Lucene 全文检索引擎工具包的使用

Lucene 全文检索引擎的使用：

• 导入依赖jar包：

<?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>cn.mesmile</groupId>
    <artifactId>hello-lucene</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <!--Lucene版本控制-->
        <lucene-version>5.5.0</lucene-version>
    </properties>

    <dependencies>
        <!--测试依赖包-->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.lucene/lucene-core -->
        <!--Lucene核心包-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>${lucene-version}</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.lucene/lucene-analyzers-common -->
        <!--分词器依赖包-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>${lucene-version}</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.lucene/lucene-queryparser -->
        <!--查询解析器依赖包-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>${lucene-version}</version>
        </dependency>

    </dependencies>
</project>

测试Lucene步骤：

• 一、创建索引
  步骤：
  1、 把文本内容转换为Document对象
  文本是作为Document对象的一个字段而存在
  2、准备IndexWriter（索引写入器）
  3 、通过IndexWriter，把Document添加到缓冲区并提交
  addDocument
  commit
  close

• 二、搜索索引
  步骤：
  1 封装查询提交为查询对象
  2 准备IndexSearcher
  3 使用IndexSearcher传入查询对象做查询-----查询出来只是文档编号DocID
  4 通过IndexSearcher传入DocID获取文档
  5 把文档转换为前台需要的对象 Docment----> Article

• 测试代码 :

package cn.mesmile;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
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.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 java.nio.file.Paths;

/**
 * @Created with IDEA
 * @author: Super Zheng
 * @Description: Lucene测试
 * @Date:2018/12/23
 * @Time:12:14
 */
public class TestLucene {

    // 本地存储路径
    private final static String  PATH=\"D:\\\\javaEE\\\\crms-project\\\\hello-lucene\\\\lucene_repository\\\\hello\";

    /**
     * 1.测试创建索引
     * @throws Exception
     */
    @Test
    public void testCreate () throws Exception{
        // 准备的存入本地数据
        String str1= \"hello world\";
        String str2= \"hello java\";
        String str3= \"hello lucene java\";
        // 索引库的位置 FS fileSystem
        Directory d = FSDirectory.open(Paths.get(PATH ));
        // 分词器，注意这个分词器只能用于 分英文，若需分中文，请用导入包 Lucene-smartcn  然后用SmartChineseAnalyzer()替换SimpleAnalyzer()
        Analyzer analyzer = new SimpleAnalyzer();
        // 索引写入器的配置对象
        IndexWriterConfig conf = new IndexWriterConfig(analyzer);
        IndexWriter indexWriter = new IndexWriter(d, conf);

        // 将文本内容装换成Document
        Document document1 = new Document();
        document1.add(new TextField(\"title\",\"str1\", Field.Store.YES));
        document1.add(new TextField(\"context\",str1, Field.Store.YES));
        // 将文本内容装换成Document
        Document document2 = new Document();
        document2.add(new TextField(\"title\",\"str2\", Field.Store.YES));
        document2.add(new TextField(\"context\",str2, Field.Store.YES));
        // 将文本内容装换成Document
        Document document3 = new Document();
        document3.add(new TextField(\"title\",\"str3\", Field.Store.YES));
        document3.add(new TextField(\"context\",str3, Field.Store.YES));

        // 添加到缓存区
        indexWriter.addDocument(document1);
        indexWriter.addDocument(document2);
        indexWriter.addDocument(document3);

        // 提交
        indexWriter.commit();
        // 关闭
        indexWriter.close();

    }

    /**
     * 2.测试通过索引搜索
     * @throws Exception
     */
    @Test
    public void testSearch () throws Exception{
        // 测试查询的关键字
        String keyWord = \"java\";

        // 查询默认字段名
        String f = \"context\";

        // 查询所有关键词，分词器
        Analyzer a =  new SimpleAnalyzer();

        QueryParser parser = new QueryParser(f, a);
        // 获得查询条件             列名+查询的关键字
        Query query = parser.parse(\"context:\" + keyWord);

        // 准备IndexSearch
        Directory  directory = FSDirectory.open(Paths.get(PATH));

        IndexReader indexReader = DirectoryReader.open(directory);

        IndexSearcher searcher = new IndexSearcher(indexReader);

        // 查询记录的条数
        int n = 10;

        TopDocs topDocs =searcher.search(query, n);
        // 命中所有的文档封装
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;

        for (ScoreDoc scoreDoc : scoreDocs) {
            // 索引的下标，从0开始
            int doc = scoreDoc.doc;
            // 将查询的数据封装成document
            Document document = searcher.doc(doc);
            // 打印输出查询结果
            System.out.println(\"title:\"+document.get(\"title\")+\"  context:\"+document.get(\"context\"));
        }
    }
}

测试查询结果：