public static void SimplifyMarkup(WordprocessingDocument doc,
SimplifyMarkupSettings settings)
{
if (settings.RemoveMarkupForDocumentComparison)
{
settings.RemoveRsidInfo = true;
RemoveElementsForDocumentComparison(doc);
}
if (settings.RemoveRsidInfo)
{
RemoveRsidInfoInSettings(doc);
}
if (settings.AcceptRevisions)
{
RevisionAccepter.AcceptRevisions(doc);
}
foreach (var part in doc.ContentParts())
{
SimplifyMarkupForPart(part, settings);
}
if (doc.MainDocumentPart.StyleDefinitionsPart != null)
{
SimplifyMarkupForPart(doc.MainDocumentPart.StyleDefinitionsPart, settings);
}
if (doc.MainDocumentPart.StylesWithEffectsPart != null)
{
SimplifyMarkupForPart(doc.MainDocumentPart.StylesWithEffectsPart, settings);
}
}
/// <summary>
/// Converts a specific node instead of the whole word document into HTML.
/// Note: this method is added for the above purpose. See the other method:
/// public static XElement ConvertToHtml(WordprocessingDocument wordDoc, HtmlConverterSettings htmlConverterSettings, Func<ImageInfo, XElement> imageHandler)
/// </summary>
/// <param name="wordDoc"></param>
/// <param name="node">The node to convert to HTML.</param>
/// <param name="htmlConverterSettings"></param>
/// <returns></returns>
public static XElement ConvertToHtml(WordprocessingDocument wordDoc, XNode node,
HtmlConverterSettings htmlConverterSettings)
{
InitEntityMap();
if (htmlConverterSettings.ConvertFormatting)
{
throw new InvalidSettingsException("Conversion with formatting is not supported");
}
RevisionAccepter.AcceptRevisions(wordDoc);
SimplifyMarkupSettings settings = new SimplifyMarkupSettings
{
RemoveComments = true,
RemoveContentControls = true,
RemoveEndAndFootNotes = true,
RemoveFieldCodes = false,
RemoveLastRenderedPageBreak = true,
RemovePermissions = true,
RemoveProof = true,
RemoveRsidInfo = true,
RemoveSmartTags = true,
RemoveSoftHyphens = true,
ReplaceTabsWithSpaces = true,
};
MarkupSimplifier.SimplifyMarkup(wordDoc, settings);
AnnotateHyperlinkContent((XElement)node);
XElement xhtml = (XElement)ConvertToHtmlTransform(wordDoc, htmlConverterSettings,
node, null);
return(xhtml);
}
public static void SimplifyMarkup(WordprocessingDocument doc,
SimplifyMarkupSettings settings)
{
if (settings.AcceptRevisions)
{
RevisionAccepter.AcceptRevisions(doc);
}
foreach (var part in doc.ContentParts())
{
SimplifyMarkupForPart(part, settings);
}
if (doc.MainDocumentPart.StyleDefinitionsPart != null)
{
SimplifyMarkupForPart(doc.MainDocumentPart.StyleDefinitionsPart, settings);
}
if (doc.MainDocumentPart.StylesWithEffectsPart != null)
{
SimplifyMarkupForPart(doc.MainDocumentPart.StylesWithEffectsPart, settings);
}
}
public static XElement ConvertToHtml(WordprocessingDocument wordDoc,
HtmlConverterSettings htmlConverterSettings, Func <ImageInfo, XElement> imageHandler)
{
InitEntityMap();
if (htmlConverterSettings.ConvertFormatting)
{
throw new InvalidSettingsException("Conversion with formatting is not supported");
}
RevisionAccepter.AcceptRevisions(wordDoc);
SimplifyMarkupSettings settings = new SimplifyMarkupSettings
{
RemoveComments = true,
RemoveContentControls = true,
RemoveEndAndFootNotes = true,
RemoveFieldCodes = false,
RemoveLastRenderedPageBreak = true,
RemovePermissions = true,
RemoveProof = true,
RemoveRsidInfo = true,
RemoveSmartTags = true,
RemoveSoftHyphens = true,
ReplaceTabsWithSpaces = true,
};
MarkupSimplifier.SimplifyMarkup(wordDoc, settings);
XElement rootElement = wordDoc.MainDocumentPart.GetXDocument().Root;
AnnotateHyperlinkContent(rootElement);
XElement xhtml = (XElement)ConvertToHtmlTransform(wordDoc, htmlConverterSettings,
rootElement, imageHandler);
// 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.
return(xhtml);
}