Lucene入门

我只提供入门级的教材， 后续的优化，连数据库，还需要你们自己去扩展。 授人以鱼不如授人以渔。

准备：

IKAnalyzer3.2.8.jar

lucene-analyzers-3.5.0.jar

lucene-core-3.5.0.jar

lucene-highlighter-3.5.0.jar  

lucene-memory-3.5.0.jar

如果你使用maven的话：

<!--这里我使用的3.5的包，maven仓库最低为4.0.0的。所以我直接在lib下加的包，再就是IKAnalyzer包在仓库里没有，需要手动加到仓库里，我不喜欢麻烦 -->

<!-- 注：IKAnalyzer包在仓库里没有，需要手动加到仓库里，手动打包：http://blog.csdn.net/u013829202/article/details/71632636   -->
	<dependency>  
		    <groupId>org.apache.lucene</groupId>  
		    <artifactId>lucene-core</artifactId>  
		    <version>4.0.0</version>  
		</dependency>  
		<dependency>  
		    <groupId>org.apache.lucene</groupId>  
		    <artifactId>lucene-highlighter</artifactId>  
		    <version>4.0.0</version>  
		</dependency>  
		<dependency>  
		    <groupId>org.apache.lucene</groupId>  
		    <artifactId>lucene-memory</artifactId>  
		    <version>4.0.0</version>  
		</dependency> 
        <dependency>  
            <groupId>org.apache.lucene</groupId>  
            <artifactId>lucene-analyzers-common</artifactId>  
            <version>4.0.0</version>  
        </dependency> 
        <dependency>  
            <groupId>org.apache.lucene</groupId>  
            <artifactId>lucene-queryparser</artifactId>  
            <version>4.0.0</version>  
        </dependency>
         <dependency>  
            <groupId>org.apache.lucene</groupId>  
            <artifactId>lucene-sandbox</artifactId>  
            <version>4.0.0</version>  
        </dependency> 

代码：

package com.xl.ssm.lucene.lucene;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
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;

/**
 * 简单入门 lucene 
 * @author 黑夜
 * jar: IKAnalyzer3.2.8.jar   lucene-analyzers-3.5.0.jar  lucene-core-3.5.0.jar
 * 			lucene-highlighter-3.5.0.jar  lucene-memory-3.5.0.jar
 */
public class MyLucene2 {

     private File indexFile=new File("E:\\lucene\\luceneIndex");  //索引存储地址
     //private Analyzer analyzer = new IKAnalyzer(true);	
     //一元分词，全部拆分为单个字搜索
     private Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_35);
     
     //这是创建的索引里面的的一条记录，这个是记录某个属性，【只记录你需要查询的即可】
     private String[] queryString={"username","content"};    
     
     
     /**  
      * 创建索引  
      * @throws IOException  
      */    
     public void createIndex() throws IOException {    
         //创建索引目录    
         Directory directory = FSDirectory.open(indexFile);    
         //建立索引创建类    
         IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_35, analyzer); 
         //总是重新创建索引【测试用：你可以做一个更新索引，需要的时候进行更新就行】
         indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE); //APPEND 追加    CREATE_OR_APPEND如果不存在则创建否则追加
         IndexWriter writer = new IndexWriter(directory, indexWriterConfig);    
     
         //加载数据
 		 MyLucene2 my2 = new MyLucene2();
 		 List<Student> list =  my2.getStore();
         //建立索引    
 		long time1 = System.currentTimeMillis();  
 		 for (Student student : list) {
 			 Document document = new Document();    
 			 document.add(new Field("id", String.valueOf(student.getId()), Field.Store.YES, Field.Index.ANALYZED));
             document.add(new Field("username", student.getName(), Field.Store.YES, Field.Index.ANALYZED)); 
             document.add(new Field("content", student.getContent(), Field.Store.YES, Field.Index.ANALYZED));    
             writer.addDocument(document);    
		}
 		 long time2 = System.currentTimeMillis();    
         System.out.println("创建了" + writer.numDocs() + "条索引");    
         System.out.println("一共花了" + (time2 - time1) + "毫秒");  
         System.out.println("==============================");
 		 
         writer.close();    
     }    
     
     /**  
      * 搜索  
      * @throws IOException  
      * @throws ParseException  
      */    
     public void search()   {    
    	 IndexReader indexReader = null;
         try {
        	 indexReader = IndexReader.open(FSDirectory.open(indexFile));    
    		 //创建搜索类    使用不同的分词法,结果会不一样
    		 IndexSearcher indexSearcher = new IndexSearcher(indexReader);    
    		 QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_35, queryString, analyzer);  
			 //要搜索的文件名
			 Query query = queryParser.parse("吗");    
			 TopDocs topDocs = indexSearcher.search(query, 10000);    
			 System.out.println("一共查到:" + topDocs.totalHits + "记录");    
			 ScoreDoc[] scoreDoc = topDocs.scoreDocs;    

			 for (int i = 0; i < scoreDoc.length; i++) {    
			     //内部编号    
			     int doc = scoreDoc[i].doc;    
			     System.out.println("编号:" + doc);    
			     //根据文档id找到文档    
			     Document mydoc = indexSearcher.doc(doc);    
			     System.out.println("结果:" + mydoc.get("content"));    
			 }
		} catch (Exception e) {
			e.printStackTrace();
		}finally{
			try {
				indexReader.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}    
     }    
     
     //test
     public static void main(String[] args) throws ParseException {
    	 MyLucene2 lu = new MyLucene2();
    	 try {
			lu.createIndex();
			lu.search();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
  
   /**
    * 这个可以是从数据库查询出来的数据
    * @return
    */
  public List<Student> getStore(){
	  ArrayList<Student> list =new ArrayList<Student>();
	  
      Student stu1 = new Student();
      stu1.setId(1);
      stu1.setName("这是一个例子");;
      stu1.setContent("你好");
      
      Student stu2 = new Student();
      stu2.setId(2);
      stu2.setName("我也是一个例子");;
      stu2.setContent("你好吗?");
      
      list.add(stu1);
      list.add(stu2);  
      return list;
  }
}


/**
 * 实体类 
 * @author lh
 * 参考： 当做你们的数据来源
 */
 class Student{
	int id;
	String name;
	String content;
	public int getId() {
		return id;
	}
	public void setId(int id) {
		this.id = id;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public String getContent() {
		return content;
	}
	public void setContent(String content) {
		this.content = content;
	}
	
	public Student(){}
	public Student(int id ,String name,String content){}
 }

接下来，会写关于solr和es的全文检索，当然也是入门级的。