Java & xml学习笔记 SAX篇

Java & XML学习笔记
1、需要软件
java,解析器(例如Xerces),API(例如SAX,DOM)
2、SAX机制
1)解析
String xmlURI = "c:/test.xml";
String vendorParserClass = "org.apache.xerces.parsers.SAXParser";
XMLReaer reader = XMLReaderFactory.createXMLReader(vendorParserClass);

InputSource inputSource = new InputSource(xmlURI);
reader.parse(inputSource);

这样一个xml文档解析过程就完成了。因为SAX是采用时间处理机制来解析XML
文档的，在解析过程中会触发一些事件，也就是执行特定的方法，你可以实现
这些方法，就可以通过解析xml来做一些事情了
2)处理
SAX2.0定义的核心处理接口一共有
org.xml.sax.ContentHandler
org.xml.sax.ErrorHandler
org.xml.sax.DTDHandler
org.xml.sax.EntityResolver
这些接口是通过
org.xml.sax.XMLReader的setContentHandler(),setEroorHandler(),
setDTDHandler(),setEntityHandler()注册到解析器，这里面最重要的是
org.xml.sax.ContentHandler接口，它具体如下
public interface ContentHandler{
public void setDocumentLocator(Locator locator);
public void startDocument() throws SAXException;
public void endDocument() throws SAXException;
public void startPrefixMapping(String prefix,String uri)
throws SAXException;
public void endPrefixMapping(String prifix)
throws SAXException;
public void startElement(String namespaceURI,String localName,
String qName,Attributes atts) throws SAXException;
public void endElement(String namespaceURI,String localName,
String qName) throws SAXException;
public void characters(char ch[],int start,int length)
throws SAXException;
public void ignorableWhitespace(char ch[],int start,int length)
throws SAXException;
public void processingInstruction(String target,String data)
throws SAXException;
public void skippedEntity(String name)
throws SAXException;
}
通过setContentHandler()将你实现的ContentHandler注册给XMLReader之后，
在解析过程中，系统根据各种条件执行接口中的方法，下面简单说明一下
1)文档定位器
private Locator locator;

public void setDocumentLocator(Locator locator){
this.locator = locator;
}

通常情况下，你只要如此实现就可以了，这个主要是得到当前解析的位置，
通过得到的locator，你可以使用它的getLineNumber(),getColumnName()等
方法，可以得到文档当前的位置，但要注意的是，这个locator不能保存，只
针对当前的解析有效
2)文档的开头和结尾
public void startDocument() throws SAXException{
//解析过程中仅位于setDocumentLocator()方法后调用
}
public void endDocument() throws SAXException{
//解析过程中最后调用
}

大多数情况下你可以不用理他们，只要写个空方法就可以了
3)名字空间的开始和结束
public void startPrefixMapping(String prefix,String uri)
throws SAXException{
}
public void endPrefixMapping(String prifix)
throws SAXException{
}
4)元素的开始和结束
public void startElement(String namespaceURI,String localName,
String qName,Attributes atts) throws SAXException{
}
public void endElement(String namespaceURI,String localName,
String qName) throws SAXException{
}
5)元素的数据
public void characters(char ch[],int start,int length)
throws SAXException{
String s = new String(ch,start,length);
}
这个是得到当前的元素的文本数据
6)可以忽略的空白
public void ignorableWhitespace(char ch[],int start,int length)
throws SAXException{
}
7)实体
public void skippedEntity(String name)
throws SAXException{
}
8)指令处理
public void processingInstruction(String target,String data)
throws SAXException{
}
3)例子：这个是从Java & XML 中复制过来的，
/*
* Created on 2004-11-30
*
* TODO To change the template for this generated file go to
* Window - Preferences - Java - Code Style - Code Templates
*/
package javaxml2;

/**
* @author yuangfang
*
* TODO To change the template for this generated type comment go to
* Window - Preferences - Java - Code Style - Code Templates
*/

import java.io.*;
import java.util.*;
import org.xml.sax.*;
import org.xml.sax.ext.LexicalHandler;
import org.xml.sax.helpers.XMLReaderFactory;

import java.awt.*;
import javax.swing.*;
import javax.swing.tree.*;

public class SAXTreeViewer extends JFrame{

private String vendorParserClass = "org.apache.xerces.parsers.SAXParser";

private JTree jTree;
DefaultTreeModel defaultTreeModel;

public SAXTreeViewer(){
super("SAX Tree Viewer");
setSize(600,450);
}

public void init(String xmlURI) throws IOException,SAXException{
DefaultMutableTreeNode base = new DefaultMutableTreeNode("XML Document:" + xmlURI);
defaultTreeModel = new DefaultTreeModel(base);
jTree = new JTree(defaultTreeModel);

buildTree(defaultTreeModel,base,xmlURI);
getContentPane().add(new JScrollPane(jTree),BorderLayout.CENTER);

}

public void buildTree(DefaultTreeModel treeModel,DefaultMutableTreeNode base,String xmlURI)
throws IOException,SAXException{

String featureURI = "";
try{
XMLReader reader = XMLReaderFactory.createXMLReader(vendorParserClass);

ContentHandler jTreeContentHandler = new JTreeContentHandler(treeModel,base);
ErrorHandler jTreeErrorHandler = new JTreeErrorHandler();

reader.setContentHandler(jTreeContentHandler);
reader.setErrorHandler(jTreeErrorHandler);
reader.setEntityResolver(new SimpleEntityResolver());

featureURI = "http://xml.org/sax/features/validation";
reader.setFeature(featureURI,true);

featureURI = "http://xml.org/sax/features/namespaces";
setNamespaceProcessing(reader,true);

featureURI = "http://xml.org/sax/features/string-interning";
reader.setFeature(featureURI,true);

featureURI = "http://apache.org/xml/features/validation/schema";
reader.setFeature(featureURI,false);

InputSource inputSource = new InputSource(xmlURI);
reader.parse(inputSource);
}
catch(SAXNotRecognizedException e){
System.out.println("The parse class " + vendorParserClass
+ " does not recognize the feature URI " + featureURI);
System.exit(0);
}
catch(SAXNotSupportedException e){
System.out.println("The parser class " + vendorParserClass +
" does not support the feature URI " + featureURI);
}
}

private void setNamespaceProcessing(XMLReader reader,boolean state)
throws SAXNotSupportedException,SAXNotRecognizedException
{
reader.setFeature("http://xml.org/sax/features/namespaces",state);
reader.setFeature("http://xml.org/sax/features/namespace-prefixes",!state);
}
public static void main(String[] args) {
try{
if(args.length != 1){
System.out.println("Usage:Java javaxml2.SAXTreeViewer " + "[XML Document URI]");
System.exit(0);
}
SAXTreeViewer viewer = new SAXTreeViewer();
viewer.init(args[0]);
viewer.setVisible(true);
}catch(Exception e)
{
e.printStackTrace();
}
}
}

class JTreeContentHandler implements ContentHandler,LexicalHandler{
private DefaultTreeModel treeModel;

private DefaultMutableTreeNode current;

private Locator locator;

private Map namespaceMappings;

/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#comment(char[], int, int)
*/
public void comment(char[] ch, int start, int length) throws SAXException {
// TODO Auto-generated method stub

}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#endCDATA()
*/
public void endCDATA() throws SAXException {
// TODO Auto-generated method stub

}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#endDTD()
*/
public void endDTD() throws SAXException {
// TODO Auto-generated method stub

}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#endEntity(java.lang.String)
*/
public void endEntity(String name) throws SAXException {
// TODO Auto-generated method stub
current = (DefaultMutableTreeNode)current.getParent();
}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#startCDATA()
*/
public void startCDATA() throws SAXException {
// TODO Auto-generated method stub

}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#startDTD(java.lang.String, java.lang.String, java.lang.String)
*/
public void startDTD(String name, String publicId, String systemId)
throws SAXException {
// TODO Auto-generated method stub
System.out.println("start DTD");
DefaultMutableTreeNode dtdReference = new DefaultMutableTreeNode("DTD for ''" + name + "''");
if(publicId != null)
{
DefaultMutableTreeNode publicIDNode = new DefaultMutableTreeNode("Public ID: " + publicId + "''");
dtdReference.add(publicIDNode);
}
if(systemId != null)
{
DefaultMutableTreeNode systemIDNode = new DefaultMutableTreeNode("System ID: " + systemId + "''");
dtdReference.add(systemIDNode);
}
current.add(dtdReference);
}
/* (non-Javadoc)
* @see org.xml.sax.ext.LexicalHandler#startEntity(java.lang.String)
*/
public void startEntity(String name) throws SAXException {
// TODO Auto-generated method stub
DefaultMutableTreeNode entity = new DefaultMutableTreeNode("Entity: ''" + name + "''");
current.add(entity);
current = entity;
}
public JTreeContentHandler(DefaultTreeModel treeModel,DefaultMutableTreeNode base)
{
this.treeModel = treeModel;
this.current = base;
this.namespaceMappings = new HashMap();
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#setDocumentLocator(org.xml.sax.Locator)
*/
public void setDocumentLocator(Locator locator) {
// TODO Auto-generated method stub
this.locator = locator;

}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#startDocument()
*/
public void startDocument() throws SAXException {
// TODO Auto-generated method stub
System.out.println("start document");
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#endDocument()
*/
public void endDocument() throws SAXException {
// TODO Auto-generated method stub
System.out.println("end document");
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#startPrefixMapping(java.lang.String, java.lang.String)
*/
public void startPrefixMapping(String prefix, String uri) throws SAXException {
// TODO Auto-generated method stub
namespaceMappings.put(uri,prefix);
System.out.println("start PrefixMapping " + prefix);
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#endPrefixMapping(java.lang.String)
*/
public void endPrefixMapping(String prefix) throws SAXException {
// TODO Auto-generated method stub
for(Iterator i = namespaceMappings.keySet().iterator();i.hasNext();)
{
String uri = (String) i.next();
String thisPrefix = (String)namespaceMappings.get(uri);
if(prefix.equals(thisPrefix)){
namespaceMappings.remove(uri);
break;
}
}
System.out.println("end PrefixMapping " + prefix);
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#startElement(java.lang.String, java.lang.String, java.lang.String, org.xml.sax.Attributes)
*/
public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
// TODO Auto-generated method stub
DefaultMutableTreeNode element = new DefaultMutableTreeNode("Element: " + localName + " at line " + locator.getLineNumber());
current.add(element);
current = element;

if(uri.length() > 0)
{
String prefix = (String)namespaceMappings.get(uri);
if(prefix.equals("")){
prefix = "[None]";
}
DefaultMutableTreeNode namespace = new DefaultMutableTreeNode("Namespace: prefix = ''" +
prefix + "'',URI = ''" + uri + "''");
current.add(namespace);
}

for(int i = 0;i<atts.getLength();i++)
{
DefaultMutableTreeNode attribute = new DefaultMutableTreeNode("Attribute (name = ''" +
atts.getLocalName(i) + "'',value = ''" + atts.getValue(i) + "'')");
String attURI = atts.getURI(i);
if(attURI.length() > 0)
{
String attPrefix = (String)namespaceMappings.get(attURI);
if(attPrefix.equals("")){
attPrefix = "[None]";
}
DefaultMutableTreeNode attNamespace = new DefaultMutableTreeNode("Namespace: prefix = ''" +
attPrefix + "'',URI = ''" + attURI + "''");
attribute.add(attNamespace);
}
current.add(attribute);
}
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#endElement(java.lang.String, java.lang.String, java.lang.String)
*/
public void endElement(String uri, String localName, String qName) throws SAXException {
// TODO Auto-generated method stub
current = (DefaultMutableTreeNode)current.getParent();
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#characters(char[], int, int)
*/
public void characters(char[] ch, int start, int length) throws SAXException {
// TODO Auto-generated method stub
String s = new String(ch,start,length);
DefaultMutableTreeNode data = new DefaultMutableTreeNode("Character Data: ''" + s + "''");
current.add(data);
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#ignorableWhitespace(char[], int, int)
*/
public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
// TODO Auto-generated method stub

}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#processingInstruction(java.lang.String, java.lang.String)
*/
public void processingInstruction(String target, String data) throws SAXException {
// TODO Auto-generated method stub
DefaultMutableTreeNode pi = new DefaultMutableTreeNode("PI (target = ''"
+ target + "'', data = ''" + data + "'')");
current.add(pi);
}

/* (non-Javadoc)
* @see org.xml.sax.ContentHandler#skippedEntity(java.lang.String)
*/
public void skippedEntity(String name) throws SAXException {
// TODO Auto-generated method stub
DefaultMutableTreeNode skipped = new DefaultMutableTreeNode("Skipped Entity: ''" + name + "''");
current.add(skipped);
}
}

class JTreeErrorHandler implements ErrorHandler{

/* (non-Javadoc)
* @see org.xml.sax.ErrorHandler#warning(org.xml.sax.SAXParseException)
*/
public void warning(SAXParseException exception) throws SAXException {
// TODO Auto-generated method stub
System.out.println("**Parsing Warning**\n" +
" Line: " +
exception.getLineNumber() + "\n" +
" URI: " +
exception.getSystemId() + "\n" +
" Message:" +
exception.getMessage());
throw new SAXException("Warning encountered");
}

/* (non-Javadoc)
* @see org.xml.sax.ErrorHandler#error(org.xml.sax.SAXParseException)
*/
public void error(SAXParseException exception) throws SAXException {
// TODO Auto-generated method stub
System.out.println("**Parsing Error**\n" +
" Line: " +
exception.getLineNumber() + "\n" +
" URI: " +
exception.getSystemId() + "\n" +
" Message:" +
exception.getMessage());
throw new SAXException("Error encounted");
}

/* (non-Javadoc)
* @see org.xml.sax.ErrorHandler#fatalError(org.xml.sax.SAXParseException)
*/
public void fatalError(SAXParseException exception) throws SAXException {
// TODO Auto-generated method stub
System.out.println("**Parsing Fatal Error**\n" +
" Line: " +
exception.getLineNumber() + "\n" +
" URI: " +
exception.getSystemId() + "\n" +
" Message:" +
exception.getMessage());
throw new SAXException("Fatal Error encounted");
}

}
xml文件如下：你可以不用这个xml，用别的xml文件也可以
<?xml version="1.0"?>
<!DOCTYPE book SYSTEM "DTD/JavaXML.dtd">
<!-- Java and XML Contents -->
<book xmlns="http://www.oreilly.com/javaxml2" xmlns:ora="http://www.oreilly.com" >
<title ora:series="Java">Java and XML</title>
<!-- Chapter List -->
<contents>
<chapter title="Introduction" number="1">
<topic name="XML Matters"/>
<topic name="What''s Important"/>
<topic name="The Essentials"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Nuts and Bolts" number="2">
<topic name="The Basics"/>
<topic name="Constraints"/>
<topic name="Transformations"/>
<topic name="And More..."/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="SAX" number="3">
<topic name="Getting Prepared"/>
<topic name="SAX Readers"/>
<topic name="Content Handlers"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Advanced SAX" number="4">
<topic name="Properties and Features"/>
<topic name="More Handlers"/>
<topic name="Filters and Writers"/>
<topic name="Even More Handlers"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="DOM" number="5">
<topic name="The Document Object Model"/>
<topic name="Serialization"/>
<topic name="Mutability"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Advanced DOM" number="6">
<topic name="DOM and Mutation"/>
<topic name="Namespaces and DOM Level 2"/>
<topic name="DOM and HTML"/>
<topic name="DOM Level 3"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="JDOM" number="7">
<topic name="The Basics"/>
<topic name="PropsToXML"/>
<topic name="XMLProperties"/>
<topic name="Is JDOM a Standard?"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Advanced JDOM" number="8">
<topic name="The Whole Ball of Wax"/>
<topic name="JDOM and Factories"/>
<topic name="Wrappers and Decorators"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="JAXP" number="9">
<topic name="API or Abstraction?"/>
<topic name="JAXP 1.0"/>
<topic name="JAXP 1.1"/>
<topic name="Gotcha!"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Web Publishing Frameworks" number="10">
<topic name="Selecting a Framework"/>
<topic name="Installation"/>
<topic name="Using a Publishing Framework"/>
<topic name="XSP"/>
<topic name="Cocoon 2.0 and Beyond"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="XML-RPC" number="11">
<topic name="RPC Versus RMI"/>
<topic name="Saying Hello"/>
<topic name="The Real World"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="SOAP" number="12">
<topic name="Starting Out"/>
<topic name="Setting Up"/>
<topic name="Getting Dirty"/>
<topic name="Going Further"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Web Services" number="13">
<topic name="Web Services"/>
<topic name="UDDI"/>
<topic name="WSDL"/>
<topic name="Putting It All Together"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Content Syndication" number="14">
<topic name="The Foobar Public Library"/>
<topic name="mytechbooks.comI"/>
<topic name="Push Versus Pull"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="XML Data Binding" number="15">
<topic name="First Principles"/>
<topic name="Castor"/>
<topic name="Zeus"/>
<topic name="JAXB"/>
<topic name="What&apos;s Next?"/>
</chapter>
<chapter title="Looking Forward" number="16">
<topic name="XLink"/>
<topic name="XPointer"/>
<topic name="XML Schema Bindings"/>
<topic name="And the Rest..."/>
<topic name="What&apos;s Next?"/>
</chapter>
</contents>
<ora:copyright>&OReillyCopyright;</ora:copyright>
</book>

原文转自：http://www.ltesting.net