Lucene

向右看齐 2023-06-10 16:20 256阅读 0赞

## 什么是Lucene ##

*  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/

## 用idea写代码 ##

1.  创建maven项目(new—project----maven)
2.  添加依赖（pom.xml）  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70]

<properties>
            <lunece.version>4.10.2</lunece.version>
        </properties>
    
        <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-core</artifactId>
                <version>${lunece.version}</version>
        </dependency>
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-queryparser</artifactId>
                <version>${lunece.version}</version>
            </dependency>
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-analyzers-common</artifactId>
                <version>${lunece.version}</version>
            </dependency>
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-highlighter</artifactId>
                <version>${lunece.version}</version>
            </dependency>
    
    
    </dependencies>

3.在idea下的这个文件里新建class  
![在这里插入图片描述][2019102818092670.png]

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.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.FSDirectory;
    import org.apache.lucene.util.Version;
    import org.junit.Test;
    
    import java.io.File;
    
    public class lucencetest { 
    //创建索引
        @Test
        public void testCreate() throws Exception{ 
          //1、创建文档对象
            Document document =new Document();
            // 创建并添加字段信息。参数：字段的名称、字段的值、是否存储，这里选Store.YES代表存储到文档列表。Store.NO代表不存储
    
            document.add(new StringField("id", "1", Field.Store.YES));
            // 这里我们title字段需要用TextField，即创建索引又会被分词。StringField会创建索引，但是不会被分词
            document.add(new TextField("title","谷歌地图之父跳槽facebook", Field.Store.YES));
            //2 索引目录类,指定索引在硬盘中的位置
            Directory directory = FSDirectory.open(new File("d:\\indexDir"));
            //3 创建分词器对象
            Analyzer analyzer = new StandardAnalyzer();
            //4 索引写出工具的配置对象
            IndexWriterConfig conf = new IndexWriterConfig(Version.LATEST, analyzer);
            //5 创建索引的写出工具类。参数：索引的目录和配置信息
            IndexWriter indexWriter = new IndexWriter(directory, conf);
    
            //6 把文档交给IndexWriter
            indexWriter.addDocument(document);
            //7 提交
            indexWriter.commit();
            //8 关闭
            indexWriter.close();
    
        }
    }

点击运行  
![在这里插入图片描述][20191028181139378.png]

查看d盘下，是否有你所创建的文件夹  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70 1]  
也可以创建多条文档的文件  
现在pom.xml添加  
` <dependency> <groupId>com.janeluo</groupId> <artifactId>ikanalyzer</artifactId> <version>2012_u6</version> </dependency>`依赖

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.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.store.FSDirectory;
    import org.apache.lucene.util.Version;
    import org.junit.Test;
    import org.wltea.analyzer.lucene.IKAnalyzer;
    
    import java.io.File;
    import java.util.ArrayList;
    
    public class lucencebb { 
        @Test
        public void testCreate2() { 
            try { 
                ArrayList<Document> documents = 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));
                documents.add(document);
    
                Document document2 = new Document();
                document2.add(new StringField("id","2",Field.Store.YES));
                document2.add(new TextField("title","谷歌地图之父加盟FaceBook",Field.Store.YES));
                documents.add(document2);
    
                Document document3 = new Document();
                document3.add(new StringField("id","3",Field.Store.YES));
                document3.add(new TextField("title","谷歌地图创始人拉斯离开谷歌加盟Facebook",Field.Store.YES));
                documents.add(document3);
    
                Document document4 = new Document();
                document4.add(new StringField("id","4",Field.Store.YES));
                document4.add(new TextField("title","谷歌地图之父跳槽Facebook与Wave项目取消有关",Field.Store.YES));
                documents.add(document4);
    
                Document document5 = new Document();
                document5.add(new StringField("id","5",Field.Store.YES));
                document5.add(new TextField("title","谷歌地图之父拉斯加盟社交网站Facebook",Field.Store.YES));
                documents.add(document5);
    
                FSDirectory dir = FSDirectory.open(new File("d:/lucenedata"));
    
                IndexWriterConfig conf = new IndexWriterConfig(Version.LATEST, new IKAnalyzer());
                conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
                IndexWriter indexWriter = new IndexWriter(dir, conf);
    
                indexWriter.addDocuments(documents);
                indexWriter.commit();
                indexWriter.close();
    
            } catch (Exception e) { 
                e.printStackTrace();
            }
        }
    
    }

同样运行，查看  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70 2]  
4.运行查询代码

import org.apache.lucene.document.Document;
    import org.apache.lucene.index.DirectoryReader;
    import org.apache.lucene.index.IndexReader;
    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.junit.Test;
    import org.wltea.analyzer.lucene.IKAnalyzer;
    
    import java.io.File;
    
    public class tabletest { 
        @Test
        public void testSearch() throws Exception { 
            // 索引目录对象
            Directory directory = FSDirectory.open(new File("d:\\lucenedata"));
            // 索引读取工具
            IndexReader reader = DirectoryReader.open(directory);
            // 索引搜索工具
            IndexSearcher searcher = new IndexSearcher(reader);
    
            // 创建查询解析器,两个参数：默认要查询的字段的名称，分词器
            QueryParser parser = new QueryParser("title", new IKAnalyzer());
            // 创建查询对象
            Query query = parser.parse("谷歌");
    
            // 搜索数据,两个参数：查询条件对象要查询的最大结果条数
            // 返回的结果是 按照匹配度排名得分前N名的文档信息（包含查询到的总条数信息、所有符合条件的文档的编号信息）。
            TopDocs topDocs = searcher.search(query, 10);
            // 获取总条数
            System.out.println("本次搜索共找到" + topDocs.totalHits + "条数据");
            // 获取得分文档对象（ScoreDoc）数组.SocreDoc中包含：文档的编号、文档的得分
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (ScoreDoc scoreDoc : scoreDocs) { 
                // 取出文档编号
                int docID = scoreDoc.doc;
                // 根据编号去找文档
                Document doc = reader.document(docID);
                System.out.println("id: " + doc.get("id"));
                System.out.println("title: " + doc.get("title"));
                // 取出文档得分
                System.out.println("得分： " + scoreDoc.score);
            }
        }
    
    }

查询结果：

"C:\Program Files\Java\jdk1.8.0_144\bin\java.exe" -ea -Didea.test.cyclic.buffer.size=1048576 "-javaagent:F:\idea2019\IntelliJ IDEA 2019.1.3\lib\idea_rt.jar=52601:F:\idea2019\IntelliJ IDEA 2019.1.3\bin" -Dfile.encoding=UTF-8 -classpath "F:\idea2019\IntelliJ IDEA 2019.1.3\lib\idea_rt.jar;F:\idea2019\IntelliJ IDEA 2019.1.3\plugins\junit\lib\junit-rt.jar;F:\idea2019\IntelliJ IDEA 2019.1.3\plugins\junit\lib\junit5-rt.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\charsets.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\deploy.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\access-bridge-64.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\cldrdata.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\dnsns.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\jaccess.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\jfxrt.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\localedata.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\nashorn.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\sunec.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\sunjce_provider.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\sunmscapi.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\sunpkcs11.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\ext\zipfs.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\javaws.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\jce.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\jfr.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\jfxswt.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\jsse.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\management-agent.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\plugin.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\resources.jar;C:\Program Files\Java\jdk1.8.0_144\jre\lib\rt.jar;F:\idea2019\Luceneaa\target\test-classes;C:\Users\ABU\.m2\repository\junit\junit\4.12\junit-4.12.jar;C:\Users\ABU\.m2\repository\org\hamcrest\hamcrest-core\1.3\hamcrest-core-1.3.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-core\4.10.2\lucene-core-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-queryparser\4.10.2\lucene-queryparser-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-queries\4.10.2\lucene-queries-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-sandbox\4.10.2\lucene-sandbox-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-analyzers-common\4.10.2\lucene-analyzers-common-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-highlighter\4.10.2\lucene-highlighter-4.10.2.jar;C:\Users\ABU\.m2\repository\org\apache\lucene\lucene-memory\4.10.2\lucene-memory-4.10.2.jar;C:\Users\ABU\.m2\repository\com\janeluo\ikanalyzer\2012_u6\ikanalyzer-2012_u6.jar" com.intellij.rt.execution.junit.JUnitStarter -ideVersion5 -junit4 tabletest,testSearch
    本次搜索共找到5条数据
    id: 1
    title: 谷歌地图之父跳槽facebook
    得分： 0.35773432
    id: 2
    title: 谷歌地图之父加盟FaceBook
    得分： 0.35773432
    id: 3
    title: 谷歌地图创始人拉斯离开谷歌加盟Facebook
    得分： 0.289093
    id: 5
    title: 谷歌地图之父拉斯加盟社交网站Facebook
    得分： 0.25552452
    id: 4
    title: 谷歌地图之父跳槽Facebook与Wave项目取消有关
    得分： 0.20441961
    
    Process finished with exit code 0

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70]: /images/20230531/464abcc593184ffa8cbf4a0cb0fe895e.png
[2019102818092670.png]: /images/20230531/d3d28806cf714fb09fba8aeac7f2ce53.png
[20191028181139378.png]: /images/20230531/f6721765146f4989b28ec37d49fca244.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70 1]: /images/20230531/778619b149ee4f92b369a40d2b52ace4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0FCVV9NT2xJX0lUVUk_size_16_color_FFFFFF_t_70 2]: /images/20230531/4aceff137d294439a76c9f02b533bfab.png