[Java开发之路]（11）SAX解析XML文档
最后更新于：2022-04-01 09:59:48
### 1.简介
Dom解析功能强大，可增删改查，操作时会将XML文档读到内存，因此适用于小文档；
SAX解析是从头到尾逐行逐个元素解析，修改较为不便，但适用于只读的大文档；
SAX采用事件驱动的方式解析XML。套用网友的解释：如同在电影院看电影一样，从头到尾看一遍，不能回退（Dom可来来回回读取），在看电影的过程中，每遇到一个情节，都会调用大脑去接收处理这些信息。SAX也是相同的原理，每遇到一个元素节点，都会调用相应的方法来处理。在SAX的解析过程中，读取到文档开头、文档结尾，元素的开头和元素结尾都会调用相应方法，我们可以在这些方法中进行相应事件处理。
对应方法：
~~~
public void startDocument() throws SAXException {
}
public void endDocument() throws SAXException {
}
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
}
public void endElement(String uri, String localName, String qName) throws SAXException {
}
~~~
我们还需一个方法来处理元素节点中间的文本节点（我们常误以为元素节点的文本值）
~~~
public void characters(char[] ch, int start, int length) throws SAXException {
}
~~~
### 2.解析
解析步骤：
（1）通过SAXParserFactory的静态方法newInstance()方法获取SAXParserFactory实例对象factory
~~~
SAXParserFactory factory = SAXParserFactory.newInstance();
~~~
（2）通过SAXParserFactory实例的newSAXParser()方法返回SAXParser实例parser
~~~
SAXParser parser = factory.newSAXParser();
~~~
（3）创建一个类继承DefaultHandler,重写其中的一些方法进行业务处理
~~~
package com.qunar.handler;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class SAXParserHandler extends DefaultHandler{
// 用来标示解析开始
@Override
public void startDocument() throws SAXException {
}
// 用来标示解析结束
@Override
public void endDocument() throws SAXException {
}
// 用来遍历XML文件的开始标签
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
super.startElement(uri, localName, qName, attributes);
}
// 用来遍历XML文件的结束标签
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
super.endElement(uri, localName, qName);
}
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
super.characters(ch, start, length);
}
}
~~~
（4）创建Handler类对象实例
~~~
// 定义SAXParserHandler对象
SAXParserHandler handler = new SAXParserHandler();
~~~
（5）解析XML文档
~~~
<?xml version="1.0" encoding="utf-8"?><bookstore>
<book category="Java">
<title lang="chi">Java多线程编程核心技术</title>
<author>高洪岩</author>
<year>2015</year>
<price>69.00</price>
</book>
<book category="C++">
<title lang="en">Effective C++: 55 Specific Ways to Improve Your Programs and Designs</title>
<author>Scott Meyers</author>
<year>2006</year>
<price>58.00</price>
</book>
<book category="Web">
<title lang="en">Learning XML</title>
<author>Erik T. Ray</author>
<year>2016</year>
<price>39.95</price>
</book>
</bookstore>
~~~
### 3.具体实例：
~~~
package com.qunar.handler;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class SAXParserHandler extends DefaultHandler{
private int bookIndex = 0;
// 用来标示解析开始
@Override
public void startDocument() throws SAXException {
System.out.println("SAX解析开始...");
}
// 用来标示解析结束
@Override
public void endDocument() throws SAXException {
System.out.println("SAX解析结束...");
}
// 用来遍历XML文件的开始标签
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
// 调用DefaultHandler类的startElement方法
super.startElement(uri, localName, qName, attributes);
// 开始解析book元素节点
if(qName.equals("book")){
++ bookIndex;
System.out.println("开始解析第" + bookIndex + "本书...");
// 已知book元素节点下的属性名称，根据属性名称获取属性值
/*String value = attributes.getValue("category");
System.out.println("value->"+value);*/
// 不知道book元素节点下的属性名称以及个数
int size = attributes.getLength();
for(int i = 0;i < size;++i){
System.out.println(attributes.getQName(i) + "：" + attributes.getValue(i));
}//for
}//if
else if(!qName.equals("bookstore")){
System.out.print(qName + "：");
}//else
}
// 用来遍历XML文件的结束标签
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
super.endElement(uri, localName, qName);
// 判断一本书是否解析完
if(qName.equals("book")){
System.out.println("结束解析第" + bookIndex + "本书...");
}//if
}
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
super.characters(ch, start, length);
String text = new String(ch, start, length);
if(!text.trim().equals("")){
System.out.println(text);
}//if
}
}
~~~
~~~
package com.qunar.xml;
import java.io.IOException;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.SAXException;
import com.qunar.handler.SAXParserHandler;
/**
* SAX方式解析XML文档
* @author sjf0115
*
*/
public class SAXXMLCode {
public static void main(String[] args) {
String path = "D:\\bookstore.xml";
try {
// 通过SAXParserFactory的静态方法newInstance()方法获取SAXParserFactory实例对象factory
SAXParserFactory factory = SAXParserFactory.newInstance();
// 通过SAXParserFactory实例的newSAXParser()方法返回SAXParser实例parser
SAXParser saxParser = factory.newSAXParser();
// 定义SAXParserHandler对象
SAXParserHandler handler = new SAXParserHandler();
// 解析XML文档
saxParser.parse(path, handler);
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
~~~
**运行结果：**
<table cellspacing="0" cellpadding="0" style="border-collapse:collapse; border:1px solid rgb(187,187,187); width:1050px"><tbody><tr><td style="border-collapse:collapse; border:1px solid rgb(187,187,187); width:1049px"><br/><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">SAX解析开始...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第1本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：Java</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">title：Java多线程编程核心技术</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">author：高洪岩</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">year：2015</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">price：69.00</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第1本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第2本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：C++</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">title：Effective C++: 55 Specific Ways to Improve Your Programs and Designs</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">author：Scott Meyers</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">year：2006</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">price：58.00</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第2本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第3本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：Web</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">title：Learning XML</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">author：Erik T. Ray</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">year：2016</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">price：39.95</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第3本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">SAX解析结束...</span></div></td></tr></tbody></table>
### 4.解析并储存于对象中
~~~
package com.qunar.bean;
/**
* book实体类
* @author sjf0115
*
*/
public class Book {
private String category;
private String title;
private String author;
private String year;
private String price;
private String lang;
public String getCategory() {
return category;
}
public void setCategory(String category) {
this.category = category;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public String getAuthor() {
return author;
}
public void setAuthor(String author) {
this.author = author;
}
public String getYear() {
return year;
}
public void setYear(String year) {
this.year = year;
}
public String getPrice() {
return price;
}
public void setPrice(String price) {
this.price = price;
}
public String getLang() {
return lang;
}
public void setLang(String lang) {
this.lang = lang;
}
@Override
public String toString() {
return "category：" + category + " lang：" + lang + " title：" + title + " author：" + author + " year：" + year + " price：" + price;
}
}
~~~
~~~
package com.qunar.handler;
import java.util.ArrayList;
import java.util.List;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import com.qunar.bean.Book;
public class SAXParserHandler extends DefaultHandler{
private Book book;
private int bookIndex = 0;
// 节点文本内容
private String text;
private List<Book> bookList = new ArrayList<Book>();
public List<Book> getBookList() {
return bookList;
}
// 用来标示解析开始
@Override
public void startDocument() throws SAXException {
System.out.println("SAX解析开始...");
}
// 用来标示解析结束
@Override
public void endDocument() throws SAXException {
System.out.println("SAX解析结束...");
}
// 用来遍历XML文件的开始标签
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
// 调用DefaultHandler类的startElement方法
super.startElement(uri, localName, qName, attributes);
// 开始解析book元素节点
if(qName.equals("book")){
// 创建一个book对象
book = new Book();
++ bookIndex;
System.out.println("开始解析第" + bookIndex + "本书...");
int size = attributes.getLength();
for(int i = 0;i < size;++i){
String attr = attributes.getQName(i);
// 属性category
if(attr.equals("category")){
book.setCategory(attributes.getValue(i));
}//if
}//for
}//if
// 用于遍历title节点中的属性
else if(qName.equals("title")){
int size = attributes.getLength();
for(int i = 0;i < size;++i){
String attr = attributes.getQName(i);
// 属性category
if(attr.equals("lang")){
book.setLang(attributes.getValue(i));
}//if
}//for
}//else
}
// 用来遍历XML文件的结束标签
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
super.endElement(uri, localName, qName);
// 判断一本书是否解析完
if(qName.equals("book")){
bookList.add(book);
book = null;
System.out.println("结束解析第" + bookIndex + "本书...");
}//if
else if(qName.equals("title")){
book.setTitle(text);
}//else
else if(qName.equals("author")){
book.setAuthor(text);
}//else
else if(qName.equals("year")){
book.setYear(text);
}//else
else if(qName.equals("price")){
book.setPrice(text);
}//else
}
// 文本值
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
super.characters(ch, start, length);
text = new String(ch, start, length);
}
}
~~~
~~~
package com.qunar.xml;
import java.io.IOException;
import java.util.List;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.SAXException;
import com.qunar.bean.Book;
import com.qunar.handler.SAXParserHandler;
/**
* SAX方式解析XML文档
* @author sjf0115
*
*/
public class SAXXMLCode {
public static void main(String[] args) {
String path = "D:\\bookstore.xml";
try {
// 通过SAXParserFactory的静态方法newInstance()方法获取SAXParserFactory实例对象factory
SAXParserFactory factory = SAXParserFactory.newInstance();
// 通过SAXParserFactory实例的newSAXParser()方法返回SAXParser实例parser
SAXParser saxParser = factory.newSAXParser();
// 定义SAXParserHandler对象
SAXParserHandler handler = new SAXParserHandler();
// 解析XML文档
saxParser.parse(path, handler);
// 得到遍历结果
List<Book> bookList = handler.getBookList();
System.out.println("遍历结果：");
for (Book book : bookList) {
System.out.println(book);
}//for
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
~~~
**运行结果：**
<table cellspacing="0" cellpadding="0" style="border-collapse:collapse; border:1px solid rgb(187,187,187); width:1050px"><tbody><tr><td style="border-collapse:collapse; border:1px solid rgb(187,187,187); width:1049px"><br/><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">SAX解析开始...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第1本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第1本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第2本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第2本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">开始解析第3本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">结束解析第3本书...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">SAX解析结束...</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">遍历结果：</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：Java lang：chi title：Java多线程编程核心技术 author：高洪岩 year：2015 price：69.00</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：C++ lang：en title：Effective C++: 55 Specific Ways to Improve Your Programs and Designs author：Scott Meyers year：2006 price：58.00</span></div><div><span style="font-size:14pt; color:windowtext; font-family:微软雅黑">category：Web lang：en title：Learning XML author：Erik T. Ray year：2016 price：39.95</span></div></td></tr></tbody></table>