lucene第一步---2.查询

package demo.first;

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.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RangeQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.WildcardQuery;

public class Search {

	Date startTime,endTime;
	
	/**
	 * 索引文件的存放位置
	 */
	String path = "D://workspace//fwk//lucenedemo//firstLuceneIndex";
	
	/**
	 * 创建索引
	 */
	public void createLuceneIndex(){
		IndexWriter writer;
		try {
			writer = new IndexWriter(path,new StandardAnalyzer(),true);
			Document docA = new Document();
			//相当于数据库中列的概念，因此第一个参数是列名，第二个参数是列的值，最后两个参数是enum类型的(JDK1.5)，对创建的索引的设置
			//Field.Store 是否覆盖原来的索引文件，而不是重新建一个
			Field fieldA = new Field("content","搜索引擎",Field.Store.YES,Field.Index.TOKENIZED);
			//我们把列(fieldA)加到某一行(docA)中
			docA.add(fieldA);
			//英文 测试
			docA.add(new Field("content","hello llying ,I love you",Field.Store.YES,Field.Index.TOKENIZED));
			docA.add(new Field("lastModifyTime","2010个人",Field.Store.YES,Field.Index.TOKENIZED));
			
			Document docB = new Document();
			//相当于数据库中列的概念，因此第一个参数是列名，第二个参数是列的值，最后两个参数是enum类型的(JDK1.5)，对创建的索引的设置
			Field fieldB = new Field("content","创建索引",Field.Store.YES,Field.Index.TOKENIZED);
			//我们把列(fieldA)加到某一行(docA)中
			docB.add(fieldB);
			docB.add(new Field("content","i live in shanghai.i come from cn",Field.Store.YES,Field.Index.TOKENIZED));
			docB.add(new Field("lastModifyTime","2020个人",Field.Store.YES,Field.Index.TOKENIZED));
			
			writer.addDocument(docA);
			writer.addDocument(docB);
			
			//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();
		} 
	}
	
	/**
	 * 创建文件索引
	 */
	public void createIndexByFile(){
		IndexWriter writer;
		try {
			
			String filePath = "D://workspace//fwk//lucenedemo//firstLuceneIndex//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();
		} 
	}
	
	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();
	}
	
	/**
	 * 相当于sql中where 后面的条件，WildcardQuery不推荐大家使用
	 * 通配符搜索
	 */
	private Query wildcardQuery(){
		// where username = '张xiangqiang' and password='ILoveChina'
		//?代表至少有一个字符在前面
		//搜索"*搜*"，找到一条数据；搜索"*索*"，找到两条数据；搜索"*搜索*"，找到0条数据；搜索"*索引*"，找到0条数据；
		//为什么是这样的结果呢？流行伏笔
		Term term = new Term("content","*c*");
		return new WildcardQuery(term);
	}
	
	//基于lucene的分词 -- TermQuery只能对当个中文进行搜索。英文只能对当个单词进行搜索
	public Query termQuery(){
		Term term = new Term("content","19:58:25");
		return new TermQuery(term);
	}
	/**
	 * 智能搜索
	 * 
	 * @return
	 */
	public Query queryParser(){
		QueryParser queryParser = new QueryParser("content", new StandardAnalyzer());
		try {
			return queryParser.parse("搜索 - 擎");
		} catch (Exception e) {
			e.printStackTrace();
		}
		return null;
	}
	/**
	 * '与或'--搜索
	 * @return
	 */
	public Query booleanQuery(){
		Term term1 = new Term("content","索");
		Term term2 = new Term("content","搜");
		
		TermQuery tempQuery1 =  new TermQuery(term1);
		TermQuery tempQuery2 =  new TermQuery(term2);
		
		//本人觉得他更应该叫做JoinQuery 
		BooleanQuery booleanQuery = new BooleanQuery();
		booleanQuery.add(tempQuery1,BooleanClause.Occur.MUST);
		booleanQuery.add(tempQuery2,BooleanClause.Occur.SHOULD);
		return booleanQuery;
	}
	/**
	 * 多关键词搜索
	 * @return
	 */
	public Query phraseQuery(){
		PhraseQuery phraseQuery = new PhraseQuery();
		phraseQuery.setSlop(1);
		phraseQuery.add(new Term("content","搜"));
		phraseQuery.add(new Term("content","擎"));
		return phraseQuery;
	}
	/**
	 * 范围搜索
	 * @return
	 */
	public Query rangeQuery(){
		RangeQuery rangeQuery = new RangeQuery(new Term("lastModifyTime","20000808"),new Term("lastModifyTime","20150808"), true);
		return rangeQuery;
	}
	
	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();
			//Query query = phraseQuery();
			//搜索结果集Hits，和JDBC的查询结果集完全类似的概念 -- 为什么是这样的呢？
			//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(hits.id(i));
				System.out.println(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();
		}
	}
	
	
	

	
	/**
	 * @param args
	 */
	public static void main(String[] args) {
		Search search = new Search();
		//search.createLuceneIndex();
		search.createIndexByFile();
		
		search.search();

	}

}

评论

1 楼 BarryWei 2008-09-10  

感谢楼主
我看到以前的一个教程
不过那是老版本的

这篇文章的是新版本的lucene 谢谢你了