lucene-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_43164399/article/details/102785211

倒排索引

Lucene是一套用于全文检索和搜寻的开源程序库，由Apache软件基金会支持和提供

Lucene提供了一个简单却强大的应用程序接口（API），能够做全文索引和搜寻，在Java开发环境里Lucene是一个成熟的免费开放源代码工具

Lucene并不是现成的搜索引擎产品，但可以用来制作搜索引擎产品

官网：http://lucene.apache.org/

Lucene、Solr、Elasticsearch关系
Lucene：底层的API，工具包

Solr：基于Lucene开发的企业级的搜索引擎产品

Elasticsearch：基于Lucene开发的企业级的搜索引擎产品

Lucene的基本使用
使用Lucene的API来实现对索引的增（创建索引）、删（删除索引）、改（修改索引）、查（搜索数据）。

创建索引
创建索引的流程

文档Document：数据库中一条具体的记录

字段Field：数据库中的每个字段

目录对象Directory：物理存储位置

写出器的配置对象：需要分词器和lucene的版本
添加依赖：

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.zpark</groupId>
    <artifactId>luncene</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <lunece.version>4.10.2</lunece.version>

    </properties>
    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <!-- lucene核心库 -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>${lunece.version}</version>
        </dependency>
        <!-- Lucene的查询解析器 -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>${lunece.version}</version>
        </dependency>
        <!-- lucene的默认分词器库 -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>${lunece.version}</version>
        </dependency>
        <!-- lucene的高亮显示 -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-highlighter</artifactId>
            <version>${lunece.version}</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/com.janeluo/ikanalyzer -->
        <dependency>
            <groupId>com.janeluo</groupId>
            <artifactId>ikanalyzer</artifactId>
            <version>2012_u6</version>
        </dependency>

    </dependencies>

</project>

//1 创建文档对象
//2 创建存储目录
//3 创建分词器
//4 创建索引写入器的配置对象
//5 创建索引写入器对象
//6 将文档交给索引写入器
//7 提交
//8 关闭
只有一条文档的文件，创建多条文档的文件，以及查询`


```java
import jdk.nashorn.internal.ir.CallNode;
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.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.jcp.xml.dsig.internal.dom.DOMCanonicalizationMethod;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;


public class TestLuncene {
    @Test
    public void testCreate(){
        {
            try {
                Document document = new Document();
                document.add(new StringField("id","1", Field.Store.YES));
                document.add(new TextField("title","谷歌地图之父跳槽facebook",Field.Store.YES));
                Directory directory = FSDirectory.open(new File("d:\\lunceneata"));
                IKAnalyzer analyzer = new IKAnalyzer();
                IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LATEST,analyzer);
                indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
                IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig);
                indexWriter.addDocument(document);
                indexWriter.commit();
                indexWriter.close();


            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
    @Test
    public void testCreate2(){
        try {
        ArrayList<Document> list = new ArrayList<Document>();

        Document document = new Document();
        document.add(new StringField("id","1", Field.Store.YES));
        document.add(new TextField("title","谷歌地图之父跳槽facebook", Field.Store.YES));
        list.add(document);

        Document document1 = new Document();
        document1.add(new StringField("id","2", Field.Store.YES));
        document1.add(new TextField("title","谷歌地图之父加盟FaceBook", Field.Store.YES));
        list.add(document1);

        Document document2 = new Document();
        document2.add(new StringField("id","3", Field.Store.YES));
        document2.add(new TextField("title","谷歌地图创始人拉斯离开谷歌加盟Facebook", Field.Store.YES));
        list.add(document2);

        Document document3 = new Document();
        document3.add(new StringField("id","4", Field.Store.YES));
        document3.add(new TextField("title","谷歌地图之父跳槽Facebook与Wave项目取消有关", Field.Store.YES));
        list.add(document3);

        Document document4 = new Document();
        document4.add(new StringField("id","5", Field.Store.YES));
        document4.add(new TextField("title","谷歌地图之父拉斯加盟社交网站Facebook", Field.Store.YES));
        list.add(document4);

            FSDirectory directory = FSDirectory.open(new File("d:\\lunceneata"));
            IndexWriterConfig conf = new IndexWriterConfig(Version.LATEST,  new IKAnalyzer());
            conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
            IndexWriter indexWriter = new IndexWriter(directory,conf);
            indexWriter.addDocuments(list);
            indexWriter.commit();
            indexWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
        }


    }
    @Test
    public void testSercher(){
        try {
            FSDirectory directory = FSDirectory.open(new File("d:\\lunceneata"));
            DirectoryReader directoryReader = DirectoryReader.open(directory);
            IndexSearcher indexSearcher = new IndexSearcher(directoryReader);
            QueryParser parser = new QueryParser("title", new IKAnalyzer());
            Query query = parser.parse("谷歌");
            TopDocs topDocs = indexSearcher.search(query, 10);
            System.out.println("本次共搜索到" + topDocs.totalHits+"条数据");
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (ScoreDoc scoreDoc :scoreDocs){
                int docid = scoreDoc.doc;
                Document doc = directoryReader.document(docid);
                System.out.println("id:" + doc.get("id"));
                System.out.println("title" + doc.get("title"));
                System.out.println("得分" + scoreDoc.score);

            }


        } catch (IOException e) {
            e.printStackTrace();
        }catch (Exception e)
        {
            e.printStackTrace();
        }

    }
        }

https://blog.youkuaiyun.com/weixin_42633131/article/details/82873731