使用Stax解析XML

完整版见https://jadyer.github.io/2013/03/19/xml-stax/

首先是我们用到的位于src下面的books.xml

<?xml version="1.0" encoding="UTF-8"?><bookstore><book category="COOKING" aaaaaa="111111"><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>

下面是Stax用法

package com.jadyer.stax;import java.io.InputStream;import javax.xml.parsers.DocumentBuilder;import javax.xml.parsers.DocumentBuilderFactory;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.Transformer;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.XPathFactory;import org.w3c.dom.Document;import org.w3c.dom.Element;import org.w3c.dom.NodeList;/** * 使用Stax解析XML * @see Stax(Streaming API for XML) * @create Mar 17, 2013 5:30:31 PM * @author 玄玉<http://blog.csdn/net/jadyer> */public class TestStax {public static void main(String[] args) throws Exception {cursorParseXML();iteratorParseXML();filterParseXML();xpathParseXML();xmlStreamWriterXML();transformerModifyXML();}/** * 基于光标的方式解析XML */private static void cursorParseXML() throws Exception {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = TestStax.class.getClassLoader().getResourceAsStream("books.xml");XMLStreamReader reader = factory.createXMLStreamReader(is);while(reader.hasNext()) {int type = reader.next();//处理不同的节点类型//处理开始节点,如<bookstore>,<book>if(type == XMLStreamConstants.START_ELEMENT) {String name = reader.getName().toString();System.out.println("<" + name + ">");//打印<book category="COOKING" aaaaaa="111111">节点中的第二个属性值aaaaaaif(name.equals("book")){System.out.println("节点属性值为" + reader.getAttributeName(1) + "=" + reader.getAttributeValue(1));}if(name.equals("title")) {System.out.println("书籍[" + reader.getElementText() + "]");}if(name.equals("price")) {System.out.println("的价格为[" + reader.getElementText() + "]");}//打印文本节点的内容,注意各xml标签中的空白部分也属于文本节点..并且文本节点是没有name的,所以不能getName} else if(type == XMLStreamConstants.CHARACTERS) {System.out.println("文本节点值=[" + reader.getText().trim() + "]");//处理结束节点,如</book>,</title>} else if(type == XMLStreamConstants.END_ELEMENT) {System.out.println("</" + reader.getName() + ">");}}//最后处理完了xml,记得关闭..但不能提前关闭,因为Stax是读一点流就解析一点的is.close();}/** * 基于迭代模型的方式解析XML */private static void iteratorParseXML() throws Exception {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = TestStax.class.getClassLoader().getResourceAsStream("books.xml");XMLEventReader reader = factory.createXMLEventReader(is);int iteratorNum = 0; //统计遍历的次数while(reader.hasNext()) {XMLEvent event = reader.nextEvent();if(event.isStartElement()) {                                   //通过XMLEvent判断节点类型String name = event.asStartElement().getName().toString(); //通过event.asxxx转换节点if(name.equals("title")) {System.out.print("书籍[" + reader.getElementText() + "]");}if(name.equals("price")) {System.out.println("的价格为[" + reader.getElementText() + "]");}}iteratorNum++;}is.close();System.out.println("本次操作遍历XML的次数合计为[" + iteratorNum + "]次");}/** * 基于Filter的方式解析XML * @see 可以有效的过滤掉不用进行操作的节点,效率会高一些 */private static void filterParseXML() throws Exception {XMLInputFactory factory = XMLInputFactory.newInstance();InputStream is = TestStax.class.getClassLoader().getResourceAsStream("books.xml");XMLEventReader reader = factory.createFilteredReader(factory.createXMLEventReader(is),new EventFilter() {@Overridepublic boolean accept(XMLEvent event) {if(event.isStartElement()) {String name = event.asStartElement().getName().toString();if(name.equals("title") || name.equals("price")){return true; //返回true表示会显示,false表示不显示}}return false;}});int iteratorNum = 0; //统计遍历的次数while(reader.hasNext()) {XMLEvent event = reader.nextEvent();if(event.isStartElement()) {String name = event.asStartElement().getName().toString();if(name.equals("title")) {System.out.print("书籍[" + reader.getElementText() + "]");}if(name.equals("price")) {System.out.println("的价格为[" + reader.getElementText() + "]");}}iteratorNum++;}is.close();System.out.println("本次操作遍历XML的次数合计为[" + iteratorNum + "]次");}/** * 基于XPath的方式解析XML */private static void xpathParseXML() throws Exception {InputStream is = TestStax.class.getClassLoader().getResourceAsStream("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表达式,第二参数就是文档..这里是查找所有属性为category="WEB"的<book>节点NodeList list = (NodeList)xpath.evaluate("//book[@category='WEB']", doc, XPathConstants.NODESET);for(int i=0; i<list.getLength(); i++) {Element e = (Element)list.item(i);//由于<book>节点下只会有一个<title>节点,所有这里是item(0)System.out.println(e.getElementsByTagName("title").item(0).getTextContent());System.out.println(e.getElementsByTagName("price").item(0).getTextContent());}is.close();}/** * 使用XMLStreamWriter创建XML */private static void xmlStreamWriterXML() throws XMLStreamException, FactoryConfigurationError {XMLStreamWriter xsw = XMLOutputFactory.newInstance().createXMLStreamWriter(System.out);xsw.writeStartDocument("GBK","1.0");xsw.writeEndDocument(); //先写<?xml version="1.0" encoding="GBK"?>String namespaceURI = "http://blog.csdn.net/jadyer";xsw.writeStartElement("pre", "uesr", namespaceURI); //再写<pre:uesr>xsw.writeStartElement(namespaceURI, "id");          //再写<pre:id>xsw.writeCharacters("1");                           //再写1xsw.writeEndElement();                              //再写</pre:id>xsw.writeEndElement();                              //再写</pre:uesr>xsw.flush();xsw.close();}/** * 使用Transformer更新XML */private static void transformerModifyXML() throws Exception, TransformerFactoryConfigurationError {InputStream is = TestStax.class.getClassLoader().getResourceAsStream("books.xml");DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();Document doc = db.parse(is);XPath xpath = XPathFactory.newInstance().newXPath();//查找内容含title="Learning XML"的<book>节点NodeList list = (NodeList)xpath.evaluate("//book[title='Learning XML']", doc, XPathConstants.NODESET);//获取<price>节点,这里只有一个符合条件的<book>节点,所以写成了list.item(0)Element e = (Element)(((Element)list.item(0)).getElementsByTagName("price").item(0));e.setTextContent("333.9");Transformer tran = TransformerFactory.newInstance().newTransformer();tran.setOutputProperty(OutputKeys.ENCODING, "UTF-8");tran.setOutputProperty(OutputKeys.INDENT, "yes"); //让<?xml version=...?>与<bookestore>节点之间换行,默认不换行//修改节点tran.transform(new DOMSource(doc), new StreamResult(System.out));is.close();}}