|
Document Object Model (DOM)
Part:
1
2
3
(Continued from previous part...)
The following program illustrates how an XML file can be parse into a DOM
document tree, and how the get methods of Node can be used
to browse the tree:
/**
* DOMBrowser.java
* Copyright (c) 2002 by Dr. Herong Yang
*/
import java.io.*;
import javax.xml.parsers.*;
import org.w3c.dom.*;
import org.xml.sax.*;
class DOMBrowser {
public static void main(String[] args) {
try {
File x = new File(args[0]);
DocumentBuilderFactory f = DocumentBuilderFactory.newInstance();
DocumentBuilder b = f.newDocumentBuilder();
Document d = b.parse(x);
printNode(d, "");
} catch (ParserConfigurationException e) {
System.out.println(e.toString());
} catch (SAXException e) {
System.out.println(e.toString());
} catch (IOException e) {
System.out.println(e.toString());
}
}
static void printNode(Node n, String p) {
NodeList l = n.getChildNodes();
NamedNodeMap m = n.getAttributes();
int ml = -1;
if (m!=null) ml = m.getLength();
System.out.println(p+n.getNodeName()+": "+n.getNodeType()+", "
+l.getLength()+", "+ml+", "+n.getNodeValue());
for (int i=0; i<ml; i++) {
Node c = m.item(i);
printNode(c,p+" |-");
}
for (int i=0; i<l.getLength(); i++) {
Node c = l.item(i);
printNode(c,p+" ");
}
}
}
Now let's use this program to browse my first XML file, hello.xml:
<?xml version="1.0"?>
<body>Hello world!</body>
you will get the following output:
#document: 9, 1, -1, null
body: 1, 1, 0, null
#text: 3, 0, -1, Hello world!
Here is how to read the output:
- The Document object is also a Node object, which is presented by the
first line in the output.
- The "xml" processing instruction is not part of the document object.
- The second line in the output says that the root element is named as
"body", of type 1, has 1 child node, has 0 attribute, and has no value.
- The third line in the output says that there is child node nested
inside the "body" node. The child node is called "#text", of type 3,
has 0 child node, could not have any attribute, and has a value of string
"Hello world!".
- Note that the text enclosed by the "body" tags is parsed into
a node separated from the "body" node. So how can we link that text with
the tag name "body"?
Here is another XML file with more elements, user.xml:
<?xml version="1.0"?>
<user status="active">
<!-- This is not a real user. -->
<first_name>John</first_name>
<last_name>Smith</last_name>
</user>
Run DOMBrowser with this XML file, you will get:
#document: 9, 1, -1, null
user: 1, 7, 1, null
|-status: 2, 0, -1, active
#text: 3, 0, -1,
#comment: 8, 0, -1, This is not a real user.
#text: 3, 0, -1,
first_name: 1, 1, 0, null
#text: 3, 0, -1, John
#text: 3, 0, -1,
last_name: 1, 1, 0, null
#text: 3, 0, -1, Smith
#text: 3, 0, -1,
The output is more interesting:
- Line breaks are also parsed into "#text" nodes. This is why node "user"
has 7 child nodes: 4 line breaks, 1 comment, and 2 elements: "first_name"
and "last_name".
- For a node that represents an attribute of element, the node value is
the attribute value. See node "status" under "user".
Building a New DOM Document
DOM documents can also be created from scratch instead of parsed from an XML file.
This can be easily done by using the following methods:
- DocumentBuilder.newDocument(): Create an empty DOM document.
- Document.createElement(): Create a new Element.
- Document.createTextNode(): Create a new TextNode.
- Node.appendChild(): Insert a sub Node into the current Node.
- Element.setAttribute(): Add new attribute into an element.
The following program shows how to create a simple DOM document with these methods:
/**
* DOMNewDoc.java
* Copyright (c) 2002 by Dr. Herong Yang
*/
import java.io.*;
import javax.xml.parsers.*;
import org.w3c.dom.*;
class DOMNewDoc {
public static void main(String[] args) {
try {
DocumentBuilderFactory f = DocumentBuilderFactory.newInstance();
DocumentBuilder b = f.newDocumentBuilder();
Document d = b.newDocument();
Element r = d.createElement("dictionary");
d.appendChild(r);
Element w = d.createElement("word");
r.appendChild(w);
Element e = d.createElement("update");
w.appendChild(e);
e.setAttribute("date","2002-12-24");
e = d.createElement("name");
w.appendChild(e);
e.setAttribute("is_acronym","true");
e.appendChild(d.createTextNode("DTD"));
e = d.createElement("definition");
w.appendChild(e);
e.appendChild(d.createTextNode("Document Type Definition"));
printNode(d, "");
} catch (ParserConfigurationException e) {
System.out.println(e.toString());
}
}
static void printNode(Node n, String p) {
NodeList l = n.getChildNodes();
NamedNodeMap m = n.getAttributes();
int ml = -1;
if (m!=null) ml = m.getLength();
System.out.println(p+n.getNodeName()+": "+n.getNodeType()+", "
+l.getLength()+", "+ml+", "+n.getNodeValue());
for (int i=0; i<ml; i++) {
Node c = m.item(i);
printNode(c,p+" |-");
}
for (int i=0; i<l.getLength(); i++) {
Node c = l.item(i);
printNode(c,p+" ");
}
}
}
(Continued on next part...)
Part:
1
2
3
| 