我正在从 tiff 文件生成 pdf。使用 Acrobat 7 打开时出现无法识别令牌类型的错误。我只看到全文中的一些文字，但没有看到这个pdf中的图片！
使用 acrobat reader XI 可以正确查看 pdf。当我向下滚动时，我收到一条消息，指出此文件中有错误，但没有更多信息。
有谁知道问题出在哪里？我在 Itext 中尝试了许多 PDF 版本，但没有其他结果！
这是一些代码：
Clock.hocr.Elements.hDocument hdoc = new Clock.hocr.Elements.hDocument();
hdoc.AddFile("out3.html");
Clock.hocr.PDFSettings pdfset = new Clock.hocr.PDFSettings();
pdfset.ImageType = Clock.hocr.PdfImageType.JPeg;
pdfset.ImageQuality = 50;
//pdfset.Subject = "Fulltext";
//pdfset.Title = "ft";
//pdfset.Language = "german";
//pdfset.Author = "datapool";
pdfset.Dpi=300;
//pdfset.Keywords="...";
//pdfset.PdfOcrMode =Clock.hocr.OcrMode.Tesseract;
pdfset.WriteTextMode = Clock.hocr.WriteTextMode.Word;
//pdfset.Dpi = 300;
Clock.hocr.PdfCreator pdfcreat = new Clock.hocr.PdfCreator(pdfset,"test.pdf");
List<Image> pages = GetAllPages("test.tif");
for (int i = 0; i<hdoc.Pages.Count;i++)
{
Clock.hocr.Elements.hPage hpage = hdoc.Pages[i];
pdfcreat.AddPage(hpage, pages[i]);
}
pdfcreat.SaveAndClose();
您可以在以下位置找到 Clock.hocr 模块：http: //hocrtopdf.codeplex.com/
public void AddPage(hPage page, System.Drawing.Image pageImage)
{
doc.NewPage();
doc.AddHeader("COPYRIGHT", "DATAPOOL GmbH");
AddImage(pageImage);
WriteUnderlayContent(page);
}
doc 来自类型 itextsharp.text.document
public void AddImage(System.Drawing.Image image)
{
try
{
if (OnProcessImage != null)
{
AddImage(OnProcessImage(image));
return;
}
iTextSharp.text.Image i = GetImageForPDF(ImageProcessor.GetAsBitmap(image));
i.SetAbsolutePosition(0, 0);
// doc.SetPageSize(new iTextSharp.text.Rectangle(i.Width, i.Height));
i.ScaleAbsolute(doc.PageSize.Width, doc.PageSize.Height);
doc.Add(i);
}
catch (Exception x)
{
Debug.WriteLine(x.Message);
throw x;
}
}
...
private void WriteUnderlayContent(hPage page)
{
string pageText = page.Text;
foreach (hParagraph para in page.Paragraphs)
{
foreach (hLine line in para.Lines)
{
if (pdfSettings.WriteTextMode == WriteTextMode.Word)
{
line.AlignTops();
foreach (hWord c in line.Words)
{
c.CleanText();
BBox b = BBox.ConvertBBoxToPoints(c.BBox, pdfSettings.Dpi);
BBox lineBox = BBox.ConvertBBoxToPoints(line.BBox, pdfSettings.Dpi);
PdfContentByte cb = cb = writer.DirectContentUnder;
BaseFont base_font = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.WINANSI, false);
iTextSharp.text.Font font = new iTextSharp.text.Font(base_font);
float h = (int)Math.Ceiling(b.Height);
int font_size = (int)Math.Ceiling(h);
if (font_size == 0)
font_size = 2;
cb.BeginText();
cb.SetFontAndSize(base_font, (float)font_size);
cb.SetTextMatrix(b.Left, doc.PageSize.Height - b.Top - b.Height);
//float spacing = (c.BBox.Width / (c.Text.ToCharArray().Count())) / 100;
float spacing = (c.BBox.Width / (c.Text.ToCharArray().Count())) / 100 ;
cb.SetCharacterSpacing(spacing);
cb.ShowText(c.Text + " ");
cb.EndText();
}
}
else
{
line.CleanText();
BBox b = BBox.ConvertBBoxToPoints(line.BBox, pdfSettings.Dpi);
BBox lineBox = BBox.ConvertBBoxToPoints(line.BBox, pdfSettings.Dpi);
PdfContentByte cb = cb = writer.DirectContentUnder;
BaseFont base_font = BaseFont.CreateFont(BaseFont.HELVETICA, BaseFont.WINANSI, false);
iTextSharp.text.Font font = new iTextSharp.text.Font(base_font);
float h = (int)Math.Ceiling(b.Height);
int font_size = (int)Math.Ceiling(h);
if (font_size == 0)
font_size = 2;
cb.BeginText();
cb.SetFontAndSize(base_font, (float)font_size);
cb.SetTextMatrix(b.Left, doc.PageSize.Height - b.Top - b.Height);
float spacing = (line.BBox.Width / (line.Text.ToCharArray().Count())) / 100;
cb.SetCharacterSpacing(spacing);
cb.ShowText(line.Text);
cb.EndText();
}
}
}
}