使用DocumentBuilderFactory解析和深度优先遍历XML DOM全部节点

喜欢ヅ旅行 2022-03-08 20:08 177阅读 0赞

**假设有如下xml dom,对其进行深度优先遍历解析**

<?xml version='1.0' encoding='UTF-8' ?>
    <schools>
    <school id="huanggang">
    	<grade id="1">
    		<classes>
    			<class id="1">
    				<students>
    					<student id="1" name="zhangsan"></student>
    					<student id="2" name="lisi"></student>
    					<student id="3" name="wangwu"></student>
    				</students>
    			</class>
    		</classes>
    	</grade>
    	<grade id="2">
    		<classes>
    			<class id="1">
    				<students>
    					<student id="1" name="zhangsan2"/>
    					<student id="2" name="lisi2"/>
    					<student id="3" name="wangwu2"/>
    				</students>
    			</class>
    		</classes>
    	</grade>
    </school>
    <school id="qifu">
    	<grade id="1">
    		<classes>
    			<class id="1">
    				<students>
    					<student id="1" name="zhangsan3"></student>
    					<student id="2" name="lisi3"></student>
    					<student id="3" name="wangwu3"></student>
    				</students>
    			</class>
    		</classes>
    	</grade>
    	<grade id="2">
    		<classes>
    			<class id="1">
    				<students>
    					<student id="1" name="zhangsan4"/>
    					<student id="2" name="lisi4"/>
    					<student id="3" name="wangwu4"/>
    				</students>
    			</class>
    		</classes>
    	</grade>
    </school>
    </schools>

**遍历解析**

import javax.xml.parsers.DocumentBuilder;
    import javax.xml.parsers.DocumentBuilderFactory;
    import javax.xml.transform.Transformer;
    import javax.xml.transform.TransformerFactory;
    import javax.xml.transform.dom.DOMSource;
    import javax.xml.transform.stream.StreamResult;
    
    import org.w3c.dom.Document;
    import org.w3c.dom.Element;
    import org.w3c.dom.Node;
    import org.w3c.dom.NodeList;
    
    public class ParseStudents { 
    
    	public static void main(String[] args) throws Exception
    	{ 
    		String filePath = "D:\\students.xml";
            DocumentBuilderFactory docFactory = DocumentBuilderFactory.newInstance();
            
            DocumentBuilder docBuilder = docFactory.newDocumentBuilder();
            Document doc = docBuilder.parse(filePath);
            Element root = doc.getDocumentElement();
            NodeList nodeList = root.getChildNodes();
            
            if (null != nodeList) { 
            	int i=0;
            	//开始遍历school 
            	while(i<nodeList.getLength())
            	{ 
            		//school 
            		Node node = nodeList.item(i);
            		//期间还会遍历出Text节点，而我们只关注element节点
                    if(node.getNodeType()==Node.ELEMENT_NODE)
                    { 
                    	int layer_level = 1;
                    	//第一个school
                    	printnodeinfo((Element)node);
                    	Node c_node = node.getFirstChild();
                    	//判断节点是否存在
                    	while(c_node!=null)
                    	{ 
                    		if(c_node.getNodeType()==Node.ELEMENT_NODE)
                    		{ 
                    			Element element_childnode  = (Element)c_node;
                    			printnodeinfo(element_childnode);
                    			//查看是否存在子节点.如果存在，输出当前节点结果，然后继续找子节点，如果没有子节点，则遍历兄弟节点
                    			if(element_childnode.hasChildNodes())
                    			{ 
                    				c_node = element_childnode.getFirstChild();
                    				layer_level = layer_level + 1;
                    				continue;
                    			}
                    			//没有子节点，有兄弟节点，因为Text节点和Element节点间隔出现，而我们只关心Element节点，所有有两次getNextSibling()
                    			if(element_childnode.getNextSibling().getNextSibling()!=null)
                    			{ 
                    				c_node = element_childnode.getNextSibling().getNextSibling();
                    				continue;
                    			}
                    			//没有子节点，又没有兄弟节点，则返回上一层节点,因为上一层节点已经遍历过了，所以找它的兄弟节点
                    			while(layer_level>1)
                    			{ 
                    				layer_level = layer_level - 1;
                    				c_node = c_node.getParentNode();
                    				//如果有兄弟节点则继续兄弟节点，否则又再往上一层
                    				if(c_node.getNextSibling().getNextSibling()!=null)
                    				{ 
                    					c_node = c_node.getNextSibling();
                    					break;
                    				}
                    			}
                    		}
                    		c_node = c_node.getNextSibling();
                    	}
                    }
                    else if(node.getNodeType()==Node.COMMENT_NODE)
                    { 	
                    	//直接删除注释节点
                    	root.removeChild(node);
                    	continue;
                    }
                    i++;
            	}
            }
            //创建新的xml dom
    // TransformerFactory transformerFactory = TransformerFactory.newInstance();
    // Transformer transformer = transformerFactory.newTransformer();
    // transformer.transform(new DOMSource(doc), new StreamResult("D:\\newstudents.xml"));
    	}
    
    	public static void printnodeinfo(Element element_node)
    	{ 
    		System.out.println("tagname:"+element_node.getTagName()+"\tid:"+element_node.getAttribute("id")+"\tname:"+element_node.getAttribute("name"));
    	}
    }

**输出结果，也为遍历顺序**

tagname:school	id:huanggang	name:
    tagname:grade	id:1	name:
    tagname:classes	id:	name:
    tagname:class	id:1	name:
    tagname:students	id:	name:
    tagname:student	id:1	name:zhangsan
    tagname:student	id:2	name:lisi
    tagname:student	id:3	name:wangwu
    tagname:grade	id:2	name:
    tagname:classes	id:	name:
    tagname:class	id:1	name:
    tagname:students	id:	name:
    tagname:student	id:1	name:zhangsan2
    tagname:student	id:2	name:lisi2
    tagname:student	id:3	name:wangwu2
    tagname:school	id:qifu	name:
    tagname:grade	id:1	name:
    tagname:classes	id:	name:
    tagname:class	id:1	name:
    tagname:students	id:	name:
    tagname:student	id:1	name:zhangsan3
    tagname:student	id:2	name:lisi3
    tagname:student	id:3	name:wangwu3
    tagname:grade	id:2	name:
    tagname:classes	id:	name:
    tagname:class	id:1	name:
    tagname:students	id:	name:
    tagname:student	id:1	name:zhangsan4
    tagname:student	id:2	name:lisi4
    tagname:student	id:3	name:wangwu4