/// <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 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);
}
public WmlDocument SimplifyMarkup(SimplifyMarkupSettings settings)
{
return(MarkupSimplifier.SimplifyMarkup(this, settings));
}
private static WmlDocument PreProcessMarkup(WmlDocument source, int startingIdForFootnotesEndnotes)
{
// open and close to get rid of MC content
using (var ms = new MemoryStream())
{
ms.Write(source.DocumentByteArray, 0, source.DocumentByteArray.Length);
var os = new OpenSettings
{
MarkupCompatibilityProcessSettings = new MarkupCompatibilityProcessSettings(
MarkupCompatibilityProcessMode.ProcessAllParts,
FileFormatVersions.Office2007)
};
using (WordprocessingDocument wDoc = WordprocessingDocument.Open(ms, true, os))
{
OpenXmlPartRootElement unused = wDoc.MainDocumentPart.RootElement;
if (wDoc.MainDocumentPart.FootnotesPart != null)
{
// contrary to what you might think, looking at the API, it is necessary to access the root element of each part to cause
// the SDK to process MC markup.
OpenXmlPartRootElement unused1 = wDoc.MainDocumentPart.FootnotesPart.RootElement;
}
if (wDoc.MainDocumentPart.EndnotesPart != null)
{
OpenXmlPartRootElement unused1 = wDoc.MainDocumentPart.EndnotesPart.RootElement;
}
}
source = new WmlDocument(source.FileName, ms.ToArray());
}
// open and close to get rid of MC content
using (var ms = new MemoryStream())
{
ms.Write(source.DocumentByteArray, 0, source.DocumentByteArray.Length);
var os = new OpenSettings
{
MarkupCompatibilityProcessSettings = new MarkupCompatibilityProcessSettings(
MarkupCompatibilityProcessMode.ProcessAllParts,
FileFormatVersions.Office2007)
};
using (WordprocessingDocument wDoc = WordprocessingDocument.Open(ms, true, os))
{
TestForInvalidContent(wDoc);
RemoveExistingPowerToolsMarkup(wDoc);
// Removing content controls, field codes, and bookmarks is a no-no for many use cases.
// We need content controls, e.g., on the title page. Field codes are required for
// automatic cross-references, which require bookmarks.
// TODO: Revisit
var msSettings = new SimplifyMarkupSettings
{
RemoveBookmarks = true,
AcceptRevisions = false,
RemoveComments = true,
RemoveContentControls = true,
RemoveFieldCodes = true,
RemoveGoBackBookmark = true,
RemoveLastRenderedPageBreak = true,
RemovePermissions = true,
RemoveProof = true,
RemoveSmartTags = true,
RemoveSoftHyphens = true,
RemoveHyperlinks = true
};
MarkupSimplifier.SimplifyMarkup(wDoc, msSettings);
ChangeFootnoteEndnoteReferencesToUniqueRange(wDoc, startingIdForFootnotesEndnotes);
AddUnidsToMarkupInContentParts(wDoc);
AddFootnotesEndnotesParts(wDoc);
FillInEmptyFootnotesEndnotes(wDoc);
}
return(new WmlDocument(source.FileName, ms.ToArray()));
}
}
public static WmlDocument MergeComments(WmlDocument document1, WmlDocument document2,
bool ensureLocked)
{
WmlDocument cDoc1 = new WmlDocument(document1);
WmlDocument cDoc2 = new WmlDocument(document2);
using (OpenXmlMemoryStreamDocument streamDoc1 = new OpenXmlMemoryStreamDocument(cDoc1))
using (WordprocessingDocument doc1 = streamDoc1.GetWordprocessingDocument())
using (OpenXmlMemoryStreamDocument streamDoc2 = new OpenXmlMemoryStreamDocument(cDoc2))
using (WordprocessingDocument doc2 = streamDoc2.GetWordprocessingDocument())
{
SimplifyMarkupSettings mss = new SimplifyMarkupSettings()
{
RemoveProof = true,
RemoveRsidInfo = true,
RemoveGoBackBookmark = true,
};
MarkupSimplifier.SimplifyMarkup(doc1, mss);
MarkupSimplifier.SimplifyMarkup(doc2, mss);
// If documents don't contain the same content, then don't attempt to merge comments.
bool same = DocumentComparer.CompareDocuments(doc1, doc2);
if (!same)
{
throw new CommentMergerDifferingContentsException(
"Documents do not contain the same content");
}
if (doc1.MainDocumentPart.WordprocessingCommentsPart == null &&
doc2.MainDocumentPart.WordprocessingCommentsPart == null)
{
return(new WmlDocument(document1));
}
if (doc1.MainDocumentPart.WordprocessingCommentsPart != null &&
doc2.MainDocumentPart.WordprocessingCommentsPart == null)
{
return(new WmlDocument(document1));
}
if (doc1.MainDocumentPart.WordprocessingCommentsPart == null &&
doc2.MainDocumentPart.WordprocessingCommentsPart != null)
{
return(new WmlDocument(document2));
}
// If either of the documents have no comments, then return the other one.
if (!doc1.MainDocumentPart.WordprocessingCommentsPart.GetXDocument().Root
.Elements(W.comment).Any())
{
return(new WmlDocument(document2));
}
if (!doc2.MainDocumentPart.WordprocessingCommentsPart.GetXDocument().Root
.Elements(W.comment).Any())
{
return(new WmlDocument(document1));
}
if (ensureLocked)
{
// If either document is not locked (allowing only commenting), don't attempt to
// merge comments.
if (doc1.ExtendedFilePropertiesPart.GetXDocument().Root
.Element(EP.DocSecurity).Value != "8")
{
throw new CommentMergerUnlockedDocumentException(
"Document1 is not locked");
}
if (doc2.ExtendedFilePropertiesPart.GetXDocument().Root
.Element(EP.DocSecurity).Value != "8")
{
throw new CommentMergerUnlockedDocumentException(
"Document2 is not locked");
}
}
RenumberCommentsInDoc2(doc1, doc2);
WmlDocument destDoc = new WmlDocument(document1);
using (OpenXmlMemoryStreamDocument streamDoc = new OpenXmlMemoryStreamDocument(destDoc))
{
using (WordprocessingDocument destWDoc = streamDoc.GetWordprocessingDocument())
{
// Merge the comments part.
XDocument commentsPartXDoc = new XDocument(
new XElement(W.comments,
new XAttribute(XNamespace.Xmlns + "w", W.w),
doc1.MainDocumentPart.WordprocessingCommentsPart.GetXDocument().Root.Elements(),
doc2.MainDocumentPart.WordprocessingCommentsPart.GetXDocument().Root.Elements()));
destWDoc.MainDocumentPart.WordprocessingCommentsPart.PutXDocument(commentsPartXDoc);
MergeCommentsInPart(doc1.MainDocumentPart, doc2.MainDocumentPart,
destWDoc.MainDocumentPart, commentsPartXDoc);
}
return(streamDoc.GetModifiedWmlDocument());
}
}
}