stax解析xml文档的6种方式

原文链接：http://blog.csdn.net/u011593278/article/details/9745271

stax解析xml文档的方式：

1. 基于光标的查询；
2. 基于迭代模型的查找；
3. 基于过滤器的查找；
4. 基于xpath的查找；
5. 使用 XMLStreamWriter 创建 xml 文档：
6. 通过 Transformer 更新节点信息；

package com.zp.ws.test03;import java.io.IOException;import java.io.InputStream;import javax.xml.parsers.DocumentBuilder;import javax.xml.parsers.DocumentBuilderFactory;import javax.xml.parsers.ParserConfigurationException;import javax.xml.stream.EventFilter;import javax.xml.stream.FactoryConfigurationError;import javax.xml.stream.XMLEventReader;import javax.xml.stream.XMLInputFactory;import javax.xml.stream.XMLOutputFactory;import javax.xml.stream.XMLStreamConstants;import javax.xml.stream.XMLStreamException;import javax.xml.stream.XMLStreamReader;import javax.xml.stream.XMLStreamWriter;import javax.xml.stream.events.XMLEvent;import javax.xml.transform.OutputKeys;import javax.xml.transform.Result;import javax.xml.transform.Transformer;import javax.xml.transform.TransformerConfigurationException;import javax.xml.transform.TransformerException;import javax.xml.transform.TransformerFactory;import javax.xml.transform.TransformerFactoryConfigurationError;import javax.xml.transform.dom.DOMSource;import javax.xml.transform.stream.StreamResult;import javax.xml.xpath.XPath;import javax.xml.xpath.XPathConstants;import javax.xml.xpath.XPathExpressionException;import javax.xml.xpath.XPathFactory;import org.junit.Test;import org.w3c.dom.Document;import org.w3c.dom.Element;import org.w3c.dom.NodeList;import org.xml.sax.SAXException;public class TestStax {/** * 基于光标模型： *  * 获取xml文件的元素和文本内容； */@Testpublic void test01() {//实例化一个xml输入流工厂，创建一个xml文件读取器；XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = null;try {//获取xml文件的的输入流；is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");//创建一个XMLStreamReader，读取xml文件，获取相应内容；XMLStreamReader reader = factory.createXMLStreamReader(is);while(reader.hasNext()) {int type = reader.next();/** * 判断节点类型是否是开始或者结束或者文本节点,之后根据情况及进行处理： *  * START_ELEMENT：开始元素； * CHARACTERS：文本； * END_ELEMENT：结束元素； *  * reader.getName()得先判断是什么节点，再输出name，否则会报错，因为文本节点没有name； */if(type==XMLStreamConstants.START_ELEMENT) {System.out.println(reader.getName());} else if(type==XMLStreamConstants.CHARACTERS) {System.out.println(reader.getText().trim());} else if(type==XMLStreamConstants.END_ELEMENT) {System.out.println("/"+reader.getName());}}} catch (XMLStreamException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 基于光标模型： *  * 获取指定元素名的属性名和属性值； */@Testpublic void test02() {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");XMLStreamReader reader = factory.createXMLStreamReader(is);while(reader.hasNext()) {int type = reader.next();if(type==XMLStreamConstants.START_ELEMENT) {String name = reader.getName().toString();//获取元素名称为book的第一个属性名和属性值；if(name.equals("book")) {System.out.println(reader.getAttributeName(0)+":"+reader.getAttributeValue(0));}}}} catch (XMLStreamException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 基于光标模型： *  * 获取xml文件指定元素的文本内容(元素的值) */@Testpublic void test03() {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");XMLStreamReader reader = factory.createXMLStreamReader(is);while(reader.hasNext()) {int type = reader.next();if(type==XMLStreamConstants.START_ELEMENT) {String name = reader.getName().toString();//获取名为"title"的元素的文本内容(元素的值)if(name.equals("title")) {System.out.print(reader.getElementText()+":");}//获取名为"price"的元素的文本内容(元素的值)if(name.equals("price")) {System.out.print(reader.getElementText()+"\n");}}}} catch (XMLStreamException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 基于迭代模型： *  * 获取xml文件指定元素的文本内容(元素的值) *  * 迭代次数：本次测试时85； *  * 根据迭代次数和过滤模型相比，过滤模型的远高于迭代模型的； */@Testpublic void test04() {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");//基于迭代模型的操作方式XMLEventReader reader = factory.createXMLEventReader(is);int num = 0;while(reader.hasNext()) {//通过XMLEvent来获取是否是某种节点类型XMLEvent event = reader.nextEvent();if(event.isStartElement()) {//通过event.asxxx转换节点类型；String name = event.asStartElement().getName().toString();if(name.equals("title")) {System.out.print(reader.getElementText()+":");}if(name.equals("price")) {System.out.print(reader.getElementText()+"\n");}}num++;}//返回迭代次数是：85；System.out.println(num);} catch (XMLStreamException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 基于过滤模型： *  * 获取xml文件指定元素的文本内容(元素的值) *  * 加过滤器后的迭代次数：本次测试结果：8； *  * 所以可以得到的结果是：使用过滤模型的效率远高于迭代模型； */@Testpublic void test05() {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");//基于Filter的过滤方式，可以有效的过滤掉不用进行操作的节点，效率会高一些XMLEventReader reader = factory.createFilteredReader(factory.createXMLEventReader(is),new EventFilter() {@Overridepublic boolean accept(XMLEvent event) {//返回true表示会显示，返回false表示不显示if(event.isStartElement()) {String name = event.asStartElement().getName().toString();if(name.equals("title")||name.equals("price"))return true;}return false;}});int num = 0;while(reader.hasNext()) {//通过XMLEvent来获取是否是某种节点类型XMLEvent event = reader.nextEvent();if(event.isStartElement()) {//通过event.asxxx转换节点String name = event.asStartElement().getName().toString();if(name.equals("title")) {System.out.print(reader.getElementText()+":");}if(name.equals("price")) {System.out.print(reader.getElementText()+"\n");}}num++;}//返回迭代次数：8；System.out.println(num);} catch (XMLStreamException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 基于XPath ：XPath 是一门在 XML 文档中查找信息的语言； */@Testpublic void test06() {InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");//创建文档处理对象DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();//通过DocumentBuilder创建doc的文档对象Document doc = db.parse(is);//创建XPathXPath xpath = XPathFactory.newInstance().newXPath();//第一个参数就是xpath,第二参数就是文档NodeList list = (NodeList)xpath.evaluate("//book[@category='WEB']", doc,XPathConstants.NODESET);for(int i=0;i<list.getLength();i++) {//遍历输出相应的结果Element e = (Element)list.item(i);System.out.println(e.getElementsByTagName("title").item(0).getTextContent());}} catch (ParserConfigurationException e) {e.printStackTrace();} catch (SAXException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();} catch (XPathExpressionException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}/** * 使用 XMLStreamWriter 创建 xml 文档： */@Testpublic void test07() {try {XMLStreamWriter xsw = XMLOutputFactory.newInstance().createXMLStreamWriter(System.out);xsw.writeStartDocument("UTF-8","1.0");xsw.writeEndDocument();String ns = "http://11:dd";xsw.writeStartElement("nsadfsadf","person",ns);xsw.writeStartElement(ns,"id");xsw.writeCharacters("1");xsw.writeEndElement();xsw.writeEndElement();xsw.flush();xsw.close();} catch (XMLStreamException e) {e.printStackTrace();} catch (FactoryConfigurationError e) {e.printStackTrace();}}/** * 通过 Transformer 更新节点信息； */@Testpublic void test08() {InputStream is = null;try {is = TestStax.class.getClassLoader().getResourceAsStream("com/zp/ws/test03/books.xml");//创建文档处理对象DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();//通过DocumentBuilder创建doc的文档对象Document doc = db.parse(is);//创建XPathXPath xpath = XPathFactory.newInstance().newXPath();Transformer tran = TransformerFactory.newInstance().newTransformer();tran.setOutputProperty(OutputKeys.ENCODING,"UTF-8");tran.setOutputProperty(OutputKeys.INDENT, "yes");//第一个参数就是xpath,第二参数就是文档NodeList list = (NodeList)xpath.evaluate("//book[title='Learning XML']", doc,XPathConstants.NODESET);//获取price节点Element be = (Element)list.item(0);Element e = (Element)(be.getElementsByTagName("price").item(0));e.setTextContent("333.9");//通过输出流创建一个结果；Result result = new StreamResult(System.out);//通过tranformer修改节点tran.transform(new DOMSource(doc), result);} catch (ParserConfigurationException e) {e.printStackTrace();} catch (SAXException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();} catch (XPathExpressionException e) {e.printStackTrace();} catch (TransformerConfigurationException e) {e.printStackTrace();} catch (TransformerFactoryConfigurationError e) {e.printStackTrace();} catch (TransformerException e) {e.printStackTrace();} finally {try {//关闭读取xml文件的输入流；if(is!=null) is.close();} catch (IOException e) {e.printStackTrace();}}}}

books.xml文件代码：

<?xml version="1.0" encoding="UTF-8"?><bookstore><book category="COOKING">  <title lang="en">Everyday Italian</title>  <author>Giada De Laurentiis</author>  <year>2005</year>  <price>30.00</price></book><book category="CHILDREN">  <title lang="en">Harry Potter</title>  <author>J K. Rowling</author>  <year>2005</year>  <price>29.99</price></book><book category="WEB">  <title lang="en">XQuery Kick Start</title>  <author>James McGovern</author>  <author>Per Bothner</author>  <author>Kurt Cagle</author>  <author>James Linn</author>  <author>Vaidyanathan Nagarajan</author>  <year>2003</year>  <price>49.99</price></book><book category="WEB">  <title lang="en">Learning XML</title>  <author>Erik T. Ray</author>  <year>2003</year>  <price>39.95</price></book></bookstore>