XML转Dom的模拟实现

最近项目空闲，开始研究起一些细节的东西，在和PM争论dom4j的时候出现了些分歧，于是想自己实现一下dom的实现过程。

首先自己先定义了一个Node类，用来保存每一个dom的节点。Node类里有每一个节点的信息：tag, 父节点，子节点，及节点之间的内容（这次模拟没有加入tag里的属性识别）。

package apple.document; import java.util.List; /* * author Apple Wu */ public class Node { private Node parent; private List<Node> child; private String tagName; private String text; public Node getParent() { return parent; } public void setParent(Node parent) { this.parent = parent; } public List<Node> getChild() { return child; } public void setChild(List<Node> child) { this.child = child; } public String getTagName() { return tagName; } public void setTagName(String tagName) { this.tagName = tagName; } public String getText() { return text; } public void setText(String text) { this.text = text; } }

下一个类是Document类，用来把字符转成DOM. 该类用了模式匹配来查找<**>这样的tag,并把每个tag用Node对象封装。

package apple.document; import java.util.ArrayList; import java.util.List; import java.util.regex.Matcher; import java.util.regex.Pattern; /* * @author = Apple Wu * 2011/05/14 */ public class Document { public static String start_reg = "//<//w+//>"; //public static String end_reg = "//</w+//>"; public static Pattern startPatten = Pattern.compile(start_reg); //public static Pattern endPatten = Pattern.compile(end_reg); public Document(){} public static Node parseStringToDom(String string){ Node node = new Node(); List<Node> childern = new ArrayList<Node>(); Matcher startMatcher = startPatten.matcher(string); int start; int end; Node childNode = null; if(startMatcher.find()){ start = startMatcher.start(); end = startMatcher.end(); childNode = new Node(); childNode.setTagName(string.substring(1, end-1)); childern.add(childNode); string = string.substring(end); } String endReg = "//<///"+childNode.getTagName() +"//>"; Pattern endPatten = Pattern.compile(endReg); Matcher endMatcher = endPatten.matcher(string); if(endMatcher.find()){ start = endMatcher.start(); end = endMatcher.end(); childNode.setText(string.substring(0, start)); startMatcher = startPatten.matcher(childNode.getText()); if(startMatcher.find()){ childNode.setChild(new ArrayList<Node>()); childNode.getChild().add(parseStringToDom(childNode.getText()).getChild().get(0)); } if(string.length() > end){ childern.add(parseStringToDom(string.substring(end)).getChild().get(0)); } node.setChild(childern); } return node; } public static void main(String[] args){ Node root =parseStringToDom("<abe><c><d><f>dfdf</f></d></c></abe><acd><e>ddd</e></acd>"); System.out.println("firstElementTag:"+root.getChild().get(0).getTagName()); System.out.println("firstElementTag->firstElementTag:"+root.getChild().get(0).getChild().get(0).getTagName()); System.out.println("firstElementTag->firstElementTag->firstElementTag:"+root.getChild().get(0).getChild().get(0).getChild().get(0).getTagName()); System.out.println("secendElementTag:"+root.getChild().get(1).getTagName()); System.out.println("secendElementTag->firstElementTag:"+root.getChild().get(1).getChild().get(0).getTagName()); } }

输出结果为：

firstElementTag:abe
firstElementTag->firstElementTag:c
firstElementTag->firstElementTag->firstElementTag:d
secendElementTag:acd
secendElementTag->firstElementTag:e