在java环境下读取xml文件的方法主要有4种:DOM、SAX、JDOM、JAXB
1. DOM(Document Object Model)
此 方法主要由W3C提供,它将xml文件全部读入内存中,然后将各个元素组成一棵数据树,以便快速的访问各个节点 。 因此非常消耗系统性能 ,对比较大的文档不适宜采用DOM方法来解析。 DOM API 直接沿袭了 XML 规范。每个结点都可以扩展的基于 Node 的接口,就多态性的观点来讲,它是优秀的,但是在 Java 语言中的应用不方便,并且可读性不强。
实例:
- import javax.xml.parsers.*;
-
- import org.w3c.dom.*;
-
- import org.apache.crimson.tree.XmlDocument;
-
- DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
-
- factory.setNamespaceAware(true);
-
- factory.setValidating(true);
-
- try {
- DocumentBuilder builder = factory.newDocumentBuilder();
- } catch (ParserConfigurationException pce) {
- System.err.println(pce);
-
- System.exit(1);
- }
-
- try {
- Document doc = builder.parse(fileURI);
- } catch (DOMException dom) {
- System.err.println(dom.getMessage());
- System.exit(1);
- } catch (IOException ioe) {
- System.err.println(ioe);
- System.exit(1);
- }
-
- Element elmtStuInfo = doc.getDocumentElement();
-
- NodeList nlStudent = elmtStuInfo.getElementsByTagNameNS(
- strNamespace, "student");
- for (……){
-
- Element elmtStudent = (Element)nlStudent.item(i);
- NodeList nlCurrent = elmtStudent.getElementsByTagNameNS(
- strNamespace, "name");
- }
import javax.xml.parsers.*;
//XML解析器接口
import org.w3c.dom.*;
//XML的DOM实现
import org.apache.crimson.tree.XmlDocument;
//写XML文件要用到
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
//允许名字空间
factory.setNamespaceAware(true);
//允许验证
factory.setValidating(true);
//获得DocumentBuilder的一个实例
try {
DocumentBuilder builder = factory.newDocumentBuilder();
} catch (ParserConfigurationException pce) {
System.err.println(pce);
// 出异常时输出异常信息,然后退出,下同
System.exit(1);
}
//解析文档,并获得一个Document实例。
try {
Document doc = builder.parse(fileURI);
} catch (DOMException dom) {
System.err.println(dom.getMessage());
System.exit(1);
} catch (IOException ioe) {
System.err.println(ioe);
System.exit(1);
}
//获得根节点StuInfo
Element elmtStuInfo = doc.getDocumentElement();
//得到所有student节点
NodeList nlStudent = elmtStuInfo.getElementsByTagNameNS(
strNamespace, "student");
for (……){
//当前student节点元素
Element elmtStudent = (Element)nlStudent.item(i);
NodeList nlCurrent = elmtStudent.getElementsByTagNameNS(
strNamespace, "name");
}
对于读取得方法其实是很简单的,写入xml文件也是一样不复杂。
- DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
- DocumentBuilder builder = null;
- try {
- builder = factory .newDocumentBuilder();
- } catch (ParserConfigurationException pce) {
- System.err.println(pce);
- System.exit(1);
- }
- Document doc = null;
- doc = builder .newDocument();
-
-
- Element root = doc.createElement("学生花名册");
-
- doc.appendChild(root);
-
- Element student = doc.createElement("学生");
- student.setAttribute("性别", studentBean.getSex());
- root.appendChild(student);
-
- Element name = doc.createElement("姓名");
- student.appendChild(name);
- Text tName = doc.createTextNode(studentBean.getName());
- name.appendChild(tName);
- Element age = doc.createElement("年龄");
- student.appendChild(age);
- Text tAge = doc.createTextNode(String.valueOf(studentBean.getAge()));
- age.appendChild(tAge);
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = null;
try {
builder = factory .newDocumentBuilder();
} catch (ParserConfigurationException pce) {
System.err.println(pce);
System.exit(1);
}
Document doc = null;
doc = builder .newDocument();
//下面是建立XML文档内容的过程,
//先建立根元素"学生花名册"
Element root = doc.createElement("学生花名册");
//根元素添加上文档
doc.appendChild(root);
//建立"学生"元素,添加到根元素
Element student = doc.createElement("学生");
student.setAttribute("性别", studentBean.getSex());
root.appendChild(student);
//建立"姓名"元素,添加到学生下面,下同
Element name = doc.createElement("姓名");
student.appendChild(name);
Text tName = doc.createTextNode(studentBean.getName());
name.appendChild(tName);
Element age = doc.createElement("年龄");
student.appendChild(age);
Text tAge = doc.createTextNode(String.valueOf(studentBean.getAge()));
age.appendChild(tAge);
2.SAX (Simple API for XML)
此方法主要由XML-DEV 邮件列表的成员开发的,SAX是基于事件的方法,它很类似于标签库的处理机制,在标签开始、结束以及错误发生等等地方调用相应的接口实现方法,不是全部文 档都读入内存。 SAX具有优异的性能和利用更少的存储空间特点。SAX 的设计只考虑了功能的强大性,却没有考虑程序员使用起来是否方便。
使用必须扩展ContentHandler、ErrorHandler、DTDHandler等,但是必须扩展ContentHandler(或者DefaultHandler )。
- import org.xml.sax.*;
- public class MyContentHandler implements ContentHandler {
- … …
- }
-
-
-
-
- public void setDocumentLocator(Locator locator){
- }
-
-
-
-
- public void startDocument() throws SAXException{
- System.out.println("** Student information start **");
- }
-
-
-
-
- public void endDocument() throws SAXException{
- System.out.println("**** Student information end ****");
- }
-
-
-
-
-
-
- public void startPrefixMapping(String prefix
- , String uri) throws SAXException{
- }
-
-
-
-
-
- public void endPrefixMapping(String prefix) 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{
- if (localName.equals(“student”)){
- System.out.println(localName+":"+currentData);
- }
- }
import org.xml.sax.*;
public class MyContentHandler implements ContentHandler {
… …
}
/**
* 当其他某一个调用事件发生时,先调用此方法来在文档中定位。
* @param locator
*/
public void setDocumentLocator(Locator locator){
}
/**
* 在解析整个文档开始时调用
* @throws SAXException
*/
public void startDocument() throws SAXException{
System.out.println("** Student information start **");
}
/**
* 在解析整个文档结束时调用
* @throws SAXException
*/
public void endDocument() throws SAXException{
System.out.println("**** Student information end ****");
}
/**
* 在解析名字空间开始时调用
* @param prefix
* @param uri
* @throws SAXException
*/
public void startPrefixMapping(String prefix
, String uri) throws SAXException{
}
/**
* 在解析名字空间结束时调用
* @param prefix
* @throws SAXException
*/
public void endPrefixMapping(String prefix) throws SAXException{
}
/**
* 在解析元素开始时调用
* @param namespaceURI
* @param localName
* @param qName
* @param atts
* @throws SAXException
*/
public void startElement(String namespaceURI, String localName
, String qName, Attributes atts) throws SAXException{
}
/** 在解析元素结束时调用
* @param namespaceURI
* @param localName 本地名,如student
* @param qName 原始名,如LIT:student
* @throws SAXException */
public void endElement(String namespaceURI, String localName,String qName) throws SAXException{
if (localName.equals(“student”)){
System.out.println(localName+":"+currentData);
}
}
取得元素数据的方法——characters
取得元素数据中的空白的方法——ignorableWhitespace
在解析到处理指令时调用的方法——processingInstruction
当未验证解析器忽略实体时调用的方法——skippedEntity
运行时,只需要使用下列代码:
- MySAXParser mySAXParser = new MySAXParser();
- mySAXParser.parserXMLFile("SutInfo.xml");
MySAXParser mySAXParser = new MySAXParser();
mySAXParser.parserXMLFile("SutInfo.xml");
3.JDOM
JDOM的处理方式有些类似于DOM,但它主要是用SAX实现的 。JDOM用Java的数据类型来定义操作数据树的各个节点 。JDOM的性能也很优越。
- import org.jdom.*;
- import org.jdom.input.*;
- import org.jdom.output.*;
- SAXBuilder builder = new SAXBuilder(false);
-
- Document doc = builder.build(fileURI);
-
- Namespace ns = Namespace.getNamespace("LIT" , "http://www.lit.edu.cn/student/ ");
-
- List lstStudents = elmtStuInfo.getChildren("student",ns);
- for ( … ){
- Element elmtStudent = (Element)lstStudents.get(i);
- elmtStudent.getChildTextTrim("name", ns);
- }
-
- elmtLesson.getChild("lessonScore" , ns).setText("100");
-
- elmtStuInfo.removeChild("master", ns);
-
- elmtStuInfo.addContent(new Element("master" , ns).addContent(new Entity("masterName")));
-
-
-
- XMLOutputter printDoc = new XMLOutputter(" ", true);
- printDoc.output(doc, new FileOutputStream("StuInfo.xml"));
import org.jdom.*;
import org.jdom.input.*;
import org.jdom.output.*;
SAXBuilder builder = new SAXBuilder(false);
//得到Document
Document doc = builder.build(fileURI);
//名字空间
Namespace ns = Namespace.getNamespace("LIT" , "http://www.lit.edu.cn/student/ ");
//取得所有LIT:student节点的集合
List lstStudents = elmtStuInfo.getChildren("student",ns);
for ( … ){
Element elmtStudent = (Element)lstStudents.get(i);
elmtStudent.getChildTextTrim("name", ns);
}
//修改
elmtLesson.getChild("lessonScore" , ns).setText("100");
//删除
elmtStuInfo.removeChild("master", ns);
//添加
elmtStuInfo.addContent(new Element("master" , ns).addContent(new Entity("masterName")));
//输出文档
//第一个参数是缩进字符串,这里是4个空格。
//第二个参数是true,表示需要换行。
XMLOutputter printDoc = new XMLOutputter(" ", true);
printDoc.output(doc, new FileOutputStream("StuInfo.xml"));
4.JAXB (Java And XML Binding)
JAXB 是以SUN为主的一些公司公布的。JAXB将schema(或者DTD)映射为java对象(.java文件),然后使用这些java对象来解析xml文件。需要使用之前生成java文件,因而要有固定的schema,无法处理动态的xml文件。
首先使用xjc命令,生成java文件
xjc [-options ...]
(生成的文件较多)
- JAXBContext jc = JAXBContext.newInstance(“packageName");
- Unmarshaller unmarshaller = jc.createUnmarshaller();
- Collection collection= (Collection)unmarshaller.unmarshal(new File( "books.xml"));
- CollectionType.BooksType booksType =collection.getBooks();
- List bookList = booksType.getBook();
- for( … ){
- test.jaxb.BookType book =(test.jaxb.BookType) bookList.get(i);
- System.out.println("Book Name: " + book.getName().trim());
- System.out.println("Book ISBN: " + book.getISBN());
- }
JAXBContext jc = JAXBContext.newInstance(“packageName");
Unmarshaller unmarshaller = jc.createUnmarshaller();
Collection collection= (Collection)unmarshaller.unmarshal(new File( "books.xml"));
CollectionType.BooksType booksType =collection.getBooks();
List bookList = booksType.getBook();
for( … ){
test.jaxb.BookType book =(test.jaxb.BookType) bookList.get(i);
System.out.println("Book Name: " + book.getName().trim());
System.out.println("Book ISBN: " + book.getISBN());
}
补充另一种方法:
据悉dom4j在xml解析方面是性能最好的,hibernate等框架都使用它作为解析的工具。
要使用dom4j读写XML文档,需要先下载dom4j包,dom4j官方网站在 http://www.dom4j.org/
目前最新dom4j包下载地址:http://nchc.dl.sourceforge.net/sourceforge/dom4j/dom4j-1.6.1.zip
解开后有两个包,仅操作XML文档的话把dom4j-1.6.1.jar加入工程就可以了,如果需要使用XPath的话还需要加入包jaxen-1.1-beta-7.jar
写了简单的dom4j的使用的demo,以备回忆,有些是dom4j的文挡里例子改编的
使用dom4j解析下面的xml文件。
- <?xml version="1.0" encoding="GB2312"?>
-
- <?xml-stylesheet type="text/xsl" href="students.xsl"?>
-
- <students>
- <student sn="01">
- <name>张三</name>
- <age>18</age>
- </student>
-
- <student sn="02">
- <name>李四</name>
- <age>20</age>
- </student>
- </students>
<?xml version="1.0" encoding="GB2312"?>
<?xml-stylesheet type="text/xsl" href="students.xsl"?>
<students>
<student sn="01">
<name>张三</name>
<age>18</age>
</student>
<student sn="02">
<name>李四</name>
<age>20</age>
</student>
</students>
Parse.java
- import java.io.File;
-
- import org.dom4j.Attribute;
- import org.dom4j.Document;
- import org.dom4j.DocumentException;
- import org.dom4j.Element;
- import org.dom4j.ProcessingInstruction;
- import org.dom4j.VisitorSupport;
- import org.dom4j.io.SAXReader;
-
- public class Parse {
-
- public static void main(String[] args) {
- SAXReader reader = new SAXReader();
- File file = new File("src/students.xml");
- try {
- Document doc = reader.read(file);
- doc.accept(new MyVistor());
- } catch (DocumentException e) {
-
- e.printStackTrace();
- }
- }
-
- public static class MyVistor extends VisitorSupport {
- public void visit(Attribute node) {
- System.out.println("Attibute:---" + node.getName() + "="+ node.getValue());
- }
-
- public void visit(Element node) {
- if (node.isTextOnly()) {
- System.out.println("Element:---" + node.getName() + "="
- + node.getText());
- }else{
- System.out.println("--------" + node.getName() + "-------");
- }
- }
-
- @Override
- public void visit(ProcessingInstruction node) {
- System.out.println("PI:"+node.getTarget()+" "+node.getText());
- }
- }
- }
import java.io.File;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.ProcessingInstruction;
import org.dom4j.VisitorSupport;
import org.dom4j.io.SAXReader;
public class Parse {
public static void main(String[] args) {
SAXReader reader = new SAXReader();
File file = new File("src/students.xml");
try {
Document doc = reader.read(file);
doc.accept(new MyVistor());
} catch (DocumentException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public static class MyVistor extends VisitorSupport {
public void visit(Attribute node) {
System.out.println("Attibute:---" + node.getName() + "="+ node.getValue());
}
public void visit(Element node) {
if (node.isTextOnly()) {
System.out.println("Element:---" + node.getName() + "="
+ node.getText());
}else{
System.out.println("--------" + node.getName() + "-------");
}
}
@Override
public void visit(ProcessingInstruction node) {
System.out.println("PI:"+node.getTarget()+" "+node.getText());
}
}
}
使用dom4j来将属性写入xml
- import java.io.FileWriter;
- import java.io.IOException;
-
- import org.dom4j.Document;
- import org.dom4j.DocumentHelper;
- import org.dom4j.Element;
- import org.dom4j.io.OutputFormat;
- import org.dom4j.io.XMLWriter;
-
- public class DWriter {
-
- public static void main(String[] args) {
-
- try {
- XMLWriter writer = new XMLWriter(new FileWriter("src/author.xml"));
- Document doc = createDoc();
- writer.write(doc);
- writer.close();
-
-
-
- OutputFormat format = OutputFormat.createPrettyPrint();
- writer = new XMLWriter(System.out, format);
- writer.write(doc);
-
- } catch (IOException e) {
-
- e.printStackTrace();
- }
- }
-
- public static Document createDoc() {
- Document doc = DocumentHelper.createDocument();
- Element root = doc.addElement("root");
- Element author1 = root.addElement("author").addAttribute("name",
- "Kree").addAttribute("location", "UK")
- .addText("Kree Strachan");
- Element author2 = root.addElement("author").addAttribute("name", "King")
- .addAttribute("location", "US").addText("King McWrirter");
- return doc;
- }
- }
import java.io.FileWriter;
import java.io.IOException;
import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.XMLWriter;
public class DWriter {
public static void main(String[] args) {
// TODO Auto-generated method stub
try {
XMLWriter writer = new XMLWriter(new FileWriter("src/author.xml"));
Document doc = createDoc();
writer.write(doc);
writer.close();
// Pretty print the document to System.out
// 设置了打印的格式,将读出到控制台的格式进行美化
OutputFormat format = OutputFormat.createPrettyPrint();
writer = new XMLWriter(System.out, format);
writer.write(doc);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public static Document createDoc() {
Document doc = DocumentHelper.createDocument();
Element root = doc.addElement("root");
Element author1 = root.addElement("author").addAttribute("name",
"Kree").addAttribute("location", "UK")
.addText("Kree Strachan");
Element author2 = root.addElement("author").addAttribute("name", "King")
.addAttribute("location", "US").addText("King McWrirter");
return doc;
}
}
使用dom4j写入到author.xml文件的内容
- <?xml version="1.0" encoding="UTF-8"?>
- <root>
- <author name="Kree" location="UK">Kree Strachan</author>
- <author name="King" location="US">King McWrirter</author>
- </root>