Convert XML to JSON format

Question

I have to convert docx file format (which is in openXML format) into JSON format. I need some guidelines to do it. Thanks in advance.

Answer 1

Use

xmlSerializer.setForceTopLevelObject(true)

to include root element in resulting JSON.

Your code would be like this

String xml = "<hello><test>1.2</test><test2>123</test2></hello>";
XMLSerializer xmlSerializer = new XMLSerializer();
xmlSerializer.setForceTopLevelObject(true);
JSON json = xmlSerializer.read(xml);

Answer 2

Docx4j

I've used docx4j before, and it's worth taking a look at.

unXml

You could also check out my open source unXml-library that is available on Maven Central.

It is lightweight, and has a simple syntax to pick out XPaths from your xml, and get them returned as Json attributes in a Jackson ObjectNode.

Answer 3

You may take a look at the Json-lib Java library, that provides XML-to-JSON conversion.

String xml = "<hello><test>1.2</test><test2>123</test2></hello>";
XMLSerializer xmlSerializer = new XMLSerializer();  
JSON json = xmlSerializer.read( xml );  

If you need the root tag too, simply add an outer dummy tag:

String xml = "<hello><test>1.2</test><test2>123</test2></hello>";
XMLSerializer xmlSerializer = new XMLSerializer();  
JSON json = xmlSerializer.read("<x>" + xml + "</x>");  

Answer 4

If you are dissatisfied with the various implementations, try rolling your own. Here is some code I wrote this afternoon to get you started. It works with net.sf.json and apache common-lang:

static public JSONObject readToJSON(InputStream stream) throws Exception {
    SAXParserFactory factory = SAXParserFactory.newInstance();
    factory.setNamespaceAware(true);
    SAXParser parser = factory.newSAXParser();
    SAXJsonParser handler = new SAXJsonParser();
    parser.parse(stream, handler);
    return handler.getJson();
}

And the SAXJsonParser implementation:

package xml2json;

import net.sf.json.*;
import org.apache.commons.lang.StringUtils;
import org.xml.sax.*;
import org.xml.sax.helpers.DefaultHandler;
import java.util.ArrayList;
import java.util.List;

public class SAXJsonParser extends DefaultHandler {

    static final String TEXTKEY = "_text";

    JSONObject result;
    List<JSONObject> stack;

    public SAXJsonParser(){}
    public JSONObject getJson(){return result;}
    public String attributeName(String name){return "@"+name;}

    public void startDocument () throws SAXException {
        stack = new ArrayList<JSONObject>();
        stack.add(0,new JSONObject());
    }
    public void endDocument () throws SAXException {result = stack.remove(0);}
    public void startElement (String uri, String localName,String qName, Attributes attributes) throws SAXException {
        JSONObject work = new JSONObject();
        for (int ix=0;ix<attributes.getLength();ix++)
            work.put( attributeName( attributes.getLocalName(ix) ), attributes.getValue(ix) );
        stack.add(0,work);
    }
    public void endElement (String uri, String localName, String qName) throws SAXException {
        JSONObject pop = stack.remove(0);       // examine stack
        Object stashable = pop;
        if (pop.containsKey(TEXTKEY)) {
            String value = pop.getString(TEXTKEY).trim();
            if (pop.keySet().size()==1) stashable = value; // single value
            else if (StringUtils.isBlank(value)) pop.remove(TEXTKEY);
        }
        JSONObject parent = stack.get(0);
        if (!parent.containsKey(localName)) {   // add new object
            parent.put( localName, stashable );
        }
        else {                                  // aggregate into arrays
            Object work = parent.get(localName);
            if (work instanceof JSONArray) {
                ((JSONArray)work).add(stashable);
            }
            else {
                parent.put(localName,new JSONArray());
                parent.getJSONArray(localName).add(work);
                parent.getJSONArray(localName).add(stashable);
            }
        }
    }
    public void characters (char ch[], int start, int length) throws SAXException {
        JSONObject work = stack.get(0);            // aggregate characters
        String value = (work.containsKey(TEXTKEY) ? work.getString(TEXTKEY) : "" );
        work.put(TEXTKEY, value+new String(ch,start,length) );
    }
    public void warning (SAXParseException e) throws SAXException {
        System.out.println("warning  e=" + e.getMessage());
    }
    public void error (SAXParseException e) throws SAXException {
        System.err.println("error  e=" + e.getMessage());
    }
    public void fatalError (SAXParseException e) throws SAXException {
        System.err.println("fatalError  e=" + e.getMessage());
        throw e;
    }
}