Lucene查询方式

最新推荐文章于 2021-07-16 16:37:51 发布

待烟火清凉

最新推荐文章于 2021-07-16 16:37:51 发布

阅读量450

点赞数

分类专栏： Lucene

本文链接：https://blog.csdn.net/gcxzflgl/article/details/74502894

版权

Lucene 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

本文讲解6种查询方式

指定项查询、queryParse查询、指定项范围查询、指定数字范围查询、指定字符串开头查询、组合查询

自己提前准备一些数据以便测试

直接Demo

package com.gcx.search;

import java.io.File;
import java.io.FileReader;
import java.nio.file.Paths;

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.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class Indexer {

	private IndexWriter writer; // 写索引实例
	
	/**
	 * 构造方法 实例化IndexWriter
	 * @param indexDir
	 * @throws Exception
	 */
	public Indexer(String indexDir)throws Exception{
		Directory dir=FSDirectory.open(Paths.get(indexDir));
		Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		writer=new IndexWriter(dir, iwc);
	}
	
	/**
	 * 关闭写索引
	 * @throws Exception
	 */
	public void close()throws Exception{
		writer.close();
	}
	
	/**
	 * 索引指定目录的所有文件
	 * @param dataDir
	 * @throws Exception
	 */
	public int index(String dataDir)throws Exception{
		File []files=new File(dataDir).listFiles();
		for(File f:files){
			indexFile(f);
		}
		return writer.numDocs();
	}

	/**
	 * 索引指定文件
	 * @param f
	 */
	private void indexFile(File f) throws Exception{
		System.out.println("索引文件："+f.getCanonicalPath());
		Document doc=getDocument(f);
		writer.addDocument(doc);
	}

	/**
	 * 获取文档，文档里再设置每个字段
	 * @param f
	 */
	private Document getDocument(File f)throws Exception {
		Document doc=new Document();
		doc.add(new TextField("contents",new FileReader(f)));
		doc.add(new TextField("fileName", f.getName(),Field.Store.YES));
		doc.add(new TextField("fullPath",f.getCanonicalPath(),Field.Store.YES));
		return doc;
	}
	
	public static void main(String[] args) {
		String indexDir="D:\\lucene4";
		String dataDir="D:\\lucene4\\data";
		Indexer indexer=null;
		int numIndexed=0;
		long start=System.currentTimeMillis();
		try {
			indexer = new Indexer(indexDir);
			numIndexed=indexer.index(dataDir);
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}finally{
			try {
				indexer.close();
			} catch (Exception e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
		}
		long end=System.currentTimeMillis();
		System.out.println("索引："+numIndexed+" 个文件 花费了"+(end-start)+" 毫秒");
	}
}

生成索引后，开始查询

package com.gcx.search;


import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
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;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

public class SearchTest {

	private Directory dir;
	private IndexReader reader;
	private IndexSearcher is;
	
	@Before
	public void setUp() throws Exception {
		dir=FSDirectory.open(Paths.get("D:\\lucene4"));
		reader=DirectoryReader.open(dir);
		is=new IndexSearcher(reader);
	}

	@After
	public void tearDown() throws Exception {
		reader.close();
	}

	/**
	 * 对特定项搜索
	 * @throws Exception
	 */
	@Test
	public void testTermQuery()throws Exception{
		String searchField="contents";
		String q="particular";
		Term t=new Term(searchField,q);
		Query query=new TermQuery(t);
		TopDocs hits=is.search(query, 10);
		System.out.println("匹配 '"+q+"'，总共查询到"+hits.totalHits+"个文档");
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("fullPath"));
		}
	}
	
	/**
	 * 解析查询表达式
	 * @throws Exception
	 */
	@Test
	public void testQueryParser()throws Exception{
		Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
		String searchField="contents";
		String q="abc~";
		QueryParser parser=new QueryParser(searchField, analyzer);
		Query query=parser.parse(q);
		TopDocs hits=is.search(query, 100);
		System.out.println("匹配 "+q+"查询到"+hits.totalHits+"个记录");
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("fullPath"));
		}
	}
	
	
	
}

再来一波demo

package com.gcx.otherSearch;

import java.nio.file.Paths;

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.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class Indexer {

	private Integer ids[]={1,2,3};
	private String citys[]={"aingdao","banjing","changhai"};
	private String descs[]={
			"Qingdao is b beautiful city.",
			"Nanjing is c city of culture.",
			"Shanghai is d bustling city."
	};
	
	private Directory dir;
	
	/**
	 * 获取IndexWriter实例
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getWriter()throws Exception{
		Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		IndexWriter writer=new IndexWriter(dir, iwc);
		return writer;
	}
	
	/**
	 * 生成索引
	 * @param indexDir
	 * @throws Exception
	 */
	private void index(String indexDir)throws Exception{
		dir=FSDirectory.open(Paths.get(indexDir));
		IndexWriter writer=getWriter();
		for(int i=0;i<ids.length;i++){
			Document doc=new Document();
			doc.add(new IntField("id", ids[i], Field.Store.YES));
			doc.add(new StringField("city",citys[i],Field.Store.YES));
			doc.add(new TextField("desc", descs[i], Field.Store.YES));
			writer.addDocument(doc); // 添加文档
		}
		writer.close();
	}
	
	
	public static void main(String[] args) throws Exception {
		new Indexer().index("D:\\lucene5");
	}
	
}

生成索引后，进行查询

package com.gcx.otherSearch;

import java.nio.file.Paths;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.NumericRangeQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.BytesRef;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

public class otherQuery {
	private Directory dir;
	private IndexReader reader;
	private IndexSearcher is;
	
	@Before
	public void setUp() throws Exception {
		dir=FSDirectory.open(Paths.get("D:\\lucene5"));
		reader=DirectoryReader.open(dir);
		is=new IndexSearcher(reader);
	}

	@After
	public void tearDown() throws Exception {
		reader.close();
	}

	/**
	 * 指定项范围搜索
	 * @throws Exception
	 */
	@Test
	public void testTermRangeQuery()throws Exception{
		TermRangeQuery query=new TermRangeQuery("desc", new BytesRef("b".getBytes()), new BytesRef("c".getBytes()), true, true);
		TopDocs hits=is.search(query, 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}		
	}
	
	/**
	 * 指定数字范围
	 * @throws Exception
	 */
	@Test
	public void testNumericRangeQuery()throws Exception{
		NumericRangeQuery<Integer> query=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
		TopDocs hits=is.search(query, 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}		
	}
	
	/**
	 * 指定字符串开头搜索
	 * @throws Exception
	 */
	@Test
	public void testPrefixQuery()throws Exception{
		PrefixQuery query=new PrefixQuery(new Term("city","a"));
		TopDocs hits=is.search(query, 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}	
	}
	
	/**
	 * 多条件查询
	 * @throws Exception
	 */
	@Test
	public void testBooleanQuery()throws Exception{
		NumericRangeQuery<Integer> query1=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
		PrefixQuery query2=new PrefixQuery(new Term("city","a"));
		BooleanQuery.Builder booleanQuery=new BooleanQuery.Builder();
		booleanQuery.add(query1,BooleanClause.Occur.MUST);
		booleanQuery.add(query2,BooleanClause.Occur.MUST);
		TopDocs hits=is.search(booleanQuery.build(), 10);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("id"));
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
		}	
	}

}