Java递归遍历XML所有元素

Java递归遍历XML所有元素

做一个递归遍历XML的例子，为更为复杂的解析工作做基础。

目标：遍历所有的元素节点，并且取出来其中的值，结果打印到控制台。

源代码如下：
本程序依赖DOM4j包。

import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.DocumentException;
import org.dom4j.Element;

import java.util.*;

/**
* Created by IntelliJ IDEA.<br>
* <b>User</b>: leizhimin<br>
* <b>Date</b>: 2008-4-14 14:02:12<br>
* <b>Note</b>: Java递归遍历XML所有元素
*/
public class XmlTest {

// private static Map<String, String> xmlmap = new HashMap<String, String>();
//存储xml元素信息的容器
private static List<Leaf> elemList = new ArrayList<Leaf>();

//要测试的xml对象
private static String srcXml = "<?xml version=\"1.0\" encoding=\"GBK\"?>\n" +
"<doc>\n" +
" <person>\n" +
" <name>某人</name>\n" +
" <adds> \n" +
" <add ID=\"10002\">\n" +
" <BS>10002</BS>\n" +
" <note>西安市太白路</note>\n" +
" </add>\n" +
" <add ID=\"\">\n" +
" <BS>10002</BS>\n" +
" <note>空ID节点啊</note>\n" +
" </add>\n" +
" <add>\n" +
" <BS>10002</BS>\n" +
" <note>空ID节点啊</note>\n" +
" </add>\n" +
"\t\t\t<add ID=\"10001\">\n" +
"\t\t\t\t<BS xmlns=\"10001\"/>\n" +
" <note>西安市太白路2</note>\n" +
" </add>\n" +
"\t\t</adds>\n" +
" </person>\n" +
" <other>\n" +
" <name ID=\"HEHE\">ASDF</name>\n" +
" </other>\n" +
"</doc>";

public static void main(String args[]) throws DocumentException {
XmlTest test = new XmlTest();
Element root = test.getRootElement();
test.getElementList(root);
String x = test.getListString(elemList);

System.out.println("-----------原xml内容------------");
System.out.println(srcXml);
System.out.println("-----------解析结果------------");
System.out.println(x);

}

/**
* 获取根元素
*
* @return
* @throws DocumentException
*/
public Element getRootElement() throws DocumentException {
Document srcdoc = DocumentHelper.parseText(srcXml);
Element elem = srcdoc.getRootElement();
return elem;
}

/**
* 递归遍历方法
*
* @param element
*/
public void getElementList(Element element) {
List elements = element.elements();
if (elements.size() == 0) {
//没有子元素
String xpath = element.getPath();
String value = element.getTextTrim();
elemList.add(new Leaf(xpath, value));
} else {
//有子元素
for (Iterator it = elements.iterator(); it.hasNext();) {
Element elem = (Element) it.next();
//递归遍历
getElementList(elem);
}
}
}

public String getListString(List<Leaf> elemList) {
StringBuffer sb = new StringBuffer();
for (Iterator<Leaf> it = elemList.iterator(); it.hasNext();) {
Leaf leaf = it.next();
sb.append(leaf.getXpath()).append(" = ").append(leaf.getValue()).append("\n");
}
return sb.toString();
}
}

/**
* xml节点数据结构
*/
class Leaf {
private String xpath; //
private String value;

public Leaf(String xpath, String value) {
this.xpath = xpath;
this.value = value;
}

public String getXpath() {
return xpath;
}

public void setXpath(String xpath) {
this.xpath = xpath;
}

public String getValue() {
return value;
}

public void setValue(String value) {
this.value = value;
}
}

运行结果：

-----------原xml内容------------
<?xml version="1.0" encoding="GBK"?>
<doc>
<person>
<name>某人</name>
<adds>
<add ID="10002">
<BS>10002</BS>
<note>西安市太白路</note>
</add>
<add ID="">
<BS>10002</BS>
<note>空ID节点啊</note>
</add>
<add>
<BS>10002</BS>
<note>空ID节点啊</note>
</add>
<add ID="10001">
<BS xmlns="10001"/>
<note>西安市太白路2</note>
</add>
</adds>
</person>
<other>
<name ID="HEHE">ASDF</name>
</other>
</doc>
-----------解析结果------------
/doc/person/name = 某人
/doc/person/adds/add/BS = 10002
/doc/person/adds/add/note = 西安市太白路
/doc/person/adds/add/BS = 10002
/doc/person/adds/add/note = 空ID节点啊
/doc/person/adds/add/BS = 10002
/doc/person/adds/add/note = 空ID节点啊
/doc/person/adds/add/*[name()='BS'] =
/doc/person/adds/add/note = 西安市太白路2
/doc/other/name = ASDF

Process finished with exit code 0

可以发现，有很多xpath相同的值域。