We Keep Coding

Apache POI docx file content control parse

I'm trying to parse docx file that contains content control fields (that are added using window like this, reference image, mine is on another language)
I'm using library APACHE POI. I found this question on how to do it. I used the same code:
import java.io.FileInputStream;
import org.apache.poi.xwpf.usermodel.*;
import java.util.List;
import java.util.ArrayList;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.*;
import org.apache.xmlbeans.XmlCursor;
import javax.xml.namespace.QName;
public class ReadWordForm {
private static List<XWPFSDT> extractSDTsFromBody(XWPFDocument document) {
XWPFSDT sdt;
XmlCursor xmlcursor = document.getDocument().getBody().newCursor();
QName qnameSdt = new QName("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "sdt", "w");
List<XWPFSDT> allsdts = new ArrayList<XWPFSDT>();
while (xmlcursor.hasNextToken()) {
XmlCursor.TokenType tokentype = xmlcursor.toNextToken();
if (tokentype.isStart()) {
if (qnameSdt.equals(xmlcursor.getName())) {
if (xmlcursor.getObject() instanceof CTSdtRun) {
sdt = new XWPFSDT((CTSdtRun)xmlcursor.getObject(), document);
//System.out.println("block: " + sdt);
allsdts.add(sdt);
} else if (xmlcursor.getObject() instanceof CTSdtBlock) {
sdt = new XWPFSDT((CTSdtBlock)xmlcursor.getObject(), document);
//System.out.println("inline: " + sdt);
allsdts.add(sdt);
}
}
}
}
return allsdts;
}
public static void main(String[] args) throws Exception {
XWPFDocument document = new XWPFDocument(new FileInputStream("WordDataCollectingForm.docx"));
List<XWPFSDT> allsdts = extractSDTsFromBody(document);
for (XWPFSDT sdt : allsdts) {
//System.out.println(sdt);
String title = sdt.getTitle();
String content = sdt.getContent().getText();
if (!(title == null) && !(title.isEmpty())) {
System.out.println(title + ": " + content);
} else {
System.out.println("====sdt without title====");
}
}
document.close();
}
}
The problem is that this code doesn't see these fields in the my docx file until I open it in LibreOffice and re-save it. So if the file is from Windows being put into this code it doesn't see these content control fields. But if I re-save the file in the LibreOffice (using the same format) it starts to see these fields, even tho it loses some of the data (titles and tags of some fields). Can someone tell me what might be the reason of it, how do I fix that so it will see these fields? Or there's an easier way using docx4j maybe? Unfortunately there's not much info about how to do it using these 2 libs in the internet, at least I didn't find it.
Examle files are located on google disk. The first one doesn't work, the second one works (after it was opened in Libre and field was changed to one of the options).

According to your uploaded sample files your content controls are in a table. The code you had found only gets content controls from document body directly.
Tables are beastly things in Word as table cells may contain whole document bodies each. That's why content controls in table cells are strictly separated from content controls in main document body. Their ooxml class is CTSdtCell instead of CTSdtRun or CTSdtBlock and in apache poi their class is XWPFSDTCell instead of XWPFSDT.
If it is only about reading the content, then one could fall back to XWPFAbstractSDT which is the abstract parent class of XWPFSDTCell as well as of XWPFSDT. So following code should work:
private static List<XWPFAbstractSDT> extractSDTsFromBody(XWPFDocument document) {
XWPFAbstractSDT sdt;
XmlCursor xmlcursor = document.getDocument().getBody().newCursor();
QName qnameSdt = new QName("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "sdt", "w");
List<XWPFAbstractSDT> allsdts = new ArrayList<XWPFAbstractSDT>();
while (xmlcursor.hasNextToken()) {
XmlCursor.TokenType tokentype = xmlcursor.toNextToken();
if (tokentype.isStart()) {
if (qnameSdt.equals(xmlcursor.getName())) {
//System.out.println(xmlcursor.getObject().getClass().getName());
if (xmlcursor.getObject() instanceof CTSdtRun) {
sdt = new XWPFSDT((CTSdtRun)xmlcursor.getObject(), document);
//System.out.println("block: " + sdt);
allsdts.add(sdt);
} else if (xmlcursor.getObject() instanceof CTSdtBlock) {
sdt = new XWPFSDT((CTSdtBlock)xmlcursor.getObject(), document);
//System.out.println("inline: " + sdt);
allsdts.add(sdt);
} else if (xmlcursor.getObject() instanceof CTSdtCell) {
sdt = new XWPFSDTCell((CTSdtCell)xmlcursor.getObject(), null, null);
//System.out.println("cell: " + sdt);
allsdts.add(sdt);
}
}
}
}
return allsdts;
}
But as you see in code line sdt = new XWPFSDTCell((CTSdtCell)xmlcursor.getObject(), null, null), the XWPFSDTCell totaly lost its connection to table and tablerow.
There is not a proper method to get the XWPFSDTCell directly from a XWPFTable. So If one would need to get XWPFSDTCell connected to its table, then also parsing the XML is needed. This could look like so:
private static List<XWPFSDTCell> extractSDTsFromTableRow(XWPFTableRow row) {
XWPFSDTCell sdt;
XmlCursor xmlcursor = row.getCtRow().newCursor();
QName qnameSdt = new QName("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "sdt", "w");
QName qnameTr = new QName("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "tr", "w");
List<XWPFSDTCell> allsdts = new ArrayList<XWPFSDTCell>();
while (xmlcursor.hasNextToken()) {
XmlCursor.TokenType tokentype = xmlcursor.toNextToken();
if (tokentype.isStart()) {
if (qnameSdt.equals(xmlcursor.getName())) {
//System.out.println(xmlcursor.getObject().getClass().getName());
if (xmlcursor.getObject() instanceof CTSdtCell) {
sdt = new XWPFSDTCell((CTSdtCell)xmlcursor.getObject(), row, row.getTable().getBody());
//System.out.println("cell: " + sdt);
allsdts.add(sdt);
}
}
} else if (tokentype.isEnd()) {
//we have to check whether we are at the end of the table row
xmlcursor.push();
xmlcursor.toParent();
if (qnameTr.equals(xmlcursor.getName())) {
break;
}
xmlcursor.pop();
}
}
return allsdts;
}
And called from document like so:
...
for (XWPFTable table : document.getTables()) {
for (XWPFTableRow row : table.getRows()) {
List<XWPFSDTCell> allTrsdts = extractSDTsFromTableRow(row);
for (XWPFSDTCell sdt : allTrsdts) {
//System.out.println(sdt);
String title = sdt.getTitle();
String content = sdt.getContent().getText();
if (!(title == null) && !(title.isEmpty())) {
System.out.println(title + ": " + content);
} else {
System.out.println("====sdt without title====");
System.out.println(content);
}
}
}
}
...
Using curren apache poi 5.2.0 it is possible getting the XWPFSDTCell from XWPFTableRow via XWPFTableRow.getTableICells. This gets al List of ICells which is an interface which XWPFSDTCell also implemets.
So following code will get all XWPFSDTCell from tables without the need of low level XML parsing:
...
for (XWPFTable table : document.getTables()) {
for (XWPFTableRow row : table.getRows()) {
for (ICell iCell : row.getTableICells()) {
if (iCell instanceof XWPFSDTCell) {
XWPFSDTCell sdt = (XWPFSDTCell)iCell;
//System.out.println(sdt);
String title = sdt.getTitle();
String content = sdt.getContent().getText();
if (!(title == null) && !(title.isEmpty())) {
System.out.println(title + ": " + content);
} else {
System.out.println("====sdt without title====");
System.out.println(content);
}
}
}
}
}
...

Apache POI: Remove Chart from Word Template file entirely

I am using a Word template with Excel graphs which I want to programmatically manipulate with the Java Apache POI library. For this I also need to be able to conditionally delete a Chart which is stored in this template.
Based on Axel Richters post (Removing chart from PowerPoint slide with Apache POI) I think I am almost there, but when I want to open the updated Word file it gives an error about unreadable content. This is what I have thus far:
PackagePart packagePartChart = xWPFChart.getPackagePart();
PackagePart packagePartWordDoc = xWPFDocument.getPackagePart();
OPCPackage packageWordDoc = packagePartWordDoc.getPackage();
// iterate over all relations the chart has and remove them
for (PackageRelationship chartrelship : packagePartChart.getRelationships()) {
String partname = chartrelship.getTargetURI().toString();
PackagePart part = packageWordDoc.getPartsByName(Pattern.compile(partname)).get(0);
packageWordDoc.removePart(part);
packagePartChart.removeRelationship(chartrelship.getId());
}
// now remove the chart itself from the word doc
Method removeRelation = POIXMLDocumentPart.class.getDeclaredMethod("removeRelation", POIXMLDocumentPart.class);
removeRelation.setAccessible(true);
removeRelation.invoke(xWPFDocument, xWPFChart);
If I unzip the Word file I correctly see that:
the relation between the WordDoc and the Chart are deleted in '\word\ _rels\document.xml.rels'
the chart itself is deleted in folder '\word\charts'
the relations between the documents supporting the Chart itself are deleted in folder '\word\charts\' _rels
the related chart items themselves are deleted:
StyleN / ColorsN in folder '\word\charts' and
Microsoft_Excel_WorksheetN in folder '\word\embeddings'
Anybody any idea on what could be going wrong here?

Indeed the finding of the right paragraph holding the chart was a challenge. In the end, for simplicity sake, I added a one row/one column placeholder table with one cell with a text, let's say 'targetWordString' in it, DIRECTLY before the chart. With the below function I am location the BodyElementID of this table:
private Integer iBodyElementIterator (XWPFDocument wordDoc,String targetWordString) {
Iterator<IBodyElement> iter = wordDoc.getBodyElementsIterator();
Integer bodyElementID = null;
while (iter.hasNext()) {
IBodyElement elem = iter.next();
bodyElementID = wordDoc.getBodyElements().indexOf(elem);
if (elem instanceof XWPFParagraph) {
XWPFParagraph paragraph = (XWPFParagraph) elem;
for (XWPFRun runText : paragraph.getRuns()) {
String text = runText.getText(0);
Core.getLogger("WordExporter").trace("Body Element ID: " + bodyElementID + " Text: " + text);
if (text != null && text.equals(targetWordString)) {
break;
}
}
} else if (elem instanceof XWPFTable) {
if (((XWPFTable) elem).getRow(0) != null && ((XWPFTable) elem).getRow(0).getCell(0) != null) {
// the first cell holds the name via the template
String tableTitle = ((XWPFTable) elem).getRow(0).getCell(0).getText();
if (tableTitle.equals(targetWordString)) {
break;
}
Core.getLogger("WordExporter").trace("Body Element ID: " + bodyElementID + " Text: " + tableTitle);
} else {
Core.getLogger("WordExporter").trace("Body Element ID: " + bodyElementID + " Table removed!");
}
}
else {
Core.getLogger("WordExporter").trace("Body Element ID: " + bodyElementID + " Text: ?");
}
}
return bodyElementID;
}
In the main part of the code I am calling this function to locate the table, then first delete the chart (ID +1) and then the table (ID)
int elementIDToBeRemoved = iBodyElementIterator(xWPFWordDoc,targetWordString);
xWPFWordDoc.removeBodyElement(elementIDToBeRemoved + 1);
xWPFWordDoc.removeBodyElement(elementIDToBeRemoved);
It needs to be in this order, because the ID's are reordered once you delete a number in between, hence deleting the table first, would mean the chart would get that ID in principle.

I did find a more structural solution for it without the use of dummy tables for the positioning. The solution is build out into 2 parts:
Determine relationship id of chart in word document
Remove chart based on relationship id and remove paragraph + runs
Determine relationship id of chart in word document
First I have determined with a boolean variable 'chartUsed' whether the chart needs to be deleted.
if (!chartUsed) {
String chartPartName = xWPFChart.getPackagePart().getPartName().getName();
String ridChartToBeRemoved = null;
// iterate over all relations the chart has and remove them
for (RelationPart relation : wordDoc.getRelationParts()) {
PackageRelationship relShip = relation.getRelationship();
if (relShip.getTargetURI().toString().equals(chartPartName)) {
ridChartToBeRemoved = relShip.getId();
Core.getLogger(logNode).info("Chart with title " + chartTitle + " has relationship id " + relShip.getId());
break;
}
}
removeChartByRelId(wordDoc, ridChartToBeRemoved);
}
(Core.getLogger is an internal API from the Mendix low code platform I use).
At the end I am calling the function removeChartByRelId which will remove the chart if the relation is found within a run of a paragraph:
Remove chart based on relationship id and remove paragraph + runs
private void removeChartByRelId (XWPFDocument wordDoc, String chartRelId) {
Iterator<IBodyElement> iter = wordDoc.getBodyElementsIterator();
Integer bodyElementID = null;
while (iter.hasNext()) {
IBodyElement elem = iter.next();
bodyElementID = wordDoc.getBodyElements().indexOf(elem);
if (elem instanceof XWPFParagraph) {
Core.getLogger(logNode).trace("XWPFParagraph Body Element ID: " + bodyElementID);
XWPFParagraph paragraph = (XWPFParagraph) elem;
boolean removeParagraph = false;
for (XWPFRun run : paragraph.getRuns()) {
if (run.getCTR().getDrawingList().size()>0) {
String drawingXMLText = run.getCTR().getDrawingList().get(0).xmlText();
boolean isChart = drawingXMLText.contains("http://schemas.openxmlformats.org/drawingml/2006/chart");
String graphicDataXMLText = run.getCTR().getDrawingList().get(0).getInlineArray(0).getGraphic().getGraphicData().xmlText();
boolean contains = graphicDataXMLText.contains(chartRelId);
if (isChart && contains) {
Core.getLogger(logNode).info("Removing chart with relId " + chartRelId + " as it isnt used in data");
run.getCTR().getDrawingList().clear();
removeParagraph = true;
}
}
}
if (removeParagraph) {
for (int i = 0; i < paragraph.getRuns().size(); i++){
paragraph.removeRun(i);
}
}
}
}
}

Error in Lucene text Search

I'm new to text search and I'm studying some examples related to lucene. I found one of the example from this link. http://javatechniques.com/blog/lucene-in-memory-text-search-example/ I tried it in my eclipse IDE. But it gives some errors. I imported all the relevent jar files as well.
Here Is the code :
public class InMemoryExample {
public static void main(String[] args) {
// Construct a RAMDirectory to hold the in-memory representation
// of the index.
RAMDirectory idx = new RAMDirectory();
try {
// Make an writer to create the index
IndexWriter writer =
new IndexWriter(idx, new StandardAnalyzer(Version.LUCENE_48),
IndexWriter.MaxFieldLength.LIMITED);
// Add some Document objects containing quotes
writer.addDocument(createDocument("Theodore Roosevelt",
"It behooves every man to remember that the work of the " +
"critic, is of altogether secondary importance, and that, " +
"in the end, progress is accomplished by the man who does " +
"things."));
writer.addDocument(createDocument("Friedrich Hayek",
"The case for individual freedom rests largely on the " +
"recognition of the inevitable and universal ignorance " +
"of all of us concerning a great many of the factors on " +
"which the achievements of our ends and welfare depend."));
writer.addDocument(createDocument("Ayn Rand",
"There is nothing to take a man's freedom away from " +
"him, save other men. To be free, a man must be free " +
"of his brothers."));
writer.addDocument(createDocument("Mohandas Gandhi",
"Freedom is not worth having if it does not connote " +
"freedom to err."));
// Optimize and close the writer to finish building the index
writer.optimize();
writer.close();
// Build an IndexSearcher using the in-memory index
Searcher searcher = new IndexSearcher(idx);
// Run some queries
search(searcher, "freedom");
search(searcher, "free");
search(searcher, "progress or achievements");
searcher.close();
}
catch (IOException ioe) {
// In this example we aren't really doing an I/O, so this
// exception should never actually be thrown.
ioe.printStackTrace();
}
catch (ParseException pe) {
pe.printStackTrace();
}
}
/**
* Make a Document object with an un-indexed title field and an
* indexed content field.
*/
private static Document createDocument(String title, String content) {
Document doc = new Document();
// Add the title as an unindexed field...
doc.add(new Field("title", title, Field.Store.YES, Field.Index.NO));
// ...and the content as an indexed field. Note that indexed
// Text fields are constructed using a Reader. Lucene can read
// and index very large chunks of text, without storing the
// entire content verbatim in the index. In this example we
// can just wrap the content string in a StringReader.
doc.add(new Field("content", content, Field.Store.YES, Field.Index.ANALYZED));
return doc;
}
/**
* Searches for the given string in the "content" field
*/
private static void search(Searcher searcher, String queryString)
throws ParseException, IOException {
// Build a Query object
//Query query = QueryParser.parse(
QueryParser parser = new QueryParser("content", new StandardAnalyzer(Version.LUCENE_48));
Query query = parser.parse(queryString);
int hitsPerPage = 10;
// Search for the query
TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
searcher.search(query, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
int hitCount = collector.getTotalHits();
System.out.println(hitCount + " total matching documents");
// Examine the Hits object to see if there were any matches
if (hitCount == 0) {
System.out.println(
"No matches were found for \"" + queryString + "\"");
} else {
System.out.println("Hits for \"" +
queryString + "\" were found in quotes by:");
// Iterate over the Documents in the Hits object
for (int i = 0; i < hitCount; i++) {
// Document doc = hits.doc(i);
ScoreDoc scoreDoc = hits[i];
int docId = scoreDoc.doc;
float docScore = scoreDoc.score;
System.out.println("docId: " + docId + "\t" + "docScore: " + docScore);
Document doc = searcher.doc(docId);
// Print the value that we stored in the "title" field. Note
// that this Field was not indexed, but (unlike the
// "contents" field) was stored verbatim and can be
// retrieved.
System.out.println(" " + (i + 1) + ". " + doc.get("title"));
System.out.println("Content: " + doc.get("content"));
}
}
System.out.println();
} }
but it shows few syntax errors in following lines :
Error 1:
IndexWriter writer = underline MaxFieldLength in red
new IndexWriter(idx, new StandardAnalyzer(Version.LUCENE_48),
IndexWriter.MaxFieldLength.LIMITED);
Error 2: underline optimeze() in red
writer.optimize();
Error 3: underline new IndexSearcher(idx) in red
Searcher searcher = new IndexSearcher(idx);
Error 4: underline search in red
searcher.search(query, collector);
Could you please help me to get rid of these errors? It will be a great help. Thanks
Modified code:
public class InMemoryExample {
public static void main(String[] args) throws Exception{
// Construct a RAMDirectory to hold the in-memory representation
// of the index.
RAMDirectory idx = new RAMDirectory();
// Make an writer to create the index
IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_48, new
StandardAnalyzer(Version.LUCENE_48));
IndexWriter writer = new IndexWriter(idx, cfg);
// Add some Document objects containing quotes
writer.addDocument(createDocument("Theodore Roosevelt",
"It behooves every man to remember that the work of the " +
"critic, is of altogether secondary importance, and that, " +
"in the end, progress is accomplished by the man who does " +
"things."));
writer.addDocument(createDocument("Friedrich Hayek",
"The case for individual freedom rests largely on the " +
"recognition of the inevitable and universal ignorance " +
"of all of us concerning a great many of the factors on " +
"which the achievements of our ends and welfare depend."));
writer.addDocument(createDocument("Ayn Rand",
"There is nothing to take a man's freedom away from " +
"him, save other men. To be free, a man must be free " +
"of his brothers."));
writer.addDocument(createDocument("Mohandas Gandhi",
"Freedom is not worth having if it does not connote " +
"freedom to err."));
// Optimize and close the writer to finish building the index
writer.commit();
writer.close();
// Build an IndexSearcher using the in-memory index
IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(idx));
// Run some queries
search(searcher, "freedom");
search(searcher, "free");
search(searcher, "progress or achievements");
//searcher.close();
}
/**
* Make a Document object with an un-indexed title field and an
* indexed content field.
*/
private static Document createDocument(String title, String content) {
Document doc = new Document();
// Add the title as an unindexed field...
doc.add(new Field("title", title, Field.Store.YES, Field.Index.NO));
// ...and the content as an indexed field. Note that indexed
// Text fields are constructed using a Reader. Lucene can read
// and index very large chunks of text, without storing the
// entire content verbatim in the index. In this example we
// can just wrap the content string in a StringReader.
doc.add(new Field("content", content, Field.Store.YES, Field.Index.ANALYZED));
return doc;
}
/**
* Searches for the given string in the "content" field
*/
private static void search(IndexSearcher searcher, String queryString)
throws ParseException, IOException {
// Build a Query object
//Query query = QueryParser.parse(
QueryParser parser = new QueryParser("content", new StandardAnalyzer(Version.LUCENE_48));
Query query = parser.parse(queryString);
int hitsPerPage = 10;
// Search for the query
TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
searcher.search(query, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
int hitCount = collector.getTotalHits();
System.out.println(hitCount + " total matching documents");
// Examine the Hits object to see if there were any matches
if (hitCount == 0) {
System.out.println(
"No matches were found for \"" + queryString + "\"");
} else {
System.out.println("Hits for \"" +
queryString + "\" were found in quotes by:");
// Iterate over the Documents in the Hits object
for (int i = 0; i < hitCount; i++) {
// Document doc = hits.doc(i);
ScoreDoc scoreDoc = hits[i];
int docId = scoreDoc.doc;
float docScore = scoreDoc.score;
System.out.println("docId: " + docId + "\t" + "docScore: " + docScore);
Document doc = searcher.doc(docId);
// Print the value that we stored in the "title" field. Note
// that this Field was not indexed, but (unlike the
// "contents" field) was stored verbatim and can be
// retrieved.
System.out.println(" " + (i + 1) + ". " + doc.get("title"));
System.out.println("Content: " + doc.get("content"));
}
}
System.out.println();
} }
and this is the output:
Exception in thread "main" java.lang.VerifyError: class
org.apache.lucene.analysis.SimpleAnalyzer overrides final method
tokenStream.(Ljava/lang/String;Ljava/io/Reader;)Lorg/apache/lucene/analysis/TokenStream;
at java.lang.ClassLoader.defineClass1(Native Method) at
java.lang.ClassLoader.defineClass(Unknown Source) at
java.security.SecureClassLoader.defineClass(Unknown Source) at
java.net.URLClassLoader.defineClass(Unknown Source) at
java.net.URLClassLoader.access$100(Unknown Source) at
java.net.URLClassLoader$1.run(Unknown Source) at
java.net.URLClassLoader$1.run(Unknown Source) at
java.security.AccessController.doPrivileged(Native Method) at
java.net.URLClassLoader.findClass(Unknown Source) at
java.lang.ClassLoader.loadClass(Unknown Source) at
sun.misc.Launcher$AppClassLoader.loadClass(Unknown Source) at
java.lang.ClassLoader.loadClass(Unknown Source) at
beehex.inmemeory.textsearch.InMemoryExample.search(InMemoryExample.java:98)
at
beehex.inmemeory.textsearch.InMemoryExample.main(InMemoryExample.java:58)

I don't see a third argument on the IndexWriter constructor. You should modify The code to fit to the new lucene api like so :
IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_48, new StandardAnalyzer(Version.LUCENE_48));
IndexWriter writer = new IndexWriter(idx, cfg);
Also , rather than catching an exception here , i'd rather make my main method throw Exception and let the program fail altogether
EDIT :
2) remove the optimize call as the IndexWriter class does not have that method any longer (i think commit will do the trick here) .
3) define the IndexSearcher class like so :
IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(idx));

Can't update a cq5 workflow to get the current state.

I'm following this tutorial to write a workflow for 3 HTML forms (without using CQ5 form component and CQ5 workflow submit button). I use this code to write Process step handling for my workflow:
public class MyProcess implements WorkflowProcess {
public void execute(WorkItem item, WorkflowSession session,
MetaDataMap map) throws WorkflowException {
boolean advanced = false;
Boolean goBack = map.get("goBack", Boolean.class);
List<Route> routes = null;
if (goBack == null || goBack == false) {
routes = session.getRoutes(item);
} else {
routes = session.getBackRoutes(item);
}
for (Route route : routes) {
LOG.info("===============================");
LOG.info("Rout name: " + route.getName());
LOG.info("Destinations: ");
for (WorkflowTransition dest: route.getDestinations()) {
LOG.info("dest: " + dest.getTo().getTitle());
}
LOG.info("===============================");
if (route.hasDefault()) {
String fromTitle = item.getNode().getTitle();
String toTitle = route.getDestinations().get(0).getTo()
.getTitle();
session.complete(item, route);
LOG.info("===============================");
LOG.info(item.getId() + " advanced from " + fromTitle
+ " to " + toTitle);
LOG.info("===============================");
advanced = true;
}
}
// fallback if no route was marked as default
if (!advanced) {
session.complete(item, routes.get(0));
String fromTitle = item.getNode().getTitle();
String toTitle = routes.get(0).getDestinations().get(0).getTo()
.getTitle();
LOG.info("===============================");
LOG.info(item.getId() + " advanced from " + fromTitle + " to "
+ toTitle);
LOG.info("===============================");
}
}
}
My question is: after i use session.complete to advance to next step, how can i refresh the workflow session to reach the current step information.

I think #yashahuja is correct. I was poking around and on the aem 'working with workflow' page I found some information about persisting data throw workflow steps using MetaDataMap.
From this page: http://dev.day.com/docs/en/cq/current/workflows/wf-extending.html
"Use workflow metadata to persist information that is required during the lifetime of the workflow. A common requirement of workflow steps is to persist data for future use in the workflow, or to retrieve the persisted data.
Workflow metadata is stored in a MetaDataMap object. The Java API provides the Workflow.getMetaDataMap method that returns the MetaDataMap object. Also, the WorkItem.getWorkflowData method returns a WorkflowData object that provides the same getMetaDataMap object.
Therefore, the workflow MetaDataMap object is available to the OSGi service or ECMA script of a step component."
example:
public void execute(WorkItem item, WorkflowSession session, MetaDataMap args) throws WorkflowException {
MetaDataMap wfd = item.getWorkflow().getMetaDataMap();
wfd.put("mykey", "My Step Value");
Set<String> keyset = wfd.keySet();
Iterator<String> i = keyset.iterator();
while (i.hasNext()){
Object key = i.next();
log.info("The workflow medata includes key {} and value {}",key.toString(),wfd.get(key).toString());
}

How to find min-max occurrence of an element in xsd using xsom

I want to find out the minimum occurence maximm occurence of an xsd element using xsom of java.I got this code to find out complex elements.Can anyone help me in find out occurence of all the xsd element.Atlest give me a code snippet with the class and method to be used to find the occurrence
xmlfile = "Calendar.xsd"
XSOMParser parser = new XSOMParser();
parser.parse(new File(xmlfile));
XSSchemaSet sset = parser.getResult();
XSSchema s = sset.getSchema(1);
if (s.getTargetNamespace().equals("")) // this is the ns with all the stuff
// in
{
// try ElementDecls
Iterator jtr = s.iterateElementDecls();
while (jtr.hasNext())
{
XSElementDecl e = (XSElementDecl) jtr.next();
System.out.print("got ElementDecls " + e.getName());
// ok we've got a CALENDAR.. what next?
// not this anyway
/*
*
* XSParticle[] particles = e.asElementDecl() for (final XSParticle p :
* particles) { final XSTerm pterm = p.getTerm(); if
* (pterm.isElementDecl()) { final XSElementDecl ed =
* pterm.asElementDecl(); System.out.println(ed.getName()); }
*/
}
// try all Complex Types in schema
Iterator<XSComplexType> ctiter = s.iterateComplexTypes();
while (ctiter.hasNext())
{
// this will be a eSTATUS. Lets type and get the extension to
// see its a ENUM
XSComplexType ct = (XSComplexType) ctiter.next();
String typeName = ct.getName();
System.out.println(typeName + newline);
// as Content
XSContentType content = ct.getContentType();
// now what?
// as Partacle?
XSParticle p2 = content.asParticle();
if (null != p2)
{
System.out.print("We got partical thing !" + newline);
// might would be good if we got here but we never do :-(
}
// try complex type Element Decs
List<XSElementDecl> el = ct.getElementDecls();
for (XSElementDecl ed : el)
{
System.out.print("We got ElementDecl !" + ed.getName() + newline);
// would be good if we got here but we never do :-(
}
Collection<? extends XSAttributeUse> c = ct.getAttributeUses();
Iterator<? extends XSAttributeUse> i = c.iterator();
while (i.hasNext())
{
XSAttributeDecl attributeDecl = i.next().getDecl();
System.out.println("type: " + attributeDecl.getType());
System.out.println("name:" + attributeDecl.getName());
}
}
}

Assuming you are referring to com.sun.xml.xsom, the occurrence is specific to a particle (elements are not the only particles).
Here are the APIs: maxOccurs and minOccurs
For one source to see how to traverse a schema tree using XSOM please take a look here. It shows basically how the visitor patterns works with XSOM (for which Sun built a package).