每日一练

Dom4j解析xml并利用lucene建立引索并搜索

package jim.luceneXML;

import java.io.File;
import java.io.IOException;
import java.util.Iterator;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.wltea.analyzer.lucene.IKAnalyzer;

//import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

@SuppressWarnings("unused")
public class MyTest {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		try {
			new MyLucene().creatIndex("test.xml");
		} catch (DocumentException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		MySearch searcher = new MySearch();
		searcher.Search();

	}

}

class MyLucene{
	Directory directory = null;//用来决定引索目录的储存方式
	IndexWriter writer = null;//引索器
	Document document = null;//引索文件
	Field field = null;//字段信息
	IndexWriterConfig iwc = null;//用来选择lucene的版本以及分词器的版本
	String indexPath = "index";//引索目录的储存地址
	String title = "title";//文件的标题
	String content = "content";//文件的内容
	String [] files = null;//用来记录文件夹里所有文件的地址
	String XmlContent = null;//用来记录从XML文件中读取来的内容
	String XmlName = null; //用来记录XML文件的节点名
	int num= 0;
	public void creatIndex(String fileName) throws DocumentException{
		//构造器
		try {
			directory = FSDirectory.open(new File(indexPath));//创建directory,其储存方式为在硬盘上储存
			iwc = new IndexWriterConfig(Version.LUCENE_35, new IKAnalyzer());//选择lucene的版本以及分词器的版本
			writer = new IndexWriter(directory,iwc);//创建引索器

		} catch (IOException e) {
			System.out.println("创建Directory时发生错误!");
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		
		

		SAXReader saxReader = new SAXReader();
		org.dom4j.Document doc = saxReader.read(new File(fileName));
		//List list = doc.selectNodes("/books/book/title");
		Element root = doc.getRootElement();
		@SuppressWarnings("rawtypes")
		Iterator iter = root.elementIterator();
		while(iter.hasNext()){
			Element rootElement = (Element)iter.next();
			@SuppressWarnings("rawtypes")
			Iterator childElementIter = rootElement.elementIterator();
			
			document = new Document();//创建索引文件
			while(childElementIter.hasNext()){
				
				Element childElement = (Element)childElementIter.next();
				System.out.println(childElement.getName()+": "+childElement.getText());
				XmlContent = childElement.getText();
				XmlName = childElement.getName();
				if(XmlName.equals("id")){
					field = new Field("id",String.valueOf(++num),Field.Store.YES,Index.NOT_ANALYZED);
			}
			else if(XmlName.equals("title")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
			else  if(XmlName.equals("keywords")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.ANALYZED);
				}
				
			else if(XmlName.equals("kind")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
			else  if(XmlName.equals("describe")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.ANALYZED);
				}
			else  if(XmlName.equals("date")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
			else  if(XmlName.equals("url")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
			else  if(XmlName.equals("author")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
			else  if(XmlName.equals("publisher")){
					field = new Field(XmlName,XmlContent,Field.Store.YES,Index.NOT_ANALYZED);
				}
				document.add(field);
 
				try {
					writer.addDocument(document);
				} catch (CorruptIndexException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				} catch (IOException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				}
				
				
			}
		}
		try {
			writer.close();
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	


		System.out.println("Index is Created!");  
	
	}
}

package jim.luceneXML;

import java.io.File;
import java.io.IOException;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class MySearch {
	Directory directory = null;//存储方式
	String indexPath = "index";//引索存放的目录
	IndexReader reader = null;//读入引索
	IndexSearcher searcher = null;//确定搜索对象
	QueryParser parser = null;//用于确定搜索时的引索的版本以及分词器
	Query query = null;//记录要搜索的词语
	TopDocs tds = null;//记录搜索后返回的结果
	Document document = null;//存放搜索结果以便于提取结果
	ScoreDoc[] sds = null;//存放TopDocs传来的内容(搜索结果)
	public void Search(){

		try {
			directory = FSDirectory.open(new File(indexPath));
		} catch (IOException e) {
			// TODO Auto-generated catch block
			System.out.println("创建Directory时发生错误!");
			e.printStackTrace();
		}//创建directory,其储存方式为在硬盘上储存
		try {
			reader = IndexReader.open(directory);
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			System.out.println("创建IndexReader时发生错误!");
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			System.out.println("创建IndexReader时发生错误!");
			e.printStackTrace();
		}
		searcher = new IndexSearcher(reader);
		parser = new QueryParser(Version.LUCENE_35,"keywords",new IKAnalyzer());
		try {
			query = parser.parse("期中");
		} catch (ParseException e) {
			// TODO Auto-generated catch block
			System.out.println("query = parser.parse(\"keyword\")时发生错误");
			e.printStackTrace();
		}
		try {
			tds = searcher.search(query,10);
		} catch (IOException e) {
			System.out.println("std = searcher.search(query,5);时发生错误");
			// TODO Auto-generated catch block
			e.printStackTrace();
		} 
		sds = tds.scoreDocs;
		System.out.println("一共搜索到: "+sds.length+" 条");
		if(sds.length != 0){
		for( ScoreDoc sd:sds){
			
			try {
				document = searcher.doc(sd.doc);
			} catch (CorruptIndexException e) {
				// TODO Auto-generated catch block
				System.out.println("document = searcher.doc(sd.doc);时发生错误");
				e.printStackTrace();
			} catch (IOException e) {
				System.out.println("document = searcher.doc(sd.doc);时发生错误");
				e.printStackTrace();
			}
			String test = document.get("id");

			System.out.println(test+document.get("keywords")+document.get("url"));
			//System.out.println("Id: "+document.get("id")+" name: "+document.get("name")+" number: "+document.get("number"));
			
		}
	}
		else
			System.out.println("The word you enter can't be found!");
		
		try {
			reader.close();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			System.out.println("关闭reader时发生错误!");
			e.printStackTrace();
		}
		
		System.out.println("Finished");
	
	}
	public void check() throws IOException{
		directory = FSDirectory.open(new File("index"));
		IndexReader reader = IndexReader.open(directory);
		for(int i = 0;i<reader.numDocs();i++){
			System.out.println(reader.document(i));
		}
	}
	
}

今天的收获:

今天对Dom4j解析xml有了一定得了解,并写了一个测试的程序.

今天的不足:

对Dom4j解析xml还有些不完美,做得不够细腻,明天希望这个问题能够改善.