c# - 如何在 C# 中借助 memoryStream 将带有图像和方程式的 ms word 文件转换为 html

Question

我正在使用如下编码并且工作正常。这些程序将 word 文件转换为带有图像的 html 文件。

方程式有问题。我无法转换 ms word 文件方程式 HTML。

有人可以帮忙吗？

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 - 您应该到这里了解如何在 word 文件中获取 Math 对象 here

第 2 步 - 遍历 word 文件的段落并选择其中的 OfficeMath 对象，将其转换为 MathML(参见第 1 步)，如果您可以转换为 LaTex想要(我认为在 HTML 中使用 LaTex 会很友好)

注意:在第 1 步中从 MMOL2MML 转换为 LaTex 将类似 see here to get file

第 3 步 - 在第 2 步的对象之前/之后插入内容为 MathML/LaTex 的文本对象(在第 2 步中)。使用此步骤是因为当使用 HtmlConverter.ConvertToHtml 时会丢失 Word 内容中的数学对象，因此当您在对象数学之前/之后插入时，文本将在 HTML 中可用

这是我的代码:

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);
                }
            }
        }