Lucene（全文检索）索引库维护

Lucene索引库的维护

    Lucene工具类封装

package com.xushuai.lucene;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.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;import java.io.File;
import java.io.IOException;/*** Lucene工具类* Author: xushuai* Date: 2018/5/7* Time: 12:36* Description:*/
public class LuceneUtil {/*** 获取索引库写入流对象* &＃64;auther: xushuai* &＃64;date: 2018/5/7 12:37* &＃64;return: 写入流对象* &＃64;throws: IOException*/public static IndexWriter getIndexWriter(String pathname, Analyzer analyzer) throws IOException {//存放索引库的路径Directory directory &＃61; FSDirectory.open(new File(pathname));//创建分析器(使用其子类&＃xff0c;标准分析器类)IndexWriterConfig indexWriterConfig &＃61; new IndexWriterConfig(Version.LATEST, analyzer);//使用索引库路径和分析器构造索引库写入流return new IndexWriter(directory,indexWriterConfig);}/*** 获取索引库读取流* &＃64;auther: xushuai* &＃64;date: 2018/5/7 12:45* &＃64;return: 读取流对象* &＃64;throws: IOException*/public static IndexReader getIndexReader(String pathname) throws IOException {//指定索引库位置Directory directory &＃61; FSDirectory.open(new File(pathname));//创建索引库读取流return DirectoryReader.open(directory);}/*** 打印结果集到控制台* &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:23* &＃64;throws: IOException*/public static void printResult(IndexSearcher indexSearcher, Query query, int count) throws IOException {//执行查询,第一个参数为&＃xff1a;查询条件 第二个参数为&＃xff1a;结果返回最大个数TopDocs topDocs &＃61; indexSearcher.search(query, count);//打印结果集长度System.out.println("查询结果总条数&＃xff1a;" &＃43; topDocs.totalHits);//遍历结果集for (ScoreDoc doc:topDocs.scoreDocs) {//获取其查询到的文档对象,ScoreDoc对象的doc属性可以获取document的id值Document document &＃61; indexSearcher.doc(doc.doc);//打印文件名System.out.println("文件名&＃xff1a; " &＃43; document.get("filename"));//打印文件大小System.out.println("文件大小&＃xff1a;" &＃43; document.get("filesize"));//打印文件路径System.out.println("文件路径&＃xff1a;" &＃43; document.get("filepath"));//分割线System.out.println("------------------------------------------------------------------------------");}}
}


一、索引库的修改和删除

package com.xushuai.lucene;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.Term;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;import java.io.IOException;/*** 索引库维护* Author: xushuai* Date: 2018/5/7* Time: 12:47* Description:对索引库的维护主要分为&＃xff1a;增删改查(CRUD)&＃xff0c;其中新增即为创建索引库&＃xff0c;查询内容较多&＃xff0c;单独为一个分支。*/
public class LuceneManager {private IndexWriter indexWriter &＃61; null;/*** 加载写入流* &＃64;auther: xushuai* &＃64;date: 2018/5/7 17:21* &＃64;throws: IOException*/&＃64;Beforepublic void setUp() throws IOException {//注意&＃xff1a;IKAnalyzer为第三方分析器&＃xff0c;需要单独导包indexWriter &＃61; LuceneUtil.getIndexWriter("D:\\lucene-solr\\lucene\\index", new IKAnalyzer());}/*** 释放资源* &＃64;auther: xushuai* &＃64;date: 2018/5/7 17:21* &＃64;throws: IOException*/&＃64;Afterpublic void tearDown() throws IOException {indexWriter.close();}/*** Lucene索引修改过程&＃xff1a;先删除&＃xff0c;再添加* &＃64;auther: xushuai* &＃64;date: 2018/5/7 12:56* &＃64;throws: IOException*/&＃64;Testpublic void luceneUpdateRepository() throws IOException {//创建Document对象Document document &＃61; new Document();//添加域document.add(new TextField("fname","修改后的文件名", Field.Store.YES));document.add(new TextField("fcontent","修改后的文件内容",Field.Store.YES));//修改,其中第一个参数&＃xff1a;为一个Term&＃xff0c;会根据该Term去匹配要修改的文档对象indexWriter.updateDocument(new Term("filename","java"),document);}/*** 删除索引* &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:00* &＃64;throws: IOException*/&＃64;Testpublic void luceneDeleteRepository() throws IOException{//第一种删除&＃xff1a;删除索引库全部内容indexWriter.deleteAll();//第二种删除&＃xff1a;删除指定索引。过程&＃xff1a;先查询&＃xff0c;后删除//新建一个查询条件,例如&＃xff1a;删除 "filename" 域的值中含有 "java" 的Query query &＃61; new TermQuery(new Term("filename","java"));//根据条件进行删除(参数为&＃xff1a;Query可变数组&＃xff0c;可以为多个条件&＃xff0c;即组合条件删除)indexWriter.deleteDocuments(query);}}


二、查询索引&＃xff08;Query子类&＃xff09;

package com.xushuai.lucene;import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.*;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;import java.io.IOException;/*** Lucene索引查询* Author: xushuai* Date: 2018/5/7* Time: 13:19* Description:*/
public class LuceneQuery {private IndexSearcher indexSearcher &＃61; null;/*** 准备工作* &＃64;auther: xushuai* &＃64;date: 2018/5/7 17:27* &＃64;throws: IOException*/&＃64;Beforepublic void setUp() throws IOException {IndexReader indexReader &＃61; LuceneUtil.getIndexReader("D:\\lucene-solr\\lucene\\index");indexSearcher &＃61; new IndexSearcher(indexReader);}/*** 释放资源* &＃64;auther: xushuai* &＃64;date: 2018/5/7 17:27* &＃64;throws: IOException*/&＃64;Afterpublic void tearDown() throws IOException {indexSearcher.getIndexReader().close();}/*** 查询索引目录中的所有文档* &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:22* &＃64;return: * &＃64;throws: */&＃64;Testpublic void luceneMatchAllDocsQuery() throws IOException {//创建查询条件对象&＃xff0c;MatchAllDocsQuery&＃xff1a;查询全部文档对象Query query &＃61; new MatchAllDocsQuery();//打印查询结果集(最后一个参数为&＃xff1a;打印查询出来的结果集中的前10条)LuceneUtil.printResult(indexSearcher,query,10);}/*** 精准查询* &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:32* &＃64;return:* &＃64;throws:*/&＃64;Testpublic void luceneTermQuery() throws IOException {//创建查询条件对象&＃xff0c;TermQuery:精准查询&＃xff0c;按Term查询。例如&＃xff1a; 查询 filename 域的值为 java的文档对象Query query &＃61; new TermQuery(new Term("filename","java"));//打印查询结果集(最后一个参数为&＃xff1a;打印查询出来的结果集中的前10条)LuceneUtil.printResult(indexSearcher,query,10);}/*** * &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:34* &＃64;return: * &＃64;throws: */&＃64;Testpublic void luceneNumericRangeQuery() throws IOException {//创建查询条件对象/** newLongRange参数&＃xff1a;* 1、域名称* 2、最小值* 3、最大值* 4、是否包含最小值&＃xff1a;boolean* 5、是否包含最大值&＃xff1a;boolean*/Query query &＃61; NumericRangeQuery.newLongRange("filesize",50L,200L,true,true);//打印查询结果集(最后一个参数为&＃xff1a;打印查询出来的结果集中的前10条)LuceneUtil.printResult(indexSearcher,query,10);}/*** 条件组合查询* &＃64;auther: xushuai* &＃64;date: 2018/5/7 13:38* &＃64;throws: IOException*/&＃64;Testpublic void luceneBooleanQuery() throws IOException{//创建查询对象BooleanQuery booleanQuery &＃61; new BooleanQuery();//创建查询条件Query query1 &＃61; new TermQuery(new Term("filename","java"));Query query2 &＃61; new TermQuery(new Term("filename","apache"));//设置其两个条件的关系/** BooleanClause.Occur.MUST&＃xff1a;必须&＃xff0c;即该条件必须成立* BooleanClause.Occur.MUST_NOT&＃xff1a;必须不&＃xff0c;即该条件必须不成立* BooleanClause.Occur.SHOULD&＃xff1a;应该&＃xff0c;即该条件可以成立也可以不成立&＃xff0c;与OR类似\** 下面这个组合条件翻译为&＃xff1a;搜索文件名称中含有java或apache的文档对象*/booleanQuery.add(query1, BooleanClause.Occur.SHOULD);booleanQuery.add(query2, BooleanClause.Occur.SHOULD);//打印查询结果集(最后一个参数为&＃xff1a;打印查询出来的结果集中的前10条)LuceneUtil.printResult(indexSearcher,booleanQuery,10);}}