Hi Team,
I need to extract all formatted content from a word document which has track changes.
I am able to extract revisions , but it is not returning the formatted description, whether bold, italic, strikethrough…
I too need to get page number from the below code.
Document doc = new Document(documentNameAndPath);
RevisionCollection revisionCollections = doc.getRevisions();
revisionCollections.getGroups();
for (Revision revision : revisionCollections) {
stopIteration++;
JSONObject revisionDataJsonObject = new JSONObject();
JSONObject formattedDataJsonObject = new JSONObject();
String revisionText = revision.getParentNode().getText();
revisionDataJsonObject.put("revisionText", revisionText);
formattedDataJsonObject.put("revisionText", revisionText);
String revisionAuthor = revision.getAuthor();
revisionDataJsonObject.put("revisionAuthor", revisionAuthor);
formattedDataJsonObject.put("revisionAuthor", revisionAuthor);
String revisionPostedAt = "";
SimpleDateFormat sdf = new SimpleDateFormat("dd-MMM-yyyy HH:mm");
Date revisionDate = revision.getDateTime();
sdf.setTimeZone(TimeZone.getTimeZone("UTC"));
if(revisionDate != null && !revisionDate.toString().isEmpty()){
revisionPostedAt = sdf.format(revisionDate);
revisionDataJsonObject.put("revisionDate", revisionPostedAt);
formattedDataJsonObject.put("revisionDate", revisionPostedAt);
}
int revisionModeInt = revision.getRevisionType();
String revisionMode = "";
if(revisionModeInt == 0 ){
revisionMode = "INSERTION";
}else if(revisionModeInt == 1 ){
revisionMode = "DELETION";
}else if(revisionModeInt == 2 ){
revisionMode = "FORMAT_CHANGE";
}else if(revisionModeInt == 3 ){
revisionMode = "STYLE_DEFINITION_CHANGE";
}else if(revisionModeInt == 4 ){
revisionMode = "MOVING";
}
revisionDataJsonObject.put("revisionMode", revisionMode);
formattedDataJsonObject.put("revisionMode", revisionMode);
revisionJsonArray.add(0,formattedDataJsonObject);
revisionJsonArray.add(1,revisionDataJsonObject);
Regards,
Mamtha.A.C.D.