XML get all nodes with the same name

Question

I have xml documents that look like this:

<?xml version="1.0"?>
<root>
    <success>true</success>
    <note>
        <note_id>32219</note_id>
        <the_date>1336763490</the_date>
        <member_id>108649</member_id>
        <area>6</area>
        <note>Note 123123123</note>
    </note>
    <note>
        <note_id>33734</note_id>
        <the_date>1339003652</the_date>
        <member_id>108649</member_id>
        <area>1</area>
        <note>This is another note.</note>
    </note>
    <note>
        <note_id>49617</note_id>
        <the_date>1343050791</the_date>
        <member_id>108649</member_id>
        <area>1</area>
        <note>this is a 3rd note.</note>
    </note>
</root>

I would like to take that document, and get all of the <note> tags and convert them to a string, then pass them to my XML class and place the XML class into an array list. I hope that makes sense. So Here is the method that I am trying to use to get all of the <note> tags.

public ArrayList<XML> getNodes(String root, String name){
    ArrayList<XML> elList = new ArrayList<>();
    NodeList nodes = doc.getElementsByTagName(root);
    for(int i = 0; i < nodes.getLength(); i++){
        Element element = (Element)nodes.item(i);
        NodeList nl = element.getElementsByTagName(name);
        for(int c = 0; c < nl.getLength(); c++){
            Element e = (Element)nl.item(c);
            String xmlStr = this.nodeToString(e);
            XML xml = new XML();
            xml.parse(xmlStr);
            elList.add(xml);
        }
    }
    return elList;
}

private String nodeToString(Node node){
    StringWriter sw = new StringWriter();
    try{
        Transformer t = TransformerFactory.newInstance().newTransformer();
        t.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        t.transform(new DOMSource(node), new StreamResult(sw));
    }catch(TransformerException te){
        System.out.println("nodeToString Transformer Exception");
    }
    return sw.toString();
}

So, my question is, how can I get each <note> tag as a string? With the code I have now all I get back is null for String xmlStr = e.getNodeValue();.

Edit
I edited my main code, this seems to work.

So, you have an already parsed dom tree, and instead of populating your XML object with values retrieved from this dom tree, you want to transform back a branch of this dom tree into a string, and re-parse this string? And do that for every note element? Seems counter-productive to me. — JB Nizet, Jan 21 '13 at 22:02
I am just trying to find a way to get `root->note->note` or `root->note->the_date` really easily. With the class that I have, I kind of makes it easy. I tell it get a list of these nodes, then I can say get this item from this block. Maybe there is an easier way IDK, you tell me. — Get Off My Lawn, Jan 21 '13 at 22:05
To get the date, you just need `e.getElementsByTagName("the_date").item(0).getTextContent()`. Same thing for the note (with "note" instead of "the_date" of course). — JB Nizet, Jan 21 '13 at 22:07
Okay, now I am getting: `[Fatal Error] :1:1: Content is not allowed in prolog.` what does that mean? — Get Off My Lawn, Jan 21 '13 at 22:13
You probably have some characters before the line. Probably a hidden BOM. — JB Nizet, Jan 21 '13 at 22:17

MadProgrammer · Accepted Answer · 2013-01-21T22:43:29.963

Updated after clarification

You can find all the <note> elements using XPath.

This will allow you to isolate each node simply. You can then create a new document, based on the found nodes and transform it back to string

public class TestXML01 {

    public static void main(String[] args) {

        String xml = "<?xml version=\"1.0\"?>";
        xml += "<root>";
        xml += "<success>true</success>";
        xml += "<note>";
        xml += "<note_id>32219</note_id>";
        xml += "<the_date>1336763490</the_date>";
        xml += "<member_id>108649</member_id>";
        xml += "<area>6</area>";
        xml += "<note>Note 123123123</note>";
        xml += "</note>";
        xml += "<note>";
        xml += "<note_id>33734</note_id>";
        xml += "<the_date>1339003652</the_date>";
        xml += "<member_id>108649</member_id>";
        xml += "<area>1</area>";
        xml += "<note>This is another note.</note>";
        xml += "</note>";
        xml += "<note>";
        xml += "<note_id>49617</note_id>";
        xml += "<the_date>1343050791</the_date>";
        xml += "<member_id>108649</member_id>";
        xml += "<area>1</area>";
        xml += "<note>this is a 3rd note.</note>";
        xml += "</note>";
        xml += "</root>";

        ByteArrayInputStream bais = null;

        try {
            bais = new ByteArrayInputStream(xml.getBytes());
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            factory.setNamespaceAware(false);
            DocumentBuilder builder = factory.newDocumentBuilder();
            Document xmlDoc = builder.parse(bais);

            Node root = xmlDoc.getDocumentElement();

            XPathFactory xFactory = XPathFactory.newInstance();
            XPath xPath = xFactory.newXPath();

            XPathExpression xExpress = xPath.compile("/root/note");
            NodeList nodes = (NodeList) xExpress.evaluate(root, XPathConstants.NODESET);

            System.out.println("Found " + nodes.getLength() + " note nodes");

            for (int index = 0; index < nodes.getLength(); index++) {
                Node node = nodes.item(index);
                Document childDoc = builder.newDocument();
                childDoc.adoptNode(node);
                childDoc.appendChild(node);
                System.out.println(toString(childDoc));
            }

        } catch (Exception exp) {
            exp.printStackTrace();
        } finally {
            try {
                bais.close();
            } catch (Exception e) {
            }
        }
    }

    public static String toString(Document doc) {

        String sValue = null;

        ByteArrayOutputStream baos = null;
        OutputStreamWriter osw = null;

        try {
            baos = new ByteArrayOutputStream();
            osw = new OutputStreamWriter(baos);

            Transformer tf = TransformerFactory.newInstance().newTransformer();
            tf.setOutputProperty(OutputKeys.INDENT, "yes");
            tf.setOutputProperty(OutputKeys.METHOD, "xml");
            tf.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "4");

            DOMSource domSource = new DOMSource(doc);
            StreamResult sr = new StreamResult(osw);
            tf.transform(domSource, sr);

            osw.flush();
            baos.flush();
            sValue = new String(baos.toByteArray());
        } catch (Exception exp) {
            exp.printStackTrace();
        } finally {
            try {
                osw.close();
            } catch (Exception exp) {
            }
            try {
                baos.close();
            } catch (Exception exp) {
            }
        }
        return sValue;
    }
}

This now outputs...

Found 3 note nodes
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<note>
    <note_id>32219</note_id>
    <the_date>1336763490</the_date>
    <member_id>108649</member_id>
    <area>6</area>
    <note>Note 123123123</note>
</note>

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<note>
    <note_id>33734</note_id>
    <the_date>1339003652</the_date>
    <member_id>108649</member_id>
    <area>1</area>
    <note>This is another note.</note>
</note>

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<note>
    <note_id>49617</note_id>
    <the_date>1343050791</the_date>
    <member_id>108649</member_id>
    <area>1</area>
    <note>this is a 3rd note.</note>
</note>

I found this which seems to be very close: http://stackoverflow.com/a/6534233/1778465 — Get Off My Lawn, Jan 21 '13 at 22:55

Aubin · Answer 2 · 2013-01-21T22:42:43.247

Using XPath, the following code :

public class NotesExtractor {
   public static List< String > getTextOf( Document doc, String tagName )
      throws Exception
   {
      List< String > notes  = new ArrayList<>();
      XPathFactory xPathFactory = XPathFactory.newInstance();
      XPath xPath = xPathFactory.newXPath();
      NodeList xText =
         (NodeList)xPath.evaluate(
            "//" + tagName + "/text()", doc, XPathConstants.NODESET );
      for( int i = 0; i < xText.getLength(); ++i ) {
         Text textElt = (Text)xText.item( i );
         String noteTxt = textElt.getTextContent().trim();
         if( ! noteTxt.isEmpty())
         {
            notes.add( noteTxt.trim());
         }
      }
      return notes;
   }

   public static void main( String[] args ) throws Exception {
      DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
      dbf.setIgnoringElementContentWhitespace( true );
      DocumentBuilder db = dbf.newDocumentBuilder();
      Document doc = db.parse( "Notes.xml" );
      System.out.println( getTextOf( doc, "note" ));
   }

outputs:

[Note 123123123, This is another note., this is a 3rd note.]

Kind of, I would like a xml string back though. – Get Off My Lawn Jan 21 '13 at 22:29 — Get Off My Lawn, Jan 21 '13 at 22:29

XML get all nodes with the same name

2 Answers2

Linked