Hi !!
I need to change all the line break to paragraph break. I will not save the changes. I need this changes for doing some other processing.
Is there any solution in Java?
Regards.
Thanks for your request. Please try using the following code:
<?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:office" />
// Open document
Document doc = new Document("C:\\Temp\\in.docx");
doc.getRange().replace(new asposewobfuscated.rn(ControlChar.LineBreak), new LineBreakReplacer(), false);
doc.save("C:\\Temp\\out.docx");
public static class LineBreakReplacer implements IReplacingCallback
{
public int replacing(ReplacingArgs e) {
// Get MatchNode, this is Run node where matched word starts
// The word can consist of more than one run,
// in this case MatchNode will represent only part of the word
Run matchRun = (Run)e.getMatchNode();
// We will store all parts of the word in the list
ArrayList mainTextNodes = new ArrayList();
// Get match word
String word = e.getMatch().getValue();
// The run can contain whole match word or part of the word
// When run contains only part of the word IndexOf will return negative value
int index = matchRun.getText().lastIndexOf(word);
int wordLength = word.length();
while (index < 0)
index = matchRun.getText().lastIndexOf(word.substring(0, wordLength--));
// Match Run can contain text before match word, so we should split the Run
if (index > 0) {
// Clone match run to preserve formating
Run beforeRun = (Run)matchRun.deepClone(true);
// Split text betwee two runs
beforeRun.setText(matchRun.getText().substring(0, index));
matchRun.setText(matchRun.getText().substring(index));
matchRun.getParentNode().insertBefore(beforeRun, matchRun);
}
// If the word is spanned to several Run nodes, we should find all runs that represent whole word
int currentIdx = word.length();
while (currentIdx > 0) {
if (matchRun.getText().length() > currentIdx) {
break;
}
else {
mainTextNodes.add(matchRun);
currentIdx = currentIdx - matchRun.getText().length();
// If there is no next nodes, we should stop while loop
Node currentNode = matchRun.getNextSibling();
if (currentNode == null) {
break;
}
else {
// The next node could be not Run node (BookmarkStart or BookmarkEnd for instance)
// in this case we should move to the next node
while (currentNode != null) {
if (currentNode.getNodeType() == NodeType.RUN) {
matchRun = (Run)currentNode;
break;
}
currentNode = currentNode.getNextSibling();
}
}
}
}
// Now we should split the latest run in the sequence that represents whole word,
// if there is text after match word
if (matchRun != null) {
if (matchRun.getText().length() == currentIdx) {
mainTextNodes.add(matchRun);
}
else {
Run lastRun = (Run)matchRun.deepClone(true);
lastRun.setText(matchRun.getText().substring(0, currentIdx));
matchRun.setText(matchRun.getText().substring(currentIdx));
matchRun.getParentNode().insertBefore(lastRun, matchRun);
mainTextNodes.add(lastRun);
}
}
// Move DocumentBuilder cursor to the run with line break ans insert a paragraph break.
DocumentBuilder builder = new DocumentBuilder((Document)e.getMatchNode().getDocument());
builder.moveTo((Node)mainTextNodes.get(0));
builder.writeln();
// Remove run(s) with line break
for(int i=0; i<mainTextNodes.size(); i++ )
{
Run currentRun = (Run)mainTextNodes.get(i);
currentRun.remove();
}
return ReplaceAction.SKIP;
}
}
Best regards,
Do you have a c# / .net Example ?
Where does asposewobfuscated come from ?
Hi Boas,
Thanks for your request. I have converted the above Java code to C#:
// Open document
Document
doc = new Document(“C:\Temp\in.docx”);
doc = new Document(“C:\Temp\in.docx”);
doc.Range.Replace(new Regex(ControlChar.LineBreak), new
LineBreakReplacer(), false);
LineBreakReplacer(), false);
doc.Save(“C:\Temp\out.docx”);
---------------------------------------------------------
public class LineBreakReplacer
: IReplacingCallback
: IReplacingCallback
{
ReplaceAction
IReplacingCallback.Replacing(ReplacingArgs e)
IReplacingCallback.Replacing(ReplacingArgs e)
{
// MatchNode,
this is Run node where matched word starts
this is Run node where matched word starts
// The word
can consist of more than one run,
can consist of more than one run,
// in this
case MatchNode will represent only part of the word
case MatchNode will represent only part of the word
Run
matchRun = (Run)e.MatchNode;
matchRun = (Run)e.MatchNode;
// We will
store all parts of the word in the list
store all parts of the word in the list
ArrayList
mainTextNodes = new ArrayList();
mainTextNodes = new ArrayList();
// Get match
word
word
String
word = e.Match.Value;
word = e.Match.Value;
// The run
can contain whole match word or part of the word
can contain whole match word or part of the word
// When run
contains only part of the word IndexOf will return negative value
contains only part of the word IndexOf will return negative value
int
index = matchRun.Text.LastIndexOf(word);
index = matchRun.Text.LastIndexOf(word);
int
wordLength = word.Length;
wordLength = word.Length;
while
(index < 0)
(index < 0)
index =
matchRun.Text.LastIndexOf(word.Substring(0, wordLength–));
matchRun.Text.LastIndexOf(word.Substring(0, wordLength–));
// Match Run
can contain text before match word, so we should split the Run
can contain text before match word, so we should split the Run
if
(index > 0)
(index > 0)
{
// Clone
match run to preserve formating
match run to preserve formating
Run
beforeRun = (Run)matchRun.Clone(true);
beforeRun = (Run)matchRun.Clone(true);
// Split
text betwee two runs
text betwee two runs
beforeRun.Text =
(matchRun.Text.Substring(0, index));
(matchRun.Text.Substring(0, index));
matchRun.Text =
matchRun.Text.Substring(index);
matchRun.Text.Substring(index);
matchRun.ParentNode.InsertBefore(beforeRun,
matchRun);
matchRun);
}
// If the
word is spanned to several Run nodes, we should find all runs that represent
whole word
word is spanned to several Run nodes, we should find all runs that represent
whole word
int
currentIdx = word.Length;
currentIdx = word.Length;
while
(currentIdx > 0)
(currentIdx > 0)
{
if
(matchRun.Text.Length > currentIdx)
(matchRun.Text.Length > currentIdx)
{
break;
}
else
{
mainTextNodes.Add(matchRun);
currentIdx = currentIdx -
matchRun.Text.Length;
matchRun.Text.Length;
// If
there is no next nodes, we should stop while loop
there is no next nodes, we should stop while loop
Node
currentNode = matchRun.NextSibling;
currentNode = matchRun.NextSibling;
if
(currentNode == null)
(currentNode == null)
{
break;
}
else
{
//
The next node could be not Run node (BookmarkStart or BookmarkEnd for instance)
The next node could be not Run node (BookmarkStart or BookmarkEnd for instance)
//
in this case we should move to the next node
in this case we should move to the next node
while
(currentNode != null)
(currentNode != null)
{
if (currentNode.NodeType == NodeType.Run)
{
matchRun = (Run)currentNode;
break;
}
currentNode =
currentNode.NextSibling;
currentNode.NextSibling;
}
}
}
}
// Now we
should split the latest run in the sequence that represents whole word,
should split the latest run in the sequence that represents whole word,
// if there
is text after match word
is text after match word
if
(matchRun != null)
(matchRun != null)
{
if
(matchRun.Text.Length == currentIdx)
(matchRun.Text.Length == currentIdx)
{
mainTextNodes.Add(matchRun);
}
else
{
Run
lastRun = (Run)matchRun.Clone(true);
lastRun = (Run)matchRun.Clone(true);
lastRun.Text =
matchRun.Text.Substring(0, currentIdx);
matchRun.Text.Substring(0, currentIdx);
matchRun.Text =
matchRun.Text.Substring(currentIdx);
matchRun.Text.Substring(currentIdx);
matchRun.ParentNode.InsertBefore(lastRun, matchRun);
mainTextNodes.Add(lastRun);
}
}
// Move
DocumentBuilder cursor to the run with line break ans insert a paragraph break.
DocumentBuilder cursor to the run with line break ans insert a paragraph break.
DocumentBuilder
builder = new DocumentBuilder((Document)e.MatchNode.Document);
builder = new DocumentBuilder((Document)e.MatchNode.Document);
builder.MoveTo((Node)mainTextNodes[0]);
builder.Writeln();
// Remove run(s) with line break
for (int i = 0; i < mainTextNodes.Count; i++)
{
Run
currentRun = (Run)mainTextNodes[i];
currentRun = (Run)mainTextNodes[i];
currentRun.Remove();
}
return ReplaceAction.Skip;
}
}
I hope, this will help.
Best Regards,