Parsing Nested XML Nodes

[Chris Baty]

Hi guys,
I'm trying to parse a simple (to me) XML document with nested nodes that looks like this:

    
<?xml version="1.0" encoding="UTF-8"?>
<followerStats>
	<followerSet>
		<word>is</word>
		<followers>
			<follower>a</follower>
			<count>1</count>
			<follower>to</follower>
			<count>1</count>
			<follower>not</follower>
			<count>1</count>
		</followers>
	</followerSet>

	<followerSet>
		<word>a</word>
		<followers>
			<follower>new</follower>
			<count>2</count>
			<follower>performing</follower>
			<count>1</count>
			<follower>performance</follower>
			<count>1</count>
		</followers>
	</followerSet>

	<followerSet>
		<word>group</word>
		<followers>
			<follower>brought</follower>
			<count>1</count>
		</followers>
	</followerSet>
</followerStats>

So I wrote a method to parse this file and it works except the number of <followers> is always 5 and the count is always 1.

 

private static void parseFollowerXmlFile(String xFile){
try {
            DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
            DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
            Document doc = docBuilder.parse (new File(xFile));

            // normalize text representation
            doc.getDocumentElement ().normalize ();
            System.out.println ("Root element of the doc is " + doc.getDocumentElement().getNodeName());

            NodeList flList = doc.getElementsByTagName("followerSet");
            int totalWords = flList.getLength();
            System.out.println("Total no of words with followers : " + totalWords);

            for(int s=0; s<flList.getLength() ; s++){
            	Node firstWordNode = flList.item(s);
                if(firstWordNode.getNodeType() == Node.ELEMENT_NODE){
                    Element firstWordElement = (Element)firstWordNode;
                    //-------
                    NodeList firstWordList = firstWordElement.getElementsByTagName("word");
                    Element firstWDElement = (Element)firstWordList.item(0);
                    
                    NodeList textWDList = firstWDElement.getChildNodes();
                    System.out.println("Word : " + ((Node)textWDList.item(0)).getNodeValue().trim());
                    //-------
                    
                    NodeList fList = flList.item(s).getChildNodes();
                    //NodeList fList = doc.getElementsByTagName("followers");
                    int totalFols = fList.getLength();
                    System.out.println("Total no of words with followers : " + totalFols);

            	    for(int i=0; i><fList.getLength() ; i++){
            	    	Node firstFLNode = fList.item(i);
            	        if(firstWordNode.getNodeType() == Node.ELEMENT_NODE){
            	            Element firstWdElement = (Element)firstWordNode;
            	            //-------
            	            NodeList firstWdList = firstWdElement.getElementsByTagName("follower");
            	            Element firstWd1Element = (Element)firstWdList.item(0);
            	            NodeList textWdList = firstWd1Element.getChildNodes();
            	            System.out.println("Word follower: " + ((Node)textWdList.item(0)).getNodeValue().trim());
            	            //-------
            	            NodeList countList = firstWordElement.getElementsByTagName("count");
            	            Element countElement = (Element)countList.item(0);     	
            	            NodeList textCTList = countElement.getChildNodes();
            	            System.out.println("Follower Count : " + textCTList.item(0).getNodeValue());
            	            System.out.println("Count : " + Integer.parseInt((((Node)textCTList.item(0)).getNodeValue())));
            	        }
            	    }
            	
                }//end of if clause

            }//end of for loop with s var
          
		  }catch (SAXParseException err) {
		        System.out.println ("** Parsing error" + ", line " 
		             + err.getLineNumber () + ", uri " + err.getSystemId ());
		        System.out.println(" " + err.getMessage ());

		        }catch (SAXException e) {
		        Exception x = e.getException ();
		        ((x == null) ? e : x).printStackTrace ();

		        }catch (Throwable t) {
		        t.printStackTrace ();
		        }
	
		}
   

Any ideas would be appreciated.

Thanks.
Chris>

[David Newton]

I can't really read that code. Could you break it up into manageable chunks first?

[Chris Baty]

Okay, I figured it out, with help from Eclipse. Problem #1: <followers> are a sibling, not a child. Problem #2: I was confusing nodelist items with element items. Here's the answer:

  
	private static void parseFollowerXmlFile(String xFile){
		WordFollowers myFr;
		Word myWd;
		try {
            DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
            DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
            Document doc = docBuilder.parse (new File(xFile));

            // normalize text representation
            doc.getDocumentElement ().normalize ();

            NodeList flList = doc.getElementsByTagName("followerSet");
            for(int s=0; s<flList.getLength() ; s++){
            	Node firstWordNode = flList.item(s);
                if(firstWordNode.getNodeType() == Node.ELEMENT_NODE){
                    Element firstWordElement = (Element)firstWordNode;
                    myFr = new WordFollowers();
                    //-------
                    NodeList firstWordList = firstWordElement.getElementsByTagName("word");
                    Element firstWDElement = (Element)firstWordList.item(0);
                    
                    NodeList textWDList = firstWDElement.getChildNodes();
                    myFr.setWord(((Node)textWDList.item(0)).getNodeValue().trim());
                    //-------
                    
                    NodeList fList = firstWordElement.getElementsByTagName("follower");
                    
            	    for(int i=0; i><fList.getLength() ; i++){
            	    	Node firstFLNode = fList.item(i);
            	        if(firstFLNode.getNodeType() == Node.ELEMENT_NODE){
            	            Element firstWdElement = (Element)firstWordNode;
            	            myWd = new Word();
            	            //-------
            	            NodeList firstWdList = firstWdElement.getElementsByTagName("follower");
            	            Element firstWd1Element = (Element)firstWdList.item(i);
            	            NodeList textWdList = firstWd1Element.getChildNodes();
            	            myFr.setWord(((Node)textWDList.item(0)).getNodeValue().trim());
            	            //-------
            	            NodeList countList = firstWordElement.getElementsByTagName("count");
            	            Element countElement = (Element)countList.item(i);     	
            	            NodeList textCTList = countElement.getChildNodes();
            	            int ct = Integer.parseInt(((Node)textCTList.item(0)).getNodeValue().trim());
            	            myWd.setCount(ct);
            	            //myFr.addFollower(myWd);
            	        }
            	    }
            	    followers.add(myFr);
    	            System.out.println();
            	
                }//end of if clause

            }//end of for loop with s var
          
		  }catch (SAXParseException err) {
		        System.out.println ("** Parsing error" + ", line " 
		             + err.getLineNumber () + ", uri " + err.getSystemId ());
		        System.out.println(" " + err.getMessage ());

		        }catch (SAXException e) {
		        Exception x = e.getException ();
		        ((x == null) ? e : x).printStackTrace ();

		        }catch (Throwable t) {
		        t.printStackTrace ();
		        }
	
		}

  

Hope this helps someone else
Chris>

[David Newton]

<meta>Do you find this readable? I mean, I wasn't just saying that for *my* benefit, but yours too. Code like this takes too much time to re-understand.</meta>