Develop Reference

OpenXML Word Document - Unreadable content found after altchunk

I build a small application using .NET 6 that is replacing values inside a word document and saving a copy.
Some keys are replaced with other files content using an AltChunk.
Using file A, in which I merge AltChunk1, the output is working fine.
Using file B with same AltChunk1, the output produce the error "found unreadable content" when opening with Word.
Using file B and a different AltChunk file (even the same after I trimmed it) can, in some cases, work.
I don't have any clue what the issue might be.
I tried comparing files using OpenXML productivity tool however:
File A and File B have a lot of differences, it is really hard to find anything that would explain this behavior
They are identical in the place the AltChunk is put.
Tried comparing the not working result with what word is creating with a repair but word is not keeping the AltChunk, it completely merges content of AltChunk with File B making any comparison almost impossible with my non-working result.
Here is the code Is use:
First method is creating the AltChunk from file, then calls methods used to replace "keys" with the wanted value (including case where the key is split accross various runs)
internal static void MergeOutSideDocument(string key, string filePath, IEnumerable<string> outsideDocs)
{
if (string.IsNullOrEmpty(key)) throw new ArgumentException("Cannot replace empty key.");
if (!File.Exists(filePath) || outsideDocs.Any(path => !File.Exists(path))) throw new FileNotFoundException();
using WordprocessingDocument doc = WordprocessingDocument.Open(filePath, true);
List<OpenXmlElement> altChunks = new();
foreach (var outsideDoc in outsideDocs)
{
var existingIds = doc.MainDocumentPart.Document.Body.Descendants<AltChunk>();
string altChunkId = "AltChunkId" + DateTime.Now.Ticks.ToString();
MainDocumentPart mainPart = doc.MainDocumentPart;
AlternativeFormatImportPart chunk = mainPart.AddAlternativeFormatImportPart(
AlternativeFormatImportPartType.WordprocessingML, altChunkId);
using (FileStream fileStream = File.Open(outsideDoc, FileMode.Open))
chunk.FeedData(fileStream);
altChunks.Add(new AltChunk()
{
Id = altChunkId
});
inMemoryAltChunkIds.Add(altChunkId);
}
var body = doc.MainDocumentPart.Document.Body;
SetElementForKey(key, altChunks,
body.Descendants<Paragraph>().First(par => par.Contains(key)),
body);
}
private static void SetElementForKey(string key, List<OpenXmlElement> replacements, OpenXmlElement el, Body body)
{
List<Run> previousRuns = new();
if (el?.InnerText.Contains(key) != true) return;
for (int i = 0; i <= el.Descendants<Run>().Count(); i++)
{
var innerText = string.Join("", previousRuns.Select(r => r.InnerText));
if (innerText.Contains(key))
{
var usedRuns = GetRequiredRunsForText(previousRuns, key);
var firstRun = usedRuns.First();
MergeRunsWithKey(key, usedRuns, firstRun);
var usedRun = usedRuns.First();
var firstPart = usedRun.InnerText.IndexOf(key) != -1 ? usedRun.InnerText[..usedRun.InnerText.IndexOf(key)] : "";
ReplaceText(key, "", usedRun);
foreach (var replacement in replacements)
el.Parent.InsertAfter(replacement, el);
if (string.IsNullOrEmpty(usedRun.InnerText)) usedRun.Remove();
if (string.IsNullOrEmpty(el.InnerText)) el.Remove();
break;
}
else
{
previousRuns.Add(el.Descendants<Run>().ElementAt(i));
}
}
}
private static void MergeRunsWithKey(string key, List<Run> usedRuns, Run firstRun)
{
while (!usedRuns.First().InnerText.Contains(key))
{
AddText(usedRuns.Skip(1).First().InnerText, firstRun);
usedRuns.Skip(1).First().Remove();
usedRuns.RemoveAt(1);
}
}
private static void AddText(string newText, Run run)
{
Text text = run.Elements<Text>().LastOrDefault();
if (text == null)
{
run.Append(new Text());
text = run.Elements<Text>().Last();
}
text.Text += newText;
if (text.Text.StartsWith(" ") || text.Text.EndsWith(" "))
text.Space = SpaceProcessingModeValues.Preserve;
}
What can I do to understand where the problem lies?
I tried replacing some values I don't understand in File B with the ones from File A (header and footer have rectangles with different gfxdata values, the "recovered" from word was setting the same values as File A).
I tried a different way of generating the AltChunkIds and storing a global list for the file.
I tried comparing various parts of the documents (File A and B or Fil B's result and its recovered version). There are differences, but too many and none seem to be relevant.

Replace text in docx file with content of another docx file

I'm trying to use OpenXml to replace a text "Veteran" in file A.docx with content in B.docx . If B.docx contains text or paragraph , it works fine and I get modified A.docx file.
However, if B.docx contains a table, then the code doesn't work.
static void Main(string[] args)
{
SearchAndReplace(#"C:\A.docx", #"C:\B.docx");
}
public static void SearchAndReplace(string docTo, string docFrom)
{
List<WordprocessingDocument> docList = new List<WordprocessingDocument>();
using (WordprocessingDocument wordDoc = WordprocessingDocument.Open(docTo, true))
using (WordprocessingDocument wordDoc1 = WordprocessingDocument.Open(docFrom, true))
{
var parts = wordDoc1.MainDocumentPart.Document.Descendants().FirstOrDefault();
docList.Add(wordDoc);
docList.Add(wordDoc1);
if (parts != null)
{
foreach (var node in parts.ChildElements)
{
if (node is Table)
{
ParseTable(docList, (Table)node, textBuilder);
}
}
}
}
}
public static void ParseText(List<WordprocessingDocument> wpd, Paragraph node, StringBuilder textBuilder)
{
Body body = wpd[0].MainDocumentPart.Document.Body;
Body body1 = wpd[1].MainDocumentPart.Document.Body;
string content = body1.InnerXml;
var paras = body.Elements<Paragraph>();
foreach (var para in paras)
{
foreach (var run in para.Elements<Run>())
{
foreach (var text in run.Elements<Text>())
{
if (text.Text.Contains("Veteran"))
{
run.InnerXml.Replace(run.InnerXml, content);
break;
}
}
}
}
}
public static void ParseTable(List<WordprocessingDocument> wpd, Table node, StringBuilder textBuilder)
{
foreach (var row in node.Descendants<TableRow>())
{
textBuilder.Append("| ");
foreach (var cell in row.Descendants<TableCell>())
{
foreach (var para in cell.Descendants<Paragraph>())
{
ParseText(wpd, para, textBuilder);
}
textBuilder.Append(" | ");
}
textBuilder.AppendLine("");
}
}
}
}
How to make this work ? Is there a better way to replace content with another docx file?

Not having enough detail for a specific answer, here's how you solve such problems in general:
Ensure you understand the Open XML specification and valid Open XML markup on an appropriate level of detail.
If you don't understand what w:document, w:body, w:p, w:r, w:t, w:tbl, etc. are and how they relate to each other, you have no chance.
You must look at actual Open XML markup, e.g., using the Open XML Productivity Tool or the Open XML Package Editor for Modern Visual Studios to get to an appropriate level of understanding and develop Open XML-based solutions.
Understand that most Open XML-related code transforms some source markup into some target markup. Therefore, you must:
understand the source and target markup first and then
define the transformation required to create the target from the source.
Depending on what you need to do, the Open XML Productivity Tool can help create the transforming code. If you have a source and target document, you can use the Productivity Tool to compare those documents. This shows the difference in the markup, so you see what markup is created, deleted, or changed. It even shows you the Open XML SDK-based code required to effect the change.
In my own use cases, I typically prefer to write recursive, pure functional transformations. While you need to wrap your head around the concept, this is an extremely powerful approach.
In your case, you should:
take a few representative, manually-created samples of source (A.docx with "Vetaran" still to be replaced) and target (A.docx with "Veteran" replaced as desired) documents;
look at the Open XML markup of the source and target documents; and
write code that creates the target markup.
Once you have created code that at least tries to create valid target Open XML markup, you could come back with further questions in case you identify further issues.

Merged document using AltChunks has innertext empty

I am trying to merge multiple documents into a single one and then open the result document and process it further.
The "ChunkId" is a property that is increased every time this method is called in order to get a unique id. I followed the example from this site.
This is the code used to merge multiple documents (using altchunks):
`
private void MergeDocument(string mergePath, bool appendPageBreak)
{
if (!File.Exists(mergePath))
{
Log.Warn(string.Format("Document: \"{0}\" was not found.", mergePath));
return;
}
ChunkId++;
var altChunkId = "AltChunkId" + ChunkId;
var mainDocPart = DestinationDocument.MainDocumentPart;
if (mainDocPart == null)
{
DestinationDocument.AddMainDocumentPart();
mainDocPart = DestinationDocument.MainDocumentPart;
if (mainDocPart.Document == null)
mainDocPart.Document = new Document { Body = new Body() };
}
try
{
var chunk = mainDocPart.AddAlternativeFormatImportPart(
AlternativeFormatImportPartType.WordprocessingML, altChunkId);
if (chunk != null)
using (var ms = new FileStream(mergePath, FileMode.Open))
{
chunk.FeedData(ms);
}
else
{
Log.Error(string.Format("Merge - Failed to create chunk document based on \"{0}\".", mergePath));
return; // failed to create chunk document, return from merge method
}
}
catch (Exception e)
{
Log.Error(string.Format("Merge - Failed to insert chunk document based on \"{0}\".", mergePath));
return; // failed to create chunk document, return from merge method
}
var altChunk = new AltChunk { Id = altChunkId };
//append the page break
if (appendPageBreak)
try
{
AppendPageBreak(mainDocPart);
Log.Info(string.Format("Successfully appended page break."));
}
catch (Exception ex)
{
Log.Error(string.Format("Eror appending page break. Message: \"{0}\".", ex.Message));
return; // return if page break insertion failed
}
// insert the document
var last = mainDocPart.Document
.Body
.Elements()
.LastOrDefault(e => e is Paragraph || e is AltChunk);
try
{
if (last == null)
mainDocPart.Document.Body.InsertAt(altChunk, 0);
else
last.InsertAfterSelf(altChunk);
Log.Info(string.Format("Successfully inserted new doc \"{0}\" into destination.", mergePath));
}
catch (Exception ex)
{
Log.Error(string.Format("Error merging document \"{0}\". Message: \"{1}\".", mergePath, ex.Message));
return; // return if the merge was not successfull
}
try
{
mainDocPart.Document.Save();
}
catch (Exception ex)
{
Log.Error(string.Format("Error saving document \"{0}\". Message: \"{1}\".", mergePath, ex.Message));
}
}`
If I open the merged document with Word I can see its content (tables, text, paragraphs..), but if I open if from code again it says that inner text is "" (empty string). I need that inner text to reflect what the document contains because I have to replace some placeholders like "##name##" with another text and I can't if the inner text is empty.
This is the innerxml of the merged document,
This is how I open the merged document:
DestinationDocument = WordprocessingDocument.Open(Path.GetFullPath(destinationPath), true);
How can I read the inner text of the document? Or how can I merge these documents into a single one so that this problem would not occur anymore?

When documents merged with AltChunks it is like embedded attachments to the original word document. The client (MS Word) handles the rendering of the altchunk sections. Hence the resulting document won't have the openxml markup of the merged documents.
If you want to use the resulting document for further programmatic post-processing use Openxml Power Tools. pelase refer to my answer here
Openxml powertools - https://github.com/OfficeDev/Open-Xml-PowerTools

The problem is that the documents are not really merged (per se), the altChunk element only defines a place where the alternative content should be placed in the document and it has a reference to that alternative content.
When you open this document in MS Word then it will actually merge all those alternative contents automatically for you. So when you resave that document with MS Word you'll no longer have altChunk elements.
Nevertheless what you can do is actually manipulate with those altChunk DOCX files (the child DOCX documents) just like you do with the main DOCX file (the parent document).
For example:
string destinationPath = "Sample.docx";
string search = "##name##";
string replace ="John Doe";
using (var parent = WordprocessingDocument.Open(Path.GetFullPath(destinationPath), true))
{
foreach (var altChunk in parent.MainDocumentPart.GetPartsOfType<AlternativeFormatImportPart>())
{
if (Path.GetExtension(altChunk.Uri.OriginalString) != ".docx")
continue;
using (var child = WordprocessingDocument.Open(altChunk.GetStream(), true))
{
var foundText = child.MainDocumentPart.Document.Body
.Descendants<Text>()
.Where(t => t.Text.Contains(search))
.FirstOrDefault();
if (foundText != null)
{
foundText.Text = foundText.Text.Replace(search, replace);
break;
}
}
}
}
Alternatively you'll need to use some approach to merge those documents for real. One solution is mentioned by Flowerking, another one that you could try is with GemBox.Document library. It will merge those alternative contents for you on loading (just as MS Word does when opening).
For example:
string destinationPath = "Sample.docx";
string search = "##name##";
string replace = "John Doe";
DocumentModel document = DocumentModel.Load(destinationPath);
ContentRange foundText = document.Content.Find(search).FirstOrDefault();
if (foundText != null)
foundText.LoadText(replace);
document.Save(destinationPath);

Merging Word documents using WordProcessingDocument

I am currently working on a program in which a user should be able to merge several Word documents into one, without losing any formatting, headers and so on. The documents should simply stack up, one after another, without any changes.
Here is my current code:
public virtual Byte[] MergeWordFiles(IEnumerable<SendData> sourceFiles)
{
int f = 0;
// If only one Word document then skip merge.
if (sourceFiles.Count() == 1)
{
return sourceFiles.First().File;
}
else
{
MemoryStream destinationFile = new MemoryStream();
// Add first file
var firstFile = sourceFiles.First().File;
destinationFile.Write(firstFile, 0, firstFile.Length);
destinationFile.Position = 0;
int pointer = 1;
byte[] ret;
// Add the rest of the files
try
{
using (WordprocessingDocument mainDocument = WordprocessingDocument.Open(destinationFile, true))
{
XElement newBody = XElement.Parse(mainDocument.MainDocumentPart.Document.Body.OuterXml);
for (pointer = 1; pointer < sourceFiles.Count(); pointer++)
{
WordprocessingDocument tempDocument = WordprocessingDocument.Open(new MemoryStream(sourceFiles.ElementAt(pointer).File), true);
XElement tempBody = XElement.Parse(tempDocument.MainDocumentPart.Document.Body.OuterXml);
newBody.Add(XElement.Parse(new DocumentFormat.OpenXml.Wordprocessing.Paragraph(new Run(new Break { Type = BreakValues.Page })).OuterXml));
newBody.Add(tempBody);
mainDocument.MainDocumentPart.Document.Body = new Body(newBody.ToString());
mainDocument.MainDocumentPart.Document.Save();
mainDocument.Package.Flush();
}
}
}
catch (OpenXmlPackageException oxmle)
{
throw new Exception(string.Format(CultureInfo.CurrentCulture, "Error while merging files. Document index {0}", pointer), oxmle);
}
catch (Exception e)
{
throw new Exception(string.Format(CultureInfo.CurrentCulture, "Error while merging files. Document index {0}", pointer), e);
}
finally
{
ret = destinationFile.ToArray();
destinationFile.Close();
destinationFile.Dispose();
}
return ret;
}
}
The problem here is that the formatting is copied from the first document and applied to all the rest, meaning that for instance a different header in the second document will be ignored. How do I prevent this?
I have been looking in to breaking the document in to sections using SectionMarkValues.NextPage, as well as using altChunk.
The problem with the latter is altChunk does not seem to be able to handle a MemoryStream into its "FeedData" method.

DocIO is a .NET library that can read, write, merge and render Word 2003/2007/2010/2013/2016 files. The whole suite of controls is available for free (commercial applications also) through the community license program if you qualify. The community license is the full product with no limitations or watermarks.
Step 1: Create a console application
Step 2: Add reference to Syncfusion.DocIO.Base, Syncfusion.Compression.Base and Syncfusion.OfficeChart.Base; You can add these reference to your project using NuGet also.
Step 3: Copy & paste the following code snippet.
This code snippet will produce the document as per your requirement; each input Word document will get merged with its original formatting, styles and headers/footer.
using Syncfusion.DocIO.DLS;
using Syncfusion.DocIO;
using System.IO;
namespace DocIO_MergeDocument
{
class Program
{
static void Main(string[] args)
{
//Boolean to indicate whether any of the input document has different odd and even headers as true
bool isDifferentOddAndEvenPagesEnabled = false;
// Creating a new document.
using (WordDocument mergedDocument = new WordDocument())
{
//Get the files from input directory
DirectoryInfo dirInfo = new DirectoryInfo(System.Environment.CurrentDirectory + #"\..\..\Data");
FileInfo[] fileInfo = dirInfo.GetFiles();
for (int i = 0; i < fileInfo.Length; i++)
{
if (fileInfo[i].Extension == ".doc" || fileInfo[i].Extension == ".docx")
{
using (WordDocument sourceDocument = new WordDocument(fileInfo[i].FullName))
{
//Check whether the document has different odd and even header/footer
if (!isDifferentOddAndEvenPagesEnabled)
{
foreach (WSection section in sourceDocument.Sections)
{
isDifferentOddAndEvenPagesEnabled = section.PageSetup.DifferentOddAndEvenPages;
if (isDifferentOddAndEvenPagesEnabled)
break;
}
}
//Sets the breakcode of First section of source document as NoBreak to avoid imported from a new page
sourceDocument.Sections[0].BreakCode = SectionBreakCode.EvenPage;
//Imports the contents of source document at the end of merged document
mergedDocument.ImportContent(sourceDocument, ImportOptions.KeepSourceFormatting);
}
}
}
//if any of the input document has different odd and even headers as true then
//Copy the content of the odd header/foort and add the copied content into the even header/footer
if (isDifferentOddAndEvenPagesEnabled)
{
foreach (WSection section in mergedDocument.Sections)
{
section.PageSetup.DifferentOddAndEvenPages = true;
if (section.HeadersFooters.OddHeader.Count > 0 && section.HeadersFooters.EvenHeader.Count == 0)
{
for (int i = 0; i < section.HeadersFooters.OddHeader.Count; i++)
section.HeadersFooters.EvenHeader.ChildEntities.Add(section.HeadersFooters.OddHeader.ChildEntities[i].Clone());
}
if (section.HeadersFooters.OddFooter.Count > 0 && section.HeadersFooters.EvenFooter.Count == 0)
{
for (int i = 0; i < section.HeadersFooters.OddFooter.Count; i++)
section.HeadersFooters.EvenFooter.ChildEntities.Add(section.HeadersFooters.OddFooter.ChildEntities[i].Clone());
}
}
}
//If there is no document to merge then add empty section with empty paragraph
if (mergedDocument.Sections.Count == 0)
mergedDocument.EnsureMinimal();
//Saves the document in the given name and format
mergedDocument.Save("result.docx", FormatType.Docx);
}
}
}
}
Downloadable Demo
Note: There is a Word document (not section) level settings for
applying different header/footer for odd and even pages. Each input
document can have different values for this property. if any of the
input document has different odd and even header/footer as true, it
will affect the visual appearance of header/footer in the resultant
document. Hence, if any of the input document has different odd and
even header/footer, then the resultant Word document will have been
replaced with the odd header/footer contents.
For further information about DocIO, please refer our help documentation
Note: I work for Syncfusion

how can I put a content in a mergefield in docx

I'm developing a web application with asp.net and I have a file called Template.docx that works like a template to generate other reports. Inside this Template.docx I have some MergeFields (Title, CustomerName, Content, Footer, etc) to replace for some dynamic content in C#.
I would like to know, how can I put a content in a mergefield in docx ?
I don't know if MergeFields is the right way to do this or if there is another way. If you can suggest me, I appreciate!
PS: I have openxml referenced in my web application.
Edits:
private MemoryStream LoadFileIntoStream(string fileName)
{
MemoryStream memoryStream = new MemoryStream();
using (FileStream fileStream = File.OpenRead(fileName))
{
memoryStream.SetLength(fileStream.Length);
fileStream.Read(memoryStream.GetBuffer(), 0, (int) fileStream.Length);
memoryStream.Flush();
fileStream.Close();
}
return memoryStream;
}
public MemoryStream GenerateWord()
{
string templateDoc = "C:\\temp\\template.docx";
string reportFileName = "C:\\temp\\result.docx";
var reportStream = LoadFileIntoStream(templateDoc);
// Copy a new file name from template file
//File.Copy(templateDoc, reportFileName, true);
// Open the new Package
Package pkg = Package.Open(reportStream, FileMode.Open, FileAccess.ReadWrite);
// Specify the URI of the part to be read
Uri uri = new Uri("/word/document.xml", UriKind.Relative);
PackagePart part = pkg.GetPart(uri);
XmlDocument xmlMainXMLDoc = new XmlDocument();
xmlMainXMLDoc.Load(part.GetStream(FileMode.Open, FileAccess.Read));
// replace some keys inside xml (it will come from database, it's just a test)
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_customer", "My Customer Name");
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_title", "Report of Documents");
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_content", "Content of Document");
// Open the stream to write document
StreamWriter partWrt = new StreamWriter(part.GetStream(FileMode.Open, FileAccess.Write));
//doc.Save(partWrt);
xmlMainXMLDoc.Save(partWrt);
partWrt.Flush();
partWrt.Close();
reportStream.Flush();
pkg.Close();
return reportStream;
}
PS: When I convert MemoryStream to a file, I got a corrupted file. Thanks!

I know this is an old post, but I could not get the accepted answer to work for me. The project linked would not even compile (which someone has already commented in that link). Also, it seems to use other Nuget packages like WPFToolkit.
So I'm adding my answer here in case someone finds it useful. This only uses the OpenXML SDK 2.5 and also the WindowsBase v4. This works on MS Word 2010 and later.
string sourceFile = #"C:\Template.docx";
string targetFile = #"C:\Result.docx";
File.Copy(sourceFile, targetFile, true);
using (WordprocessingDocument document = WordprocessingDocument.Open(targetFile, true))
{
// If your sourceFile is a different type (e.g., .DOTX), you will need to change the target type like so:
document.ChangeDocumentType(WordprocessingDocumentType.Document);
// Get the MainPart of the document
MainDocumentPart mainPart = document.MainDocumentPart;
var mergeFields = mainPart.RootElement.Descendants<FieldCode>();
var mergeFieldName = "SenderFullName";
var replacementText = "John Smith";
ReplaceMergeFieldWithText(mergeFields, mergeFieldName, replacementText);
// Save the document
mainPart.Document.Save();
}
private void ReplaceMergeFieldWithText(IEnumerable<FieldCode> fields, string mergeFieldName, string replacementText)
{
var field = fields
.Where(f => f.InnerText.Contains(mergeFieldName))
.FirstOrDefault();
if (field != null)
{
// Get the Run that contains our FieldCode
// Then get the parent container of this Run
Run rFldCode = (Run)field.Parent;
// Get the three (3) other Runs that make up our merge field
Run rBegin = rFldCode.PreviousSibling<Run>();
Run rSep = rFldCode.NextSibling<Run>();
Run rText = rSep.NextSibling<Run>();
Run rEnd = rText.NextSibling<Run>();
// Get the Run that holds the Text element for our merge field
// Get the Text element and replace the text content
Text t = rText.GetFirstChild<Text>();
t.Text = replacementText;
// Remove all the four (4) Runs for our merge field
rFldCode.Remove();
rBegin.Remove();
rSep.Remove();
rEnd.Remove();
}
}
What the code above does is basically this:
Identify the 4 Runs that make up the merge field named "SenderFullName".
Identify the Run that contains the Text element for our merge field.
Remove the 4 Runs.
Update the text property of the Text element for our merge field.
UPDATE
For anyone interested, here is a simple static class I used to help me with replacing merge fields.

Frank Fajardo's answer was 99% of the way there for me, but it is important to note that MERGEFIELDS can be SimpleFields or FieldCodes.
In the case of SimpleFields, the text runs displayed to the user in the document are children of the SimpleField.
In the case of FieldCodes, the text runs shown to the user are between the runs containing FieldChars with the Separate and the End FieldCharValues. Occasionally, several text containing runs exist between the Separate and End Elements.
The code below deals with these problems. Further details of how to get all the MERGEFIELDS from the document, including the header and footer is available in a GitHub repository at https://github.com/mcshaz/SimPlanner/blob/master/SP.DTOs/Utilities/OpenXmlExtensions.cs
private static Run CreateSimpleTextRun(string text)
{
Run returnVar = new Run();
RunProperties runProp = new RunProperties();
runProp.Append(new NoProof());
returnVar.Append(runProp);
returnVar.Append(new Text() { Text = text });
return returnVar;
}
private static void InsertMergeFieldText(OpenXmlElement field, string replacementText)
{
var sf = field as SimpleField;
if (sf != null)
{
var textChildren = sf.Descendants<Text>();
textChildren.First().Text = replacementText;
foreach (var others in textChildren.Skip(1))
{
others.Remove();
}
}
else
{
var runs = GetAssociatedRuns((FieldCode)field);
var rEnd = runs[runs.Count - 1];
foreach (var r in runs
.SkipWhile(r => !r.ContainsCharType(FieldCharValues.Separate))
.Skip(1)
.TakeWhile(r=>r!= rEnd))
{
r.Remove();
}
rEnd.InsertBeforeSelf(CreateSimpleTextRun(replacementText));
}
}
private static IList<Run> GetAssociatedRuns(FieldCode fieldCode)
{
Run rFieldCode = (Run)fieldCode.Parent;
Run rBegin = rFieldCode.PreviousSibling<Run>();
Run rCurrent = rFieldCode.NextSibling<Run>();
var runs = new List<Run>(new[] { rBegin, rCurrent });
while (!rCurrent.ContainsCharType(FieldCharValues.End))
{
rCurrent = rCurrent.NextSibling<Run>();
runs.Add(rCurrent);
};
return runs;
}
private static bool ContainsCharType(this Run run, FieldCharValues fieldCharType)
{
var fc = run.GetFirstChild<FieldChar>();
return fc == null
? false
: fc.FieldCharType.Value == fieldCharType;
}

You could try http://www.codeproject.com/KB/office/Fill_Mergefields.aspx which uses the Open XML SDK to do this.