基于Lucene的QueryParser搜索

[color=blue]

import java.io.*;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;


public class QueryParserTest {

 Date startTime,endTime;
 
 /**
  * 索引文件的存放位置
  */
 private String path = "C:/lucene/test.txt";
 
 /**
  * 创建索引
  */
 public void createIndexByFile(){
  IndexWriter writer;
  try {
   
   String filePath = "C:/lucene/test.txt";
   String content = file2String(filePath, "GBK");
   
   //System.out.println(content);
   
   writer = new IndexWriter(path,new StandardAnalyzer(),true);
   
   Document docA = new Document();
   
   Field fieldA = new Field("content",content,Field.Store.YES,Field.Index.TOKENIZED);
   docA.add(new Field("path",filePath,Field.Store.YES,Field.Index.UN_TOKENIZED));
   docA.add(fieldA);
   
   writer.addDocument(docA);
   
   //如果对海量数据进行创建索引的时候，需要对索引进行优化，以便提高速度
   writer.optimize();
   
   //跟数据库类似，打开一个连接，使用完后，要关闭它
   writer.close();
   
  } catch (Exception e) {
   e.printStackTrace();
  } 
 }
 

public Query queryParser(){
  QueryParser queryParser = new QueryParser("content", new StandardAnalyzer());
  try {
   return queryParser.parse("搜索");
  } catch (Exception e) {
   e.printStackTrace();
  }
  return null;
 }
 
 public void search(){
  try {
   //相当于sql中的 select * from talbeName 
   IndexSearcher search = new IndexSearcher(path);
   
   startTime = new Date();
   //抽象的查询对象
   Query query = queryParser();
   
   //lucene在设计的时候，就参照了JDBC的很多概念
   Hits hits = search.search(query);
   for (int i = 0; i < hits.length(); i++) {
    System.out.println("id= "+hits.id(i));
    System.out.println("搜索的内容: "+hits.doc(i));
    //System.out.println(hits.score(i));
   }
   endTime = new Date();
   
   System.out.println("本次搜索用时：" + (endTime.getTime() - startTime.getTime()) + "毫秒");
   
  } catch (Exception e) {
   e.printStackTrace();
  }
 }
 
 
 
 private String file2String(String fileName,String charset) throws Exception{
  BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(fileName),charset));
  //StringBuilder ,StringBuffer
  StringBuilder builder = new StringBuilder();
  String line = null;
  while((line = reader.readLine())!=null){
   builder.append(line);
  }
  return builder.toString();
 }
 
 /**
  * @param args
  */
 public static void main(String[] args) {
  QueryParserTest ff = new QueryParserTest();
  ff.createIndexByFile();
  
  ff.search();

 }

}

 

搜索结果如下：

id= 0
搜索的内容: Document<stored/uncompressed,indexed<path:C:/lucene/test.txt> stored/uncompressed,indexed,tokenized<content:最近在学习Lucene，学习这个东西也差不多一个月了，现在想写一些搜索的测试看看。呵呵，很想做一个属于自己的简单的搜索引擎，继续坚持学习吧！>>
本次搜索用时：138毫秒[/color]