java dom 对xml的操作

package com.linzl.cn.xml;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;

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

import org.w3c.dom.CDATASection;
import org.w3c.dom.Comment;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

/**
* w3c xml 例子 详细方法可见JDK1.6的API 文档驱动： 缺点： 在处理DOM的时候，我们需要读入整个的XML文档， 然后在内存中创建DOM树，
* 当xml非常大的时候，很消耗内存 超过10M不适用 优点： 形成树结构，代码易编写;解析过程树结构在内存中，方便修改
*
* @author linzl 最后修改时间：2014年10月10日
*/
public class DomUtils {
/**
* 创建DocumentBuilder
*
* @return
* @throws ParserConfigurationException
*/
private static DocumentBuilder createBuilder()
throws ParserConfigurationException {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setNamespaceAware(true); // never forget this!
DocumentBuilder builder = factory.newDocumentBuilder();
return builder;
}

/**
 * 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();
    // 设置编码
    transformer
            .setOutputProperty(OutputKeys.ENCODING, doc.getXmlEncoding());
    // 设置格式换行
    transformer.setOutputProperty(OutputKeys.INDENT, "yes");
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    transformer.transform(new DOMSource(doc), new StreamResult(bos));
    return bos.toString();
}

/**
 * xml文件转Document
 * 
 * @param file
 * @return
 * @throws SAXException
 * @throws IOException
 * @throws ParserConfigurationException
 */
public static Document fileToDoc(File file)
        throws ParserConfigurationException, SAXException, IOException {
    // 创建DocumentBuilder
    DocumentBuilder builder = createBuilder();
    // 创建Document
    Document doc = builder.parse(file);
    doc.normalize();
    return doc;
}

/**
 * xml文件转Document
 * 
 * @param is
 * @return
 * @throws SAXException
 * @throws IOException
 * @throws ParserConfigurationException
 */
public static Document fileToDoc(InputStream is)
        throws ParserConfigurationException, SAXException, IOException {
    // 创建DocumentBuilder
    DocumentBuilder builder = createBuilder();
    // 创建Document
    Document doc = builder.parse(is);
    doc.normalize();
    return doc;
}

/**
 * 字符串内容转换成Document对象
 * 
 * @param xmlStr
 * @return
 * @throws ParserConfigurationException
 * @throws SAXException
 * @throws IOException
 */
public static Document stringToDoc(String xmlStr)
        throws ParserConfigurationException, SAXException, IOException {
    DocumentBuilder builder = createBuilder();

    StringReader sr = new StringReader(xmlStr);
    InputSource is = new InputSource(sr);
    Document doc = builder.parse(is);
    doc.normalize();
    return doc;
}

/**
 * 将Document格式化到目标文件
 * 
 * @param doc
 * @param targetFile
 * @throws IOException
 * @throws TransformerException
 */
public static void formatToXMLFile(Document doc, File targetFile)
        throws TransformerException, IOException {
    TransformerFactory tf = TransformerFactory.newInstance();
    Transformer transformer = tf.newTransformer();
    // 设置编码
    transformer
            .setOutputProperty(OutputKeys.ENCODING, doc.getXmlEncoding());
    // 设置格式换行
    transformer.setOutputProperty(OutputKeys.INDENT, "yes");
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    transformer.transform(new DOMSource(doc), new StreamResult(bos));

    // 将xmlStr输出到目标路径，使用xml文件的头文件编码
    FileOutputStream fos = new FileOutputStream(targetFile);
    bos.writeTo(fos);
}

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

/**
 * 将xml文件格式化到目标文件
 * 
 * @param srcFile
 *            xml源文件
 * @param targetFile
 *            格式化输出xml文件
 * @throws TransformerException
 * @throws IOException
 * @throws SAXException
 * @throws ParserConfigurationException
 */
public static void formatToXMLFile(File srcFile, File targetFile)
        throws TransformerException, ParserConfigurationException,
        SAXException, IOException {
    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.getDocumentElement();
    printRecursive(root);
}

/**
 * 递归打印结点信息
 * 
 * @param element
 */
private static void printRecursive(Node element) {
    int length = 0;
    Node node = null;
    NamedNodeMap nnm = element.getAttributes();
    if (nnm != null || (length = nnm.getLength()) > 0) {
        for (int attrIndex = 0; attrIndex < length; attrIndex++) {
            node = nnm.item(attrIndex);
            System.err.println("属性名称：" + node.getNodeName() + " -->属性值："
                    + node.getNodeValue());
        }
    }

    // NodeList nodeList = element.getElementsByTagName("exoa-config");
    NodeList nodeList = element.getChildNodes();
    if (nodeList != null && (length = nodeList.getLength()) > 0) {
        for (int index = 0; index < length; index++) {
            node = nodeList.item(index);
            // dom会将换行和注释都做为document的结点，所以去除这些非element结点
            if (node != null && node.getNodeType() != Node.ELEMENT_NODE) {
                continue;
            }
            System.err.println("结点名称 -->" + node.getNodeName().trim());
            // getTextContent将所有该结点下所有结点的纯文本值
            System.err.println("结点下所有结点的值 -->"
                    + node.getTextContent().trim());
            // 当该结点下只有一个文本结点时，效果等同getTextContent，否则根据JDK中对于Node的解释，getNodeValue是取不到值的
            Node child = node.getFirstChild();
            if (child != null) {
                System.err.println("结点值 -->" + child.getNodeValue().trim());
            }

            printRecursive(node);
        }
    }
}

/**
 * w3c Dom的生成： 直接按照从上到下的结点顺序创建，然后append在父结点下
 * 
 * @throws ParserConfigurationException
 * @throws TransformerException
 */
public static void createDocXML() throws ParserConfigurationException,
        TransformerException {
    Document doc = createBuilder().newDocument();
    doc.setXmlStandalone(true);
    // 根结点
    Element root = doc.createElement("root");
    // 注释内容
    Comment comment = doc.createComment("根结点注释");
    root.appendChild(comment);

    // 生成第一个孩子结点
    Element rootChildA = doc.createElement("rootChildA");
    rootChildA.setTextContent("rootChildA孩子结点");
    rootChildA.setAttribute("name", "姓名");
    rootChildA.setAttribute("age", "年龄");
    rootChildA.setAttribute("height", "身高");
    root.appendChild(rootChildA);

    Element rootChildB = doc.createElement("rootChildB");
    CDATASection cdata = doc.createCDATASection("rootChildB孩子结点");
    rootChildB.appendChild(cdata);
    root.appendChild(rootChildB);

    doc.appendChild(root);

    // 规范xml文件，并输出到目标文件
    TransformerFactory tf = TransformerFactory.newInstance();
    Transformer transformer = tf.newTransformer();
    // 设置格式换行
    transformer.setOutputProperty(OutputKeys.INDENT, "yes");
    DOMSource dos = new DOMSource(doc);
    File file = new File("D://w3c.xml");
    StreamResult result = new StreamResult(file);
    transformer.transform(dos, result);
}

public boolean removeNode() {
    return true;
}

public boolean updateNode() {
    return true;
}

public static void main(String[] args) throws Exception {
    // InputStream is = DomUtils.class
    // .getResourceAsStream("/com/linzl/cn/xml/xmlRead.xml");
    //
    // is = DomUtils.class.getClassLoader().getResourceAsStream(
    // "com/linzl/cn/xml/xmlRead.xml");
    // is = new
    // FileInputStream("F:\\anjianOAdoc\\oadoc\\taitan\\info\\757.xml");
    // Document doc = fileToDoc(is);
    // printNode(doc);
    // createDocXML();

    String xmlStr = "F:\\anjianOAdoc\\oadoc\\taitan\\info\\757.xml";
    String target = "F:\\anjianOAdoc\\oadoc\\taitan\\missive\\757-副本.xml";
    formatToXMLFile(new File(xmlStr), new File(target));
}

}