private static CoreFilePropertiesPart MakeValidCoreFilePropertiesPart(CoreFilePropertiesPart coreFilePropertiesPart)
{
byte[] blob = System.Text.Encoding.UTF8.GetBytes("<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?><cp:coreProperties xmlns:cp=\"http://schemas.openxmlformats.org/package/2006/metadata/core-properties\" xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:dcterms=\"http://purl.org/dc/terms/\" xmlns:dcmitype=\"http://purl.org/dc/dcmitype/\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"><cp:lastModifiedBy>Niklas Karl</cp:lastModifiedBy><cp:revision>1</cp:revision><dcterms:modified xsi:type=\"dcterms:W3CDTF\">2021-02-18T15:56:56Z</dcterms:modified></cp:coreProperties>");
using (MemoryStream stream = new MemoryStream(blob))
{
coreFilePropertiesPart.FeedData(stream);
}
return(coreFilePropertiesPart);
}
/// <summary>
/// Create instance from OpenXML part
/// </summary>
/// <param name="part">OpenXML part</param>
/// <returns>Instance</returns>
public static CoreProperties FromCoreFileProperties(CoreFilePropertiesPart part)
{
// Temporary variable
CoreProperties coreProperties = new CoreProperties();
// Read XML
using (XmlReader reader = new XmlTextReader(part.GetStream()))
{
while (reader.Read())
{
if (reader.NodeType == XmlNodeType.Element)
{
switch (reader.Name.ToLower())
{
case "dc:title":
coreProperties.Title = reader.ReadElementContentAsString();
break;
case "dc:subject":
coreProperties.Creator = reader.ReadElementContentAsString();
break;
case "dc:creator":
coreProperties.Keywords = reader.ReadElementContentAsString();
break;
case "cp:keywords":
coreProperties.Description = reader.ReadElementContentAsString();
break;
case "dc:description":
coreProperties.LastModifiedBy = reader.ReadElementContentAsString();
break;
case "cp:lastmodifiedby":
coreProperties.Revision = reader.ReadElementContentAsString();
break;
case "dcterms:created":
coreProperties.Created = DateTime.Parse(reader.ReadElementContentAsString());
break;
case "dcterms:modified":
coreProperties.Modified = DateTime.Parse(reader.ReadElementContentAsString());
break;
}
}
}
}
return(coreProperties);
}
public static void ConvertToHtml(string file, string outputDirectory)
{
var fi = new FileInfo(file);
Console.WriteLine(fi.Name);
byte[] byteArray = File.ReadAllBytes(fi.FullName);
using (var memoryStream = new MemoryStream())
{
memoryStream.Write(byteArray, 0, byteArray.Length);
using (WordprocessingDocument wDoc = WordprocessingDocument.Open(memoryStream, true))
{
var destFileName = new FileInfo(fi.Name.Replace(".docx", ".html"));
if (outputDirectory != null && outputDirectory != string.Empty)
{
var di = new DirectoryInfo(outputDirectory);
if (!di.Exists)
{
throw new OpenXmlPowerToolsException("Output directory does not exist");
}
destFileName = new FileInfo(Path.Combine(di.FullName, destFileName.Name));
}
string imageDirectoryName = destFileName.FullName.Substring(0, destFileName.FullName.Length - 5) + "_files";
var imageCounter = 0;
string pageTitle = fi.FullName;
CoreFilePropertiesPart part = wDoc.CoreFilePropertiesPart;
if (part != null)
{
pageTitle = (string)part.GetXDocument().Descendants(DC.title).FirstOrDefault() ?? fi.FullName;
}
// TODO: Determine max-width from size of content area.
var settings = new HtmlConverterSettings
{
AdditionalCss = "body { margin: 1cm auto; max-width: 20cm; padding: 0; }",
PageTitle = pageTitle,
FabricateCssClasses = true,
CssClassPrefix = "pt-",
RestrictToSupportedLanguages = false,
RestrictToSupportedNumberingFormats = false,
ImageHandler = imageInfo =>
{
var localDirInfo = new DirectoryInfo(imageDirectoryName);
if (!localDirInfo.Exists)
{
localDirInfo.Create();
}
++imageCounter;
string extension = imageInfo.ContentType.Split('/')[1].ToLower();
ImageFormat imageFormat = null;
if (extension == "png")
{
imageFormat = ImageFormat.Png;
}
else if (extension == "gif")
{
imageFormat = ImageFormat.Gif;
}
else if (extension == "bmp")
{
imageFormat = ImageFormat.Bmp;
}
else if (extension == "jpeg")
{
imageFormat = ImageFormat.Jpeg;
}
else if (extension == "tiff")
{
// Convert tiff to gif.
extension = "gif";
imageFormat = ImageFormat.Gif;
}
else if (extension == "x-wmf")
{
extension = "wmf";
imageFormat = ImageFormat.Wmf;
}
// If the image format isn't one that we expect, ignore it,
// and don't return markup for the link.
if (imageFormat == null)
{
return(null);
}
string imageFileName = imageDirectoryName + "/image" +
imageCounter + "." + extension;
try
{
imageInfo.Bitmap.Save(imageFileName, imageFormat);
}
catch (ExternalException)
{
return(null);
}
string imageSource = localDirInfo.Name + "/image" +
imageCounter + "." + extension;
var img = new XElement(Xhtml.img,
new XAttribute(NoNamespace.src, imageSource),
imageInfo.ImgStyleAttribute,
imageInfo.AltText != null ? new XAttribute(NoNamespace.alt, imageInfo.AltText) : null);
return(img);
}
};
XElement htmlElement = HtmlConverter.ConvertToHtml(wDoc, settings);
// Produce HTML document with <!DOCTYPE html > declaration to tell the browser
// we are using HTML5.
var html = new XDocument(
new XDocumentType("html", null, null, null),
htmlElement);
// Note: the xhtml returned by ConvertToHtmlTransform contains objects of type
// XEntity. PtOpenXmlUtil.cs define the XEntity class. See
// http://blogs.msdn.com/ericwhite/archive/2010/01/21/writing-entity-references-using-linq-to-xml.aspx
// for detailed explanation.
//
// If you further transform the XML tree returned by ConvertToHtmlTransform, you
// must do it correctly, or entities will not be serialized properly.
var htmlString = html.ToString(SaveOptions.DisableFormatting);
File.WriteAllText(destFileName.FullName, htmlString, Encoding.UTF8);
}
}
}
private static void ChangeCoreFilePropertiesPart1(CoreFilePropertiesPart coreFilePropertiesPart1)
{
var package = coreFilePropertiesPart1.OpenXmlPackage;
package.PackageProperties.Modified = System.Xml.XmlConvert.ToDateTime("2015-07-30T03:03:22Z", System.Xml.XmlDateTimeSerializationMode.RoundtripKind);
}
