Lucene学习笔记：基础

Lucence是Apache的一个全文检索引擎工具包。可以将采集的数据存储到索引库中，然后在根据查询条件从索引库中取出结果。索引库可以存在内存中或者存在硬盘上。

本文主要是参考了这篇博客进行学习的，原博客地址https://blog.csdn.net/bskfnvjtlyzmv867/article/details/80914156

主要开发流程是：采集数据，将数据转化成索引文档，然后存储在索引库中，索引库可以保存在内存中，或者保存在硬盘上。在查询的时候通过索引库查询结果，返回数据。

下面的例子主要是将Product表中的数据存储到索引库中，并通过索引库进行查询。项目依赖的jar包可以参考原博客，我用的Lucence版本是4.7。

新建实体类Product，其代码如下：

public class Product {
    private Long id;
    private String title;
    private String sellPoint;
}

将Product实体转化成索引库中Document，并存到索引库中。Product数据可以从数据库中查询，然后通过此方法转化成索引库中的Document，此处省略从数据库查询Product的逻辑。

import java.io.IOException;
import java.nio.file.Path;
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.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 entity.Product;

public class ProductRepository {

    public void createIndex(Product product) {
        Field id = new StringField("id", product.getId().toString(), Field.Store.YES);
        Field title = new TextField("title", product.getTitle().toString(), Field.Store.YES);
        Field sellPoint = new TextField("sellPoint", product.getSellPoint().toString(), Field.Store.YES);

        Document document = new Document();
        document.add(id);
        document.add(title);
        document.add(sellPoint);
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_47, analyzer);
　　　　　
        Path path = Paths.get("D:/develop/workspace/slem_compass/data");
        try {
            Directory directory = FSDirectory.open(path.toFile());
            IndexWriter indexWriter = new IndexWriter(directory, config);
            indexWriter.addDocument(document);
            indexWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}

其中上面的代码中Path是索引库在硬盘上的位置，我这里是放在D盘上的某个文件夹内。

下面如何从索引库中查询数据呢？我写了一个Servlet，用户提交查询关键字，request获取到后，根据关键字从索引库中查询数据。当然也可以用Main方法或者test测试类。

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

import javax.servlet.ServletException;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

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.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;

@WebServlet("/search")
public class SearchServlet extends HttpServlet {
    private static final long serialVersionUID = 1L;

    public SearchServlet() {
        super();
    }

    protected void doGet(HttpServletRequest request, HttpServletResponse response)
            throws ServletException, IOException {
        request.setCharacterEncoding("utf-8");
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
        QueryParser parser = new QueryParser(Version.LUCENE_47, "title", analyzer);
        String title = request.getParameter("title");
        System.out.println("");
        System.out.println("title: " + title);
        try {
            Query query = parser.parse(title);
            Path path = Paths.get("D:/develop/workspace/slem_compass/data");
            Directory directory = FSDirectory.open(path.toFile());
            IndexReader reader = DirectoryReader.open(directory);
            IndexSearcher indexSearcher = new IndexSearcher(reader);

            TopDocs topDocs = indexSearcher.search(query, 10);
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;

            for (ScoreDoc scoreDoc : scoreDocs) {
                int docID = scoreDoc.doc;

                Document doc = indexSearcher.doc(docID);
                System.out.println(doc.get("id") + " " + doc.get("title") + " " + doc.get("sellPoint"));
            }
            System.out.println("");
            reader.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        response.setContentType("text/html;charset=utf-8");
        response.getWriter().append("Served at: ").append(request.getContextPath());
    }

    protected void doPost(HttpServletRequest request, HttpServletResponse response)
            throws ServletException, IOException {
        doGet(request, response);
    }

}

查询的时候也是从D盘上的索引库中读取相应的信息，然后根据关键字进行查询。

这样就完成了索引库的存储和查询。索引的查询很复杂，上面的demo只是一个比较简单的例子，说明大致的原理，后面继续补充索引的查询。