How can I remove all comments from a docx file using docx4j?
I want to remove all comments from docx file using docx4j.
I can remove the actual comments with a code snippet as shown below, but I also have to remove links to comments from the main body of the document (otherwise the document is corrupted), but I cannot figure out how.
CommentsPart cmtsPart = wordMLPackage.getMainDocumentPart().getCommentsPart();
org.docx4j.wml.Comments cmts = cpart.getJaxbElement();
List<Comments.Comment> coms = cmts.getComment();
coms.clear();
Any recommendations are appreciated!
I also posted this question on the docx4j forum: http://www.docx4java.org/forums/docx-java-f6/how-to-remove-all-comments-from-docx-file-t1329.html .
Thank.
source to share
You can use TraversalUtil to find matching objects (CommentRangeStart, CommentRangeEnd, R.CommentReference) and then remove them.
import java.util.ArrayList;
import java.util.List;
import javax.xml.bind.JAXBElement;
import org.docx4j.TraversalUtil;
import org.docx4j.TraversalUtil.CallbackImpl;
import org.docx4j.XmlUtils;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart;
import org.docx4j.wml.Body;
import org.docx4j.wml.CommentRangeEnd;
import org.docx4j.wml.CommentRangeStart;
import org.docx4j.wml.ContentAccessor;
import org.docx4j.wml.R.CommentReference;
import org.jvnet.jaxb2_commons.ppp.Child;
public class Foo {
public static void main(String[] args) throws Exception {
WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage
.load(new java.io.File(System.getProperty("user.dir") + "/Foo.docx"));
MainDocumentPart documentPart = wordMLPackage.getMainDocumentPart();
org.docx4j.wml.Document wmlDocumentEl = (org.docx4j.wml.Document) documentPart
.getJaxbElement();
Body body = wmlDocumentEl.getBody();
CommentFinder cf = new CommentFinder();
new TraversalUtil(body, cf);
for (Child commentElement : cf.commentElements) {
System.out.println(commentElement.getClass().getName());
Object parent = commentElement.getParent();
List<Object> theList = ((ContentAccessor)parent).getContent();
boolean removeResult = remove(theList, commentElement );
System.out.println(removeResult);
}
}
private static boolean remove(List<Object> theList, Object bm) {
// Can't just remove the object from the parent,
// since in the parent, it may be wrapped in a JAXBElement
for (Object ox : theList) {
if (XmlUtils.unwrap(ox).equals(bm)) {
return theList.remove(ox);
}
}
return false;
}
static class CommentFinder extends CallbackImpl {
List<Child> commentElements = new ArrayList<Child>();
@Override
public List<Object> apply(Object o) {
if (o instanceof javax.xml.bind.JAXBElement
&& (((JAXBElement)o).getName().getLocalPart().equals("commentReference")
|| ((JAXBElement)o).getName().getLocalPart().equals("commentRangeStart")
|| ((JAXBElement)o).getName().getLocalPart().equals("commentRangeEnd")
)) {
System.out.println(((JAXBElement)o).getName().getLocalPart());
commentElements.add( (Child)XmlUtils.unwrap(o) );
} else
if (o instanceof CommentReference ||
o instanceof CommentRangeStart ||
o instanceof CommentRangeEnd) {
System.out.println(o.getClass().getName());
commentElements.add((Child)o);
}
return null;
}
@Override // to setParent
public void walkJAXBElements(Object parent) {
List children = getChildren(parent);
if (children != null) {
for (Object o : children) {
if (o instanceof javax.xml.bind.JAXBElement
&& (((JAXBElement)o).getName().getLocalPart().equals("commentReference")
|| ((JAXBElement)o).getName().getLocalPart().equals("commentRangeStart")
|| ((JAXBElement)o).getName().getLocalPart().equals("commentRangeEnd")
)) {
((Child)((JAXBElement)o).getValue()).setParent(XmlUtils.unwrap(parent));
} else {
o = XmlUtils.unwrap(o);
if (o instanceof Child) {
((Child)o).setParent(XmlUtils.unwrap(parent));
}
}
this.apply(o);
if (this.shouldTraverse(o)) {
walkJAXBElements(o);
}
}
}
}
}
}
source to share
Jason,
Thanks for the offer; I have implemented the solution (posted below) using TraversalUtil, with a CommentFinder class that finds comments, RangeStarts and CommentRangeEnds and adds them to the list. Then I loop through the list and remove each item using parent.getContent (). Remove (obj).
RangeStart / RangeEnd elements are removed from their parent P nodes as expected, but the CommentReference is not removed from the parent R - if I check for the removeResult value, it is false when the CommentReference is removed. Any idea why this would be the case?
Thanks again.
static class CommentFinder extends CallbackImpl {
List<Child> commentElements = new ArrayList<Child>();
@Override
public List<Object> apply(Object o) {
if (o instanceof CommentReference ||
o instanceof CommentRangeStart ||
o instanceof CommentRangeEnd) {
commentElements.add((Child) o);
}
return null;
}
@Override
public void walkJAXBElements(Object parent) {
List<Object> children = getChildren(parent);
if (children != null) {
for (Object o : children) {
o = XmlUtils.unwrap(o);
this.apply(o);
if (this.shouldTraverse(o)) {
walkJAXBElements(o);
}
}
}
}
}
// how it is used
CommentFinder cf = new CommentFinder();
new TraversalUtil(body, cf);
for (Child commentElement : cf.commentElements) {
Object parent = commentElement.getParent();
if (parent instanceof P) {
boolean removeResult = ((P)parent).getContent().remove(commentElement);
} else if (parent instanceof R) {
boolean removeResult = ((R)parent).getContent().remove(commentElement);
}
}
source to share