如何使用C＃中的help memoryStream將帶有圖像和公式的MS Word文件轉換為html

Question

我正在使用下面的編碼，它工作正常。 這些編程將Word文件轉換為帶有圖像的HTML文件。

方程式有問題。我無法轉換ms word文件方程式HTML。

有人可以幫忙嗎？

FileUpload1.SaveAs(Server.MapPath(FileUpload1.FileName));

string imageDirectoryName = FileUpload1.FileName + "_files";
DirectoryInfo dirInfo = new DirectoryInfo(Server.MapPath(imageDirectoryName));

if (dirInfo.Exists)
{
        // Delete the directory and files.
        foreach (var f in dirInfo.GetFiles())
            f.Delete();
        dirInfo.Delete();
}

int imageCounter = 0;

byte[] byteArray = File.ReadAllBytes(sourceDocumentFileName);

using (MemoryStream memoryStream = new MemoryStream())
{
        memoryStream.Write(byteArray, 0, byteArray.Length);
        using (WordprocessingDocument doc =
            WordprocessingDocument.Open(memoryStream, true))
        {
            HtmlConverterSettings settings = new HtmlConverterSettings()
            {
                //PageTitle = "Test Title",
                //ConvertFormatting = false,
            };
            XElement html = HtmlConverter.ConvertToHtml(doc, settings,
                imageInfo =>
                {
                    DirectoryInfo localDirInfo = new DirectoryInfo(Server.MapPath(imageDirectoryName));
                    if (!localDirInfo.Exists)
                        localDirInfo.Create();
                    ++imageCounter;
                    string extension = imageInfo.ContentType.Split('/')[1].ToLower();
                    ImageFormat imageFormat = null;
                    if (extension == "png")
                    {
                        // Convert the .png file to a .jpeg file.
                        extension = "jpeg";
                        imageFormat = ImageFormat.Jpeg;
                    }
                    else if (extension == "bmp")
                        imageFormat = ImageFormat.Bmp;
                    else if (extension == "jpeg")
                        imageFormat = ImageFormat.Jpeg;
                    else if (extension == "tiff")
                        imageFormat = ImageFormat.Tiff;
                    else if (extension == "wmf")
                        imageFormat = ImageFormat.Jpeg;
                    else if (extension == "png")
                        imageFormat = ImageFormat.Png;


                    // If the image format is not one that you expect, ignore it,
                    // and do not return markup for the link.
                    if (imageFormat == null)
                        return null;

                    string imageFileName = imageDirectoryName + "/image" +
                        imageCounter.ToString() + "." + extension;
                    try
                    {
                        imageInfo.Bitmap.Save(Server.MapPath(imageFileName), imageFormat);
                    }
                    catch (System.Runtime.InteropServices.ExternalException)
                    {
                        return null;
                    }
                    XElement img = new XElement(Xhtml.img,
                        new XAttribute(NoNamespace.src, imageFileName),
                        imageInfo.ImgStyleAttribute,
                        imageInfo.AltText != null ?
                            new XAttribute(NoNamespace.alt, imageInfo.AltText) : null);
                    return img;
                });
            File.WriteAllText(fileInfo.Directory.FullName + "/" + fileInfo.Name.Substring(0,
                fileInfo.Name.Length - fileInfo.Extension.Length) + ".html",
                html.ToStringNewLineOnAttributes());
        }
}

Answer 1

第1步 -你應該在這里得到了解如何讓數學對象的Word文件在這里

第2步 -遍歷word文件的段落並在其中選擇OfficeMath對象，將其轉換為MathML （請參閱第1步），並且可以根據需要轉換為LaTex（我認為在HTML中使用LaTex會很友好）

注意：在步驟1中從MMOL2MML進行轉換時，轉換為LaTex將會類似， 請參見此處獲取文件

步驟3-在步驟2中的對象之前/之后插入一個文本對象，其內容為MathML / LaTex（在步驟2中）。 使用此步驟是因為使用HtmlConverter.ConvertToHtml將丟失Word內容中的數學對象，因此在對象數學之前/之后插入文本時，HTML中將提供文本

這是我的代碼：

using (WordprocessingDocument doc = WordprocessingDocument.Open(docFilePath, true))
        {
            foreach (var paragraph in doc.MainDocumentPart.RootElement.Descendants<Paragraph>())
            {
                foreach (var ele in paragraph.Descendants<DocumentFormat.OpenXml.Math.OfficeMath>())
                {
                    string wordDocXml = ele.OuterXml;

                    XslCompiledTransform xslTransform = new XslCompiledTransform();
                    xslTransform.Load(officeMathMLSchemaFilePath);
                    var result = "";
                    using (TextReader tr = new StringReader(wordDocXml))
                    {
                        // Load the xml of your main document part.
                        using (XmlReader reader = XmlReader.Create(tr))
                        {
                            using (MemoryStream ms = new MemoryStream())
                            {
                                XmlWriterSettings settings = xslTransform.OutputSettings.Clone();

                                // Configure xml writer to omit xml declaration.
                                settings.ConformanceLevel = ConformanceLevel.Fragment;
                                settings.OmitXmlDeclaration = true;

                                XmlWriter xw = XmlWriter.Create(ms, settings);

                                // Transform our OfficeMathML to MathML.
                                xslTransform.Transform(reader, xw);
                                ms.Seek(0, SeekOrigin.Begin);

                                using (StreamReader sr = new StreamReader(ms, Encoding.UTF8))
                                {
                                    result = MathML2Latex(sr.ReadToEnd());
                                    officeMLFormulas.Add(result);
                                }
                            }
                        }
                    }

                    Run run = new Run();
                    run.Append(new Text(result));
                    ele.InsertBeforeSelf(run);
                }
            }
        }