There are nine additional interfaces that we will not examine in low-level detail but will be required for many applications. The first four have to do with actual content:
CharacterData TheCharacterData interface extends Node. No DOM objects of type CharacterData exist but rather this object represents common methods inherited by other DOM interfaces. The CharacterData interface contains eight methods for setting, getting, inserting, appending, and otherwise manipulating normal character data information.
Comment The Commentinterface extends CharacterData and represents a comment in an XML document. No additional methods are defined on this interface.
Text The Textinterface extends CharacterData. The Text interface contains a single method splitText(int offset) that allows the given text node to be split at an offset into two text nodes which may later be recombined with normalize();.
CDATASection TheCDATASection interface extends Text and allows for blocks of text to be contained within a DOM node that would otherwise be considered markup without the need to escape markup characters. No additional methods are defined in this interface.
The next five interfaces represent other elements in XML.
Entity ExtendsNode. Represents the Entities within an XML document. Depending on validation, these entities may or may not be expanded and the object may (not expanded, non-validating parsers) or may not (expanded) have children. Defines three methods for accessing entity information.
Notation ExtendsNode. Represents the Notation elements of an XML document. Defines two methods for accessing information about a Notation.
DocumentType Extends Node. The DocumentType interface is used to gather information about the Document itself and has three methods for accessing Entities, Notations, and the name of the DTD itself.
ProcessingInstruction Extends Node. The ProcessingInstruction interface represents processing instruction information. This interface specifies three methods for accessing and manipulating processing instruction information.
DocumentFragmentExtends Node. Contains no additional methods beyond the Node interface. The DocumentFragment interface is designed to allow users and developers to develop XML documents that are not well formed. A document fragment can be built that represents data at any level in an XML tree. After being inserted back into a Document object, the underlying children are inserted and not the DocumentFragment object itself. For these reasons, DocumentFragments can be thought of as lightweightDocuments.
Listing 3.7, DumpXMLOracle.java, uses the Oracle DOM and wraps up all of the DOM Core Level I interfaces into one neat package that displays, in semi human-readable format, any given XML document. The output is shown in Listing 3.8.
Code Listing 3.7. DumpXMLOracle.java
1: /*
2: * @(#)DumpXMLOracle.java 1.0 99/05/28
3: *
4: * Copyright (c) 1999 Sams Publishing. All Rights Reserved.
5: *
6: */
7: package sams.chp3;
8:
9: import java.io.*;
10: import java.net.*;
11:
12: import oracle.xml.parser.XMLParser;
13:
14: import org.w3c.dom.*;
15:
16: public class DumpXMLOracle
17: {
18: // map the type to a string
19: static String mapNodeTypeToString(short nodeType)
20: {
21: switch(nodeType)
22: {
23: case org.w3c.dom.Node.ATTRIBUTE_NODE: return "ATTRIBUTE_NODE";
24: case org.w3c.dom.Node.CDATA_SECTION_NODE:return "CDATA_SECTION_NODE";
25: case org.w3c.dom.Node.COMMENT_NODE: return "COMMENT_NODE";
26: case org.w3c.dom.Node.DOCUMENT_FRAGMENT_NODE: return
"DOCUMENT_FRAGMENT_NODE";
27: case org.w3c.dom.Node.DOCUMENT_NODE: return "DOCUMENT_NODE";
28: case org.w3c.dom.Node.DOCUMENT_TYPE_NODE: return "DOCUMENT_TYPE_NODE";
29: case org.w3c.dom.Node.ELEMENT_NODE: return "ELEMENT_NODE";
30: case org.w3c.dom.Node.ENTITY_NODE: return "ENTITY_NODE";
31: case org.w3c.dom.Node.ENTITY_REFERENCE_NODE: return "ENTITY_REFERENCE_NODE";
32: case org.w3c.dom.Node.NOTATION_NODE: return "NOTATION_NODE";
33: case org.w3c.dom.Node.PROCESSING_INSTRUCTION_NODE: return
"PROCESSING_INSTRUCTION_NODE";
34: case org.w3c.dom.Node.TEXT_NODE: return "TEXT_NODE";
35:
36: }
37: return "Unknown";
38: }
39:
40: // Display attribute information
41: static void displayAttributeInfo(String prefix, Node node)
42: {
43: // only elements have attributes
44: if (node.getNodeType() != org.w3c.dom.Node.ELEMENT_NODE) return;
45:
46: NamedNodeMap attributes = node.getAttributes();
47: if ( null == attributes || attributes.getLength() == 0)
48: {
49: return;
50: }
51:
52: System.out.println(prefix +"has " + attributes.getLength() + "
attributes");
53: System.out.println(prefix + attributes.toString());
54: for (int i = 0; i < attributes.getLength(); i++)
55: {
56: Node attribute = attributes.item(i);
57: System.out.print(prefix+"["+i+"] " + attribute.getNodeName());
58: System.out.println(" = " + attribute.getNodeValue());
59: }
60:
61: }
62:
63: // Display generalized node properties
64: static void displayNodeInfo(String prefix,Node node)
65: {
66: System.out.println(prefix+ "----------------");
67: System.out.println(prefix + "name:"+node.getNodeName());
68: System.out.println(prefix + "type:("+node.getNodeType()+ ")"
+mapNodeTypeToString(node.getNodeType()));
69: System.out.println(prefix + "value:"+ node.getNodeValue());
70: displayAttributeInfo(prefix,node);
71: if (node.getNodeType() != org.w3c.dom.Node.TEXT_NODE)
72: {
73: NodeList children = node.getChildNodes();
74: System.out.println(prefix + "Children("+ children.getLength()+"):");
75: if ( children.getLength() > 0)
76: {
77: System.out.print(prefix+ " ");
78: for (int i = 0; i < children.getLength(); i++)
79: {
80: Node child = children.item(i);
81: System.out.print(" ["+i+"] " + child.getNodeName());
82: }
83: System.out.println();
84: }
85:
86: }
87: }
88: // Display Entity Information
89: static void displayEntityInfo(String prefix, Entity entity)
90: {
91: System.out.println(prefix + "Entity information");
92: System.out.println(prefix + " public id:"+ entity.getPublicId());
93: System.out.println(prefix + " system id:"+ entity.getSystemId());
94: System.out.println(prefix + " notation name:"+ entity.getNotationName());
95: displayNodeInfo(prefix,entity);
96:
97: NodeList children = entity.getChildNodes();
98: if ( children.getLength() == 0)
99: System.out.println(prefix + " Has 0 children");
100: else
101: System.out.println(prefix + " Children(" + children.getLength()+ ")");
102:
103: for (int i = 0; i < children.getLength(); i++)
104: {
105: Node child = (Entity)children.item(i);
106: System.out.println(" child(" + i + ")");
107: displayNodeInfo(" ",child);
108: }
109:
110: }
111: // Display Document information
112: static void displayDocumentInfo(Document document)
113: {
114: DocumentType docTypeInfo = document.getDoctype();
115: System.out.println(" ");
116: System.out.println("Document Type Information");
117: System.out.println("----------------");
118: System.out.println("name:"+document.getNodeName());
119: System.out.println("type:("+document.getNodeType()+ ")" +mapNodeTypeToString
(document.getNodeType()));
120: System.out.println("value:"+ document.getNodeValue());
121: System.out.println(" Properties");
122: System.out.println(" Name Property:"+docTypeInfo.getName());
123: NamedNodeMap entities = docTypeInfo.getEntities();
124: System.out.println(" contains " + entities.getLength() + " entities");
125: NamedNodeMap notations = docTypeInfo.getNotations();
126: if ( notations != null)
127: System.out.println(" contains " + notations.getLength() +
" notations");
128: else
129: System.out.println(" contains (null) notations");
130:
131: if ( entities != null && entities.getLength() > 0)
132: {
133: System.out.println(" Entities");
134: for (int i = 0; i < entities.getLength(); i++)
135: {
136: //
137: // Note that in the SUN implementation this works as expected
138: // The IBM implementation causes a class cast exception.
139: try
140: {
141: Entity entity = (Entity)entities.item(i);
142: System.out.println(" Entity(" + i + ")");
143: displayEntityInfo(" ",entity);
144: }
145: catch (Exception e) { System.out.println("exception! "
+ e); } ;
146: }
147: }
148:
149: if ( notations != null && notations.getLength() > 0)
150: {
151: System.out.println(" Notations");
152: for (int i = 0; i < notations.getLength(); i++)
153: {
154: Node node = notations.item(i);
155: System.out.println(" Notation(" + i + ")");
156: displayNodeInfo(" ",node);
157: }
158: }
159:
160:
161: }
162:
163: // Process all the children of a node.
164: public static void displayChildren(String prefix,Node parent)
165: {
166: NodeList children = parent.getChildNodes();
167: if ( children == null || children.getLength() == 0) return;
168: for (int i = 0; i < children.getLength(); i++)
169: {
170: try
171: {
172: Node node = children.item(i);
173: displayNodeInfo(prefix,node);
174: displayChildren(prefix + " ",node);
175: }
176: catch (Exception e)
177: {
178: }
179: }
180:
181:
182: }
183:
184:
185: public static void main (String argv [])
186: {
187: if (argv.length != 1)
188: {
189:
190: System.err.println( "Usage: java sams.chp3.DumpXMLOracle filename");
191: System.exit(1);
192: }
193:
194: try
195: {
196: XMLParser parser = new XMLParser();
197: FileInputStream inStream = new FileInputStream(argv[0]);
198: parser.setErrorStream(System.err);
199: parser.setValidationMode(true);
200: parser.showWarnings(true);
201:
202: parser.parse(inStream);
203:
204: Document document = parser.getDocument();
205: System.out.println("Sucessfully created document on " +
argv[0]);
206:
207: //
208: // Print relevent info about the document type
209: //
210: displayDocumentInfo(document);
211: displayNodeInfo("",document);
212:
213: //
214: // Now walk the document itself displaying data
215: //
216: displayChildren(" ",document);
217: }
218: catch (Exception e)
219: {
220: System.out.println("Unexpected exception reading document!" +e);
221: System.out.println(e);
222: System.exit (0);
223: }
224:
225:
226: }
Code Listing 3.8. Abbreviated Output of DumpXMLOracle.java
1: C:java sams.chp3.DumpXMLOracle
2: Sucessfully created document on catalog.xml
3:
4: Document Type Information
5: ----------------
6: name:#document
7: type:(9)DOCUMENT_NODE
8: value:null
9: Properties
10: Name Property:catalog
11: contains 2 entities
12: contains (null) notations
13: Entities
14: Entity(0)
15: Entity information
16: public id:null
17: system id:null
18: notation name:null
19: ----------------
20: name:PublisherInfo
21: type:(6)ENTITY_NODE
22: value:MCP
23: Children(0):
24: Has 0 children
25: Entity(1)
26: Entity information
27: public id:null
28: system id:null
29: notation name:null
30: ----------------
31: name:AuthorName
32: type:(6)ENTITY_NODE
33: value:Albert J. Saganich Jr
34: Children(0):
35: Has 0 children
36: ----------------
37: name:#document
38: type:(9)DOCUMENT_NODE
39: value:null
40: Children(4):
41: [0] xml [1] #comment [2] catalog [3] catalog
42: ----------------
43: name:xml
44: type:(7)PROCESSING_INSTRUCTION_NODE
45: value: version = '1.0'encoding = 'UTF-8'
46: Children(0):
47: ----------------
48: name:#comment
49: type:(8)COMMENT_NODE
50: value:
51:
52: A Simple catalog of books a bookstore might carry
53:
54: Al Saganich for Macmillan Computer Publishing
55:
56: Children(0):
57: ----------------
58: name:catalog
59: type:(10)DOCUMENT_TYPE_NODE
60: value:null
61: Children(0):
62: ----------------
63: name:catalog
64: type:(1)ELEMENT_NODE
65: value:null
66: Children(7):
67: [0] #comment [1] catheader [2] entry [3] entry [4] entry [5] entry [6]
cattrailer
68: ----------------
69: name:#comment
70: type:(8)COMMENT_NODE
71: value:
72:
73: This is a comment.
74:
75: It follows after <catalog> entry
76:
77: Children(0):
78: ----------------
79: name:catheader
80: type:(1)ELEMENT_NODE
81: value:null
82: Children(1):
83: [0] #text
84: ----------------
85: name:#text
86: type:(3)TEXT_NODE
87: value:This is the catalog header only one instance of this guy
88: ----------------
89: . . .
90: name:entry
91: type:(1)ELEMENT_NODE
92: value:null
93: Children(7):
94: [0] title [1] author [2] author [3] publisher [4] price [5] price [6] isbn
95: ----------------
96: name:title
97: type:(1)ELEMENT_NODE
98: value:null
99: Children(1):
100: [0] #text
101: ----------------
102: name:#text
103: type:(3)TEXT_NODE
104: value:Special Edition:Using XML and Java 2.0
105: ----------------
106: name:author
107: type:(1)ELEMENT_NODE
108: value:null
109: Children(1):
110: [0] #text
111: ----------------
112: name:#text
113: type:(3)TEXT_NODE
114: value:Al Saganich
115: ----------------
116: name:author
117: type:(1)ELEMENT_NODE
118: value:null
119: Children(1):
120: [0] #text
121: ----------------
122: name:#text
123: type:(3)TEXT_NODE
124: value:Mike Daconta
125: ----------------
126: name:publisher
127: type:(1)ELEMENT_NODE
128: value:null
129: Children(1):
130: [0] #text
131: ----------------
132: name:#text
133: type:(3)TEXT_NODE
134: value:Sams Publishing
135: ----------------
136: name:price
137: type:(1)ELEMENT_NODE
138: value:null
139: has 2 attributes
140: [oracle.xml.parser.XMLAttr@29be915b, oracle.xml.parser. XMLAttr@2b06915b]
141: [0] discount = retail
142: [1] cur = us
143: Children(1):
144: [0] #text
145: ----------------
146: name:#text
147: type:(3)TEXT_NODE
148: value:9.95
149: ----------------
150: name:price
151: type:(1)ELEMENT_NODE
152: value:null
153: has 2 attributes
154: [oracle.xml.parser.XMLAttr@28ae915b, oracle.xml.parser.
XMLAttr@2872915b]
155: [0] discount = wholesale
156: [1] cur = us
157: Children(1):
158: [0] #text
159: ----------------
160: name:#text
161: type:(3)TEXT_NODE
162: value:7.95
163: ----------------
164: name:isbn
165: type:(1)ELEMENT_NODE
166: value:null
167: Children(1):
168: [0] #text
169: ----------------
170: name:#text
171: type:(3)TEXT_NODE
172: value:0101010124
173: ----------------
174: . . .
175: name:entry
176: type:(1)ELEMENT_NODE
177: value:null
178: Children(6):
179: [0] title [1] author [2] publisher [3] price [4] price [5] isbn
180: . . .
181: ----------------
182: name:cattrailer
183: type:(1)ELEMENT_NODE
184: value:null
185: Children(1):
186: [0] #text
187: ----------------
188: name:#text
189: type:(3)TEXT_NODE
190: value:This is the catalog trailer only one instance of this guy as well
"DOCUMENT_FRAGMENT_NODE";
27: case org.w3c.dom.Node.DOCUMENT_NODE: return "DOCUMENT_NODE";
28: case org.w3c.dom.Node.DOCUMENT_TYPE_NODE: return "DOCUMENT_TYPE_NODE";
29: case org.w3c.dom.Node.ELEMENT_NODE: return "ELEMENT_NODE";
30: case org.w3c.dom.Node.ENTITY_NODE: return "ENTITY_NODE";
31: case org.w3c.dom.Node.ENTITY_REFERENCE_NODE: return "ENTITY_REFERENCE_NODE";
32: case org.w3c.dom.Node.NOTATION_NODE: return "NOTATION_NODE";
33: case org.w3c.dom.Node.PROCESSING_INSTRUCTION_NODE: return