Java 递归地从XML中删除空节点
我想从XML元素中删除空节点。 这个xml是由供应商生成的,我无法控制xml的生成。但是由于XML几乎没有空节点,我需要递归地删除这些空节点 这个xml是从OmeElement获取的,我使用[XMLUtils][1]从这个对象获取一个元素 示例XMLJava 递归地从XML中删除空节点,java,xml,xmlnode,Java,Xml,Xmlnode,我想从XML元素中删除空节点。 这个xml是由供应商生成的,我无法控制xml的生成。但是由于XML几乎没有空节点,我需要递归地删除这些空节点 这个xml是从OmeElement获取的,我使用[XMLUtils][1]从这个对象获取一个元素 示例XML <A> <B> <C> <C1> <C11>something</C11> <C12>something&l
<A>
<B>
<C>
<C1>
<C11>something</C11>
<C12>something</C12>
</C1>
</C>
<D>
<D1>
<D11>
<D111 operation="create">
<Node>something else</Node>
</D11>
</D11>
</D1>
<D2>
<D21>
</D21>
</D2>
</D>
</B>
</A>
问候Dheeraj Joshi在DOM的顶级元素上使用
getTextContent()
。若方法返回空字符串或null,则可以删除此节点,因为此节点和所有子节点均为空。如果方法getTextContent()
返回非空字符串,则对当前节点的每个子节点调用getTextContent
,依此类推。请参阅。这是可行的,只需先创建一个“深入”的递归函数,然后在“备份树”的过程中删除空节点,这将产生删除D21和D2的效果
public static void main(String[] args) throws Exception {
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
String input = "<A><B><C><C1><C11>something</C11><C12>something</C12></C1></C><D><D1><D11><D111 operation=\"create\"><Node>something else</Node></D111></D11></D1><D2><D21></D21></D2></D></B></A>";
Document document = builder.parse(new InputSource(new StringReader(
input)));
removeNodes(document);
Transformer transformer = TransformerFactory.newInstance()
.newTransformer();
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
StreamResult result = new StreamResult(new StringWriter());
transformer.transform(new DOMSource(document), result);
System.out.println(result.getWriter().toString());
}
public static void removeNodes(Node node) {
NodeList list = node.getChildNodes();
for (int i = 0; i < list.getLength(); i++) {
removeNodes(list.item(i));
}
boolean emptyElement = node.getNodeType() == Node.ELEMENT_NODE
&& node.getChildNodes().getLength() == 0;
boolean emptyText = node.getNodeType() == Node.TEXT_NODE
&& node.getNodeValue().trim().isEmpty();
if (emptyElement || emptyText) {
node.getParentNode().removeChild(node);
}
}
publicstaticvoidmain(字符串[]args)引发异常{
DocumentBuilder=DocumentBuilderFactory.newInstance().newDocumentBuilder();
String input=“somethingsomethingsomethingsother”;
Document Document=builder.parse(新的InputSource(新的StringReader(
输入),;
移除节点(文件);
Transformer Transformer=TransformerFactory.newInstance()
.新变压器();
transformer.setOutputProperty(OutputKeys.INDENT,“是”);
StreamResult=新的StreamResult(新的StringWriter());
transform(新的DOMSource(文档)、result);
System.out.println(result.getWriter().toString());
}
公共静态void removeNodes(节点){
NodeList list=node.getChildNodes();
对于(int i=0;i
输出
<A>
<B>
<C>
<C1>
<C11>something</C11>
<C12>something</C12>
</C1>
</C>
<D>
<D1>
<D11>
<D111 operation="create">
<Node>something else</Node>
</D111>
</D11>
</D1>
</D>
</B>
</A>
某物
某物
别的
我没有足够的代表对@Adam的解决方案发表评论,但我遇到了一个问题,在删除节点后,该节点的最后一个同级节点被移动到索引零,导致它无法完全删除空元素。修复方法是使用一个列表来保存我们要递归调用以删除的所有节点
此外,还有一个bug删除了具有属性的空元素
这两个问题的解决办法:
public static void removeEmptyNodes(Node node) {
NodeList list = node.getChildNodes();
List<Node> nodesToRecursivelyCall = new LinkedList();
for (int i = 0; i < list.getLength(); i++) {
nodesToRecursivelyCall.add(list.item(i));
}
for(Node tempNode : nodesToRecursivelyCall) {
removeEmptyNodes(tempNode);
}
boolean emptyElement = node.getNodeType() == Node.ELEMENT_NODE
&& node.getChildNodes().getLength() == 0;
boolean emptyText = node.getNodeType() == Node.TEXT_NODE
&& node.getNodeValue().trim().isEmpty();
if (emptyElement || emptyText) {
if(!node.hasAttributes()) {
node.getParentNode().removeChild(node);
}
}
}
公共静态void removemptynodes(节点){
NodeList list=node.getChildNodes();
List nodesToRecursivelyCall=新建LinkedList();
对于(int i=0;i
公共类RemoveEmptElement{
公共静态void main(字符串[]args){
ReadFile ReadFile=新的ReadFile();
字符串strXml=readFile.readFileFromPath(新文件(“sampleXml4.xml”);
removeMpRTElement元素empRTElement=新的removeMpRTElement();
DocumentBuilder dBuilder=null;
单据单据=空;
试一试{
dBuilder=DocumentBuilderFactory.newInstance().newDocumentBuilder();
doc=dBuilder.parse(新的ByteArrayInputStream(strXml.getBytes());
elementemptelement.getEmptyNodes(doc);
TransformerFactory tf=TransformerFactory.newInstance();
变压器变压器=tf.新变压器();
StreamResult=新的StreamResult(新的StringWriter());
转换(新的DOMSource(doc),结果);
System.out.println(result.getWriter().toString());
}捕获(例外e){
e、 printStackTrace();
}
}
私有无效getEmptyNodes(文档文档){
试一试{
XPathFactory=XPathFactory.newInstance();
XPath=factory.newXPath();
XPathExpression expr=xpath.compile(“//*[非(*)]”;
Object resultNS=expr.evaluate(doc,XPathConstants.NODESET);
节点列表节点=(节点列表)结果;
对于(int i=0;i<A>
<B>
<C>
<C1>
<C11>something</C11>
<C12>something</C12>
</C1>
</C>
<D>
<D1>
<D11>
<D111 operation="create">
<Node>something else</Node>
</D111>
</D11>
</D1>
</D>
</B>
</A>
public static void removeEmptyNodes(Node node) {
NodeList list = node.getChildNodes();
List<Node> nodesToRecursivelyCall = new LinkedList();
for (int i = 0; i < list.getLength(); i++) {
nodesToRecursivelyCall.add(list.item(i));
}
for(Node tempNode : nodesToRecursivelyCall) {
removeEmptyNodes(tempNode);
}
boolean emptyElement = node.getNodeType() == Node.ELEMENT_NODE
&& node.getChildNodes().getLength() == 0;
boolean emptyText = node.getNodeType() == Node.TEXT_NODE
&& node.getNodeValue().trim().isEmpty();
if (emptyElement || emptyText) {
if(!node.hasAttributes()) {
node.getParentNode().removeChild(node);
}
}
}
public class RemoveEmprtElement {
public static void main(String[] args) {
ReadFile readFile =new ReadFile();
String strXml=readFile.readFileFromPath(new File("sampleXml4.xml"));
RemoveEmprtElement elementEmprtElement=new RemoveEmprtElement();
DocumentBuilder dBuilder = null;
Document doc = null;
try {
dBuilder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
doc = dBuilder.parse(new ByteArrayInputStream(strXml.getBytes()));
elementEmprtElement.getEmptyNodes(doc);
TransformerFactory tf = TransformerFactory.newInstance();
Transformer trans = tf.newTransformer();
StreamResult result = new StreamResult(new StringWriter());
trans.transform(new DOMSource(doc), result);
System.out.println(result.getWriter().toString());
}catch(Exception e) {
e.printStackTrace();
}
}
private void getEmptyNodes(Document doc){
try {
XPathFactory factory = XPathFactory.newInstance();
XPath xpath = factory.newXPath();
XPathExpression expr = xpath.compile("//*[not(*)]");
Object resultNS = expr.evaluate(doc, XPathConstants.NODESET);
NodeList nodes = (NodeList) resultNS;
for(int i =0 ; i < nodes.getLength() ; i++){
Node node = nodes.item(i);
boolean emptyElement = node.getNodeType() == Node.ELEMENT_NODE
&& node.getChildNodes().getLength() == 0;
boolean emptyText = node.getNodeType() == Node.TEXT_NODE
&& node.getNodeValue().trim().isEmpty();
if (emptyElement || emptyText) {
xmlNodeRemove(doc,findPath(node));
getEmptyNodes(doc);
}
}
}catch(Exception e) {
e.printStackTrace();
}
}
private void xmlNodeRemove(Document doc,String xmlNodeLocation){
try {
XPathFactory factory = XPathFactory.newInstance();
XPath xpath = factory.newXPath();
XPathExpression expr = xpath.compile(xmlNodeLocation);
Object resultNS = expr.evaluate(doc, XPathConstants.NODESET);
NodeList nodes = (NodeList) resultNS;
Node node =nodes.item(0);
if(node!=null && node.getParentNode()!=null && node.getParentNode().hasChildNodes()){
node.getParentNode().removeChild(node);
}
}catch(Exception e) {
e.printStackTrace();
}
}
private String findPath(Node n) {
String path="";
if(n==null){
return path;
}else if(n.getNodeName().equals("#document")){
return "";
}
else{
path=n.getNodeName();
path=findPath(n.getParentNode())+"/"+path;
}
return path;
}
}
Pattern emptyValueTag = Pattern.compile("\\s*<\\w+/>");
Pattern emptyTagMultiLine = Pattern.compile("\\s*<\\w+>\n*\\s*</\\w+>");
xml = emptyValueTag.matcher(xml).replaceAll("");
while (xml.length() != (xml = emptyTagMultiLine.matcher(xml).replaceAll("")).length()) {
}
return xml;