`
smallearth
  • 浏览: 34652 次
  • 性别: Icon_minigender_1
社区版块
存档分类
最新评论

Lucene小练十（八种搜索）

 
阅读更多 
package Java.se.lucene;
//主类
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumericField;
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.index.Term;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

public class Search {
	private String[] ids={"1","2","3","4","5","6"};
	private String[] emails={"aa@aa.com","bb@bb.com",
			"cc@cc.com","dd@dd.com","ee@ee.com","ff@ff.com"};
	private String[] contents={"i like  gdsfgfds","i like fsdfs","i like fdsfsd",
			"i like fdsfsd","i like like fdfs","i like like like fsefsdfg"};
	private int[] attachs={1,2,3,4,5,6};
	private String[] names={"liwu","zhangsan","xiaoqinag","laona",
			"dabao","lisi"};
	private IndexWriter writer=null;
	private Date[] dates=null;
	private Map<String,Float> scores=new HashMap<String,Float>();
	private Directory directory=null;
	private IndexReader reader=null;
	
	public Search()
	{
		directory=new RAMDirectory();
		setDate();
		index();
	}
	//建立索引
	public void index()
	{
		Document document=null;
         try {
			writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36,
				new StandardAnalyzer(Version.LUCENE_36)));
			writer.deleteAll();//更新索引
			for(int i=0;i<ids.length;i++)
			{
				document=new Document();
				document.add(new Field("id", ids[i], 
						Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS  ));
				document.add(new Field("email",emails[i],
						Field.Store.YES,Field.Index.NOT_ANALYZED));
				document.add(new Field("content", contents[i], 
						Field.Store.YES, Field.Index.ANALYZED));
				document.add(new Field("name",names[i],
						Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
		    	//为数字添加索引
				document.add(new NumericField("attach", Field.Store.YES,true).
						setIntValue(attachs[i]));
				//为日期添加索引
				document.add(new NumericField("date", Field.Store.YES,true)
				.setLongValue(dates[i].getTime()));//记住要getTime
						
				
		    	String str=emails[i].substring(emails[i].lastIndexOf("@")+1);
		    	//System.out.println(str);
    		    if(scores.containsKey(str))
		    	{
		    		document.setBoost(scores.get(str));
		    	}else{
	    		document.setBoost(0.5f);
		    	}
		    	writer.addDocument(document);
		    	writer.commit();//提交writer
			}
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		finally{
            try {
				writer.close();
			} catch (CorruptIndexException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
		}
	}
	//获取searcher
	public IndexSearcher getSearcher()
	{
		try {
			if(reader==null)
			{
				reader=IndexReader.open(directory);
			}else {
				IndexReader rd=IndexReader.openIfChanged(reader);
				if(reader!=null)
				{
					reader.close();
					reader=rd;
				}
			}
			return new IndexSearcher(reader);
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return null;
	}
	//精确查找 1
	public void searchByTerm(String field,String name,int num)
	{
		try {
			IndexSearcher searcher=getSearcher();
			Query query =new TermQuery(new Term(field,name));
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}
						
			searcher.close();
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	//范围查询 2
	public void searchByTermRange(String field,String start,String end,int num){
	
			try {
				IndexSearcher searcher=getSearcher();
				Query query =new TermRangeQuery(field, start, end, true, true);
				TopDocs tds=searcher.search(query, num);
				System.out.println("一共查询了："+tds.totalHits);
				for(ScoreDoc sd:tds.scoreDocs)
				{
					Document doc=searcher.doc(sd.doc);
					System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
							+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
							"-->"+doc.get("attach")+".."+doc.get("date"));				
				}			
				searcher.close();
			} catch (CorruptIndexException e) {
				e.printStackTrace();
			} catch (IOException e) {
				e.printStackTrace();
			}
	}
	//范围查询 3
	public void searchByNumRange(String field,int start,int end,int num){
	
			try {
				IndexSearcher searcher=getSearcher();
				Query query =NumericRangeQuery.newIntRange(field, start, end, true,true);
				TopDocs tds=searcher.search(query, num);
				System.out.println("一共查询了："+tds.totalHits);
				for(ScoreDoc sd:tds.scoreDocs)
				{
					Document doc=searcher.doc(sd.doc);
					System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
							+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
							"-->"+doc.get("attach")+".."+doc.get("date"));				
				}			
				searcher.close();
			} catch (CorruptIndexException e) {
				e.printStackTrace();
			} catch (IOException e) {
				e.printStackTrace();
			}
	}
	//前缀搜索 4
	public void searchByPrefix(String field,String value,int num)
	{
		try {
			IndexSearcher searcher=getSearcher();
			Query query =new PrefixQuery(new Term(field,value));
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}			
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	//通配搜索 5
	public void searchBywildCard(String field,String value,int num)
	{
		try {
			IndexSearcher searcher=getSearcher();
			//通配符操作符，？可以匹配一个通配符，*可以匹配多个通配符
			Query query =new WildcardQuery(new Term(field,value));
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}			
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	//Boolean查询 6
	public void searchByBoolean(int num)
	{
       try {
			IndexSearcher searcher=getSearcher();
			//通配符操作符，？可以匹配一个通配符，*可以匹配多个通配符
			Query query = new BooleanQuery();
			((BooleanQuery) query).add(new TermQuery(new Term("name", "laona")),Occur.MUST);
			((BooleanQuery) query).add(new TermQuery(new Term("content", "fdfs")),Occur.SHOULD);
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}			
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	//短语查询 7
	public void searchByPhrase(int num)
	{
       try {
			IndexSearcher searcher=getSearcher();
			//通配符操作符，？可以匹配一个通配符，*可以匹配多个通配符
			PhraseQuery query = new PhraseQuery();
			query.setSlop(1);
			query.add(new Term("content","i"));
			query.add(new Term("content","fdsfsd"));
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}			
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	//模糊查询  8
	public void searchByFuzzy(int num)
	{
       try {
			IndexSearcher searcher=getSearcher();
			//通配符操作符，？可以匹配一个通配符，*可以匹配多个通配符
			Query query = new FuzzyQuery(new Term("name","laonaa"),0.5f);
			TopDocs tds=searcher.search(query, num);
			System.out.println("一共查询了："+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs)
			{
				Document doc=searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"-->"+doc.get("name")+".."
						+"["+doc.get("email")+"]"+"("+doc.get("content")+")"+
						"-->"+doc.get("attach")+".."+doc.get("date"));				
			}			
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	//创建日期
    public void setDate()
    {
    	SimpleDateFormat sdf=new SimpleDateFormat("yyyy-mm-kk");
    	try {
    		dates=new Date[ids.length];
        	dates[0]=sdf.parse("2010-08-17");
        	dates[1]=sdf.parse("2011-02-17");
        	dates[2]=sdf.parse("2012-03-17");
        	dates[3]=sdf.parse("2011-04-17");
        	dates[4]=sdf.parse("2012-05-17");
        	dates[5]=sdf.parse("2011-07-17");
		} catch (Exception e) {
			e.printStackTrace();
			// TODO: handle exception
		}
    } 
}
/测试类
package Java.se.lucene;

import org.junit.Before;
import org.junit.Test;

public class Test_Search {
	private static final int num=10;
	private Search search=null;
	
	@Before
	public void init()
	{
	   search=new Search();	
	}
	@Test
	public void test_search01()
	{
		search.searchByTerm("content", "like", 6);
	}
	@Test
	public void test_search02()
	{
		//查询（内容--content） 范围（a-z）
		search.searchByTermRange("content","a","z",10);
		//查询（内容--name） 范围（a-z）
		search.searchByTermRange("content","a","z",10);
		//查询（内容--attach） 范围（a-z） 查询不出
		search.searchByTermRange("attach","2","6",10);
	}
	@Test
	public void test_search03()
	{
		//查询（内容--content） 范围（a-z）
		search.searchByNumRange("attach",1,4,num);
	
	}
	@Test
	public void test_search04()
	{
		//查询（内容--content） 
		search.searchByPrefix("content","lgfdfg",num);
	
	}
	@Test
	public void test_search05()
	{
		search.searchBywildCard("email","aa**",num);
	}
	@Test
	public void test_search06()
	{
		search.searchByBoolean(num);
	}
	@Test
	public void test_search07()
	{
		search.searchByPhrase(num);
	}
	@Test
	public void test_search08()
	{
		search.searchByFuzzy(num);
	}
//	public static void main(String[] args) {
//		Search search=new Search();
//		search.searchByTerm("name", "mike", 3);
//	}

}


分享到：
| Lucene小练九——各种搜索（精确，范围，数 ...
评论
发表评论

您还没有登录,请您登录后再发表评论

相关推荐

    基于Lucene小型搜索引擎的研究与实现

    基于Lucene小型搜索引擎的研究与实现

    lucene实例lucene实例

    lucene实例lucene实例lucene实例lucene实例lucene实例lucene实例lucene实例lucene实例lucene实例

    lucene入门小例子

    lucene入门小例子

    lucene，lucene教程，lucene讲解

    lucene，lucene教程，lucene讲解。 为了对文档进行索引，Lucene 提供了五个基础的类 public class IndexWriter org.apache.lucene.index.IndexWriter public abstract class Directory org.apache.lucene.store....

    lucene3.6 搜索例子

    lucene3.6 搜索例子

    Lucene时间区间搜索

    c#下实现Lucene时间区间查询匹配。主要还是对Lucene查循对像Query的实现

    Lucene全文搜索_LuceneJava全文搜索_

    Lucene实现全文搜索，支持英文、模糊和智能查询

    lucene3.0 lucene3.0

    lucene3.0 lucene3.0 lucene3.0 lucene3.0 lucene3.0

    Java搜索引擎 Lucene

    Java搜索引擎 Lucene

    lucene近实时搜索

    lucene 近实时搜索 很清楚的解释了关于lucene近实时搜索的代码。很值得学习

    lucene学习lucene学习

    lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习lucene学习...

    lucene相关十几个包

    lucene相关十几个包。

    lucene站内搜索

    主要是关于lucene站内搜索的技术代码，可以使用；按照需要进行代码修改。

    lucene 高级搜索项目

    lucene 高级搜索项目 附件搜索 附件内容搜索 全文搜索

    lucene实现全文搜索

    全文检索介绍 索引 分词 Lucene介绍 Lucene应用详解 索引器 检索器 条件查询 实用工具及高亮器 Lucene综合应用——仿搜索引擎

    lucene的小案例

    关于搜索的一个小案例，使用的是lucene,框架为ibatis，spring，stuts2

    利用lucene进行搜索

    利用lucene进行搜索，IndexSearcher是整个Lucene搜索查询相关信息的驱动引擎，在使IndexSearcher之前，需要构建IndexSearcher对象，Lucene提供了两种构建IndexSearcher对象的方式： 1、基于Directory对象构建； 2...

    lucene 小资源

    lucene 小资源,只是接触lucene的经验积累过程，从中学习一些有意义的经验。

    Lucene4.X第九讲-Lucene搜索深入实战

    Lucene是一个高性能、可伸缩的信息搜索(IR)库。目前最新版本是4.3.1. 它可以为你的应用程序添加索引和搜索能力。Lucene是用java实现的、成熟的开源项目，是著名的Apache Jakarta大家庭的一员，并且基于Apache软件...

    Lucene4.X 第十五讲-Lucene高级进阶

    Lucene是一个高性能、可伸缩的信息搜索(IR)库。目前最新版本是4.3.1. 它可以为你的应用程序添加索引和搜索能力。Lucene是用java实现的、成熟的开源项目，是著名的Apache Jakarta大家庭的一员，并且基于Apache软件...

Magicbox
Global site tag (gtag.js) - Google Analytics