I have a word document with many special tags that represent
a bookmark and a link to a bookmark. I want to replace these tags with a proper bookmark and link to bookmarks.(see attached example doc: special_tags.docx) here’s what i mean…
Bookmark Tag:
The format of a bookmark tag in my word doc is ** [] **
where x is the bookmark.
for example:
[] = This represents a bookmark called b1
How can I scan my word document and find all Tags like this [] and
replace them with a correct word bookmark.
Link to Bookmark Tag:
The format for an internal link to a bookmark is: ** [ > T~x < ] **
where
T = the display text for the link
x = bookmark
for example:
[>Go to Special Offers~sp1<]
This tag should be replaced with a link that looks like this: Go to Special Offers
When the user CTRL+Clicks this link he jumps to the sp1 bookmark.
I have lots of these types of tags which were generated dynamically so i do not know
what the bookmark id is or the display text.
I have attached 2 docs as an example.
-Original word doc with tag: special_tags.docx\ - The same document after the tags have been replaced: tags_converted.docx
Hi Nitin,
Thanks for your inquiry.
*Nitin:
> How can I scan my word document and find all Tags like this[] and replace them with a correct word bookmark.*
Here is the code to achieve this.
Document doc = new Document(@"C:\Temp\special_tags.docx");
// Replace tags with Bookmarks
doc.Range.Replace(new Regex("\\[<[a-z]+\\d>\\]"), new InsertBookmarkAtReplaceHandler(), true);
doc.Save(@"C:\Temp\out.docx");
private class InsertBookmarkAtReplaceHandler : IReplacingCallback
{
ReplaceAction IReplacingCallback.Replacing(ReplacingArgs e)
{
// This is a Run node that contains either the beginning or the complete match.
Node currentNode = e.MatchNode;
// The first (and may be the only) run can contain text before the match,
// in this case it is necessary to split the run.
if (e.MatchOffset > 0)
currentNode = SplitRun((Run)currentNode, e.MatchOffset);
// This array is used to store all nodes of the match for further removing.
ArrayList runs = new ArrayList();
// Find all runs that contain parts of the match string.
int remainingLength = e.Match.Value.Length;
while (
(remainingLength > 0) &&
(currentNode != null) &&
(currentNode.GetText().Length <= remainingLength))
{
runs.Add(currentNode);
remainingLength = remainingLength - currentNode.GetText().Length;
// Select the next Run node.
// Have to loop because there could be other nodes such as BookmarkStart etc.
do
{
currentNode = currentNode.NextSibling;
}
while ((currentNode != null) && (currentNode.NodeType != NodeType.Run));
}
// Split the last run that contains the match if there is any text left.
if ((currentNode != null) && (remainingLength > 0))
{
SplitRun((Run)currentNode, remainingLength);
runs.Add(currentNode);
}
string tagName = e.Match.Value.Replace("[<", "").Replace(">]", "");
DocumentBuilder builder = new DocumentBuilder((Document)e.MatchNode.Document);
builder.MoveTo(e.MatchNode);
builder.MoveTo((Run)runs[runs.Count - 1]);
builder.StartBookmark(tagName);
builder.EndBookmark(tagName);
return ReplaceAction.Replace;
}
///
/// Splits text of the specified run into two runs.
/// Inserts the new run just after the specified run.
///
private static Run SplitRun(Run run, int position)
{
Run afterRun = (Run)run.Clone(true);
afterRun.Text = run.Text.Substring(position);
run.Text = run.Text.Substring(0, position);
run.ParentNode.InsertAfter(afterRun, run);
return afterRun;
}
}
Moreover, I am working over the second part of your request and will get back to you soon.
Best Regards,
Hi Nitin,
Thanks for your patience. For the second part of your problem, I think the following routine will serve the purpose.
private class LinkToBookmarkAtReplaceHandler : IReplacingCallback
{
ReplaceAction IReplacingCallback.Replacing(ReplacingArgs e)
{
// This is a Run node that contains either the beginning or the complete match.
Node currentNode = e.MatchNode;
// The first (and may be the only) run can contain text before the match,
// in this case it is necessary to split the run.
if (e.MatchOffset > 0)
currentNode = SplitRun((Run)currentNode, e.MatchOffset);
// This array is used to store all nodes of the match for further removing.
ArrayList runs = new ArrayList();
// Find all runs that contain parts of the match string.
int remainingLength = e.Match.Value.Length;
while (
(remainingLength > 0) &&
(currentNode != null) &&
(currentNode.GetText().Length <= remainingLength))
{
runs.Add(currentNode);
remainingLength = remainingLength - currentNode.GetText().Length;
// Select the next Run node.
// Have to loop because there could be other nodes such as BookmarkStart etc.
do
{
currentNode = currentNode.NextSibling;
}
while ((currentNode != null) && (currentNode.NodeType != NodeType.Run));
}
// Split the last run that contains the match if there is any text left.
if ((currentNode != null) && (remainingLength > 0))
{
SplitRun((Run)currentNode, remainingLength);
runs.Add(currentNode);
}
string tagName = e.Match.Value.Replace("[>", "").Replace("<]", "");
string[] splits = tagName.Split(new char[] { '~' });
string displayText = splits[0];
string bookmarkName = splits[1];
DocumentBuilder builder = new DocumentBuilder((Document)e.MatchNode.Document);
builder.MoveTo(e.MatchNode);
builder.MoveTo((Run)runs[runs.Count - 1]);
builder.InsertHyperlink(displayText, bookmarkName, true);
return ReplaceAction.Replace;
}
///
/// Splits text of the specified run into two runs.
/// Inserts the new run just after the specified run.
///
private static Run SplitRun(Run run, int position)
{
Run afterRun = (Run)run.Clone(true);
afterRun.Text = run.Text.Substring(position);
run.Text = run.Text.Substring(0, position);
run.ParentNode.InsertAfter(afterRun, run);
return afterRun;
}
}
Best Regards,
That’s fantastic! It worked.
Thank you so much!
Hi Nitin,
Thanks for your feedback. Please let us know any time you have any further queries. We’re always glad to help you.
Best Regards,