Lucene初识

目录

Lucene简介

pom.xml:

lucene建立索引：

lucene的几种检索方式：

---

Lucene简介

https://baike.baidu.com/item/Lucene/6753302

简单来说，Lucene是一个用来检索的开源框架。

lucene检索需要的jar包：

pom.xml:

<dependencies>
  
    <dependency>
	    <groupId>org.apache.lucene</groupId>
	    <artifactId>lucene-core</artifactId>
	    <version>7.4.0</version>
    </dependency>
    
    <dependency>
	    <groupId>org.apache.lucene</groupId>
	    <artifactId>lucene-queryparser</artifactId>
        <version>7.4.0</version>
    </dependency>
    
    <dependency>
	    <groupId>org.apache.lucene</groupId>
	    <artifactId>lucene-analyzers-common</artifactId>
	    <version>7.4.0</version>
    </dependency>
  </dependencies>

lucene建立索引：

写了一个Junit测试类：

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.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;
        /*
            lucene测试类
           */
public class IndexingTest {

	private String ids[]={"1","2","3"};
	private String citys[]={"qingdao","nanjing","shanghai"};
	private String descs[]={
			"Qingdao is a beautiful city.",
			"Nanjing is a city of culture.",
			"Shanghai is a bustling city."
	};
	
	private Directory dir;
	
	@Before
	public void setUp() throws Exception {
		dir=FSDirectory.open(Paths.get("D:\\lucene2"));
		IndexWriter writer=getWriter();
		for(int i=0;i<ids.length;i++) {
			Document doc=new Document();
			doc.add(new StringField("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.NO));
			writer.addDocument(doc);
		}
		writer.close();
	}
	
	
	/**
	 * 获取IndexWriter实例
	 */
	private IndexWriter getWriter()throws Exception{
		
		Analyzer analyzer=new StandardAnalyzer();
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		IndexWriter writer=new IndexWriter(dir, iwc);
		return writer;
	}

	/**
	 * 测试写了几个文档
	 * @throws Exception
	 */
	@Test
	public void testIndexWriter()throws Exception{
		 IndexWriter writer=getWriter();
		 System.out.println("写入了"+writer.numDocs()+"个文档");
		 writer.close();
	}
	
	/**
	 * 测试读取文档实例
	 */
	@Test
	public void testIndexReader()throws Exception{
		IndexReader reader=DirectoryReader.open(dir);
		System.out.println("最大文档数:"+reader.maxDoc());
		System.out.println("实际文档数:"+reader.numDocs());
		reader.close();
	}
	
	/**
	 * 测试删除，在合并之前
	 * 
	 */
	@Test
	public void testDeleteBeforeMerge()throws Exception{
		IndexWriter writer=getWriter();
		System.out.println("删除之前的文档数量："+writer.numDocs());
		writer.deleteDocuments(new Term("id","1"));
		writer.commit();
		System.out.println("writer.numDocs:"+writer.numDocs());
		System.out.println("writer.maxDocs:"+writer.maxDoc());
		writer.close();
	}
	
	/**
	 * 测试删除，在合并之后
	 */
	@Test
	public void testDeleteAfterMerge()throws Exception{
		IndexWriter writer=getWriter();
		System.out.println("删除之前的文档数量："+writer.numDocs());
		writer.deleteDocuments(new Term("id","1"));
		writer.forceMergeDeletes();  //强制删除
		writer.commit();
		System.out.println("writer.numDocs:"+writer.numDocs());
		System.out.println("writer.maxDocs:"+writer.maxDoc());
		writer.close();
	}
	
	/**
	 * 测试更新
	 */
	@Test
	public void testUpdate()throws Exception{
		
		IndexWriter writer=getWriter();
		Document doc=new Document();
		doc.add(new StringField("id","1",Field.Store.YES));
		doc.add(new StringField("city","qingdao",Field.Store.YES));
		doc.add(new TextField("desc","ddd is a city",Field.Store.NO));
		writer.updateDocument(new Term("id","1"), doc);
		writer.close();
	}
}

结果:

lucene的几种检索方式：

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:\\lucene3"));
		reader=DirectoryReader.open(dir);
		is=new IndexSearcher(reader);
	}

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

	/**
	 * 对特定项进行搜索
	 * @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+"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"));
		}
	}
	
/**
 * 表达式，模糊搜索，匹配搜索，解析查询表达式
 */
	@Test
	public void TestQueryParser()throws Exception{
		Analyzer analyzerr=new StandardAnalyzer();
		String searchField="contents";
		String q="particular AND Requirements AND benchmarks";
		QueryParser parser=new QueryParser(searchField,analyzerr);
		Query query=parser.parse(q);
		TopDocs hits=is.search(query, 10);
		System.out.println("匹配"+q+"共查询到"+hits.totalHits+"个记录。。。");
		for(ScoreDoc scoreDoc:hits.scoreDocs) {
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("fullPath"));
		}
	}
}