xml的解析与创建——bing到youdao导入文件的转换

时间：2024-01-14 18:37:44

首先是为了解决一个问题：如何将必应单词本中记录的单词转入到有道词典中去。实际上，必应词典可以导出xml文件，但是该文件有道词典无法解析。这里涉及到xml的解析和创建了。

代码如下：

import java.io.File;

import java.io.FileNotFoundException;

import java.io.FileOutputStream;

import java.io.PrintWriter;

import java.text.SimpleDateFormat;

import java.util.Date;

import javax.xml.parsers.DocumentBuilder;

import javax.xml.parsers.DocumentBuilderFactory;

import javax.xml.transform.OutputKeys;

import javax.xml.transform.Transformer;

import javax.xml.transform.TransformerConfigurationException;

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.Document;

import org.w3c.dom.Element;

import org.w3c.dom.Node;

import org.w3c.dom.NodeList;

public class bing2youdao {

	private  String bingPath;//input filepath

	private String time;// filtering time (Default:current time)

	private String tag=null;

	final static String youdao="youdao.xml";//output file

	public bing2youdao(String filename){

		bingPath=filename;

		SimpleDateFormat sdf=new SimpleDateFormat("yyyy-MM-dd");

		time=sdf.format(new Date());

	}

	public bing2youdao(String filename,String d){

		bingPath=filename;

		time=d;

	}

	public bing2youdao(String filename,String d,String t){

		this(filename,d);

		tag=t;

	}

	public void run(){

		Node word=null;

		Node detail=null;

		String danci=null;

		String pronunciation=null;

		String definition=null;

		String data=null;

		try {

            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();

            DocumentBuilder builder = factory.newDocumentBuilder();

            Document  document = builder.newDocument();

			Element wordbook = document.createElement("wordbook");   //创建根节点

            document.appendChild(wordbook);

			DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();

			DocumentBuilder db = dbf.newDocumentBuilder();

			Document dm = db.parse(new File(bingPath));//获得根元素

			Element bingWord = dm.getDocumentElement();

			NodeList wordList= bingWord.getChildNodes().item(1).getChildNodes();

			for (int i = 1; i < wordList.getLength(); i++) {

				   word = wordList.item(i);

			       NodeList nodeDetail = word.getChildNodes();

			       for (int j = 0; j < nodeDetail.getLength(); j++) {

			        	detail = nodeDetail.item(j);

			        	if ("Eng".equals(detail.getNodeName()))

			        		  danci=detail.getTextContent();

			            else if ("Phonetic".equals(detail.getNodeName()))

			            	  pronunciation=detail.getTextContent();

			            else if ("Defi".equals(detail.getNodeName()))

			            	  definition=detail.getTextContent();

			            else if("Date".equals(detail.getNodeName()))

			            	  data=detail.getTextContent();

			       }

			       //If the recorded time is after the filtering time than output it

			       if(timeDecision(data)&&nodeDetail.getLength()>0){

			    	   Element item= document.createElement("item"); 

			    	   Element vacbulary= document.createElement("word");

			    	   vacbulary.appendChild(document.createTextNode(danci));

			    	   item.appendChild(vacbulary); 

			    	   Element trans = document.createElement("trans");

			    	   trans.appendChild(document.createTextNode(definition));

			    	   item.appendChild(trans); 

			    	   Element phonetic = document.createElement("phonetic");

			    	   phonetic.appendChild(document.createTextNode(pronunciation));

			    	   item.appendChild(phonetic);

			    	   Element tags = document.createElement("tags");

			    	   if(tag!=null)

			    	        tags.appendChild(document.createTextNode(tag));

			    	   item.appendChild(tags);

			    	   Element progress = document.createElement("progress");

			    	   progress.appendChild(document.createTextNode(1+""));//复习进度，默认为1,可调为-1表示不加入复习计划

			    	   item.appendChild(progress); 

			    	   wordbook.appendChild(item);

			       }

			}

			try {

			    TransformerFactory tf = TransformerFactory.newInstance();

	            Transformer transformer = tf.newTransformer();

	            DOMSource source = new DOMSource(document);

	            transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");

	            transformer.setOutputProperty(OutputKeys.INDENT, "yes");

	            PrintWriter pw = new PrintWriter(new FileOutputStream(youdao));

	            StreamResult result = new StreamResult(pw);

	            transformer.transform(source, result);

	            System.out.println("【必应词典】转换为【有道词典】成功!");

	        }

			catch (TransformerConfigurationException e) {

	            System.out.println(e.getMessage());

	        }

			catch (IllegalArgumentException e) {

	            System.out.println(e.getMessage());

	        }

			catch (FileNotFoundException e) {

	            System.out.println(e.getMessage());

	        }

			catch (TransformerException e) {

	            System.out.println(e.getMessage());

	        }

	    }

		 catch (Exception ex) {

			 System.out.println(ex.getMessage());

		}

     }

	 //filtering function

	 private boolean timeDecision(String data){

		 if(data.compareTo(time)>=0)

		    return true;

		 else

		    return false;

	 }

}

使用说明：

(1)将必应词典导出到本地文件“bing.xml”，放入工程根目录下。

(2)定义 bing2youdao对象，可以使用三种构造函数:

     new bing2youdao("bing.xml");

                new bing2youdao("bing.xml",“yyyy-mm-dd”);//表示仅仅转换“yyyy-mm-dd”(含)之后天数记录的单词

                new bing2youdao("bing.xml",“yyyy-mm-dd”,“newClass”);//表示将转换的单词归为“newClass”类

(3)调用run()生成“youdao.xml”并将其导入到有道词典单词本即可。本例模式的复习进度为1，若希望其不加入复习计划，修改为“-1”即可

如：

	 public static void main(String args[]) {

		 bing2youdao jisuan= new bing2youdao("bing.xml","2015-10-21","CC");

		 jisuan.run();

	 }

上例仅仅转换2015年10月21日后保存到必应词典中的单词，并将其统一归为“CC”类。

相关文章