInstance("c:\\srgb.profile");
PdfICCBased ib = new PdfICCBased(icc);
ib.Remove(PdfName.ALTERNATE);
outi.Put(PdfName.DESTOUTPUTPROFILE, writer.AddToBody(ib).IndirectReference);
writer.ExtraCatalog.Put(PdfName.OUTPUTINTENTS, new PdfArray(outi));
BaseFont bf = BaseFont.CreateFont("c:\\windows\\fonts\\arial.ttf", BaseFont.WINANSI, true);
Font f = new iTextSharp.text.Font(bf, 12);
doc.Add(new Paragraph("hello", f));
writer.CreateXmpMetadata();
doc.Close();
}
The link above includes a download for the ICC_Profile file.
回答2:
Here's my method for parsing an HTML file and creating a PDF/A archive document from it, also with embedding fonts by using a stylesheet (in order to avoid the error: "All the fonts must be embedded. This one isn't: Helvetica")
Hope this helps someone..
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using iTextSharp.text.pdf;
using iTextSharp.text;
using System.IO;
using iTextSharp.text.html.simpleparser;
namespace SaveAsPDF
{
class HtmlPdfConverter
{
public void RendererWebForm2PDFArchive(string fileName)
{
Console.WriteLine("Parsing HTML " + fileName);
Document document = new Document(PageSize.A4);
try
{
// we create a writer that listens to the document and directs a XML-stream to a file
PdfWriter writer = PdfWriter.GetInstance(document, new FileStream(fileName + ".pdf", FileMode.Create));
//set document as arhive
writer.PDFXConformance = PdfWriter.PDFA1A;
document.Open();
//apply stylesheet to change font (and embedd it)
StyleSheet styles = new StyleSheet();
FontFactory.Register("c:\\windows\\fonts\\verdana.ttf");
styles.LoadTagStyle("body", "face", "Verdana");
//prepare html
StreamReader sr = new StreamReader(fileName, Encoding.Default);
string html = sr.ReadToEnd();
html = RemoveTag(html, "<title>", "</title>");
//convert string to stream
byte[] byteArray = Encoding.UTF8.GetBytes(html);
MemoryStream ms = new MemoryStream(byteArray);
//parse html
HTMLWorker htmlWorker = new HTMLWorker(document);
System.Collections.Generic.List<IElement> elements;
elements = HTMLWorker.ParseToList(new StreamReader(ms), styles);
foreach (IElement item in elements)
{
document.Add(item);
}
writer.CreateXmpMetadata();
document.Close();
Console.WriteLine("Done");
}
catch (Exception e)
{
Console.Error.WriteLine(e.Message);
Console.Error.WriteLine(e.StackTrace);
}
}**strong text**
来源:https://stackoverflow.com/questions/2366851/can-itextsharp-convert-pdf-document-to-pdf-a