Lucene搜索笔记

Lucene的常用检索类：

IndexSearcher ：检索操作的核心组件，用于对 IndexWriter 创建的索引执行，只读的检索操作，工作模式为接收 Query 对象而返回 ScoreDoc对象。

Term ：检索的基本单元，标示检索的字段名称和检索对象的值，如Term( “title”, “lucene” )。即表示在 title 字段中搜寻关键词 lucene 。

Query：表示查询的抽象类，由相应的 Term 来标识。

TermQuery ：最基本的查询类型，用于匹配含有指定值字段的文档。

TopDocs:保存查询结果的类。

ScoreDoc(Hits)：用来装载搜索结果文档队列指针的数组容器。

package com.fxr.demo3;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestSearcher {

	/**
	 * @param args
	 * @throws IOException 
	 */
	public static void main(String[] args) throws IOException {
		Analyzer analyzer = new StandardAnalyzer();//创建标准的分词
		String indexDir = "f:/lucenefxrindex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc []hits = null;
		Term term = new Term("address","shanghai");
		TermQuery termQuery = new TermQuery(term);
		TopDocs topDocs = indexSearcher.search(termQuery, 10);
		hits= topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document document = indexSearcher.doc(hits[i].doc);
			System.out.println(hits[i].score);
			System.out.println(document.get("id"));
			System.out.println(document.get("name"));
			System.out.println(document.get("address"));
			
		}
		indexSearcher.close();
		directory.close();
		

	}

}

　　通配符的查询：

在Lucene中也可以使用通配符查询："*"是匹配任意长度的字符,"?"是匹配定长的字符。

package com.fxr.demo3;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestWildcardSearcher {

	/**
	 * @param args
	 * @throws IOException 
	 */
	public static void main(String[] args) throws IOException {
		Analyzer analyzer = new StandardAnalyzer();//创建标准的分词
		String indexDir = "f:/lucenefxrindex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc []hits = null;
		Term term = new Term("address","z*");
		WildcardQuery wildcardQuery = new WildcardQuery(term);
		TopDocs topDocs = indexSearcher.search(wildcardQuery, 10);
		hits= topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document document = indexSearcher.doc(hits[i].doc);
			System.out.println(hits[i].score);
			System.out.println(document.get("id"));
			System.out.println(document.get("name"));
			System.out.println(document.get("address"));
			
		}
		indexSearcher.close();
		directory.close();
		

	}

}

　　如何把查询结合起来使用？我们在实际需求中有时候需要这样做，这里需要BooleanQuery，BooleanQuery里面有几个参数，参数可以实现几个Query结合起来的使用

package com.fxr.demo3;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestWildcardSearcher {

	/**
	 * @param args
	 * @throws IOException 
	 */
	public static void main(String[] args) throws IOException {
		Analyzer analyzer = new StandardAnalyzer();//创建标准的分词
		String indexDir = "f:/lucenefxrindex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc []hits = null;
		Term wterm = new Term("address","z*");
		WildcardQuery wildcardQuery = new WildcardQuery(wterm);
		Term tterm = new Term("name","zhangsan");
		TermQuery termQuery = new TermQuery(tterm);
		
		BooleanQuery booleanQuery = new BooleanQuery();
		booleanQuery.add(wildcardQuery, BooleanClause.Occur.MUST);//必须出现
		booleanQuery.add(termQuery, BooleanClause.Occur.SHOULD);//或的关系
		
		TopDocs topDocs = indexSearcher.search(wildcardQuery, 10);
		hits= topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document document = indexSearcher.doc(hits[i].doc);
			System.out.println(hits[i].score);
			System.out.println(document.get("id"));
			System.out.println(document.get("name"));
			System.out.println(document.get("address"));
			
		}
		indexSearcher.close();
		directory.close();
		

	}

}

　　指定范围的查询RangeQuery,可以查询区间的数据，

package com.firstproject.testsearch;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.RangeQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestRangeQuery {
	
	public static void main(String[] args) throws IOException {
		Analyzer analyzer=new StandardAnalyzer();
		String indexDir = "f:/lucenefxrindex";
		Directory dir=FSDirectory.getDirectory(indexDir);
		IndexSearcher searcher=new IndexSearcher(dir);
		ScoreDoc [] hits=null;
		Term beginTerm=new Term("birthday","19820720");
		Term endTerm=new Term("birthday","19830130");
		RangeQuery query=new RangeQuery(beginTerm,endTerm,true);
		
		
		TopDocs topDocs=searcher.search(query, 2);
		
		hits=topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document doc=searcher.doc(hits[i].doc);
//		    System.out.print(hits[i].score+" ");
			System.out.print(doc.get("id")+" ");
			System.out.print(doc.get("name")+" ");
			System.out.print(doc.get("address")+" ");
			System.out.println(doc.get("birthday")+" ");
		}
		searcher.close();
		dir.close();
		
	}

}

　　读取文件中的数据

package com.fxr.demo3;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;

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.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestFileDataQuery {

	
	
	public static void main(String[] args) throws IOException {
		File file = new File("f:/data/data.txt");
		FileReader reader = new FileReader(file);
		//把文件下的数据读入到char数组中
		char[]chs = new char[60000];
		reader.read(chs);
		String strtemp = new String(chs);
		String[] strs = strtemp.split("Database: Compendex");
		System.out.println(strs.length);
		for(int i=0;i<strs.length;i++){
			strs[i] = strs[i].trim();
		}
		Analyzer analyzer = new StandardAnalyzer();
		String indexDir = "f:/lucenefxrindex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexWriter indexWriter = new IndexWriter(directory,analyzer,IndexWriter.MaxFieldLength.UNLIMITED);
		for(int i=0;i<strs.length;i++){
			Document document = new Document();
			document.add(new Field("contents",strs[i],Field.Store.YES,Field.Index.ANALYZED));
			indexWriter.addDocument(document);
		}
		indexWriter.optimize();
		indexWriter.close();
		directory.close();
		System.out.println("ok!");
		
		
		
		
	}
	
	
}

　　

package com.fxr.demo3;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestFileQuery {

	/**
	 * @param args
	 * @throws IOException 
	 */
	public static void main(String[] args) throws IOException {
		
		Analyzer analyzer = new StandardAnalyzer();//创建标准的分词
		String indexDir = "f:/lucenefxrindex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc []hits = null;
		Term term = new Term("contents","*dsorption*");
		WildcardQuery wildcardQuery = new WildcardQuery(term);
		//TermQuery termQuery = new TermQuery(term);
		TopDocs topDocs = indexSearcher.search(wildcardQuery, 126);
		hits= topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document document = indexSearcher.doc(hits[i].doc);
			System.out.println(hits[i].score);
			System.out.println(document.get("contents"));
			
			
		}
		indexSearcher.close();
		directory.close();
		

	}


}