dom4j对xml的操作

package com.linzl.cn.xml;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Iterator;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.stream.StreamResult;

import org.apache.commons.io.FileUtils;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.DocumentSource;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
import org.xml.sax.SAXException;

/**
* 读写性能最佳 依赖dom4j.jar jaxen-1.1-beta-4.jar 对于复杂格式的xml更合适
*
* @author linzl 最后修改时间：2014年10月10日
*/
public class Dom4jUtils {

/**
 * 使用JDK自带的类转换Document对象转成字符串
 * 
 * @param doc
 * @return
 * @throws TransformerException
 */
public static String docToString(Document doc) throws TransformerException {
    TransformerFactory tf = TransformerFactory.newInstance();
    Transformer transformer = tf.newTransformer();
    transformer.setOutputProperty("encoding", doc.getXMLEncoding());
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    // 此处代码 和JDK本身的dom稍有不同
    transformer.transform(new DocumentSource(doc), new StreamResult(bos));
    return bos.toString();
}

/**
 * xml文件转Document 有时该方法未必能用， 建议使用stringToDoc将文件读成string后再转
 * 
 * @param file
 * @return
 * @throws DocumentException
 * @throws FileNotFoundException
 */
public static Document fileToDoc(File file) throws DocumentException,
        FileNotFoundException {
    SAXReader reader = new SAXReader();
    Document doc = reader.read(file);
    doc.normalize();
    return doc;
}

/**
 * xml文件转Document 有时该方法未必能用， 建议使用stringToDoc将文件读成string后再转
 * 
 * @param is
 * @return
 * @throws DocumentException
 */
public static Document fileToDoc(InputStream is) throws DocumentException {
    SAXReader reader = new SAXReader();
    Document doc = reader.read(is);
    doc.normalize();
    return doc;
}

/**
 * 字符串内容转换成Document对象
 * 
 * @param xmlStr
 * @return
 * @throws DocumentException
 */
public static Document stringToDoc(String xmlContent) throws DocumentException {
    Document doc = DocumentHelper.parseText(xmlContent);
    return doc;
}

/**
 * 将xmlStr格式化输出到目标文件
 * 
 * @param doc
 * @param targetFile
 * @throws IOException
 */
public static void formatToXMLFile(Document doc, File targetFile)
        throws IOException {
    OutputFormat outformat = OutputFormat.createPrettyPrint();
    // xml自身的编码
    outformat.setEncoding(doc.getXMLEncoding());
    outformat.setIndent(true);

    // 将xmlStr输出到目标路径，使用xml文件的头文件编码
    OutputStream out = new FileOutputStream(targetFile);
    XMLWriter writer = new XMLWriter(out, outformat);
    writer.write(doc);
    writer.flush();
}

/**
 * 将xmlContent格式化输出到目标文件
 * 
 * @param xmlContent
 * @param targetFile
 * @throws TransformerException
 * @throws IOException
 * @throws SAXException
 * @throws ParserConfigurationException
 * @throws DocumentException
 */
public static void formatToXMLFile(String xmlContent, File targetFile)
        throws TransformerException, ParserConfigurationException,
        SAXException, IOException, DocumentException {
    Document doc = stringToDoc(xmlContent);
    formatToXMLFile(doc, targetFile);
}

/**
 * 将xml文件格式化输出到目标文件
 * 
 * @param srcFile
 *            xml源文件
 * @param targetFile
 *            格式化输出xml文件
 * @throws TransformerException
 * @throws IOException
 * @throws SAXException
 * @throws ParserConfigurationException
 * @throws DocumentException
 */
public static void formatToXMLFile(File srcFile, File targetFile)
        throws TransformerException, ParserConfigurationException,
        SAXException, IOException, DocumentException {
    Document doc = fileToDoc(srcFile);
    formatToXMLFile(doc, targetFile);
}

/**
 * 打印Document的结点基本信息
 * 
 * @param doc
 */
public static void printNode(Document doc) {
    Element root = doc.getRootElement();
    printRecursive(root);

}

/**
 * 递归打印结点信息
 * 
 * @param element
 */
private static void printRecursive(Element element) {

    // 首先获取当前节点的所有属性节点
    Iterator<Attribute> iter = element.attributeIterator();
    // 遍历属性节点
    Attribute attribute = null;
    while (iter.hasNext()) {
        attribute = (Attribute) iter.next();
        System.out.println("结点" + element.getName() + "--》属性"
                + attribute.getName() + ":" + attribute.getValue());
    }
    iter = element.elementIterator();
    Element temp = null;
    while (iter.hasNext()) {
        temp = (Element) iter.next();
        System.out.println("------------------------");
        System.out.println(temp.getName());
        System.out.println("值--》" + temp.getTextTrim());

        printRecursive(temp);
    }
}

/**
 * Dom4j 的Dom的生成： 直接按照从上到下的结点顺序addElement
 * 
 * @return
 * @throws IOException
 */
public static void createDocXML() throws IOException {
    Document doc = DocumentHelper.createDocument();
    doc.addComment("根结点注释");
    Element root = doc.addElement("root");

    Element rootChildA = root.addElement("rootChildA");
    rootChildA.setText("rootChildA孩子结点");
    rootChildA.addAttribute("name", "姓名");
    rootChildA.addAttribute("age", "年龄");
    rootChildA.addAttribute("height", "身高");

    Element rootChildB = root.addElement("rootChildB");
    // CDATA 指的是不应由 XML 解析器进行解析的文本数据
    rootChildB.setText("<![CDATA[rootChildB孩子结点]]>");

    File file = new File("D:/dom4j.xml");
    OutputStream os = new FileOutputStream(file);

    OutputFormat outformat = OutputFormat.createPrettyPrint();
    // xml自身的编码
    outformat.setEncoding(doc.getXMLEncoding());
    outformat.setIndent(true);

    XMLWriter writer = new XMLWriter(os, outformat);
    // 是否转义字符，默认true转义，false表示不转义
    writer.setEscapeText(false);
    writer.write(doc);
    writer.flush();
}

/**
 * Document对象格式化成字符串
 * 
 * @param doc
 * @return
 * @throws IOException
 */
public static String formatDocToString(Document doc) throws IOException {
    OutputFormat outformat = OutputFormat.createPrettyPrint();
    // xml自身的编码
    outformat.setEncoding(doc.getXMLEncoding());
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    XMLWriter writer = new XMLWriter(bos, outformat);
    writer.write(doc);
    writer.flush();
    return bos.toString();
}

/**
 * Document对象转成xml字符串
 * 
 * @param doc
 * @return
 */
public static String docAsXML(Document doc) {
    return doc.asXML();
}

public static void removeNode() {

}

public static void updateNode() {

}

public static void main(String[] args) throws Exception {

// InputStream is = Dom4jUtils.class
// .getResourceAsStream(“/com/linzl/cn/xml/xmlRead.xml”);
//
// is = Dom4jUtils.class.getClassLoader().getResourceAsStream(
// “com/linzl/cn/xml/xmlRead.xml”);
// Document doc = fileToDoc(is);
// printNode(doc);
//
// createDocXML();
String file =”F:\anjianOAdoc\oadoc\taitan\missive\3189-apacheBase64.xml”;
String target =”F:\anjianOAdoc\oadoc\taitan\missive\757-副本.xml”;
String xmlStr = FileUtils.readFileToString(new File(file));

    formatToXMLFile(xmlStr, new File(target));
}

}