Java读取xml文件

写了一篇xml的文章，点发布发表不上，点舍去就他妈的一下子全没了，连回收站和草稿箱都没有了，真不知道怎么想CSDN

参考http://blog.csdn.net/yangzl2008/article/details/7045369

废话不多说了，贴代码：

/**
*
*/
package com.zlp.test.xml;

import java.io.File;
import java.util.Iterator;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

/**
* @author Administrator
*
*/
public class XmlRead extends DefaultHandler{

/**
* @param args
*/
/*
* DOM
*/
public void TestDOM(){
DocumentBuilderFactory factory = DocumentBuilderFactory
.newInstance();
Document doc = null;
try {
DocumentBuilder builder = factory.newDocumentBuilder();
doc = builder.parse(new File("test.xml"));
} catch (Exception e) {
e.printStackTrace();
}

String str = doc.getElementsByTagName("name").item(0).getFirstChild().getNodeValue().trim();
System.out.println(str);
}

/*
* dom4j
*/
public void Dom4jReadTest(){
File f = new File("test.xml");
SAXReader saxReader = new SAXReader();
org.dom4j.Document document = null;
try {
document = saxReader.read(f);
} catch (DocumentException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
Element rootElement = document.getRootElement();
Iterator iterator = rootElement.elementIterator("node");

for (; iterator.hasNext();) {
Element other = (Element)iterator.next();
System.out.println(other.elementTextTrim("name"));
}
}

public void SAX(){
java.util.Stack tags = new java.util.Stack();
SAXParserFactory saxparserfactory = SAXParserFactory.newInstance();
try {
SAXParser parser = saxparserfactory.newSAXParser();
parser.parse(new InputSource("test.xml"), new XmlRead());

} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
java.util.Stack tags = new java.util.Stack();
public void startElement(String uri, String localName, String qName,Attributes attrs) {
tags.push(qName);
}

public void characters(char ch[], int start, int length)
throws SAXException {

String tag = (String) tags.peek();
if (tag.equals("name")) {
System.out.print("name" + new String(ch, start, length));
}
if (tag.equals("space")) {
System.out.println("space:" + new String(ch, start, length));
}
}

public static void main(String[] args) {
//new XmlRead().TestDOM();
new XmlRead().Dom4jReadTest();
//new XmlRead().SAX();
}

}

test.xml文件

<?xml version="1.0" encoding="UTF-8"?>
<list>
<node>
<name>
weidewei
</name>
<space> http://wishlife.iteye.com </space>
</node>
</list>

Sax解析xml

package com.zlp.test.xml;

import java.io.File;
import java.util.Vector;

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

public class PraseXML extends DefaultHandler
{

private Vector<String> tagName;

private Vector<String> tagValue;

private int step;
// 开始解析XML文件
public void startDocument() throws SAXException
{
tagName = new Vector<String>();
tagValue = new Vector<String>();
step = 0;
}
// 结束解析XML文件
public void endDocument() throws SAXException
{
for (int i = 0; i < tagName.size(); i++)
{
if (!tagName.get(i).equals("") || tagName.get(i) != null)
{
System.out.println("节点名称：" + tagName.get(i));
System.out.println("节点值：" + tagValue.get(i));
}
}
}
/**
* 在解释到一个开始元素时会调用此方法.但是当元素有重复时可以自己写算法来区分
* 这些重复的元素.qName是什么? <name:page ll=""></name:page>这样写就会抛出SAXException错误
* 通常情况下qName等于localName
*/
public void startElement(String uri, String localName, String qName,
Attributes attributes) throws SAXException
{
// 节点名称
tagName.add(qName);
// 循环输出属性
for (int i = 0; i < attributes.getLength(); i++)
{
// 获取属性名称
System.out.println("属性名称：" + attributes.getQName(i));
// 获取属性值
System.out.println("属性值："
+ attributes.getValue(attributes.getQName(i)));
}

}

/**
* 在遇到结束标签时调用此方法
*/
public void endElement(String uri, String localName, String qName)
throws SAXException
{

step = step + 1;
}

/**
* 读取标签里的值,ch用来存放某行的xml的字符数据,包括标签,初始大小是2048,
* 每解释到新的字符会把它添加到char[]里。    * 注意,这个char字符会自己管理存储的字符,
* 并不是每一行就会刷新一次char,start,length是由xml的元素数据确定的,
* 暂时找不到规律,以后看源代码.
*
* 这里一个正标签，反标签都会被执行一次characters，所以在反标签时不用获得其中的值
*/
public void characters(char ch[], int start, int length)
throws SAXException
{
// 只要当前的标签组的长度一至，值就不赋，则反标签不被计划在内
if (tagName.size() - 1 == tagValue.size())
{
tagValue.add(new String(ch, start, length));
}
}

public static void main(String[] args)
{
String filename = "test.xml";
SAXParserFactory spf = SAXParserFactory.newInstance();
try
{
SAXParser saxParser = spf.newSAXParser();
saxParser.parse(new File(filename), new PraseXML());
}
catch (Exception e)
{
e.printStackTrace();
}
}
public Vector getTagName()
{
return tagName;
}
public void setTagName(Vector tagName)
{
this.tagName = tagName;
}
public Vector getTagValue()
{
return tagValue;
}

public void setTagValue(Vector tagValue)
{
this.tagValue = tagValue;
}

}

在贴上一个simplejee中读取xml的文件。

package com.yuqiaotech.simplejee.xml;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.Iterator;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import javax.xml.transform.stream.StreamSource;

import org.dom4j.DocumentException;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import com.sun.org.apache.xpath.internal.XPathAPI;
/**
* 大体代码是从http://www.javaeye.com/topic/181865抄来的。
* 下面这个是被广泛抄袭的，关于java里读取xml的概要介绍。
* http://blog.csdn.net/geekwang/archive/2008/05/25/2480504.aspx *
* 我主要是把从绝对路径读取xml换成了从classpath读取。
* 另外添加了Transformer和xslt，以及XPath的演示，以及相关的一些链接。
*
* 另外可以搜一下jaxp了解这个规范的相关内容。
*
* @author YUQIAOTECH
*
*/
public class SimpleSample  {
static String xmlName = "test.xml";
static String xlst = "xslt.xsl";
static String dom4jSaveTo = "c:/text.xml";
static String xsltSaveTo = "c:/text2.html";

/**
* DOM方式
*/
public void DOM() {
long lasting = System.currentTimeMillis();

try {
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
DocumentBuilderFactory factory = DocumentBuilderFactory
.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(in); //注意这里的Document是org.w3c.dom包下的
NodeList nl = doc.getElementsByTagName("node");
for (int i = 0; i < nl.getLength(); i++) {
System.out.println("|| Name:  |"
+ doc.getElementsByTagName("name").item(i)
.getFirstChild().getNodeValue());
System.out.println("||Space:  |"
+ doc.getElementsByTagName("space").item(i)
.getFirstChild().getNodeValue());
System.out.println("-------------------------------------------------");            }
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("耗时："
+ (System.currentTimeMillis() - lasting) + " MS");
}

class SaxHandler extends DefaultHandler{
java.util.Stack tags = new java.util.Stack();
public void startElement(String uri, String localName, String qName,
Attributes attrs) {
tags.push(qName);
}

public void characters(char ch[], int start, int length)
throws SAXException {
String tag = (String) tags.peek();
if (tag.equals("name")) {
System.out.println("|| Name:  |" + new String(ch, start, length));
}
if (tag.equals("space")) {
System.out.println("||Space:  |" + new String(ch, start, length));
}
System.out.println("-------------------------------------------------");
}
}

/**
* SAX方式
*/
public void SAX() {

long lasting = System.currentTimeMillis();
try {
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
SAXParserFactory sf = SAXParserFactory.newInstance();
SAXParser sp = sf.newSAXParser();
SaxHandler reader = new SaxHandler();
sp.parse(in, reader);
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("SAX 耗时："
+ (System.currentTimeMillis() - lasting) + " MS");
}

/**
* 我懒得去了解JDOM了 :-)。
* JDOM方式
*/
//    public void JDOM() {
//        long lasting = System.currentTimeMillis();
//        try {
//            SAXBuilder builder = new SAXBuilder();
//            org.jdom.Document doc = builder.build(new File("F:/xmltest.xml"));
//            Element foo = doc.getRootElement();
//            List allChildren = foo.getChildren();
//            for (int i = 0; i < allChildren.size(); i++) {
//                System.out.println("|| Name:  |"
//                        + ((Element) allChildren.get(i)).getChild("name")
//                                .getText());
//                System.out.println("||Space:  |"
//                        + ((Element) allChildren.get(i)).getChild("space")
//                                .getText());
//                System.out.println("-------------------------------------------------");            }
//        } catch (Exception e) {
//            e.printStackTrace();
//        }
//        System.out.println("JDOM RUNTIME："
//                + (System.currentTimeMillis() - lasting) + " MS");
//    }

/**
* DOM4J方式
*/
public void DOM4J() {
long lasting = System.currentTimeMillis();
try {
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
SAXReader reader = new SAXReader();
org.dom4j.Document doc = reader.read(in);  //注意这里的Document是org.dom4j包下的
org.dom4j.Element root = doc.getRootElement();
org.dom4j.Element foo;
for (Iterator i = root.elementIterator("node"); i.hasNext();) {
foo = (org.dom4j.Element) i.next();
System.out.println("|| Name:  |" + foo.elementText("name"));
System.out.println("||Space:  |" + foo.elementText("space"));
System.out.println("-------------------------------------------------");
}
} catch (Exception e) {
e.printStackTrace();
}
System.out.println("DOM4J 耗时："
+ (System.currentTimeMillis() - lasting) + " MS");
}
/**
* 调用dom4j的保存方法。
*
* @throws DocumentException
* @throws IOException
*/
public static void saveDocByDom4J() throws DocumentException, IOException{
Writer out = new OutputStreamWriter(new FileOutputStream(dom4jSaveTo ),"GBK");
OutputFormat format = OutputFormat.createPrettyPrint();
XMLWriter writer = new XMLWriter( out, format );
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
SAXReader reader = new SAXReader();
org.dom4j.Document doc = reader.read(in);
writer.write( doc );
out.close();
}

/**
* 使用Transformer和xslt。
* http://www.ibm.com/developerworks/cn/xml/x-xslt/ *
* @throws ParserConfigurationException
* @throws SAXException
* @throws IOException
*/
public static void saveByTransformer() throws ParserConfigurationException, SAXException, IOException {
try {
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
InputStream inXsl = SimpleSample.class.getResourceAsStream(xlst);
DocumentBuilderFactory factory = DocumentBuilderFactory
.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(in);
StreamSource style = new StreamSource(inXsl);
TransformerFactory tFactory = TransformerFactory.newInstance();
Transformer transformer = tFactory.newTransformer(style);
transformer.setOutputProperty(OutputKeys.ENCODING, "GBK");
DOMSource source = new DOMSource(doc);
StreamResult result = new StreamResult(new File(xsltSaveTo));
transformer.transform(source, result);
} catch (TransformerConfigurationException e) {
throw new RuntimeException(e.getMessage(), e);
} catch (TransformerException e) {
throw new RuntimeException(e.getMessage(), e);
}
}

//**********************XPath*****************************

/**
* 返回指定的节点。
*
* @param topNode
* @param xPath
* @return
*/
public static Node selectSingleNode(Node topNode, String xPath) {
try {
return XPathAPI.selectSingleNode(topNode, xPath);
} catch (TransformerException e) {
System.out.println(e.getMessage() + " xPath=" + xPath);
throw new RuntimeException(e.getMessage(), e);
}
}

/**
* 根据属性名获取属性节点。
*
* @param node
* @param attributeName
* @return
*/
public static Node getAttributeNode(Node node, String attributeName) {
NamedNodeMap namedNodeMap = node.getAttributes();
return namedNodeMap.getNamedItem(attributeName);
}

/**
* 几个方法的组合。
*
* @param node
* @param xPath
* @param attributeName
* @return
*/
public static String getAttributeNodeByXPath(Node node, String xPath,
String attributeName) {
Node rtn = null;
Node selectedNode = selectSingleNode(node, xPath);
if (selectedNode != null) {
rtn = getAttributeNode(selectedNode, attributeName);
}
if(rtn == null)return null;
return rtn.getNodeValue();
}
/**
* http://www.zvon.org/xxl/XPathTutorial/General_chi/examples.html * http://www.ibm.com/developerworks/cn/xml/x-wxxm35.html *
* @throws ParserConfigurationException
* @throws SAXException
* @throws IOException
*/
public static void XPath() throws ParserConfigurationException, SAXException, IOException{
InputStream in = SimpleSample.class.getResourceAsStream(xmlName);
DocumentBuilderFactory factory = DocumentBuilderFactory
.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(in);
String attr = getAttributeNodeByXPath(doc,"//node[@id=1]/name","alias");
System.out.println("alias="+attr);

}
public static void main(String arge[]) throws ParserConfigurationException, SAXException, IOException, DocumentException {
SimpleSample myXML = new SimpleSample();
System.out.println("=====================DOM=========================");
myXML.DOM();
System.out.println("=====================SAX=========================");
myXML.SAX();
//System.out.println("=====================JDOM========================");
//myXML.JDOM();
System.out.println("=====================DOM4J=======================");
myXML.DOM4J();
System.out.println("=====================DOM4J的格式化保存=======================");
saveDocByDom4J();
System.out.println("=====================Transformer和xslt的使用=======================");
saveByTransformer();
System.out.println("=====================XPath的演示=======================");
XPath();
}
}

test1.xml

<?xml version="1.0" encoding="gbk"?>
<list>
<node id="1"><name alias="李逵">张三</name><space>http://wishlife.javaeye.com</space></node>
<node><name>李四</name><space>http://user.qzone.qq.com/94611981</space></node>
</list>

xslt.xsl

<xsl:transform
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="1.0">
<xsl:variable name="nodes" select="//node"/>
<xsl:template match="list">
<html><body>
<h1>名单</h1>
<table cellpadding="5">
<tr>
<td>姓名</td>
<td>博客</td>
</tr>
<xsl:for-each select="$nodes">
<tr>
<td> <xsl:value-of select="./name"/>(<xsl:value-of select="./name/@alias"/>)</td>
<td> <xsl:value-of select="./space"/></td>
</tr>
</xsl:for-each>
</table>
</body></html>
</xsl:template>
</xsl:transform>