iTextSharp 正在生成损坏的 PDF

Question

下面的代码 sn-p 返回一个损坏的 PDF 文档，但是如果我返回 mergeDocument，它总是返回一个有效的 PDF。 mergeDocument 是基于我使用 Word 创建的 PDF 文件，而完成的文档是完全以编程方式生成的。代码“有效”，因为它不会引发异常。为什么 iTextSharp 创建损坏的 PDF？

byte[] completedDocument = null;            
using (MemoryStream streamCompleted = new MemoryStream())
{
    using (Document document = new Document())
    {                    
        PdfCopy copy = new PdfCopy(document, streamCompleted);
        document.Open();
        copy.Open();                    

        foreach (var item in eventItems)
        {
            byte[] mergedDocument = null;
            PdfReader reader = new PdfReader(pdfTemplates[item.DataTokens[NotifyTokenType.OrganisationID]]);
            using (MemoryStream streamTemplate = new MemoryStream())
            {
                using (PdfStamper stamper = new PdfStamper(reader, streamTemplate))
                {
                    foreach (var token in item.DataTokens)
                    {
                        if (stamper.AcroFields.Fields.Any(fld => fld.Key == token.Key.ToString()))
                        {
                            stamper.AcroFields.SetField(token.Key.ToString(), token.Value);
                        }
                    }
                    stamper.FormFlattening = true;
                    stamper.Writer.CloseStream = false;
                }

                mergedDocument = new byte[streamTemplate.Length];
                streamTemplate.Position = 0;
                streamTemplate.Read(mergedDocument, 0, (int)streamTemplate.Length);
            }
            reader = new PdfReader(mergedDocument);

            for (int i = 1; i <= reader.NumberOfPages; i++)
            {
                document.SetPageSize(PageSize.A4);
                copy.AddPage(copy.GetImportedPage(reader, i));
            }
        }
        completedDocument = new byte[streamCompleted.Length];
        streamCompleted.Position = 0;
        streamCompleted.Read(completedDocument, 0, (int)streamCompleted.Length);
    }                
}
return completedDocument;

Answer 1

您需要关闭 document 和 copy 对象以刷新 PDF 写入缓冲区。但是，这在尝试将流读入数组时会导致一些问题。解决方法是使用MemoryStream 的ToArray() 方法，它仍然适用于封闭的流。我所做的更改上有 cmets。

        byte[] completedDocument = null;
        using (MemoryStream streamCompleted = new MemoryStream())
        {
            using (Document document = new Document())
            {
                PdfCopy copy = new PdfCopy(document, streamCompleted);
                document.Open();
                copy.Open();

                foreach (var item in eventItems)
                {
                    byte[] mergedDocument = null;
                    PdfReader reader = new PdfReader(pdfTemplates[item.DataTokens[NotifyTokenType.OrganisationID]]);
                    using (MemoryStream streamTemplate = new MemoryStream())
                    {
                        using (PdfStamper stamper = new PdfStamper(reader, streamTemplate))
                        {
                            foreach (var token in item.DataTokens)
                            {
                                if (stamper.AcroFields.Fields.Any(fld => fld.Key == token.Key.ToString()))
                                {
                                    stamper.AcroFields.SetField(token.Key.ToString(), token.Value);
                                }
                            }
                            stamper.FormFlattening = true;
                            stamper.Writer.CloseStream = false;
                        }
                        //Copy the stream's bytes
                        mergedDocument = streamTemplate.ToArray();
                    }
                    reader = new PdfReader(mergedDocument);

                    for (int i = 1; i <= reader.NumberOfPages; i++)
                    {
                        document.SetPageSize(PageSize.A4);
                        copy.AddPage(copy.GetImportedPage(reader, i));
                    }
                    //Close the document and the copy
                    document.Close();
                    copy.Close();
                }
                //ToArray() can operate on closed streams
                completedDocument = streamCompleted.ToArray();
            }
        }
        return completedDocument;

Answer 2

在将 html 转换为 pdf 时，还要确保您的 html 不包含 hr 标签

hdnEditorText.Value.Replace("\"", "'").Replace("<hr />", "").Replace("<hr/>", "")